Merge tag 'pmdomain-v6.15-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/linux-pm
Pull pmdomain fixes from Ulf Hansson:
"Core:
- Fix error checking in genpd_dev_pm_attach_by_id()
Providers:
- renesas: Remove obsolete nullify checks for rcar domains"
* tag 'pmdomain-v6.15-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/linux-pm:
pmdomain: core: Fix error checking in genpd_dev_pm_attach_by_id()
pmdomain: renesas: rcar: Remove obsolete nullify checks
diff --git a/.clippy.toml b/.clippy.toml
index 815c947..137f41d 100644
--- a/.clippy.toml
+++ b/.clippy.toml
@@ -7,5 +7,5 @@
disallowed-macros = [
# The `clippy::dbg_macro` lint only works with `std::dbg!`, thus we simulate
# it here, see: https://github.com/rust-lang/rust-clippy/issues/11303.
- { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool" },
+ { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool", allow-invalid = true },
]
diff --git a/.mailmap b/.mailmap
index 9afde79..9531546 100644
--- a/.mailmap
+++ b/.mailmap
@@ -102,6 +102,7 @@
Arnaud Patard <arnaud.patard@rtp-net.org>
Arnd Bergmann <arnd@arndb.de>
Arun Kumar Neelakantam <quic_aneela@quicinc.com> <aneela@codeaurora.org>
+Asahi Lina <lina+kernel@asahilina.net> <lina@asahilina.net>
Ashok Raj Nagarajan <quic_arnagara@quicinc.com> <arnagara@codeaurora.org>
Ashwin Chaugule <quic_ashwinc@quicinc.com> <ashwinc@codeaurora.org>
Asutosh Das <quic_asutoshd@quicinc.com> <asutoshd@codeaurora.org>
@@ -447,6 +448,8 @@
Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz>
Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
Luo Jie <quic_luoj@quicinc.com> <luoj@codeaurora.org>
+Lance Yang <lance.yang@linux.dev> <ioworker0@gmail.com>
+Lance Yang <lance.yang@linux.dev> <mingzhe.yang@ly.com>
Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org>
Maharaja Kennadyrajan <quic_mkenna@quicinc.com> <mkenna@codeaurora.org>
@@ -483,6 +486,7 @@
Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net>
Matthieu CASTET <castet.matthieu@free.fr>
Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
+Mattijs Korpershoek <mkorpershoek@kernel.org> <mkorpershoek@baylibre.com>
Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com>
Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting>
Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com>
@@ -749,6 +753,7 @@
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
+Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com>
Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Uwe Kleine-König <ukleinek@strlen.de>
Uwe Kleine-König <ukl@pengutronix.de>
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 206079d..6a1acab 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -511,6 +511,7 @@
What: /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/gather_data_sampling
+ /sys/devices/system/cpu/vulnerabilities/indirect_target_selection
/sys/devices/system/cpu/vulnerabilities/itlb_multihit
/sys/devices/system/cpu/vulnerabilities/l1tf
/sys/devices/system/cpu/vulnerabilities/mds
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd b/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd
index 2a19584..8c9718d 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd
+++ b/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd
@@ -1,6 +1,6 @@
What: /sys/bus/hid/drivers/hid-appletb-kbd/<dev>/mode
-Date: September, 2023
-KernelVersion: 6.5
+Date: March, 2025
+KernelVersion: 6.15
Contact: linux-input@vger.kernel.org
Description:
The set of keys displayed on the Touch Bar.
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
index 9bce281..cb207c7 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
@@ -111,7 +111,7 @@
What: /sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/temp2_input
Date: March 2025
-KernelVersion: 6.14
+KernelVersion: 6.15
Contact: intel-xe@lists.freedesktop.org
Description: RO. Package temperature in millidegree Celsius.
@@ -119,7 +119,7 @@
What: /sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/temp3_input
Date: March 2025
-KernelVersion: 6.14
+KernelVersion: 6.15
Contact: intel-xe@lists.freedesktop.org
Description: RO. VRAM temperature in millidegree Celsius.
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index 451874b..ce296b8 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -23,3 +23,4 @@
gather_data_sampling
reg-file-data-sampling
rsb
+ indirect-target-selection
diff --git a/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
new file mode 100644
index 0000000..d9ca641
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
@@ -0,0 +1,168 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Indirect Target Selection (ITS)
+===============================
+
+ITS is a vulnerability in some Intel CPUs that support Enhanced IBRS and were
+released before Alder Lake. ITS may allow an attacker to control the prediction
+of indirect branches and RETs located in the lower half of a cacheline.
+
+ITS is assigned CVE-2024-28956 with a CVSS score of 4.7 (Medium).
+
+Scope of Impact
+---------------
+- **eIBRS Guest/Host Isolation**: Indirect branches in KVM/kernel may still be
+ predicted with unintended target corresponding to a branch in the guest.
+
+- **Intra-Mode BTI**: In-kernel training such as through cBPF or other native
+ gadgets.
+
+- **Indirect Branch Prediction Barrier (IBPB)**: After an IBPB, indirect
+ branches may still be predicted with targets corresponding to direct branches
+ executed prior to the IBPB. This is fixed by the IPU 2025.1 microcode, which
+ should be available via distro updates. Alternatively microcode can be
+ obtained from Intel's github repository [#f1]_.
+
+Affected CPUs
+-------------
+Below is the list of ITS affected CPUs [#f2]_ [#f3]_:
+
+ ======================== ============ ==================== ===============
+ Common name Family_Model eIBRS Intra-mode BTI
+ Guest/Host Isolation
+ ======================== ============ ==================== ===============
+ SKYLAKE_X (step >= 6) 06_55H Affected Affected
+ ICELAKE_X 06_6AH Not affected Affected
+ ICELAKE_D 06_6CH Not affected Affected
+ ICELAKE_L 06_7EH Not affected Affected
+ TIGERLAKE_L 06_8CH Not affected Affected
+ TIGERLAKE 06_8DH Not affected Affected
+ KABYLAKE_L (step >= 12) 06_8EH Affected Affected
+ KABYLAKE (step >= 13) 06_9EH Affected Affected
+ COMETLAKE 06_A5H Affected Affected
+ COMETLAKE_L 06_A6H Affected Affected
+ ROCKETLAKE 06_A7H Not affected Affected
+ ======================== ============ ==================== ===============
+
+- All affected CPUs enumerate Enhanced IBRS feature.
+- IBPB isolation is affected on all ITS affected CPUs, and need a microcode
+ update for mitigation.
+- None of the affected CPUs enumerate BHI_CTRL which was introduced in Golden
+ Cove (Alder Lake and Sapphire Rapids). This can help guests to determine the
+ host's affected status.
+- Intel Atom CPUs are not affected by ITS.
+
+Mitigation
+----------
+As only the indirect branches and RETs that have their last byte of instruction
+in the lower half of the cacheline are vulnerable to ITS, the basic idea behind
+the mitigation is to not allow indirect branches in the lower half.
+
+This is achieved by relying on existing retpoline support in the kernel, and in
+compilers. ITS-vulnerable retpoline sites are runtime patched to point to newly
+added ITS-safe thunks. These safe thunks consists of indirect branch in the
+second half of the cacheline. Not all retpoline sites are patched to thunks, if
+a retpoline site is evaluated to be ITS-safe, it is replaced with an inline
+indirect branch.
+
+Dynamic thunks
+~~~~~~~~~~~~~~
+From a dynamically allocated pool of safe-thunks, each vulnerable site is
+replaced with a new thunk, such that they get a unique address. This could
+improve the branch prediction accuracy. Also, it is a defense-in-depth measure
+against aliasing.
+
+Note, for simplicity, indirect branches in eBPF programs are always replaced
+with a jump to a static thunk in __x86_indirect_its_thunk_array. If required,
+in future this can be changed to use dynamic thunks.
+
+All vulnerable RETs are replaced with a static thunk, they do not use dynamic
+thunks. This is because RETs get their prediction from RSB mostly that does not
+depend on source address. RETs that underflow RSB may benefit from dynamic
+thunks. But, RETs significantly outnumber indirect branches, and any benefit
+from a unique source address could be outweighed by the increased icache
+footprint and iTLB pressure.
+
+Retpoline
+~~~~~~~~~
+Retpoline sequence also mitigates ITS-unsafe indirect branches. For this
+reason, when retpoline is enabled, ITS mitigation only relocates the RETs to
+safe thunks. Unless user requested the RSB-stuffing mitigation.
+
+RSB Stuffing
+~~~~~~~~~~~~
+RSB-stuffing via Call Depth Tracking is a mitigation for Retbleed RSB-underflow
+attacks. And it also mitigates RETs that are vulnerable to ITS.
+
+Mitigation in guests
+^^^^^^^^^^^^^^^^^^^^
+All guests deploy ITS mitigation by default, irrespective of eIBRS enumeration
+and Family/Model of the guest. This is because eIBRS feature could be hidden
+from a guest. One exception to this is when a guest enumerates BHI_DIS_S, which
+indicates that the guest is running on an unaffected host.
+
+To prevent guests from unnecessarily deploying the mitigation on unaffected
+platforms, Intel has defined ITS_NO bit(62) in MSR IA32_ARCH_CAPABILITIES. When
+a guest sees this bit set, it should not enumerate the ITS bug. Note, this bit
+is not set by any hardware, but is **intended for VMMs to synthesize** it for
+guests as per the host's affected status.
+
+Mitigation options
+^^^^^^^^^^^^^^^^^^
+The ITS mitigation can be controlled using the "indirect_target_selection"
+kernel parameter. The available options are:
+
+ ======== ===================================================================
+ on (default) Deploy the "Aligned branch/return thunks" mitigation.
+ If spectre_v2 mitigation enables retpoline, aligned-thunks are only
+ deployed for the affected RET instructions. Retpoline mitigates
+ indirect branches.
+
+ off Disable ITS mitigation.
+
+ vmexit Equivalent to "=on" if the CPU is affected by guest/host isolation
+ part of ITS. Otherwise, mitigation is not deployed. This option is
+ useful when host userspace is not in the threat model, and only
+ attacks from guest to host are considered.
+
+ stuff Deploy RSB-fill mitigation when retpoline is also deployed.
+ Otherwise, deploy the default mitigation. When retpoline mitigation
+ is enabled, RSB-stuffing via Call-Depth-Tracking also mitigates
+ ITS.
+
+ force Force the ITS bug and deploy the default mitigation.
+ ======== ===================================================================
+
+Sysfs reporting
+---------------
+
+The sysfs file showing ITS mitigation status is:
+
+ /sys/devices/system/cpu/vulnerabilities/indirect_target_selection
+
+Note, microcode mitigation status is not reported in this file.
+
+The possible values in this file are:
+
+.. list-table::
+
+ * - Not affected
+ - The processor is not vulnerable.
+ * - Vulnerable
+ - System is vulnerable and no mitigation has been applied.
+ * - Vulnerable, KVM: Not affected
+ - System is vulnerable to intra-mode BTI, but not affected by eIBRS
+ guest/host isolation.
+ * - Mitigation: Aligned branch/return thunks
+ - The mitigation is enabled, affected indirect branches and RETs are
+ relocated to safe thunks.
+ * - Mitigation: Retpolines, Stuffing RSB
+ - The mitigation is enabled using retpoline and RSB stuffing.
+
+References
+----------
+.. [#f1] Microcode repository - https://github.com/intel/Intel-Linux-Processor-Microcode-Data-Files
+
+.. [#f2] Affected Processors list - https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html
+
+.. [#f3] Affected Processors list (machine readable) - https://github.com/intel/Intel-affected-processor-list
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d9fd26b..8f75ec17 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2202,6 +2202,23 @@
different crypto accelerators. This option can be used
to achieve best performance for particular HW.
+ indirect_target_selection= [X86,Intel] Mitigation control for Indirect
+ Target Selection(ITS) bug in Intel CPUs. Updated
+ microcode is also required for a fix in IBPB.
+
+ on: Enable mitigation (default).
+ off: Disable mitigation.
+ force: Force the ITS bug and deploy default
+ mitigation.
+ vmexit: Only deploy mitigation if CPU is affected by
+ guest/host isolation part of ITS.
+ stuff: Deploy RSB-fill mitigation when retpoline is
+ also deployed. Otherwise, deploy the default
+ mitigation.
+
+ For details see:
+ Documentation/admin-guide/hw-vuln/indirect-target-selection.rst
+
init= [KNL]
Format: <full_path>
Run specified binary instead of /sbin/init as init
@@ -3693,6 +3710,7 @@
expose users to several CPU vulnerabilities.
Equivalent to: if nokaslr then kpti=0 [ARM64]
gather_data_sampling=off [X86]
+ indirect_target_selection=off [X86]
kvm.nx_huge_pages=off [X86]
l1tf=off [X86]
mds=off [X86]
diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst
index 3e76276..5becb44 100644
--- a/Documentation/admin-guide/xfs.rst
+++ b/Documentation/admin-guide/xfs.rst
@@ -562,7 +562,7 @@
Zoned Filesystems
=================
-For zoned file systems, the following attribute is exposed in:
+For zoned file systems, the following attributes are exposed in:
/sys/fs/xfs/<dev>/zoned/
@@ -572,23 +572,10 @@
is limited by the capabilities of the backing zoned device, file system
size and the max_open_zones mount option.
-Zoned Filesystems
-=================
-
-For zoned file systems, the following attributes are exposed in:
-
- /sys/fs/xfs/<dev>/zoned/
-
- max_open_zones (Min: 1 Default: Varies Max: UINTMAX)
- This read-only attribute exposes the maximum number of open zones
- available for data placement. The value is determined at mount time and
- is limited by the capabilities of the backing zoned device, file system
- size and the max_open_zones mount option.
-
- zonegc_low_space (Min: 0 Default: 0 Max: 100)
- Define a percentage for how much of the unused space that GC should keep
- available for writing. A high value will reclaim more of the space
- occupied by unused blocks, creating a larger buffer against write
- bursts at the cost of increased write amplification. Regardless
- of this value, garbage collection will always aim to free a minimum
- amount of blocks to keep max_open_zones open for data placement purposes.
+ zonegc_low_space (Min: 0 Default: 0 Max: 100)
+ Define a percentage for how much of the unused space that GC should keep
+ available for writing. A high value will reclaim more of the space
+ occupied by unused blocks, creating a larger buffer against write
+ bursts at the cost of increased write amplification. Regardless
+ of this value, garbage collection will always aim to free a minimum
+ amount of blocks to keep max_open_zones open for data placement purposes.
diff --git a/Documentation/arch/openrisc/openrisc_port.rst b/Documentation/arch/openrisc/openrisc_port.rst
index 1565b95..a8f307a 100644
--- a/Documentation/arch/openrisc/openrisc_port.rst
+++ b/Documentation/arch/openrisc/openrisc_port.rst
@@ -7,10 +7,10 @@
For information about OpenRISC processors and ongoing development:
- ======= =============================
+ ======= ==============================
website https://openrisc.io
- email openrisc@lists.librecores.org
- ======= =============================
+ email linux-openrisc@vger.kernel.org
+ ======= ==============================
---------------------------------------------------------------------
@@ -27,11 +27,11 @@
Instructions for building the different toolchains can be found on openrisc.io
or Stafford's toolchain build and release scripts.
- ========== =================================================
- binaries https://github.com/openrisc/or1k-gcc/releases
+ ========== ==========================================================
+ binaries https://github.com/stffrdhrn/or1k-toolchain-build/releases
toolchains https://openrisc.io/software
building https://github.com/stffrdhrn/or1k-toolchain-build
- ========== =================================================
+ ========== ==========================================================
2) Building
diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst
index de27e16..0acb4c9 100644
--- a/Documentation/bpf/bpf_devel_QA.rst
+++ b/Documentation/bpf/bpf_devel_QA.rst
@@ -382,6 +382,14 @@
into the Linux kernel, please implement support into LLVM's BPF back
end. See LLVM_ section below for further information.
+Q: What "BPF_INTERNAL" symbol namespace is for?
+-----------------------------------------------
+A: Symbols exported as BPF_INTERNAL can only be used by BPF infrastructure
+like preload kernel modules with light skeleton. Most symbols outside
+of BPF_INTERNAL are not expected to be used by code outside of BPF either.
+Symbols may lack the designation because they predate the namespaces,
+or due to an oversight.
+
Stable submission
=================
diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
index 517a4ac..e365413 100644
--- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
+++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
@@ -7,7 +7,7 @@
title: Mediatek's Keypad Controller
maintainers:
- - Mattijs Korpershoek <mkorpershoek@baylibre.com>
+ - Mattijs Korpershoek <mkorpershoek@kernel.org>
allOf:
- $ref: /schemas/input/matrix-keymap.yaml#
diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
index e0ec53b..1525a50 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
%YAML 1.2
---
-$id: http://devicetree.org/schemas/can/microchip,mcp2510.yaml#
+$id: http://devicetree.org/schemas/net/can/microchip,mcp2510.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Microchip MCP251X stand-alone CAN controller
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 45819b2..a2d4c62 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -74,19 +74,17 @@
- rev-rmii
- moca
- # RX and TX delays are added by the MAC when required
+ # RX and TX delays are provided by the PCB. See below
- rgmii
- # RGMII with internal RX and TX delays provided by the PHY,
- # the MAC should not add the RX or TX delays in this case
+ # RX and TX delays are not provided by the PCB. This is the most
+ # frequent case. See below
- rgmii-id
- # RGMII with internal RX delay provided by the PHY, the MAC
- # should not add an RX delay in this case
+ # TX delay is provided by the PCB. See below
- rgmii-rxid
- # RGMII with internal TX delay provided by the PHY, the MAC
- # should not add an TX delay in this case
+ # RX delay is provided by the PCB. See below
- rgmii-txid
- rtbi
- smii
@@ -286,4 +284,89 @@
additionalProperties: true
+# Informative
+# ===========
+#
+# 'phy-modes' & 'phy-connection-type' properties 'rgmii', 'rgmii-id',
+# 'rgmii-rxid', and 'rgmii-txid' are frequently used wrongly by
+# developers. This informative section clarifies their usage.
+#
+# The RGMII specification requires a 2ns delay between the data and
+# clock signals on the RGMII bus. How this delay is implemented is not
+# specified.
+#
+# One option is to make the clock traces on the PCB longer than the
+# data traces. A sufficiently difference in length can provide the 2ns
+# delay. If both the RX and TX delays are implemented in this manner,
+# 'rgmii' should be used, so indicating the PCB adds the delays.
+#
+# If the PCB does not add these delays via extra long traces,
+# 'rgmii-id' should be used. Here, 'id' refers to 'internal delay',
+# where either the MAC or PHY adds the delay.
+#
+# If only one of the two delays are implemented via extra long clock
+# lines, either 'rgmii-rxid' or 'rgmii-txid' should be used,
+# indicating the MAC or PHY should implement one of the delays
+# internally, while the PCB implements the other delay.
+#
+# Device Tree describes hardware, and in this case, it describes the
+# PCB between the MAC and the PHY, if the PCB implements delays or
+# not.
+#
+# In practice, very few PCBs make use of extra long clock lines. Hence
+# any RGMII phy mode other than 'rgmii-id' is probably wrong, and is
+# unlikely to be accepted during review without details provided in
+# the commit description and comments in the .dts file.
+#
+# When the PCB does not implement the delays, the MAC or PHY must. As
+# such, this is software configuration, and so not described in Device
+# Tree.
+#
+# The following describes how Linux implements the configuration of
+# the MAC and PHY to add these delays when the PCB does not. As stated
+# above, developers often get this wrong, and the aim of this section
+# is reduce the frequency of these errors by Linux developers. Other
+# users of the Device Tree may implement it differently, and still be
+# consistent with both the normative and informative description
+# above.
+#
+# By default in Linux, when using phylib/phylink, the MAC is expected
+# to read the 'phy-mode' from Device Tree, not implement any delays,
+# and pass the value to the PHY. The PHY will then implement delays as
+# specified by the 'phy-mode'. The PHY should always be reconfigured
+# to implement the needed delays, replacing any setting performed by
+# strapping or the bootloader, etc.
+#
+# Experience to date is that all PHYs which implement RGMII also
+# implement the ability to add or not add the needed delays. Hence
+# this default is expected to work in all cases. Ignoring this default
+# is likely to be questioned by Reviews, and require a strong argument
+# to be accepted.
+#
+# There are a small number of cases where the MAC has hard coded
+# delays which cannot be disabled. The 'phy-mode' only describes the
+# PCB. The inability to disable the delays in the MAC does not change
+# the meaning of 'phy-mode'. It does however mean that a 'phy-mode' of
+# 'rgmii' is now invalid, it cannot be supported, since both the PCB
+# and the MAC and PHY adding delays cannot result in a functional
+# link. Thus the MAC should report a fatal error for any modes which
+# cannot be supported. When the MAC implements the delay, it must
+# ensure that the PHY does not also implement the same delay. So it
+# must modify the phy-mode it passes to the PHY, removing the delay it
+# has added. Failure to remove the delay will result in a
+# non-functioning link.
+#
+# Sometimes there is a need to fine tune the delays. Often the MAC or
+# PHY can perform this fine tuning. In the MAC node, the Device Tree
+# properties 'rx-internal-delay-ps' and 'tx-internal-delay-ps' should
+# be used to indicate fine tuning performed by the MAC. The values
+# expected here are small. A value of 2000ps, i.e 2ns, and a phy-mode
+# of 'rgmii' will not be accepted by Reviewers.
+#
+# If the PHY is to perform fine tuning, the properties
+# 'rx-internal-delay-ps' and 'tx-internal-delay-ps' in the PHY node
+# should be used. When the PHY is implementing delays, e.g. 'rgmii-id'
+# these properties should have a value near to 2000ps. If the PCB is
+# implementing delays, e.g. 'rgmii', a small value can be used to fine
+# tune the delay added by the PCB.
...
diff --git a/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml b/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
index 8b382624..38e3ad5 100644
--- a/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
+++ b/Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml
@@ -27,7 +27,7 @@
$ref: /schemas/types.yaml#/definitions/uint32-array
items:
- minimum: 0
- maximum: 7
+ maximum: 31
description:
Offset in bit within the address range specified by reg.
- minimum: 1
diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
index 39c2092..3f6dc6a 100644
--- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
+++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
@@ -19,6 +19,7 @@
- enum:
- qcom,apq8064-qfprom
- qcom,apq8084-qfprom
+ - qcom,ipq5018-qfprom
- qcom,ipq5332-qfprom
- qcom,ipq5424-qfprom
- qcom,ipq6018-qfprom
@@ -28,6 +29,8 @@
- qcom,msm8226-qfprom
- qcom,msm8916-qfprom
- qcom,msm8917-qfprom
+ - qcom,msm8937-qfprom
+ - qcom,msm8960-qfprom
- qcom,msm8974-qfprom
- qcom,msm8976-qfprom
- qcom,msm8996-qfprom
@@ -51,6 +54,7 @@
- qcom,sm8450-qfprom
- qcom,sm8550-qfprom
- qcom,sm8650-qfprom
+ - qcom,x1e80100-qfprom
- const: qcom,qfprom
reg:
diff --git a/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml b/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
index a44d44b..dc89020 100644
--- a/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
+++ b/Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml
@@ -14,6 +14,7 @@
enum:
- rockchip,px30-otp
- rockchip,rk3308-otp
+ - rockchip,rk3576-otp
- rockchip,rk3588-otp
reg:
@@ -62,6 +63,8 @@
properties:
clocks:
maxItems: 3
+ clock-names:
+ maxItems: 3
resets:
maxItems: 1
reset-names:
@@ -73,11 +76,33 @@
compatible:
contains:
enum:
+ - rockchip,rk3576-otp
+ then:
+ properties:
+ clocks:
+ maxItems: 3
+ clock-names:
+ maxItems: 3
+ resets:
+ minItems: 2
+ maxItems: 2
+ reset-names:
+ items:
+ - const: otp
+ - const: apb
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
- rockchip,rk3588-otp
then:
properties:
clocks:
minItems: 4
+ clock-names:
+ minItems: 4
resets:
minItems: 3
reset-names:
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index bccd00a..53d00ca 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -56,19 +56,18 @@
enum:
- snps,dw-apb-ssi
- snps,dwc-ssi-1.01a
- - description: Microsemi Ocelot/Jaguar2 SoC SPI Controller
- items:
- - enum:
- - mscc,ocelot-spi
- - mscc,jaguar2-spi
- - const: snps,dw-apb-ssi
- description: Microchip Sparx5 SoC SPI Controller
const: microchip,sparx5-spi
- description: Amazon Alpine SPI Controller
const: amazon,alpine-dw-apb-ssi
- - description: Renesas RZ/N1 SPI Controller
+ - description: Vendor controllers which use snps,dw-apb-ssi as fallback
items:
- - const: renesas,rzn1-spi
+ - enum:
+ - mscc,ocelot-spi
+ - mscc,jaguar2-spi
+ - renesas,rzn1-spi
+ - sophgo,sg2042-spi
+ - thead,th1520-spi
- const: snps,dw-apb-ssi
- description: Intel Keem Bay SPI Controller
const: intel,keembay-ssi
@@ -88,10 +87,6 @@
- renesas,r9a06g032-spi # RZ/N1D
- renesas,r9a06g033-spi # RZ/N1S
- const: renesas,rzn1-spi # RZ/N1
- - description: T-HEAD TH1520 SoC SPI Controller
- items:
- - const: thead,th1520-spi
- - const: snps,dw-apb-ssi
reg:
minItems: 1
diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index a776248..f2dcc39 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -46,6 +46,21 @@
`KBUILD_BUILD_USER and KBUILD_BUILD_HOST`_ variables. If you are
building from a git commit, you could use its committer address.
+Absolute filenames
+------------------
+
+When the kernel is built out-of-tree, debug information may include
+absolute filenames for the source files. This must be overridden by
+including the ``-fdebug-prefix-map`` option in the `KCFLAGS`_ variable.
+
+Depending on the compiler used, the ``__FILE__`` macro may also expand
+to an absolute filename in an out-of-tree build. Kbuild automatically
+uses the ``-fmacro-prefix-map`` option to prevent this, if it is
+supported.
+
+The Reproducible Builds web site has more information about these
+`prefix-map options`_.
+
Generated files in source packages
----------------------------------
@@ -116,5 +131,7 @@
.. _KBUILD_BUILD_TIMESTAMP: kbuild.html#kbuild-build-timestamp
.. _KBUILD_BUILD_USER and KBUILD_BUILD_HOST: kbuild.html#kbuild-build-user-kbuild-build-host
+.. _KCFLAGS: kbuild.html#kcflags
+.. _prefix-map options: https://reproducible-builds.org/docs/build-path/
.. _Reproducible Builds project: https://reproducible-builds.org/
.. _SOURCE_DATE_EPOCH: https://reproducible-builds.org/docs/source-date-epoch/
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 655d8d1..c650cd3 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -89,8 +89,10 @@
doc: Group of short_detected states
-
name: phy-upstream-type
- enum-name:
+ enum-name: phy-upstream
+ header: linux/ethtool.h
type: enum
+ name-prefix: phy-upstream
entries: [ mac, phy ]
-
name: tcp-data-split
diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml
index aacccea..953aa83 100644
--- a/Documentation/netlink/specs/tc.yaml
+++ b/Documentation/netlink/specs/tc.yaml
@@ -2017,7 +2017,8 @@
attributes:
-
name: act
- type: nest
+ type: indexed-array
+ sub-type: nest
nested-attributes: tc-act-attrs
-
name: police
@@ -2250,7 +2251,8 @@
attributes:
-
name: act
- type: nest
+ type: indexed-array
+ sub-type: nest
nested-attributes: tc-act-attrs
-
name: police
@@ -2745,7 +2747,7 @@
type: u16
byte-order: big-endian
-
- name: key-l2-tpv3-sid
+ name: key-l2tpv3-sid
type: u32
byte-order: big-endian
-
@@ -3504,7 +3506,7 @@
name: rate64
type: u64
-
- name: prate4
+ name: prate64
type: u64
-
name: burst
diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index b8fef81..7aabead 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -811,11 +811,9 @@
3.2.4 Other caveats for MAC drivers
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-Stacked PHCs, especially DSA (but not only) - since that doesn't require any
-modification to MAC drivers, so it is more difficult to ensure correctness of
-all possible code paths - is that they uncover bugs which were impossible to
-trigger before the existence of stacked PTP clocks. One example has to do with
-this line of code, already presented earlier::
+The use of stacked PHCs may uncover MAC driver bugs which were impossible to
+trigger without them. One example has to do with this line of code, already
+presented earlier::
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
diff --git a/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst b/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
index cadc580..d728e4d 100644
--- a/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
+++ b/Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst
@@ -17,10 +17,10 @@
关于OpenRISC处理器和正在进行中的开发的信息:
- ======= =============================
+ ======= ==============================
网站 https://openrisc.io
- 邮箱 openrisc@lists.librecores.org
- ======= =============================
+ 邮箱 linux-openrisc@vger.kernel.org
+ ======= ==============================
---------------------------------------------------------------------
@@ -36,11 +36,11 @@
工具链的构建指南可以在openrisc.io或Stafford的工具链构建和发布脚本
中找到。
- ====== =================================================
- 二进制 https://github.com/openrisc/or1k-gcc/releases
+ ====== ==========================================================
+ 二进制 https://github.com/stffrdhrn/or1k-toolchain-build/releases
工具链 https://openrisc.io/software
构建 https://github.com/stffrdhrn/or1k-toolchain-build
- ====== =================================================
+ ====== ==========================================================
2) 构建
diff --git a/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst b/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
index 422fe9f..a1e4517 100644
--- a/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
+++ b/Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst
@@ -17,10 +17,10 @@
關於OpenRISC處理器和正在進行中的開發的信息:
- ======= =============================
+ ======= ==============================
網站 https://openrisc.io
- 郵箱 openrisc@lists.librecores.org
- ======= =============================
+ 郵箱 linux-openrisc@vger.kernel.org
+ ======= ==============================
---------------------------------------------------------------------
@@ -36,11 +36,11 @@
工具鏈的構建指南可以在openrisc.io或Stafford的工具鏈構建和發佈腳本
中找到。
- ====== =================================================
- 二進制 https://github.com/openrisc/or1k-gcc/releases
+ ====== ==========================================================
+ 二進制 https://github.com/stffrdhrn/or1k-toolchain-build/releases
工具鏈 https://openrisc.io/software
構建 https://github.com/stffrdhrn/or1k-toolchain-build
- ====== =================================================
+ ====== ==========================================================
2) 構建
diff --git a/MAINTAINERS b/MAINTAINERS
index fa1e04e..3c6f9e70 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2519,6 +2519,7 @@
F: arch/arm/boot/dts/nxp/imx/
F: arch/arm/boot/dts/nxp/mxs/
F: arch/arm64/boot/dts/freescale/
+X: Documentation/devicetree/bindings/media/i2c/
X: arch/arm64/boot/dts/freescale/fsl-*
X: arch/arm64/boot/dts/freescale/qoriq-*
X: drivers/media/i2c/
@@ -3191,6 +3192,12 @@
S: Maintained
F: drivers/clk/socfpga/
+ARM/SOCFPGA DWMAC GLUE LAYER
+M: Maxime Chevallier <maxime.chevallier@bootlin.com>
+S: Maintained
+F: Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+F: drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+
ARM/SOCFPGA EDAC BINDINGS
M: Matthew Gerlach <matthew.gerlach@altera.com>
S: Maintained
@@ -3867,8 +3874,9 @@
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
R: Dave Ertman <david.m.ertman@intel.com>
R: Ira Weiny <ira.weiny@intel.com>
+R: Leon Romanovsky <leon@kernel.org>
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
F: Documentation/driver-api/auxiliary_bus.rst
F: drivers/base/auxiliary.c
F: include/linux/auxiliary_bus.h
@@ -7227,7 +7235,7 @@
M: "Rafael J. Wysocki" <rafael@kernel.org>
M: Danilo Krummrich <dakr@kernel.org>
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
F: Documentation/core-api/kobject.rst
F: drivers/base/
F: fs/debugfs/
@@ -8719,6 +8727,7 @@
R: Yue Hu <zbestahu@gmail.com>
R: Jeffle Xu <jefflexu@linux.alibaba.com>
R: Sandeep Dhavale <dhavale@google.com>
+R: Hongbo Li <lihongbo22@huawei.com>
L: linux-erofs@lists.ozlabs.org
S: Maintained
W: https://erofs.docs.kernel.org
@@ -10138,6 +10147,13 @@
F: include/linux/gpio/regmap.h
K: (devm_)?gpio_regmap_(un)?register
+GPIO SLOPPY LOGIC ANALYZER
+M: Wolfram Sang <wsa+renesas@sang-engineering.com>
+S: Supported
+F: Documentation/dev-tools/gpio-sloppy-logic-analyzer.rst
+F: drivers/gpio/gpio-sloppy-logic-analyzer.c
+F: tools/gpio/gpio-sloppy-logic-analyzer.sh
+
GPIO SUBSYSTEM
M: Linus Walleij <linus.walleij@linaro.org>
M: Bartosz Golaszewski <brgl@bgdev.pl>
@@ -10457,14 +10473,20 @@
F: drivers/infiniband/hw/hfi1
HFS FILESYSTEM
+M: Viacheslav Dubeyko <slava@dubeyko.com>
+M: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
+M: Yangtao Li <frank.li@vivo.com>
L: linux-fsdevel@vger.kernel.org
-S: Orphan
+S: Maintained
F: Documentation/filesystems/hfs.rst
F: fs/hfs/
HFSPLUS FILESYSTEM
+M: Viacheslav Dubeyko <slava@dubeyko.com>
+M: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
+M: Yangtao Li <frank.li@vivo.com>
L: linux-fsdevel@vger.kernel.org
-S: Orphan
+S: Maintained
F: Documentation/filesystems/hfsplus.rst
F: fs/hfsplus/
@@ -11222,7 +11244,6 @@
F: drivers/i2c/busses/i2c-cht-wc.c
I2C/SMBUS ISMT DRIVER
-M: Seth Heasley <seth.heasley@intel.com>
M: Neil Horman <nhorman@tuxdriver.com>
L: linux-i2c@vger.kernel.org
F: Documentation/i2c/busses/i2c-ismt.rst
@@ -13112,7 +13133,7 @@
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
M: Tejun Heo <tj@kernel.org>
S: Supported
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
F: fs/kernfs/
F: include/linux/kernfs.h
@@ -15058,7 +15079,7 @@
F: drivers/media/platform/mediatek/jpeg/
MEDIATEK KEYPAD DRIVER
-M: Mattijs Korpershoek <mkorpershoek@baylibre.com>
+M: Mattijs Korpershoek <mkorpershoek@kernel.org>
S: Supported
F: Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml
F: drivers/input/keyboard/mt6779-keypad.c
@@ -15481,24 +15502,45 @@
F: include/linux/gfp.h
F: include/linux/gfp_types.h
F: include/linux/memfd.h
-F: include/linux/memory.h
F: include/linux/memory_hotplug.h
F: include/linux/memory-tiers.h
F: include/linux/mempolicy.h
F: include/linux/mempool.h
F: include/linux/memremap.h
-F: include/linux/mm.h
-F: include/linux/mm_*.h
F: include/linux/mmzone.h
F: include/linux/mmu_notifier.h
F: include/linux/pagewalk.h
-F: include/linux/rmap.h
F: include/trace/events/ksm.h
F: mm/
F: tools/mm/
F: tools/testing/selftests/mm/
N: include/linux/page[-_]*
+MEMORY MANAGEMENT - CORE
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Mike Rapoport <rppt@kernel.org>
+R: Suren Baghdasaryan <surenb@google.com>
+R: Michal Hocko <mhocko@suse.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: include/linux/memory.h
+F: include/linux/mm.h
+F: include/linux/mm_*.h
+F: include/linux/mmdebug.h
+F: include/linux/pagewalk.h
+F: mm/Kconfig
+F: mm/debug.c
+F: mm/init-mm.c
+F: mm/memory.c
+F: mm/pagewalk.c
+F: mm/util.c
+
MEMORY MANAGEMENT - EXECMEM
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15507,6 +15549,18 @@
F: include/linux/execmem.h
F: mm/execmem.c
+MEMORY MANAGEMENT - GUP (GET USER PAGES)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Jason Gunthorpe <jgg@nvidia.com>
+R: John Hubbard <jhubbard@nvidia.com>
+R: Peter Xu <peterx@redhat.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: mm/gup.c
+
MEMORY MANAGEMENT - NUMA MEMBLOCKS AND NUMA EMULATION
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15532,6 +15586,19 @@
F: include/linux/gfp.h
F: include/linux/compaction.h
+MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Rik van Riel <riel@surriel.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Vlastimil Babka <vbabka@suse.cz>
+R: Harry Yoo <harry.yoo@oracle.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: include/linux/rmap.h
+F: mm/rmap.c
+
MEMORY MANAGEMENT - SECRETMEM
M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
@@ -15540,6 +15607,30 @@
F: include/linux/secretmem.h
F: mm/secretmem.c
+MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
+M: Andrew Morton <akpm@linux-foundation.org>
+M: David Hildenbrand <david@redhat.com>
+R: Zi Yan <ziy@nvidia.com>
+R: Baolin Wang <baolin.wang@linux.alibaba.com>
+R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R: Liam R. Howlett <Liam.Howlett@oracle.com>
+R: Nico Pache <npache@redhat.com>
+R: Ryan Roberts <ryan.roberts@arm.com>
+R: Dev Jain <dev.jain@arm.com>
+L: linux-mm@kvack.org
+S: Maintained
+W: http://www.linux-mm.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: Documentation/admin-guide/mm/transhuge.rst
+F: include/linux/huge_mm.h
+F: include/linux/khugepaged.h
+F: include/trace/events/huge_memory.h
+F: mm/huge_memory.c
+F: mm/khugepaged.c
+F: tools/testing/selftests/mm/khugepaged.c
+F: tools/testing/selftests/mm/split_huge_page_test.c
+F: tools/testing/selftests/mm/transhuge-stress.c
+
MEMORY MANAGEMENT - USERFAULTFD
M: Andrew Morton <akpm@linux-foundation.org>
R: Peter Xu <peterx@redhat.com>
@@ -16812,6 +16903,7 @@
F: drivers/connector/
F: drivers/net/
F: drivers/ptp/
+F: drivers/s390/net/
F: include/dt-bindings/net/
F: include/linux/cn_proc.h
F: include/linux/etherdevice.h
@@ -16821,6 +16913,7 @@
F: include/linux/hippidevice.h
F: include/linux/if_*
F: include/linux/inetdevice.h
+F: include/linux/ism.h
F: include/linux/netdev*
F: include/linux/platform_data/wiznet.h
F: include/uapi/linux/cn_proc.h
@@ -18358,7 +18451,7 @@
PARAVIRT_OPS INTERFACE
M: Juergen Gross <jgross@suse.com>
R: Ajay Kaher <ajay.kaher@broadcom.com>
-R: Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R: Alexey Makhalov <alexey.makhalov@broadcom.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: virtualization@lists.linux.dev
L: x86@kernel.org
@@ -18689,7 +18782,7 @@
PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
M: Lorenzo Pieralisi <lpieralisi@kernel.org>
M: Krzysztof Wilczyński <kw@linux.com>
-R: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
R: Rob Herring <robh@kernel.org>
L: linux-pci@vger.kernel.org
S: Supported
@@ -18742,6 +18835,16 @@
F: include/linux/of_pci.h
F: include/linux/pci*
F: include/uapi/linux/pci*
+
+PCI SUBSYSTEM [RUST]
+M: Danilo Krummrich <dakr@kernel.org>
+R: Bjorn Helgaas <bhelgaas@google.com>
+R: Krzysztof Wilczyński <kwilczynski@kernel.org>
+L: linux-pci@vger.kernel.org
+S: Maintained
+C: irc://irc.oftc.net/linux-pci
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
+F: rust/helpers/pci.c
F: rust/kernel/pci.rs
F: samples/rust/rust_driver_pci.rs
@@ -20510,8 +20613,8 @@
F: drivers/i2c/busses/i2c-emev2.c
RENESAS ETHERNET AVB DRIVER
-M: Paul Barker <paul.barker.ct@bp.renesas.com>
M: Niklas Söderlund <niklas.soderlund@ragnatech.se>
+R: Paul Barker <paul@pbarker.dev>
L: netdev@vger.kernel.org
L: linux-renesas-soc@vger.kernel.org
S: Maintained
@@ -21312,6 +21415,7 @@
L: netdev@vger.kernel.org
S: Supported
F: drivers/s390/net/
+F: include/linux/ism.h
S390 PCI SUBSYSTEM
M: Niklas Schnelle <schnelle@linux.ibm.com>
@@ -22712,9 +22816,15 @@
F: Documentation/devicetree/bindings/sound/
F: Documentation/sound/soc/
F: include/dt-bindings/sound/
+F: include/sound/cs-amp-lib.h
+F: include/sound/cs35l*
+F: include/sound/cs4271.h
+F: include/sound/cs42l*
+F: include/sound/madera-pdata.h
F: include/sound/soc*
F: include/sound/sof.h
F: include/sound/sof/
+F: include/sound/wm*.h
F: include/trace/events/sof*.h
F: include/uapi/sound/asoc.h
F: sound/soc/
@@ -22825,7 +22935,6 @@
SPEAR PLATFORM/CLOCK/PINCTRL SUPPORT
M: Viresh Kumar <vireshk@kernel.org>
-M: Shiraz Hashim <shiraz.linux.kernel@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: soc@lists.linux.dev
S: Maintained
@@ -25184,9 +25293,13 @@
F: drivers/usb/typec/mux/pi3usb30532.c
USB TYPEC PORT CONTROLLER DRIVERS
+M: Badhri Jagan Sridharan <badhri@google.com>
L: linux-usb@vger.kernel.org
-S: Orphan
-F: drivers/usb/typec/tcpm/
+S: Maintained
+F: drivers/usb/typec/tcpm/tcpci.c
+F: drivers/usb/typec/tcpm/tcpm.c
+F: include/linux/usb/tcpci.h
+F: include/linux/usb/tcpm.h
USB TYPEC TUSB1046 MUX DRIVER
M: Romain Gantois <romain.gantois@bootlin.com>
@@ -25823,7 +25936,7 @@
VMWARE HYPERVISOR INTERFACE
M: Ajay Kaher <ajay.kaher@broadcom.com>
-M: Alexey Makhalov <alexey.amakhalov@broadcom.com>
+M: Alexey Makhalov <alexey.makhalov@broadcom.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: virtualization@lists.linux.dev
L: x86@kernel.org
@@ -25851,7 +25964,7 @@
VMWARE VIRTUAL PTP CLOCK DRIVER
M: Nick Shi <nick.shi@broadcom.com>
R: Ajay Kaher <ajay.kaher@broadcom.com>
-R: Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R: Alexey Makhalov <alexey.makhalov@broadcom.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: netdev@vger.kernel.org
S: Supported
diff --git a/Makefile b/Makefile
index 3dcad23..a9edd03 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 15
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc7
NAME = Baby Opossum Posse
# *DOCUMENTATION*
@@ -1052,13 +1052,6 @@
# perform bounds checking.
KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
-#Currently, disable -Wstringop-overflow for GCC 11, globally.
-KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
-KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
-
-#Currently, disable -Wunterminated-string-initialization as an error
-KBUILD_CFLAGS += $(call cc-option, -Wno-error=unterminated-string-initialization)
-
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += -fno-strict-overflow
@@ -1075,8 +1068,7 @@
# change __FILE__ to the relative path to the source directory
ifdef building_out_of_srctree
-KBUILD_CPPFLAGS += $(call cc-option,-ffile-prefix-map=$(srcroot)/=)
-KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/=
+KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srcroot)/=)
endif
# include additional Makefiles when needed
diff --git a/arch/arm/boot/dts/amlogic/meson8.dtsi b/arch/arm/boot/dts/amlogic/meson8.dtsi
index 847f7b1..f785e0d 100644
--- a/arch/arm/boot/dts/amlogic/meson8.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8.dtsi
@@ -451,7 +451,7 @@ analog_top: analog-top@81a8 {
pwm_ef: pwm@86c0 {
compatible = "amlogic,meson8-pwm-v2";
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+ <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
reg = <0x86c0 0x10>;
@@ -705,7 +705,7 @@ timer@600 {
&pwm_ab {
compatible = "amlogic,meson8-pwm-v2";
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+ <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
@@ -713,7 +713,7 @@ &pwm_ab {
&pwm_cd {
compatible = "amlogic,meson8-pwm-v2";
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+ <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
diff --git a/arch/arm/boot/dts/amlogic/meson8b.dtsi b/arch/arm/boot/dts/amlogic/meson8b.dtsi
index 0876611..fdb0abe 100644
--- a/arch/arm/boot/dts/amlogic/meson8b.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8b.dtsi
@@ -406,7 +406,7 @@ pwm_ef: pwm@86c0 {
compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
reg = <0x86c0 0x10>;
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+ <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
#pwm-cells = <3>;
@@ -680,7 +680,7 @@ timer@600 {
&pwm_ab {
compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+ <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
@@ -688,7 +688,7 @@ &pwm_ab {
&pwm_cd {
compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "Video PLL" */
+ <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
index f2386dc..dda4fa91 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
@@ -40,6 +40,9 @@ ethphy1: ethernet-phy@1 {
reg = <1>;
interrupt-parent = <&gpio4>;
interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
+ micrel,led-mode = <1>;
+ clocks = <&clks IMX6UL_CLK_ENET_REF>;
+ clock-names = "rmii-ref";
status = "okay";
};
};
diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
index da9de49..5a72f0b 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
@@ -151,7 +151,7 @@ msix: msix@fbe00000 {
al,msi-num-spis = <160>;
};
- io-fabric@fc000000 {
+ io-bus@fc000000 {
compatible = "simple-bus";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
index 8b6156b..dea60d1 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
@@ -361,7 +361,7 @@ msix: msix@fbe00000 {
interrupt-parent = <&gic>;
};
- io-fabric@fc000000 {
+ io-bus@fc000000 {
compatible = "simple-bus";
#address-cells = <1>;
#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index ab2b3f1..69834b4 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -2313,7 +2313,7 @@ pwm_ef: pwm@19000 {
"amlogic,meson8-pwm-v2";
reg = <0x0 0x19000 0x0 0x20>;
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
#pwm-cells = <3>;
@@ -2325,7 +2325,7 @@ pwm_cd: pwm@1a000 {
"amlogic,meson8-pwm-v2";
reg = <0x0 0x1a000 0x0 0x20>;
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
#pwm-cells = <3>;
@@ -2337,7 +2337,7 @@ pwm_ab: pwm@1b000 {
"amlogic,meson8-pwm-v2";
reg = <0x0 0x1b000 0x0 0x20>;
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
#pwm-cells = <3>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
index de35fa2..8e3e335 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
@@ -116,6 +116,10 @@ &arb {
status = "okay";
};
+&clkc_audio {
+ status = "okay";
+};
+
&frddr_a {
status = "okay";
};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 8ebce71..6c13459 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -741,7 +741,7 @@ mux {
&pwm_ab {
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
@@ -752,14 +752,14 @@ &pwm_AO_ab {
&pwm_cd {
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
&pwm_ef {
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 2dc2fda..19b8a39 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -811,7 +811,7 @@ internal_phy: ethernet-phy@8 {
&pwm_ab {
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
@@ -822,14 +822,14 @@ &pwm_AO_ab {
&pwm_cd {
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
&pwm_ef {
clocks = <&xtal>,
- <>, /* unknown/untested, the datasheet calls it "vid_pll" */
+ <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
<&clkc CLKID_FCLK_DIV4>,
<&clkc CLKID_FCLK_DIV3>;
};
diff --git a/arch/arm64/boot/dts/apple/t8103-j293.dts b/arch/arm64/boot/dts/apple/t8103-j293.dts
index 2dfe7b8..e2d9439 100644
--- a/arch/arm64/boot/dts/apple/t8103-j293.dts
+++ b/arch/arm64/boot/dts/apple/t8103-j293.dts
@@ -77,6 +77,16 @@ touchbar0: touchbar@0 {
};
};
+/*
+ * The driver depends on boot loader initialized state which resets when this
+ * power-domain is powered off. This happens on suspend or when the driver is
+ * missing during boot. Mark the domain as always on until the driver can
+ * handle this.
+ */
+&ps_dispdfr_be {
+ apple,always-on;
+};
+
&display_dfr {
status = "okay";
};
diff --git a/arch/arm64/boot/dts/apple/t8112-j493.dts b/arch/arm64/boot/dts/apple/t8112-j493.dts
index 3d73f9e..be86d34 100644
--- a/arch/arm64/boot/dts/apple/t8112-j493.dts
+++ b/arch/arm64/boot/dts/apple/t8112-j493.dts
@@ -40,6 +40,16 @@ led-0 {
};
};
+/*
+ * The driver depends on boot loader initialized state which resets when this
+ * power-domain is powered off. This happens on suspend or when the driver is
+ * missing during boot. Mark the domain as always on until the driver can
+ * handle this.
+ */
+&ps_dispdfr_be {
+ apple,always-on;
+};
+
&display_dfr {
status = "okay";
};
diff --git a/arch/arm64/boot/dts/arm/morello.dtsi b/arch/arm64/boot/dts/arm/morello.dtsi
index 0bab0b3..5bc1c72 100644
--- a/arch/arm64/boot/dts/arm/morello.dtsi
+++ b/arch/arm64/boot/dts/arm/morello.dtsi
@@ -44,7 +44,7 @@ cpu0: cpu@0 {
next-level-cache = <&l2_0>;
clocks = <&scmi_dvfs 0>;
- l2_0: l2-cache-0 {
+ l2_0: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -53,13 +53,6 @@ l2_0: l2-cache-0 {
cache-sets = <2048>;
cache-unified;
next-level-cache = <&l3_0>;
-
- l3_0: l3-cache {
- compatible = "cache";
- cache-level = <3>;
- cache-size = <0x100000>;
- cache-unified;
- };
};
};
@@ -78,7 +71,7 @@ cpu1: cpu@100 {
next-level-cache = <&l2_1>;
clocks = <&scmi_dvfs 0>;
- l2_1: l2-cache-1 {
+ l2_1: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -105,7 +98,7 @@ cpu2: cpu@10000 {
next-level-cache = <&l2_2>;
clocks = <&scmi_dvfs 1>;
- l2_2: l2-cache-2 {
+ l2_2: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -132,7 +125,7 @@ cpu3: cpu@10100 {
next-level-cache = <&l2_3>;
clocks = <&scmi_dvfs 1>;
- l2_3: l2-cache-3 {
+ l2_3: l2-cache {
compatible = "cache";
cache-level = <2>;
/* 8 ways set associative */
@@ -143,6 +136,13 @@ l2_3: l2-cache-3 {
next-level-cache = <&l3_0>;
};
};
+
+ l3_0: l3-cache {
+ compatible = "cache";
+ cache-level = <3>;
+ cache-size = <0x100000>;
+ cache-unified;
+ };
};
firmware {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
index 7251ad3..b46566f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
@@ -144,6 +144,19 @@ reg_usdhc2_vmmc: regulator-usdhc2 {
startup-delay-us = <20000>;
};
+ reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+ compatible = "regulator-gpio";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usdhc2_vsel>;
+ gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+ regulator-max-microvolt = <3300000>;
+ regulator-min-microvolt = <1800000>;
+ states = <1800000 0x1>,
+ <3300000 0x0>;
+ regulator-name = "PMIC_USDHC_VSELECT";
+ vin-supply = <®_nvcc_sd>;
+ };
+
reserved-memory {
#address-cells = <2>;
#size-cells = <2>;
@@ -269,7 +282,7 @@ &gpio1 {
"SODIMM_19",
"",
"",
- "",
+ "PMIC_USDHC_VSELECT",
"",
"",
"",
@@ -785,6 +798,7 @@ &usdhc2 {
pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>;
pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>;
vmmc-supply = <®_usdhc2_vmmc>;
+ vqmmc-supply = <®_usdhc2_vqmmc>;
};
&wdog1 {
@@ -1206,13 +1220,17 @@ pinctrl_usdhc2_pwr_en: usdhc2pwrengrp {
<MX8MM_IOMUXC_NAND_CLE_GPIO3_IO5 0x6>; /* SODIMM 76 */
};
+ pinctrl_usdhc2_vsel: usdhc2vselgrp {
+ fsl,pins =
+ <MX8MM_IOMUXC_GPIO1_IO04_GPIO1_IO4 0x10>; /* PMIC_USDHC_VSELECT */
+ };
+
/*
* Note: Due to ERR050080 we use discrete external on-module resistors pulling-up to the
* on-module +V3.3_1.8_SD (LDO5) rail and explicitly disable the internal pull-ups here.
*/
pinctrl_usdhc2: usdhc2grp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90>, /* SODIMM 78 */
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x90>, /* SODIMM 74 */
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x90>, /* SODIMM 80 */
@@ -1223,7 +1241,6 @@ pinctrl_usdhc2: usdhc2grp {
pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94>,
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x94>,
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x94>,
@@ -1234,7 +1251,6 @@ pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96>,
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x96>,
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x96>,
@@ -1246,7 +1262,6 @@ pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
/* Avoid backfeeding with removed card power */
pinctrl_usdhc2_sleep: usdhc2slpgrp {
fsl,pins =
- <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x0>,
<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x0>,
<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x0>,
<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x0>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
index a1b75c9..2ce1860b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
@@ -24,6 +24,20 @@ &clk {
fsl,operating-mode = "nominal";
};
+&gpu2d {
+ assigned-clocks = <&clk IMX8MP_CLK_GPU2D_CORE>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <800000000>;
+};
+
+&gpu3d {
+ assigned-clocks = <&clk IMX8MP_CLK_GPU3D_CORE>,
+ <&clk IMX8MP_CLK_GPU3D_SHADER_CORE>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <800000000>, <800000000>;
+};
+
&pgc_hdmimix {
assigned-clocks = <&clk IMX8MP_CLK_HDMI_AXI>,
<&clk IMX8MP_CLK_HDMI_APB>;
@@ -46,6 +60,18 @@ &pgc_gpumix {
assigned-clock-rates = <600000000>, <300000000>;
};
+&pgc_mlmix {
+ assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
+ <&clk IMX8MP_CLK_ML_AXI>,
+ <&clk IMX8MP_CLK_ML_AHB>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <800000000>,
+ <800000000>,
+ <300000000>;
+};
+
&media_blk_ctrl {
assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>,
<&clk IMX8MP_CLK_MEDIA_APB>,
@@ -62,3 +88,5 @@ &media_blk_ctrl {
<0>, <0>, <400000000>,
<1039500000>;
};
+
+/delete-node/ &{noc_opp_table/opp-1000000000};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
index b2ac258..b59da91 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
@@ -35,7 +35,6 @@ memory@40000000 {
<0x1 0x00000000 0 0xc0000000>;
};
-
reg_usdhc2_vmmc: regulator-usdhc2-vmmc {
compatible = "regulator-fixed";
regulator-name = "VSD_3V3";
@@ -46,6 +45,16 @@ reg_usdhc2_vmmc: regulator-usdhc2-vmmc {
startup-delay-us = <100>;
off-on-delay-us = <12000>;
};
+
+ reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+ compatible = "regulator-gpio";
+ regulator-name = "VSD_VSEL";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <3300000>;
+ gpios = <&gpio2 12 GPIO_ACTIVE_HIGH>;
+ states = <3300000 0x0 1800000 0x1>;
+ vin-supply = <&ldo5>;
+ };
};
&A53_0 {
@@ -205,6 +214,7 @@ &usdhc2 {
pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
cd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
vmmc-supply = <®_usdhc2_vmmc>;
+ vqmmc-supply = <®_usdhc2_vqmmc>;
bus-width = <4>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index ce6793b..7c1c87e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1645,6 +1645,12 @@ opp-200000000 {
opp-hz = /bits/ 64 <200000000>;
};
+ /* Nominal drive mode maximum */
+ opp-800000000 {
+ opp-hz = /bits/ 64 <800000000>;
+ };
+
+ /* Overdrive mode maximum */
opp-1000000000 {
opp-hz = /bits/ 64 <1000000000>;
};
diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi
index 9bb26b4..59f057b 100644
--- a/arch/arm64/boot/dts/freescale/imx95.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx95.dtsi
@@ -1626,7 +1626,7 @@ pcie0: pcie@4c300000 {
reg = <0 0x4c300000 0 0x10000>,
<0 0x60100000 0 0xfe00000>,
<0 0x4c360000 0 0x10000>,
- <0 0x4c340000 0 0x2000>;
+ <0 0x4c340000 0 0x4000>;
reg-names = "dbi", "config", "atu", "app";
ranges = <0x81000000 0x0 0x00000000 0x0 0x6ff00000 0 0x00100000>,
<0x82000000 0x0 0x10000000 0x9 0x10000000 0 0x10000000>;
@@ -1673,7 +1673,7 @@ pcie0_ep: pcie-ep@4c300000 {
reg = <0 0x4c300000 0 0x10000>,
<0 0x4c360000 0 0x1000>,
<0 0x4c320000 0 0x1000>,
- <0 0x4c340000 0 0x2000>,
+ <0 0x4c340000 0 0x4000>,
<0 0x4c370000 0 0x10000>,
<0x9 0 1 0>;
reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space";
@@ -1700,7 +1700,7 @@ pcie1: pcie@4c380000 {
reg = <0 0x4c380000 0 0x10000>,
<8 0x80100000 0 0xfe00000>,
<0 0x4c3e0000 0 0x10000>,
- <0 0x4c3c0000 0 0x2000>;
+ <0 0x4c3c0000 0 0x4000>;
reg-names = "dbi", "config", "atu", "app";
ranges = <0x81000000 0 0x00000000 0x8 0x8ff00000 0 0x00100000>,
<0x82000000 0 0x10000000 0xa 0x10000000 0 0x10000000>;
@@ -1749,7 +1749,7 @@ pcie1_ep: pcie-ep@4c380000 {
reg = <0 0x4c380000 0 0x10000>,
<0 0x4c3e0000 0 0x1000>,
<0 0x4c3a0000 0 0x1000>,
- <0 0x4c3c0000 0 0x2000>,
+ <0 0x4c3c0000 0 0x4000>,
<0 0x4c3f0000 0 0x10000>,
<0xa 0 1 0>;
reg-names = "dbi", "atu", "dbi2", "app", "dma", "addr_space";
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
index 1edfd64..a334ef0 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
@@ -31,7 +31,7 @@ sdio_pwrseq: sdio-pwrseq {
};
vcc3v3_btreg: vcc3v3-btreg {
- compatible = "regulator-gpio";
+ compatible = "regulator-fixed";
enable-active-high;
pinctrl-names = "default";
pinctrl-0 = <&bt_enable_h>;
@@ -39,7 +39,6 @@ vcc3v3_btreg: vcc3v3-btreg {
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
regulator-always-on;
- states = <3300000 0x0>;
};
vcc3v3_rf_aux_mod: regulator-vcc3v3-rf-aux-mod {
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
index 80db778..b60e68f 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
@@ -26,5 +26,5 @@ &sdio_pwrseq {
};
&vcc3v3_btreg {
- enable-gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
};
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
index 165d09c..5886b80 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
@@ -39,5 +39,5 @@ &sdio_pwrseq {
};
&vcc3v3_btreg {
- enable-gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
index 541dca1..046dbe3 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
@@ -43,7 +43,7 @@ led-0 {
sdio_pwrseq: sdio-pwrseq {
compatible = "mmc-pwrseq-simple";
clocks = <&rk808 1>;
- clock-names = "lpo";
+ clock-names = "ext_clock";
pinctrl-names = "default";
pinctrl-0 = <&wifi_enable_h>;
reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
index a483514..e7ba477 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
@@ -775,7 +775,7 @@ &sdmmc1 {
rockchip,default-sample-phase = <90>;
status = "okay";
- sdio-wifi@1 {
+ wifi@1 {
compatible = "brcm,bcm4329-fmac";
reg = <1>;
interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
index 7bd32d2..b80d628 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
@@ -619,6 +619,8 @@ &sdhci {
bus-width = <8>;
max-frequency = <200000000>;
non-removable;
+ pinctrl-names = "default";
+ pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd &emmc_datastrobe>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
index 828bde7f..314067b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
@@ -610,7 +610,7 @@ hym8563: rtc@51 {
reg = <0x51>;
clock-output-names = "hym8563";
interrupt-parent = <&gpio0>;
- interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
pinctrl-names = "default";
pinctrl-0 = <&hym8563_int>;
wakeup-source;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
index 1af0a30..af431fd 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
@@ -222,6 +222,10 @@ rt5616: audio-codec@1b {
compatible = "realtek,rt5616";
reg = <0x1b>;
#sound-dai-cells = <0>;
+ assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
+ assigned-clock-rates = <12288000>;
+ clocks = <&cru I2S0_8CH_MCLKOUT>;
+ clock-names = "mclk";
};
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
index 711ac4f..60ad272 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
@@ -214,6 +214,8 @@ rgmii_phy: ethernet-phy@1 {
};
&package_thermal {
+ polling-delay = <1000>;
+
trips {
package_active1: trip-active1 {
temperature = <45000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
index bce72ba..3045cb3b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
@@ -11,20 +11,15 @@ cluster0_opp_table: opp-table-cluster0 {
compatible = "operating-points-v2";
opp-shared;
- opp-1416000000 {
- opp-hz = /bits/ 64 <1416000000>;
+ opp-1200000000 {
+ opp-hz = /bits/ 64 <1200000000>;
opp-microvolt = <750000 750000 950000>;
clock-latency-ns = <40000>;
opp-suspend;
};
- opp-1608000000 {
- opp-hz = /bits/ 64 <1608000000>;
- opp-microvolt = <887500 887500 950000>;
- clock-latency-ns = <40000>;
- };
- opp-1704000000 {
- opp-hz = /bits/ 64 <1704000000>;
- opp-microvolt = <937500 937500 950000>;
+ opp-1296000000 {
+ opp-hz = /bits/ 64 <1296000000>;
+ opp-microvolt = <775000 775000 950000>;
clock-latency-ns = <40000>;
};
};
@@ -33,9 +28,14 @@ cluster1_opp_table: opp-table-cluster1 {
compatible = "operating-points-v2";
opp-shared;
+ opp-1200000000{
+ opp-hz = /bits/ 64 <1200000000>;
+ opp-microvolt = <750000 750000 950000>;
+ clock-latency-ns = <40000>;
+ };
opp-1416000000 {
opp-hz = /bits/ 64 <1416000000>;
- opp-microvolt = <750000 750000 950000>;
+ opp-microvolt = <762500 762500 950000>;
clock-latency-ns = <40000>;
};
opp-1608000000 {
@@ -43,25 +43,20 @@ opp-1608000000 {
opp-microvolt = <787500 787500 950000>;
clock-latency-ns = <40000>;
};
- opp-1800000000 {
- opp-hz = /bits/ 64 <1800000000>;
- opp-microvolt = <875000 875000 950000>;
- clock-latency-ns = <40000>;
- };
- opp-2016000000 {
- opp-hz = /bits/ 64 <2016000000>;
- opp-microvolt = <950000 950000 950000>;
- clock-latency-ns = <40000>;
- };
};
cluster2_opp_table: opp-table-cluster2 {
compatible = "operating-points-v2";
opp-shared;
+ opp-1200000000{
+ opp-hz = /bits/ 64 <1200000000>;
+ opp-microvolt = <750000 750000 950000>;
+ clock-latency-ns = <40000>;
+ };
opp-1416000000 {
opp-hz = /bits/ 64 <1416000000>;
- opp-microvolt = <750000 750000 950000>;
+ opp-microvolt = <762500 762500 950000>;
clock-latency-ns = <40000>;
};
opp-1608000000 {
@@ -69,16 +64,6 @@ opp-1608000000 {
opp-microvolt = <787500 787500 950000>;
clock-latency-ns = <40000>;
};
- opp-1800000000 {
- opp-hz = /bits/ 64 <1800000000>;
- opp-microvolt = <875000 875000 950000>;
- clock-latency-ns = <40000>;
- };
- opp-2016000000 {
- opp-hz = /bits/ 64 <2016000000>;
- opp-microvolt = <950000 950000 950000>;
- clock-latency-ns = <40000>;
- };
};
gpu_opp_table: opp-table {
@@ -104,10 +89,6 @@ opp-700000000 {
opp-hz = /bits/ 64 <700000000>;
opp-microvolt = <750000 750000 850000>;
};
- opp-850000000 {
- opp-hz = /bits/ 64 <800000000>;
- opp-microvolt = <787500 787500 850000>;
- };
};
};
diff --git a/arch/arm64/boot/dts/st/stm32mp211.dtsi b/arch/arm64/boot/dts/st/stm32mp211.dtsi
index 6dd1377..bf888d6 100644
--- a/arch/arm64/boot/dts/st/stm32mp211.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp211.dtsi
@@ -116,11 +116,11 @@ syscfg: syscon@44230000 {
};
intc: interrupt-controller@4ac10000 {
- compatible = "arm,cortex-a7-gic";
+ compatible = "arm,gic-400";
reg = <0x4ac10000 0x0 0x1000>,
- <0x4ac20000 0x0 0x2000>,
- <0x4ac40000 0x0 0x2000>,
- <0x4ac60000 0x0 0x2000>;
+ <0x4ac20000 0x0 0x20000>,
+ <0x4ac40000 0x0 0x20000>,
+ <0x4ac60000 0x0 0x20000>;
#interrupt-cells = <3>;
interrupt-controller;
};
diff --git a/arch/arm64/boot/dts/st/stm32mp231.dtsi b/arch/arm64/boot/dts/st/stm32mp231.dtsi
index 8820d21..75697ac 100644
--- a/arch/arm64/boot/dts/st/stm32mp231.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp231.dtsi
@@ -1201,13 +1201,12 @@ exti2: interrupt-controller@46230000 {
};
intc: interrupt-controller@4ac10000 {
- compatible = "arm,cortex-a7-gic";
+ compatible = "arm,gic-400";
reg = <0x4ac10000 0x1000>,
- <0x4ac20000 0x2000>,
- <0x4ac40000 0x2000>,
- <0x4ac60000 0x2000>;
+ <0x4ac20000 0x20000>,
+ <0x4ac40000 0x20000>,
+ <0x4ac60000 0x20000>;
#interrupt-cells = <3>;
- #address-cells = <1>;
interrupt-controller;
};
};
diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi
index f3c6cdf..87110f9 100644
--- a/arch/arm64/boot/dts/st/stm32mp251.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi
@@ -115,14 +115,13 @@ scmi_vdda18adc: regulator@7 {
};
intc: interrupt-controller@4ac00000 {
- compatible = "arm,cortex-a7-gic";
+ compatible = "arm,gic-400";
#interrupt-cells = <3>;
- #address-cells = <1>;
interrupt-controller;
reg = <0x0 0x4ac10000 0x0 0x1000>,
- <0x0 0x4ac20000 0x0 0x2000>,
- <0x0 0x4ac40000 0x0 0x2000>,
- <0x0 0x4ac60000 0x0 0x2000>;
+ <0x0 0x4ac20000 0x0 0x20000>,
+ <0x0 0x4ac40000 0x0 0x20000>,
+ <0x0 0x4ac60000 0x0 0x20000>;
};
psci {
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index d1cc057..dffff67 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -81,6 +81,7 @@
#define ARM_CPU_PART_CORTEX_A78AE 0xD42
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
+#define ARM_CPU_PART_CORTEX_X1C 0xD4C
#define ARM_CPU_PART_CORTEX_A520 0xD80
#define ARM_CPU_PART_CORTEX_A710 0xD47
#define ARM_CPU_PART_CORTEX_A715 0xD4D
@@ -168,6 +169,7 @@
#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index ebceaae..d40e427 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -52,7 +52,7 @@
mrs x0, id_aa64mmfr1_el1
ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
cbz x0, .Lskip_hcrx_\@
- mov_q x0, HCRX_HOST_FLAGS
+ mov_q x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
/* Enable GCS if supported */
mrs_s x1, SYS_ID_AA64PFR1_EL1
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 39577f1..18c7811 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -706,6 +706,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
}
#endif
u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type);
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type);
u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
enum aarch64_insn_system_register sysreg);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 974d72b..e9c8a58 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -100,9 +100,8 @@
HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID1)
#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
-#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H | HCR_AMO | HCR_IMO | HCR_FMO)
-#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
#define MPAMHCR_HOST_FLAGS 0
/* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e98cfe7..08ba91e6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1588,4 +1588,9 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
#define kvm_has_s1poe(k) \
(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return true;
+}
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 30a29e8..6e8aa8e 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -94,17 +94,6 @@ static inline bool kaslr_requires_kpti(void)
return false;
}
- /*
- * Systems affected by Cavium erratum 24756 are incompatible
- * with KPTI.
- */
- if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
- extern const struct midr_range cavium_erratum_27456_cpus[];
-
- if (is_midr_in_range_list(cavium_erratum_27456_cpus))
- return false;
- }
-
return true;
}
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index f1524cd..8fef126 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -97,6 +97,9 @@ enum mitigation_state arm64_get_meltdown_state(void);
enum mitigation_state arm64_get_spectre_bhb_state(void);
bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
+extern bool __nospectre_bhb;
+u8 get_spectre_bhb_loop_value(void);
+bool is_spectre_bhb_fw_mitigated(void);
void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr);
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 92a2b59..3322c70 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -99,6 +99,19 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
return res;
}
+#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
+{
+ const struct vdso_time_data *ret = &vdso_u_time_data;
+
+ /* Work around invalid absolute relocations */
+ OPTIMIZER_HIDE_VAR(ret);
+
+ return ret;
+}
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
+#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index b55f5f7..6b0ad50 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -335,7 +335,7 @@ static const struct midr_range cavium_erratum_23154_cpus[] = {
#endif
#ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
/* Cavium ThunderX, T88 pass 1.x - 2.1 */
MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
/* Cavium ThunderX, T81 pass 1.0 */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9c4d6d5..4c46d80 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -114,7 +114,14 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NC
DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS);
-bool arm64_use_ng_mappings = false;
+/*
+ * arm64_use_ng_mappings must be placed in the .data section, otherwise it
+ * ends up in the .bss section where it is initialized in early_map_kernel()
+ * after the MMU (with the idmap) was enabled. create_init_idmap() - which
+ * runs before early_map_kernel() and reads the variable via PTE_MAYBE_NG -
+ * may end up generating an incorrect idmap page table attributes.
+ */
+bool arm64_use_ng_mappings __read_mostly = false;
EXPORT_SYMBOL(arm64_use_ng_mappings);
DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 5e3c4b5..2004b4f 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -47,10 +47,6 @@ PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override);
PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override);
PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override);
PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus);
-PROVIDE(__pi_is_midr_in_range_list = is_midr_in_range_list);
-#endif
PROVIDE(__pi__ctype = _ctype);
PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed);
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index e57b043..c6650cf 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -207,6 +207,29 @@ static void __init map_fdt(u64 fdt)
dsb(ishst);
}
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+ static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+ /* Cavium ThunderX, T88 pass 1.x - 2.1 */
+ MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+ /* Cavium ThunderX, T81 pass 1.0 */
+ MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+ {},
+ };
+
+ for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+ if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+ r->rv_min, r->rv_max))
+ return false;
+ }
+
+ return true;
+}
+
asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
{
static char const chosen_str[] __initconst = "/chosen";
@@ -246,7 +269,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
u64 kaslr_seed = kaslr_early_init(fdt, chosen);
if (kaslr_seed && kaslr_requires_kpti())
- arm64_use_ng_mappings = true;
+ arm64_use_ng_mappings = ng_mappings_allowed();
kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
}
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index b198dde..edf1783 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -879,16 +879,19 @@ static u8 spectre_bhb_loop_affected(void)
static const struct midr_range spectre_bhb_k132_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+ {},
};
static const struct midr_range spectre_bhb_k38_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+ {},
};
static const struct midr_range spectre_bhb_k32_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
@@ -997,6 +1000,11 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
return true;
}
+u8 get_spectre_bhb_loop_value(void)
+{
+ return max_bhb_k;
+}
+
static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
{
const char *v = arm64_get_bp_hardening_vector(slot);
@@ -1014,7 +1022,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
isb();
}
-static bool __read_mostly __nospectre_bhb;
+bool __read_mostly __nospectre_bhb;
static int __init parse_spectre_bhb_param(char *str)
{
__nospectre_bhb = true;
@@ -1092,6 +1100,11 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
update_mitigation_state(&spectre_bhb_state, state);
}
+bool is_spectre_bhb_fw_mitigated(void)
+{
+ return test_bit(BHB_FW, &system_bhb_mitigations);
+}
+
/* Patched to NOP when enabled */
void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt,
__le32 *origptr,
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 68fec8c..19ca57d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2743,11 +2743,6 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
return irqchip_in_kernel(kvm);
}
-bool kvm_arch_has_irq_bypass(void)
-{
- return true;
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index b741ea6..96f625d 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -235,6 +235,8 @@ static inline void __deactivate_traps_mpam(void)
static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
{
+ struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
write_sysreg(1 << 15, hstr_el2);
@@ -245,11 +247,8 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
* EL1 instead of being trapped to EL2.
*/
if (system_supports_pmuv3()) {
- struct kvm_cpu_context *hctxt;
-
write_sysreg(0, pmselr_el0);
- hctxt = host_data_ptr(host_ctxt);
ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
@@ -269,6 +268,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
hcrx &= ~clr;
}
+ ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2);
write_sysreg_s(hcrx, SYS_HCRX_EL2);
}
@@ -278,19 +278,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
{
+ struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2);
write_sysreg(0, hstr_el2);
if (system_supports_pmuv3()) {
- struct kvm_cpu_context *hctxt;
-
- hctxt = host_data_ptr(host_ctxt);
write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0);
vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
}
if (cpus_have_final_cap(ARM64_HAS_HCX))
- write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
+ write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2);
__deactivate_traps_hfgxtr(vcpu);
__deactivate_traps_mpam();
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 2a5284f..e80f3eb 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -503,7 +503,7 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
{
int ret;
- if (!addr_is_memory(addr))
+ if (!range_is_memory(addr, addr + size))
return -EPERM;
ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index ed363aa..50aa8db 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void)
/*
* To check whether we have a MMIO-based (GICv2 compatible)
* CPU interface, we need to disable the system register
- * view. To do that safely, we have to prevent any interrupt
- * from firing (which would be deadly).
+ * view.
*
- * Note that this only makes sense on VHE, as interrupts are
- * already masked for nVHE as part of the exception entry to
- * EL2.
- */
- if (has_vhe())
- flags = local_daif_save();
-
- /*
* Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
* that to be able to set ICC_SRE_EL1.SRE to 0, all the
* interrupt overrides must be set. You've got to love this.
+ *
+ * As we always run VHE with HCR_xMO set, no extra xMO
+ * manipulation is required in that case.
+ *
+ * To safely disable SRE, we have to prevent any interrupt
+ * from firing (which would be deadly). This only makes sense
+ * on VHE, as interrupts are already masked for nVHE as part
+ * of the exception entry to EL2.
*/
- sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
- isb();
+ if (has_vhe()) {
+ flags = local_daif_save();
+ } else {
+ sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+ isb();
+ }
+
write_gicreg(0, ICC_SRE_EL1);
isb();
@@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void)
write_gicreg(sre, ICC_SRE_EL1);
isb();
- sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
- isb();
- if (has_vhe())
+ if (has_vhe()) {
local_daif_restore(flags);
+ } else {
+ sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+ isb();
+ }
val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
val |= read_gicreg(ICH_VTR_EL2);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 754f2fe..eeda923 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1501,6 +1501,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
+ if (!is_protected_kvm_enabled())
+ memcache = &vcpu->arch.mmu_page_cache;
+ else
+ memcache = &vcpu->arch.pkvm_memcache;
+
/*
* Permission faults just need to update the existing leaf entry,
* and so normally don't require allocations from the memcache. The
@@ -1510,13 +1515,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (!fault_is_perm || (logging_active && write_fault)) {
int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
- if (!is_protected_kvm_enabled()) {
- memcache = &vcpu->arch.mmu_page_cache;
+ if (!is_protected_kvm_enabled())
ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
- } else {
- memcache = &vcpu->arch.pkvm_memcache;
+ else
ret = topup_hyp_memcache(memcache, min_pages);
- }
+
if (ret)
return ret;
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 005ad28..5dde928 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1945,6 +1945,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
if ((hw_val & mpam_mask) == (user_val & mpam_mask))
user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
+ /* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */
+ if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) ||
+ !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) ||
+ (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val)))
+ return -EINVAL;
+
return set_id_reg(vcpu, rd, user_val);
}
diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c
index 9bef696..4e298ba 100644
--- a/arch/arm64/lib/insn.c
+++ b/arch/arm64/lib/insn.c
@@ -5,6 +5,7 @@
*
* Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
*/
+#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <linux/bug.h>
#include <linux/printk.h>
@@ -1500,43 +1501,41 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm);
}
+static u32 __get_barrier_crm_val(enum aarch64_insn_mb_type type)
+{
+ switch (type) {
+ case AARCH64_INSN_MB_SY:
+ return 0xf;
+ case AARCH64_INSN_MB_ST:
+ return 0xe;
+ case AARCH64_INSN_MB_LD:
+ return 0xd;
+ case AARCH64_INSN_MB_ISH:
+ return 0xb;
+ case AARCH64_INSN_MB_ISHST:
+ return 0xa;
+ case AARCH64_INSN_MB_ISHLD:
+ return 0x9;
+ case AARCH64_INSN_MB_NSH:
+ return 0x7;
+ case AARCH64_INSN_MB_NSHST:
+ return 0x6;
+ case AARCH64_INSN_MB_NSHLD:
+ return 0x5;
+ default:
+ pr_err("%s: unknown barrier type %d\n", __func__, type);
+ return AARCH64_BREAK_FAULT;
+ }
+}
+
u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
{
u32 opt;
u32 insn;
- switch (type) {
- case AARCH64_INSN_MB_SY:
- opt = 0xf;
- break;
- case AARCH64_INSN_MB_ST:
- opt = 0xe;
- break;
- case AARCH64_INSN_MB_LD:
- opt = 0xd;
- break;
- case AARCH64_INSN_MB_ISH:
- opt = 0xb;
- break;
- case AARCH64_INSN_MB_ISHST:
- opt = 0xa;
- break;
- case AARCH64_INSN_MB_ISHLD:
- opt = 0x9;
- break;
- case AARCH64_INSN_MB_NSH:
- opt = 0x7;
- break;
- case AARCH64_INSN_MB_NSHST:
- opt = 0x6;
- break;
- case AARCH64_INSN_MB_NSHLD:
- opt = 0x5;
- break;
- default:
- pr_err("%s: unknown dmb type %d\n", __func__, type);
+ opt = __get_barrier_crm_val(type);
+ if (opt == AARCH64_BREAK_FAULT)
return AARCH64_BREAK_FAULT;
- }
insn = aarch64_insn_get_dmb_value();
insn &= ~GENMASK(11, 8);
@@ -1545,6 +1544,21 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
return insn;
}
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type)
+{
+ u32 opt, insn;
+
+ opt = __get_barrier_crm_val(type);
+ if (opt == AARCH64_BREAK_FAULT)
+ return AARCH64_BREAK_FAULT;
+
+ insn = aarch64_insn_get_dsb_base_value();
+ insn &= ~GENMASK(11, 8);
+ insn |= (opt << 8);
+
+ return insn;
+}
+
u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
enum aarch64_insn_system_register sysreg)
{
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 70d7c89..634d784 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -7,6 +7,7 @@
#define pr_fmt(fmt) "bpf_jit: " fmt
+#include <linux/arm-smccc.h>
#include <linux/bitfield.h>
#include <linux/bpf.h>
#include <linux/filter.h>
@@ -17,6 +18,7 @@
#include <asm/asm-extable.h>
#include <asm/byteorder.h>
#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
#include <asm/insn.h>
#include <asm/text-patching.h>
@@ -939,7 +941,51 @@ static void build_plt(struct jit_ctx *ctx)
plt->target = (u64)&dummy_tramp;
}
-static void build_epilogue(struct jit_ctx *ctx)
+/* Clobbers BPF registers 1-4, aka x0-x3 */
+static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx)
+{
+ const u8 r1 = bpf2a64[BPF_REG_1]; /* aka x0 */
+ u8 k = get_spectre_bhb_loop_value();
+
+ if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) ||
+ cpu_mitigations_off() || __nospectre_bhb ||
+ arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE)
+ return;
+
+ if (capable(CAP_SYS_ADMIN))
+ return;
+
+ if (supports_clearbhb(SCOPE_SYSTEM)) {
+ emit(aarch64_insn_gen_hint(AARCH64_INSN_HINT_CLEARBHB), ctx);
+ return;
+ }
+
+ if (k) {
+ emit_a64_mov_i64(r1, k, ctx);
+ emit(A64_B(1), ctx);
+ emit(A64_SUBS_I(true, r1, r1, 1), ctx);
+ emit(A64_B_(A64_COND_NE, -2), ctx);
+ emit(aarch64_insn_gen_dsb(AARCH64_INSN_MB_ISH), ctx);
+ emit(aarch64_insn_get_isb_value(), ctx);
+ }
+
+ if (is_spectre_bhb_fw_mitigated()) {
+ emit(A64_ORR_I(false, r1, AARCH64_INSN_REG_ZR,
+ ARM_SMCCC_ARCH_WORKAROUND_3), ctx);
+ switch (arm_smccc_1_1_get_conduit()) {
+ case SMCCC_CONDUIT_HVC:
+ emit(aarch64_insn_get_hvc_value(), ctx);
+ break;
+ case SMCCC_CONDUIT_SMC:
+ emit(aarch64_insn_get_smc_value(), ctx);
+ break;
+ default:
+ pr_err_once("Firmware mitigation enabled with unknown conduit\n");
+ }
+ }
+}
+
+static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
{
const u8 r0 = bpf2a64[BPF_REG_0];
const u8 ptr = bpf2a64[TCCNT_PTR];
@@ -952,10 +998,13 @@ static void build_epilogue(struct jit_ctx *ctx)
emit(A64_POP(A64_ZR, ptr, A64_SP), ctx);
+ if (was_classic)
+ build_bhb_mitigation(ctx);
+
/* Restore FP/LR registers */
emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
- /* Set return value */
+ /* Move the return value from bpf:r0 (aka x7) to x0 */
emit(A64_MOV(1, A64_R(0), r0), ctx);
/* Authenticate lr */
@@ -1898,7 +1947,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
}
ctx.epilogue_offset = ctx.idx;
- build_epilogue(&ctx);
+ build_epilogue(&ctx, was_classic);
build_plt(&ctx);
extable_align = __alignof__(struct exception_table_entry);
@@ -1961,7 +2010,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
goto out_free_hdr;
}
- build_epilogue(&ctx);
+ build_epilogue(&ctx, was_classic);
build_plt(&ctx);
/* Extra pass to validate JITed code. */
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 067c0b9..1a2cf01 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -73,6 +73,7 @@
select ARCH_SUPPORTS_RT
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF
+ select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_DEFAULT_BPF_JIT
diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h
index 3177674..45514f3 100644
--- a/arch/loongarch/include/asm/fpu.h
+++ b/arch/loongarch/include/asm/fpu.h
@@ -22,22 +22,29 @@
struct sigcontext;
#define kernel_fpu_available() cpu_has_fpu
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
-extern void _init_fpu(unsigned int);
-extern void _save_fp(struct loongarch_fpu *);
-extern void _restore_fp(struct loongarch_fpu *);
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
-extern void _save_lsx(struct loongarch_fpu *fpu);
-extern void _restore_lsx(struct loongarch_fpu *fpu);
-extern void _init_lsx_upper(void);
-extern void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage void _init_fpu(unsigned int);
+asmlinkage void _save_fp(struct loongarch_fpu *);
+asmlinkage void _restore_fp(struct loongarch_fpu *);
+asmlinkage int _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+asmlinkage int _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern void _save_lasx(struct loongarch_fpu *fpu);
-extern void _restore_lasx(struct loongarch_fpu *fpu);
-extern void _init_lasx_upper(void);
-extern void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage void _save_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lsx_upper(void);
+asmlinkage void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+
+asmlinkage void _save_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lasx_upper(void);
+asmlinkage void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
static inline void enable_lsx(void);
static inline void disable_lsx(void);
diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h
index e671978..3856657 100644
--- a/arch/loongarch/include/asm/lbt.h
+++ b/arch/loongarch/include/asm/lbt.h
@@ -12,9 +12,13 @@
#include <asm/loongarch.h>
#include <asm/processor.h>
-extern void _init_lbt(void);
-extern void _save_lbt(struct loongarch_lbt *);
-extern void _restore_lbt(struct loongarch_lbt *);
+asmlinkage void _init_lbt(void);
+asmlinkage void _save_lbt(struct loongarch_lbt *);
+asmlinkage void _restore_lbt(struct loongarch_lbt *);
+asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _save_ftop_context(void __user *ftop);
+asmlinkage int _restore_ftop_context(void __user *ftop);
static inline int is_lbt_enabled(void)
{
diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h
index f3ddaed..e5d21e8 100644
--- a/arch/loongarch/include/asm/ptrace.h
+++ b/arch/loongarch/include/asm/ptrace.h
@@ -33,9 +33,9 @@ struct pt_regs {
unsigned long __last[];
} __aligned(8);
-static inline int regs_irqs_disabled(struct pt_regs *regs)
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
{
- return arch_irqs_disabled_flags(regs->csr_prmd);
+ return !(regs->csr_prmd & CSR_PRMD_PIE);
}
static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
@@ -55,7 +55,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long v
/* Query offset/name of register from its name/offset */
extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last) - sizeof(unsigned long))
/**
* regs_get_register() - get register value from its offset
diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h
index 99a0d19..025fc3f 100644
--- a/arch/loongarch/include/asm/uprobes.h
+++ b/arch/loongarch/include/asm/uprobes.h
@@ -15,7 +15,6 @@ typedef u32 uprobe_opcode_t;
#define UPROBE_XOLBP_INSN __emit_break(BRK_UPROBE_XOLBP)
struct arch_uprobe {
- unsigned long resume_era;
u32 insn[2];
u32 ixol[2];
bool simulate;
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4853e8b..f9dcaa6 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -21,10 +21,10 @@
obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o
-CFLAGS_module.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_traps.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_module.o += $(call cc-disable-warning, override-init)
+CFLAGS_syscall.o += $(call cc-disable-warning, override-init)
+CFLAGS_traps.o += $(call cc-disable-warning, override-init)
+CFLAGS_perf_event.o += $(call cc-disable-warning, override-init)
ifdef CONFIG_FUNCTION_TRACER
ifndef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 6ab6401..28caf41 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -458,6 +458,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_fp_context)
+EXPORT_SYMBOL_GPL(_save_fp_context)
/*
* a0: fpregs
@@ -471,6 +472,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_fp_context)
+EXPORT_SYMBOL_GPL(_restore_fp_context)
/*
* a0: fpregs
@@ -484,6 +486,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_lsx_context)
+EXPORT_SYMBOL_GPL(_save_lsx_context)
/*
* a0: fpregs
@@ -497,6 +500,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_lsx_context)
+EXPORT_SYMBOL_GPL(_restore_lsx_context)
/*
* a0: fpregs
@@ -510,6 +514,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_lasx_context)
+EXPORT_SYMBOL_GPL(_save_lasx_context)
/*
* a0: fpregs
@@ -523,6 +528,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_lasx_context)
+EXPORT_SYMBOL_GPL(_restore_lasx_context)
.L_fpu_fault:
li.w a0, -EFAULT # failure
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 4f09121..733a766 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -16,6 +16,7 @@
#include <asm/stackframe.h>
#include <asm/thread_info.h>
+ .section .cpuidle.text, "ax"
.align 5
SYM_FUNC_START(__arch_cpu_idle)
/* start of idle interrupt region */
@@ -31,14 +32,16 @@
*/
idle 0
/* end of idle interrupt region */
-1: jr ra
+idle_exit:
+ jr ra
SYM_FUNC_END(__arch_cpu_idle)
+ .previous
SYM_CODE_START(handle_vint)
UNWIND_HINT_UNDEFINED
BACKUP_T0T1
SAVE_ALL
- la_abs t1, 1b
+ la_abs t1, idle_exit
LONG_L t0, sp, PT_ERA
/* 3 instructions idle interrupt region */
ori t0, t0, 0b1100
diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c
index ec5b28e..4c47690 100644
--- a/arch/loongarch/kernel/kfpu.c
+++ b/arch/loongarch/kernel/kfpu.c
@@ -18,11 +18,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN;
static DEFINE_PER_CPU(bool, in_kernel_fpu);
static DEFINE_PER_CPU(unsigned int, euen_current);
+static inline void fpregs_lock(void)
+{
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
+ else
+ local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
+ else
+ local_bh_enable();
+}
+
void kernel_fpu_begin(void)
{
unsigned int *euen_curr;
- preempt_disable();
+ if (!irqs_disabled())
+ fpregs_lock();
WARN_ON(this_cpu_read(in_kernel_fpu));
@@ -73,7 +90,8 @@ void kernel_fpu_end(void)
this_cpu_write(in_kernel_fpu, false);
- preempt_enable();
+ if (!irqs_disabled())
+ fpregs_unlock();
}
EXPORT_SYMBOL_GPL(kernel_fpu_end);
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
index 001f061d..7167891 100644
--- a/arch/loongarch/kernel/lbt.S
+++ b/arch/loongarch/kernel/lbt.S
@@ -90,6 +90,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_lbt_context)
+EXPORT_SYMBOL_GPL(_save_lbt_context)
/*
* a0: scr
@@ -110,6 +111,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_lbt_context)
+EXPORT_SYMBOL_GPL(_restore_lbt_context)
/*
* a0: ftop
@@ -120,6 +122,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_save_ftop_context)
+EXPORT_SYMBOL_GPL(_save_ftop_context)
/*
* a0: ftop
@@ -150,6 +153,7 @@
li.w a0, 0 # success
jr ra
SYM_FUNC_END(_restore_ftop_context)
+EXPORT_SYMBOL_GPL(_restore_ftop_context)
.L_lbt_fault:
li.w a0, -EFAULT # failure
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 7a555b6..4740cb5 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -51,27 +51,6 @@
#define lock_lbt_owner() ({ preempt_disable(); pagefault_disable(); })
#define unlock_lbt_owner() ({ pagefault_enable(); preempt_enable(); })
-/* Assembly functions to move context to/from the FPU */
-extern asmlinkage int
-_save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-
-#ifdef CONFIG_CPU_HAS_LBT
-extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _save_ftop_context(void __user *ftop);
-extern asmlinkage int _restore_ftop_context(void __user *ftop);
-#endif
-
struct rt_sigframe {
struct siginfo rs_info;
struct ucontext rs_uctx;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index e2d3bfe..bc75a3a 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -111,7 +111,7 @@ static unsigned long __init get_loops_per_jiffy(void)
return lpj;
}
-static long init_offset __nosavedata;
+static long init_offset;
void save_counter(void)
{
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 2ec3106..47fc2de 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -553,9 +553,10 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
die_if_kernel("Kernel ale access", regs);
force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
#else
+ bool pie = regs_irqs_disabled(regs);
unsigned int *pc;
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
@@ -582,7 +583,7 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
die_if_kernel("Kernel ale access", regs);
force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
#endif
irqentry_exit(regs, state);
@@ -621,12 +622,13 @@ static void bug_handler(struct pt_regs *regs)
asmlinkage void noinstr do_bce(struct pt_regs *regs)
{
bool user = user_mode(regs);
+ bool pie = regs_irqs_disabled(regs);
unsigned long era = exception_era(regs);
u64 badv = 0, lower = 0, upper = ULONG_MAX;
union loongarch_instruction insn;
irqentry_state_t state = irqentry_enter(regs);
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
current->thread.trap_nr = read_csr_excode();
@@ -692,7 +694,7 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs)
force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper);
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
irqentry_exit(regs, state);
@@ -710,11 +712,12 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs)
asmlinkage void noinstr do_bp(struct pt_regs *regs)
{
bool user = user_mode(regs);
+ bool pie = regs_irqs_disabled(regs);
unsigned int opcode, bcode;
unsigned long era = exception_era(regs);
irqentry_state_t state = irqentry_enter(regs);
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
if (__get_inst(&opcode, (u32 *)era, user))
@@ -780,7 +783,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
}
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
irqentry_exit(regs, state);
@@ -1015,6 +1018,7 @@ static void init_restore_lbt(void)
asmlinkage void noinstr do_lbt(struct pt_regs *regs)
{
+ bool pie = regs_irqs_disabled(regs);
irqentry_state_t state = irqentry_enter(regs);
/*
@@ -1024,7 +1028,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
* (including the user using 'MOVGR2GCSR' to turn on TM, which
* will not trigger the BTE), we need to check PRMD first.
*/
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_enable();
if (!cpu_has_lbt) {
@@ -1038,7 +1042,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
preempt_enable();
out:
- if (regs->csr_prmd & CSR_PRMD_PIE)
+ if (!pie)
local_irq_disable();
irqentry_exit(regs, state);
diff --git a/arch/loongarch/kernel/uprobes.c b/arch/loongarch/kernel/uprobes.c
index 87abc71..6022eb0 100644
--- a/arch/loongarch/kernel/uprobes.c
+++ b/arch/loongarch/kernel/uprobes.c
@@ -42,7 +42,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
utask->autask.saved_trap_nr = current->thread.trap_nr;
current->thread.trap_nr = UPROBE_TRAP_NR;
instruction_pointer_set(regs, utask->xol_vaddr);
- user_enable_single_step(current);
return 0;
}
@@ -53,13 +52,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR);
current->thread.trap_nr = utask->autask.saved_trap_nr;
-
- if (auprobe->simulate)
- instruction_pointer_set(regs, auprobe->resume_era);
- else
- instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
-
- user_disable_single_step(current);
+ instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
return 0;
}
@@ -70,7 +63,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
current->thread.trap_nr = utask->autask.saved_trap_nr;
instruction_pointer_set(regs, utask->vaddr);
- user_disable_single_step(current);
}
bool arch_uprobe_xol_was_trapped(struct task_struct *t)
@@ -90,7 +82,6 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
insn.word = auprobe->insn[0];
arch_simulate_insn(insn, regs);
- auprobe->resume_era = regs->csr_era;
return true;
}
diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile
index f4c8e35..cb41d92 100644
--- a/arch/loongarch/kvm/Makefile
+++ b/arch/loongarch/kvm/Makefile
@@ -21,4 +21,4 @@
kvm-y += intc/pch_pic.o
kvm-y += irqfd.o
-CFLAGS_exit.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_exit.o += $(call cc-disable-warning, override-init)
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index 93f4acd..fe734dc 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -111,7 +111,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (unlikely(ret)) {
- kvm_err("%s: : read date from addr %llx failed\n", __func__, addr);
+ kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
return ret;
}
/* Construct the mask by scanning the bit 27-30 */
@@ -127,7 +127,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (unlikely(ret))
- kvm_err("%s: : write date to addr %llx failed\n", __func__, addr);
+ kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
return ret;
}
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index d165cd3..80ea63d 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -296,10 +296,10 @@ int kvm_arch_enable_virtualization_cpu(void)
/*
* Enable virtualization features granting guest direct control of
* certain features:
- * GCI=2: Trap on init or unimplement cache instruction.
+ * GCI=2: Trap on init or unimplemented cache instruction.
* TORU=0: Trap on Root Unimplement.
* CACTRL=1: Root control cache.
- * TOP=0: Trap on Previlege.
+ * TOP=0: Trap on Privilege.
* TOE=0: Trap on Exception.
* TIT=0: Trap on Timer.
*/
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 8e427b3..5af32ec 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -294,6 +294,7 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) {
+ kvm_lose_pmu(vcpu);
/* make sure the vcpu mode has been written */
smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE);
local_irq_enable();
@@ -902,6 +903,13 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
vcpu->arch.st.guest_addr = 0;
memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+
+ /*
+ * When vCPU reset, clear the ESTAT and GINTC registers
+ * Other CSR registers are cleared with function _kvm_setcsr().
+ */
+ kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_GINTC, 0);
+ kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_ESTAT, 0);
break;
default:
ret = -EINVAL;
diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c
index e406890..cea84d7f 100644
--- a/arch/loongarch/mm/hugetlbpage.c
+++ b/arch/loongarch/mm/hugetlbpage.c
@@ -47,7 +47,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
pmd = pmd_offset(pud, addr);
}
}
- return (pte_t *) pmd;
+ return pmd_none(pmdp_get(pmd)) ? NULL : (pte_t *) pmd;
}
uint64_t pmd_to_entrylo(unsigned long pmd_val)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index fdb7f73..06f11d9 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -65,9 +65,6 @@ void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
-#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
#ifdef CONFIG_ZONE_DMA32
max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
#endif
diff --git a/arch/loongarch/power/hibernate.c b/arch/loongarch/power/hibernate.c
index 1e05905..e7b7346 100644
--- a/arch/loongarch/power/hibernate.c
+++ b/arch/loongarch/power/hibernate.c
@@ -2,6 +2,7 @@
#include <asm/fpu.h>
#include <asm/loongson.h>
#include <asm/sections.h>
+#include <asm/time.h>
#include <asm/tlbflush.h>
#include <linux/suspend.h>
@@ -14,6 +15,7 @@ struct pt_regs saved_regs;
void save_processor_state(void)
{
+ save_counter();
saved_crmd = csr_read32(LOONGARCH_CSR_CRMD);
saved_prmd = csr_read32(LOONGARCH_CSR_PRMD);
saved_euen = csr_read32(LOONGARCH_CSR_EUEN);
@@ -26,6 +28,7 @@ void save_processor_state(void)
void restore_processor_state(void)
{
+ sync_counter();
csr_write32(saved_crmd, LOONGARCH_CSR_CRMD);
csr_write32(saved_prmd, LOONGARCH_CSR_PRMD);
csr_write32(saved_euen, LOONGARCH_CSR_EUEN);
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index 0992cad..c7d7580 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -6,11 +6,10 @@
#include <linux/linkage.h>
extern void (*cpu_wait)(void);
-extern void r4k_wait(void);
-extern asmlinkage void __r4k_wait(void);
+extern asmlinkage void r4k_wait(void);
extern void r4k_wait_irqoff(void);
-static inline int using_rollback_handler(void)
+static inline int using_skipover_handler(void)
{
return cpu_wait == r4k_wait;
}
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 85fa996..ef72c46 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
/* Query offset/name of register from its name/offset */
extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET \
+ (offsetof(struct pt_regs, __last) - sizeof(unsigned long))
/**
* regs_get_register() - get register value from its offset
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a572ce3..08c0a01 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -104,48 +104,59 @@
__FINIT
- .align 5 /* 32 byte rollback region */
-LEAF(__r4k_wait)
- .set push
- .set noreorder
- /* start of rollback region */
- LONG_L t0, TI_FLAGS($28)
- nop
- andi t0, _TIF_NEED_RESCHED
- bnez t0, 1f
- nop
- nop
- nop
-#ifdef CONFIG_CPU_MICROMIPS
- nop
- nop
- nop
- nop
-#endif
+ .section .cpuidle.text,"ax"
+ /* Align to 32 bytes for the maximum idle interrupt region size. */
+ .align 5
+LEAF(r4k_wait)
+ /* Keep the ISA bit clear for calculations on local labels here. */
+0: .fill 0
+ /* Start of idle interrupt region. */
+ local_irq_enable
+ /*
+ * If an interrupt lands here, before going idle on the next
+ * instruction, we must *NOT* go idle since the interrupt could
+ * have set TIF_NEED_RESCHED or caused a timer to need resched.
+ * Fall through -- see skipover_handler below -- and have the
+ * idle loop take care of things.
+ */
+1: .fill 0
+ /* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up. */
+ .if 1b - 0b > 32
+ .error "overlong idle interrupt region"
+ .elseif 1b - 0b > 8
+ .align 4
+ .endif
+2: .fill 0
+ .equ r4k_wait_idle_size, 2b - 0b
+ /* End of idle interrupt region; size has to be a power of 2. */
.set MIPS_ISA_ARCH_LEVEL_RAW
+r4k_wait_insn:
wait
- /* end of rollback region (the region size must be power of two) */
-1:
+r4k_wait_exit:
+ .set mips0
+ local_irq_disable
jr ra
- nop
- .set pop
- END(__r4k_wait)
+ END(r4k_wait)
+ .previous
- .macro BUILD_ROLLBACK_PROLOGUE handler
- FEXPORT(rollback_\handler)
+ .macro BUILD_SKIPOVER_PROLOGUE handler
+ FEXPORT(skipover_\handler)
.set push
.set noat
MFC0 k0, CP0_EPC
- PTR_LA k1, __r4k_wait
- ori k0, 0x1f /* 32 byte rollback region */
- xori k0, 0x1f
+ /* Subtract/add 2 to let the ISA bit propagate through the mask. */
+ PTR_LA k1, r4k_wait_insn - 2
+ ori k0, r4k_wait_idle_size - 2
+ .set noreorder
bne k0, k1, \handler
+ PTR_ADDIU k0, r4k_wait_exit - r4k_wait_insn + 2
+ .set reorder
MTC0 k0, CP0_EPC
.set pop
.endm
.align 5
-BUILD_ROLLBACK_PROLOGUE handle_int
+BUILD_SKIPOVER_PROLOGUE handle_int
NESTED(handle_int, PT_SIZE, sp)
.cfi_signal_frame
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -265,7 +276,7 @@
* This prototype is copied to ebase + n*IntCtl.VS and patched
* to invoke the handler
*/
-BUILD_ROLLBACK_PROLOGUE except_vec_vi
+BUILD_SKIPOVER_PROLOGUE except_vec_vi
NESTED(except_vec_vi, 0, sp)
SAVE_SOME docfi=1
SAVE_AT docfi=1
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 5abc8b7..80e8a04a 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void)
write_c0_conf(cfg | R30XX_CONF_HALT);
}
-void __cpuidle r4k_wait(void)
-{
- raw_local_irq_enable();
- __r4k_wait();
- raw_local_irq_disable();
-}
-
/*
* This variant is preferable as it allows testing need_resched and going to
* sleep depending on the outcome atomically. Unfortunately the "It is
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e85bd08..cc26d56 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -332,6 +332,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
mips_cps_cluster_bootcfg = kcalloc(nclusters,
sizeof(*mips_cps_cluster_bootcfg),
GFP_KERNEL);
+ if (!mips_cps_cluster_bootcfg)
+ goto err_out;
if (nclusters > 1)
mips_cm_update_property();
@@ -348,6 +350,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
mips_cps_cluster_bootcfg[cl].core_power =
kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long),
GFP_KERNEL);
+ if (!mips_cps_cluster_bootcfg[cl].core_power)
+ goto err_out;
/* Allocate VPE boot configuration structs */
for (c = 0; c < ncores; c++) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 39e248d0..8ec1e18 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -77,7 +77,7 @@
#include "access-helper.h"
extern void check_wait(void);
-extern asmlinkage void rollback_handle_int(void);
+extern asmlinkage void skipover_handle_int(void);
extern asmlinkage void handle_int(void);
extern asmlinkage void handle_adel(void);
extern asmlinkage void handle_ades(void);
@@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
{
extern const u8 except_vec_vi[];
extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
- extern const u8 rollback_except_vec_vi[];
+ extern const u8 skipover_except_vec_vi[];
unsigned long handler;
unsigned long old_handler = vi_handlers[n];
int srssets = current_cpu_data.srsets;
@@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
change_c0_srsmap(0xf << n*4, 0 << n*4);
}
- vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+ vec_start = using_skipover_handler() ? skipover_except_vec_vi :
except_vec_vi;
#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
ori_offset = except_vec_vi_ori - vec_start + 2;
@@ -2426,8 +2426,8 @@ void __init trap_init(void)
if (board_be_init)
board_be_init();
- set_except_vector(EXCCODE_INT, using_rollback_handler() ?
- rollback_handle_int : handle_int);
+ set_except_vector(EXCCODE_INT, using_skipover_handler() ?
+ skipover_handle_int : handle_int);
set_except_vector(EXCCODE_MOD, handle_tlbm);
set_except_vector(EXCCODE_TLBL, handle_tlbl);
set_except_vector(EXCCODE_TLBS, handle_tlbs);
diff --git a/arch/openrisc/include/asm/cacheflush.h b/arch/openrisc/include/asm/cacheflush.h
index 984c331..0e60af4 100644
--- a/arch/openrisc/include/asm/cacheflush.h
+++ b/arch/openrisc/include/asm/cacheflush.h
@@ -23,6 +23,9 @@
*/
extern void local_dcache_page_flush(struct page *page);
extern void local_icache_page_inv(struct page *page);
+extern void local_dcache_range_flush(unsigned long start, unsigned long end);
+extern void local_dcache_range_inv(unsigned long start, unsigned long end);
+extern void local_icache_range_inv(unsigned long start, unsigned long end);
/*
* Data cache flushing always happen on the local cpu. Instruction cache
@@ -39,6 +42,20 @@ extern void smp_icache_page_inv(struct page *page);
#endif /* CONFIG_SMP */
/*
+ * Even if the actual block size is larger than L1_CACHE_BYTES, paddr
+ * can be incremented by L1_CACHE_BYTES. When paddr is written to the
+ * invalidate register, the entire cache line encompassing this address
+ * is invalidated. Each subsequent reference to the same cache line will
+ * not affect the invalidation process.
+ */
+#define local_dcache_block_flush(addr) \
+ local_dcache_range_flush(addr, addr + L1_CACHE_BYTES)
+#define local_dcache_block_inv(addr) \
+ local_dcache_range_inv(addr, addr + L1_CACHE_BYTES)
+#define local_icache_block_inv(addr) \
+ local_icache_range_inv(addr, addr + L1_CACHE_BYTES)
+
+/*
* Synchronizes caches. Whenever a cpu writes executable code to memory, this
* should be called to make sure the processor sees the newly written code.
*/
diff --git a/arch/openrisc/include/asm/cpuinfo.h b/arch/openrisc/include/asm/cpuinfo.h
index 5e47441..3cfc4cf 100644
--- a/arch/openrisc/include/asm/cpuinfo.h
+++ b/arch/openrisc/include/asm/cpuinfo.h
@@ -15,16 +15,21 @@
#ifndef __ASM_OPENRISC_CPUINFO_H
#define __ASM_OPENRISC_CPUINFO_H
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+struct cache_desc {
+ u32 size;
+ u32 sets;
+ u32 block_size;
+ u32 ways;
+};
+
struct cpuinfo_or1k {
u32 clock_frequency;
- u32 icache_size;
- u32 icache_block_size;
- u32 icache_ways;
-
- u32 dcache_size;
- u32 dcache_block_size;
- u32 dcache_ways;
+ struct cache_desc icache;
+ struct cache_desc dcache;
u16 coreid;
};
@@ -32,4 +37,9 @@ struct cpuinfo_or1k {
extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
extern void setup_cpuinfo(void);
+/*
+ * Check if the cache component exists.
+ */
+extern bool cpu_cache_is_present(const unsigned int cache_type);
+
#endif /* __ASM_OPENRISC_CPUINFO_H */
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index 7912916..e4c7d9b 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -7,7 +7,7 @@
obj-y := head.o setup.o or32_ksyms.o process.o dma.o \
traps.o time.o irq.o entry.o ptrace.o signal.o \
- sys_call_table.o unwinder.o
+ sys_call_table.o unwinder.o cacheinfo.o
obj-$(CONFIG_SMP) += smp.o sync-timer.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
diff --git a/arch/openrisc/kernel/cacheinfo.c b/arch/openrisc/kernel/cacheinfo.c
new file mode 100644
index 0000000..6123054
--- /dev/null
+++ b/arch/openrisc/kernel/cacheinfo.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * OpenRISC cacheinfo support
+ *
+ * Based on work done for MIPS and LoongArch. All original copyrights
+ * apply as per the original source declaration.
+ *
+ * OpenRISC implementation:
+ * Copyright (C) 2025 Sahil Siddiq <sahilcdq@proton.me>
+ */
+
+#include <linux/cacheinfo.h>
+#include <asm/cpuinfo.h>
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+static inline void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+ unsigned int level, struct cache_desc *cache, int cpu)
+{
+ this_leaf->type = type;
+ this_leaf->level = level;
+ this_leaf->coherency_line_size = cache->block_size;
+ this_leaf->number_of_sets = cache->sets;
+ this_leaf->ways_of_associativity = cache->ways;
+ this_leaf->size = cache->size;
+ cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+}
+
+int init_cache_level(unsigned int cpu)
+{
+ struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ int leaves = 0, levels = 0;
+ unsigned long upr = mfspr(SPR_UPR);
+ unsigned long iccfgr, dccfgr;
+
+ if (!(upr & SPR_UPR_UP)) {
+ printk(KERN_INFO
+ "-- no UPR register... unable to detect configuration\n");
+ return -ENOENT;
+ }
+
+ if (cpu_cache_is_present(SPR_UPR_DCP)) {
+ dccfgr = mfspr(SPR_DCCFGR);
+ cpuinfo->dcache.ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+ cpuinfo->dcache.sets = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
+ cpuinfo->dcache.block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+ cpuinfo->dcache.size =
+ cpuinfo->dcache.sets * cpuinfo->dcache.ways * cpuinfo->dcache.block_size;
+ leaves += 1;
+ printk(KERN_INFO
+ "-- dcache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+ cpuinfo->dcache.size, cpuinfo->dcache.block_size,
+ cpuinfo->dcache.sets, cpuinfo->dcache.ways);
+ } else
+ printk(KERN_INFO "-- dcache disabled\n");
+
+ if (cpu_cache_is_present(SPR_UPR_ICP)) {
+ iccfgr = mfspr(SPR_ICCFGR);
+ cpuinfo->icache.ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+ cpuinfo->icache.sets = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
+ cpuinfo->icache.block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+ cpuinfo->icache.size =
+ cpuinfo->icache.sets * cpuinfo->icache.ways * cpuinfo->icache.block_size;
+ leaves += 1;
+ printk(KERN_INFO
+ "-- icache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+ cpuinfo->icache.size, cpuinfo->icache.block_size,
+ cpuinfo->icache.sets, cpuinfo->icache.ways);
+ } else
+ printk(KERN_INFO "-- icache disabled\n");
+
+ if (!leaves)
+ return -ENOENT;
+
+ levels = 1;
+
+ this_cpu_ci->num_leaves = leaves;
+ this_cpu_ci->num_levels = levels;
+
+ return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+ struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+ int level = 1;
+
+ if (cpu_cache_is_present(SPR_UPR_DCP)) {
+ ci_leaf_init(this_leaf, CACHE_TYPE_DATA, level, &cpuinfo->dcache, cpu);
+ this_leaf->attributes = ((mfspr(SPR_DCCFGR) & SPR_DCCFGR_CWS) >> 8) ?
+ CACHE_WRITE_BACK : CACHE_WRITE_THROUGH;
+ this_leaf++;
+ }
+
+ if (cpu_cache_is_present(SPR_UPR_ICP))
+ ci_leaf_init(this_leaf, CACHE_TYPE_INST, level, &cpuinfo->icache, cpu);
+
+ this_cpu_ci->cpu_map_populated = true;
+
+ return 0;
+}
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index b3edbb3..3a7b5ba 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -17,6 +17,7 @@
#include <linux/pagewalk.h>
#include <asm/cpuinfo.h>
+#include <asm/cacheflush.h>
#include <asm/spr_defs.h>
#include <asm/tlbflush.h>
@@ -24,9 +25,6 @@ static int
page_set_nocache(pte_t *pte, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
- unsigned long cl;
- struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
pte_val(*pte) |= _PAGE_CI;
/*
@@ -36,8 +34,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
/* Flush page out of dcache */
- for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
- mtspr(SPR_DCBFR, cl);
+ local_dcache_range_flush(__pa(addr), __pa(next));
return 0;
}
@@ -98,21 +95,14 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
enum dma_data_direction dir)
{
- unsigned long cl;
- struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
switch (dir) {
case DMA_TO_DEVICE:
/* Flush the dcache for the requested range */
- for (cl = addr; cl < addr + size;
- cl += cpuinfo->dcache_block_size)
- mtspr(SPR_DCBFR, cl);
+ local_dcache_range_flush(addr, addr + size);
break;
case DMA_FROM_DEVICE:
/* Invalidate the dcache for the requested range */
- for (cl = addr; cl < addr + size;
- cl += cpuinfo->dcache_block_size)
- mtspr(SPR_DCBIR, cl);
+ local_dcache_range_inv(addr, addr + size);
break;
default:
/*
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index be56eaa..a9fb9cc 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -113,21 +113,6 @@ static void print_cpuinfo(void)
return;
}
- if (upr & SPR_UPR_DCP)
- printk(KERN_INFO
- "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
- cpuinfo->dcache_size, cpuinfo->dcache_block_size,
- cpuinfo->dcache_ways);
- else
- printk(KERN_INFO "-- dcache disabled\n");
- if (upr & SPR_UPR_ICP)
- printk(KERN_INFO
- "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
- cpuinfo->icache_size, cpuinfo->icache_block_size,
- cpuinfo->icache_ways);
- else
- printk(KERN_INFO "-- icache disabled\n");
-
if (upr & SPR_UPR_DMP)
printk(KERN_INFO "-- dmmu: %4d entries, %lu way(s)\n",
1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
@@ -155,8 +140,6 @@ static void print_cpuinfo(void)
void __init setup_cpuinfo(void)
{
struct device_node *cpu;
- unsigned long iccfgr, dccfgr;
- unsigned long cache_set_size;
int cpu_id = smp_processor_id();
struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
@@ -164,20 +147,6 @@ void __init setup_cpuinfo(void)
if (!cpu)
panic("Couldn't find CPU%d in device tree...\n", cpu_id);
- iccfgr = mfspr(SPR_ICCFGR);
- cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
- cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
- cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
- cpuinfo->icache_size =
- cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
-
- dccfgr = mfspr(SPR_DCCFGR);
- cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
- cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
- cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
- cpuinfo->dcache_size =
- cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
-
if (of_property_read_u32(cpu, "clock-frequency",
&cpuinfo->clock_frequency)) {
printk(KERN_WARNING
@@ -294,14 +263,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
unsigned int vr, cpucfgr;
unsigned int avr;
unsigned int version;
+#ifdef CONFIG_SMP
struct cpuinfo_or1k *cpuinfo = v;
+ seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
vr = mfspr(SPR_VR);
cpucfgr = mfspr(SPR_CPUCFGR);
-#ifdef CONFIG_SMP
- seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
-#endif
if (vr & SPR_VR_UVRP) {
vr = mfspr(SPR_VR2);
version = vr & SPR_VR2_VER;
@@ -320,14 +289,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
}
seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
- seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
- seq_printf(m, "dcache block size\t: %d bytes\n",
- cpuinfo->dcache_block_size);
- seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
- seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
- seq_printf(m, "icache block size\t: %d bytes\n",
- cpuinfo->icache_block_size);
- seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
index eb43b73..0f265b8 100644
--- a/arch/openrisc/mm/cache.c
+++ b/arch/openrisc/mm/cache.c
@@ -14,31 +14,70 @@
#include <asm/spr_defs.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
+#include <asm/cpuinfo.h>
#include <asm/tlbflush.h>
-static __always_inline void cache_loop(struct page *page, const unsigned int reg)
+/*
+ * Check if the cache component exists.
+ */
+bool cpu_cache_is_present(const unsigned int cache_type)
+{
+ unsigned long upr = mfspr(SPR_UPR);
+ unsigned long mask = SPR_UPR_UP | cache_type;
+
+ return !((upr & mask) ^ mask);
+}
+
+static __always_inline void cache_loop(unsigned long paddr, unsigned long end,
+ const unsigned short reg, const unsigned int cache_type)
+{
+ if (!cpu_cache_is_present(cache_type))
+ return;
+
+ while (paddr < end) {
+ mtspr(reg, paddr);
+ paddr += L1_CACHE_BYTES;
+ }
+}
+
+static __always_inline void cache_loop_page(struct page *page, const unsigned short reg,
+ const unsigned int cache_type)
{
unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
- unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+ unsigned long end = paddr + PAGE_SIZE;
- while (line < paddr + PAGE_SIZE) {
- mtspr(reg, line);
- line += L1_CACHE_BYTES;
- }
+ paddr &= ~(L1_CACHE_BYTES - 1);
+
+ cache_loop(paddr, end, reg, cache_type);
}
void local_dcache_page_flush(struct page *page)
{
- cache_loop(page, SPR_DCBFR);
+ cache_loop_page(page, SPR_DCBFR, SPR_UPR_DCP);
}
EXPORT_SYMBOL(local_dcache_page_flush);
void local_icache_page_inv(struct page *page)
{
- cache_loop(page, SPR_ICBIR);
+ cache_loop_page(page, SPR_ICBIR, SPR_UPR_ICP);
}
EXPORT_SYMBOL(local_icache_page_inv);
+void local_dcache_range_flush(unsigned long start, unsigned long end)
+{
+ cache_loop(start, end, SPR_DCBFR, SPR_UPR_DCP);
+}
+
+void local_dcache_range_inv(unsigned long start, unsigned long end)
+{
+ cache_loop(start, end, SPR_DCBIR, SPR_UPR_DCP);
+}
+
+void local_icache_range_inv(unsigned long start, unsigned long end)
+{
+ cache_loop(start, end, SPR_ICBIR, SPR_UPR_ICP);
+}
+
void update_cache(struct vm_area_struct *vma, unsigned long address,
pte_t *pte)
{
@@ -58,4 +97,3 @@ void update_cache(struct vm_area_struct *vma, unsigned long address,
sync_icache_dcache(folio_page(folio, nr));
}
}
-
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index be1c2eb..e4904ca 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -35,6 +35,7 @@
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
+#include <asm/cacheflush.h>
int mem_init_done;
@@ -176,8 +177,8 @@ void __init paging_init(void)
barrier();
/* Invalidate instruction caches after code modification */
- mtspr(SPR_ICBIR, 0x900);
- mtspr(SPR_ICBIR, 0xa00);
+ local_icache_block_inv(0x900);
+ local_icache_block_inv(0xa00);
/* New TLB miss handlers and kernel page tables are in now place.
* Make sure that page flags get updated for all pages in TLB by
diff --git a/arch/parisc/math-emu/driver.c b/arch/parisc/math-emu/driver.c
index 3449544..71829cb 100644
--- a/arch/parisc/math-emu/driver.c
+++ b/arch/parisc/math-emu/driver.c
@@ -97,9 +97,19 @@ handle_fpe(struct pt_regs *regs)
memcpy(regs->fr, frcopy, sizeof regs->fr);
if (signalcode != 0) {
- force_sig_fault(signalcode >> 24, signalcode & 0xffffff,
- (void __user *) regs->iaoq[0]);
- return -1;
+ int sig = signalcode >> 24;
+
+ if (sig == SIGFPE) {
+ /*
+ * Clear floating point trap bit to avoid trapping
+ * again on the first floating-point instruction in
+ * the userspace signal handler.
+ */
+ regs->fr[0] &= ~(1ULL << 38);
+ }
+ force_sig_fault(sig, signalcode & 0xffffff,
+ (void __user *) regs->iaoq[0]);
+ return -1;
}
return signalcode ? -1 : 0;
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 1db60fe..3d8dc82 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -234,10 +234,8 @@
# suppress some warnings in recent ld versions
nowarn="-z noexecstack"
-if ! ld_is_lld; then
- if [ "$LD_VERSION" -ge "$(echo 2.39 | ld_version)" ]; then
- nowarn="$nowarn --no-warn-rwx-segments"
- fi
+if "${CROSS}ld" -v --no-warn-rwx-segments >/dev/null 2>&1; then
+ nowarn="$nowarn --no-warn-rwx-segments"
fi
platformo=$object/"$platform".o
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 34a5aec..126bf3b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -258,10 +258,6 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
break;
}
}
- if (i == hdr->e_shnum) {
- pr_err("%s: doesn't contain __patchable_function_entries.\n", me->name);
- return -ENOEXEC;
- }
#endif
pr_debug("Looks like a total of %lu stubs, max\n", relocs);
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 311e211..9f764bc 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -976,7 +976,7 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
return 0;
}
-
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
{
if (radix_enabled())
@@ -984,6 +984,7 @@ bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
return false;
}
+#endif
int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
unsigned long addr, unsigned long next)
@@ -1120,6 +1121,19 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
pmd_t *pmd;
pte_t *pte;
+ /*
+ * Make sure we align the start vmemmap addr so that we calculate
+ * the correct start_pfn in altmap boundary check to decided whether
+ * we should use altmap or RAM based backing memory allocation. Also
+ * the address need to be aligned for set_pte operation.
+
+ * If the start addr is already PMD_SIZE aligned we will try to use
+ * a pmd mapping. We don't want to be too aggressive here beacause
+ * that will cause more allocations in RAM. So only if the namespace
+ * vmemmap start addr is PMD_SIZE aligned we will use PMD mapping.
+ */
+
+ start = ALIGN_DOWN(start, PAGE_SIZE);
for (addr = start; addr < end; addr = next) {
next = pmd_addr_end(addr, end);
@@ -1145,8 +1159,8 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
* in altmap block allocation failures, in which case
* we fallback to RAM for vmemmap allocation.
*/
- if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) ||
- altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
+ if (!IS_ALIGNED(addr, PMD_SIZE) || (altmap &&
+ altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
/*
* make sure we don't create altmap mappings
* covering things outside the device.
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 3fbe029..95d7ba7 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -17,7 +17,7 @@
select MMU_NOTIFIER
select FORCE_SMP
select ARCH_SUPPORTS_PER_VMA_LOCK
- select PPC_RADIX_BROADCAST_TLBIE
+ select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
default y
config OPAL_PRD
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index a934c2a..fa3c2ff 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -23,7 +23,7 @@
select FORCE_SMP
select SWIOTLB
select ARCH_SUPPORTS_PER_VMA_LOCK
- select PPC_RADIX_BROADCAST_TLBIE
+ select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
default y
config PARAVIRT
diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
index c18822e..58cd546 100644
--- a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
+++ b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
@@ -341,7 +341,7 @@ dmac: dma-controller@4330000 {
1024 1024 1024 1024>;
snps,priority = <0 1 2 3 4 5 6 7>;
snps,dma-masters = <2>;
- snps,data-width = <4>;
+ snps,data-width = <2>;
status = "disabled";
};
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8de73f9..b59ffeb 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page)
flush_dcache_folio(page_folio(page));
}
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
#define flush_icache_user_page(vma, pg, addr, len) \
do { \
if (vma->vm_flags & VM_EXEC) \
@@ -78,6 +73,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+ flush_icache_all();
+}
+
extern unsigned int riscv_cbom_block_size;
extern unsigned int riscv_cboz_block_size;
void riscv_init_cbo_blocksizes(void);
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 8d186bf..f7480c9 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -9,8 +9,8 @@
CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
endif
-CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
ifdef CONFIG_KEXEC_CORE
AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8b..cc15f7ca 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
/* Initialize the slot */
void *kaddr = kmap_atomic(page);
void *dst = kaddr + (vaddr & ~PAGE_MASK);
+ unsigned long start = (unsigned long)dst;
memcpy(dst, src, len);
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
*(uprobe_opcode_t *)dst = __BUG_INSN_32;
}
+ flush_icache_range(start, start + len);
kunmap_atomic(kaddr);
-
- /*
- * We probably need flush_icache_user_page() but it needs vma.
- * This should work on most of architectures by default. If
- * architecture needs to do something different it can define
- * its own version of the function.
- */
- flush_dcache_page(page);
}
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 7c244de..15d8f75 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -275,6 +275,9 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
unsigned long pmm;
u8 pmlen;
+ if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+ return -EINVAL;
+
if (is_compat_thread(ti))
return -EINVAL;
@@ -330,6 +333,9 @@ long get_tagged_addr_ctrl(struct task_struct *task)
struct thread_info *ti = task_thread_info(task);
long ret = 0;
+ if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+ return -EINVAL;
+
if (is_compat_thread(ti))
return -EINVAL;
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 8ff8e8b..9c83848 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -198,47 +198,57 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
DO_ERROR_INFO(do_trap_load_fault,
SIGSEGV, SEGV_ACCERR, "load access fault");
-asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
+enum misaligned_access_type {
+ MISALIGNED_STORE,
+ MISALIGNED_LOAD,
+};
+static const struct {
+ const char *type_str;
+ int (*handler)(struct pt_regs *regs);
+} misaligned_handler[] = {
+ [MISALIGNED_STORE] = {
+ .type_str = "Oops - store (or AMO) address misaligned",
+ .handler = handle_misaligned_store,
+ },
+ [MISALIGNED_LOAD] = {
+ .type_str = "Oops - load address misaligned",
+ .handler = handle_misaligned_load,
+ },
+};
+
+static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type)
{
+ irqentry_state_t state;
+
if (user_mode(regs)) {
irqentry_enter_from_user_mode(regs);
+ local_irq_enable();
+ } else {
+ state = irqentry_nmi_enter(regs);
+ }
- if (handle_misaligned_load(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - load address misaligned");
+ if (misaligned_handler[type].handler(regs))
+ do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+ misaligned_handler[type].type_str);
+ if (user_mode(regs)) {
+ local_irq_disable();
irqentry_exit_to_user_mode(regs);
} else {
- irqentry_state_t state = irqentry_nmi_enter(regs);
-
- if (handle_misaligned_load(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - load address misaligned");
-
irqentry_nmi_exit(regs, state);
}
}
+asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
+{
+ do_trap_misaligned(regs, MISALIGNED_LOAD);
+}
+
asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
{
- if (user_mode(regs)) {
- irqentry_enter_from_user_mode(regs);
-
- if (handle_misaligned_store(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - store (or AMO) address misaligned");
-
- irqentry_exit_to_user_mode(regs);
- } else {
- irqentry_state_t state = irqentry_nmi_enter(regs);
-
- if (handle_misaligned_store(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - store (or AMO) address misaligned");
-
- irqentry_nmi_exit(regs, state);
- }
+ do_trap_misaligned(regs, MISALIGNED_STORE);
}
+
DO_ERROR_INFO(do_trap_store_fault,
SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
DO_ERROR_INFO(do_trap_ecall_s,
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 4354c87..77c7886 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -88,6 +88,13 @@
#define INSN_MATCH_C_FSWSP 0xe002
#define INSN_MASK_C_FSWSP 0xe003
+#define INSN_MATCH_C_LHU 0x8400
+#define INSN_MASK_C_LHU 0xfc43
+#define INSN_MATCH_C_LH 0x8440
+#define INSN_MASK_C_LH 0xfc43
+#define INSN_MATCH_C_SH 0x8c00
+#define INSN_MASK_C_SH 0xfc43
+
#define INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4)
#if defined(CONFIG_64BIT)
@@ -268,7 +275,7 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
int __ret; \
\
if (user_mode(regs)) { \
- __ret = __get_user(insn, (type __user *) insn_addr); \
+ __ret = get_user(insn, (type __user *) insn_addr); \
} else { \
insn = *(type *)insn_addr; \
__ret = 0; \
@@ -431,6 +438,13 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
fp = 1;
len = 4;
#endif
+ } else if ((insn & INSN_MASK_C_LHU) == INSN_MATCH_C_LHU) {
+ len = 2;
+ insn = RVC_RS2S(insn) << SH_RD;
+ } else if ((insn & INSN_MASK_C_LH) == INSN_MATCH_C_LH) {
+ len = 2;
+ shift = 8 * (sizeof(ulong) - len);
+ insn = RVC_RS2S(insn) << SH_RD;
} else {
regs->epc = epc;
return -1;
@@ -530,6 +544,9 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs)
len = 4;
val.data_ulong = GET_F32_RS2C(insn, regs);
#endif
+ } else if ((insn & INSN_MASK_C_SH) == INSN_MATCH_C_SH) {
+ len = 2;
+ val.data_ulong = GET_RS2S(insn, regs);
} else {
regs->epc = epc;
return -1;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 60d684c..02635ba 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -77,6 +77,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
memcpy(cntx, reset_cntx, sizeof(*cntx));
spin_unlock(&vcpu->arch.reset_cntx_lock);
+ memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+
kvm_riscv_vcpu_fp_reset(vcpu);
kvm_riscv_vcpu_vector_reset(vcpu);
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 6f2c9ce..24b22f6 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -38,7 +38,6 @@
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
CONFIG_PROFILING=y
CONFIG_KEXEC=y
CONFIG_KEXEC_FILE=y
@@ -92,7 +91,6 @@
CONFIG_IOSCHED_BFQ=y
CONFIG_BINFMT_MISC=m
CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_SLAB_BUCKETS=y
CONFIG_SLUB_STATS=y
@@ -395,6 +393,9 @@
CONFIG_NET_CLS_FLOW=m
CONFIG_NET_CLS_CGROUP=y
CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_EMATCH=y
CONFIG_NET_CLS_ACT=y
CONFIG_NET_ACT_POLICE=m
CONFIG_NET_ACT_GACT=m
@@ -405,6 +406,9 @@
CONFIG_NET_ACT_SIMP=m
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_CT=m
CONFIG_NET_ACT_GATE=m
CONFIG_NET_TC_SKB_EXT=y
CONFIG_DNS_RESOLVER=y
@@ -628,8 +632,16 @@
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_MEM=m
CONFIG_VIRTIO_INPUT=y
+CONFIG_VDPA=m
+CONFIG_VDPA_SIM=m
+CONFIG_VDPA_SIM_NET=m
+CONFIG_VDPA_SIM_BLOCK=m
+CONFIG_VDPA_USER=m
+CONFIG_MLX5_VDPA_NET=m
+CONFIG_VP_VDPA=m
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
+CONFIG_VHOST_VDPA=m
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
@@ -654,7 +666,6 @@
CONFIG_BCACHEFS_FS=y
CONFIG_BCACHEFS_QUOTA=y
CONFIG_BCACHEFS_POSIX_ACL=y
-CONFIG_FS_DAX=y
CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_FS_ENCRYPTION=y
CONFIG_FS_VERITY=y
@@ -724,11 +735,10 @@
CONFIG_DLM=m
CONFIG_UNICODE=y
CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_KEY_NOTIFICATIONS=y
CONFIG_SECURITY=y
-CONFIG_HARDENED_USERCOPY=y
-CONFIG_FORTIFY_SOURCE=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
@@ -741,6 +751,8 @@
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_HARDENED_USERCOPY=y
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -756,7 +768,6 @@
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_ARIA=m
CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
CONFIG_CRYPTO_CAST5=m
CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_DES=m
@@ -801,7 +812,6 @@
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
CONFIG_CRYPTO_HMAC_S390=m
CONFIG_ZCRYPT=m
CONFIG_PKEY=m
@@ -812,9 +822,9 @@
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_SYSTEM_BLACKLIST_KEYRING=y
+CONFIG_CRYPTO_KRB5=m
+CONFIG_CRYPTO_KRB5_SELFTESTS=y
CONFIG_CORDIC=m
-CONFIG_CRYPTO_LIB_CURVE25519=m
-CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
CONFIG_RANDOM32_SELFTEST=y
CONFIG_XZ_DEC_MICROLZMA=y
CONFIG_DMA_CMA=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index f18a7d9..2b8b42d 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -36,7 +36,6 @@
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
CONFIG_PROFILING=y
CONFIG_KEXEC=y
CONFIG_KEXEC_FILE=y
@@ -86,7 +85,6 @@
CONFIG_IOSCHED_BFQ=y
CONFIG_BINFMT_MISC=m
CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_SLAB_BUCKETS=y
# CONFIG_COMPAT_BRK is not set
@@ -385,6 +383,9 @@
CONFIG_NET_CLS_FLOW=m
CONFIG_NET_CLS_CGROUP=y
CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_EMATCH=y
CONFIG_NET_CLS_ACT=y
CONFIG_NET_ACT_POLICE=m
CONFIG_NET_ACT_GACT=m
@@ -395,6 +396,9 @@
CONFIG_NET_ACT_SIMP=m
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_CT=m
CONFIG_NET_ACT_GATE=m
CONFIG_NET_TC_SKB_EXT=y
CONFIG_DNS_RESOLVER=y
@@ -618,8 +622,16 @@
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_MEM=m
CONFIG_VIRTIO_INPUT=y
+CONFIG_VDPA=m
+CONFIG_VDPA_SIM=m
+CONFIG_VDPA_SIM_NET=m
+CONFIG_VDPA_SIM_BLOCK=m
+CONFIG_VDPA_USER=m
+CONFIG_MLX5_VDPA_NET=m
+CONFIG_VP_VDPA=m
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
+CONFIG_VHOST_VDPA=m
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
@@ -641,7 +653,6 @@
CONFIG_BCACHEFS_FS=m
CONFIG_BCACHEFS_QUOTA=y
CONFIG_BCACHEFS_POSIX_ACL=y
-CONFIG_FS_DAX=y
CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_FS_ENCRYPTION=y
CONFIG_FS_VERITY=y
@@ -711,6 +722,7 @@
CONFIG_DLM=m
CONFIG_UNICODE=y
CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_KEY_NOTIFICATIONS=y
CONFIG_SECURITY=y
@@ -742,7 +754,6 @@
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_ARIA=m
CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
CONFIG_CRYPTO_CAST5=m
CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_DES=m
@@ -788,7 +799,6 @@
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
CONFIG_CRYPTO_HMAC_S390=m
CONFIG_ZCRYPT=m
CONFIG_PKEY=m
@@ -799,10 +809,10 @@
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_SYSTEM_BLACKLIST_KEYRING=y
+CONFIG_CRYPTO_KRB5=m
+CONFIG_CRYPTO_KRB5_SELFTESTS=y
CONFIG_CORDIC=m
CONFIG_PRIME_NUMBERS=m
-CONFIG_CRYPTO_LIB_CURVE25519=m
-CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
CONFIG_XZ_DEC_MICROLZMA=y
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 853b2326..8163c17 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -70,7 +70,6 @@
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_DEBUG_FS=y
CONFIG_PANIC_ON_OOPS=y
-# CONFIG_SCHED_DEBUG is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=60
# CONFIG_RCU_TRACE is not set
# CONFIG_FTRACE is not set
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index dd291c9..9980c17 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -602,7 +602,8 @@
stmg %r0,%r7,__PT_R0(%r11)
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_R8(64,%r11),0(%r14)
- stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
+ GET_LC %r2
+ mvc __PT_ORIG_GPR2(8,%r11),__LC_PGM_LAST_BREAK(%r2)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
jg kernel_stack_invalid
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 9a929bb..241f725 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -428,6 +428,8 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
return;
}
zdev = zpci_create_device(entry->fid, entry->fh, entry->config_state);
+ if (IS_ERR(zdev))
+ return;
list_add_tail(&zdev->entry, scan_list);
}
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 1d36a61..9ed792e 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -154,5 +154,6 @@
archclean:
@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
-o -name '*.gcov' \) -type f -print | xargs rm -f
+ $(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) clean
export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING DEV_NULL_PATH
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index 3a08f90..1c6e0ae 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -55,6 +55,7 @@ do { \
goto err_label; \
} \
*((type *)dst) = get_unaligned((type *)(src)); \
+ barrier(); \
current->thread.segv_continue = NULL; \
} while (0)
@@ -66,6 +67,7 @@ do { \
if (__faulted) \
goto err_label; \
put_unaligned(*((type *)src), (type *)(dst)); \
+ barrier(); \
current->thread.segv_continue = NULL; \
} while (0)
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ce07315..ef2272e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -225,20 +225,20 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
panic("Failed to sync kernel TLBs: %d", err);
goto out;
}
- else if (current->mm == NULL) {
- if (current->pagefault_disabled) {
- if (!mc) {
- show_regs(container_of(regs, struct pt_regs, regs));
- panic("Segfault with pagefaults disabled but no mcontext");
- }
- if (!current->thread.segv_continue) {
- show_regs(container_of(regs, struct pt_regs, regs));
- panic("Segfault without recovery target");
- }
- mc_set_rip(mc, current->thread.segv_continue);
- current->thread.segv_continue = NULL;
- goto out;
+ else if (current->pagefault_disabled) {
+ if (!mc) {
+ show_regs(container_of(regs, struct pt_regs, regs));
+ panic("Segfault with pagefaults disabled but no mcontext");
}
+ if (!current->thread.segv_continue) {
+ show_regs(container_of(regs, struct pt_regs, regs));
+ panic("Segfault without recovery target");
+ }
+ mc_set_rip(mc, current->thread.segv_continue);
+ current->thread.segv_continue = NULL;
+ goto out;
+ }
+ else if (current->mm == NULL) {
show_regs(container_of(regs, struct pt_regs, regs));
panic("Segfault with no mm");
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4b9f378..e21cca4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2368,6 +2368,7 @@
config CFI_AUTO_DEFAULT
bool "Attempt to use FineIBT by default at boot time"
depends on FINEIBT
+ depends on !RUST || RUSTC_VERSION >= 108800
default y
help
Attempt to use FineIBT by default at boot time. If enabled,
@@ -2710,6 +2711,18 @@
of speculative execution in a similar way to the Meltdown and Spectre
security vulnerabilities.
+config MITIGATION_ITS
+ bool "Enable Indirect Target Selection mitigation"
+ depends on CPU_SUP_INTEL && X86_64
+ depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK
+ select EXECMEM
+ default y
+ help
+ Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in
+ BPU on some Intel CPUs that may allow Spectre V2 style attacks. If
+ disabled, mitigation cannot be enabled via cmdline.
+ See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 81f55da..640fcac 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -59,7 +59,7 @@
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
- cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
+ cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
$(call if_changed,image)
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index f676156..0e9f84a 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -34,14 +34,11 @@ static bool early_is_tdx_guest(void)
void arch_accept_memory(phys_addr_t start, phys_addr_t end)
{
- static bool sevsnp;
-
/* Platform-specific memory-acceptance call goes here */
if (early_is_tdx_guest()) {
if (!tdx_accept_memory(start, end))
panic("TDX: Failed to accept memory\n");
- } else if (sevsnp || (sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) {
- sevsnp = true;
+ } else if (early_is_sevsnp_guest()) {
snp_accept_memory(start, end);
} else {
error("Cannot accept memory: unknown platform\n");
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 89ba168..0003e44 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -645,3 +645,43 @@ void sev_prep_identity_maps(unsigned long top_level_pgt)
sev_verify_cbit(top_level_pgt);
}
+
+bool early_is_sevsnp_guest(void)
+{
+ static bool sevsnp;
+
+ if (sevsnp)
+ return true;
+
+ if (!(sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED))
+ return false;
+
+ sevsnp = true;
+
+ if (!snp_vmpl) {
+ unsigned int eax, ebx, ecx, edx;
+
+ /*
+ * CPUID Fn8000_001F_EAX[28] - SVSM support
+ */
+ eax = 0x8000001f;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ if (eax & BIT(28)) {
+ struct msr m;
+
+ /* Obtain the address of the calling area to use */
+ boot_rdmsr(MSR_SVSM_CAA, &m);
+ boot_svsm_caa = (void *)m.q;
+ boot_svsm_caa_pa = m.q;
+
+ /*
+ * The real VMPL level cannot be discovered, but the
+ * memory acceptance routines make no use of that so
+ * any non-zero value suffices here.
+ */
+ snp_vmpl = U8_MAX;
+ }
+ }
+ return true;
+}
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index 4e463f3..d390038 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -13,12 +13,14 @@
bool sev_snp_enabled(void);
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
u64 sev_get_status(void);
+bool early_is_sevsnp_guest(void);
#else
static inline bool sev_snp_enabled(void) { return false; }
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
static inline u64 sev_get_status(void) { return 0; }
+static inline bool early_is_sevsnp_guest(void) { return false; }
#endif
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index b0c1a7a..36beaac 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -959,6 +959,102 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
}
+static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32 apic_id)
+{
+ bool create = event != SVM_VMGEXIT_AP_DESTROY;
+ struct ghcb_state state;
+ unsigned long flags;
+ struct ghcb *ghcb;
+ int ret = 0;
+
+ local_irq_save(flags);
+
+ ghcb = __sev_get_ghcb(&state);
+
+ vc_ghcb_invalidate(ghcb);
+
+ if (create)
+ ghcb_set_rax(ghcb, vmsa->sev_features);
+
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
+ ghcb_set_sw_exit_info_1(ghcb,
+ ((u64)apic_id << 32) |
+ ((u64)snp_vmpl << 16) |
+ event);
+ ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
+
+ sev_es_wr_ghcb_msr(__pa(ghcb));
+ VMGEXIT();
+
+ if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
+ lower_32_bits(ghcb->save.sw_exit_info_1)) {
+ pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY"));
+ ret = -EINVAL;
+ }
+
+ __sev_put_ghcb(&state);
+
+ local_irq_restore(flags);
+
+ return ret;
+}
+
+static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
+{
+ int ret;
+
+ if (snp_vmpl) {
+ struct svsm_call call = {};
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ call.caa = this_cpu_read(svsm_caa);
+ call.rcx = __pa(va);
+
+ if (make_vmsa) {
+ /* Protocol 0, Call ID 2 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
+ call.rdx = __pa(caa);
+ call.r8 = apic_id;
+ } else {
+ /* Protocol 0, Call ID 3 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
+ }
+
+ ret = svsm_perform_call_protocol(&call);
+
+ local_irq_restore(flags);
+ } else {
+ /*
+ * If the kernel runs at VMPL0, it can change the VMSA
+ * bit for a page using the RMPADJUST instruction.
+ * However, for the instruction to succeed it must
+ * target the permissions of a lesser privileged (higher
+ * numbered) VMPL level, so use VMPL1.
+ */
+ u64 attrs = 1;
+
+ if (make_vmsa)
+ attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+ ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+ }
+
+ return ret;
+}
+
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
+{
+ int err;
+
+ err = snp_set_vmsa(vmsa, NULL, apic_id, false);
+ if (err)
+ pr_err("clear VMSA page failed (%u), leaking page\n", err);
+ else
+ free_page((unsigned long)vmsa);
+}
+
static void set_pte_enc(pte_t *kpte, int level, void *va)
{
struct pte_enc_desc d = {
@@ -1005,7 +1101,8 @@ static void unshare_all_memory(void)
data = per_cpu(runtime_data, cpu);
ghcb = (unsigned long)&data->ghcb_page;
- if (addr <= ghcb && ghcb <= addr + size) {
+ /* Handle the case of a huge page containing the GHCB page */
+ if (addr <= ghcb && ghcb < addr + size) {
skipped_addr = true;
break;
}
@@ -1055,11 +1152,70 @@ void snp_kexec_begin(void)
pr_warn("Failed to stop shared<->private conversions\n");
}
+/*
+ * Shutdown all APs except the one handling kexec/kdump and clearing
+ * the VMSA tag on AP's VMSA pages as they are not being used as
+ * VMSA page anymore.
+ */
+static void shutdown_all_aps(void)
+{
+ struct sev_es_save_area *vmsa;
+ int apic_id, this_cpu, cpu;
+
+ this_cpu = get_cpu();
+
+ /*
+ * APs are already in HLT loop when enc_kexec_finish() callback
+ * is invoked.
+ */
+ for_each_present_cpu(cpu) {
+ vmsa = per_cpu(sev_vmsa, cpu);
+
+ /*
+ * The BSP or offlined APs do not have guest allocated VMSA
+ * and there is no need to clear the VMSA tag for this page.
+ */
+ if (!vmsa)
+ continue;
+
+ /*
+ * Cannot clear the VMSA tag for the currently running vCPU.
+ */
+ if (this_cpu == cpu) {
+ unsigned long pa;
+ struct page *p;
+
+ pa = __pa(vmsa);
+ /*
+ * Mark the VMSA page of the running vCPU as offline
+ * so that is excluded and not touched by makedumpfile
+ * while generating vmcore during kdump.
+ */
+ p = pfn_to_online_page(pa >> PAGE_SHIFT);
+ if (p)
+ __SetPageOffline(p);
+ continue;
+ }
+
+ apic_id = cpuid_to_apicid[cpu];
+
+ /*
+ * Issue AP destroy to ensure AP gets kicked out of guest mode
+ * to allow using RMPADJUST to remove the VMSA tag on it's
+ * VMSA page.
+ */
+ vmgexit_ap_control(SVM_VMGEXIT_AP_DESTROY, vmsa, apic_id);
+ snp_cleanup_vmsa(vmsa, apic_id);
+ }
+
+ put_cpu();
+}
+
void snp_kexec_finish(void)
{
struct sev_es_runtime_data *data;
+ unsigned long size, addr;
unsigned int level, cpu;
- unsigned long size;
struct ghcb *ghcb;
pte_t *pte;
@@ -1069,6 +1225,8 @@ void snp_kexec_finish(void)
if (!IS_ENABLED(CONFIG_KEXEC_CORE))
return;
+ shutdown_all_aps();
+
unshare_all_memory();
/*
@@ -1085,56 +1243,13 @@ void snp_kexec_finish(void)
ghcb = &data->ghcb_page;
pte = lookup_address((unsigned long)ghcb, &level);
size = page_level_size(level);
- set_pte_enc(pte, level, (void *)ghcb);
- snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE));
+ /* Handle the case of a huge page containing the GHCB page */
+ addr = (unsigned long)ghcb & page_level_mask(level);
+ set_pte_enc(pte, level, (void *)addr);
+ snp_set_memory_private(addr, (size / PAGE_SIZE));
}
}
-static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
-{
- int ret;
-
- if (snp_vmpl) {
- struct svsm_call call = {};
- unsigned long flags;
-
- local_irq_save(flags);
-
- call.caa = this_cpu_read(svsm_caa);
- call.rcx = __pa(va);
-
- if (make_vmsa) {
- /* Protocol 0, Call ID 2 */
- call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
- call.rdx = __pa(caa);
- call.r8 = apic_id;
- } else {
- /* Protocol 0, Call ID 3 */
- call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
- }
-
- ret = svsm_perform_call_protocol(&call);
-
- local_irq_restore(flags);
- } else {
- /*
- * If the kernel runs at VMPL0, it can change the VMSA
- * bit for a page using the RMPADJUST instruction.
- * However, for the instruction to succeed it must
- * target the permissions of a lesser privileged (higher
- * numbered) VMPL level, so use VMPL1.
- */
- u64 attrs = 1;
-
- if (make_vmsa)
- attrs |= RMPADJUST_VMSA_PAGE_BIT;
-
- ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
- }
-
- return ret;
-}
-
#define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
#define INIT_CS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_READ_MASK | SVM_SELECTOR_CODE_MASK)
#define INIT_DS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_WRITE_MASK)
@@ -1166,24 +1281,10 @@ static void *snp_alloc_vmsa_page(int cpu)
return page_address(p + 1);
}
-static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
-{
- int err;
-
- err = snp_set_vmsa(vmsa, NULL, apic_id, false);
- if (err)
- pr_err("clear VMSA page failed (%u), leaking page\n", err);
- else
- free_page((unsigned long)vmsa);
-}
-
static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
{
struct sev_es_save_area *cur_vmsa, *vmsa;
- struct ghcb_state state;
struct svsm_ca *caa;
- unsigned long flags;
- struct ghcb *ghcb;
u8 sipi_vector;
int cpu, ret;
u64 cr4;
@@ -1297,33 +1398,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
}
/* Issue VMGEXIT AP Creation NAE event */
- local_irq_save(flags);
-
- ghcb = __sev_get_ghcb(&state);
-
- vc_ghcb_invalidate(ghcb);
- ghcb_set_rax(ghcb, vmsa->sev_features);
- ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
- ghcb_set_sw_exit_info_1(ghcb,
- ((u64)apic_id << 32) |
- ((u64)snp_vmpl << 16) |
- SVM_VMGEXIT_AP_CREATE);
- ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
-
- sev_es_wr_ghcb_msr(__pa(ghcb));
- VMGEXIT();
-
- if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
- lower_32_bits(ghcb->save.sw_exit_info_1)) {
- pr_err("SNP AP Creation error\n");
- ret = -EINVAL;
- }
-
- __sev_put_ghcb(&state);
-
- local_irq_restore(flags);
-
- /* Perform cleanup if there was an error */
+ ret = vmgexit_ap_control(SVM_VMGEXIT_AP_CREATE, vmsa, apic_id);
if (ret) {
snp_cleanup_vmsa(vmsa, apic_id);
vmsa = NULL;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f40bdf9..ed04a96 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1525,7 +1525,9 @@
* ORC to unwind properly.
*
* The alignment is for performance and not for safety, and may be safely
- * refactored in the future if needed.
+ * refactored in the future if needed. The .skips are for safety, to ensure
+ * that all RETs are in the second half of a cacheline to mitigate Indirect
+ * Target Selection, rather than taking the slowpath via its_return_thunk.
*/
SYM_FUNC_START(clear_bhb_loop)
ANNOTATE_NOENDBR
@@ -1536,10 +1538,22 @@
call 1f
jmp 5f
.align 64, 0xcc
+ /*
+ * Shift instructions so that the RET is in the upper half of the
+ * cacheline and don't take the slowpath to its_return_thunk.
+ */
+ .skip 32 - (.Lret1 - 1f), 0xcc
ANNOTATE_INTRA_FUNCTION_CALL
1: call 2f
- RET
+.Lret1: RET
.align 64, 0xcc
+ /*
+ * As above shift instructions for RET at .Lret2 as well.
+ *
+ * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc
+ * but some Clang versions (e.g. 18) don't like this.
+ */
+ .skip 32 - 18, 0xcc
2: movl $5, %eax
3: jmp 4f
nop
@@ -1547,7 +1561,7 @@
jnz 3b
sub $1, %ecx
jnz 1b
- RET
+.Lret2: RET
5: lfence
pop %rbp
RET
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6866cc5..139ad80 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -629,7 +629,7 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.type == event->pmu->type)
event->hw.config |= x86_pmu_get_event_config(event);
- if (!event->attr.freq && x86_pmu.limit_period) {
+ if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
s64 left = event->attr.sample_period;
x86_pmu.limit_period(event, &left);
if (left > event->attr.sample_period)
@@ -754,7 +754,7 @@ void x86_pmu_enable_all(int added)
}
}
-static inline int is_x86_event(struct perf_event *event)
+int is_x86_event(struct perf_event *event)
{
int i;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 00dfe48..c5f3854 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4395,7 +4395,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
arr[pebs_enable] = (struct perf_guest_switch_msr){
.msr = MSR_IA32_PEBS_ENABLE,
.host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
- .guest = pebs_mask & ~cpuc->intel_ctrl_host_mask,
+ .guest = pebs_mask & ~cpuc->intel_ctrl_host_mask & kvm_pmu->pebs_enable,
};
if (arr[pebs_enable].host) {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 18c3ab5..8d86e91 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2379,8 +2379,25 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
*/
intel_pmu_save_and_restart_reload(event, count);
}
- } else
- intel_pmu_save_and_restart(event);
+ } else {
+ /*
+ * For a non-precise event, it's possible the
+ * counters-snapshotting records a positive value for the
+ * overflowed event. Then the HW auto-reload mechanism
+ * reset the counter to 0 immediately, because the
+ * pebs_event_reset is cleared if the PERF_X86_EVENT_AUTO_RELOAD
+ * is not set. The counter backwards may be observed in a
+ * PMI handler.
+ *
+ * Since the event value has been updated when processing the
+ * counters-snapshotting record, only needs to set the new
+ * period for the counter.
+ */
+ if (is_pebs_counter_event_group(event))
+ static_call(x86_pmu_set_period)(event);
+ else
+ intel_pmu_save_and_restart(event);
+ }
}
static __always_inline void
@@ -2448,8 +2465,9 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
setup_pebs_fixed_sample_data);
}
-static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask)
{
+ u64 pebs_enabled = cpuc->pebs_enabled & mask;
struct perf_event *event;
int bit;
@@ -2460,7 +2478,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int
* It needs to call intel_pmu_save_and_restart_reload() to
* update the event->count for this case.
*/
- for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+ for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) {
event = cpuc->events[bit];
if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
intel_pmu_save_and_restart_reload(event, 0);
@@ -2495,7 +2513,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
}
if (unlikely(base >= top)) {
- intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ intel_pmu_pebs_event_update_no_drain(cpuc, mask);
return;
}
@@ -2609,7 +2627,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
(hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
if (unlikely(base >= top)) {
- intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
+ intel_pmu_pebs_event_update_no_drain(cpuc, mask);
return;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 2c0ce0e9..46d1205 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,14 +110,21 @@ static inline bool is_topdown_event(struct perf_event *event)
return is_metric_event(event) || is_slots_event(event);
}
+int is_x86_event(struct perf_event *event);
+
+static inline bool check_leader_group(struct perf_event *leader, int flags)
+{
+ return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false;
+}
+
static inline bool is_branch_counters_group(struct perf_event *event)
{
- return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+ return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS);
}
static inline bool is_pebs_counter_event_group(struct perf_event *event)
{
- return event->group_leader->hw.flags & PERF_X86_EVENT_PEBS_CNTR;
+ return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR);
}
struct amd_nb {
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4a37a8b..f229478 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -6,6 +6,7 @@
#include <linux/stringify.h>
#include <linux/objtool.h>
#include <asm/asm.h>
+#include <asm/bug.h>
#define ALT_FLAGS_SHIFT 16
@@ -124,6 +125,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
}
#endif
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_init_mod(struct module *mod);
+extern void its_fini_mod(struct module *mod);
+extern void its_free_mod(struct module *mod);
+extern u8 *its_static_thunk(int reg);
+#else /* CONFIG_MITIGATION_ITS */
+static inline void its_init_mod(struct module *mod) { }
+static inline void its_fini_mod(struct module *mod) { }
+static inline void its_free_mod(struct module *mod) { }
+static inline u8 *its_static_thunk(int reg)
+{
+ WARN_ONCE(1, "ITS not compiled in");
+
+ return NULL;
+}
+#endif
+
+#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL)
+extern bool cpu_wants_rethunk(void);
+extern bool cpu_wants_rethunk_at(void *addr);
+#else
+static __always_inline bool cpu_wants_rethunk(void)
+{
+ return false;
+}
+static __always_inline bool cpu_wants_rethunk_at(void *addr)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_SMP
extern void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6c2c152..30144ef 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -75,7 +75,7 @@
#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */
#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-/* Free ( 3*32+ 6) */
+#define X86_FEATURE_ZEN6 ( 3*32+ 6) /* CPU based on Zen6 microarchitecture */
/* Free ( 3*32+ 7) */
#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */
@@ -481,6 +481,7 @@
#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */
#define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */
/*
* BUG word(s)
@@ -533,4 +534,6 @@
#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
#define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_ITS X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3bdae45..7bc174a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,6 +35,7 @@
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#include <asm/asm.h>
+#include <asm/irq_remapping.h>
#include <asm/kvm_page_track.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/reboot.h>
@@ -2423,4 +2424,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
*/
#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 695e569..be7cddc 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -17,10 +17,12 @@ struct ucode_cpu_info {
void load_ucode_bsp(void);
void load_ucode_ap(void);
void microcode_bsp_resume(void);
+bool __init microcode_loader_disabled(void);
#else
static inline void load_ucode_bsp(void) { }
static inline void load_ucode_ap(void) { }
static inline void microcode_bsp_resume(void) { }
+static inline bool __init microcode_loader_disabled(void) { return false; }
#endif
extern unsigned long initrd_start_early;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e6134ef2..e7d2f46 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -211,6 +211,14 @@
* VERW clears CPU Register
* File.
*/
+#define ARCH_CAP_ITS_NO BIT_ULL(62) /*
+ * Not susceptible to
+ * Indirect Target Selection.
+ * This bit is not set by
+ * HW, but is synthesized by
+ * VMMs for guests to know
+ * their affected status.
+ */
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 5c43f14..7d04ade 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -336,10 +336,14 @@
#else /* __ASSEMBLER__ */
+#define ITS_THUNK_SIZE 64
+
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+typedef u8 its_thunk_t[ITS_THUNK_SIZE];
extern retpoline_thunk_t __x86_indirect_thunk_array[];
extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
+extern its_thunk_t __x86_indirect_its_thunk_array[];
#ifdef CONFIG_MITIGATION_RETHUNK
extern void __x86_return_thunk(void);
@@ -363,6 +367,12 @@ static inline void srso_return_thunk(void) {}
static inline void srso_alias_return_thunk(void) {}
#endif
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_return_thunk(void);
+#else
+static inline void its_return_thunk(void) {}
+#endif
+
extern void retbleed_return_thunk(void);
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a331475..c88691b 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,8 @@
#include <linux/mm.h> /* for struct page */
#include <linux/pagemap.h>
+#include <asm/cpufeature.h>
+
#define __HAVE_ARCH_PTE_ALLOC_ONE
#define __HAVE_ARCH_PGD_FREE
#include <asm-generic/pgalloc.h>
@@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
static inline void paravirt_release_p4d(unsigned long pfn) {}
#endif
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
- * Instead of one PGD, we acquire two PGDs. Being order-1, it is
- * both 8k in size and 8k-aligned. That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned. That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
*/
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_PTI))
+ return 1;
+ return 0;
+}
/*
* Allocate and free page tables.
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index acb85b9..0020d77 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -116,7 +116,7 @@ enum psc_op {
#define GHCB_MSR_VMPL_REQ 0x016
#define GHCB_MSR_VMPL_REQ_LEVEL(v) \
/* GHCBData[39:32] */ \
- (((u64)(v) & GENMASK_ULL(7, 0) << 32) | \
+ ((((u64)(v) & GENMASK_ULL(7, 0)) << 32) | \
/* GHCBDdata[11:0] */ \
GHCB_MSR_VMPL_REQ)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index bf82c6f..45bcff1 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -18,6 +18,7 @@
#include <linux/mmu_context.h>
#include <linux/bsearch.h>
#include <linux/sync_core.h>
+#include <linux/execmem.h>
#include <asm/text-patching.h>
#include <asm/alternative.h>
#include <asm/sections.h>
@@ -31,6 +32,8 @@
#include <asm/paravirt.h>
#include <asm/asm-prototypes.h>
#include <asm/cfi.h>
+#include <asm/ibt.h>
+#include <asm/set_memory.h>
int __read_mostly alternatives_patched;
@@ -124,6 +127,171 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
#endif
};
+#ifdef CONFIG_FINEIBT
+static bool cfi_paranoid __ro_after_init;
+#endif
+
+#ifdef CONFIG_MITIGATION_ITS
+
+#ifdef CONFIG_MODULES
+static struct module *its_mod;
+#endif
+static void *its_page;
+static unsigned int its_offset;
+
+/* Initialize a thunk with the "jmp *reg; int3" instructions. */
+static void *its_init_thunk(void *thunk, int reg)
+{
+ u8 *bytes = thunk;
+ int offset = 0;
+ int i = 0;
+
+#ifdef CONFIG_FINEIBT
+ if (cfi_paranoid) {
+ /*
+ * When ITS uses indirect branch thunk the fineibt_paranoid
+ * caller sequence doesn't fit in the caller site. So put the
+ * remaining part of the sequence (<ea> + JNE) into the ITS
+ * thunk.
+ */
+ bytes[i++] = 0xea; /* invalid instruction */
+ bytes[i++] = 0x75; /* JNE */
+ bytes[i++] = 0xfd;
+
+ offset = 1;
+ }
+#endif
+
+ if (reg >= 8) {
+ bytes[i++] = 0x41; /* REX.B prefix */
+ reg -= 8;
+ }
+ bytes[i++] = 0xff;
+ bytes[i++] = 0xe0 + reg; /* jmp *reg */
+ bytes[i++] = 0xcc;
+
+ return thunk + offset;
+}
+
+#ifdef CONFIG_MODULES
+void its_init_mod(struct module *mod)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return;
+
+ mutex_lock(&text_mutex);
+ its_mod = mod;
+ its_page = NULL;
+}
+
+void its_fini_mod(struct module *mod)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return;
+
+ WARN_ON_ONCE(its_mod != mod);
+
+ its_mod = NULL;
+ its_page = NULL;
+ mutex_unlock(&text_mutex);
+
+ for (int i = 0; i < mod->its_num_pages; i++) {
+ void *page = mod->its_page_array[i];
+ execmem_restore_rox(page, PAGE_SIZE);
+ }
+}
+
+void its_free_mod(struct module *mod)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return;
+
+ for (int i = 0; i < mod->its_num_pages; i++) {
+ void *page = mod->its_page_array[i];
+ execmem_free(page);
+ }
+ kfree(mod->its_page_array);
+}
+#endif /* CONFIG_MODULES */
+
+static void *its_alloc(void)
+{
+ void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+
+ if (!page)
+ return NULL;
+
+#ifdef CONFIG_MODULES
+ if (its_mod) {
+ void *tmp = krealloc(its_mod->its_page_array,
+ (its_mod->its_num_pages+1) * sizeof(void *),
+ GFP_KERNEL);
+ if (!tmp)
+ return NULL;
+
+ its_mod->its_page_array = tmp;
+ its_mod->its_page_array[its_mod->its_num_pages++] = page;
+
+ execmem_make_temp_rw(page, PAGE_SIZE);
+ }
+#endif /* CONFIG_MODULES */
+
+ return no_free_ptr(page);
+}
+
+static void *its_allocate_thunk(int reg)
+{
+ int size = 3 + (reg / 8);
+ void *thunk;
+
+#ifdef CONFIG_FINEIBT
+ /*
+ * The ITS thunk contains an indirect jump and an int3 instruction so
+ * its size is 3 or 4 bytes depending on the register used. If CFI
+ * paranoid is used then 3 extra bytes are added in the ITS thunk to
+ * complete the fineibt_paranoid caller sequence.
+ */
+ if (cfi_paranoid)
+ size += 3;
+#endif
+
+ if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) {
+ its_page = its_alloc();
+ if (!its_page) {
+ pr_err("ITS page allocation failed\n");
+ return NULL;
+ }
+ memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE);
+ its_offset = 32;
+ }
+
+ /*
+ * If the indirect branch instruction will be in the lower half
+ * of a cacheline, then update the offset to reach the upper half.
+ */
+ if ((its_offset + size - 1) % 64 < 32)
+ its_offset = ((its_offset - 1) | 0x3F) + 33;
+
+ thunk = its_page + its_offset;
+ its_offset += size;
+
+ return its_init_thunk(thunk, reg);
+}
+
+u8 *its_static_thunk(int reg)
+{
+ u8 *thunk = __x86_indirect_its_thunk_array[reg];
+
+#ifdef CONFIG_FINEIBT
+ /* Paranoid thunk starts 2 bytes before */
+ if (cfi_paranoid)
+ return thunk - 2;
+#endif
+ return thunk;
+}
+
+#endif
+
/*
* Nomenclature for variable names to simplify and clarify this code and ease
* any potential staring at it:
@@ -581,7 +749,8 @@ static int emit_indirect(int op, int reg, u8 *bytes)
return i;
}
-static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes,
+ void *call_dest, void *jmp_dest)
{
u8 op = insn->opcode.bytes[0];
int i = 0;
@@ -602,7 +771,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
switch (op) {
case CALL_INSN_OPCODE:
__text_gen_insn(bytes+i, op, addr+i,
- __x86_indirect_call_thunk_array[reg],
+ call_dest,
CALL_INSN_SIZE);
i += CALL_INSN_SIZE;
break;
@@ -610,7 +779,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
case JMP32_INSN_OPCODE:
clang_jcc:
__text_gen_insn(bytes+i, op, addr+i,
- __x86_indirect_jump_thunk_array[reg],
+ jmp_dest,
JMP32_INSN_SIZE);
i += JMP32_INSN_SIZE;
break;
@@ -625,6 +794,48 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
return i;
}
+static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ return __emit_trampoline(addr, insn, bytes,
+ __x86_indirect_call_thunk_array[reg],
+ __x86_indirect_jump_thunk_array[reg]);
+}
+
+#ifdef CONFIG_MITIGATION_ITS
+static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ u8 *thunk = __x86_indirect_its_thunk_array[reg];
+ u8 *tmp = its_allocate_thunk(reg);
+
+ if (tmp)
+ thunk = tmp;
+
+ return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
+/* Check if an indirect branch is at ITS-unsafe address */
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+ return false;
+
+ /* Indirect branch opcode is 2 or 3 bytes depending on reg */
+ addr += 1 + reg / 8;
+
+ /* Lower-half of the cacheline? */
+ return !(addr & 0x20);
+}
+#else /* CONFIG_MITIGATION_ITS */
+
+#ifdef CONFIG_FINEIBT
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+ return false;
+}
+#endif
+
+#endif /* CONFIG_MITIGATION_ITS */
+
/*
* Rewrite the compiler generated retpoline thunk calls.
*
@@ -699,6 +910,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
bytes[i++] = 0xe8; /* LFENCE */
}
+#ifdef CONFIG_MITIGATION_ITS
+ /*
+ * Check if the address of last byte of emitted-indirect is in
+ * lower-half of the cacheline. Such branches need ITS mitigation.
+ */
+ if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg))
+ return emit_its_trampoline(addr, insn, reg, bytes);
+#endif
+
ret = emit_indirect(op, reg, bytes + i);
if (ret < 0)
return ret;
@@ -732,6 +952,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
int len, ret;
u8 bytes[16];
u8 op1, op2;
+ u8 *dest;
ret = insn_decode_kernel(&insn, addr);
if (WARN_ON_ONCE(ret < 0))
@@ -748,6 +969,12 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
case CALL_INSN_OPCODE:
case JMP32_INSN_OPCODE:
+ /* Check for cfi_paranoid + ITS */
+ dest = addr + insn.length + insn.immediate.value;
+ if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) {
+ WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+ continue;
+ }
break;
case 0x0f: /* escape */
@@ -775,6 +1002,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
#ifdef CONFIG_MITIGATION_RETHUNK
+bool cpu_wants_rethunk(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_RETHUNK);
+}
+
+bool cpu_wants_rethunk_at(void *addr)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ return false;
+ if (x86_return_thunk != its_return_thunk)
+ return true;
+
+ return !((unsigned long)addr & 0x20);
+}
+
/*
* Rewrite the compiler generated return thunk tail-calls.
*
@@ -791,7 +1033,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
int i = 0;
/* Patch the custom return thunks... */
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+ if (cpu_wants_rethunk_at(addr)) {
i = JMP32_INSN_SIZE;
__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
} else {
@@ -808,7 +1050,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
{
s32 *s;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk())
static_call_force_reinit();
for (s = start; s < end; s++) {
@@ -1022,8 +1264,6 @@ int cfi_get_func_arity(void *func)
static bool cfi_rand __ro_after_init = true;
static u32 cfi_seed __ro_after_init;
-static bool cfi_paranoid __ro_after_init = false;
-
/*
* Re-hash the CFI hash with a boot-time seed while making sure the result is
* not a valid ENDBR instruction.
@@ -1436,6 +1676,19 @@ static int cfi_rand_callers(s32 *start, s32 *end)
return 0;
}
+static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+ u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2;
+
+#ifdef CONFIG_MITIGATION_ITS
+ u8 *tmp = its_allocate_thunk(reg);
+ if (tmp)
+ thunk = tmp;
+#endif
+
+ return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
static int cfi_rewrite_callers(s32 *start, s32 *end)
{
s32 *s;
@@ -1477,9 +1730,14 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size);
memcpy(bytes + fineibt_caller_hash, &hash, 4);
- ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
- if (WARN_ON_ONCE(ret != 3))
- continue;
+ if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) {
+ emit_paranoid_trampoline(addr + fineibt_caller_size,
+ &insn, 11, bytes + fineibt_caller_size);
+ } else {
+ ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
+ if (WARN_ON_ONCE(ret != 3))
+ continue;
+ }
text_poke_early(addr, bytes, fineibt_paranoid_size);
}
@@ -1706,29 +1964,66 @@ static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32
return false;
}
+static bool is_paranoid_thunk(unsigned long addr)
+{
+ u32 thunk;
+
+ __get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault);
+ return (thunk & 0x00FFFFFF) == 0xfd75ea;
+
+Efault:
+ return false;
+}
+
/*
* regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
- * sequence.
+ * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS
+ * thunk.
*/
static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
{
unsigned long addr = regs->ip - fineibt_paranoid_ud;
- u32 hash;
- if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2))
+ if (!cfi_paranoid)
return false;
- __get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault);
- *target = regs->r11 + fineibt_preamble_size;
- *type = regs->r10;
+ if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) {
+ *target = regs->r11 + fineibt_preamble_size;
+ *type = regs->r10;
+
+ /*
+ * Since the trapping instruction is the exact, but LOCK prefixed,
+ * Jcc.d8 that got us here, the normal fixup will work.
+ */
+ return true;
+ }
/*
- * Since the trapping instruction is the exact, but LOCK prefixed,
- * Jcc.d8 that got us here, the normal fixup will work.
+ * The cfi_paranoid + ITS thunk combination results in:
+ *
+ * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d
+ * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d
+ * a: 4d 8d 5b f0 lea -0x10(%r11), %r11
+ * e: 2e e8 XX XX XX XX cs call __x86_indirect_paranoid_thunk_r11
+ *
+ * Where the paranoid_thunk looks like:
+ *
+ * 1d: <ea> (bad)
+ * __x86_indirect_paranoid_thunk_r11:
+ * 1e: 75 fd jne 1d
+ * __x86_indirect_its_thunk_r11:
+ * 20: 41 ff eb jmp *%r11
+ * 23: cc int3
+ *
*/
- return true;
+ if (is_paranoid_thunk(regs->ip)) {
+ *target = regs->r11 + fineibt_preamble_size;
+ *type = regs->r10;
-Efault:
+ regs->ip = *target;
+ return true;
+ }
+
return false;
}
@@ -2031,6 +2326,8 @@ static noinline void __init alt_reloc_selftest(void)
void __init alternative_instructions(void)
{
+ u64 ibt;
+
int3_selftest();
/*
@@ -2057,6 +2354,9 @@ void __init alternative_instructions(void)
*/
paravirt_set_cap();
+ /* Keep CET-IBT disabled until caller/callee are patched */
+ ibt = ibt_save(/*disable*/ true);
+
__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
__cfi_sites, __cfi_sites_end, true);
@@ -2080,6 +2380,8 @@ void __init alternative_instructions(void)
*/
apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
+ ibt_restore(ibt);
+
#ifdef CONFIG_SMP
/* Patch to UP if other cpus not imminent. */
if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 2b36379..4e06baa 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -472,6 +472,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
case 0x60 ... 0x7f:
setup_force_cpu_cap(X86_FEATURE_ZEN5);
break;
+ case 0x50 ... 0x5f:
+ case 0x90 ... 0xaf:
+ case 0xc0 ... 0xcf:
+ setup_force_cpu_cap(X86_FEATURE_ZEN6);
+ break;
default:
goto warn;
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 362602b..8596ce8 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void);
static void __init l1d_flush_select_mitigation(void);
static void __init srso_select_mitigation(void);
static void __init gds_select_mitigation(void);
+static void __init its_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -66,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex);
void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
+static void __init set_return_thunk(void *thunk)
+{
+ if (x86_return_thunk != __x86_return_thunk)
+ pr_warn("x86/bugs: return thunk changed\n");
+
+ x86_return_thunk = thunk;
+}
+
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
static void update_spec_ctrl(u64 val)
{
@@ -178,6 +187,7 @@ void __init cpu_select_mitigations(void)
*/
srso_select_mitigation();
gds_select_mitigation();
+ its_select_mitigation();
}
/*
@@ -1118,7 +1128,7 @@ static void __init retbleed_select_mitigation(void)
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_UNRET);
- x86_return_thunk = retbleed_return_thunk;
+ set_return_thunk(retbleed_return_thunk);
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -1153,7 +1163,7 @@ static void __init retbleed_select_mitigation(void)
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
- x86_return_thunk = call_depth_return_thunk;
+ set_return_thunk(call_depth_return_thunk);
break;
default:
@@ -1188,6 +1198,145 @@ static void __init retbleed_select_mitigation(void)
}
#undef pr_fmt
+#define pr_fmt(fmt) "ITS: " fmt
+
+enum its_mitigation_cmd {
+ ITS_CMD_OFF,
+ ITS_CMD_ON,
+ ITS_CMD_VMEXIT,
+ ITS_CMD_RSB_STUFF,
+};
+
+enum its_mitigation {
+ ITS_MITIGATION_OFF,
+ ITS_MITIGATION_VMEXIT_ONLY,
+ ITS_MITIGATION_ALIGNED_THUNKS,
+ ITS_MITIGATION_RETPOLINE_STUFF,
+};
+
+static const char * const its_strings[] = {
+ [ITS_MITIGATION_OFF] = "Vulnerable",
+ [ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected",
+ [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks",
+ [ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB",
+};
+
+static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS;
+
+static enum its_mitigation_cmd its_cmd __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF;
+
+static int __init its_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) {
+ pr_err("Mitigation disabled at compile time, ignoring option (%s)", str);
+ return 0;
+ }
+
+ if (!strcmp(str, "off")) {
+ its_cmd = ITS_CMD_OFF;
+ } else if (!strcmp(str, "on")) {
+ its_cmd = ITS_CMD_ON;
+ } else if (!strcmp(str, "force")) {
+ its_cmd = ITS_CMD_ON;
+ setup_force_cpu_bug(X86_BUG_ITS);
+ } else if (!strcmp(str, "vmexit")) {
+ its_cmd = ITS_CMD_VMEXIT;
+ } else if (!strcmp(str, "stuff")) {
+ its_cmd = ITS_CMD_RSB_STUFF;
+ } else {
+ pr_err("Ignoring unknown indirect_target_selection option (%s).", str);
+ }
+
+ return 0;
+}
+early_param("indirect_target_selection", its_parse_cmdline);
+
+static void __init its_select_mitigation(void)
+{
+ enum its_mitigation_cmd cmd = its_cmd;
+
+ if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) {
+ its_mitigation = ITS_MITIGATION_OFF;
+ return;
+ }
+
+ /* Retpoline+CDT mitigates ITS, bail out */
+ if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ boot_cpu_has(X86_FEATURE_CALL_DEPTH)) {
+ its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+ goto out;
+ }
+
+ /* Exit early to avoid irrelevant warnings */
+ if (cmd == ITS_CMD_OFF) {
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (spectre_v2_enabled == SPECTRE_V2_NONE) {
+ pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ||
+ !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) {
+ pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) {
+ pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+ if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
+ pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ goto out;
+ }
+
+ if (cmd == ITS_CMD_RSB_STUFF &&
+ (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) {
+ pr_err("RSB stuff mitigation not supported, using default\n");
+ cmd = ITS_CMD_ON;
+ }
+
+ switch (cmd) {
+ case ITS_CMD_OFF:
+ its_mitigation = ITS_MITIGATION_OFF;
+ break;
+ case ITS_CMD_VMEXIT:
+ if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) {
+ its_mitigation = ITS_MITIGATION_VMEXIT_ONLY;
+ goto out;
+ }
+ fallthrough;
+ case ITS_CMD_ON:
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+ if (!boot_cpu_has(X86_FEATURE_RETPOLINE))
+ setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS);
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+ set_return_thunk(its_return_thunk);
+ break;
+ case ITS_CMD_RSB_STUFF:
+ its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+ setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
+ set_return_thunk(call_depth_return_thunk);
+ if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) {
+ retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+ pr_info("Retbleed mitigation updated to stuffing\n");
+ }
+ break;
+ }
+out:
+ pr_info("%s\n", its_strings[its_mitigation]);
+}
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
@@ -1697,11 +1846,11 @@ static void __init bhi_select_mitigation(void)
return;
}
- /* Mitigate in hardware if supported */
- if (spec_ctrl_bhi_dis())
+ if (!IS_ENABLED(CONFIG_X86_64))
return;
- if (!IS_ENABLED(CONFIG_X86_64))
+ /* Mitigate in hardware if supported */
+ if (spec_ctrl_bhi_dis())
return;
if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
@@ -2607,10 +2756,10 @@ static void __init srso_select_mitigation(void)
if (boot_cpu_data.x86 == 0x19) {
setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
- x86_return_thunk = srso_alias_return_thunk;
+ set_return_thunk(srso_alias_return_thunk);
} else {
setup_force_cpu_cap(X86_FEATURE_SRSO);
- x86_return_thunk = srso_return_thunk;
+ set_return_thunk(srso_return_thunk);
}
if (has_microcode)
srso_mitigation = SRSO_MITIGATION_SAFE_RET;
@@ -2800,6 +2949,11 @@ static ssize_t rfds_show_state(char *buf)
return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
}
+static ssize_t its_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]);
+}
+
static char *stibp_state(void)
{
if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
@@ -2982,6 +3136,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_RFDS:
return rfds_show_state(buf);
+ case X86_BUG_ITS:
+ return its_show_state(buf);
+
default:
break;
}
@@ -3061,6 +3218,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib
{
return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
}
+
+ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
+}
#endif
void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 12126ad..0ff057f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1227,6 +1227,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define GDS BIT(6)
/* CPU is affected by Register File Data Sampling */
#define RFDS BIT(7)
+/* CPU is affected by Indirect Target Selection */
+#define ITS BIT(8)
+/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
+#define ITS_NATIVE_ONLY BIT(9)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
@@ -1238,22 +1242,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS),
VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO),
VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS),
VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS),
VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED),
- VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS),
- VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS),
- VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY),
+ VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS),
VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS),
VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS),
@@ -1318,6 +1325,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr)
return cpu_matches(cpu_vuln_blacklist, RFDS);
}
+static bool __init vulnerable_to_its(u64 x86_arch_cap_msr)
+{
+ /* The "immunity" bit trumps everything else: */
+ if (x86_arch_cap_msr & ARCH_CAP_ITS_NO)
+ return false;
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return false;
+
+ /* None of the affected CPUs have BHI_CTRL */
+ if (boot_cpu_has(X86_FEATURE_BHI_CTRL))
+ return false;
+
+ /*
+ * If a VMM did not expose ITS_NO, assume that a guest could
+ * be running on a vulnerable hardware or may migrate to such
+ * hardware.
+ */
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return true;
+
+ if (cpu_matches(cpu_vuln_blacklist, ITS))
+ return true;
+
+ return false;
+}
+
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
@@ -1439,9 +1472,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (vulnerable_to_rfds(x86_arch_cap_msr))
setup_force_cpu_bug(X86_BUG_RFDS);
- /* When virtualized, eIBRS could be hidden, assume vulnerable */
- if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) &&
- !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+ /*
+ * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with
+ * BHI_NO still need to use the BHI mitigation to prevent Intra-mode
+ * attacks. When virtualized, eIBRS could be hidden, assume vulnerable.
+ */
+ if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
(boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
boot_cpu_has(X86_FEATURE_HYPERVISOR)))
setup_force_cpu_bug(X86_BUG_BHI);
@@ -1449,6 +1485,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET))
setup_force_cpu_bug(X86_BUG_IBPB_NO_RET);
+ if (vulnerable_to_its(x86_arch_cap_msr)) {
+ setup_force_cpu_bug(X86_BUG_ITS);
+ if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY))
+ setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
+ }
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4a10d35..96cb992 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -1098,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
static int __init save_microcode_in_initrd(void)
{
- unsigned int cpuid_1_eax = native_cpuid_eax(1);
struct cpuinfo_x86 *c = &boot_cpu_data;
struct cont_desc desc = { 0 };
+ unsigned int cpuid_1_eax;
enum ucode_state ret;
struct cpio_data cp;
- if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+ if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
return 0;
+ cpuid_1_eax = native_cpuid_eax(1);
+
if (!find_blobs_in_containers(&cp))
return -EINVAL;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3658d1..079f046 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,8 @@
#include "internal.h"
-static struct microcode_ops *microcode_ops;
-bool dis_ucode_ldr = true;
+static struct microcode_ops *microcode_ops;
+static bool dis_ucode_ldr = false;
bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
@@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void)
u32 lvl, dummy, i;
u32 *levels;
+ if (x86_cpuid_vendor() != X86_VENDOR_AMD)
+ return false;
+
native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
levels = final_levels;
@@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void)
return false;
}
-static bool __init check_loader_disabled_bsp(void)
+bool __init microcode_loader_disabled(void)
{
- static const char *__dis_opt_str = "dis_ucode_ldr";
- const char *cmdline = boot_command_line;
- const char *option = __dis_opt_str;
-
- /*
- * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
- * completely accurate as xen pv guests don't see that CPUID bit set but
- * that's good enough as they don't land on the BSP path anyway.
- */
- if (native_cpuid_ecx(1) & BIT(31))
+ if (dis_ucode_ldr)
return true;
- if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
- if (amd_check_current_patch_level())
- return true;
- }
-
- if (cmdline_find_option_bool(cmdline, option) <= 0)
- dis_ucode_ldr = false;
+ /*
+ * Disable when:
+ *
+ * 1) The CPU does not support CPUID.
+ *
+ * 2) Bit 31 in CPUID[1]:ECX is clear
+ * The bit is reserved for hypervisor use. This is still not
+ * completely accurate as XEN PV guests don't see that CPUID bit
+ * set, but that's good enough as they don't land on the BSP
+ * path anyway.
+ *
+ * 3) Certain AMD patch levels are not allowed to be
+ * overwritten.
+ */
+ if (!have_cpuid_p() ||
+ native_cpuid_ecx(1) & BIT(31) ||
+ amd_check_current_patch_level())
+ dis_ucode_ldr = true;
return dis_ucode_ldr;
}
@@ -125,7 +130,10 @@ void __init load_ucode_bsp(void)
unsigned int cpuid_1_eax;
bool intel = true;
- if (!have_cpuid_p())
+ if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0)
+ dis_ucode_ldr = true;
+
+ if (microcode_loader_disabled())
return;
cpuid_1_eax = native_cpuid_eax(1);
@@ -146,9 +154,6 @@ void __init load_ucode_bsp(void)
return;
}
- if (check_loader_disabled_bsp())
- return;
-
if (intel)
load_ucode_intel_bsp(&early_data);
else
@@ -159,6 +164,11 @@ void load_ucode_ap(void)
{
unsigned int cpuid_1_eax;
+ /*
+ * Can't use microcode_loader_disabled() here - .init section
+ * hell. It doesn't have to either - the BSP variant must've
+ * parsed cmdline already anyway.
+ */
if (dis_ucode_ldr)
return;
@@ -810,7 +820,7 @@ static int __init microcode_init(void)
struct cpuinfo_x86 *c = &boot_cpu_data;
int error;
- if (dis_ucode_ldr)
+ if (microcode_loader_disabled())
return -EINVAL;
if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 819199b..2a397da 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void)
if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
return 0;
- if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return 0;
uci.mc = get_microcode_blob(&uci, true);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 5df6217..50a9702 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void)
return x86_family(eax);
}
-extern bool dis_ucode_ldr;
extern bool force_minrev;
#ifdef CONFIG_CPU_SUP_AMD
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 9d8dd8d..9920122 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1299,6 +1299,14 @@ void __init e820__memblock_setup(void)
memblock_add(entry->addr, entry->size);
}
+ /*
+ * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+ * to even less without it.
+ * Discard memory after max_pfn - the actual limit detected at runtime.
+ */
+ if (IS_ENABLED(CONFIG_X86_32))
+ memblock_remove(PFN_PHYS(max_pfn), -1);
+
/* Throw away partial pages: */
memblock_trim_memory(PAGE_SIZE);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index cace6e8..5eb1514 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
goto fail;
ip = trampoline + size;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk_at(ip))
__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
else
memcpy(ip, retq, sizeof(retq));
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index de001b2..375f2d7 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void)
*ptr = (unsigned long)ptep + PAGE_OFFSET;
#ifdef CONFIG_MICROCODE_INITRD32
- /* Running on a hypervisor? */
- if (native_cpuid_ecx(1) & BIT(31))
- return;
-
params = (struct boot_params *)__pa_nodebug(&boot_params);
if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image)
return;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 8026516..1f32530 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -42,7 +42,7 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
- free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
@@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image)
static int machine_kexec_alloc_page_tables(struct kimage *image)
{
image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- PGD_ALLOCATION_ORDER);
+ pgd_allocation_order());
#ifdef CONFIG_X86_PAE
image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index a7998f3..ff07558 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr,
ibt_endbr = s;
}
+ its_init_mod(me);
+
if (retpolines || cfi) {
void *rseg = NULL, *cseg = NULL;
unsigned int rsize = 0, csize = 0;
@@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr,
void *rseg = (void *)retpolines->sh_addr;
apply_retpolines(rseg, rseg + retpolines->sh_size);
}
+
+ its_fini_mod(me);
+
if (returns) {
void *rseg = (void *)returns->sh_addr;
apply_returns(rseg, rseg + returns->sh_size);
@@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr,
void module_arch_cleanup(struct module *mod)
{
alternatives_smp_module_del(mod);
+ its_free_mod(mod);
}
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index a59c72e..c3d7ff4 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
break;
case RET:
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk_at(insn))
code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
else
code = &retinsn;
@@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
case JCC:
if (!func) {
func = __static_call_return;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ if (cpu_wants_rethunk())
func = x86_return_thunk;
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index ccdc45e..cda5f83 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -466,10 +466,18 @@
}
/*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this. Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
*/
. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
"kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
/* needed for Clang - see arch/x86/entry/entry.S */
PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
@@ -497,6 +505,16 @@
"SRSO function pair won't alias");
#endif
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline");
+. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart");
+. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array");
+#endif
+
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline");
+#endif
+
#endif /* CONFIG_X86_64 */
/*
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 050a0e2..f2b36d3 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
+ if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
+ kvm_mmu_free_obsolete_roots(vcpu);
+
/*
* Checking root.hpa is sufficient even when KVM has mirror root.
* We can have either:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 63bb77e..8d1b632 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu);
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
}
+EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots);
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
int *bytes)
@@ -7669,32 +7670,6 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
}
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
-bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
- struct kvm_gfn_range *range)
-{
- /*
- * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only
- * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
- * can simply ignore such slots. But if userspace is making memory
- * PRIVATE, then KVM must prevent the guest from accessing the memory
- * as shared. And if userspace is making memory SHARED and this point
- * is reached, then at least one page within the range was previously
- * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
- * Zapping SPTEs in this case ensures KVM will reassess whether or not
- * a hugepage can be used for affected ranges.
- */
- if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
- return false;
-
- /* Unmap the old attribute page. */
- if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
- range->attr_filter = KVM_FILTER_SHARED;
- else
- range->attr_filter = KVM_FILTER_PRIVATE;
-
- return kvm_unmap_gfn_range(kvm, range);
-}
-
static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
int level)
{
@@ -7713,6 +7688,69 @@ static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
}
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range)
+{
+ struct kvm_memory_slot *slot = range->slot;
+ int level;
+
+ /*
+ * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only
+ * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
+ * can simply ignore such slots. But if userspace is making memory
+ * PRIVATE, then KVM must prevent the guest from accessing the memory
+ * as shared. And if userspace is making memory SHARED and this point
+ * is reached, then at least one page within the range was previously
+ * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
+ * Zapping SPTEs in this case ensures KVM will reassess whether or not
+ * a hugepage can be used for affected ranges.
+ */
+ if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+ return false;
+
+ if (WARN_ON_ONCE(range->end <= range->start))
+ return false;
+
+ /*
+ * If the head and tail pages of the range currently allow a hugepage,
+ * i.e. reside fully in the slot and don't have mixed attributes, then
+ * add each corresponding hugepage range to the ongoing invalidation,
+ * e.g. to prevent KVM from creating a hugepage in response to a fault
+ * for a gfn whose attributes aren't changing. Note, only the range
+ * of gfns whose attributes are being modified needs to be explicitly
+ * unmapped, as that will unmap any existing hugepages.
+ */
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ gfn_t start = gfn_round_for_level(range->start, level);
+ gfn_t end = gfn_round_for_level(range->end - 1, level);
+ gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+
+ if ((start != range->start || start + nr_pages > range->end) &&
+ start >= slot->base_gfn &&
+ start + nr_pages <= slot->base_gfn + slot->npages &&
+ !hugepage_test_mixed(slot, start, level))
+ kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
+
+ if (end == start)
+ continue;
+
+ if ((end + nr_pages) > range->end &&
+ (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+ !hugepage_test_mixed(slot, end, level))
+ kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+ }
+
+ /* Unmap the old attribute page. */
+ if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
+ range->attr_filter = KVM_FILTER_SHARED;
+ else
+ range->attr_filter = KVM_FILTER_PRIVATE;
+
+ return kvm_unmap_gfn_range(kvm, range);
+}
+
+
+
static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, int level, unsigned long attrs)
{
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index 699e551..9864c05 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
kvm_mmu_reset_context(vcpu);
}
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
void process_smi(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 65fd245..7338879 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -796,12 +796,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
struct amd_svm_iommu_ir *ir;
u64 entry;
+ if (WARN_ON_ONCE(!pi->ir_data))
+ return -EINVAL;
+
/**
* In some cases, the existing irte is updated and re-set,
* so we need to check here if it's already been * added
* to the ir_list.
*/
- if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+ if (pi->prev_ga_tag) {
struct kvm *kvm = svm->vcpu.kvm;
u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
@@ -820,7 +823,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
* Allocating new amd_iommu_pi_data, which will get
* add to the per-vcpu ir_list.
*/
- ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
if (!ir) {
ret = -ENOMEM;
goto out;
@@ -896,10 +899,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
return 0;
pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
@@ -933,6 +936,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_vcpu_apicv_active(&svm->vcpu)) {
struct amd_iommu_pi_data pi;
+ enable_remapped_mode = false;
+
/* Try to enable guest_mode in IRTE */
pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
AVIC_HPA_MASK);
@@ -951,33 +956,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
*/
if (!ret && pi.is_guest_mode)
svm_ir_list_add(svm, &pi);
- } else {
- /* Use legacy mode in IRTE */
- struct amd_iommu_pi_data pi;
-
- /**
- * Here, pi is used to:
- * - Tell IOMMU to use legacy mode for this interrupt.
- * - Retrieve ga_tag of prior interrupt remapping data.
- */
- pi.prev_ga_tag = 0;
- pi.is_guest_mode = false;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
-
- /**
- * Check if the posted interrupt was previously
- * setup with the guest_mode by checking if the ga_tag
- * was cached. If so, we need to clean up the per-vcpu
- * ir_list.
- */
- if (!ret && pi.prev_ga_tag) {
- int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
- struct kvm_vcpu *vcpu;
-
- vcpu = kvm_get_vcpu_by_id(kvm, id);
- if (vcpu)
- svm_ir_list_del(to_svm(vcpu), &pi);
- }
}
if (!ret && svm) {
@@ -993,6 +971,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
ret = 0;
+ if (enable_remapped_mode) {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.prev_ga_tag = 0;
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0bc708e..a7a7dc5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3173,9 +3173,14 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
kvfree(svm->sev_es.ghcb_sa);
}
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+ return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
static void dump_ghcb(struct vcpu_svm *svm)
{
- struct ghcb *ghcb = svm->sev_es.ghcb;
+ struct vmcb_control_area *control = &svm->vmcb->control;
unsigned int nbits;
/* Re-use the dump_invalid_vmcb module parameter */
@@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm)
return;
}
- nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+ nbits = sizeof(svm->sev_es.valid_bitmap) * 8;
- pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+ /*
+ * Print KVM's snapshot of the GHCB values that were (unsuccessfully)
+ * used to handle the exit. If the guest has since modified the GHCB
+ * itself, dumping the raw GHCB won't help debug why KVM was unable to
+ * handle the VMGEXIT that KVM observed.
+ */
+ pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
- ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+ kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
- ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+ control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
- ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+ control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm));
pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
- ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
- pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+ svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm));
+ pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap);
}
static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
@@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
}
-static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
-{
- return (((u64)control->exit_code_hi) << 32) | control->exit_code;
-}
-
static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d5d0c5c..a89c271 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void)
kvm_cpu_svm_disable();
amd_pmu_disable_virt();
-
- if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
- msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
}
static int svm_enable_virtualization_cpu(void)
@@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void)
rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
}
- if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
- msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
-
return 0;
}
@@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
}
+#ifdef CONFIG_CPU_MITIGATIONS
+static DEFINE_SPINLOCK(srso_lock);
+static atomic_t srso_nr_vms;
+
+static void svm_srso_clear_bp_spec_reduce(void *ign)
+{
+ struct svm_cpu_data *sd = this_cpu_ptr(&svm_data);
+
+ if (!sd->bp_spec_reduce_set)
+ return;
+
+ msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+ sd->bp_spec_reduce_set = false;
+}
+
+static void svm_srso_vm_destroy(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+ return;
+
+ if (atomic_dec_return(&srso_nr_vms))
+ return;
+
+ guard(spinlock)(&srso_lock);
+
+ /*
+ * Verify a new VM didn't come along, acquire the lock, and increment
+ * the count before this task acquired the lock.
+ */
+ if (atomic_read(&srso_nr_vms))
+ return;
+
+ on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1);
+}
+
+static void svm_srso_vm_init(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+ return;
+
+ /*
+ * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0
+ * transition, i.e. destroying the last VM, is fully complete, e.g. so
+ * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs.
+ */
+ if (atomic_inc_not_zero(&srso_nr_vms))
+ return;
+
+ guard(spinlock)(&srso_lock);
+
+ atomic_inc(&srso_nr_vms);
+}
+#else
+static void svm_srso_vm_init(void) { }
+static void svm_srso_vm_destroy(void) { }
+#endif
+
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
(!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
+ if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) &&
+ !sd->bp_spec_reduce_set) {
+ sd->bp_spec_reduce_set = true;
+ msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+ }
svm->guest_state_loaded = true;
}
@@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
*/
if (!sev_es_guest(vcpu->kvm)) {
clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+ if (is_smm(vcpu))
+ kvm_smm_changed(vcpu, false);
+#endif
kvm_vcpu_reset(vcpu, true);
}
@@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm)
{
avic_vm_destroy(kvm);
sev_vm_destroy(kvm);
+
+ svm_srso_vm_destroy();
}
static int svm_vm_init(struct kvm *kvm)
@@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm)
return ret;
}
+ svm_srso_vm_init();
return 0;
}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index d4490ea..f16b068 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -335,6 +335,8 @@ struct svm_cpu_data {
u32 next_asid;
u32 min_asid;
+ bool bp_spec_reduce_set;
+
struct vmcb *save_area;
unsigned long save_area_pa;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ccda95e53..ba736cb 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -11,6 +11,13 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({ \
+ typeof(vcpu) __vcpu = vcpu; \
+ __vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu); \
+ })
+#endif
+
/*
* Tracepoint for guest mode entry.
*/
@@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->rip = kvm_rip_read(vcpu);
+ __entry->rip = tracing_kvm_rip_read(vcpu);
__entry->immediate_exit = force_immediate_exit;
kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
@@ -319,7 +326,7 @@ TRACE_EVENT(name, \
), \
\
TP_fast_assign( \
- __entry->guest_rip = kvm_rip_read(vcpu); \
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu); \
__entry->isa = isa; \
__entry->vcpu_id = vcpu->vcpu_id; \
__entry->requests = READ_ONCE(vcpu->requests); \
@@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->guest_rip = kvm_rip_read(vcpu);
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu);
__entry->fault_address = fault_address;
__entry->error_code = error_code;
),
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 51116fe..d70e5b9 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -297,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
@@ -335,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_set_msi_irq(kvm, e, &irq);
if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq)) {
- /*
- * Make sure the IRTE is in remapped mode if
- * we don't handle it in posted mode.
- */
- ret = irq_set_vcpu_affinity(host_irq, NULL);
- if (ret < 0) {
- printk(KERN_INFO
- "failed to back to remapped mode, irq: %u\n",
- host_irq);
- goto out;
- }
-
+ !kvm_irq_is_postable(&irq))
continue;
- }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
@@ -357,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
- if (set)
- ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else
- ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (!set)
+ continue;
+ enable_remapped_mode = false;
+
+ ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
__func__);
@@ -369,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
}
+ if (enable_remapped_mode)
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+
ret = 0;
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3712dde..be7bb6d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1584,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
- ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
+ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO)
static u64 kvm_get_arch_capabilities(void)
{
@@ -1618,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void)
data |= ARCH_CAP_MDS_NO;
if (!boot_cpu_has_bug(X86_BUG_RFDS))
data |= ARCH_CAP_RFDS_NO;
+ if (!boot_cpu_has_bug(X86_BUG_ITS))
+ data |= ARCH_CAP_ITS_NO;
if (!boot_cpu_has(X86_FEATURE_RTM)) {
/*
@@ -4597,7 +4599,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
}
-static inline u32 kvm_sync_valid_fields(struct kvm *kvm)
+static inline u64 kvm_sync_valid_fields(struct kvm *kvm)
{
return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
}
@@ -11098,7 +11100,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
/*
* Profile KVM exit RIPs:
*/
- if (unlikely(prof_on == KVM_PROFILING)) {
+ if (unlikely(prof_on == KVM_PROFILING &&
+ !vcpu->arch.guest_state_protected)) {
unsigned long rip = kvm_rip_read(vcpu);
profile_hit(KVM_PROFILING, (void *)rip);
}
@@ -11492,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_queued_exception *ex = &vcpu->arch.exception;
struct kvm_run *kvm_run = vcpu->run;
- u32 sync_valid_fields;
+ u64 sync_valid_fields;
int r;
r = kvm_mmu_post_init_vm(vcpu->kvm);
@@ -13556,25 +13559,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
-bool kvm_arch_has_irq_bypass(void)
-{
- return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
int ret;
- irqfd->producer = prod;
kvm_arch_start_assignment(irqfd->kvm);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = prod;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 1);
if (ret)
kvm_arch_end_assignment(irqfd->kvm);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
return ret;
}
@@ -13584,9 +13589,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
int ret;
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
WARN_ON(irqfd->producer != prod);
- irqfd->producer = NULL;
/*
* When producer of consumer is unregistered, we change back to
@@ -13594,12 +13599,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
* when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = NULL;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 0);
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
kvm_arch_end_assignment(irqfd->kvm);
}
@@ -13612,7 +13623,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
struct kvm_kernel_irq_routing_entry *new)
{
- if (new->type != KVM_IRQ_ROUTING_MSI)
+ if (old->type != KVM_IRQ_ROUTING_MSI ||
+ new->type != KVM_IRQ_ROUTING_MSI)
return true;
return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index a26c43ab..3937494 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -367,6 +367,54 @@
#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
+#ifdef CONFIG_MITIGATION_ITS
+
+.macro ITS_THUNK reg
+
+/*
+ * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b)
+ * that complete the fineibt_paranoid caller sequence.
+ */
+1: .byte 0xea
+SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ jne 1b
+SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ ANNOTATE_RETPOLINE_SAFE
+ jmp *%\reg
+ int3
+ .align 32, 0xcc /* fill to the end of the line */
+ .skip 32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */
+.endm
+
+/* ITS mitigation requires thunks be aligned to upper half of cacheline */
+.align 64, 0xcc
+.skip 29, 0xcc
+
+#define GEN(reg) ITS_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+ .align 64, 0xcc
+SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax)
+SYM_CODE_END(__x86_indirect_its_thunk_array)
+
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
+
/*
* This function name is magical and is used by -mfunction-return=thunk-extern
* for the compiler to generate JMPs to it.
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3e..f5dd84e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ad662cc..bb8d99e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,6 +30,7 @@
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>
+#include <linux/execmem.h>
#include <asm/asm.h>
#include <asm/bios_ebda.h>
@@ -565,7 +566,7 @@ static void __init lowmem_pfn_init(void)
"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
#define MSG_HIGHMEM_TRIMMED \
- "Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n"
+ "Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n"
/*
* We have more RAM than fits into lowmem - we try to put it into
* highmem, also taking the highmem=x boot parameter into account:
@@ -755,6 +756,8 @@ void mark_rodata_ro(void)
pr_info("Write protecting kernel text and read-only data: %luk\n",
size >> 10);
+ execmem_cache_make_ro();
+
kernel_set_to_readonly = 1;
#ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7c4f6f5..949a447 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,6 +34,7 @@
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/bootmem_info.h>
+#include <linux/execmem.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
@@ -1391,6 +1392,8 @@ void mark_rodata_ro(void)
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+ execmem_cache_make_ro();
+
kernel_set_to_readonly = 1;
/*
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a05fcdd..f7ae44d3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
* We allocate one page for pgd.
*/
if (!SHARED_KERNEL_PMD)
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
/*
* Now PAE kernel is not running as a Xen domain. We can allocate
@@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
{
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
}
static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index eb83348f..b6d6750 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -899,8 +899,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
cond_mitigation(tsk);
/*
- * Let nmi_uaccess_okay() and finish_asid_transition()
- * know that CR3 is changing.
+ * Indicate that CR3 is about to change. nmi_uaccess_okay()
+ * and others are sensitive to the window where mm_cpumask(),
+ * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
*/
this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
barrier();
@@ -1204,8 +1205,16 @@ static void flush_tlb_func(void *info)
static bool should_flush_tlb(int cpu, void *data)
{
+ struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu);
struct flush_tlb_info *info = data;
+ /*
+ * Order the 'loaded_mm' and 'is_lazy' against their
+ * write ordering in switch_mm_irqs_off(). Ensure
+ * 'is_lazy' is at least as new as 'loaded_mm'.
+ */
+ smp_rmb();
+
/* Lazy TLB will get flushed at the next context switch. */
if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
return false;
@@ -1214,8 +1223,15 @@ static bool should_flush_tlb(int cpu, void *data)
if (!info->mm)
return true;
+ /*
+ * While switching, the remote CPU could have state from
+ * either the prev or next mm. Assume the worst and flush.
+ */
+ if (loaded_mm == LOADED_MM_SWITCHING)
+ return true;
+
/* The target mm is loaded, and the CPU is not lazy. */
- if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+ if (loaded_mm == info->mm)
return true;
/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9e5fe2b..ea4dd5b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+#define EMIT5(b1, b2, b3, b4, b5) \
+ do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0)
#define EMIT1_off32(b1, off) \
do { EMIT1(b1); EMIT(off, 4); } while (0)
@@ -661,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
{
u8 *prog = *pprog;
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+ if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) {
+ OPTIMIZER_HIDE_VAR(reg);
+ emit_jump(&prog, its_static_thunk(reg), ip);
+ } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
EMIT_LFENCE();
EMIT2(0xFF, 0xE0 + reg);
} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
@@ -683,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip)
{
u8 *prog = *pprog;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+ if (cpu_wants_rethunk()) {
emit_jump(&prog, x86_return_thunk, ip);
} else {
EMIT1(0xC3); /* ret */
@@ -1502,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
#define PRIV_STACK_GUARD_SZ 8
#define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL
+static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
+ struct bpf_prog *bpf_prog)
+{
+ u8 *prog = *pprog;
+ u8 *func;
+
+ if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) {
+ /* The clearing sequence clobbers eax and ecx. */
+ EMIT1(0x50); /* push rax */
+ EMIT1(0x51); /* push rcx */
+ ip += 2;
+
+ func = (u8 *)clear_bhb_loop;
+ ip += x86_call_depth_emit_accounting(&prog, func, ip);
+
+ if (emit_call(&prog, func, ip))
+ return -EINVAL;
+ EMIT1(0x59); /* pop rcx */
+ EMIT1(0x58); /* pop rax */
+ }
+ /* Insert IBHF instruction */
+ if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) &&
+ cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) ||
+ cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) {
+ /*
+ * Add an Indirect Branch History Fence (IBHF). IBHF acts as a
+ * fence preventing branch history from before the fence from
+ * affecting indirect branches after the fence. This is
+ * specifically used in cBPF jitted code to prevent Intra-mode
+ * BHI attacks. The IBHF instruction is designed to be a NOP on
+ * hardware that doesn't need or support it. The REP and REX.W
+ * prefixes are required by the microcode, and they also ensure
+ * that the NOP is unlikely to be used in existing code.
+ *
+ * IBHF is not a valid instruction in 32-bit mode.
+ */
+ EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */
+ }
+ *pprog = prog;
+ return 0;
+}
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
@@ -2544,6 +2591,13 @@ st: if (is_imm8(insn->off))
seen_exit = true;
/* Update cleanup_addr */
ctx->cleanup_addr = proglen;
+ if (bpf_prog_was_classic(bpf_prog) &&
+ !capable(CAP_SYS_ADMIN)) {
+ u8 *ip = image + addrs[i - 1];
+
+ if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
+ return -EINVAL;
+ }
if (bpf_prog->aux->exception_boundary) {
pop_callee_regs(&prog, all_callee_regs_used);
pop_r12(&prog);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac57259..a4b4ebd 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void)
gfp_t gfp_mask;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
if (!efi_pgd)
goto fail;
@@ -96,7 +96,7 @@ int __init efi_alloc_page_tables(void)
if (pgtable_l5_enabled())
free_page((unsigned long)pgd_page_vaddr(*pgd));
free_pgd:
- free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)efi_pgd, pgd_allocation_order());
fail:
return -ENOMEM;
}
diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
index ab5c8e4..9193a77 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_32.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -31,8 +31,8 @@ struct faultinfo {
#define ___backtrack_faulted(_faulted) \
asm volatile ( \
- "mov $0, %0\n" \
"movl $__get_kernel_nofault_faulted_%=,%1\n" \
+ "mov $0, %0\n" \
"jmp _end_%=\n" \
"__get_kernel_nofault_faulted_%=:\n" \
"mov $1, %0;" \
diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
index 26fb483..61e4ca1 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_64.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -31,8 +31,8 @@ struct faultinfo {
#define ___backtrack_faulted(_faulted) \
asm volatile ( \
- "mov $0, %0\n" \
"movq $__get_kernel_nofault_faulted_%=,%1\n" \
+ "mov $0, %0\n" \
"jmp _end_%=\n" \
"__get_kernel_nofault_faulted_%=:\n" \
"mov $1, %0;" \
diff --git a/block/bdev.c b/block/bdev.c
index 6a34179..889ec6e 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -152,27 +152,65 @@ static void set_init_blocksize(struct block_device *bdev)
get_order(bsize));
}
+/**
+ * bdev_validate_blocksize - check that this block size is acceptable
+ * @bdev: blockdevice to check
+ * @block_size: block size to check
+ *
+ * For block device users that do not use buffer heads or the block device
+ * page cache, make sure that this block size can be used with the device.
+ *
+ * Return: On success zero is returned, negative error code on failure.
+ */
+int bdev_validate_blocksize(struct block_device *bdev, int block_size)
+{
+ if (blk_validate_block_size(block_size))
+ return -EINVAL;
+
+ /* Size cannot be smaller than the size supported by the device */
+ if (block_size < bdev_logical_block_size(bdev))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_validate_blocksize);
+
int set_blocksize(struct file *file, int size)
{
struct inode *inode = file->f_mapping->host;
struct block_device *bdev = I_BDEV(inode);
+ int ret;
- if (blk_validate_block_size(size))
- return -EINVAL;
-
- /* Size cannot be smaller than the size supported by the device */
- if (size < bdev_logical_block_size(bdev))
- return -EINVAL;
+ ret = bdev_validate_blocksize(bdev, size);
+ if (ret)
+ return ret;
if (!file->private_data)
return -EINVAL;
/* Don't change the size if it is same as current */
if (inode->i_blkbits != blksize_bits(size)) {
+ /*
+ * Flush and truncate the pagecache before we reconfigure the
+ * mapping geometry because folio sizes are variable now. If a
+ * reader has already allocated a folio whose size is smaller
+ * than the new min_order but invokes readahead after the new
+ * min_order becomes visible, readahead will think there are
+ * "zero" blocks per folio and crash. Take the inode and
+ * invalidation locks to avoid racing with
+ * read/write/fallocate.
+ */
+ inode_lock(inode);
+ filemap_invalidate_lock(inode->i_mapping);
+
sync_blockdev(bdev);
+ kill_bdev(bdev);
+
inode->i_blkbits = blksize_bits(size);
mapping_set_folio_min_order(inode->i_mapping, get_order(size));
kill_bdev(bdev);
+ filemap_invalidate_unlock(inode->i_mapping);
+ inode_unlock(inode);
}
return 0;
}
@@ -777,13 +815,13 @@ static void blkdev_put_part(struct block_device *part)
blkdev_put_whole(whole);
}
-struct block_device *blkdev_get_no_open(dev_t dev)
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload)
{
struct block_device *bdev;
struct inode *inode;
inode = ilookup(blockdev_superblock, dev);
- if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
+ if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
blk_request_module(dev);
inode = ilookup(blockdev_superblock, dev);
if (inode)
@@ -1005,7 +1043,7 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
if (ret)
return ERR_PTR(ret);
- bdev = blkdev_get_no_open(dev);
+ bdev = blkdev_get_no_open(dev, true);
if (!bdev)
return ERR_PTR(-ENXIO);
@@ -1274,18 +1312,15 @@ void sync_bdevs(bool wait)
*/
void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask)
{
- struct inode *backing_inode;
struct block_device *bdev;
- backing_inode = d_backing_inode(path->dentry);
-
/*
- * Note that backing_inode is the inode of a block device node file,
- * not the block device's internal inode. Therefore it is *not* valid
- * to use I_BDEV() here; the block device has to be looked up by i_rdev
+ * Note that d_backing_inode() returns the block device node inode, not
+ * the block device's internal inode. Therefore it is *not* valid to
+ * use I_BDEV() here; the block device has to be looked up by i_rdev
* instead.
*/
- bdev = blkdev_get_no_open(backing_inode->i_rdev);
+ bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false);
if (!bdev)
return;
diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c
index e524c60..9c66576 100644
--- a/block/bio-integrity-auto.c
+++ b/block/bio-integrity-auto.c
@@ -9,6 +9,7 @@
* not aware of PI.
*/
#include <linux/blk-integrity.h>
+#include <linux/t10-pi.h>
#include <linux/workqueue.h>
#include "blk.h"
@@ -43,6 +44,29 @@ static void bio_integrity_verify_fn(struct work_struct *work)
bio_endio(bio);
}
+#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+static bool bip_should_check(struct bio_integrity_payload *bip)
+{
+ return bip->bip_flags & BIP_CHECK_FLAGS;
+}
+
+static bool bi_offload_capable(struct blk_integrity *bi)
+{
+ switch (bi->csum_type) {
+ case BLK_INTEGRITY_CSUM_CRC64:
+ return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+ case BLK_INTEGRITY_CSUM_CRC:
+ case BLK_INTEGRITY_CSUM_IP:
+ return bi->tuple_size == sizeof(struct t10_pi_tuple);
+ default:
+ pr_warn_once("%s: unknown integrity checksum type:%d\n",
+ __func__, bi->csum_type);
+ fallthrough;
+ case BLK_INTEGRITY_CSUM_NONE:
+ return false;
+ }
+}
+
/**
* __bio_integrity_endio - Integrity I/O completion function
* @bio: Protected bio
@@ -54,12 +78,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
*/
bool __bio_integrity_endio(struct bio *bio)
{
- struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
struct bio_integrity_payload *bip = bio_integrity(bio);
struct bio_integrity_data *bid =
container_of(bip, struct bio_integrity_data, bip);
- if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
+ if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
+ bip_should_check(bip)) {
INIT_WORK(&bid->work, bio_integrity_verify_fn);
queue_work(kintegrityd_wq, &bid->work);
return false;
@@ -84,6 +108,7 @@ bool bio_integrity_prep(struct bio *bio)
{
struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
struct bio_integrity_data *bid;
+ bool set_flags = true;
gfp_t gfp = GFP_NOIO;
unsigned int len;
void *buf;
@@ -100,19 +125,24 @@ bool bio_integrity_prep(struct bio *bio)
switch (bio_op(bio)) {
case REQ_OP_READ:
- if (bi->flags & BLK_INTEGRITY_NOVERIFY)
- return true;
+ if (bi->flags & BLK_INTEGRITY_NOVERIFY) {
+ if (bi_offload_capable(bi))
+ return true;
+ set_flags = false;
+ }
break;
case REQ_OP_WRITE:
- if (bi->flags & BLK_INTEGRITY_NOGENERATE)
- return true;
-
/*
* Zero the memory allocated to not leak uninitialized kernel
* memory to disk for non-integrity metadata where nothing else
* initializes the memory.
*/
- if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
+ if (bi->flags & BLK_INTEGRITY_NOGENERATE) {
+ if (bi_offload_capable(bi))
+ return true;
+ set_flags = false;
+ gfp |= __GFP_ZERO;
+ } else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
gfp |= __GFP_ZERO;
break;
default:
@@ -137,19 +167,21 @@ bool bio_integrity_prep(struct bio *bio)
bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY;
bip_set_seed(&bid->bip, bio->bi_iter.bi_sector);
- if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
- bid->bip.bip_flags |= BIP_IP_CHECKSUM;
- if (bi->csum_type)
- bid->bip.bip_flags |= BIP_CHECK_GUARD;
- if (bi->flags & BLK_INTEGRITY_REF_TAG)
- bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+ if (set_flags) {
+ if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
+ bid->bip.bip_flags |= BIP_IP_CHECKSUM;
+ if (bi->csum_type)
+ bid->bip.bip_flags |= BIP_CHECK_GUARD;
+ if (bi->flags & BLK_INTEGRITY_REF_TAG)
+ bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+ }
if (bio_integrity_add_page(bio, virt_to_page(buf), len,
offset_in_page(buf)) < len)
goto err_end_io;
/* Auto-generate integrity metadata if this is a write */
- if (bio_data_dir(bio) == WRITE)
+ if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip))
blk_integrity_generate(bio);
else
bid->saved_bio_iter = bio->bi_iter;
diff --git a/block/bio.c b/block/bio.c
index 4e6c85a..4be592d 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -611,7 +611,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask)
{
struct bio *bio;
- if (nr_vecs > UIO_MAXIOV)
+ if (nr_vecs > BIO_MAX_INLINE_VECS)
return NULL;
return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask);
}
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5905f27..ce93706 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -797,7 +797,7 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
return -EINVAL;
input = skip_spaces(input);
- bdev = blkdev_get_no_open(MKDEV(major, minor));
+ bdev = blkdev_get_no_open(MKDEV(major, minor), false);
if (!bdev)
return -ENODEV;
if (bdev_is_partition(bdev)) {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 6b2dbe6..4817e7c 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -61,8 +61,14 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi,
/*
* For read-ahead of large files to be effective, we need to read ahead
* at least twice the optimal I/O size.
+ *
+ * There is no hardware limitation for the read-ahead size and the user
+ * might have increased the read-ahead size through sysfs, so don't ever
+ * decrease it.
*/
- bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+ bdi->ra_pages = max3(bdi->ra_pages,
+ lim->io_opt * 2 / PAGE_SIZE,
+ VM_READAHEAD_PAGES);
bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
}
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 0c77244..8f15d1a 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -343,6 +343,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
op = REQ_OP_ZONE_RESET;
/* Invalidate the page cache, including dirty pages. */
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
if (ret)
@@ -364,8 +365,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
fail:
- if (cmd == BLKRESETZONE)
+ if (cmd == BLKRESETZONE) {
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
+ }
return ret;
}
diff --git a/block/blk.h b/block/blk.h
index 006e3be..594eeba 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -94,6 +94,9 @@ static inline void blk_wait_io(struct completion *done)
wait_for_completion_io(done);
}
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload);
+void blkdev_put_no_open(struct block_device *bdev);
+
#define BIO_INLINE_VECS 4
struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
gfp_t gfp_mask);
@@ -477,7 +480,8 @@ static inline void blk_zone_update_request_bio(struct request *rq,
* the original BIO sector so that blk_zone_write_plug_bio_endio() can
* lookup the zone write plug.
*/
- if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio))
+ if (req_op(rq) == REQ_OP_ZONE_APPEND ||
+ bio_flagged(bio, BIO_EMULATES_ZONE_APPEND))
bio->bi_iter.bi_sector = rq->__sector;
}
void blk_zone_write_plug_bio_endio(struct bio *bio);
diff --git a/block/fops.c b/block/fops.c
index be9f1db..82b672d 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -642,7 +642,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
if (ret)
return ret;
- bdev = blkdev_get_no_open(inode->i_rdev);
+ bdev = blkdev_get_no_open(inode->i_rdev, true);
if (!bdev)
return -ENXIO;
@@ -746,7 +746,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = direct_write_fallback(iocb, from, ret,
blkdev_buffered_write(iocb, from));
} else {
+ /*
+ * Take i_rwsem and invalidate_lock to avoid racing with
+ * set_blocksize changing i_blkbits/folio order and punching
+ * out the pagecache.
+ */
+ inode_lock_shared(bd_inode);
ret = blkdev_buffered_write(iocb, from);
+ inode_unlock_shared(bd_inode);
}
if (ret > 0)
@@ -757,6 +764,7 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
+ struct inode *bd_inode = bdev_file_inode(iocb->ki_filp);
struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
loff_t size = bdev_nr_bytes(bdev);
loff_t pos = iocb->ki_pos;
@@ -793,7 +801,13 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
goto reexpand;
}
+ /*
+ * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
+ * changing i_blkbits/folio order and punching out the pagecache.
+ */
+ inode_lock_shared(bd_inode);
ret = filemap_read(iocb, to, ret);
+ inode_unlock_shared(bd_inode);
reexpand:
if (unlikely(shorted))
@@ -836,6 +850,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
if ((start | len) & (bdev_logical_block_size(bdev) - 1))
return -EINVAL;
+ inode_lock(inode);
filemap_invalidate_lock(inode->i_mapping);
/*
@@ -868,6 +883,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
fail:
filemap_invalidate_unlock(inode->i_mapping);
+ inode_unlock(inode);
return error;
}
diff --git a/block/ioctl.c b/block/ioctl.c
index faa40f3..e472cc10 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -142,6 +142,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
if (err)
return err;
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
err = truncate_bdev_range(bdev, mode, start, start + len - 1);
if (err)
@@ -174,6 +175,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
blk_finish_plug(&plug);
fail:
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
return err;
}
@@ -199,12 +201,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
end > bdev_nr_bytes(bdev))
return -EINVAL;
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
err = truncate_bdev_range(bdev, mode, start, end - 1);
if (!err)
err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
GFP_KERNEL);
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
return err;
}
@@ -236,6 +240,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
return -EINVAL;
/* Invalidate the page cache, including dirty pages */
+ inode_lock(bdev->bd_mapping->host);
filemap_invalidate_lock(bdev->bd_mapping);
err = truncate_bdev_range(bdev, mode, start, end);
if (err)
@@ -246,6 +251,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
fail:
filemap_invalidate_unlock(bdev->bd_mapping);
+ inode_unlock(bdev->bd_mapping->host);
return err;
}
diff --git a/block/ioprio.c b/block/ioprio.c
index 73301a2..f0ee279 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -46,12 +46,8 @@ int ioprio_check_cap(int ioprio)
*/
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
return -EPERM;
- fallthrough;
- /* rt has prio field too */
- case IOPRIO_CLASS_BE:
- if (level >= IOPRIO_NR_LEVELS)
- return -EINVAL;
break;
+ case IOPRIO_CLASS_BE:
case IOPRIO_CLASS_IDLE:
break;
case IOPRIO_CLASS_NONE:
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 5498a87..e3f1a48 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -265,10 +265,6 @@ static int hash_accept(struct socket *sock, struct socket *newsock,
goto out_free_state;
err = crypto_ahash_import(&ctx2->req, state);
- if (err) {
- sock_orphan(sk2);
- sock_put(sk2);
- }
out_free_state:
kfree_sensitive(state);
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 5762fcc..ffeedcf 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -163,11 +163,10 @@ static int crypto_scomp_init_tfm(struct crypto_tfm *tfm)
if (ret)
goto unlock;
}
- if (!scomp_scratch_users) {
+ if (!scomp_scratch_users++) {
ret = crypto_scomp_alloc_scratches();
if (ret)
- goto unlock;
- scomp_scratch_users++;
+ scomp_scratch_users--;
}
unlock:
mutex_unlock(&scomp_lock);
@@ -215,8 +214,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
spage = nth_page(spage, soff / PAGE_SIZE);
soff = offset_in_page(soff);
- n = slen / PAGE_SIZE;
- n += (offset_in_page(slen) + soff - 1) / PAGE_SIZE;
+ n = (slen - 1) / PAGE_SIZE;
+ n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE;
if (PageHighMem(nth_page(spage, n)) &&
size_add(soff, slen) > PAGE_SIZE)
break;
@@ -243,9 +242,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
dpage = nth_page(dpage, doff / PAGE_SIZE);
doff = offset_in_page(doff);
- n = dlen / PAGE_SIZE;
- n += (offset_in_page(dlen) + doff - 1) / PAGE_SIZE;
- if (PageHighMem(dpage + n) &&
+ n = (dlen - 1) / PAGE_SIZE;
+ n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE;
+ if (PageHighMem(nth_page(dpage, n)) &&
size_add(doff, dlen) > PAGE_SIZE)
break;
dst = kmap_local_page(dpage) + doff;
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index abd609d..82977ea 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -58,9 +58,6 @@ module_param(fuzz_iterations, uint, 0644);
MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
#endif
-/* Multibuffer is unlimited. Set arbitrary limit for testing. */
-#define MAX_MB_MSGS 16
-
#ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
/* a perfect nop */
@@ -3329,48 +3326,27 @@ static int test_acomp(struct crypto_acomp *tfm,
int ctcount, int dtcount)
{
const char *algo = crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm));
- struct scatterlist *src = NULL, *dst = NULL;
- struct acomp_req *reqs[MAX_MB_MSGS] = {};
- char *decomp_out[MAX_MB_MSGS] = {};
- char *output[MAX_MB_MSGS] = {};
- struct crypto_wait wait;
- struct acomp_req *req;
- int ret = -ENOMEM;
unsigned int i;
+ char *output, *decomp_out;
+ int ret;
+ struct scatterlist src, dst;
+ struct acomp_req *req;
+ struct crypto_wait wait;
- src = kmalloc_array(MAX_MB_MSGS, sizeof(*src), GFP_KERNEL);
- if (!src)
- goto out;
- dst = kmalloc_array(MAX_MB_MSGS, sizeof(*dst), GFP_KERNEL);
- if (!dst)
- goto out;
+ output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+ if (!output)
+ return -ENOMEM;
- for (i = 0; i < MAX_MB_MSGS; i++) {
- reqs[i] = acomp_request_alloc(tfm);
- if (!reqs[i])
- goto out;
-
- acomp_request_set_callback(reqs[i],
- CRYPTO_TFM_REQ_MAY_SLEEP |
- CRYPTO_TFM_REQ_MAY_BACKLOG,
- crypto_req_done, &wait);
- if (i)
- acomp_request_chain(reqs[i], reqs[0]);
-
- output[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
- if (!output[i])
- goto out;
-
- decomp_out[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
- if (!decomp_out[i])
- goto out;
+ decomp_out = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+ if (!decomp_out) {
+ kfree(output);
+ return -ENOMEM;
}
for (i = 0; i < ctcount; i++) {
unsigned int dlen = COMP_BUF_SIZE;
int ilen = ctemplate[i].inlen;
void *input_vec;
- int j;
input_vec = kmemdup(ctemplate[i].input, ilen, GFP_KERNEL);
if (!input_vec) {
@@ -3378,61 +3354,70 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
+ memset(output, 0, dlen);
crypto_init_wait(&wait);
- sg_init_one(src, input_vec, ilen);
+ sg_init_one(&src, input_vec, ilen);
+ sg_init_one(&dst, output, dlen);
- for (j = 0; j < MAX_MB_MSGS; j++) {
- sg_init_one(dst + j, output[j], dlen);
- acomp_request_set_params(reqs[j], src, dst + j, ilen, dlen);
+ req = acomp_request_alloc(tfm);
+ if (!req) {
+ pr_err("alg: acomp: request alloc failed for %s\n",
+ algo);
+ kfree(input_vec);
+ ret = -ENOMEM;
+ goto out;
}
- req = reqs[0];
+ acomp_request_set_params(req, &src, &dst, ilen, dlen);
+ acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ crypto_req_done, &wait);
+
ret = crypto_wait_req(crypto_acomp_compress(req), &wait);
if (ret) {
pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
i + 1, algo, -ret);
kfree(input_vec);
+ acomp_request_free(req);
goto out;
}
ilen = req->dlen;
dlen = COMP_BUF_SIZE;
+ sg_init_one(&src, output, ilen);
+ sg_init_one(&dst, decomp_out, dlen);
crypto_init_wait(&wait);
- for (j = 0; j < MAX_MB_MSGS; j++) {
- sg_init_one(src + j, output[j], ilen);
- sg_init_one(dst + j, decomp_out[j], dlen);
- acomp_request_set_params(reqs[j], src + j, dst + j, ilen, dlen);
+ acomp_request_set_params(req, &src, &dst, ilen, dlen);
+
+ ret = crypto_wait_req(crypto_acomp_decompress(req), &wait);
+ if (ret) {
+ pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
+ i + 1, algo, -ret);
+ kfree(input_vec);
+ acomp_request_free(req);
+ goto out;
}
- crypto_wait_req(crypto_acomp_decompress(req), &wait);
- for (j = 0; j < MAX_MB_MSGS; j++) {
- ret = reqs[j]->base.err;
- if (ret) {
- pr_err("alg: acomp: compression failed on test %d (%d) for %s: ret=%d\n",
- i + 1, j, algo, -ret);
- kfree(input_vec);
- goto out;
- }
+ if (req->dlen != ctemplate[i].inlen) {
+ pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
+ i + 1, algo, req->dlen);
+ ret = -EINVAL;
+ kfree(input_vec);
+ acomp_request_free(req);
+ goto out;
+ }
- if (reqs[j]->dlen != ctemplate[i].inlen) {
- pr_err("alg: acomp: Compression test %d (%d) failed for %s: output len = %d\n",
- i + 1, j, algo, reqs[j]->dlen);
- ret = -EINVAL;
- kfree(input_vec);
- goto out;
- }
-
- if (memcmp(input_vec, decomp_out[j], reqs[j]->dlen)) {
- pr_err("alg: acomp: Compression test %d (%d) failed for %s\n",
- i + 1, j, algo);
- hexdump(output[j], reqs[j]->dlen);
- ret = -EINVAL;
- kfree(input_vec);
- goto out;
- }
+ if (memcmp(input_vec, decomp_out, req->dlen)) {
+ pr_err("alg: acomp: Compression test %d failed for %s\n",
+ i + 1, algo);
+ hexdump(output, req->dlen);
+ ret = -EINVAL;
+ kfree(input_vec);
+ acomp_request_free(req);
+ goto out;
}
kfree(input_vec);
+ acomp_request_free(req);
}
for (i = 0; i < dtcount; i++) {
@@ -3446,9 +3431,10 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
+ memset(output, 0, dlen);
crypto_init_wait(&wait);
- sg_init_one(src, input_vec, ilen);
- sg_init_one(dst, output[0], dlen);
+ sg_init_one(&src, input_vec, ilen);
+ sg_init_one(&dst, output, dlen);
req = acomp_request_alloc(tfm);
if (!req) {
@@ -3459,7 +3445,7 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
- acomp_request_set_params(req, src, dst, ilen, dlen);
+ acomp_request_set_params(req, &src, &dst, ilen, dlen);
acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
crypto_req_done, &wait);
@@ -3481,10 +3467,10 @@ static int test_acomp(struct crypto_acomp *tfm,
goto out;
}
- if (memcmp(output[0], dtemplate[i].output, req->dlen)) {
+ if (memcmp(output, dtemplate[i].output, req->dlen)) {
pr_err("alg: acomp: Decompression test %d failed for %s\n",
i + 1, algo);
- hexdump(output[0], req->dlen);
+ hexdump(output, req->dlen);
ret = -EINVAL;
kfree(input_vec);
acomp_request_free(req);
@@ -3498,13 +3484,8 @@ static int test_acomp(struct crypto_acomp *tfm,
ret = 0;
out:
- acomp_request_free(reqs[0]);
- for (i = 0; i < MAX_MB_MSGS; i++) {
- kfree(output[i]);
- kfree(decomp_out[i]);
- }
- kfree(dst);
- kfree(src);
+ kfree(decomp_out);
+ kfree(output);
return ret;
}
diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index f0dad0c..cd24ccd 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -455,7 +455,7 @@ priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t
if (ret < 0)
return ret;
- buf[size] = '\0';
+ buf[ret] = '\0';
ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period,
&process_quantum);
if (ret != 4)
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 5e1d709..ccaaf6c 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -544,7 +544,7 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
boot_params->d0i3_entry_vpu_ts);
ivpu_dbg(vdev, FW_BOOT, "boot_params.system_time_us = %llu\n",
boot_params->system_time_us);
- ivpu_dbg(vdev, FW_BOOT, "boot_params.power_profile = %u\n",
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.power_profile = 0x%x\n",
boot_params->power_profile);
}
@@ -646,7 +646,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
boot_params->d0i3_residency_time_us = 0;
boot_params->d0i3_entry_vpu_ts = 0;
if (IVPU_WA(disable_d0i2))
- boot_params->power_profile = 1;
+ boot_params->power_profile |= BIT(1);
boot_params->system_time_us = ktime_to_us(ktime_get_real());
wmb(); /* Flush WC buffers after writing bootparams */
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index ec9a362..6331604 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -119,7 +119,7 @@ static void timeouts_init(struct ivpu_device *vdev)
else
vdev->timeout.autosuspend = 100;
vdev->timeout.d0i3_entry_msg = 5;
- vdev->timeout.state_dump_msg = 10;
+ vdev->timeout.state_dump_msg = 100;
}
}
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h
index 300f749..d2d8265 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.h
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.h
@@ -14,7 +14,7 @@
#define PLL_PROFILING_FREQ_DEFAULT 38400000
#define PLL_PROFILING_FREQ_HIGH 400000000
-#define DCT_DEFAULT_ACTIVE_PERCENT 15u
+#define DCT_DEFAULT_ACTIVE_PERCENT 30u
#define DCT_PERIOD_US 35300u
int ivpu_hw_btrs_info_init(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 863e3cd..b28da35 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -681,8 +681,8 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id)
err_erase_xa:
xa_erase(&vdev->submitted_jobs_xa, job->job_id);
err_unlock:
- mutex_unlock(&vdev->submitted_jobs_lock);
mutex_unlock(&file_priv->lock);
+ mutex_unlock(&vdev->submitted_jobs_lock);
ivpu_rpm_put(vdev);
return ret;
}
@@ -874,15 +874,21 @@ int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *
int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
{
struct ivpu_file_priv *file_priv = file->driver_priv;
+ struct ivpu_device *vdev = file_priv->vdev;
struct drm_ivpu_cmdq_create *args = data;
struct ivpu_cmdq *cmdq;
+ int ret;
- if (!ivpu_is_capable(file_priv->vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
+ if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
return -ENODEV;
if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
return -EINVAL;
+ ret = ivpu_rpm_get(vdev);
+ if (ret < 0)
+ return ret;
+
mutex_lock(&file_priv->lock);
cmdq = ivpu_cmdq_create(file_priv, ivpu_job_to_jsm_priority(args->priority), false);
@@ -891,6 +897,8 @@ int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *
mutex_unlock(&file_priv->lock);
+ ivpu_rpm_put(vdev);
+
return cmdq ? 0 : -ENOMEM;
}
@@ -900,28 +908,35 @@ int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file
struct ivpu_device *vdev = file_priv->vdev;
struct drm_ivpu_cmdq_destroy *args = data;
struct ivpu_cmdq *cmdq;
- u32 cmdq_id;
+ u32 cmdq_id = 0;
int ret;
if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ))
return -ENODEV;
+ ret = ivpu_rpm_get(vdev);
+ if (ret < 0)
+ return ret;
+
mutex_lock(&file_priv->lock);
cmdq = xa_load(&file_priv->cmdq_xa, args->cmdq_id);
if (!cmdq || cmdq->is_legacy) {
ret = -ENOENT;
- goto err_unlock;
+ } else {
+ cmdq_id = cmdq->id;
+ ivpu_cmdq_destroy(file_priv, cmdq);
+ ret = 0;
}
- cmdq_id = cmdq->id;
- ivpu_cmdq_destroy(file_priv, cmdq);
mutex_unlock(&file_priv->lock);
- ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id);
- return 0;
-err_unlock:
- mutex_unlock(&file_priv->lock);
+ /* Abort any pending jobs only if cmdq was destroyed */
+ if (!ret)
+ ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id);
+
+ ivpu_rpm_put(vdev);
+
return ret;
}
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index b5891e9..ac0e224 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -428,16 +428,17 @@ int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent)
active_us = (DCT_PERIOD_US * active_percent) / 100;
inactive_us = DCT_PERIOD_US - active_us;
+ vdev->pm->dct_active_percent = active_percent;
+
+ ivpu_dbg(vdev, PM, "DCT requested %u%% (D0: %uus, D0i2: %uus)\n",
+ active_percent, active_us, inactive_us);
+
ret = ivpu_jsm_dct_enable(vdev, active_us, inactive_us);
if (ret) {
ivpu_err_ratelimited(vdev, "Failed to enable DCT: %d\n", ret);
return ret;
}
- vdev->pm->dct_active_percent = active_percent;
-
- ivpu_dbg(vdev, PM, "DCT set to %u%% (D0: %uus, D0i2: %uus)\n",
- active_percent, active_us, inactive_us);
return 0;
}
@@ -445,15 +446,16 @@ int ivpu_pm_dct_disable(struct ivpu_device *vdev)
{
int ret;
+ vdev->pm->dct_active_percent = 0;
+
+ ivpu_dbg(vdev, PM, "DCT requested to be disabled\n");
+
ret = ivpu_jsm_dct_disable(vdev);
if (ret) {
ivpu_err_ratelimited(vdev, "Failed to disable DCT: %d\n", ret);
return ret;
}
- vdev->pm->dct_active_percent = 0;
-
- ivpu_dbg(vdev, PM, "DCT disabled\n");
return 0;
}
@@ -466,7 +468,7 @@ void ivpu_pm_irq_dct_work_fn(struct work_struct *work)
if (ivpu_hw_btrs_dct_get_request(vdev, &enable))
return;
- if (vdev->pm->dct_active_percent)
+ if (enable)
ret = ivpu_pm_dct_enable(vdev, DCT_DEFAULT_ACTIVE_PERCENT);
else
ret = ivpu_pm_dct_disable(vdev);
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index f73ce6e..54676e3 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -231,16 +231,18 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
sizeof(struct acpi_table_pptt));
proc_sz = sizeof(struct acpi_pptt_processor);
- while ((unsigned long)entry + proc_sz < table_end) {
+ /* ignore subtable types that are smaller than a processor node */
+ while ((unsigned long)entry + proc_sz <= table_end) {
cpu_node = (struct acpi_pptt_processor *)entry;
+
if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
cpu_node->parent == node_entry)
return 0;
if (entry->length == 0)
return 0;
+
entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry,
entry->length);
-
}
return 1;
}
@@ -273,15 +275,18 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he
proc_sz = sizeof(struct acpi_pptt_processor);
/* find the processor structure associated with this cpuid */
- while ((unsigned long)entry + proc_sz < table_end) {
+ while ((unsigned long)entry + proc_sz <= table_end) {
cpu_node = (struct acpi_pptt_processor *)entry;
if (entry->length == 0) {
pr_warn("Invalid zero length subtable\n");
break;
}
+ /* entry->length may not equal proc_sz, revalidate the processor structure length */
if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
acpi_cpu_id == cpu_node->acpi_processor_id &&
+ (unsigned long)entry + entry->length <= table_end &&
+ entry->length == proc_sz + cpu_node->number_of_priv_resources * sizeof(u32) &&
acpi_pptt_leaf_node(table_hdr, cpu_node)) {
return (struct acpi_pptt_processor *)entry;
}
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index b5205d4..2295abb 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -396,7 +396,7 @@ static u8 __init acpi_table_checksum(u8 *buffer, u32 length)
}
/* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
-static const char table_sigs[][ACPI_NAMESEG_SIZE] __initconst __nonstring = {
+static const char table_sigs[][ACPI_NAMESEG_SIZE] __initconst = {
ACPI_SIG_BERT, ACPI_SIG_BGRT, ACPI_SIG_CPEP, ACPI_SIG_ECDT,
ACPI_SIG_EINJ, ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT,
ACPI_SIG_MSCT, ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT,
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 7605200..5fc2c8e 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -6373,7 +6373,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
seq_printf(m, " node %d", buffer->target_node->debug_id);
seq_printf(m, " size %zd:%zd offset %lx\n",
buffer->data_size, buffer->offsets_size,
- proc->alloc.vm_start - buffer->user_data);
+ buffer->user_data - proc->alloc.vm_start);
}
static void print_binder_work_ilocked(struct seq_file *m,
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2796c0d..c0eb8c6 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2453,8 +2453,8 @@ static unsigned int ata_msense_control_ata_feature(struct ata_device *dev,
*/
put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]);
- if (dev->flags & ATA_DFLAG_CDL)
- buf[4] = 0x02; /* Support T2A and T2B pages */
+ if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+ buf[4] = 0x02; /* T2A and T2B pages enabled */
else
buf[4] = 0;
@@ -3886,12 +3886,11 @@ static int ata_mselect_control_spg0(struct ata_queued_cmd *qc,
}
/*
- * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode
+ * Translate MODE SELECT control mode page, sub-page f2h (ATA feature mode
* page) into a SET FEATURES command.
*/
-static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
- const u8 *buf, int len,
- u16 *fp)
+static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
+ const u8 *buf, int len, u16 *fp)
{
struct ata_device *dev = qc->dev;
struct ata_taskfile *tf = &qc->tf;
@@ -3909,17 +3908,27 @@ static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
/* Check cdl_ctrl */
switch (buf[0] & 0x03) {
case 0:
- /* Disable CDL */
+ /* Disable CDL if it is enabled */
+ if (!(dev->flags & ATA_DFLAG_CDL_ENABLED))
+ return 0;
+ ata_dev_dbg(dev, "Disabling CDL\n");
cdl_action = 0;
dev->flags &= ~ATA_DFLAG_CDL_ENABLED;
break;
case 0x02:
- /* Enable CDL T2A/T2B: NCQ priority must be disabled */
+ /*
+ * Enable CDL if not already enabled. Since this is mutually
+ * exclusive with NCQ priority, allow this only if NCQ priority
+ * is disabled.
+ */
+ if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+ return 0;
if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) {
ata_dev_err(dev,
"NCQ priority must be disabled to enable CDL\n");
return -EINVAL;
}
+ ata_dev_dbg(dev, "Enabling CDL\n");
cdl_action = 1;
dev->flags |= ATA_DFLAG_CDL_ENABLED;
break;
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index afa4df4..95717d5 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -156,6 +156,16 @@
* },
* .ops = my_custom_ops,
* };
+ *
+ * Please note that such custom ops approach is valid, but it is hard to implement
+ * it right without global locks per-device to protect from auxiliary_drv removal
+ * during call to that ops. In addition, this implementation lacks proper module
+ * dependency, which causes to load/unload races between auxiliary parent and devices
+ * modules.
+ *
+ * The most easiest way to provide these ops reliably without needing to
+ * have a lock is to EXPORT_SYMBOL*() them and rely on already existing
+ * modules infrastructure for validity and correct dependencies chains.
*/
static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id,
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 0042e47..123031a 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -73,6 +73,7 @@ static inline void subsys_put(struct subsys_private *sp)
kset_put(&sp->subsys);
}
+struct subsys_private *bus_to_subsys(const struct bus_type *bus);
struct subsys_private *class_to_subsys(const struct class *class);
struct driver_private {
@@ -180,6 +181,22 @@ int driver_add_groups(const struct device_driver *drv, const struct attribute_gr
void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
void device_driver_detach(struct device *dev);
+static inline void device_set_driver(struct device *dev, const struct device_driver *drv)
+{
+ /*
+ * Majority (all?) read accesses to dev->driver happens either
+ * while holding device lock or in bus/driver code that is only
+ * invoked when the device is bound to a driver and there is no
+ * concern of the pointer being changed while it is being read.
+ * However when reading device's uevent file we read driver pointer
+ * without taking device lock (so we do not block there for
+ * arbitrary amount of time). We use WRITE_ONCE() here to prevent
+ * tearing so that READ_ONCE() can safely be used in uevent code.
+ */
+ // FIXME - this cast should not be needed "soon"
+ WRITE_ONCE(dev->driver, (struct device_driver *)drv);
+}
+
int devres_release_all(struct device *dev);
void device_block_probing(void);
void device_unblock_probing(void);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 5ea3b03..5e75e1b 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -57,7 +57,7 @@ static int __must_check bus_rescan_devices_helper(struct device *dev,
* NULL. A call to subsys_put() must be done when finished with the pointer in
* order for it to be properly freed.
*/
-static struct subsys_private *bus_to_subsys(const struct bus_type *bus)
+struct subsys_private *bus_to_subsys(const struct bus_type *bus)
{
struct subsys_private *sp = NULL;
struct kobject *kobj;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index d2f9d3a..cbc0099 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2624,6 +2624,35 @@ static const char *dev_uevent_name(const struct kobject *kobj)
return NULL;
}
+/*
+ * Try filling "DRIVER=<name>" uevent variable for a device. Because this
+ * function may race with binding and unbinding the device from a driver,
+ * we need to be careful. Binding is generally safe, at worst we miss the
+ * fact that the device is already bound to a driver (but the driver
+ * information that is delivered through uevents is best-effort, it may
+ * become obsolete as soon as it is generated anyways). Unbinding is more
+ * risky as driver pointer is transitioning to NULL, so READ_ONCE() should
+ * be used to make sure we are dealing with the same pointer, and to
+ * ensure that driver structure is not going to disappear from under us
+ * we take bus' drivers klist lock. The assumption that only registered
+ * driver can be bound to a device, and to unregister a driver bus code
+ * will take the same lock.
+ */
+static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+ struct subsys_private *sp = bus_to_subsys(dev->bus);
+
+ if (sp) {
+ scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
+ struct device_driver *drv = READ_ONCE(dev->driver);
+ if (drv)
+ add_uevent_var(env, "DRIVER=%s", drv->name);
+ }
+
+ subsys_put(sp);
+ }
+}
+
static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
{
const struct device *dev = kobj_to_dev(kobj);
@@ -2655,8 +2684,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
if (dev->type && dev->type->name)
add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
- if (dev->driver)
- add_uevent_var(env, "DRIVER=%s", dev->driver->name);
+ /* Add "DRIVER=%s" variable if the device is bound to a driver */
+ dev_driver_uevent(dev, env);
/* Add common DT information about the device */
of_device_uevent(dev, env);
@@ -2726,11 +2755,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
if (!env)
return -ENOMEM;
- /* Synchronize with really_probe() */
- device_lock(dev);
/* let the kset specific function add its keys */
retval = kset->uevent_ops->uevent(&dev->kobj, env);
- device_unlock(dev);
if (retval)
goto out;
@@ -3700,7 +3726,7 @@ int device_add(struct device *dev)
device_pm_remove(dev);
dpm_sysfs_remove(dev);
DPMError:
- dev->driver = NULL;
+ device_set_driver(dev, NULL);
bus_remove_device(dev);
BusError:
device_remove_attrs(dev);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index a7e5118..5065143 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -600,6 +600,7 @@ CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow);
CPU_SHOW_VULN_FALLBACK(gds);
CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
CPU_SHOW_VULN_FALLBACK(ghostwrite);
+CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -616,6 +617,7 @@ static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NU
static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL);
static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
+static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
@@ -633,6 +635,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_gather_data_sampling.attr,
&dev_attr_reg_file_data_sampling.attr,
&dev_attr_ghostwrite.attr,
+ &dev_attr_indirect_target_selection.attr,
NULL
};
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index f0e4b4ab..b526e0e 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -550,7 +550,7 @@ static void device_unbind_cleanup(struct device *dev)
arch_teardown_dma_ops(dev);
kfree(dev->dma_range_map);
dev->dma_range_map = NULL;
- dev->driver = NULL;
+ device_set_driver(dev, NULL);
dev_set_drvdata(dev, NULL);
if (dev->pm_domain && dev->pm_domain->dismiss)
dev->pm_domain->dismiss(dev);
@@ -629,8 +629,7 @@ static int really_probe(struct device *dev, const struct device_driver *drv)
}
re_probe:
- // FIXME - this cast should not be needed "soon"
- dev->driver = (struct device_driver *)drv;
+ device_set_driver(dev, drv);
/* If using pinctrl, bind pins now before probing */
ret = pinctrl_bind_pins(dev);
@@ -1014,7 +1013,7 @@ static int __device_attach(struct device *dev, bool allow_async)
if (ret == 0)
ret = 1;
else {
- dev->driver = NULL;
+ device_set_driver(dev, NULL);
ret = 0;
}
} else {
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 6dd1a88..31bfb31 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -296,7 +296,7 @@ static int delete_path(const char *nodepath)
return err;
}
-static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+static int dev_mynode(struct device *dev, struct inode *inode)
{
/* did we create it */
if (inode->i_private != &thread)
@@ -304,13 +304,13 @@ static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *sta
/* does the dev_t match */
if (is_blockdev(dev)) {
- if (!S_ISBLK(stat->mode))
+ if (!S_ISBLK(inode->i_mode))
return 0;
} else {
- if (!S_ISCHR(stat->mode))
+ if (!S_ISCHR(inode->i_mode))
return 0;
}
- if (stat->rdev != dev->devt)
+ if (inode->i_rdev != dev->devt)
return 0;
/* ours */
@@ -321,20 +321,16 @@ static int handle_remove(const char *nodename, struct device *dev)
{
struct path parent;
struct dentry *dentry;
- struct kstat stat;
- struct path p;
+ struct inode *inode;
int deleted = 0;
- int err;
+ int err = 0;
dentry = kern_path_locked(nodename, &parent);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- p.mnt = parent.mnt;
- p.dentry = dentry;
- err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
- AT_STATX_SYNC_AS_STAT);
- if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
+ inode = d_inode(dentry);
+ if (dev_mynode(dev, inode)) {
struct iattr newattrs;
/*
* before unlinking this node, reset permissions
@@ -342,7 +338,7 @@ static int handle_remove(const char *nodename, struct device *dev)
*/
newattrs.ia_uid = GLOBAL_ROOT_UID;
newattrs.ia_gid = GLOBAL_ROOT_GID;
- newattrs.ia_mode = stat.mode & ~0777;
+ newattrs.ia_mode = inode->i_mode & ~0777;
newattrs.ia_valid =
ATTR_UID|ATTR_GID|ATTR_MODE;
inode_lock(d_inode(dentry));
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8f3a41d..19469e7 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -816,21 +816,6 @@ static int add_memory_block(unsigned long block_id, unsigned long state,
return 0;
}
-static int __init add_boot_memory_block(unsigned long base_section_nr)
-{
- unsigned long nr;
-
- for_each_present_section_nr(base_section_nr, nr) {
- if (nr >= (base_section_nr + sections_per_block))
- break;
-
- return add_memory_block(memory_block_id(base_section_nr),
- MEM_ONLINE, NULL, NULL);
- }
-
- return 0;
-}
-
static int add_hotplug_memory_block(unsigned long block_id,
struct vmem_altmap *altmap,
struct memory_group *group)
@@ -957,7 +942,7 @@ static const struct attribute_group *memory_root_attr_groups[] = {
void __init memory_dev_init(void)
{
int ret;
- unsigned long block_sz, nr;
+ unsigned long block_sz, block_id, nr;
/* Validate the configured memory block size */
block_sz = memory_block_size_bytes();
@@ -970,15 +955,23 @@ void __init memory_dev_init(void)
panic("%s() failed to register subsystem: %d\n", __func__, ret);
/*
- * Create entries for memory sections that were found
- * during boot and have been initialized
+ * Create entries for memory sections that were found during boot
+ * and have been initialized. Use @block_id to track the last
+ * handled block and initialize it to an invalid value (ULONG_MAX)
+ * to bypass the block ID matching check for the first present
+ * block so that it can be covered.
*/
- for (nr = 0; nr <= __highest_present_section_nr;
- nr += sections_per_block) {
- ret = add_boot_memory_block(nr);
- if (ret)
- panic("%s() failed to add memory block: %d\n", __func__,
- ret);
+ block_id = ULONG_MAX;
+ for_each_present_section_nr(0, nr) {
+ if (block_id != ULONG_MAX && memory_block_id(nr) == block_id)
+ continue;
+
+ block_id = memory_block_id(nr);
+ ret = add_memory_block(block_id, MEM_ONLINE, NULL, NULL);
+ if (ret) {
+ panic("%s() failed to add memory block: %d\n",
+ __func__, ret);
+ }
}
}
diff --git a/drivers/base/module.c b/drivers/base/module.c
index 5bc71be..218aaa0 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -42,16 +42,13 @@ int module_add_driver(struct module *mod, const struct device_driver *drv)
if (mod)
mk = &mod->mkobj;
else if (drv->mod_name) {
- struct kobject *mkobj;
-
- /* Lookup built-in module entry in /sys/modules */
- mkobj = kset_find_obj(module_kset, drv->mod_name);
- if (mkobj) {
- mk = container_of(mkobj, struct module_kobject, kobj);
+ /* Lookup or create built-in module entry in /sys/modules */
+ mk = lookup_or_create_module_kobject(drv->mod_name);
+ if (mk) {
/* remember our module structure */
drv->p->mkobj = mk;
- /* kset_find_obj took a reference */
- kobject_put(mkobj);
+ /* lookup_or_create_module_kobject took a reference */
+ kobject_put(&mk->kobj);
}
}
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 1813cfd0..cfccf3f 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1440,7 +1440,7 @@ static void platform_shutdown(struct device *_dev)
static int platform_dma_configure(struct device *dev)
{
- struct platform_driver *drv = to_platform_driver(dev->driver);
+ struct device_driver *drv = READ_ONCE(dev->driver);
struct fwnode_handle *fwnode = dev_fwnode(dev);
enum dev_dma_attr attr;
int ret = 0;
@@ -1451,8 +1451,8 @@ static int platform_dma_configure(struct device *dev)
attr = acpi_get_dma_attr(to_acpi_device_node(fwnode));
ret = acpi_dma_configure(dev, attr);
}
- /* @drv may not be valid when we're called from the IOMMU layer */
- if (ret || !dev->driver || drv->driver_managed_dma)
+ /* @dev->driver may not be valid when we're called from the IOMMU layer */
+ if (ret || !drv || to_platform_driver(drv)->driver_managed_dma)
return ret;
ret = iommu_device_use_default_domain(dev);
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index b1726a3..5c78fa6 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -1080,6 +1080,7 @@ void software_node_notify(struct device *dev)
if (!swnode)
return;
+ kobject_get(&swnode->kobj);
ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node");
if (ret)
return;
@@ -1089,8 +1090,6 @@ void software_node_notify(struct device *dev)
sysfs_remove_link(&dev->kobj, "software_node");
return;
}
-
- kobject_get(&swnode->kobj);
}
void software_node_notify_remove(struct device *dev)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 46cba26..e2b1f37 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -505,6 +505,17 @@ static void loop_assign_backing_file(struct loop_device *lo, struct file *file)
lo->lo_min_dio_size = loop_query_min_dio_size(lo);
}
+static int loop_check_backing_file(struct file *file)
+{
+ if (!file->f_op->read_iter)
+ return -EINVAL;
+
+ if ((file->f_mode & FMODE_WRITE) && !file->f_op->write_iter)
+ return -EINVAL;
+
+ return 0;
+}
+
/*
* loop_change_fd switched the backing store of a loopback device to
* a new file. This is useful for operating system installers to free up
@@ -526,6 +537,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
if (!file)
return -EBADF;
+ error = loop_check_backing_file(file);
+ if (error)
+ return error;
+
/* suppress uevents while reconfiguring the device */
dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1);
@@ -963,6 +978,11 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
if (!file)
return -EBADF;
+
+ error = loop_check_backing_file(file);
+ if (error)
+ return error;
+
is_loop = is_loop_device(file);
/* This is safe, since we have a reference from open(). */
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 2de7b2bd..dc104c0 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -201,15 +201,10 @@ struct ublk_params_header {
static void ublk_stop_dev_unlocked(struct ublk_device *ub);
static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq);
static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
- struct ublk_queue *ubq, int tag, size_t offset);
+ const struct ublk_queue *ubq, int tag, size_t offset);
static inline unsigned int ublk_req_build_flags(struct request *req);
static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
int tag);
-static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
-{
- return ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
-}
-
static inline bool ublk_dev_is_zoned(const struct ublk_device *ub)
{
return ub->dev_info.flags & UBLK_F_ZONED;
@@ -609,14 +604,19 @@ static void ublk_apply_params(struct ublk_device *ub)
ublk_dev_param_zoned_apply(ub);
}
+static inline bool ublk_support_zero_copy(const struct ublk_queue *ubq)
+{
+ return ubq->flags & UBLK_F_SUPPORT_ZERO_COPY;
+}
+
static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
{
- return ubq->flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
+ return ubq->flags & UBLK_F_USER_COPY;
}
static inline bool ublk_need_map_io(const struct ublk_queue *ubq)
{
- return !ublk_support_user_copy(ubq);
+ return !ublk_support_user_copy(ubq) && !ublk_support_zero_copy(ubq);
}
static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
@@ -624,8 +624,11 @@ static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
/*
* read()/write() is involved in user copy, so request reference
* has to be grabbed
+ *
+ * for zero copy, request buffer need to be registered to io_uring
+ * buffer table, so reference is needed
*/
- return ublk_support_user_copy(ubq);
+ return ublk_support_user_copy(ubq) || ublk_support_zero_copy(ubq);
}
static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
@@ -1683,14 +1686,31 @@ static void ublk_start_cancel(struct ublk_queue *ubq)
ublk_put_disk(disk);
}
-static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
+static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag,
unsigned int issue_flags)
{
+ struct ublk_io *io = &ubq->ios[tag];
+ struct ublk_device *ub = ubq->dev;
+ struct request *req;
bool done;
if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
return;
+ /*
+ * Don't try to cancel this command if the request is started for
+ * avoiding race between io_uring_cmd_done() and
+ * io_uring_cmd_complete_in_task().
+ *
+ * Either the started request will be aborted via __ublk_abort_rq(),
+ * then this uring_cmd is canceled next time, or it will be done in
+ * task work function ublk_dispatch_req() because io_uring guarantees
+ * that ublk_dispatch_req() is always called
+ */
+ req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+ if (req && blk_mq_request_started(req) && req->tag == tag)
+ return;
+
spin_lock(&ubq->cancel_lock);
done = !!(io->flags & UBLK_IO_FLAG_CANCELED);
if (!done)
@@ -1722,7 +1742,6 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
struct ublk_queue *ubq = pdu->ubq;
struct task_struct *task;
- struct ublk_io *io;
if (WARN_ON_ONCE(!ubq))
return;
@@ -1737,9 +1756,8 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
if (!ubq->canceling)
ublk_start_cancel(ubq);
- io = &ubq->ios[pdu->tag];
- WARN_ON_ONCE(io->cmd != cmd);
- ublk_cancel_cmd(ubq, io, issue_flags);
+ WARN_ON_ONCE(ubq->ios[pdu->tag].cmd != cmd);
+ ublk_cancel_cmd(ubq, pdu->tag, issue_flags);
}
static inline bool ublk_queue_ready(struct ublk_queue *ubq)
@@ -1752,7 +1770,7 @@ static void ublk_cancel_queue(struct ublk_queue *ubq)
int i;
for (i = 0; i < ubq->q_depth; i++)
- ublk_cancel_cmd(ubq, &ubq->ios[i], IO_URING_F_UNLOCKED);
+ ublk_cancel_cmd(ubq, i, IO_URING_F_UNLOCKED);
}
/* Cancel all pending commands, must be called after del_gendisk() returns */
@@ -1886,15 +1904,6 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
}
}
-static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
- int tag)
-{
- struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
- struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag);
-
- ublk_queue_cmd(ubq, req);
-}
-
static inline int ublk_check_cmd_op(u32 cmd_op)
{
u32 ioc_type = _IOC_TYPE(cmd_op);
@@ -1940,13 +1949,20 @@ static void ublk_io_release(void *priv)
}
static int ublk_register_io_buf(struct io_uring_cmd *cmd,
- struct ublk_queue *ubq, unsigned int tag,
+ const struct ublk_queue *ubq, unsigned int tag,
unsigned int index, unsigned int issue_flags)
{
struct ublk_device *ub = cmd->file->private_data;
+ const struct ublk_io *io = &ubq->ios[tag];
struct request *req;
int ret;
+ if (!ublk_support_zero_copy(ubq))
+ return -EINVAL;
+
+ if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+ return -EINVAL;
+
req = __ublk_check_and_get_req(ub, ubq, tag, 0);
if (!req)
return -EINVAL;
@@ -1962,8 +1978,17 @@ static int ublk_register_io_buf(struct io_uring_cmd *cmd,
}
static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
+ const struct ublk_queue *ubq, unsigned int tag,
unsigned int index, unsigned int issue_flags)
{
+ const struct ublk_io *io = &ubq->ios[tag];
+
+ if (!ublk_support_zero_copy(ubq))
+ return -EINVAL;
+
+ if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+ return -EINVAL;
+
return io_buffer_unregister_bvec(cmd, index, issue_flags);
}
@@ -2067,7 +2092,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
case UBLK_IO_REGISTER_IO_BUF:
return ublk_register_io_buf(cmd, ubq, tag, ub_cmd->addr, issue_flags);
case UBLK_IO_UNREGISTER_IO_BUF:
- return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags);
+ return ublk_unregister_io_buf(cmd, ubq, tag, ub_cmd->addr, issue_flags);
case UBLK_IO_FETCH_REQ:
ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr);
if (ret)
@@ -2103,8 +2128,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
goto out;
ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
- ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
- break;
+ req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
+ ublk_dispatch_req(ubq, req, issue_flags);
+ return -EIOCBQUEUED;
default:
goto out;
}
@@ -2118,13 +2144,10 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
}
static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
- struct ublk_queue *ubq, int tag, size_t offset)
+ const struct ublk_queue *ubq, int tag, size_t offset)
{
struct request *req;
- if (!ublk_need_req_ref(ubq))
- return NULL;
-
req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
if (!req)
return NULL;
@@ -2238,6 +2261,9 @@ static struct request *ublk_check_and_get_req(struct kiocb *iocb,
if (!ubq)
return ERR_PTR(-EINVAL);
+ if (!ublk_support_user_copy(ubq))
+ return ERR_PTR(-EACCES);
+
if (tag >= ubq->q_depth)
return ERR_PTR(-EINVAL);
@@ -2776,13 +2802,18 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
UBLK_F_URING_CMD_COMP_IN_TASK;
- /* GET_DATA isn't needed any more with USER_COPY */
- if (ublk_dev_is_user_copy(ub))
+ /* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */
+ if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY))
ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;
- /* Zoned storage support requires user copy feature */
+ /*
+ * Zoned storage support requires reuse `ublksrv_io_cmd->addr` for
+ * returning write_append_lba, which is only allowed in case of
+ * user copy or zero copy
+ */
if (ublk_dev_is_zoned(ub) &&
- (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !ublk_dev_is_user_copy(ub))) {
+ (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !(ub->dev_info.flags &
+ (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY)))) {
ret = -EINVAL;
goto out_free_dev_number;
}
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index c1e69fc..0a759ea 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -957,8 +957,10 @@ static int btintel_pcie_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
/* This is a debug event that comes from IML and OP image when it
* starts execution. There is no need pass this event to stack.
*/
- if (skb->data[2] == 0x97)
+ if (skb->data[2] == 0x97) {
+ hci_recv_diag(hdev, skb);
return 0;
+ }
}
return hci_recv_frame(hdev, skb);
@@ -974,7 +976,6 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
u8 pkt_type;
u16 plen;
u32 pcie_pkt_type;
- struct sk_buff *new_skb;
void *pdata;
struct hci_dev *hdev = data->hdev;
@@ -1051,24 +1052,20 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
bt_dev_dbg(hdev, "pkt_type: 0x%2.2x len: %u", pkt_type, plen);
- new_skb = bt_skb_alloc(plen, GFP_ATOMIC);
- if (!new_skb) {
- bt_dev_err(hdev, "Failed to allocate memory for skb of len: %u",
- skb->len);
- ret = -ENOMEM;
- goto exit_error;
- }
-
- hci_skb_pkt_type(new_skb) = pkt_type;
- skb_put_data(new_skb, skb->data, plen);
+ hci_skb_pkt_type(skb) = pkt_type;
hdev->stat.byte_rx += plen;
+ skb_trim(skb, plen);
if (pcie_pkt_type == BTINTEL_PCIE_HCI_EVT_PKT)
- ret = btintel_pcie_recv_event(hdev, new_skb);
+ ret = btintel_pcie_recv_event(hdev, skb);
else
- ret = hci_recv_frame(hdev, new_skb);
+ ret = hci_recv_frame(hdev, skb);
+ skb = NULL; /* skb is freed in the callee */
exit_error:
+ if (skb)
+ kfree_skb(skb);
+
if (ret)
hdev->stat.err_rx++;
@@ -1202,8 +1199,6 @@ static void btintel_pcie_rx_work(struct work_struct *work)
struct btintel_pcie_data *data = container_of(work,
struct btintel_pcie_data, rx_work);
struct sk_buff *skb;
- int err;
- struct hci_dev *hdev = data->hdev;
if (test_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags)) {
/* Unlike usb products, controller will not send hardware
@@ -1224,11 +1219,7 @@ static void btintel_pcie_rx_work(struct work_struct *work)
/* Process the sk_buf in queue and send to the HCI layer */
while ((skb = skb_dequeue(&data->rx_skb_q))) {
- err = btintel_pcie_recv_frame(data, skb);
- if (err)
- bt_dev_err(hdev, "Failed to send received frame: %d",
- err);
- kfree_skb(skb);
+ btintel_pcie_recv_frame(data, skb);
}
}
@@ -1281,10 +1272,8 @@ static void btintel_pcie_msix_rx_handle(struct btintel_pcie_data *data)
bt_dev_dbg(hdev, "RXQ: cr_hia: %u cr_tia: %u", cr_hia, cr_tia);
/* Check CR_TIA and CR_HIA for change */
- if (cr_tia == cr_hia) {
- bt_dev_warn(hdev, "RXQ: no new CD found");
+ if (cr_tia == cr_hia)
return;
- }
rxq = &data->rxq;
@@ -1320,6 +1309,16 @@ static irqreturn_t btintel_pcie_msix_isr(int irq, void *data)
return IRQ_WAKE_THREAD;
}
+static inline bool btintel_pcie_is_rxq_empty(struct btintel_pcie_data *data)
+{
+ return data->ia.cr_hia[BTINTEL_PCIE_RXQ_NUM] == data->ia.cr_tia[BTINTEL_PCIE_RXQ_NUM];
+}
+
+static inline bool btintel_pcie_is_txackq_empty(struct btintel_pcie_data *data)
+{
+ return data->ia.cr_tia[BTINTEL_PCIE_TXQ_NUM] == data->ia.cr_hia[BTINTEL_PCIE_TXQ_NUM];
+}
+
static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
{
struct msix_entry *entry = dev_id;
@@ -1351,12 +1350,18 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
btintel_pcie_msix_gp0_handler(data);
/* For TX */
- if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0)
+ if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0) {
btintel_pcie_msix_tx_handle(data);
+ if (!btintel_pcie_is_rxq_empty(data))
+ btintel_pcie_msix_rx_handle(data);
+ }
/* For RX */
- if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1)
+ if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1) {
btintel_pcie_msix_rx_handle(data);
+ if (!btintel_pcie_is_txackq_empty(data))
+ btintel_pcie_msix_tx_handle(data);
+ }
/*
* Before sending the interrupt the HW disables it to prevent a nested
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index edd5eea..1d26207 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -723,6 +723,10 @@ static int btmtksdio_close(struct hci_dev *hdev)
{
struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
+ /* Skip btmtksdio_close if BTMTKSDIO_FUNC_ENABLED isn't set */
+ if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+ return 0;
+
sdio_claim_host(bdev->func);
/* Disable interrupt */
@@ -1443,11 +1447,15 @@ static void btmtksdio_remove(struct sdio_func *func)
if (!bdev)
return;
+ hdev = bdev->hdev;
+
+ /* Make sure to call btmtksdio_close before removing sdio card */
+ if (test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+ btmtksdio_close(hdev);
+
/* Be consistent the state in btmtksdio_probe */
pm_runtime_get_noresume(bdev->dev);
- hdev = bdev->hdev;
-
sdio_set_drvdata(func, NULL);
hci_unregister_dev(hdev);
hci_free_dev(hdev);
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5012b5f..256b451 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3010,55 +3010,27 @@ static void btusb_coredump_qca(struct hci_dev *hdev)
bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err);
}
-/*
- * ==0: not a dump pkt.
- * < 0: fails to handle a dump pkt
- * > 0: otherwise.
- */
+/* Return: 0 on success, negative errno on failure. */
static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
{
- int ret = 1;
+ int ret = 0;
+ unsigned int skip = 0;
u8 pkt_type;
- u8 *sk_ptr;
- unsigned int sk_len;
u16 seqno;
u32 dump_size;
- struct hci_event_hdr *event_hdr;
- struct hci_acl_hdr *acl_hdr;
struct qca_dump_hdr *dump_hdr;
struct btusb_data *btdata = hci_get_drvdata(hdev);
struct usb_device *udev = btdata->udev;
pkt_type = hci_skb_pkt_type(skb);
- sk_ptr = skb->data;
- sk_len = skb->len;
+ skip = sizeof(struct hci_event_hdr);
+ if (pkt_type == HCI_ACLDATA_PKT)
+ skip += sizeof(struct hci_acl_hdr);
- if (pkt_type == HCI_ACLDATA_PKT) {
- acl_hdr = hci_acl_hdr(skb);
- if (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE)
- return 0;
- sk_ptr += HCI_ACL_HDR_SIZE;
- sk_len -= HCI_ACL_HDR_SIZE;
- event_hdr = (struct hci_event_hdr *)sk_ptr;
- } else {
- event_hdr = hci_event_hdr(skb);
- }
+ skb_pull(skb, skip);
+ dump_hdr = (struct qca_dump_hdr *)skb->data;
- if ((event_hdr->evt != HCI_VENDOR_PKT)
- || (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE)))
- return 0;
-
- sk_ptr += HCI_EVENT_HDR_SIZE;
- sk_len -= HCI_EVENT_HDR_SIZE;
-
- dump_hdr = (struct qca_dump_hdr *)sk_ptr;
- if ((sk_len < offsetof(struct qca_dump_hdr, data))
- || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS)
- || (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
- return 0;
-
- /*it is dump pkt now*/
seqno = le16_to_cpu(dump_hdr->seqno);
if (seqno == 0) {
set_bit(BTUSB_HW_SSR_ACTIVE, &btdata->flags);
@@ -3078,16 +3050,15 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
btdata->qca_dump.ram_dump_size = dump_size;
btdata->qca_dump.ram_dump_seqno = 0;
- sk_ptr += offsetof(struct qca_dump_hdr, data0);
- sk_len -= offsetof(struct qca_dump_hdr, data0);
+
+ skb_pull(skb, offsetof(struct qca_dump_hdr, data0));
usb_disable_autosuspend(udev);
bt_dev_info(hdev, "%s memdump size(%u)\n",
(pkt_type == HCI_ACLDATA_PKT) ? "ACL" : "event",
dump_size);
} else {
- sk_ptr += offsetof(struct qca_dump_hdr, data);
- sk_len -= offsetof(struct qca_dump_hdr, data);
+ skb_pull(skb, offsetof(struct qca_dump_hdr, data));
}
if (!btdata->qca_dump.ram_dump_size) {
@@ -3107,7 +3078,6 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
return ret;
}
- skb_pull(skb, skb->len - sk_len);
hci_devcd_append(hdev, skb);
btdata->qca_dump.ram_dump_seqno++;
if (seqno == QCA_LAST_SEQUENCE_NUM) {
@@ -3132,17 +3102,74 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
return ret;
}
+/* Return: true if the ACL packet is a dump packet, false otherwise. */
+static bool acl_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ struct hci_event_hdr *event_hdr;
+ struct hci_acl_hdr *acl_hdr;
+ struct qca_dump_hdr *dump_hdr;
+ struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
+ bool is_dump = false;
+
+ if (!clone)
+ return false;
+
+ acl_hdr = skb_pull_data(clone, sizeof(*acl_hdr));
+ if (!acl_hdr || (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE))
+ goto out;
+
+ event_hdr = skb_pull_data(clone, sizeof(*event_hdr));
+ if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT))
+ goto out;
+
+ dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr));
+ if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+ (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+ goto out;
+
+ is_dump = true;
+out:
+ consume_skb(clone);
+ return is_dump;
+}
+
+/* Return: true if the event packet is a dump packet, false otherwise. */
+static bool evt_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ struct hci_event_hdr *event_hdr;
+ struct qca_dump_hdr *dump_hdr;
+ struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
+ bool is_dump = false;
+
+ if (!clone)
+ return false;
+
+ event_hdr = skb_pull_data(clone, sizeof(*event_hdr));
+ if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT))
+ goto out;
+
+ dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr));
+ if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+ (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+ goto out;
+
+ is_dump = true;
+out:
+ consume_skb(clone);
+ return is_dump;
+}
+
static int btusb_recv_acl_qca(struct hci_dev *hdev, struct sk_buff *skb)
{
- if (handle_dump_pkt_qca(hdev, skb))
- return 0;
+ if (acl_pkt_is_dump_qca(hdev, skb))
+ return handle_dump_pkt_qca(hdev, skb);
return hci_recv_frame(hdev, skb);
}
static int btusb_recv_evt_qca(struct hci_dev *hdev, struct sk_buff *skb)
{
- if (handle_dump_pkt_qca(hdev, skb))
- return 0;
+ if (evt_pkt_is_dump_qca(hdev, skb))
+ return handle_dump_pkt_qca(hdev, skb);
return hci_recv_frame(hdev, skb);
}
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index f7dd455..dda466f 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -315,7 +315,7 @@ static int __init misc_init(void)
goto fail_remove;
err = -EIO;
- if (register_chrdev(MISC_MAJOR, "misc", &misc_fops))
+ if (__register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops))
goto fail_printk;
return 0;
diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c
index e49a19f..dc882fc9 100644
--- a/drivers/char/tpm/tpm-buf.c
+++ b/drivers/char/tpm/tpm-buf.c
@@ -201,7 +201,7 @@ static void tpm_buf_read(struct tpm_buf *buf, off_t *offset, size_t count, void
*/
u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset)
{
- u8 value;
+ u8 value = 0;
tpm_buf_read(buf, offset, sizeof(value), &value);
@@ -218,7 +218,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u8);
*/
u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset)
{
- u16 value;
+ u16 value = 0;
tpm_buf_read(buf, offset, sizeof(value), &value);
@@ -235,7 +235,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u16);
*/
u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset)
{
- u32 value;
+ u32 value = 0;
tpm_buf_read(buf, offset, sizeof(value), &value);
diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index 3f89635..7b5049b 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -40,11 +40,6 @@
*
* These are the usage functions:
*
- * tpm2_start_auth_session() which allocates the opaque auth structure
- * and gets a session from the TPM. This must be called before
- * any of the following functions. The session is protected by a
- * session_key which is derived from a random salt value
- * encrypted to the NULL seed.
* tpm2_end_auth_session() kills the session and frees the resources.
* Under normal operation this function is done by
* tpm_buf_check_hmac_response(), so this is only to be used on
@@ -963,16 +958,13 @@ static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key)
}
/**
- * tpm2_start_auth_session() - create a HMAC authentication session with the TPM
- * @chip: the TPM chip structure to create the session with
+ * tpm2_start_auth_session() - Create an a HMAC authentication session
+ * @chip: A TPM chip
*
- * This function loads the NULL seed from its saved context and starts
- * an authentication session on the null seed, fills in the
- * @chip->auth structure to contain all the session details necessary
- * for performing the HMAC, encrypt and decrypt operations and
- * returns. The NULL seed is flushed before this function returns.
+ * Loads the ephemeral key (null seed), and starts an HMAC authenticated
+ * session. The null seed is flushed before the return.
*
- * Return: zero on success or actual error encountered.
+ * Returns zero on success, or a POSIX error code.
*/
int tpm2_start_auth_session(struct tpm_chip *chip)
{
@@ -1024,7 +1016,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
/* hash algorithm for session */
tpm_buf_append_u16(&buf, TPM_ALG_SHA256);
- rc = tpm_transmit_cmd(chip, &buf, 0, "start auth session");
+ rc = tpm_ret_to_err(tpm_transmit_cmd(chip, &buf, 0, "StartAuthSession"));
tpm2_flush_context(chip, null_key);
if (rc == TPM2_RC_SUCCESS)
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index 970d02c..6c3aa48 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -54,7 +54,7 @@ enum tis_int_flags {
enum tis_defaults {
TIS_MEM_LEN = 0x5000,
TIS_SHORT_TIMEOUT = 750, /* ms */
- TIS_LONG_TIMEOUT = 2000, /* 2 sec */
+ TIS_LONG_TIMEOUT = 4000, /* 4 secs */
TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */
TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */
};
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 5f04951..088182e 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1576,8 +1576,8 @@ static void handle_control_message(struct virtio_device *vdev,
break;
case VIRTIO_CONSOLE_RESIZE: {
struct {
- __u16 rows;
- __u16 cols;
+ __virtio16 cols;
+ __virtio16 rows;
} size;
if (!is_console_port(port))
@@ -1585,7 +1585,8 @@ static void handle_control_message(struct virtio_device *vdev,
memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
sizeof(size));
- set_console_size(port, size.rows, size.cols);
+ set_console_size(port, virtio16_to_cpu(vdev, size.rows),
+ virtio16_to_cpu(vdev, size.cols));
port->cons.hvc->irq_requested = 1;
resize_console(port);
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 014db63..8ddf3a9 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -137,6 +137,8 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
if (!clk_data)
return -ENOMEM;
+ clk_data->num = S2MPS11_CLKS_NUM;
+
switch (hwid) {
case S2MPS11X:
s2mps11_reg = S2MPS11_REG_RTC_CTRL;
@@ -186,7 +188,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
clk_data->hws[i] = &s2mps11_clks[i].hw;
}
- clk_data->num = S2MPS11_CLKS_NUM;
of_clk_add_hw_provider(s2mps11_clks->clk_np, of_clk_hw_onecell_get,
clk_data);
diff --git a/drivers/clk/rockchip/clk-rk3576.c b/drivers/clk/rockchip/clk-rk3576.c
index 595e010..be703f2 100644
--- a/drivers/clk/rockchip/clk-rk3576.c
+++ b/drivers/clk/rockchip/clk-rk3576.c
@@ -541,6 +541,8 @@ static struct rockchip_clk_branch rk3576_clk_branches[] __initdata = {
RK3576_CLKGATE_CON(5), 14, GFLAGS),
GATE(CLK_OTPC_AUTO_RD_G, "clk_otpc_auto_rd_g", "xin24m", 0,
RK3576_CLKGATE_CON(5), 15, GFLAGS),
+ GATE(CLK_OTP_PHY_G, "clk_otp_phy_g", "xin24m", 0,
+ RK3576_CLKGATE_CON(6), 0, GFLAGS),
COMPOSITE(CLK_MIPI_CAMERAOUT_M0, "clk_mipi_cameraout_m0", mux_24m_spll_gpll_cpll_p, 0,
RK3576_CLKSEL_CON(38), 8, 2, MFLAGS, 0, 8, DFLAGS,
RK3576_CLKGATE_CON(6), 3, GFLAGS),
diff --git a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
index bb66c90..e83d4fd 100644
--- a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
+++ b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
@@ -412,19 +412,23 @@ static const struct clk_parent_data mmc0_mmc1_parents[] = {
{ .hw = &pll_periph0_2x_clk.common.hw },
{ .hw = &pll_audio1_div2_clk.common.hw },
};
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc0_clk, "mmc0", mmc0_mmc1_parents, 0x830,
- 0, 4, /* M */
- 8, 2, /* P */
- 24, 3, /* mux */
- BIT(31), /* gate */
- 0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0",
+ mmc0_mmc1_parents, 0x830,
+ 0, 4, /* M */
+ 8, 2, /* P */
+ 24, 3, /* mux */
+ BIT(31), /* gate */
+ 2, /* post-div */
+ 0);
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc1_clk, "mmc1", mmc0_mmc1_parents, 0x834,
- 0, 4, /* M */
- 8, 2, /* P */
- 24, 3, /* mux */
- BIT(31), /* gate */
- 0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1",
+ mmc0_mmc1_parents, 0x834,
+ 0, 4, /* M */
+ 8, 2, /* P */
+ 24, 3, /* mux */
+ BIT(31), /* gate */
+ 2, /* post-div */
+ 0);
static const struct clk_parent_data mmc2_parents[] = {
{ .fw_name = "hosc" },
@@ -433,12 +437,14 @@ static const struct clk_parent_data mmc2_parents[] = {
{ .hw = &pll_periph0_800M_clk.common.hw },
{ .hw = &pll_audio1_div2_clk.common.hw },
};
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc2_clk, "mmc2", mmc2_parents, 0x838,
- 0, 4, /* M */
- 8, 2, /* P */
- 24, 3, /* mux */
- BIT(31), /* gate */
- 0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc2_parents,
+ 0x838,
+ 0, 4, /* M */
+ 8, 2, /* P */
+ 24, 3, /* mux */
+ BIT(31), /* gate */
+ 2, /* post-div */
+ 0);
static SUNXI_CCU_GATE_HWS(bus_mmc0_clk, "bus-mmc0", psi_ahb_hws,
0x84c, BIT(0), 0);
diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h
index b35aeec..bb09c64 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.h
+++ b/drivers/clk/sunxi-ng/ccu_mp.h
@@ -52,6 +52,28 @@ struct ccu_mp {
} \
}
+#define SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(_struct, _name, _parents, \
+ _reg, \
+ _mshift, _mwidth, \
+ _pshift, _pwidth, \
+ _muxshift, _muxwidth, \
+ _gate, _postdiv, _flags)\
+ struct ccu_mp _struct = { \
+ .enable = _gate, \
+ .m = _SUNXI_CCU_DIV(_mshift, _mwidth), \
+ .p = _SUNXI_CCU_DIV(_pshift, _pwidth), \
+ .mux = _SUNXI_CCU_MUX(_muxshift, _muxwidth), \
+ .fixed_post_div = _postdiv, \
+ .common = { \
+ .reg = _reg, \
+ .features = CCU_FEATURE_FIXED_POSTDIV, \
+ .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, \
+ _parents, \
+ &ccu_mp_ops, \
+ _flags), \
+ } \
+ }
+
#define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg, \
_mshift, _mwidth, \
_pshift, _pwidth, \
@@ -109,8 +131,7 @@ struct ccu_mp {
_mshift, _mwidth, \
_pshift, _pwidth, \
_muxshift, _muxwidth, \
- _gate, _features, \
- _flags) \
+ _gate, _flags, _features) \
struct ccu_mp _struct = { \
.enable = _gate, \
.m = _SUNXI_CCU_DIV(_mshift, _mwidth), \
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 39f7c2d..b603c25 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void)
#ifdef CONFIG_CLKEVT_I8253
void clockevent_i8253_disable(void)
{
- raw_spin_lock(&i8253_lock);
+ guard(raw_spinlock_irqsave)(&i8253_lock);
/*
* Writing the MODE register should stop the counter, according to
@@ -132,8 +132,6 @@ void clockevent_i8253_disable(void)
outb_p(0, PIT_CH0);
outb_p(0x30, PIT_MODE);
-
- raw_spin_unlock(&i8253_lock);
}
static int pit_shutdown(struct clock_event_device *evt)
diff --git a/drivers/comedi/drivers/jr3_pci.c b/drivers/comedi/drivers/jr3_pci.c
index cdc842b..75dce1f 100644
--- a/drivers/comedi/drivers/jr3_pci.c
+++ b/drivers/comedi/drivers/jr3_pci.c
@@ -758,7 +758,7 @@ static void jr3_pci_detach(struct comedi_device *dev)
struct jr3_pci_dev_private *devpriv = dev->private;
if (devpriv)
- timer_delete_sync(&devpriv->timer);
+ timer_shutdown_sync(&devpriv->timer);
comedi_pci_detach(dev);
}
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 4f9cb94..0d46402 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -76,7 +76,7 @@
config ARM_BRCMSTB_AVS_CPUFREQ
tristate "Broadcom STB AVS CPUfreq driver"
depends on (ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ) || COMPILE_TEST
- default y
+ default y if ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ
help
Some Broadcom STB SoCs use a co-processor running proprietary firmware
("AVS") to handle voltage and frequency scaling. This driver provides
@@ -88,7 +88,7 @@
tristate "Calxeda Highbank-based"
depends on ARCH_HIGHBANK || COMPILE_TEST
depends on CPUFREQ_DT && REGULATOR && PL320_MBOX
- default m
+ default m if ARCH_HIGHBANK
help
This adds the CPUFreq driver for Calxeda Highbank SoC
based boards.
@@ -133,7 +133,7 @@
config ARM_MEDIATEK_CPUFREQ_HW
tristate "MediaTek CPUFreq HW driver"
depends on ARCH_MEDIATEK || COMPILE_TEST
- default m
+ default m if ARCH_MEDIATEK
help
Support for the CPUFreq HW driver.
Some MediaTek chipsets have a HW engine to offload the steps
@@ -181,7 +181,7 @@
config ARM_S3C64XX_CPUFREQ
bool "Samsung S3C64XX"
depends on CPU_S3C6410 || COMPILE_TEST
- default y
+ default CPU_S3C6410
help
This adds the CPUFreq driver for Samsung S3C6410 SoC.
@@ -190,7 +190,7 @@
config ARM_S5PV210_CPUFREQ
bool "Samsung S5PV210 and S5PC110"
depends on CPU_S5PV210 || COMPILE_TEST
- default y
+ default CPU_S5PV210
help
This adds the CPUFreq driver for Samsung S5PV210 and
S5PC110 SoCs.
@@ -214,7 +214,7 @@
config ARM_SPEAR_CPUFREQ
bool "SPEAr CPUFreq support"
depends on PLAT_SPEAR || COMPILE_TEST
- default y
+ default PLAT_SPEAR
help
This adds the CPUFreq driver support for SPEAr SOCs.
@@ -233,7 +233,7 @@
tristate "Tegra20/30 CPUFreq support"
depends on ARCH_TEGRA || COMPILE_TEST
depends on CPUFREQ_DT
- default y
+ default ARCH_TEGRA
help
This adds the CPUFreq driver support for Tegra20/30 SOCs.
@@ -241,7 +241,7 @@
bool "Tegra124 CPUFreq support"
depends on ARCH_TEGRA || COMPILE_TEST
depends on CPUFREQ_DT
- default y
+ default ARCH_TEGRA
help
This adds the CPUFreq driver support for Tegra124 SOCs.
@@ -256,14 +256,14 @@
tristate "Tegra194 CPUFreq support"
depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || (64BIT && COMPILE_TEST)
depends on TEGRA_BPMP
- default y
+ default ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC
help
This adds CPU frequency driver support for Tegra194 SOCs.
config ARM_TI_CPUFREQ
bool "Texas Instruments CPUFreq support"
depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
- default y
+ default ARCH_OMAP2PLUS || ARCH_K3
help
This driver enables valid OPPs on the running platform based on
values contained within the SoC in use. Enable this in order to
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 924314c..d26b610 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -909,8 +909,19 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency)
pr_warn(FW_WARN "P-state 0 is not max freq\n");
- if (acpi_cpufreq_driver.set_boost)
- policy->boost_supported = true;
+ if (acpi_cpufreq_driver.set_boost) {
+ if (policy->boost_supported) {
+ /*
+ * The firmware may have altered boost state while the
+ * CPU was offline (for example during a suspend-resume
+ * cycle).
+ */
+ if (policy->boost_enabled != boost_state(cpu))
+ set_boost(policy, policy->boost_enabled);
+ } else {
+ policy->boost_supported = true;
+ }
+ }
return result;
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index 4994c86..b1d29b7 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -134,11 +134,17 @@ static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = {
static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu)
{
- struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
- struct apple_cpu_priv *priv = policy->driver_data;
+ struct cpufreq_policy *policy;
+ struct apple_cpu_priv *priv;
struct cpufreq_frequency_table *p;
unsigned int pstate;
+ policy = cpufreq_cpu_get_raw(cpu);
+ if (unlikely(!policy))
+ return 0;
+
+ priv = policy->driver_data;
+
if (priv->info->cur_pstate_mask) {
u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index b3d74f9..cb93f00 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -747,7 +747,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
int ret;
if (!policy)
- return -ENODEV;
+ return 0;
cpu_data = policy->driver_data;
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 2aa0076..a010da0 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -175,6 +175,7 @@ static const struct of_device_id blocklist[] __initconst = {
{ .compatible = "qcom,sm8350", },
{ .compatible = "qcom,sm8450", },
{ .compatible = "qcom,sm8550", },
+ { .compatible = "qcom,sm8650", },
{ .compatible = "st,stih407", },
{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index acf19b0..f45ded6 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -536,14 +536,18 @@ void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
static unsigned int __resolve_freq(struct cpufreq_policy *policy,
- unsigned int target_freq, unsigned int relation)
+ unsigned int target_freq,
+ unsigned int min, unsigned int max,
+ unsigned int relation)
{
unsigned int idx;
+ target_freq = clamp_val(target_freq, min, max);
+
if (!policy->freq_table)
return target_freq;
- idx = cpufreq_frequency_table_target(policy, target_freq, relation);
+ idx = cpufreq_frequency_table_target(policy, target_freq, min, max, relation);
policy->cached_resolved_idx = idx;
policy->cached_target_freq = target_freq;
return policy->freq_table[idx].frequency;
@@ -577,8 +581,7 @@ unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
if (unlikely(min > max))
min = max;
- return __resolve_freq(policy, clamp_val(target_freq, min, max),
- CPUFREQ_RELATION_LE);
+ return __resolve_freq(policy, target_freq, min, max, CPUFREQ_RELATION_LE);
}
EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
@@ -2397,8 +2400,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
if (cpufreq_disabled())
return -ENODEV;
- target_freq = clamp_val(target_freq, policy->min, policy->max);
- target_freq = __resolve_freq(policy, target_freq, relation);
+ target_freq = __resolve_freq(policy, target_freq, policy->min,
+ policy->max, relation);
pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
policy->cpu, target_freq, relation, old_target_freq);
@@ -2727,8 +2730,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
* compiler optimizations around them because they may be accessed
* concurrently by cpufreq_driver_resolve_freq() during the update.
*/
- WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max, CPUFREQ_RELATION_H));
- new_data.min = __resolve_freq(policy, new_data.min, CPUFREQ_RELATION_L);
+ WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max,
+ new_data.min, new_data.max,
+ CPUFREQ_RELATION_H));
+ new_data.min = __resolve_freq(policy, new_data.min, new_data.min,
+ new_data.max, CPUFREQ_RELATION_L);
WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min);
trace_cpu_frequency_limits(policy);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index a7c38b8..0e65d37 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -76,7 +76,8 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
return freq_next;
}
- index = cpufreq_frequency_table_target(policy, freq_next, relation);
+ index = cpufreq_frequency_table_target(policy, freq_next, policy->min,
+ policy->max, relation);
freq_req = freq_table[index].frequency;
freq_reduc = freq_req * od_tuners->powersave_bias / 1000;
freq_avg = freq_req - freq_reduc;
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index c03a91502..35de513 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -115,8 +115,8 @@ int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy)
EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
+ unsigned int target_freq, unsigned int min,
+ unsigned int max, unsigned int relation)
{
struct cpufreq_frequency_table optimal = {
.driver_data = ~0,
@@ -147,7 +147,7 @@ int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
cpufreq_for_each_valid_entry_idx(pos, table, i) {
freq = pos->frequency;
- if ((freq < policy->min) || (freq > policy->max))
+ if (freq < min || freq > max)
continue;
if (freq == target_freq) {
optimal.driver_data = i;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f41ed0b..ba9bf06 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -598,6 +598,9 @@ static bool turbo_is_disabled(void)
{
u64 misc_en;
+ if (!cpu_feature_enabled(X86_FEATURE_IDA))
+ return true;
+
rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index c310aee..944e899 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -37,11 +37,17 @@ static struct cpufreq_driver scmi_cpufreq_driver;
static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
{
- struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
- struct scmi_data *priv = policy->driver_data;
+ struct cpufreq_policy *policy;
+ struct scmi_data *priv;
unsigned long rate;
int ret;
+ policy = cpufreq_cpu_get_raw(cpu);
+ if (unlikely(!policy))
+ return 0;
+
+ priv = policy->driver_data;
+
ret = perf_ops->freq_get(ph, priv->domain_id, &rate, false);
if (ret)
return 0;
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 17cda84..dcbb0ae 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -29,9 +29,16 @@ static struct scpi_ops *scpi_ops;
static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
{
- struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
- struct scpi_data *priv = policy->driver_data;
- unsigned long rate = clk_get_rate(priv->clk);
+ struct cpufreq_policy *policy;
+ struct scpi_data *priv;
+ unsigned long rate;
+
+ policy = cpufreq_cpu_get_raw(cpu);
+ if (unlikely(!policy))
+ return 0;
+
+ priv = policy->driver_data;
+ rate = clk_get_rate(priv->clk);
return rate / 1000;
}
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index 47d6840..744312a 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -194,7 +194,9 @@ static int sun50i_cpufreq_get_efuse(void)
struct nvmem_cell *speedbin_nvmem;
const struct of_device_id *match;
struct device *cpu_dev;
- u32 *speedbin;
+ void *speedbin_ptr;
+ u32 speedbin = 0;
+ size_t len;
int ret;
cpu_dev = get_cpu_device(0);
@@ -217,14 +219,18 @@ static int sun50i_cpufreq_get_efuse(void)
return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
"Could not get nvmem cell\n");
- speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+ speedbin_ptr = nvmem_cell_read(speedbin_nvmem, &len);
nvmem_cell_put(speedbin_nvmem);
- if (IS_ERR(speedbin))
- return PTR_ERR(speedbin);
+ if (IS_ERR(speedbin_ptr))
+ return PTR_ERR(speedbin_ptr);
- ret = opp_data->efuse_xlate(*speedbin);
+ if (len <= 4)
+ memcpy(&speedbin, speedbin_ptr, len);
+ speedbin = le32_to_cpu(speedbin);
- kfree(speedbin);
+ ret = opp_data->efuse_xlate(speedbin);
+
+ kfree(speedbin_ptr);
return ret;
};
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 75bebec..0fcf4a3 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -163,6 +163,12 @@ static int atmel_sha204a_probe(struct i2c_client *client)
i2c_priv->hwrng.name = dev_name(&client->dev);
i2c_priv->hwrng.read = atmel_sha204a_rng_read;
+ /*
+ * According to review by Bill Cox [1], this HWRNG has very low entropy.
+ * [1] https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
+ */
+ i2c_priv->hwrng.quality = 1;
+
ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
if (ret)
dev_warn(&client->dev, "failed to register RNG (%d)\n", ret);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 1569929..17b692e 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -119,7 +119,7 @@ int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
int cxl_ras_init(void);
void cxl_ras_exit(void);
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port);
+int cxl_gpf_port_setup(struct cxl_dport *dport);
int cxl_acpi_get_extended_linear_cache_size(struct resource *backing_res,
int nid, resource_size_t *size);
diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c
index f4daefe..1498e23 100644
--- a/drivers/cxl/core/features.c
+++ b/drivers/cxl/core/features.c
@@ -528,13 +528,13 @@ static void *cxlctl_set_feature(struct cxl_features_state *cxlfs,
rc = cxl_set_feature(cxl_mbox, &feat_in->uuid,
feat_in->version, feat_in->feat_data,
data_size, flags, offset, &return_code);
+ *out_len = sizeof(*rpc_out);
if (rc) {
rpc_out->retval = return_code;
return no_free_ptr(rpc_out);
}
rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
- *out_len = sizeof(*rpc_out);
return no_free_ptr(rpc_out);
}
@@ -677,7 +677,7 @@ static void free_memdev_fwctl(void *_fwctl_dev)
fwctl_put(fwctl_dev);
}
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd)
{
struct cxl_dev_state *cxlds = cxlmd->cxlds;
struct cxl_features_state *cxlfs;
@@ -700,7 +700,7 @@ int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
if (rc)
return rc;
- return devm_add_action_or_reset(&cxlmd->dev, free_memdev_fwctl,
+ return devm_add_action_or_reset(host, free_memdev_fwctl,
no_free_ptr(fwctl_dev));
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fwctl, "CXL");
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 96fecb7..3b80e9a7 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1072,14 +1072,20 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c)
#define GPF_TIMEOUT_BASE_MAX 2
#define GPF_TIMEOUT_SCALE_MAX 7 /* 10 seconds */
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port)
+u16 cxl_gpf_get_dvsec(struct device *dev)
{
+ struct pci_dev *pdev;
+ bool is_port = true;
u16 dvsec;
if (!dev_is_pci(dev))
return 0;
- dvsec = pci_find_dvsec_capability(to_pci_dev(dev), PCI_VENDOR_ID_CXL,
+ pdev = to_pci_dev(dev);
+ if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT)
+ is_port = false;
+
+ dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
is_port ? CXL_DVSEC_PORT_GPF : CXL_DVSEC_DEVICE_GPF);
if (!dvsec)
dev_warn(dev, "%s GPF DVSEC not present\n",
@@ -1128,26 +1134,24 @@ static int update_gpf_port_dvsec(struct pci_dev *pdev, int dvsec, int phase)
return rc;
}
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port)
+int cxl_gpf_port_setup(struct cxl_dport *dport)
{
- struct pci_dev *pdev;
-
- if (!port)
+ if (!dport)
return -EINVAL;
- if (!port->gpf_dvsec) {
+ if (!dport->gpf_dvsec) {
+ struct pci_dev *pdev;
int dvsec;
- dvsec = cxl_gpf_get_dvsec(dport_dev, true);
+ dvsec = cxl_gpf_get_dvsec(dport->dport_dev);
if (!dvsec)
return -EINVAL;
- port->gpf_dvsec = dvsec;
+ dport->gpf_dvsec = dvsec;
+ pdev = to_pci_dev(dport->dport_dev);
+ update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 1);
+ update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 2);
}
- pdev = to_pci_dev(dport_dev);
- update_gpf_port_dvsec(pdev, port->gpf_dvsec, 1);
- update_gpf_port_dvsec(pdev, port->gpf_dvsec, 2);
-
return 0;
}
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 0fd6646c..726bd4a 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1678,7 +1678,7 @@ int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
if (rc && rc != -EBUSY)
return rc;
- cxl_gpf_port_setup(dport_dev, port);
+ cxl_gpf_port_setup(dport);
/* Any more ports to add between this one and the root? */
if (!dev_is_cxl_root_child(&port->dev))
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index 117c2e9..5ca7b0e 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -581,7 +581,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
resource_size_t rcrb = ri->base;
void __iomem *addr;
u32 bar0, bar1;
- u16 cmd;
u32 id;
if (which == CXL_RCRB_UPSTREAM)
@@ -603,7 +602,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
}
id = readl(addr + PCI_VENDOR_ID);
- cmd = readw(addr + PCI_COMMAND);
bar0 = readl(addr + PCI_BASE_ADDRESS_0);
bar1 = readl(addr + PCI_BASE_ADDRESS_1);
iounmap(addr);
@@ -618,8 +616,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
dev_err(dev, "Failed to access Downstream Port RCRB\n");
return CXL_RESOURCE_NONE;
}
- if (!(cmd & PCI_COMMAND_MEMORY))
- return CXL_RESOURCE_NONE;
/* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */
if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO))
return CXL_RESOURCE_NONE;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index be8a7dc..a9ab46e 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -592,7 +592,6 @@ struct cxl_dax_region {
* @cdat: Cached CDAT data
* @cdat_available: Should a CDAT attribute be available in sysfs
* @pci_latency: Upstream latency in picoseconds
- * @gpf_dvsec: Cached GPF port DVSEC
*/
struct cxl_port {
struct device dev;
@@ -616,7 +615,6 @@ struct cxl_port {
} cdat;
bool cdat_available;
long pci_latency;
- int gpf_dvsec;
};
/**
@@ -664,6 +662,7 @@ struct cxl_rcrb_info {
* @regs: Dport parsed register blocks
* @coord: access coordinates (bandwidth and latency performance attributes)
* @link_latency: calculated PCIe downstream latency
+ * @gpf_dvsec: Cached GPF port DVSEC
*/
struct cxl_dport {
struct device *dport_dev;
@@ -675,6 +674,7 @@ struct cxl_dport {
struct cxl_regs regs;
struct access_coordinate coord[ACCESS_COORDINATE_MAX];
long link_latency;
+ int gpf_dvsec;
};
/**
@@ -910,6 +910,6 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
#define __mock static
#endif
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port);
+u16 cxl_gpf_get_dvsec(struct device *dev);
#endif /* __CXL_H__ */
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 7b14a15..785aa2a 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1018,7 +1018,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (rc)
return rc;
- rc = devm_cxl_setup_fwctl(cxlmd);
+ rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
if (rc)
dev_dbg(&pdev->dev, "No CXL FWCTL setup\n");
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index d061fe3..e197883 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -108,7 +108,7 @@ static void cxl_nvdimm_arm_dirty_shutdown_tracking(struct cxl_nvdimm *cxl_nvd)
return;
}
- if (!cxl_gpf_get_dvsec(cxlds->dev, false))
+ if (!cxl_gpf_get_dvsec(cxlds->dev))
return;
if (cxl_get_dirty_count(mds, &count)) {
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 5f8d010..b1ef454 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -320,8 +320,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
count++;
dma_resv_list_set(fobj, i, fence, usage);
- /* pointer update must be visible before we extend the num_fences */
- smp_store_mb(fobj->num_fences, count);
+ /* fence update must be visible before we extend the num_fences */
+ smp_wmb();
+ fobj->num_fences = count;
}
EXPORT_SYMBOL(dma_resv_add_fence);
diff --git a/drivers/dma/amd/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
index 715ac3a..8133966 100644
--- a/drivers/dma/amd/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
@@ -342,6 +342,9 @@ static void pt_cmd_callback_work(void *data, int err)
struct pt_dma_chan *chan;
unsigned long flags;
+ if (!desc)
+ return;
+
dma_chan = desc->vd.tx.chan;
chan = to_pt_chan(dma_chan);
@@ -355,16 +358,14 @@ static void pt_cmd_callback_work(void *data, int err)
desc->status = DMA_ERROR;
spin_lock_irqsave(&chan->vc.lock, flags);
- if (desc) {
- if (desc->status != DMA_COMPLETE) {
- if (desc->status != DMA_ERROR)
- desc->status = DMA_COMPLETE;
+ if (desc->status != DMA_COMPLETE) {
+ if (desc->status != DMA_ERROR)
+ desc->status = DMA_COMPLETE;
- dma_cookie_complete(tx_desc);
- dma_descriptor_unmap(tx_desc);
- } else {
- tx_desc = NULL;
- }
+ dma_cookie_complete(tx_desc);
+ dma_descriptor_unmap(tx_desc);
+ } else {
+ tx_desc = NULL;
}
spin_unlock_irqrestore(&chan->vc.lock, flags);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index d891dfc..91b2fbc 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -841,9 +841,9 @@ static int dmatest_func(void *data)
} else {
dma_async_issue_pending(chan);
- wait_event_timeout(thread->done_wait,
- done->done,
- msecs_to_jiffies(params->timeout));
+ wait_event_freezable_timeout(thread->done_wait,
+ done->done,
+ msecs_to_jiffies(params->timeout));
status = dma_async_is_tx_complete(chan, cookie, NULL,
NULL);
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 756d673..66bfa28 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -57,7 +57,7 @@ static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id)
intr = edma_readl_chreg(fsl_chan, ch_int);
if (!intr)
- return IRQ_HANDLED;
+ return IRQ_NONE;
edma_writel_chreg(fsl_chan, 1, ch_int);
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index ff94ee8..6d12033 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -222,7 +222,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
struct idxd_wq *wq;
struct device *dev, *fdev;
int rc = 0;
- struct iommu_sva *sva;
+ struct iommu_sva *sva = NULL;
unsigned int pasid;
struct idxd_cdev *idxd_cdev;
@@ -317,7 +317,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
if (device_user_pasid_enabled(idxd))
idxd_xa_pasid_remove(ctx);
failed_get_pasid:
- if (device_user_pasid_enabled(idxd))
+ if (device_user_pasid_enabled(idxd) && !IS_ERR_OR_NULL(sva))
iommu_sva_unbind_device(sva);
failed:
mutex_unlock(&wq->wq_lock);
@@ -407,6 +407,9 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma)
if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO))
return -EPERM;
+ if (current->mm != ctx->mm)
+ return -EPERM;
+
rc = check_vma(wq, vma, __func__);
if (rc < 0)
return rc;
@@ -473,6 +476,9 @@ static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t
ssize_t written = 0;
int i;
+ if (current->mm != ctx->mm)
+ return -EPERM;
+
for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) {
int rc = idxd_submit_user_descriptor(ctx, udesc + i);
@@ -493,6 +499,9 @@ static __poll_t idxd_cdev_poll(struct file *filp,
struct idxd_device *idxd = wq->idxd;
__poll_t out = 0;
+ if (current->mm != ctx->mm)
+ return POLLNVAL;
+
poll_wait(filp, &wq->err_queue, wait);
spin_lock(&idxd->dev_lock);
if (idxd->sw_err.valid)
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index fca1d29..760b7d8 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -155,6 +155,25 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd)
pci_free_irq_vectors(pdev);
}
+static void idxd_clean_wqs(struct idxd_device *idxd)
+{
+ struct idxd_wq *wq;
+ struct device *conf_dev;
+ int i;
+
+ for (i = 0; i < idxd->max_wqs; i++) {
+ wq = idxd->wqs[i];
+ if (idxd->hw.wq_cap.op_config)
+ bitmap_free(wq->opcap_bmap);
+ kfree(wq->wqcfg);
+ conf_dev = wq_confdev(wq);
+ put_device(conf_dev);
+ kfree(wq);
+ }
+ bitmap_free(idxd->wq_enable_map);
+ kfree(idxd->wqs);
+}
+
static int idxd_setup_wqs(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
@@ -169,8 +188,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev));
if (!idxd->wq_enable_map) {
- kfree(idxd->wqs);
- return -ENOMEM;
+ rc = -ENOMEM;
+ goto err_bitmap;
}
for (i = 0; i < idxd->max_wqs; i++) {
@@ -189,10 +208,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
conf_dev->bus = &dsa_bus_type;
conf_dev->type = &idxd_wq_device_type;
rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id);
- if (rc < 0) {
- put_device(conf_dev);
+ if (rc < 0)
goto err;
- }
mutex_init(&wq->wq_lock);
init_waitqueue_head(&wq->err_queue);
@@ -203,7 +220,6 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
if (!wq->wqcfg) {
- put_device(conf_dev);
rc = -ENOMEM;
goto err;
}
@@ -211,9 +227,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
if (idxd->hw.wq_cap.op_config) {
wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL);
if (!wq->opcap_bmap) {
- put_device(conf_dev);
rc = -ENOMEM;
- goto err;
+ goto err_opcap_bmap;
}
bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
}
@@ -224,15 +239,46 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
return 0;
- err:
+err_opcap_bmap:
+ kfree(wq->wqcfg);
+
+err:
+ put_device(conf_dev);
+ kfree(wq);
+
while (--i >= 0) {
wq = idxd->wqs[i];
+ if (idxd->hw.wq_cap.op_config)
+ bitmap_free(wq->opcap_bmap);
+ kfree(wq->wqcfg);
conf_dev = wq_confdev(wq);
put_device(conf_dev);
+ kfree(wq);
+
}
+ bitmap_free(idxd->wq_enable_map);
+
+err_bitmap:
+ kfree(idxd->wqs);
+
return rc;
}
+static void idxd_clean_engines(struct idxd_device *idxd)
+{
+ struct idxd_engine *engine;
+ struct device *conf_dev;
+ int i;
+
+ for (i = 0; i < idxd->max_engines; i++) {
+ engine = idxd->engines[i];
+ conf_dev = engine_confdev(engine);
+ put_device(conf_dev);
+ kfree(engine);
+ }
+ kfree(idxd->engines);
+}
+
static int idxd_setup_engines(struct idxd_device *idxd)
{
struct idxd_engine *engine;
@@ -263,6 +309,7 @@ static int idxd_setup_engines(struct idxd_device *idxd)
rc = dev_set_name(conf_dev, "engine%d.%d", idxd->id, engine->id);
if (rc < 0) {
put_device(conf_dev);
+ kfree(engine);
goto err;
}
@@ -276,10 +323,26 @@ static int idxd_setup_engines(struct idxd_device *idxd)
engine = idxd->engines[i];
conf_dev = engine_confdev(engine);
put_device(conf_dev);
+ kfree(engine);
}
+ kfree(idxd->engines);
+
return rc;
}
+static void idxd_clean_groups(struct idxd_device *idxd)
+{
+ struct idxd_group *group;
+ int i;
+
+ for (i = 0; i < idxd->max_groups; i++) {
+ group = idxd->groups[i];
+ put_device(group_confdev(group));
+ kfree(group);
+ }
+ kfree(idxd->groups);
+}
+
static int idxd_setup_groups(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
@@ -310,6 +373,7 @@ static int idxd_setup_groups(struct idxd_device *idxd)
rc = dev_set_name(conf_dev, "group%d.%d", idxd->id, group->id);
if (rc < 0) {
put_device(conf_dev);
+ kfree(group);
goto err;
}
@@ -334,20 +398,18 @@ static int idxd_setup_groups(struct idxd_device *idxd)
while (--i >= 0) {
group = idxd->groups[i];
put_device(group_confdev(group));
+ kfree(group);
}
+ kfree(idxd->groups);
+
return rc;
}
static void idxd_cleanup_internals(struct idxd_device *idxd)
{
- int i;
-
- for (i = 0; i < idxd->max_groups; i++)
- put_device(group_confdev(idxd->groups[i]));
- for (i = 0; i < idxd->max_engines; i++)
- put_device(engine_confdev(idxd->engines[i]));
- for (i = 0; i < idxd->max_wqs; i++)
- put_device(wq_confdev(idxd->wqs[i]));
+ idxd_clean_groups(idxd);
+ idxd_clean_engines(idxd);
+ idxd_clean_wqs(idxd);
destroy_workqueue(idxd->wq);
}
@@ -390,7 +452,7 @@ static int idxd_init_evl(struct idxd_device *idxd)
static int idxd_setup_internals(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
- int rc, i;
+ int rc;
init_waitqueue_head(&idxd->cmd_waitq);
@@ -421,14 +483,11 @@ static int idxd_setup_internals(struct idxd_device *idxd)
err_evl:
destroy_workqueue(idxd->wq);
err_wkq_create:
- for (i = 0; i < idxd->max_groups; i++)
- put_device(group_confdev(idxd->groups[i]));
+ idxd_clean_groups(idxd);
err_group:
- for (i = 0; i < idxd->max_engines; i++)
- put_device(engine_confdev(idxd->engines[i]));
+ idxd_clean_engines(idxd);
err_engine:
- for (i = 0; i < idxd->max_wqs; i++)
- put_device(wq_confdev(idxd->wqs[i]));
+ idxd_clean_wqs(idxd);
err_wqs:
return rc;
}
@@ -528,6 +587,17 @@ static void idxd_read_caps(struct idxd_device *idxd)
idxd->hw.iaa_cap.bits = ioread64(idxd->reg_base + IDXD_IAACAP_OFFSET);
}
+static void idxd_free(struct idxd_device *idxd)
+{
+ if (!idxd)
+ return;
+
+ put_device(idxd_confdev(idxd));
+ bitmap_free(idxd->opcap_bmap);
+ ida_free(&idxd_ida, idxd->id);
+ kfree(idxd);
+}
+
static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data)
{
struct device *dev = &pdev->dev;
@@ -545,28 +615,34 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d
idxd_dev_set_type(&idxd->idxd_dev, idxd->data->type);
idxd->id = ida_alloc(&idxd_ida, GFP_KERNEL);
if (idxd->id < 0)
- return NULL;
+ goto err_ida;
idxd->opcap_bmap = bitmap_zalloc_node(IDXD_MAX_OPCAP_BITS, GFP_KERNEL, dev_to_node(dev));
- if (!idxd->opcap_bmap) {
- ida_free(&idxd_ida, idxd->id);
- return NULL;
- }
+ if (!idxd->opcap_bmap)
+ goto err_opcap;
device_initialize(conf_dev);
conf_dev->parent = dev;
conf_dev->bus = &dsa_bus_type;
conf_dev->type = idxd->data->dev_type;
rc = dev_set_name(conf_dev, "%s%d", idxd->data->name_prefix, idxd->id);
- if (rc < 0) {
- put_device(conf_dev);
- return NULL;
- }
+ if (rc < 0)
+ goto err_name;
spin_lock_init(&idxd->dev_lock);
spin_lock_init(&idxd->cmd_lock);
return idxd;
+
+err_name:
+ put_device(conf_dev);
+ bitmap_free(idxd->opcap_bmap);
+err_opcap:
+ ida_free(&idxd_ida, idxd->id);
+err_ida:
+ kfree(idxd);
+
+ return NULL;
}
static int idxd_enable_system_pasid(struct idxd_device *idxd)
@@ -1190,7 +1266,7 @@ int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev,
err:
pci_iounmap(pdev, idxd->reg_base);
err_iomap:
- put_device(idxd_confdev(idxd));
+ idxd_free(idxd);
err_idxd_alloc:
pci_disable_device(pdev);
return rc;
@@ -1232,7 +1308,6 @@ static void idxd_shutdown(struct pci_dev *pdev)
static void idxd_remove(struct pci_dev *pdev)
{
struct idxd_device *idxd = pci_get_drvdata(pdev);
- struct idxd_irq_entry *irq_entry;
idxd_unregister_devices(idxd);
/*
@@ -1245,20 +1320,12 @@ static void idxd_remove(struct pci_dev *pdev)
get_device(idxd_confdev(idxd));
device_unregister(idxd_confdev(idxd));
idxd_shutdown(pdev);
- if (device_pasid_enabled(idxd))
- idxd_disable_system_pasid(idxd);
idxd_device_remove_debugfs(idxd);
-
- irq_entry = idxd_get_ie(idxd, 0);
- free_irq(irq_entry->vector, irq_entry);
- pci_free_irq_vectors(pdev);
+ idxd_cleanup(idxd);
pci_iounmap(pdev, idxd->reg_base);
- if (device_user_pasid_enabled(idxd))
- idxd_disable_sva(pdev);
- pci_disable_device(pdev);
- destroy_workqueue(idxd->wq);
- perfmon_pmu_remove(idxd);
put_device(idxd_confdev(idxd));
+ idxd_free(idxd);
+ pci_disable_device(pdev);
}
static struct pci_driver idxd_pci_driver = {
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
index d5ddb4e..47c8adfd 100644
--- a/drivers/dma/mediatek/mtk-cqdma.c
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -420,15 +420,11 @@ static struct virt_dma_desc *mtk_cqdma_find_active_desc(struct dma_chan *c,
{
struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
struct virt_dma_desc *vd;
- unsigned long flags;
- spin_lock_irqsave(&cvc->pc->lock, flags);
list_for_each_entry(vd, &cvc->pc->queue, node)
if (vd->tx.cookie == cookie) {
- spin_unlock_irqrestore(&cvc->pc->lock, flags);
return vd;
}
- spin_unlock_irqrestore(&cvc->pc->lock, flags);
list_for_each_entry(vd, &cvc->vc.desc_issued, node)
if (vd->tx.cookie == cookie)
@@ -452,9 +448,11 @@ static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c,
if (ret == DMA_COMPLETE || !txstate)
return ret;
+ spin_lock_irqsave(&cvc->pc->lock, flags);
spin_lock_irqsave(&cvc->vc.lock, flags);
vd = mtk_cqdma_find_active_desc(c, cookie);
spin_unlock_irqrestore(&cvc->vc.lock, flags);
+ spin_unlock_irqrestore(&cvc->pc->lock, flags);
if (vd) {
cvd = to_cqdma_vdesc(vd);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b223a7a..b6255c0 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -1091,8 +1091,11 @@ static void udma_check_tx_completion(struct work_struct *work)
u32 residue_diff;
ktime_t time_diff;
unsigned long delay;
+ unsigned long flags;
while (1) {
+ spin_lock_irqsave(&uc->vc.lock, flags);
+
if (uc->desc) {
/* Get previous residue and time stamp */
residue_diff = uc->tx_drain.residue;
@@ -1127,6 +1130,8 @@ static void udma_check_tx_completion(struct work_struct *work)
break;
}
+ spin_unlock_irqrestore(&uc->vc.lock, flags);
+
usleep_range(ktime_to_us(delay),
ktime_to_us(delay) + 10);
continue;
@@ -1143,6 +1148,8 @@ static void udma_check_tx_completion(struct work_struct *work)
break;
}
+
+ spin_unlock_irqrestore(&uc->vc.lock, flags);
}
static irqreturn_t udma_ring_irq_handler(int irq, void *data)
@@ -4246,7 +4253,6 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
struct of_dma *ofdma)
{
struct udma_dev *ud = ofdma->of_dma_data;
- dma_cap_mask_t mask = ud->ddev.cap_mask;
struct udma_filter_param filter_param;
struct dma_chan *chan;
@@ -4278,7 +4284,7 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
}
}
- chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param,
+ chan = __dma_request_channel(&ud->ddev.cap_mask, udma_dma_filter_fn, &filter_param,
ofdma->of_node);
if (!chan) {
dev_err(ud->dev, "get channel fail in %s.\n", __func__);
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 3e971f9..dcd7008 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -99,7 +99,7 @@ static irqreturn_t altr_sdram_mc_err_handler(int irq, void *dev_id)
if (status & priv->ecc_stat_ce_mask) {
regmap_read(drvdata->mc_vbase, priv->ecc_saddr_offset,
&err_addr);
- if (priv->ecc_uecnt_offset)
+ if (priv->ecc_cecnt_offset)
regmap_read(drvdata->mc_vbase, priv->ecc_cecnt_offset,
&err_count);
edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, err_count,
@@ -1005,9 +1005,6 @@ altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
}
}
- /* Interrupt mode set to every SBERR */
- regmap_write(ecc_mgr_map, ALTR_A10_ECC_INTMODE_OFST,
- ALTR_A10_ECC_INTMODE);
/* Enable ECC */
ecc_set_bits(ecc_ctrl_en_mask, (ecc_block_base +
ALTR_A10_ECC_CTRL_OFST));
@@ -2127,6 +2124,10 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
return PTR_ERR(edac->ecc_mgr_map);
}
+ /* Set irq mask for DDR SBE to avoid any pending irq before registration */
+ regmap_write(edac->ecc_mgr_map, A10_SYSMGR_ECC_INTMASK_SET_OFST,
+ (A10_SYSMGR_ECC_INTMASK_SDMMCB | A10_SYSMGR_ECC_INTMASK_DDR0));
+
edac->irq_chip.name = pdev->dev.of_node->name;
edac->irq_chip.irq_mask = a10_eccmgr_irq_mask;
edac->irq_chip.irq_unmask = a10_eccmgr_irq_unmask;
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
index 3727e72..7248d24c 100644
--- a/drivers/edac/altera_edac.h
+++ b/drivers/edac/altera_edac.h
@@ -249,6 +249,8 @@ struct altr_sdram_mc_data {
#define A10_SYSMGR_ECC_INTMASK_SET_OFST 0x94
#define A10_SYSMGR_ECC_INTMASK_CLR_OFST 0x98
#define A10_SYSMGR_ECC_INTMASK_OCRAM BIT(1)
+#define A10_SYSMGR_ECC_INTMASK_SDMMCB BIT(16)
+#define A10_SYSMGR_ECC_INTMASK_DDR0 BIT(17)
#define A10_SYSMGR_ECC_INTSTAT_SERR_OFST 0x9C
#define A10_SYSMGR_ECC_INTSTAT_DERR_OFST 0xA0
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 1929528..fe55613 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -299,7 +299,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3,
import_uuid(&buf->uuid, (u8 *)&rx_buf->uuid);
}
- ffa_rx_release();
+ if (!(flags & PARTITION_INFO_GET_RETURN_COUNT_ONLY))
+ ffa_rx_release();
mutex_unlock(&drv_info->rx_lock);
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 7af0166..3a54740 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -255,6 +255,9 @@ static struct scmi_device *scmi_child_dev_find(struct device *parent,
if (!dev)
return NULL;
+ /* Drop the refcnt bumped implicitly by device_find_child */
+ put_device(dev);
+
return to_scmi_dev(dev);
}
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 1c75a4c..0390d5f 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -1248,7 +1248,8 @@ static void xfer_put(const struct scmi_protocol_handle *ph,
}
static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
- struct scmi_xfer *xfer, ktime_t stop)
+ struct scmi_xfer *xfer, ktime_t stop,
+ bool *ooo)
{
struct scmi_info *info = handle_to_scmi_info(cinfo->handle);
@@ -1257,7 +1258,7 @@ static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
* in case of out-of-order receptions of delayed responses
*/
return info->desc->ops->poll_done(cinfo, xfer) ||
- try_wait_for_completion(&xfer->done) ||
+ (*ooo = try_wait_for_completion(&xfer->done)) ||
ktime_after(ktime_get(), stop);
}
@@ -1274,15 +1275,17 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc,
* itself to support synchronous commands replies.
*/
if (!desc->sync_cmds_completed_on_ret) {
+ bool ooo = false;
+
/*
* Poll on xfer using transport provided .poll_done();
* assumes no completion interrupt was available.
*/
ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms);
- spin_until_cond(scmi_xfer_done_no_timeout(cinfo,
- xfer, stop));
- if (ktime_after(ktime_get(), stop)) {
+ spin_until_cond(scmi_xfer_done_no_timeout(cinfo, xfer,
+ stop, &ooo));
+ if (!ooo && !info->desc->ops->poll_done(cinfo, xfer)) {
dev_err(dev,
"timed out in resp(caller: %pS) - polling\n",
(void *)_RET_IP_);
diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig
index 0a88309..e3c2e38b 100644
--- a/drivers/firmware/cirrus/Kconfig
+++ b/drivers/firmware/cirrus/Kconfig
@@ -6,14 +6,11 @@
config FW_CS_DSP_KUNIT_TEST_UTILS
tristate
- depends on KUNIT && REGMAP
- select FW_CS_DSP
config FW_CS_DSP_KUNIT_TEST
tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS
- depends on KUNIT && REGMAP
+ depends on KUNIT && REGMAP && FW_CS_DSP
default KUNIT_ALL_TESTS
- select FW_CS_DSP
select FW_CS_DSP_KUNIT_TEST_UTILS
help
This builds KUnit tests for cs_dsp.
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 3c52cb7..e3f990d 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -1224,22 +1224,28 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
if (!svc->intel_svc_fcs) {
dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
ret = -ENOMEM;
- goto err_unregister_dev;
+ goto err_unregister_rsu_dev;
}
ret = platform_device_add(svc->intel_svc_fcs);
if (ret) {
platform_device_put(svc->intel_svc_fcs);
- goto err_unregister_dev;
+ goto err_unregister_rsu_dev;
}
+ ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
+ if (ret)
+ goto err_unregister_fcs_dev;
+
dev_set_drvdata(dev, svc);
pr_info("Intel Service Layer Driver Initialized\n");
return 0;
-err_unregister_dev:
+err_unregister_fcs_dev:
+ platform_device_unregister(svc->intel_svc_fcs);
+err_unregister_rsu_dev:
platform_device_unregister(svc->stratix10_svc_rsu);
err_free_kfifo:
kfifo_free(&controller->svc_fifo);
@@ -1253,6 +1259,8 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev)
struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
+ of_platform_depopulate(ctrl->dev);
+
platform_device_unregister(svc->intel_svc_fcs);
platform_device_unregister(svc->stratix10_svc_rsu);
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 442435d..13cc120 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -1204,6 +1204,8 @@ static int pca953x_restore_context(struct pca953x_chip *chip)
guard(mutex)(&chip->i2c_lock);
+ if (chip->client->irq > 0)
+ enable_irq(chip->client->irq);
regcache_cache_only(chip->regmap, false);
regcache_mark_dirty(chip->regmap);
ret = pca953x_regcache_sync(chip);
@@ -1216,6 +1218,10 @@ static int pca953x_restore_context(struct pca953x_chip *chip)
static void pca953x_save_context(struct pca953x_chip *chip)
{
guard(mutex)(&chip->i2c_lock);
+
+ /* Disable IRQ to prevent early triggering while regmap "cache only" is on */
+ if (chip->client->irq > 0)
+ disable_irq(chip->client->irq);
regcache_cache_only(chip->regmap, true);
}
diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c
index 13407fd..eab6726 100644
--- a/drivers/gpio/gpio-virtuser.c
+++ b/drivers/gpio/gpio-virtuser.c
@@ -401,10 +401,15 @@ static ssize_t gpio_virtuser_direction_do_write(struct file *file,
char buf[32], *trimmed;
int ret, dir, val = 0;
- ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+ if (count >= sizeof(buf))
+ return -EINVAL;
+
+ ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
if (ret < 0)
return ret;
+ buf[ret] = '\0';
+
trimmed = strim(buf);
if (strcmp(trimmed, "input") == 0) {
@@ -623,12 +628,15 @@ static ssize_t gpio_virtuser_consumer_write(struct file *file,
char buf[GPIO_VIRTUSER_NAME_BUF_LEN + 2];
int ret;
+ if (count >= sizeof(buf))
+ return -EINVAL;
+
ret = simple_write_to_buffer(buf, GPIO_VIRTUSER_NAME_BUF_LEN, ppos,
user_buf, count);
if (ret < 0)
return ret;
- buf[strlen(buf) - 1] = '\0';
+ buf[ret] = '\0';
ret = gpiod_set_consumer_name(data->ad.desc, buf);
if (ret)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index cd4fecb..113c5d9 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -742,6 +742,12 @@ EXPORT_SYMBOL_GPL(gpiochip_query_valid_mask);
bool gpiochip_line_is_valid(const struct gpio_chip *gc,
unsigned int offset)
{
+ /*
+ * hog pins are requested before registering GPIO chip
+ */
+ if (!gc->gpiodev)
+ return true;
+
/* No mask means all valid */
if (likely(!gc->gpiodev->valid_mask))
return true;
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2cba2b6..f01925e 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -188,7 +188,7 @@
bool "Enable refcount backtrace history in the DP MST helpers"
depends on STACKTRACE_SUPPORT
select STACKDEPOT
- depends on DRM_KMS_HELPER
+ select DRM_KMS_HELPER
depends on DEBUG_KERNEL
depends on EXPERT
help
diff --git a/drivers/gpu/drm/adp/adp_drv.c b/drivers/gpu/drm/adp/adp_drv.c
index c98c647..54cde09 100644
--- a/drivers/gpu/drm/adp/adp_drv.c
+++ b/drivers/gpu/drm/adp/adp_drv.c
@@ -121,7 +121,6 @@ struct adp_drv_private {
dma_addr_t mask_iova;
int be_irq;
int fe_irq;
- spinlock_t irq_lock;
struct drm_pending_vblank_event *event;
};
@@ -288,6 +287,7 @@ static void adp_crtc_atomic_enable(struct drm_crtc *crtc,
writel(BIT(0), adp->be + ADBE_BLEND_EN3);
writel(BIT(0), adp->be + ADBE_BLEND_BYPASS);
writel(BIT(0), adp->be + ADBE_BLEND_EN4);
+ drm_crtc_vblank_on(crtc);
}
static void adp_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -310,6 +310,7 @@ static void adp_crtc_atomic_flush(struct drm_crtc *crtc,
struct drm_atomic_state *state)
{
u32 frame_num = 1;
+ unsigned long flags;
struct adp_drv_private *adp = crtc_to_adp(crtc);
struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc);
u64 new_size = ALIGN(new_state->mode.hdisplay *
@@ -330,13 +331,19 @@ static void adp_crtc_atomic_flush(struct drm_crtc *crtc,
}
writel(ADBE_FIFO_SYNC | frame_num, adp->be + ADBE_FIFO);
//FIXME: use adbe flush interrupt
- spin_lock_irq(&crtc->dev->event_lock);
if (crtc->state->event) {
- drm_crtc_vblank_get(crtc);
- adp->event = crtc->state->event;
+ struct drm_pending_vblank_event *event = crtc->state->event;
+
+ crtc->state->event = NULL;
+ spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+ if (drm_crtc_vblank_get(crtc) != 0)
+ drm_crtc_send_vblank_event(crtc, event);
+ else
+ adp->event = event;
+
+ spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
}
- crtc->state->event = NULL;
- spin_unlock_irq(&crtc->dev->event_lock);
}
static const struct drm_crtc_funcs adp_crtc_funcs = {
@@ -482,8 +489,6 @@ static irqreturn_t adp_fe_irq(int irq, void *arg)
u32 int_status;
u32 int_ctl;
- spin_lock(&adp->irq_lock);
-
int_status = readl(adp->fe + ADP_INT_STATUS);
if (int_status & ADP_INT_STATUS_VBLANK) {
drm_crtc_handle_vblank(&adp->crtc);
@@ -501,7 +506,6 @@ static irqreturn_t adp_fe_irq(int irq, void *arg)
writel(int_status, adp->fe + ADP_INT_STATUS);
- spin_unlock(&adp->irq_lock);
return IRQ_HANDLED;
}
@@ -512,8 +516,7 @@ static int adp_drm_bind(struct device *dev)
struct adp_drv_private *adp = to_adp(drm);
int err;
- adp_disable_vblank(adp);
- writel(ADP_CTRL_FIFO_ON | ADP_CTRL_VBLANK_ON, adp->fe + ADP_CTRL);
+ writel(ADP_CTRL_FIFO_ON, adp->fe + ADP_CTRL);
adp->next_bridge = drmm_of_get_bridge(&adp->drm, dev->of_node, 0, 0);
if (IS_ERR(adp->next_bridge)) {
@@ -567,8 +570,6 @@ static int adp_probe(struct platform_device *pdev)
if (IS_ERR(adp))
return PTR_ERR(adp);
- spin_lock_init(&adp->irq_lock);
-
dev_set_drvdata(&pdev->dev, &adp->drm);
err = adp_parse_of(pdev, adp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index ef6e782..c364133 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1614,11 +1614,9 @@ static inline void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_cap
#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
-void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
#else
static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
-static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
#endif
void amdgpu_register_gpu_instance(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index b7f8f2f..707e131 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1533,22 +1533,4 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
#endif /* CONFIG_AMD_PMC */
}
-/**
- * amdgpu_choose_low_power_state
- *
- * @adev: amdgpu_device_pointer
- *
- * Choose the target low power state for the GPU
- */
-void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
-{
- if (adev->in_runpm)
- return;
-
- if (amdgpu_acpi_is_s0ix_active(adev))
- adev->in_s0ix = true;
- else if (amdgpu_acpi_is_s3_active(adev))
- adev->in_s3 = true;
-}
-
#endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index cfdf558..02138aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -109,7 +109,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
struct drm_exec exec;
int r;
- drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
+ drm_exec_init(&exec, 0, 0);
drm_exec_until_all_locked(&exec) {
r = amdgpu_vm_lock_pd(vm, &exec, 0);
if (likely(!r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7f354cd..f8b3e04 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4907,28 +4907,20 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev)
* @data: data
*
* This function is called when the system is about to suspend or hibernate.
- * It is used to evict resources from the device before the system goes to
- * sleep while there is still access to swap.
+ * It is used to set the appropriate flags so that eviction can be optimized
+ * in the pm prepare callback.
*/
static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode,
void *data)
{
struct amdgpu_device *adev = container_of(nb, struct amdgpu_device, pm_nb);
- int r;
switch (mode) {
case PM_HIBERNATION_PREPARE:
adev->in_s4 = true;
- fallthrough;
- case PM_SUSPEND_PREPARE:
- r = amdgpu_device_evict_resources(adev);
- /*
- * This is considered non-fatal at this time because
- * amdgpu_device_prepare() will also fatally evict resources.
- * See https://gitlab.freedesktop.org/drm/amd/-/issues/3781
- */
- if (r)
- drm_warn(adev_to_drm(adev), "Failed to evict resources, freeze active processes if problems occur: %d\n", r);
+ break;
+ case PM_POST_HIBERNATION:
+ adev->in_s4 = false;
break;
}
@@ -4949,15 +4941,13 @@ int amdgpu_device_prepare(struct drm_device *dev)
struct amdgpu_device *adev = drm_to_adev(dev);
int i, r;
- amdgpu_choose_low_power_state(adev);
-
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
/* Evict the majority of BOs before starting suspend sequence */
r = amdgpu_device_evict_resources(adev);
if (r)
- goto unprepare;
+ return r;
flush_delayed_work(&adev->gfx.gfx_off_delay_work);
@@ -4968,15 +4958,10 @@ int amdgpu_device_prepare(struct drm_device *dev)
continue;
r = adev->ip_blocks[i].version->funcs->prepare_suspend(&adev->ip_blocks[i]);
if (r)
- goto unprepare;
+ return r;
}
return 0;
-
-unprepare:
- adev->in_s0ix = adev->in_s3 = adev->in_s4 = false;
-
- return r;
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 667080c..44e120f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -43,6 +43,29 @@
#include <linux/dma-fence-array.h>
#include <linux/pci-p2pdma.h>
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops;
+
+/**
+ * dma_buf_attach_adev - Helper to get adev of an attachment
+ *
+ * @attach: attachment
+ *
+ * Returns:
+ * A struct amdgpu_device * if the attaching device is an amdgpu device or
+ * partition, NULL otherwise.
+ */
+static struct amdgpu_device *dma_buf_attach_adev(struct dma_buf_attachment *attach)
+{
+ if (attach->importer_ops == &amdgpu_dma_buf_attach_ops) {
+ struct drm_gem_object *obj = attach->importer_priv;
+ struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+ return amdgpu_ttm_adev(bo->tbo.bdev);
+ }
+
+ return NULL;
+}
+
/**
* amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
*
@@ -54,11 +77,13 @@
static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
struct dma_buf_attachment *attach)
{
+ struct amdgpu_device *attach_adev = dma_buf_attach_adev(attach);
struct drm_gem_object *obj = dmabuf->priv;
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
+ if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
+ pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
attach->peer2peer = false;
amdgpu_vm_bo_update_shared(bo);
@@ -77,22 +102,32 @@ static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
{
struct dma_buf *dmabuf = attach->dmabuf;
struct amdgpu_bo *bo = gem_to_amdgpu_bo(dmabuf->priv);
- u32 domains = bo->preferred_domains;
+ u32 domains = bo->allowed_domains;
dma_resv_assert_held(dmabuf->resv);
- /*
- * Try pinning into VRAM to allow P2P with RDMA NICs without ODP
+ /* Try pinning into VRAM to allow P2P with RDMA NICs without ODP
* support if all attachments can do P2P. If any attachment can't do
* P2P just pin into GTT instead.
+ *
+ * To avoid with conflicting pinnings between GPUs and RDMA when move
+ * notifiers are disabled, only allow pinning in VRAM when move
+ * notiers are enabled.
*/
- list_for_each_entry(attach, &dmabuf->attachments, node)
- if (!attach->peer2peer)
- domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+ if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) {
+ domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+ } else {
+ list_for_each_entry(attach, &dmabuf->attachments, node)
+ if (!attach->peer2peer)
+ domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+ }
if (domains & AMDGPU_GEM_DOMAIN_VRAM)
bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+ if (WARN_ON(!domains))
+ return -EINVAL;
+
return amdgpu_bo_pin(bo, domains);
}
@@ -164,6 +199,11 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
break;
case TTM_PL_VRAM:
+ /* XGMI-accessible memory should never be DMA-mapped */
+ if (WARN_ON(amdgpu_dmabuf_is_xgmi_accessible(
+ dma_buf_attach_adev(attach), bo)))
+ return ERR_PTR(-EINVAL);
+
r = amdgpu_vram_mgr_alloc_sgt(adev, bo->tbo.resource, 0,
bo->tbo.base.size, attach->dev,
dir, &sgt);
@@ -470,6 +510,9 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
struct drm_gem_object *obj = &bo->tbo.base;
struct drm_gem_object *gobj;
+ if (!adev)
+ return false;
+
if (obj->import_attach) {
struct dma_buf *dma_buf = obj->import_attach->dmabuf;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 24ee471..72c807f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2615,13 +2615,8 @@ static int amdgpu_pmops_freeze(struct device *dev)
static int amdgpu_pmops_thaw(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- struct amdgpu_device *adev = drm_to_adev(drm_dev);
- int r;
- r = amdgpu_device_resume(drm_dev, true);
- adev->in_s4 = false;
-
- return r;
+ return amdgpu_device_resume(drm_dev, true);
}
static int amdgpu_pmops_poweroff(struct device *dev)
@@ -2634,9 +2629,6 @@ static int amdgpu_pmops_poweroff(struct device *dev)
static int amdgpu_pmops_restore(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- struct amdgpu_device *adev = drm_to_adev(drm_dev);
-
- adev->in_s4 = false;
return amdgpu_device_resume(drm_dev, true);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index cdcdae7..83adf81 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -66,7 +66,6 @@
#define VCN_ENC_CMD_REG_WAIT 0x0000000c
#define VCN_AON_SOC_ADDRESS_2_0 0x1f800
-#define VCN1_AON_SOC_ADDRESS_3_0 0x48000
#define VCN_VID_IP_ADDRESS_2_0 0x0
#define VCN_AON_IP_ADDRESS_2_0 0x30000
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index e74e26b..fec9a00 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -752,6 +752,18 @@ static int gmc_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
adev->gmc.vram_type = vram_type;
adev->gmc.vram_vendor = vram_vendor;
+ /* The mall_size is already calculated as mall_size_per_umc * num_umc.
+ * However, for gfx1151, which features a 2-to-1 UMC mapping,
+ * the result must be multiplied by 2 to determine the actual mall size.
+ */
+ switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+ case IP_VERSION(11, 5, 1):
+ adev->gmc.mall_size *= 2;
+ break;
+ default:
+ break;
+ }
+
switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
case IP_VERSION(11, 0, 0):
case IP_VERSION(11, 0, 1):
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index f1dc13b..cbbeade 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -41,7 +41,12 @@ static void hdp_v4_0_flush_hdp(struct amdgpu_device *adev,
{
if (!ring || !ring->funcs->emit_wreg) {
WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
- RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+ /* We just need to read back a register to post the write.
+ * Reading back the remapped register causes problems on
+ * some platforms so just read back the memory size register.
+ */
+ if (adev->nbio.funcs->get_memsize)
+ adev->nbio.funcs->get_memsize(adev);
} else {
amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index 43195c0..086a647 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -32,7 +32,12 @@ static void hdp_v5_0_flush_hdp(struct amdgpu_device *adev,
{
if (!ring || !ring->funcs->emit_wreg) {
WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
- RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+ /* We just need to read back a register to post the write.
+ * Reading back the remapped register causes problems on
+ * some platforms so just read back the memory size register.
+ */
+ if (adev->nbio.funcs->get_memsize)
+ adev->nbio.funcs->get_memsize(adev);
} else {
amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index fcb8dd2..40940b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -33,7 +33,17 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
if (!ring || !ring->funcs->emit_wreg) {
WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
0);
- RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+ if (amdgpu_sriov_vf(adev)) {
+ /* this is fine because SR_IOV doesn't remap the register */
+ RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+ } else {
+ /* We just need to read back a register to post the write.
+ * Reading back the remapped register causes problems on
+ * some platforms so just read back the memory size register.
+ */
+ if (adev->nbio.funcs->get_memsize)
+ adev->nbio.funcs->get_memsize(adev);
+ }
} else {
amdgpu_ring_emit_wreg(ring,
(adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
index a88d25a..6ccd31c 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
@@ -35,7 +35,12 @@ static void hdp_v6_0_flush_hdp(struct amdgpu_device *adev,
{
if (!ring || !ring->funcs->emit_wreg) {
WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
- RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+ /* We just need to read back a register to post the write.
+ * Reading back the remapped register causes problems on
+ * some platforms so just read back the memory size register.
+ */
+ if (adev->nbio.funcs->get_memsize)
+ adev->nbio.funcs->get_memsize(adev);
} else {
amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
index 49f7eb4..2c9239a 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
@@ -32,7 +32,12 @@ static void hdp_v7_0_flush_hdp(struct amdgpu_device *adev,
{
if (!ring || !ring->funcs->emit_wreg) {
WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
- RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+ /* We just need to read back a register to post the write.
+ * Reading back the remapped register causes problems on
+ * some platforms so just read back the memory size register.
+ */
+ if (adev->nbio.funcs->get_memsize)
+ adev->nbio.funcs->get_memsize(adev);
} else {
amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 2ece3ae..bed5ef4 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -360,7 +360,7 @@ static void nbio_v7_11_get_clockgating_state(struct amdgpu_device *adev,
*flags |= AMD_CG_SUPPORT_BIF_LS;
}
-#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
+#define MMIO_REG_HOLE_OFFSET 0x44000
static void nbio_v7_11_set_reg_remap(struct amdgpu_device *adev)
{
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 8e7a36f..b8d835c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -39,6 +39,7 @@
#define VCN_VID_SOC_ADDRESS_2_0 0x1fa00
#define VCN1_VID_SOC_ADDRESS_3_0 0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0 0x48000
#define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x1fd
#define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x503
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index d716510..3eec1b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -39,6 +39,7 @@
#define VCN_VID_SOC_ADDRESS_2_0 0x1fa00
#define VCN1_VID_SOC_ADDRESS_3_0 0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0 0x48000
#define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x27
#define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 22ae193..0b19f0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -40,6 +40,7 @@
#define VCN_VID_SOC_ADDRESS_2_0 0x1fa00
#define VCN1_VID_SOC_ADDRESS_3_0 0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0 0x48000
#define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x27
#define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index c6f6392..1f777c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -46,6 +46,7 @@
#define VCN_VID_SOC_ADDRESS_2_0 0x1fb00
#define VCN1_VID_SOC_ADDRESS_3_0 0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0 0x48000
#define VCN_HARVEST_MMSCH 0
@@ -614,7 +615,8 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
/* VCN global tiling registers */
WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
- VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+ VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+ adev->gfx.config.gb_addr_config, 0, indirect);
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 3e176b4..012f6ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -45,6 +45,7 @@
#define VCN_VID_SOC_ADDRESS_2_0 0x1fb00
#define VCN1_VID_SOC_ADDRESS_3_0 0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0 0x48000
static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = {
SOC15_REG_ENTRY_STR(VCN, 0, regUVD_POWER_STATUS),
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index ba603b2..f11df9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -46,6 +46,7 @@
#define VCN_VID_SOC_ADDRESS_2_0 0x1fb00
#define VCN1_VID_SOC_ADDRESS_3_0 (0x48300 + 0x38000)
+#define VCN1_AON_SOC_ADDRESS_3_0 (0x48000 + 0x38000)
#define VCN_HARVEST_MMSCH 0
@@ -1022,6 +1023,10 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
VCN_RB1_DB_CTRL__EN_MASK);
+ /* Keeping one read-back to ensure all register writes are done, otherwise
+ * it may introduce race conditions */
+ RREG32_SOC15(VCN, inst_idx, regVCN_RB1_DB_CTRL);
+
return 0;
}
@@ -1204,6 +1209,10 @@ static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst)
WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
+ /* Keeping one read-back to ensure all register writes are done, otherwise
+ * it may introduce race conditions */
+ RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index d99d05f..b90da3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -533,7 +533,8 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
/* VCN global tiling registers */
WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
- VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+ VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+ adev->gfx.config.gb_addr_config, 0, indirect);
return;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 581d862..e0e84ef7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -503,6 +503,52 @@ static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
}
/**
+ * vcn_v5_0_1_pause_dpg_mode - VCN pause with dpg mode
+ *
+ * @vinst: VCN instance
+ * @new_state: pause state
+ *
+ * Pause dpg mode for VCN block
+ */
+static int vcn_v5_0_1_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+ struct dpg_pause_state *new_state)
+{
+ struct amdgpu_device *adev = vinst->adev;
+ uint32_t reg_data = 0;
+ int vcn_inst;
+
+ vcn_inst = GET_INST(VCN, vinst->inst);
+
+ /* pause/unpause if state is changed */
+ if (vinst->pause_state.fw_based != new_state->fw_based) {
+ DRM_DEV_DEBUG(adev->dev, "dpg pause state changed %d -> %d %s\n",
+ vinst->pause_state.fw_based, new_state->fw_based,
+ new_state->fw_based ? "VCN_DPG_STATE__PAUSE" : "VCN_DPG_STATE__UNPAUSE");
+ reg_data = RREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE) &
+ (~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+
+ if (new_state->fw_based == VCN_DPG_STATE__PAUSE) {
+ /* pause DPG */
+ reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE, reg_data);
+
+ /* wait for ACK */
+ SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_DPG_PAUSE,
+ UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
+ UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+ } else {
+ /* unpause DPG, no need to wait */
+ reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+ WREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE, reg_data);
+ }
+ vinst->pause_state.fw_based = new_state->fw_based;
+ }
+
+ return 0;
+}
+
+
+/**
* vcn_v5_0_1_start_dpg_mode - VCN start with dpg mode
*
* @vinst: VCN instance
@@ -518,6 +564,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
volatile struct amdgpu_vcn5_fw_shared *fw_shared =
adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
struct amdgpu_ring *ring;
+ struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__PAUSE};
int vcn_inst;
uint32_t tmp;
@@ -582,6 +629,9 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
if (indirect)
amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+ /* Pause dpg */
+ vcn_v5_0_1_pause_dpg_mode(vinst, &state);
+
ring = &adev->vcn.inst[inst_idx].ring_enc[0];
WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, lower_32_bits(ring->gpu_addr));
@@ -775,9 +825,13 @@ static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
int inst_idx = vinst->inst;
uint32_t tmp;
int vcn_inst;
+ struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
vcn_inst = GET_INST(VCN, inst_idx);
+ /* Unpause dpg */
+ vcn_v5_0_1_pause_dpg_mode(vinst, &state);
+
/* Wait for power status to be 1 */
SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_POWER_STATUS, 1,
UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 9fed447..cc01b9c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -372,6 +372,8 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev,
static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state,
struct dm_crtc_state *new_state)
{
+ if (new_state->stream->adjust.timing_adjust_pending)
+ return true;
if (new_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED)
return true;
else if (amdgpu_dm_crtc_vrr_active(old_state) != amdgpu_dm_crtc_vrr_active(new_state))
@@ -673,15 +675,21 @@ static void dm_crtc_high_irq(void *interrupt_params)
spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
if (acrtc->dm_irq_params.stream &&
- acrtc->dm_irq_params.vrr_params.supported &&
- acrtc->dm_irq_params.freesync_config.state ==
- VRR_STATE_ACTIVE_VARIABLE) {
+ acrtc->dm_irq_params.vrr_params.supported) {
+ bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
+ bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
+ bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state == VRR_STATE_ACTIVE_VARIABLE;
+
mod_freesync_handle_v_update(adev->dm.freesync_module,
acrtc->dm_irq_params.stream,
&acrtc->dm_irq_params.vrr_params);
- dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream,
- &acrtc->dm_irq_params.vrr_params.adjust);
+ /* update vmin_vmax only if freesync is enabled, or only if PSR and REPLAY are disabled */
+ if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) {
+ dc_stream_adjust_vmin_vmax(adev->dm.dc,
+ acrtc->dm_irq_params.stream,
+ &acrtc->dm_irq_params.vrr_params.adjust);
+ }
}
/*
@@ -1920,26 +1928,6 @@ static enum dmub_ips_disable_type dm_get_default_ips_mode(
switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
case IP_VERSION(3, 5, 0):
case IP_VERSION(3, 6, 0):
- /*
- * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to
- * cause a hard hang. A fix exists for newer PMFW.
- *
- * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest
- * IPS state in all cases, except for s0ix and all displays off (DPMS),
- * where IPS2 is allowed.
- *
- * When checking pmfw version, use the major and minor only.
- */
- if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300)
- ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
- else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0))
- /*
- * Other ASICs with DCN35 that have residency issues with
- * IPS2 in idle.
- * We want them to use IPS2 only in display off cases.
- */
- ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
- break;
case IP_VERSION(3, 5, 1):
ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
break;
@@ -3355,16 +3343,16 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state,
for (k = 0; k < dc_state->stream_count; k++) {
bundle->stream_update.stream = dc_state->streams[k];
- for (m = 0; m < dc_state->stream_status->plane_count; m++) {
+ for (m = 0; m < dc_state->stream_status[k].plane_count; m++) {
bundle->surface_updates[m].surface =
- dc_state->stream_status->plane_states[m];
+ dc_state->stream_status[k].plane_states[m];
bundle->surface_updates[m].surface->force_full_update =
true;
}
update_planes_and_stream_adapter(dm->dc,
UPDATE_TYPE_FULL,
- dc_state->stream_status->plane_count,
+ dc_state->stream_status[k].plane_count,
dc_state->streams[k],
&bundle->stream_update,
bundle->surface_updates);
@@ -6521,12 +6509,12 @@ decide_crtc_timing_for_drm_display_mode(struct drm_display_mode *drm_mode,
const struct drm_display_mode *native_mode,
bool scale_enabled)
{
- if (scale_enabled) {
- copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
- } else if (native_mode->clock == drm_mode->clock &&
- native_mode->htotal == drm_mode->htotal &&
- native_mode->vtotal == drm_mode->vtotal) {
- copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
+ if (scale_enabled || (
+ native_mode->clock == drm_mode->clock &&
+ native_mode->htotal == drm_mode->htotal &&
+ native_mode->vtotal == drm_mode->vtotal)) {
+ if (native_mode->crtc_clock)
+ copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
} else {
/* no scaling nor amdgpu inserted, no need to patch */
}
@@ -11043,6 +11031,9 @@ static bool should_reset_plane(struct drm_atomic_state *state,
state->allow_modeset)
return true;
+ if (amdgpu_in_reset(adev) && state->allow_modeset)
+ return true;
+
/* Exit early if we know that we're adding or removing the plane. */
if (old_plane_state->crtc != new_plane_state->crtc)
return true;
@@ -12760,7 +12751,7 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
* Transient states before tunneling is enabled could
* lead to this error. We can ignore this for now.
*/
- if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) {
+ if (p_notify->result == AUX_RET_ERROR_PROTOCOL_ERROR) {
DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n",
payload->address, payload->length,
p_notify->result);
@@ -12769,22 +12760,15 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
goto out;
}
+ payload->reply[0] = adev->dm.dmub_notify->aux_reply.command & 0xF;
+ if (adev->dm.dmub_notify->aux_reply.command & 0xF0)
+ /* The reply is stored in the top nibble of the command. */
+ payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF;
- payload->reply[0] = adev->dm.dmub_notify->aux_reply.command;
- if (!payload->write && p_notify->aux_reply.length &&
- (payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) {
-
- if (payload->length != p_notify->aux_reply.length) {
- DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n",
- p_notify->aux_reply.length,
- payload->address, payload->length);
- *operation_result = AUX_RET_ERROR_INVALID_REPLY;
- goto out;
- }
-
+ /*write req may receive a byte indicating partially written number as well*/
+ if (p_notify->aux_reply.length)
memcpy(payload->data, p_notify->aux_reply.data,
p_notify->aux_reply.length);
- }
/* success */
ret = p_notify->aux_reply.length;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 5198a07..8f22ad9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -173,6 +173,9 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
unsigned int conn_index = aconnector->base.index;
guard(mutex)(&hdcp_w->mutex);
+ drm_connector_get(&aconnector->base);
+ if (hdcp_w->aconnector[conn_index])
+ drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
hdcp_w->aconnector[conn_index] = aconnector;
memset(&link_adjust, 0, sizeof(link_adjust));
@@ -220,7 +223,6 @@ static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
unsigned int conn_index = aconnector->base.index;
guard(mutex)(&hdcp_w->mutex);
- hdcp_w->aconnector[conn_index] = aconnector;
/* the removal of display will invoke auth reset -> hdcp destroy and
* we'd expect the Content Protection (CP) property changed back to
@@ -236,7 +238,10 @@ static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
}
mod_hdcp_remove_display(&hdcp_w->hdcp, aconnector->base.index, &hdcp_w->output);
-
+ if (hdcp_w->aconnector[conn_index]) {
+ drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+ hdcp_w->aconnector[conn_index] = NULL;
+ }
process_output(hdcp_w);
}
@@ -254,6 +259,10 @@ void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_inde
for (conn_index = 0; conn_index < AMDGPU_DM_MAX_DISPLAY_INDEX; conn_index++) {
hdcp_w->encryption_status[conn_index] =
MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+ if (hdcp_w->aconnector[conn_index]) {
+ drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+ hdcp_w->aconnector[conn_index] = NULL;
+ }
}
process_output(hdcp_w);
@@ -488,6 +497,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
struct hdcp_workqueue *hdcp_work = handle;
struct amdgpu_dm_connector *aconnector = config->dm_stream_ctx;
int link_index = aconnector->dc_link->link_index;
+ unsigned int conn_index = aconnector->base.index;
struct mod_hdcp_display *display = &hdcp_work[link_index].display;
struct mod_hdcp_link *link = &hdcp_work[link_index].link;
struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
@@ -544,7 +554,10 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
guard(mutex)(&hdcp_w->mutex);
mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
-
+ drm_connector_get(&aconnector->base);
+ if (hdcp_w->aconnector[conn_index])
+ drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+ hdcp_w->aconnector[conn_index] = aconnector;
process_output(hdcp_w);
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 2cd3539..1395a74 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -918,7 +918,7 @@ dm_helpers_probe_acpi_edid(void *data, u8 *buf, unsigned int block, size_t len)
{
struct drm_connector *connector = data;
struct acpi_device *acpidev = ACPI_COMPANION(connector->dev->dev);
- unsigned char start = block * EDID_LENGTH;
+ unsigned short start = block * EDID_LENGTH;
struct edid *edid;
int r;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 7ceedf6..5cdbc86 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -51,6 +51,9 @@
#define PEAK_FACTOR_X1000 1006
+/*
+ * This function handles both native AUX and I2C-Over-AUX transactions.
+ */
static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
struct drm_dp_aux_msg *msg)
{
@@ -59,6 +62,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
enum aux_return_code_type operation_result;
struct amdgpu_device *adev;
struct ddc_service *ddc;
+ uint8_t copy[16];
if (WARN_ON(msg->size > 16))
return -E2BIG;
@@ -74,6 +78,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
(msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0;
payload.defer_delay = 0;
+ if (payload.write) {
+ memcpy(copy, msg->buffer, msg->size);
+ payload.data = copy;
+ }
+
result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
&operation_result);
@@ -87,15 +96,25 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
if (adev->dm.aux_hpd_discon_quirk) {
if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE &&
operation_result == AUX_RET_ERROR_HPD_DISCON) {
- result = 0;
+ result = msg->size;
operation_result = AUX_RET_SUCCESS;
}
}
- if (payload.write && result >= 0)
- result = msg->size;
+ /*
+ * result equals to 0 includes the cases of AUX_DEFER/I2C_DEFER
+ */
+ if (payload.write && result >= 0) {
+ if (result) {
+ /*one byte indicating partially written bytes*/
+ drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX partially written\n");
+ result = payload.data[0];
+ } else if (!payload.reply[0])
+ /*I2C_ACK|AUX_ACK*/
+ result = msg->size;
+ }
- if (result < 0)
+ if (result < 0) {
switch (operation_result) {
case AUX_RET_SUCCESS:
break;
@@ -114,6 +133,13 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
break;
}
+ drm_dbg_dp(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result);
+ }
+
+ if (payload.reply[0])
+ drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.",
+ payload.reply[0]);
+
return result;
}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 28d1353..ba4ce8a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -439,9 +439,12 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
* Don't adjust DRR while there's bandwidth optimizations pending to
* avoid conflicting with firmware updates.
*/
- if (dc->ctx->dce_version > DCE_VERSION_MAX)
- if (dc->optimized_required || dc->wm_optimized_required)
+ if (dc->ctx->dce_version > DCE_VERSION_MAX) {
+ if (dc->optimized_required || dc->wm_optimized_required) {
+ stream->adjust.timing_adjust_pending = true;
return false;
+ }
+ }
dc_exit_ips_for_hw_access(dc);
@@ -3168,7 +3171,8 @@ static void copy_stream_update_to_stream(struct dc *dc,
if (update->crtc_timing_adjust) {
if (stream->adjust.v_total_min != update->crtc_timing_adjust->v_total_min ||
- stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max)
+ stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max ||
+ stream->adjust.timing_adjust_pending)
update->crtc_timing_adjust->timing_adjust_pending = true;
stream->adjust = *update->crtc_timing_adjust;
update->crtc_timing_adjust->timing_adjust_pending = false;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index 0c8ec30..731fbd4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -910,7 +910,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
}
//TODO : Could be possibly moved to a common helper layer.
-static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const struct dc_plane_state *plane, unsigned int *plane_id)
+static bool dml21_wrapper_get_plane_id(const struct dc_state *context, unsigned int stream_id, const struct dc_plane_state *plane, unsigned int *plane_id)
{
int i, j;
@@ -918,10 +918,12 @@ static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const str
return false;
for (i = 0; i < context->stream_count; i++) {
- for (j = 0; j < context->stream_status[i].plane_count; j++) {
- if (context->stream_status[i].plane_states[j] == plane) {
- *plane_id = (i << 16) | j;
- return true;
+ if (context->streams[i]->stream_id == stream_id) {
+ for (j = 0; j < context->stream_status[i].plane_count; j++) {
+ if (context->stream_status[i].plane_states[j] == plane) {
+ *plane_id = (i << 16) | j;
+ return true;
+ }
}
}
}
@@ -944,14 +946,14 @@ static unsigned int map_stream_to_dml21_display_cfg(const struct dml2_context *d
return location;
}
-static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx,
+static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx, unsigned int stream_id,
const struct dc_plane_state *plane, const struct dc_state *context)
{
unsigned int plane_id;
int i = 0;
int location = -1;
- if (!dml21_wrapper_get_plane_id(context, plane, &plane_id)) {
+ if (!dml21_wrapper_get_plane_id(context, stream_id, plane, &plane_id)) {
ASSERT(false);
return -1;
}
@@ -1037,7 +1039,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
} else {
for (plane_index = 0; plane_index < context->stream_status[stream_index].plane_count; plane_index++) {
- disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->stream_status[stream_index].plane_states[plane_index], context);
+ disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], context);
if (disp_cfg_plane_location < 0)
disp_cfg_plane_location = dml_dispcfg->num_planes++;
@@ -1048,7 +1050,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index);
dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
- if (dml21_wrapper_get_plane_id(context, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
+ if (dml21_wrapper_get_plane_id(context, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id_valid[disp_cfg_plane_location] = true;
/* apply forced pstate policy */
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
index 5d16f36..ed65845 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
@@ -234,7 +234,9 @@ static bool dml21_mode_check_and_programming(const struct dc *in_dc, struct dc_s
if (!result)
return false;
+ DC_FP_START();
result = dml2_build_mode_programming(mode_programming);
+ DC_FP_END();
if (!result)
return false;
@@ -277,7 +279,9 @@ static bool dml21_check_mode_support(const struct dc *in_dc, struct dc_state *co
mode_support->dml2_instance = dml_init->dml2_instance;
dml21_map_dc_state_into_dml_display_cfg(in_dc, context, dml_ctx);
dml_ctx->v21.mode_programming.dml2_instance->scratch.build_mode_programming_locals.mode_programming_params.programming = dml_ctx->v21.mode_programming.programming;
+ DC_FP_START();
is_supported = dml2_check_mode_supported(mode_support);
+ DC_FP_END();
if (!is_supported)
return false;
@@ -288,16 +292,12 @@ bool dml21_validate(const struct dc *in_dc, struct dc_state *context, struct dml
{
bool out = false;
- DC_FP_START();
-
/* Use dml_validate_only for fast_validate path */
if (fast_validate)
out = dml21_check_mode_support(in_dc, context, dml_ctx);
else
out = dml21_mode_check_and_programming(in_dc, context, dml_ctx);
- DC_FP_END();
-
return out;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 2061d43..ab6baf2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -973,7 +973,9 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
}
}
-static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context, struct scaler_data *out)
+static struct scaler_data *get_scaler_data_for_plane(
+ const struct dc_plane_state *in,
+ struct dc_state *context)
{
int i;
struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
@@ -994,7 +996,7 @@ static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc
}
ASSERT(i < MAX_PIPES);
- memcpy(out, &temp_pipe->plane_res.scl_data, sizeof(*out));
+ return &temp_pipe->plane_res.scl_data;
}
static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location,
@@ -1057,11 +1059,7 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
const struct dc_plane_state *in, struct dc_state *context,
const struct soc_bounding_box_st *soc)
{
- struct scaler_data *scaler_data = kzalloc(sizeof(*scaler_data), GFP_KERNEL);
- if (!scaler_data)
- return;
-
- get_scaler_data_for_plane(in, context, scaler_data);
+ struct scaler_data *scaler_data = get_scaler_data_for_plane(in, context);
out->CursorBPP[location] = dml_cur_32bit;
out->CursorWidth[location] = 256;
@@ -1126,8 +1124,6 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
out->DynamicMetadataTransmittedBytes[location] = 0;
out->NumberOfCursors[location] = 1;
-
- kfree(scaler_data);
}
static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml2,
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
index 1236e0f..712aff7 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
@@ -120,10 +120,11 @@ void dpp401_set_cursor_attributes(
enum dc_cursor_color_format color_format = cursor_attributes->color_format;
int cur_rom_en = 0;
- // DCN4 should always do Cursor degamma for Cursor Color modes
if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA ||
color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) {
- cur_rom_en = 1;
+ if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) {
+ cur_rom_en = 1;
+ }
}
REG_UPDATE_3(CURSOR0_CONTROL,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index 5489f3d..3af6a34 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -1980,9 +1980,9 @@ void dcn401_program_pipe(
dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->hubp_regs.det_size);
}
- if (pipe_ctx->update_flags.raw ||
- (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) ||
- pipe_ctx->stream->update_flags.raw)
+ if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw ||
+ pipe_ctx->plane_state->update_flags.raw ||
+ pipe_ctx->stream->update_flags.raw))
dc->hwss.update_dchubp_dpp(dc, pipe_ctx, context);
if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable ||
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 268626e..53c961f 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -148,6 +148,7 @@ void link_blank_dp_stream(struct dc_link *link, bool hw_init)
void link_set_all_streams_dpms_off_for_link(struct dc_link *link)
{
struct pipe_ctx *pipes[MAX_PIPES];
+ struct dc_stream_state *streams[MAX_PIPES];
struct dc_state *state = link->dc->current_state;
uint8_t count;
int i;
@@ -160,10 +161,18 @@ void link_set_all_streams_dpms_off_for_link(struct dc_link *link)
link_get_master_pipes_with_dpms_on(link, state, &count, pipes);
+ /* The subsequent call to dc_commit_updates_for_stream for a full update
+ * will release the current state and swap to a new state. Releasing the
+ * current state results in the stream pointers in the pipe_ctx structs
+ * to be zero'd. Hence, cache all streams prior to dc_commit_updates_for_stream.
+ */
+ for (i = 0; i < count; i++)
+ streams[i] = pipes[i]->stream;
+
for (i = 0; i < count; i++) {
- stream_update.stream = pipes[i]->stream;
+ stream_update.stream = streams[i];
dc_commit_updates_for_stream(link->ctx->dc, NULL, 0,
- pipes[i]->stream, &stream_update,
+ streams[i], &stream_update,
state);
}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
index 34d2e09..5a5d48f 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
@@ -35,6 +35,17 @@
#define DC_LOGGER \
link->ctx->logger
+static void get_default_8b_10b_lttpr_aux_rd_interval(
+ union training_aux_rd_interval *training_rd_interval)
+{
+ /* LTTPR are required to program DPCD 0000Eh to 0x4 (16ms) upon AUX
+ * read reply to this register. Since old sinks with DPCD rev 1.1
+ * and earlier may not support this register, assume the mandatory
+ * value is programmed by the LTTPR to avoid AUX timeout issues.
+ */
+ training_rd_interval->raw = 0x4;
+}
+
static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
const struct dc_link_settings *link_settings,
enum lttpr_mode lttpr_mode)
@@ -43,17 +54,22 @@ static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
uint32_t wait_in_micro_secs = 100;
memset(&training_rd_interval, 0, sizeof(training_rd_interval));
- if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
- link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
- core_link_read_dpcd(
- link,
- DP_TRAINING_AUX_RD_INTERVAL,
- (uint8_t *)&training_rd_interval,
- sizeof(training_rd_interval));
- if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
- wait_in_micro_secs = 400;
- if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
- wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+ if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+ core_link_read_dpcd(
+ link,
+ DP_TRAINING_AUX_RD_INTERVAL,
+ (uint8_t *)&training_rd_interval,
+ sizeof(training_rd_interval));
+ else if (dp_is_lttpr_present(link))
+ get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
+
+ if (training_rd_interval.raw != 0) {
+ if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
+ wait_in_micro_secs = 400;
+ if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
+ wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+ }
}
return wait_in_micro_secs;
}
@@ -71,13 +87,15 @@ static uint32_t get_eq_training_aux_rd_interval(
DP_128B132B_TRAINING_AUX_RD_INTERVAL,
(uint8_t *)&training_rd_interval,
sizeof(training_rd_interval));
- } else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
- link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
- core_link_read_dpcd(
- link,
- DP_TRAINING_AUX_RD_INTERVAL,
- (uint8_t *)&training_rd_interval,
- sizeof(training_rd_interval));
+ } else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+ core_link_read_dpcd(
+ link,
+ DP_TRAINING_AUX_RD_INTERVAL,
+ (uint8_t *)&training_rd_interval,
+ sizeof(training_rd_interval));
+ else if (dp_is_lttpr_present(link))
+ get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
}
switch (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL) {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index 2a59cc6..944650c 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -2114,8 +2114,6 @@ static bool dcn32_resource_construct(
#define REG_STRUCT dccg_regs
dccg_regs_init();
- DC_FP_START();
-
ctx->dc_bios->regs = &bios_regs;
pool->base.res_cap = &res_cap_dcn32;
@@ -2501,14 +2499,10 @@ static bool dcn32_resource_construct(
if (ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev) && (dc->config.sdpif_request_limit_words_per_umc == 0))
dc->config.sdpif_request_limit_words_per_umc = 16;
- DC_FP_END();
-
return true;
create_fail:
- DC_FP_END();
-
dcn32_resource_destruct(pool);
return false;
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 17fc5dc..60e5ac1 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -549,7 +549,7 @@ int drm_dev_wedged_event(struct drm_device *dev, unsigned long method)
if (drm_WARN_ONCE(dev, !recovery, "invalid recovery method %u\n", opt))
break;
- len += scnprintf(event_string + len, sizeof(event_string), "%s,", recovery);
+ len += scnprintf(event_string + len, sizeof(event_string) - len, "%s,", recovery);
}
if (recovery)
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c299cd9..cf24630 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -964,6 +964,10 @@ void drm_show_fdinfo(struct seq_file *m, struct file *f)
struct drm_file *file = f->private_data;
struct drm_device *dev = file->minor->dev;
struct drm_printer p = drm_seq_file_printer(m);
+ int idx;
+
+ if (!drm_dev_enter(dev, &idx))
+ return;
drm_printf(&p, "drm-driver:\t%s\n", dev->driver->name);
drm_printf(&p, "drm-client-id:\t%llu\n", file->client_id);
@@ -983,6 +987,8 @@ void drm_show_fdinfo(struct seq_file *m, struct file *f)
if (dev->driver->show_fdinfo)
dev->driver->show_fdinfo(&p, file);
+
+ drm_dev_exit(idx);
}
EXPORT_SYMBOL(drm_show_fdinfo);
diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index 38431e8..4b2f328 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -1118,6 +1118,10 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
lockdep_assert_held(&gpusvm->notifier_lock);
if (range->flags.has_dma_mapping) {
+ struct drm_gpusvm_range_flags flags = {
+ .__flags = range->flags.__flags,
+ };
+
for (i = 0, j = 0; i < npages; j++) {
struct drm_pagemap_device_addr *addr = &range->dma_addr[j];
@@ -1131,8 +1135,12 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
dev, *addr);
i += 1 << addr->order;
}
- range->flags.has_devmem_pages = false;
- range->flags.has_dma_mapping = false;
+
+ /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */
+ flags.has_devmem_pages = false;
+ flags.has_dma_mapping = false;
+ WRITE_ONCE(range->flags.__flags, flags.__flags);
+
range->dpagemap = NULL;
}
}
@@ -1334,6 +1342,7 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
int err = 0;
struct dev_pagemap *pagemap;
struct drm_pagemap *dpagemap;
+ struct drm_gpusvm_range_flags flags;
retry:
hmm_range.notifier_seq = mmu_interval_read_begin(notifier);
@@ -1378,7 +1387,8 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
*/
drm_gpusvm_notifier_lock(gpusvm);
- if (range->flags.unmapped) {
+ flags.__flags = range->flags.__flags;
+ if (flags.unmapped) {
drm_gpusvm_notifier_unlock(gpusvm);
err = -EFAULT;
goto err_free;
@@ -1454,6 +1464,11 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
goto err_unmap;
}
+ if (ctx->devmem_only) {
+ err = -EFAULT;
+ goto err_unmap;
+ }
+
addr = dma_map_page(gpusvm->drm->dev,
page, 0,
PAGE_SIZE << order,
@@ -1469,14 +1484,17 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
}
i += 1 << order;
num_dma_mapped = i;
+ flags.has_dma_mapping = true;
}
- range->flags.has_dma_mapping = true;
if (zdd) {
- range->flags.has_devmem_pages = true;
+ flags.has_devmem_pages = true;
range->dpagemap = dpagemap;
}
+ /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */
+ WRITE_ONCE(range->flags.__flags, flags.__flags);
+
drm_gpusvm_notifier_unlock(gpusvm);
kvfree(pfns);
set_seqno:
@@ -1765,6 +1783,8 @@ int drm_gpusvm_migrate_to_devmem(struct drm_gpusvm *gpusvm,
goto err_finalize;
/* Upon success bind devmem allocation to range and zdd */
+ devmem_allocation->timeslice_expiration = get_jiffies_64() +
+ msecs_to_jiffies(ctx->timeslice_ms);
zdd->devmem_allocation = devmem_allocation; /* Owns ref */
err_finalize:
@@ -1985,6 +2005,13 @@ static int __drm_gpusvm_migrate_to_ram(struct vm_area_struct *vas,
void *buf;
int i, err = 0;
+ if (page) {
+ zdd = page->zone_device_data;
+ if (time_before64(get_jiffies_64(),
+ zdd->devmem_allocation->timeslice_expiration))
+ return 0;
+ }
+
start = ALIGN_DOWN(fault_addr, size);
end = ALIGN(fault_addr + 1, size);
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index 89e05a5..a4cd476 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -404,12 +404,16 @@ static void mipi_dbi_blank(struct mipi_dbi_dev *dbidev)
u16 height = drm->mode_config.min_height;
u16 width = drm->mode_config.min_width;
struct mipi_dbi *dbi = &dbidev->dbi;
- size_t len = width * height * 2;
+ const struct drm_format_info *dst_format;
+ size_t len;
int idx;
if (!drm_dev_enter(drm, &idx))
return;
+ dst_format = drm_format_info(dbidev->pixel_format);
+ len = drm_format_info_min_pitch(dst_format, 0, width) * height;
+
memset(dbidev->tx_buf, 0, len);
mipi_dbi_set_window_address(dbidev, 0, width - 1, 0, height - 1);
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 5170f72..f91daef 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -43,13 +43,13 @@ struct decon_data {
unsigned int wincon_burstlen_shift;
};
-static struct decon_data exynos7_decon_data = {
+static const struct decon_data exynos7_decon_data = {
.vidw_buf_start_base = 0x80,
.shadowcon_win_protect_shift = 10,
.wincon_burstlen_shift = 11,
};
-static struct decon_data exynos7870_decon_data = {
+static const struct decon_data exynos7870_decon_data = {
.vidw_buf_start_base = 0x880,
.shadowcon_win_protect_shift = 8,
.wincon_burstlen_shift = 10,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index f313ae7..6cc7bf7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -355,8 +355,7 @@ static void exynos_drm_platform_shutdown(struct platform_device *pdev)
{
struct drm_device *drm = platform_get_drvdata(pdev);
- if (drm)
- drm_atomic_helper_shutdown(drm);
+ drm_atomic_helper_shutdown(drm);
}
static struct platform_driver exynos_drm_platform_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index b150cfd..09e33a2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -908,7 +908,7 @@ static void fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
u32 buf_num;
u32 cfg;
- DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueu[%d]\n", buf_id, enqueue);
+ DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueue[%d]\n", buf_id, enqueue);
spin_lock_irqsave(&ctx->lock, flags);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 1ad8758..c394cc7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -731,7 +731,7 @@ static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win,
/*
* Setting dma-burst to 16Word causes permanent tearing for very small
* buffers, e.g. cursor buffer. Burst Mode switching which based on
- * plane size is not recommended as plane size varies alot towards the
+ * plane size is not recommended as plane size varies a lot towards the
* end of the screen and rapid movement causes unstable DMA, but it is
* still better to change dma-burst than displaying garbage.
*/
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 08cf79a..e644e23 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -312,9 +312,6 @@ static int vidi_get_modes(struct drm_connector *connector)
else
drm_edid = drm_edid_alloc(fake_edid_info, sizeof(fake_edid_info));
- if (!drm_edid)
- return 0;
-
drm_edid_connector_update(connector, drm_edid);
count = drm_edid_connector_add_modes(connector);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 02f9510..6dc2d31 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -242,7 +242,7 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp,
to_intel_connector(conn_state->connector);
const struct drm_display_mode *adjusted_mode =
&crtc_state->hw.adjusted_mode;
- bool is_mst = intel_dp->is_mst;
+ bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
int bpp_x16, slots = -EINVAL;
int dsc_slice_count = 0;
int max_dpt_bpp_x16;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 64e9317..71ee01d 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1001,6 +1001,10 @@ void intel_rps_dec_waiters(struct intel_rps *rps)
if (rps_uses_slpc(rps)) {
slpc = rps_to_slpc(rps);
+ /* Don't decrement num_waiters for req where increment was skipped */
+ if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING)
+ return;
+
intel_guc_slpc_dec_waiters(slpc);
} else {
atomic_dec(&rps->num_waiters);
@@ -1029,11 +1033,15 @@ void intel_rps_boost(struct i915_request *rq)
if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING)
return;
- if (slpc->min_freq_softlimit >= slpc->boost_freq)
- return;
-
/* Return if old value is non zero */
if (!atomic_fetch_inc(&slpc->num_waiters)) {
+ /*
+ * Skip queuing boost work if frequency is already boosted,
+ * but still increment num_waiters.
+ */
+ if (slpc->min_freq_softlimit >= slpc->boost_freq)
+ return;
+
GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
rq->fence.context, rq->fence.seqno);
queue_work(rps_to_gt(rps)->i915->unordered_wq,
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
index 9aae779..4969d3d 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
@@ -23,6 +23,7 @@ int intel_pxp_gsccs_init(struct intel_pxp *pxp);
int intel_pxp_gsccs_create_session(struct intel_pxp *pxp, int arb_session_id);
void intel_pxp_gsccs_end_arb_fw_session(struct intel_pxp *pxp, u32 arb_session_id);
+bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
#else
static inline void intel_pxp_gsccs_fini(struct intel_pxp *pxp)
@@ -34,8 +35,11 @@ static inline int intel_pxp_gsccs_init(struct intel_pxp *pxp)
return 0;
}
-#endif
+static inline bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp)
+{
+ return false;
+}
-bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
+#endif
#endif /*__INTEL_PXP_GSCCS_H__ */
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 81d2ee3..49ff9f1 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -169,7 +169,7 @@ static const struct meson_drm_soc_attr meson_drm_soc_attrs[] = {
/* S805X/S805Y HDMI PLL won't lock for HDMI PHY freq > 1,65GHz */
{
.limits = {
- .max_hdmi_phy_freq = 1650000,
+ .max_hdmi_phy_freq = 1650000000,
},
.attrs = (const struct soc_device_attribute []) {
{ .soc_id = "GXL (S805*)", },
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 3f9345c..be4b0e4 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -37,7 +37,7 @@ struct meson_drm_match_data {
};
struct meson_drm_soc_limits {
- unsigned int max_hdmi_phy_freq;
+ unsigned long long max_hdmi_phy_freq;
};
struct meson_drm {
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 6d1c926..c08fa93 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -70,12 +70,12 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
{
struct meson_drm *priv = encoder_hdmi->priv;
int vic = drm_match_cea_mode(mode);
- unsigned int phy_freq;
- unsigned int vclk_freq;
- unsigned int venc_freq;
- unsigned int hdmi_freq;
+ unsigned long long phy_freq;
+ unsigned long long vclk_freq;
+ unsigned long long venc_freq;
+ unsigned long long hdmi_freq;
- vclk_freq = mode->clock;
+ vclk_freq = mode->clock * 1000ULL;
/* For 420, pixel clock is half unlike venc clock */
if (encoder_hdmi->output_bus_fmt == MEDIA_BUS_FMT_UYYVYY8_0_5X24)
@@ -107,7 +107,8 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
if (mode->flags & DRM_MODE_FLAG_DBLCLK)
venc_freq /= 2;
- dev_dbg(priv->dev, "vclk:%d phy=%d venc=%d hdmi=%d enci=%d\n",
+ dev_dbg(priv->dev,
+ "vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
phy_freq, vclk_freq, venc_freq, hdmi_freq,
priv->venc.hdmi_use_enci);
@@ -122,10 +123,11 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge);
struct meson_drm *priv = encoder_hdmi->priv;
bool is_hdmi2_sink = display_info->hdmi.scdc.supported;
- unsigned int phy_freq;
- unsigned int vclk_freq;
- unsigned int venc_freq;
- unsigned int hdmi_freq;
+ unsigned long long clock = mode->clock * 1000ULL;
+ unsigned long long phy_freq;
+ unsigned long long vclk_freq;
+ unsigned long long venc_freq;
+ unsigned long long hdmi_freq;
int vic = drm_match_cea_mode(mode);
enum drm_mode_status status;
@@ -144,12 +146,12 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
if (status != MODE_OK)
return status;
- return meson_vclk_dmt_supported_freq(priv, mode->clock);
+ return meson_vclk_dmt_supported_freq(priv, clock);
/* Check against supported VIC modes */
} else if (!meson_venc_hdmi_supported_vic(vic))
return MODE_BAD;
- vclk_freq = mode->clock;
+ vclk_freq = clock;
/* For 420, pixel clock is half unlike venc clock */
if (drm_mode_is_420_only(display_info, mode) ||
@@ -179,7 +181,8 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
if (mode->flags & DRM_MODE_FLAG_DBLCLK)
venc_freq /= 2;
- dev_dbg(priv->dev, "%s: vclk:%d phy=%d venc=%d hdmi=%d\n",
+ dev_dbg(priv->dev,
+ "%s: vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz\n",
__func__, phy_freq, vclk_freq, venc_freq, hdmi_freq);
return meson_vclk_vic_supported_freq(priv, phy_freq, vclk_freq);
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index 2a942dc..3325580 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -110,7 +110,10 @@
#define HDMI_PLL_LOCK BIT(31)
#define HDMI_PLL_LOCK_G12A (3 << 30)
-#define FREQ_1000_1001(_freq) DIV_ROUND_CLOSEST(_freq * 1000, 1001)
+#define PIXEL_FREQ_1000_1001(_freq) \
+ DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
+#define PHY_FREQ_1000_1001(_freq) \
+ (PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10)
/* VID PLL Dividers */
enum {
@@ -360,11 +363,11 @@ enum {
};
struct meson_vclk_params {
- unsigned int pll_freq;
- unsigned int phy_freq;
- unsigned int vclk_freq;
- unsigned int venc_freq;
- unsigned int pixel_freq;
+ unsigned long long pll_freq;
+ unsigned long long phy_freq;
+ unsigned long long vclk_freq;
+ unsigned long long venc_freq;
+ unsigned long long pixel_freq;
unsigned int pll_od1;
unsigned int pll_od2;
unsigned int pll_od3;
@@ -372,11 +375,11 @@ struct meson_vclk_params {
unsigned int vclk_div;
} params[] = {
[MESON_VCLK_HDMI_ENCI_54000] = {
- .pll_freq = 4320000,
- .phy_freq = 270000,
- .vclk_freq = 54000,
- .venc_freq = 54000,
- .pixel_freq = 54000,
+ .pll_freq = 4320000000,
+ .phy_freq = 270000000,
+ .vclk_freq = 54000000,
+ .venc_freq = 54000000,
+ .pixel_freq = 54000000,
.pll_od1 = 4,
.pll_od2 = 4,
.pll_od3 = 1,
@@ -384,11 +387,11 @@ struct meson_vclk_params {
.vclk_div = 1,
},
[MESON_VCLK_HDMI_DDR_54000] = {
- .pll_freq = 4320000,
- .phy_freq = 270000,
- .vclk_freq = 54000,
- .venc_freq = 54000,
- .pixel_freq = 27000,
+ .pll_freq = 4320000000,
+ .phy_freq = 270000000,
+ .vclk_freq = 54000000,
+ .venc_freq = 54000000,
+ .pixel_freq = 27000000,
.pll_od1 = 4,
.pll_od2 = 4,
.pll_od3 = 1,
@@ -396,11 +399,11 @@ struct meson_vclk_params {
.vclk_div = 1,
},
[MESON_VCLK_HDMI_DDR_148500] = {
- .pll_freq = 2970000,
- .phy_freq = 742500,
- .vclk_freq = 148500,
- .venc_freq = 148500,
- .pixel_freq = 74250,
+ .pll_freq = 2970000000,
+ .phy_freq = 742500000,
+ .vclk_freq = 148500000,
+ .venc_freq = 148500000,
+ .pixel_freq = 74250000,
.pll_od1 = 4,
.pll_od2 = 1,
.pll_od3 = 1,
@@ -408,11 +411,11 @@ struct meson_vclk_params {
.vclk_div = 1,
},
[MESON_VCLK_HDMI_74250] = {
- .pll_freq = 2970000,
- .phy_freq = 742500,
- .vclk_freq = 74250,
- .venc_freq = 74250,
- .pixel_freq = 74250,
+ .pll_freq = 2970000000,
+ .phy_freq = 742500000,
+ .vclk_freq = 74250000,
+ .venc_freq = 74250000,
+ .pixel_freq = 74250000,
.pll_od1 = 2,
.pll_od2 = 2,
.pll_od3 = 2,
@@ -420,11 +423,11 @@ struct meson_vclk_params {
.vclk_div = 1,
},
[MESON_VCLK_HDMI_148500] = {
- .pll_freq = 2970000,
- .phy_freq = 1485000,
- .vclk_freq = 148500,
- .venc_freq = 148500,
- .pixel_freq = 148500,
+ .pll_freq = 2970000000,
+ .phy_freq = 1485000000,
+ .vclk_freq = 148500000,
+ .venc_freq = 148500000,
+ .pixel_freq = 148500000,
.pll_od1 = 1,
.pll_od2 = 2,
.pll_od3 = 2,
@@ -432,11 +435,11 @@ struct meson_vclk_params {
.vclk_div = 1,
},
[MESON_VCLK_HDMI_297000] = {
- .pll_freq = 5940000,
- .phy_freq = 2970000,
- .venc_freq = 297000,
- .vclk_freq = 297000,
- .pixel_freq = 297000,
+ .pll_freq = 5940000000,
+ .phy_freq = 2970000000,
+ .venc_freq = 297000000,
+ .vclk_freq = 297000000,
+ .pixel_freq = 297000000,
.pll_od1 = 2,
.pll_od2 = 1,
.pll_od3 = 1,
@@ -444,11 +447,11 @@ struct meson_vclk_params {
.vclk_div = 2,
},
[MESON_VCLK_HDMI_594000] = {
- .pll_freq = 5940000,
- .phy_freq = 5940000,
- .venc_freq = 594000,
- .vclk_freq = 594000,
- .pixel_freq = 594000,
+ .pll_freq = 5940000000,
+ .phy_freq = 5940000000,
+ .venc_freq = 594000000,
+ .vclk_freq = 594000000,
+ .pixel_freq = 594000000,
.pll_od1 = 1,
.pll_od2 = 1,
.pll_od3 = 2,
@@ -456,11 +459,11 @@ struct meson_vclk_params {
.vclk_div = 1,
},
[MESON_VCLK_HDMI_594000_YUV420] = {
- .pll_freq = 5940000,
- .phy_freq = 2970000,
- .venc_freq = 594000,
- .vclk_freq = 594000,
- .pixel_freq = 297000,
+ .pll_freq = 5940000000,
+ .phy_freq = 2970000000,
+ .venc_freq = 594000000,
+ .vclk_freq = 594000000,
+ .pixel_freq = 297000000,
.pll_od1 = 2,
.pll_od2 = 1,
.pll_od3 = 1,
@@ -617,16 +620,16 @@ static void meson_hdmi_pll_set_params(struct meson_drm *priv, unsigned int m,
3 << 20, pll_od_to_reg(od3) << 20);
}
-#define XTAL_FREQ 24000
+#define XTAL_FREQ (24 * 1000 * 1000)
static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
- unsigned int pll_freq)
+ unsigned long long pll_freq)
{
/* The GXBB PLL has a /2 pre-multiplier */
if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
- pll_freq /= 2;
+ pll_freq = DIV_ROUND_DOWN_ULL(pll_freq, 2);
- return pll_freq / XTAL_FREQ;
+ return DIV_ROUND_DOWN_ULL(pll_freq, XTAL_FREQ);
}
#define HDMI_FRAC_MAX_GXBB 4096
@@ -635,12 +638,13 @@ static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
unsigned int m,
- unsigned int pll_freq)
+ unsigned long long pll_freq)
{
- unsigned int parent_freq = XTAL_FREQ;
+ unsigned long long parent_freq = XTAL_FREQ;
unsigned int frac_max = HDMI_FRAC_MAX_GXL;
unsigned int frac_m;
unsigned int frac;
+ u32 remainder;
/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
@@ -652,11 +656,11 @@ static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
frac_max = HDMI_FRAC_MAX_G12A;
/* We can have a perfect match !*/
- if (pll_freq / m == parent_freq &&
- pll_freq % m == 0)
+ if (div_u64_rem(pll_freq, m, &remainder) == parent_freq &&
+ remainder == 0)
return 0;
- frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+ frac = mul_u64_u64_div_u64(pll_freq, frac_max, parent_freq);
frac_m = m * frac_max;
if (frac_m > frac)
return frac_max;
@@ -666,7 +670,7 @@ static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
}
static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
- unsigned int m,
+ unsigned long long m,
unsigned int frac)
{
if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
@@ -694,7 +698,7 @@ static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
}
static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
- unsigned int freq,
+ unsigned long long freq,
unsigned int *m,
unsigned int *frac,
unsigned int *od)
@@ -706,7 +710,7 @@ static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
continue;
*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
- DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+ DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d\n",
freq, *m, *frac, *od);
if (meson_hdmi_pll_validate_params(priv, *m, *frac))
@@ -718,7 +722,7 @@ static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
/* pll_freq is the frequency after the OD dividers */
enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq)
{
unsigned int od, m, frac;
@@ -741,7 +745,7 @@ EXPORT_SYMBOL_GPL(meson_vclk_dmt_supported_freq);
/* pll_freq is the frequency after the OD dividers */
static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
- unsigned int pll_freq)
+ unsigned long long pll_freq)
{
unsigned int od, m, frac, od1, od2, od3;
@@ -756,7 +760,7 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
od1 = od / od2;
}
- DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+ DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d/%d/%d\n",
pll_freq, m, frac, od1, od2, od3);
meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
@@ -764,17 +768,18 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
return;
}
- DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+ DRM_ERROR("Fatal, unable to find parameters for PLL freq %lluHz\n",
pll_freq);
}
enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
- unsigned int vclk_freq)
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+ unsigned long long phy_freq,
+ unsigned long long vclk_freq)
{
int i;
- DRM_DEBUG_DRIVER("phy_freq = %d vclk_freq = %d\n",
+ DRM_DEBUG_DRIVER("phy_freq = %lluHz vclk_freq = %lluHz\n",
phy_freq, vclk_freq);
/* Check against soc revision/package limits */
@@ -785,19 +790,19 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
}
for (i = 0 ; params[i].pixel_freq ; ++i) {
- DRM_DEBUG_DRIVER("i = %d pixel_freq = %d alt = %d\n",
+ DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n",
i, params[i].pixel_freq,
- FREQ_1000_1001(params[i].pixel_freq));
- DRM_DEBUG_DRIVER("i = %d phy_freq = %d alt = %d\n",
+ PIXEL_FREQ_1000_1001(params[i].pixel_freq));
+ DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
i, params[i].phy_freq,
- FREQ_1000_1001(params[i].phy_freq/1000)*1000);
+ PHY_FREQ_1000_1001(params[i].phy_freq));
/* Match strict frequency */
if (phy_freq == params[i].phy_freq &&
vclk_freq == params[i].vclk_freq)
return MODE_OK;
/* Match 1000/1001 variant */
- if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/1000)*1000) &&
- vclk_freq == FREQ_1000_1001(params[i].vclk_freq))
+ if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) &&
+ vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq))
return MODE_OK;
}
@@ -805,8 +810,9 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
}
EXPORT_SYMBOL_GPL(meson_vclk_vic_supported_freq);
-static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
- unsigned int od1, unsigned int od2, unsigned int od3,
+static void meson_vclk_set(struct meson_drm *priv,
+ unsigned long long pll_base_freq, unsigned int od1,
+ unsigned int od2, unsigned int od3,
unsigned int vid_pll_div, unsigned int vclk_div,
unsigned int hdmi_tx_div, unsigned int venc_div,
bool hdmi_use_enci, bool vic_alternate_clock)
@@ -826,15 +832,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
meson_hdmi_pll_generic_set(priv, pll_base_freq);
} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
switch (pll_base_freq) {
- case 2970000:
+ case 2970000000:
m = 0x3d;
frac = vic_alternate_clock ? 0xd02 : 0xe00;
break;
- case 4320000:
+ case 4320000000:
m = vic_alternate_clock ? 0x59 : 0x5a;
frac = vic_alternate_clock ? 0xe8f : 0;
break;
- case 5940000:
+ case 5940000000:
m = 0x7b;
frac = vic_alternate_clock ? 0xa05 : 0xc00;
break;
@@ -844,15 +850,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) {
switch (pll_base_freq) {
- case 2970000:
+ case 2970000000:
m = 0x7b;
frac = vic_alternate_clock ? 0x281 : 0x300;
break;
- case 4320000:
+ case 4320000000:
m = vic_alternate_clock ? 0xb3 : 0xb4;
frac = vic_alternate_clock ? 0x347 : 0;
break;
- case 5940000:
+ case 5940000000:
m = 0xf7;
frac = vic_alternate_clock ? 0x102 : 0x200;
break;
@@ -861,15 +867,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
switch (pll_base_freq) {
- case 2970000:
+ case 2970000000:
m = 0x7b;
frac = vic_alternate_clock ? 0x140b4 : 0x18000;
break;
- case 4320000:
+ case 4320000000:
m = vic_alternate_clock ? 0xb3 : 0xb4;
frac = vic_alternate_clock ? 0x1a3ee : 0;
break;
- case 5940000:
+ case 5940000000:
m = 0xf7;
frac = vic_alternate_clock ? 0x8148 : 0x10000;
break;
@@ -1025,14 +1031,14 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
}
void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
- unsigned int phy_freq, unsigned int vclk_freq,
- unsigned int venc_freq, unsigned int dac_freq,
+ unsigned long long phy_freq, unsigned long long vclk_freq,
+ unsigned long long venc_freq, unsigned long long dac_freq,
bool hdmi_use_enci)
{
bool vic_alternate_clock = false;
- unsigned int freq;
- unsigned int hdmi_tx_div;
- unsigned int venc_div;
+ unsigned long long freq;
+ unsigned long long hdmi_tx_div;
+ unsigned long long venc_div;
if (target == MESON_VCLK_TARGET_CVBS) {
meson_venci_cvbs_clock_config(priv);
@@ -1052,27 +1058,27 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
return;
}
- hdmi_tx_div = vclk_freq / dac_freq;
+ hdmi_tx_div = DIV_ROUND_DOWN_ULL(vclk_freq, dac_freq);
if (hdmi_tx_div == 0) {
- pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+ pr_err("Fatal Error, invalid HDMI-TX freq %lluHz\n",
dac_freq);
return;
}
- venc_div = vclk_freq / venc_freq;
+ venc_div = DIV_ROUND_DOWN_ULL(vclk_freq, venc_freq);
if (venc_div == 0) {
- pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+ pr_err("Fatal Error, invalid HDMI venc freq %lluHz\n",
venc_freq);
return;
}
for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
if ((phy_freq == params[freq].phy_freq ||
- phy_freq == FREQ_1000_1001(params[freq].phy_freq/1000)*1000) &&
+ phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) &&
(vclk_freq == params[freq].vclk_freq ||
- vclk_freq == FREQ_1000_1001(params[freq].vclk_freq))) {
+ vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) {
if (vclk_freq != params[freq].vclk_freq)
vic_alternate_clock = true;
else
@@ -1098,7 +1104,8 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
}
if (!params[freq].pixel_freq) {
- pr_err("Fatal Error, invalid HDMI vclk freq %d\n", vclk_freq);
+ pr_err("Fatal Error, invalid HDMI vclk freq %lluHz\n",
+ vclk_freq);
return;
}
diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h
index 60617aa..7ac5574 100644
--- a/drivers/gpu/drm/meson/meson_vclk.h
+++ b/drivers/gpu/drm/meson/meson_vclk.h
@@ -20,17 +20,18 @@ enum {
};
/* 27MHz is the CVBS Pixel Clock */
-#define MESON_VCLK_CVBS 27000
+#define MESON_VCLK_CVBS (27 * 1000 * 1000)
enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq);
enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
- unsigned int vclk_freq);
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+ unsigned long long phy_freq,
+ unsigned long long vclk_freq);
void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
- unsigned int phy_freq, unsigned int vclk_freq,
- unsigned int venc_freq, unsigned int dac_freq,
+ unsigned long long phy_freq, unsigned long long vclk_freq,
+ unsigned long long venc_freq, unsigned long long dac_freq,
bool hdmi_use_enci);
#endif /* __MESON_VCLK_H */
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 7cc8447..edddfc0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -90,7 +90,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
while (!list_empty(&fctx->pending)) {
fence = list_entry(fctx->pending.next, typeof(*fence), head);
- if (error)
+ if (error && !dma_fence_is_signaled_locked(&fence->base))
dma_fence_set_error(&fence->base, error);
if (nouveau_fence_signal(fence))
diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
index 7d68a8a..eb0f837 100644
--- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
@@ -129,11 +129,11 @@ static int jadard_unprepare(struct drm_panel *panel)
{
struct jadard *jadard = panel_to_jadard(panel);
- gpiod_set_value(jadard->reset, 1);
+ gpiod_set_value(jadard->reset, 0);
msleep(120);
if (jadard->desc->reset_before_power_off_vcioo) {
- gpiod_set_value(jadard->reset, 0);
+ gpiod_set_value(jadard->reset, 1);
usleep_range(1000, 2000);
}
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 232b03c..33a3753 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1027,27 +1027,28 @@ static const struct panel_desc auo_g070vvn01 = {
},
};
-static const struct drm_display_mode auo_g101evn010_mode = {
- .clock = 68930,
- .hdisplay = 1280,
- .hsync_start = 1280 + 82,
- .hsync_end = 1280 + 82 + 2,
- .htotal = 1280 + 82 + 2 + 84,
- .vdisplay = 800,
- .vsync_start = 800 + 8,
- .vsync_end = 800 + 8 + 2,
- .vtotal = 800 + 8 + 2 + 6,
+static const struct display_timing auo_g101evn010_timing = {
+ .pixelclock = { 64000000, 68930000, 85000000 },
+ .hactive = { 1280, 1280, 1280 },
+ .hfront_porch = { 8, 64, 256 },
+ .hback_porch = { 8, 64, 256 },
+ .hsync_len = { 40, 168, 767 },
+ .vactive = { 800, 800, 800 },
+ .vfront_porch = { 4, 8, 100 },
+ .vback_porch = { 4, 8, 100 },
+ .vsync_len = { 8, 16, 223 },
};
static const struct panel_desc auo_g101evn010 = {
- .modes = &auo_g101evn010_mode,
- .num_modes = 1,
+ .timings = &auo_g101evn010_timing,
+ .num_timings = 1,
.bpc = 6,
.size = {
.width = 216,
.height = 135,
},
.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
+ .bus_flags = DRM_BUS_FLAG_DE_HIGH,
.connector_type = DRM_MODE_CONNECTOR_LVDS,
};
diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
index fd4215e..925fbc2 100644
--- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c
+++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
@@ -216,6 +216,9 @@ static void drm_gem_shmem_test_get_pages_sgt(struct kunit *test)
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sgt);
KUNIT_EXPECT_NULL(test, shmem->sgt);
+ ret = kunit_add_action_or_reset(test, kfree_wrapper, sgt);
+ KUNIT_ASSERT_EQ(test, ret, 0);
+
ret = kunit_add_action_or_reset(test, sg_free_table_wrapper, sgt);
KUNIT_ASSERT_EQ(test, ret, 0);
diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c
index 0460ecaef..23914a9 100644
--- a/drivers/gpu/drm/tiny/panel-mipi-dbi.c
+++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c
@@ -390,7 +390,10 @@ static int panel_mipi_dbi_spi_probe(struct spi_device *spi)
spi_set_drvdata(spi, drm);
- drm_client_setup(drm, NULL);
+ if (bpp == 16)
+ drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB565);
+ else
+ drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB888);
return 0;
}
diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c
index 93c007f..9e2d72c 100644
--- a/drivers/gpu/drm/ttm/ttm_backup.c
+++ b/drivers/gpu/drm/ttm/ttm_backup.c
@@ -8,20 +8,6 @@
#include <linux/swap.h>
/*
- * Casting from randomized struct file * to struct ttm_backup * is fine since
- * struct ttm_backup is never defined nor dereferenced.
- */
-static struct file *ttm_backup_to_file(struct ttm_backup *backup)
-{
- return (void *)backup;
-}
-
-static struct ttm_backup *ttm_file_to_backup(struct file *file)
-{
- return (void *)file;
-}
-
-/*
* Need to map shmem indices to handle since a handle value
* of 0 means error, following the swp_entry_t convention.
*/
@@ -40,12 +26,12 @@ static pgoff_t ttm_backup_handle_to_shmem_idx(pgoff_t handle)
* @backup: The struct backup pointer used to obtain the handle
* @handle: The handle obtained from the @backup_page function.
*/
-void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle)
+void ttm_backup_drop(struct file *backup, pgoff_t handle)
{
loff_t start = ttm_backup_handle_to_shmem_idx(handle);
start <<= PAGE_SHIFT;
- shmem_truncate_range(file_inode(ttm_backup_to_file(backup)), start,
+ shmem_truncate_range(file_inode(backup), start,
start + PAGE_SIZE - 1);
}
@@ -55,16 +41,15 @@ void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle)
* @backup: The struct backup pointer used to back up the page.
* @dst: The struct page to copy into.
* @handle: The handle returned when the page was backed up.
- * @intr: Try to perform waits interruptable or at least killable.
+ * @intr: Try to perform waits interruptible or at least killable.
*
* Return: 0 on success, Negative error code on failure, notably
* -EINTR if @intr was set to true and a signal is pending.
*/
-int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst,
+int ttm_backup_copy_page(struct file *backup, struct page *dst,
pgoff_t handle, bool intr)
{
- struct file *filp = ttm_backup_to_file(backup);
- struct address_space *mapping = filp->f_mapping;
+ struct address_space *mapping = backup->f_mapping;
struct folio *from_folio;
pgoff_t idx = ttm_backup_handle_to_shmem_idx(handle);
@@ -106,12 +91,11 @@ int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst,
* the folio size- and usage.
*/
s64
-ttm_backup_backup_page(struct ttm_backup *backup, struct page *page,
+ttm_backup_backup_page(struct file *backup, struct page *page,
bool writeback, pgoff_t idx, gfp_t page_gfp,
gfp_t alloc_gfp)
{
- struct file *filp = ttm_backup_to_file(backup);
- struct address_space *mapping = filp->f_mapping;
+ struct address_space *mapping = backup->f_mapping;
unsigned long handle = 0;
struct folio *to_folio;
int ret;
@@ -161,9 +145,9 @@ ttm_backup_backup_page(struct ttm_backup *backup, struct page *page,
*
* After a call to this function, it's illegal to use the @backup pointer.
*/
-void ttm_backup_fini(struct ttm_backup *backup)
+void ttm_backup_fini(struct file *backup)
{
- fput(ttm_backup_to_file(backup));
+ fput(backup);
}
/**
@@ -194,14 +178,10 @@ EXPORT_SYMBOL_GPL(ttm_backup_bytes_avail);
*
* Create a backup utilizing shmem objects.
*
- * Return: A pointer to a struct ttm_backup on success,
+ * Return: A pointer to a struct file on success,
* an error pointer on error.
*/
-struct ttm_backup *ttm_backup_shmem_create(loff_t size)
+struct file *ttm_backup_shmem_create(loff_t size)
{
- struct file *filp;
-
- filp = shmem_file_setup("ttm shmem backup", size, 0);
-
- return ttm_file_to_backup(filp);
+ return shmem_file_setup("ttm shmem backup", size, 0);
}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 95b8600..5bf3c96 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1093,7 +1093,8 @@ struct ttm_bo_swapout_walk {
struct ttm_lru_walk walk;
/** @gfp_flags: The gfp flags to use for ttm_tt_swapout() */
gfp_t gfp_flags;
-
+ /** @hit_low: Whether we should attempt to swap BO's with low watermark threshold */
+ /** @evict_low: If we cannot swap a bo when @try_low is false (first pass) */
bool hit_low, evict_low;
};
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 83b1070..c2ea865 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -506,7 +506,7 @@ static void ttm_pool_allocated_page_commit(struct page *allocated,
* if successful, populate the page-table and dma-address arrays.
*/
static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore,
- struct ttm_backup *backup,
+ struct file *backup,
const struct ttm_operation_ctx *ctx,
struct ttm_pool_alloc_state *alloc)
@@ -655,7 +655,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt,
pgoff_t start_page, pgoff_t end_page)
{
struct page **pages = &tt->pages[start_page];
- struct ttm_backup *backup = tt->backup;
+ struct file *backup = tt->backup;
pgoff_t i, nr;
for (i = start_page; i < end_page; i += nr, pages += nr) {
@@ -963,7 +963,7 @@ void ttm_pool_drop_backed_up(struct ttm_tt *tt)
long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
const struct ttm_backup_flags *flags)
{
- struct ttm_backup *backup = tt->backup;
+ struct file *backup = tt->backup;
struct page *page;
unsigned long handle;
gfp_t alloc_gfp;
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index df0aa6c..698cd4b 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -544,7 +544,7 @@ EXPORT_SYMBOL(ttm_tt_pages_limit);
*/
int ttm_tt_setup_backup(struct ttm_tt *tt)
{
- struct ttm_backup *backup =
+ struct file *backup =
ttm_backup_shmem_create(((loff_t)tt->num_pages) << PAGE_SHIFT);
if (WARN_ON_ONCE(!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)))
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 4a7701a..eb35482 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -744,11 +744,16 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
return DRM_GPU_SCHED_STAT_NOMINAL;
}
-/* If the current address or return address have changed, then the GPU
- * has probably made progress and we should delay the reset. This
- * could fail if the GPU got in an infinite loop in the CL, but that
- * is pretty unlikely outside of an i-g-t testcase.
- */
+static void
+v3d_sched_skip_reset(struct drm_sched_job *sched_job)
+{
+ struct drm_gpu_scheduler *sched = sched_job->sched;
+
+ spin_lock(&sched->job_list_lock);
+ list_add(&sched_job->list, &sched->pending_list);
+ spin_unlock(&sched->job_list_lock);
+}
+
static enum drm_gpu_sched_stat
v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
u32 *timedout_ctca, u32 *timedout_ctra)
@@ -758,9 +763,16 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
+ /* If the current address or return address have changed, then the GPU
+ * has probably made progress and we should delay the reset. This
+ * could fail if the GPU got in an infinite loop in the CL, but that
+ * is pretty unlikely outside of an i-g-t testcase.
+ */
if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
*timedout_ctca = ctca;
*timedout_ctra = ctra;
+
+ v3d_sched_skip_reset(sched_job);
return DRM_GPU_SCHED_STAT_NOMINAL;
}
@@ -800,11 +812,13 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job)
struct v3d_dev *v3d = job->base.v3d;
u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4(v3d->ver));
- /* If we've made progress, skip reset and let the timer get
- * rearmed.
+ /* If we've made progress, skip reset, add the job to the pending
+ * list, and let the timer get rearmed.
*/
if (job->timedout_batches != batches) {
job->timedout_batches = batches;
+
+ v3d_sched_skip_reset(sched_job);
return DRM_GPU_SCHED_STAT_NOMINAL;
}
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 2d88e39..e32e680 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -128,6 +128,14 @@ static void virtio_gpu_remove(struct virtio_device *vdev)
drm_dev_put(dev);
}
+static void virtio_gpu_shutdown(struct virtio_device *vdev)
+{
+ /*
+ * drm does its own synchronization on shutdown.
+ * Do nothing here, opt out of device reset.
+ */
+}
+
static void virtio_gpu_config_changed(struct virtio_device *vdev)
{
struct drm_device *dev = vdev->priv;
@@ -162,6 +170,7 @@ static struct virtio_driver virtio_gpu_driver = {
.id_table = id_table,
.probe = virtio_gpu_probe,
.remove = virtio_gpu_remove,
+ .shutdown = virtio_gpu_shutdown,
.config_changed = virtio_gpu_config_changed
};
diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
index 167fb0f..5a47991 100644
--- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
@@ -47,6 +47,10 @@
#define MI_LRI_FORCE_POSTED REG_BIT(12)
#define MI_LRI_LEN(x) (((x) & 0xff) + 1)
+#define MI_STORE_REGISTER_MEM (__MI_INSTR(0x24) | XE_INSTR_NUM_DW(4))
+#define MI_SRM_USE_GGTT REG_BIT(22)
+#define MI_SRM_ADD_CS_OFFSET REG_BIT(19)
+
#define MI_FLUSH_DW __MI_INSTR(0x26)
#define MI_FLUSH_DW_PROTECTED_MEM_EN REG_BIT(22)
#define MI_FLUSH_DW_STORE_INDEX REG_BIT(21)
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index fb8ec31..891f928 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -43,6 +43,10 @@
#define XEHPC_BCS8_RING_BASE 0x3ee000
#define GSCCS_RING_BASE 0x11a000
+#define ENGINE_ID(base) XE_REG((base) + 0x8c)
+#define ENGINE_INSTANCE_ID REG_GENMASK(9, 4)
+#define ENGINE_CLASS_ID REG_GENMASK(2, 0)
+
#define RING_TAIL(base) XE_REG((base) + 0x30)
#define TAIL_ADDR REG_GENMASK(20, 3)
@@ -154,6 +158,7 @@
#define STOP_RING REG_BIT(8)
#define RING_CTX_TIMESTAMP(base) XE_REG((base) + 0x3a8)
+#define RING_CTX_TIMESTAMP_UDW(base) XE_REG((base) + 0x3ac)
#define CSBE_DEBUG_STATUS(base) XE_REG((base) + 0x3fc)
#define RING_FORCE_TO_NONPRIV(base, i) XE_REG(((base) + 0x4d0) + (i) * 4)
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index da1f198..1819139 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -157,6 +157,7 @@
#define XEHPG_SC_INSTDONE_EXTRA2 XE_REG_MCR(0x7108)
#define COMMON_SLICE_CHICKEN4 XE_REG(0x7300, XE_REG_OPTION_MASKED)
+#define SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE REG_BIT(12)
#define DISABLE_TDC_LOAD_BALANCING_CALC REG_BIT(6)
#define COMMON_SLICE_CHICKEN3 XE_REG(0x7304, XE_REG_OPTION_MASKED)
diff --git a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h
index 57944f9..994af59 100644
--- a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h
+++ b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h
@@ -11,7 +11,9 @@
#define CTX_RING_TAIL (0x06 + 1)
#define CTX_RING_START (0x08 + 1)
#define CTX_RING_CTL (0x0a + 1)
+#define CTX_BB_PER_CTX_PTR (0x12 + 1)
#define CTX_TIMESTAMP (0x22 + 1)
+#define CTX_TIMESTAMP_UDW (0x24 + 1)
#define CTX_INDIRECT_RING_STATE (0x26 + 1)
#define CTX_PDP0_UDW (0x30 + 1)
#define CTX_PDP0_LDW (0x32 + 1)
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c
index ef1e525..0e502fe 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs.c
@@ -46,8 +46,11 @@ static void read_l3cc_table(struct xe_gt *gt,
unsigned int fw_ref, i;
u32 reg_val;
- fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
- KUNIT_ASSERT_NE_MSG(test, fw_ref, 0, "Forcewake Failed.\n");
+ fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+ if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
+ xe_force_wake_put(gt_to_fw(gt), fw_ref);
+ KUNIT_ASSERT_TRUE_MSG(test, true, "Forcewake Failed.\n");
+ }
for (i = 0; i < info->num_mocs_regs; i++) {
if (!(i & 1)) {
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 9f8667e..0482f26 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -330,6 +330,8 @@ struct xe_device {
u8 has_sriov:1;
/** @info.has_usm: Device has unified shared memory support */
u8 has_usm:1;
+ /** @info.has_64bit_timestamp: Device supports 64-bit timestamps */
+ u8 has_64bit_timestamp:1;
/** @info.is_dgfx: is discrete device */
u8 is_dgfx:1;
/**
diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c
index f2bb916..e2bb156 100644
--- a/drivers/gpu/drm/xe/xe_eu_stall.c
+++ b/drivers/gpu/drm/xe/xe_eu_stall.c
@@ -52,6 +52,8 @@ struct xe_eu_stall_data_stream {
struct xe_gt *gt;
struct xe_bo *bo;
+ /* Lock to protect data buffer pointers */
+ struct mutex xecore_buf_lock;
struct per_xecore_buf *xecore_buf;
struct {
bool reported_to_user;
@@ -208,6 +210,9 @@ int xe_eu_stall_init(struct xe_gt *gt)
struct xe_device *xe = gt_to_xe(gt);
int ret;
+ if (!xe_eu_stall_supported_on_platform(xe))
+ return 0;
+
gt->eu_stall = kzalloc(sizeof(*gt->eu_stall), GFP_KERNEL);
if (!gt->eu_stall) {
ret = -ENOMEM;
@@ -378,7 +383,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream)
u16 group, instance;
unsigned int xecore;
- mutex_lock(>->eu_stall->stream_lock);
+ mutex_lock(&stream->xecore_buf_lock);
for_each_dss_steering(xecore, gt, group, instance) {
xecore_buf = &stream->xecore_buf[xecore];
read_ptr = xecore_buf->read;
@@ -396,7 +401,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream)
set_bit(xecore, stream->data_drop.mask);
xecore_buf->write = write_ptr;
}
- mutex_unlock(>->eu_stall->stream_lock);
+ mutex_unlock(&stream->xecore_buf_lock);
return min_data_present;
}
@@ -511,11 +516,13 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st
unsigned int xecore;
int ret = 0;
+ mutex_lock(&stream->xecore_buf_lock);
if (bitmap_weight(stream->data_drop.mask, XE_MAX_DSS_FUSE_BITS)) {
if (!stream->data_drop.reported_to_user) {
stream->data_drop.reported_to_user = true;
xe_gt_dbg(gt, "EU stall data dropped in XeCores: %*pb\n",
XE_MAX_DSS_FUSE_BITS, stream->data_drop.mask);
+ mutex_unlock(&stream->xecore_buf_lock);
return -EIO;
}
stream->data_drop.reported_to_user = false;
@@ -527,6 +534,7 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st
if (ret || count == total_size)
break;
}
+ mutex_unlock(&stream->xecore_buf_lock);
return total_size ?: (ret ?: -EAGAIN);
}
@@ -583,6 +591,7 @@ static void xe_eu_stall_stream_free(struct xe_eu_stall_data_stream *stream)
{
struct xe_gt *gt = stream->gt;
+ mutex_destroy(&stream->xecore_buf_lock);
gt->eu_stall->stream = NULL;
kfree(stream);
}
@@ -718,6 +727,7 @@ static int xe_eu_stall_stream_init(struct xe_eu_stall_data_stream *stream,
}
init_waitqueue_head(&stream->poll_wq);
+ mutex_init(&stream->xecore_buf_lock);
INIT_DELAYED_WORK(&stream->buf_poll_work, eu_stall_data_buf_poll_work_fn);
stream->per_xecore_buf_size = per_xecore_buf_size;
stream->sampling_rate_mult = props->sampling_rate_mult;
diff --git a/drivers/gpu/drm/xe/xe_eu_stall.h b/drivers/gpu/drm/xe/xe_eu_stall.h
index ed9d0f2..d1c76e50 100644
--- a/drivers/gpu/drm/xe/xe_eu_stall.h
+++ b/drivers/gpu/drm/xe/xe_eu_stall.h
@@ -7,6 +7,7 @@
#define __XE_EU_STALL_H__
#include "xe_gt_types.h"
+#include "xe_sriov.h"
size_t xe_eu_stall_get_per_xecore_buf_size(void);
size_t xe_eu_stall_data_record_size(struct xe_device *xe);
@@ -19,6 +20,6 @@ int xe_eu_stall_stream_open(struct drm_device *dev,
static inline bool xe_eu_stall_supported_on_platform(struct xe_device *xe)
{
- return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20;
+ return !IS_SRIOV_VF(xe) && (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20);
}
#endif
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 606922d..cd9b1c3 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -830,7 +830,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
{
struct xe_device *xe = gt_to_xe(q->gt);
struct xe_lrc *lrc;
- u32 old_ts, new_ts;
+ u64 old_ts, new_ts;
int idx;
/*
diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
index fd41113..0bcf970 100644
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@@ -555,6 +555,28 @@ void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc)
flush_work(&gsc->work);
}
+void xe_gsc_stop_prepare(struct xe_gsc *gsc)
+{
+ struct xe_gt *gt = gsc_to_gt(gsc);
+ int ret;
+
+ if (!xe_uc_fw_is_loadable(&gsc->fw) || xe_uc_fw_is_in_error_state(&gsc->fw))
+ return;
+
+ xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GSC);
+
+ /*
+ * If the GSC FW load or the proxy init are interrupted, the only way
+ * to recover it is to do an FLR and reload the GSC from scratch.
+ * Therefore, let's wait for the init to complete before stopping
+ * operations. The proxy init is the last step, so we can just wait on
+ * that
+ */
+ ret = xe_gsc_wait_for_proxy_init_done(gsc);
+ if (ret)
+ xe_gt_err(gt, "failed to wait for GSC init completion before uc stop\n");
+}
+
/*
* wa_14015076503: if the GSC FW is loaded, we need to alert it before doing a
* GSC engine reset by writing a notification bit in the GS1 register and then
diff --git a/drivers/gpu/drm/xe/xe_gsc.h b/drivers/gpu/drm/xe/xe_gsc.h
index d99f66c..b8b8e08 100644
--- a/drivers/gpu/drm/xe/xe_gsc.h
+++ b/drivers/gpu/drm/xe/xe_gsc.h
@@ -16,6 +16,7 @@ struct xe_hw_engine;
int xe_gsc_init(struct xe_gsc *gsc);
int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc);
void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc);
+void xe_gsc_stop_prepare(struct xe_gsc *gsc);
void xe_gsc_load_start(struct xe_gsc *gsc);
void xe_gsc_hwe_irq_handler(struct xe_hw_engine *hwe, u16 intr_vec);
diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c
index 8cf70b2..d0519cd 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.c
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c
@@ -71,6 +71,17 @@ bool xe_gsc_proxy_init_done(struct xe_gsc *gsc)
HECI1_FWSTS1_PROXY_STATE_NORMAL;
}
+int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc)
+{
+ struct xe_gt *gt = gsc_to_gt(gsc);
+
+ /* Proxy init can take up to 500ms, so wait double that for safety */
+ return xe_mmio_wait32(>->mmio, HECI_FWSTS1(MTL_GSC_HECI1_BASE),
+ HECI1_FWSTS1_CURRENT_STATE,
+ HECI1_FWSTS1_PROXY_STATE_NORMAL,
+ USEC_PER_SEC, NULL, false);
+}
+
static void __gsc_proxy_irq_rmw(struct xe_gsc *gsc, u32 clr, u32 set)
{
struct xe_gt *gt = gsc_to_gt(gsc);
diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.h b/drivers/gpu/drm/xe/xe_gsc_proxy.h
index fdef569..7656022 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.h
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.h
@@ -12,6 +12,7 @@ struct xe_gsc;
int xe_gsc_proxy_init(struct xe_gsc *gsc);
bool xe_gsc_proxy_init_done(struct xe_gsc *gsc);
+int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc);
int xe_gsc_proxy_start(struct xe_gsc *gsc);
int xe_gsc_proxy_request_handler(struct xe_gsc *gsc);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 10a9e3c..66198cf 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -857,7 +857,7 @@ void xe_gt_suspend_prepare(struct xe_gt *gt)
fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
- xe_uc_stop_prepare(>->uc);
+ xe_uc_suspend_prepare(>->uc);
xe_force_wake_put(gt_to_fw(gt), fw_ref);
}
diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 2d63a69..f7005a3 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -92,22 +92,23 @@ static int hw_engines(struct xe_gt *gt, struct drm_printer *p)
struct xe_hw_engine *hwe;
enum xe_hw_engine_id id;
unsigned int fw_ref;
+ int ret = 0;
xe_pm_runtime_get(xe);
fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
- xe_pm_runtime_put(xe);
- xe_force_wake_put(gt_to_fw(gt), fw_ref);
- return -ETIMEDOUT;
+ ret = -ETIMEDOUT;
+ goto fw_put;
}
for_each_hw_engine(hwe, gt, id)
xe_hw_engine_print(hwe, p);
+fw_put:
xe_force_wake_put(gt_to_fw(gt), fw_ref);
xe_pm_runtime_put(xe);
- return 0;
+ return ret;
}
static int powergate_info(struct xe_gt *gt, struct drm_printer *p)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index c5ad9a0..0c22b3a 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -435,9 +435,16 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue)
num_eus = bitmap_weight(gt->fuse_topo.eu_mask_per_dss,
XE_MAX_EU_FUSE_BITS) * num_dss;
- /* user can issue separate page faults per EU and per CS */
+ /*
+ * user can issue separate page faults per EU and per CS
+ *
+ * XXX: Multiplier required as compute UMD are getting PF queue errors
+ * without it. Follow on why this multiplier is required.
+ */
+#define PF_MULTIPLIER 8
pf_queue->num_dw =
- (num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW;
+ (num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER;
+#undef PF_MULTIPLIER
pf_queue->gt = gt;
pf_queue->data = devm_kcalloc(xe->drm.dev, pf_queue->num_dw,
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index f6d523e..9095618 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -359,7 +359,7 @@ static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext,
ext->reg = XE_REG(extlist->reg.__reg.addr);
ext->flags = FIELD_PREP(GUC_REGSET_STEERING_NEEDED, 1);
- ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
+ ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id);
ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id);
ext->regname = extlist->name;
}
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 31bc202..769781d 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -941,7 +941,7 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job)
return xe_sched_invalidate_job(job, 2);
}
- ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]);
+ ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(q->lrc[0]));
ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]);
/*
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index df3cedd..03bfba6 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -24,6 +24,7 @@
#include "xe_hw_fence.h"
#include "xe_map.h"
#include "xe_memirq.h"
+#include "xe_mmio.h"
#include "xe_sriov.h"
#include "xe_trace_lrc.h"
#include "xe_vm.h"
@@ -650,6 +651,7 @@ u32 xe_lrc_pphwsp_offset(struct xe_lrc *lrc)
#define LRC_START_SEQNO_PPHWSP_OFFSET (LRC_SEQNO_PPHWSP_OFFSET + 8)
#define LRC_CTX_JOB_TIMESTAMP_OFFSET (LRC_START_SEQNO_PPHWSP_OFFSET + 8)
#define LRC_PARALLEL_PPHWSP_OFFSET 2048
+#define LRC_ENGINE_ID_PPHWSP_OFFSET 2096
#define LRC_PPHWSP_SIZE SZ_4K
u32 xe_lrc_regs_offset(struct xe_lrc *lrc)
@@ -684,7 +686,7 @@ static inline u32 __xe_lrc_start_seqno_offset(struct xe_lrc *lrc)
static u32 __xe_lrc_ctx_job_timestamp_offset(struct xe_lrc *lrc)
{
- /* The start seqno is stored in the driver-defined portion of PPHWSP */
+ /* This is stored in the driver-defined portion of PPHWSP */
return xe_lrc_pphwsp_offset(lrc) + LRC_CTX_JOB_TIMESTAMP_OFFSET;
}
@@ -694,11 +696,21 @@ static inline u32 __xe_lrc_parallel_offset(struct xe_lrc *lrc)
return xe_lrc_pphwsp_offset(lrc) + LRC_PARALLEL_PPHWSP_OFFSET;
}
+static inline u32 __xe_lrc_engine_id_offset(struct xe_lrc *lrc)
+{
+ return xe_lrc_pphwsp_offset(lrc) + LRC_ENGINE_ID_PPHWSP_OFFSET;
+}
+
static u32 __xe_lrc_ctx_timestamp_offset(struct xe_lrc *lrc)
{
return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP * sizeof(u32);
}
+static u32 __xe_lrc_ctx_timestamp_udw_offset(struct xe_lrc *lrc)
+{
+ return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP_UDW * sizeof(u32);
+}
+
static inline u32 __xe_lrc_indirect_ring_offset(struct xe_lrc *lrc)
{
/* Indirect ring state page is at the very end of LRC */
@@ -726,8 +738,10 @@ DECL_MAP_ADDR_HELPERS(regs)
DECL_MAP_ADDR_HELPERS(start_seqno)
DECL_MAP_ADDR_HELPERS(ctx_job_timestamp)
DECL_MAP_ADDR_HELPERS(ctx_timestamp)
+DECL_MAP_ADDR_HELPERS(ctx_timestamp_udw)
DECL_MAP_ADDR_HELPERS(parallel)
DECL_MAP_ADDR_HELPERS(indirect_ring)
+DECL_MAP_ADDR_HELPERS(engine_id)
#undef DECL_MAP_ADDR_HELPERS
@@ -743,18 +757,37 @@ u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc)
}
/**
+ * xe_lrc_ctx_timestamp_udw_ggtt_addr() - Get ctx timestamp udw GGTT address
+ * @lrc: Pointer to the lrc.
+ *
+ * Returns: ctx timestamp udw GGTT address
+ */
+u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc)
+{
+ return __xe_lrc_ctx_timestamp_udw_ggtt_addr(lrc);
+}
+
+/**
* xe_lrc_ctx_timestamp() - Read ctx timestamp value
* @lrc: Pointer to the lrc.
*
* Returns: ctx timestamp value
*/
-u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc)
+u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc)
{
struct xe_device *xe = lrc_to_xe(lrc);
struct iosys_map map;
+ u32 ldw, udw = 0;
map = __xe_lrc_ctx_timestamp_map(lrc);
- return xe_map_read32(xe, &map);
+ ldw = xe_map_read32(xe, &map);
+
+ if (xe->info.has_64bit_timestamp) {
+ map = __xe_lrc_ctx_timestamp_udw_map(lrc);
+ udw = xe_map_read32(xe, &map);
+ }
+
+ return (u64)udw << 32 | ldw;
}
/**
@@ -864,7 +897,7 @@ static void *empty_lrc_data(struct xe_hw_engine *hwe)
static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
{
- u64 desc = xe_vm_pdp4_descriptor(vm, lrc->tile);
+ u64 desc = xe_vm_pdp4_descriptor(vm, gt_to_tile(lrc->gt));
xe_lrc_write_ctx_reg(lrc, CTX_PDP0_UDW, upper_32_bits(desc));
xe_lrc_write_ctx_reg(lrc, CTX_PDP0_LDW, lower_32_bits(desc));
@@ -877,6 +910,65 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
xe_bo_unpin(lrc->bo);
xe_bo_unlock(lrc->bo);
xe_bo_put(lrc->bo);
+ xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo);
+}
+
+/*
+ * xe_lrc_setup_utilization() - Setup wa bb to assist in calculating active
+ * context run ticks.
+ * @lrc: Pointer to the lrc.
+ *
+ * Context Timestamp (CTX_TIMESTAMP) in the LRC accumulates the run ticks of the
+ * context, but only gets updated when the context switches out. In order to
+ * check how long a context has been active before it switches out, two things
+ * are required:
+ *
+ * (1) Determine if the context is running:
+ * To do so, we program the WA BB to set an initial value for CTX_TIMESTAMP in
+ * the LRC. The value chosen is 1 since 0 is the initial value when the LRC is
+ * initialized. During a query, we just check for this value to determine if the
+ * context is active. If the context switched out, it would overwrite this
+ * location with the actual CTX_TIMESTAMP MMIO value. Note that WA BB runs as
+ * the last part of context restore, so reusing this LRC location will not
+ * clobber anything.
+ *
+ * (2) Calculate the time that the context has been active for:
+ * The CTX_TIMESTAMP ticks only when the context is active. If a context is
+ * active, we just use the CTX_TIMESTAMP MMIO as the new value of utilization.
+ * While doing so, we need to read the CTX_TIMESTAMP MMIO for the specific
+ * engine instance. Since we do not know which instance the context is running
+ * on until it is scheduled, we also read the ENGINE_ID MMIO in the WA BB and
+ * store it in the PPHSWP.
+ */
+#define CONTEXT_ACTIVE 1ULL
+static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+{
+ u32 *cmd;
+
+ cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+
+ *cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
+ *cmd++ = ENGINE_ID(0).addr;
+ *cmd++ = __xe_lrc_engine_id_ggtt_addr(lrc);
+ *cmd++ = 0;
+
+ *cmd++ = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
+ *cmd++ = __xe_lrc_ctx_timestamp_ggtt_addr(lrc);
+ *cmd++ = 0;
+ *cmd++ = lower_32_bits(CONTEXT_ACTIVE);
+
+ if (lrc_to_xe(lrc)->info.has_64bit_timestamp) {
+ *cmd++ = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
+ *cmd++ = __xe_lrc_ctx_timestamp_udw_ggtt_addr(lrc);
+ *cmd++ = 0;
+ *cmd++ = upper_32_bits(CONTEXT_ACTIVE);
+ }
+
+ *cmd++ = MI_BATCH_BUFFER_END;
+
+ xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
+ xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
+
}
#define PVC_CTX_ASID (0x2e + 1)
@@ -893,31 +985,40 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
void *init_data = NULL;
u32 arb_enable;
u32 lrc_size;
+ u32 bo_flags;
int err;
kref_init(&lrc->refcount);
+ lrc->gt = gt;
lrc->flags = 0;
lrc_size = ring_size + xe_gt_lrc_size(gt, hwe->class);
if (xe_gt_has_indirect_ring_state(gt))
lrc->flags |= XE_LRC_FLAG_INDIRECT_RING_STATE;
+ bo_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile) | XE_BO_FLAG_GGTT |
+ XE_BO_FLAG_GGTT_INVALIDATE;
+
/*
* FIXME: Perma-pinning LRC as we don't yet support moving GGTT address
* via VM bind calls.
*/
lrc->bo = xe_bo_create_pin_map(xe, tile, vm, lrc_size,
ttm_bo_type_kernel,
- XE_BO_FLAG_VRAM_IF_DGFX(tile) |
- XE_BO_FLAG_GGTT |
- XE_BO_FLAG_GGTT_INVALIDATE);
+ bo_flags);
if (IS_ERR(lrc->bo))
return PTR_ERR(lrc->bo);
+ lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K,
+ ttm_bo_type_kernel,
+ bo_flags);
+ if (IS_ERR(lrc->bb_per_ctx_bo)) {
+ err = PTR_ERR(lrc->bb_per_ctx_bo);
+ goto err_lrc_finish;
+ }
+
lrc->size = lrc_size;
- lrc->tile = gt_to_tile(hwe->gt);
lrc->ring.size = ring_size;
lrc->ring.tail = 0;
- lrc->ctx_timestamp = 0;
xe_hw_fence_ctx_init(&lrc->fence_ctx, hwe->gt,
hwe->fence_irq, hwe->name);
@@ -990,7 +1091,10 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
xe_lrc_read_ctx_reg(lrc, CTX_CONTEXT_CONTROL) |
_MASKED_BIT_ENABLE(CTX_CTRL_PXP_ENABLE));
+ lrc->ctx_timestamp = 0;
xe_lrc_write_ctx_reg(lrc, CTX_TIMESTAMP, 0);
+ if (lrc_to_xe(lrc)->info.has_64bit_timestamp)
+ xe_lrc_write_ctx_reg(lrc, CTX_TIMESTAMP_UDW, 0);
if (xe->info.has_asid && vm)
xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid);
@@ -1019,6 +1123,8 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
map = __xe_lrc_start_seqno_map(lrc);
xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
+ xe_lrc_setup_utilization(lrc);
+
return 0;
err_lrc_finish:
@@ -1238,6 +1344,21 @@ struct iosys_map xe_lrc_parallel_map(struct xe_lrc *lrc)
return __xe_lrc_parallel_map(lrc);
}
+/**
+ * xe_lrc_engine_id() - Read engine id value
+ * @lrc: Pointer to the lrc.
+ *
+ * Returns: context id value
+ */
+static u32 xe_lrc_engine_id(struct xe_lrc *lrc)
+{
+ struct xe_device *xe = lrc_to_xe(lrc);
+ struct iosys_map map;
+
+ map = __xe_lrc_engine_id_map(lrc);
+ return xe_map_read32(xe, &map);
+}
+
static int instr_dw(u32 cmd_header)
{
/* GFXPIPE "SINGLE_DW" opcodes are a single dword */
@@ -1684,7 +1805,7 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc);
snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset;
snapshot->lrc_snapshot = NULL;
- snapshot->ctx_timestamp = xe_lrc_ctx_timestamp(lrc);
+ snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc));
snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc);
return snapshot;
}
@@ -1784,22 +1905,74 @@ void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot)
kfree(snapshot);
}
+static int get_ctx_timestamp(struct xe_lrc *lrc, u32 engine_id, u64 *reg_ctx_ts)
+{
+ u16 class = REG_FIELD_GET(ENGINE_CLASS_ID, engine_id);
+ u16 instance = REG_FIELD_GET(ENGINE_INSTANCE_ID, engine_id);
+ struct xe_hw_engine *hwe;
+ u64 val;
+
+ hwe = xe_gt_hw_engine(lrc->gt, class, instance, false);
+ if (xe_gt_WARN_ONCE(lrc->gt, !hwe || xe_hw_engine_is_reserved(hwe),
+ "Unexpected engine class:instance %d:%d for context utilization\n",
+ class, instance))
+ return -1;
+
+ if (lrc_to_xe(lrc)->info.has_64bit_timestamp)
+ val = xe_mmio_read64_2x32(&hwe->gt->mmio,
+ RING_CTX_TIMESTAMP(hwe->mmio_base));
+ else
+ val = xe_mmio_read32(&hwe->gt->mmio,
+ RING_CTX_TIMESTAMP(hwe->mmio_base));
+
+ *reg_ctx_ts = val;
+
+ return 0;
+}
+
/**
* xe_lrc_update_timestamp() - Update ctx timestamp
* @lrc: Pointer to the lrc.
* @old_ts: Old timestamp value
*
* Populate @old_ts current saved ctx timestamp, read new ctx timestamp and
- * update saved value.
+ * update saved value. With support for active contexts, the calculation may be
+ * slightly racy, so follow a read-again logic to ensure that the context is
+ * still active before returning the right timestamp.
*
* Returns: New ctx timestamp value
*/
-u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts)
+u64 xe_lrc_update_timestamp(struct xe_lrc *lrc, u64 *old_ts)
{
+ u64 lrc_ts, reg_ts;
+ u32 engine_id;
+
*old_ts = lrc->ctx_timestamp;
- lrc->ctx_timestamp = xe_lrc_ctx_timestamp(lrc);
+ lrc_ts = xe_lrc_ctx_timestamp(lrc);
+ /* CTX_TIMESTAMP mmio read is invalid on VF, so return the LRC value */
+ if (IS_SRIOV_VF(lrc_to_xe(lrc))) {
+ lrc->ctx_timestamp = lrc_ts;
+ goto done;
+ }
+ if (lrc_ts == CONTEXT_ACTIVE) {
+ engine_id = xe_lrc_engine_id(lrc);
+ if (!get_ctx_timestamp(lrc, engine_id, ®_ts))
+ lrc->ctx_timestamp = reg_ts;
+
+ /* read lrc again to ensure context is still active */
+ lrc_ts = xe_lrc_ctx_timestamp(lrc);
+ }
+
+ /*
+ * If context switched out, just use the lrc_ts. Note that this needs to
+ * be a separate if condition.
+ */
+ if (lrc_ts != CONTEXT_ACTIVE)
+ lrc->ctx_timestamp = lrc_ts;
+
+done:
trace_xe_lrc_update_timestamp(lrc, *old_ts);
return lrc->ctx_timestamp;
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 0b40f34..eb6e8de 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -120,7 +120,8 @@ void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer
void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot);
u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc);
-u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc);
+u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc);
+u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc);
u32 xe_lrc_ctx_job_timestamp_ggtt_addr(struct xe_lrc *lrc);
u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc);
@@ -136,6 +137,6 @@ u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc);
*
* Returns the current LRC timestamp
*/
-u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts);
+u64 xe_lrc_update_timestamp(struct xe_lrc *lrc, u64 *old_ts);
#endif
diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h
index 71ecb45..ae24cf6 100644
--- a/drivers/gpu/drm/xe/xe_lrc_types.h
+++ b/drivers/gpu/drm/xe/xe_lrc_types.h
@@ -25,8 +25,8 @@ struct xe_lrc {
/** @size: size of lrc including any indirect ring state page */
u32 size;
- /** @tile: tile which this LRC belongs to */
- struct xe_tile *tile;
+ /** @gt: gt which this LRC belongs to */
+ struct xe_gt *gt;
/** @flags: LRC flags */
#define XE_LRC_FLAG_INDIRECT_RING_STATE 0x1
@@ -52,7 +52,10 @@ struct xe_lrc {
struct xe_hw_fence_ctx fence_ctx;
/** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */
- u32 ctx_timestamp;
+ u64 ctx_timestamp;
+
+ /** @bb_per_ctx_bo: buffer object for per context batch wa buffer */
+ struct xe_bo *bb_per_ctx_bo;
};
struct xe_lrc_snapshot;
diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index 9f4632e..e861c69 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -29,9 +29,6 @@ struct xe_modparam xe_modparam = {
module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600);
MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size(in MiB), must be power of 2");
-module_param_named(always_migrate_to_vram, xe_modparam.always_migrate_to_vram, bool, 0444);
-MODULE_PARM_DESC(always_migrate_to_vram, "Always migrate to VRAM on GPU fault");
-
module_param_named_unsafe(force_execlist, xe_modparam.force_execlist, bool, 0444);
MODULE_PARM_DESC(force_execlist, "Force Execlist submission");
diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h
index 84339e5..5a3bfea 100644
--- a/drivers/gpu/drm/xe/xe_module.h
+++ b/drivers/gpu/drm/xe/xe_module.h
@@ -12,7 +12,6 @@
struct xe_modparam {
bool force_execlist;
bool probe_display;
- bool always_migrate_to_vram;
u32 force_vram_bar_size;
int guc_log_level;
char *guc_firmware_path;
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 818f023..f4d108d 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -140,6 +140,7 @@ static const struct xe_graphics_desc graphics_xelpg = {
.has_indirect_ring_state = 1, \
.has_range_tlb_invalidation = 1, \
.has_usm = 1, \
+ .has_64bit_timestamp = 1, \
.va_bits = 48, \
.vm_max_level = 4, \
.hw_engine_mask = \
@@ -668,6 +669,7 @@ static int xe_info_init(struct xe_device *xe,
xe->info.has_range_tlb_invalidation = graphics_desc->has_range_tlb_invalidation;
xe->info.has_usm = graphics_desc->has_usm;
+ xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp;
for_each_remote_tile(tile, xe, id) {
int err;
diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h
index e9b9bbc..ca6b10d 100644
--- a/drivers/gpu/drm/xe/xe_pci_types.h
+++ b/drivers/gpu/drm/xe/xe_pci_types.h
@@ -21,6 +21,7 @@ struct xe_graphics_desc {
u8 has_indirect_ring_state:1;
u8 has_range_tlb_invalidation:1;
u8 has_usm:1;
+ u8 has_64bit_timestamp:1;
};
struct xe_media_desc {
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index ffaf0d0..8560385 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -2232,11 +2232,19 @@ static void op_commit(struct xe_vm *vm,
}
case DRM_GPUVA_OP_DRIVER:
{
+ /* WRITE_ONCE pairs with READ_ONCE in xe_svm.c */
+
if (op->subop == XE_VMA_SUBOP_MAP_RANGE) {
- op->map_range.range->tile_present |= BIT(tile->id);
- op->map_range.range->tile_invalidated &= ~BIT(tile->id);
+ WRITE_ONCE(op->map_range.range->tile_present,
+ op->map_range.range->tile_present |
+ BIT(tile->id));
+ WRITE_ONCE(op->map_range.range->tile_invalidated,
+ op->map_range.range->tile_invalidated &
+ ~BIT(tile->id));
} else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) {
- op->unmap_range.range->tile_present &= ~BIT(tile->id);
+ WRITE_ONCE(op->unmap_range.range->tile_present,
+ op->unmap_range.range->tile_present &
+ ~BIT(tile->id));
}
break;
}
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index a7582b0..bc1689d 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -234,13 +234,10 @@ static u32 get_ppgtt_flag(struct xe_sched_job *job)
static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
{
- dw[i++] = MI_COPY_MEM_MEM | MI_COPY_MEM_MEM_SRC_GGTT |
- MI_COPY_MEM_MEM_DST_GGTT;
+ dw[i++] = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
+ dw[i++] = RING_CTX_TIMESTAMP(0).addr;
dw[i++] = xe_lrc_ctx_job_timestamp_ggtt_addr(lrc);
dw[i++] = 0;
- dw[i++] = xe_lrc_ctx_timestamp_ggtt_addr(lrc);
- dw[i++] = 0;
- dw[i++] = MI_NOOP;
return i;
}
diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c
index 8184390..86d47aa 100644
--- a/drivers/gpu/drm/xe/xe_shrinker.c
+++ b/drivers/gpu/drm/xe/xe_shrinker.c
@@ -227,7 +227,7 @@ struct xe_shrinker *xe_shrinker_create(struct xe_device *xe)
if (!shrinker)
return ERR_PTR(-ENOMEM);
- shrinker->shrink = shrinker_alloc(0, "xe system shrinker");
+ shrinker->shrink = shrinker_alloc(0, "drm-xe_gem:%s", xe->drm.unique);
if (!shrinker->shrink) {
kfree(shrinker);
return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index f8c1285..975094c 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -15,8 +15,17 @@
static bool xe_svm_range_in_vram(struct xe_svm_range *range)
{
- /* Not reliable without notifier lock */
- return range->base.flags.has_devmem_pages;
+ /*
+ * Advisory only check whether the range is currently backed by VRAM
+ * memory.
+ */
+
+ struct drm_gpusvm_range_flags flags = {
+ /* Pairs with WRITE_ONCE in drm_gpusvm.c */
+ .__flags = READ_ONCE(range->base.flags.__flags),
+ };
+
+ return flags.has_devmem_pages;
}
static bool xe_svm_range_has_vram_binding(struct xe_svm_range *range)
@@ -79,7 +88,7 @@ xe_svm_range_alloc(struct drm_gpusvm *gpusvm)
range = kzalloc(sizeof(*range), GFP_KERNEL);
if (!range)
- return ERR_PTR(-ENOMEM);
+ return NULL;
INIT_LIST_HEAD(&range->garbage_collector_link);
xe_vm_get(gpusvm_to_vm(gpusvm));
@@ -645,9 +654,16 @@ void xe_svm_fini(struct xe_vm *vm)
}
static bool xe_svm_range_is_valid(struct xe_svm_range *range,
- struct xe_tile *tile)
+ struct xe_tile *tile,
+ bool devmem_only)
{
- return (range->tile_present & ~range->tile_invalidated) & BIT(tile->id);
+ /*
+ * Advisory only check whether the range currently has a valid mapping,
+ * READ_ONCE pairs with WRITE_ONCE in xe_pt.c
+ */
+ return ((READ_ONCE(range->tile_present) &
+ ~READ_ONCE(range->tile_invalidated)) & BIT(tile->id)) &&
+ (!devmem_only || xe_svm_range_in_vram(range));
}
static struct xe_vram_region *tile_to_vr(struct xe_tile *tile)
@@ -712,6 +728,36 @@ static int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
return err;
}
+static bool supports_4K_migration(struct xe_device *xe)
+{
+ if (xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K)
+ return false;
+
+ return true;
+}
+
+static bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range,
+ struct xe_vma *vma)
+{
+ struct xe_vm *vm = range_to_vm(&range->base);
+ u64 range_size = xe_svm_range_size(range);
+
+ if (!range->base.flags.migrate_devmem)
+ return false;
+
+ if (xe_svm_range_in_vram(range)) {
+ drm_dbg(&vm->xe->drm, "Range is already in VRAM\n");
+ return false;
+ }
+
+ if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) {
+ drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n");
+ return false;
+ }
+
+ return true;
+}
+
/**
* xe_svm_handle_pagefault() - SVM handle page fault
* @vm: The VM.
@@ -735,11 +781,16 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
.check_pages_threshold = IS_DGFX(vm->xe) &&
IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0,
+ .devmem_only = atomic && IS_DGFX(vm->xe) &&
+ IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
+ .timeslice_ms = atomic && IS_DGFX(vm->xe) &&
+ IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? 5 : 0,
};
struct xe_svm_range *range;
struct drm_gpusvm_range *r;
struct drm_exec exec;
struct dma_fence *fence;
+ int migrate_try_count = ctx.devmem_only ? 3 : 1;
ktime_t end = 0;
int err;
@@ -758,24 +809,31 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
if (IS_ERR(r))
return PTR_ERR(r);
+ if (ctx.devmem_only && !r->flags.migrate_devmem)
+ return -EACCES;
+
range = to_xe_range(r);
- if (xe_svm_range_is_valid(range, tile))
+ if (xe_svm_range_is_valid(range, tile, ctx.devmem_only))
return 0;
range_debug(range, "PAGE FAULT");
- /* XXX: Add migration policy, for now migrate range once */
- if (!range->skip_migrate && range->base.flags.migrate_devmem &&
- xe_svm_range_size(range) >= SZ_64K) {
- range->skip_migrate = true;
-
+ if (--migrate_try_count >= 0 &&
+ xe_svm_range_needs_migrate_to_vram(range, vma)) {
err = xe_svm_alloc_vram(vm, tile, range, &ctx);
+ ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */
if (err) {
- drm_dbg(&vm->xe->drm,
- "VRAM allocation failed, falling back to "
- "retrying fault, asid=%u, errno=%pe\n",
- vm->usm.asid, ERR_PTR(err));
- goto retry;
+ if (migrate_try_count || !ctx.devmem_only) {
+ drm_dbg(&vm->xe->drm,
+ "VRAM allocation failed, falling back to retrying fault, asid=%u, errno=%pe\n",
+ vm->usm.asid, ERR_PTR(err));
+ goto retry;
+ } else {
+ drm_err(&vm->xe->drm,
+ "VRAM allocation failed, retry count exceeded, asid=%u, errno=%pe\n",
+ vm->usm.asid, ERR_PTR(err));
+ return err;
+ }
}
}
@@ -783,15 +841,23 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx);
/* Corner where CPU mappings have changed */
if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) {
- if (err == -EOPNOTSUPP) {
- range_debug(range, "PAGE FAULT - EVICT PAGES");
- drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base);
+ ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */
+ if (migrate_try_count > 0 || !ctx.devmem_only) {
+ if (err == -EOPNOTSUPP) {
+ range_debug(range, "PAGE FAULT - EVICT PAGES");
+ drm_gpusvm_range_evict(&vm->svm.gpusvm,
+ &range->base);
+ }
+ drm_dbg(&vm->xe->drm,
+ "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
+ vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
+ range_debug(range, "PAGE FAULT - RETRY PAGES");
+ goto retry;
+ } else {
+ drm_err(&vm->xe->drm,
+ "Get pages failed, retry count exceeded, asid=%u, gpusvm=%p, errno=%pe\n",
+ vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
}
- drm_dbg(&vm->xe->drm,
- "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
- vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
- range_debug(range, "PAGE FAULT - RETRY PAGES");
- goto retry;
}
if (err) {
range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT");
@@ -815,6 +881,7 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
drm_exec_fini(&exec);
err = PTR_ERR(fence);
if (err == -EAGAIN) {
+ ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */
range_debug(range, "PAGE FAULT - RETRY BIND");
goto retry;
}
@@ -825,9 +892,6 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
}
drm_exec_fini(&exec);
- if (xe_modparam.always_migrate_to_vram)
- range->skip_migrate = false;
-
dma_fence_wait(fence, false);
dma_fence_put(fence);
@@ -947,3 +1011,15 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr)
return 0;
}
#endif
+
+/**
+ * xe_svm_flush() - SVM flush
+ * @vm: The VM.
+ *
+ * Flush all SVM actions.
+ */
+void xe_svm_flush(struct xe_vm *vm)
+{
+ if (xe_vm_in_fault_mode(vm))
+ flush_work(&vm->svm.garbage_collector.work);
+}
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index e059590..fe58ac2 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -36,11 +36,6 @@ struct xe_svm_range {
* range. Protected by GPU SVM notifier lock.
*/
u8 tile_invalidated;
- /**
- * @skip_migrate: Skip migration to VRAM, protected by GPU fault handler
- * locking.
- */
- u8 skip_migrate :1;
};
#if IS_ENABLED(CONFIG_DRM_GPUSVM)
@@ -72,6 +67,9 @@ bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end);
int xe_svm_bo_evict(struct xe_bo *bo);
void xe_svm_range_debug(struct xe_svm_range *range, const char *operation);
+
+void xe_svm_flush(struct xe_vm *vm);
+
#else
static inline bool xe_svm_range_pages_valid(struct xe_svm_range *range)
{
@@ -124,6 +122,11 @@ static inline
void xe_svm_range_debug(struct xe_svm_range *range, const char *operation)
{
}
+
+static inline void xe_svm_flush(struct xe_vm *vm)
+{
+}
+
#endif
/**
diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h b/drivers/gpu/drm/xe/xe_trace_lrc.h
index 5c669a0..d525cbe 100644
--- a/drivers/gpu/drm/xe/xe_trace_lrc.h
+++ b/drivers/gpu/drm/xe/xe_trace_lrc.h
@@ -19,12 +19,12 @@
#define __dev_name_lrc(lrc) dev_name(gt_to_xe((lrc)->fence_ctx.gt)->drm.dev)
TRACE_EVENT(xe_lrc_update_timestamp,
- TP_PROTO(struct xe_lrc *lrc, uint32_t old),
+ TP_PROTO(struct xe_lrc *lrc, uint64_t old),
TP_ARGS(lrc, old),
TP_STRUCT__entry(
__field(struct xe_lrc *, lrc)
- __field(u32, old)
- __field(u32, new)
+ __field(u64, old)
+ __field(u64, new)
__string(name, lrc->fence_ctx.name)
__string(device_id, __dev_name_lrc(lrc))
),
@@ -36,7 +36,7 @@ TRACE_EVENT(xe_lrc_update_timestamp,
__assign_str(name);
__assign_str(device_id);
),
- TP_printk("lrc=:%p lrc->name=%s old=%u new=%u device_id:%s",
+ TP_printk("lrc=:%p lrc->name=%s old=%llu new=%llu device_id:%s",
__entry->lrc, __get_str(name),
__entry->old, __entry->new,
__get_str(device_id))
diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
index c14bd22..3a8751a 100644
--- a/drivers/gpu/drm/xe/xe_uc.c
+++ b/drivers/gpu/drm/xe/xe_uc.c
@@ -244,7 +244,7 @@ void xe_uc_gucrc_disable(struct xe_uc *uc)
void xe_uc_stop_prepare(struct xe_uc *uc)
{
- xe_gsc_wait_for_worker_completion(&uc->gsc);
+ xe_gsc_stop_prepare(&uc->gsc);
xe_guc_stop_prepare(&uc->guc);
}
@@ -278,6 +278,12 @@ static void uc_reset_wait(struct xe_uc *uc)
goto again;
}
+void xe_uc_suspend_prepare(struct xe_uc *uc)
+{
+ xe_gsc_wait_for_worker_completion(&uc->gsc);
+ xe_guc_stop_prepare(&uc->guc);
+}
+
int xe_uc_suspend(struct xe_uc *uc)
{
/* GuC submission not enabled, nothing to do */
diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h
index 3813c1e..c23e6f5 100644
--- a/drivers/gpu/drm/xe/xe_uc.h
+++ b/drivers/gpu/drm/xe/xe_uc.h
@@ -18,6 +18,7 @@ int xe_uc_reset_prepare(struct xe_uc *uc);
void xe_uc_stop_prepare(struct xe_uc *uc);
void xe_uc_stop(struct xe_uc *uc);
int xe_uc_start(struct xe_uc *uc);
+void xe_uc_suspend_prepare(struct xe_uc *uc);
int xe_uc_suspend(struct xe_uc *uc);
int xe_uc_sanitize_reset(struct xe_uc *uc);
void xe_uc_declare_wedged(struct xe_uc *uc);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 6030399..367c84b 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3312,8 +3312,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
}
/* Ensure all UNMAPs visible */
- if (xe_vm_in_fault_mode(vm))
- flush_work(&vm->svm.garbage_collector.work);
+ xe_svm_flush(vm);
err = down_write_killable(&vm->lock);
if (err)
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 24f644c..2f833f0d 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -815,6 +815,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
},
+ { XE_RTP_NAME("22021007897"),
+ XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
+ XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE))
+ },
/* Xe3_LPG */
{ XE_RTP_NAME("14021490052"),
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 17c9660..ab0e5a7 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -93,7 +93,7 @@ pub(crate) fn arch(&self) -> Architecture {
// For now, redirect to fmt::Debug for convenience.
impl fmt::Display for Chipset {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
- write!(f, "{:?}", self)
+ write!(f, "{self:?}")
}
}
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
index 25f0ebf..0a9b44ce 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
@@ -83,6 +83,9 @@ static int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata)
case ALS_IDX:
privdata->dev_en.is_als_present = false;
break;
+ case SRA_IDX:
+ privdata->dev_en.is_sra_present = false;
+ break;
}
if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
@@ -134,9 +137,6 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
for (i = 0; i < cl_data->num_hid_devices; i++) {
cl_data->sensor_sts[i] = SENSOR_DISABLED;
- if (cl_data->num_hid_devices == 1 && cl_data->sensor_idx[0] == SRA_IDX)
- break;
-
if (cl_data->sensor_idx[i] == SRA_IDX) {
info.sensor_idx = cl_data->sensor_idx[i];
writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0));
@@ -145,8 +145,10 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
(privdata, cl_data->sensor_idx[i], ENABLE_SENSOR);
cl_data->sensor_sts[i] = (status == 0) ? SENSOR_ENABLED : SENSOR_DISABLED;
- if (cl_data->sensor_sts[i] == SENSOR_ENABLED)
+ if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
+ cl_data->is_any_sensor_enabled = true;
privdata->dev_en.is_sra_present = true;
+ }
continue;
}
@@ -238,6 +240,8 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
cleanup:
amd_sfh_hid_client_deinit(privdata);
for (i = 0; i < cl_data->num_hid_devices; i++) {
+ if (cl_data->sensor_idx[i] == SRA_IDX)
+ continue;
devm_kfree(dev, cl_data->feature_report[i]);
devm_kfree(dev, in_data->input_report[i]);
devm_kfree(dev, cl_data->report_descr[i]);
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c
index 2e96ec6..9a06f9b 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.c
+++ b/drivers/hid/bpf/hid_bpf_dispatch.c
@@ -38,6 +38,9 @@ dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type
struct hid_bpf_ops *e;
int ret;
+ if (unlikely(hdev->bpf.destroyed))
+ return ERR_PTR(-ENODEV);
+
if (type >= HID_REPORT_TYPES)
return ERR_PTR(-EINVAL);
@@ -93,6 +96,9 @@ int dispatch_hid_bpf_raw_requests(struct hid_device *hdev,
struct hid_bpf_ops *e;
int ret, idx;
+ if (unlikely(hdev->bpf.destroyed))
+ return -ENODEV;
+
if (rtype >= HID_REPORT_TYPES)
return -EINVAL;
@@ -130,6 +136,9 @@ int dispatch_hid_bpf_output_report(struct hid_device *hdev,
struct hid_bpf_ops *e;
int ret, idx;
+ if (unlikely(hdev->bpf.destroyed))
+ return -ENODEV;
+
idx = srcu_read_lock(&hdev->bpf.srcu);
list_for_each_entry_srcu(e, &hdev->bpf.prog_list, list,
srcu_read_lock_held(&hdev->bpf.srcu)) {
diff --git a/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c b/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c
index 1a0aeea..a754710 100644
--- a/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c
+++ b/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c
@@ -157,6 +157,7 @@ static const __u8 fixed_rdesc_vendor[] = {
ReportCount(5) // padding
Input(Const)
// Byte 4 in report - just exists so we get to be a tablet pad
+ UsagePage_Digitizers
Usage_Dig_BarrelSwitch // BTN_STYLUS
ReportCount(1)
ReportSize(1)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 288a2b8..10627313 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -41,6 +41,10 @@
#define USB_VENDOR_ID_ACTIONSTAR 0x2101
#define USB_DEVICE_ID_ACTIONSTAR_1011 0x1011
+#define USB_VENDOR_ID_ADATA_XPG 0x125f
+#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE 0x7505
+#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE 0x7506
+
#define USB_VENDOR_ID_ADS_TECH 0x06e1
#define USB_DEVICE_ID_ADS_TECH_RADIO_SI470X 0xa155
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 6461715..0731473 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -27,6 +27,8 @@
static const struct hid_device_id hid_quirks[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_GAMEPAD), HID_QUIRK_BADPAD },
{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_PREDATOR), HID_QUIRK_BADPAD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE), HID_QUIRK_ALWAYS_POLL },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_AFATECH, USB_DEVICE_ID_AFATECH_AF9016), HID_QUIRK_FULLSPEED_INTERVAL },
{ HID_USB_DEVICE(USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX), HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index dfd9d22..949d307 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -1150,11 +1150,9 @@ static void steam_client_ll_close(struct hid_device *hdev)
struct steam_device *steam = hdev->driver_data;
unsigned long flags;
- bool connected;
spin_lock_irqsave(&steam->lock, flags);
steam->client_opened--;
- connected = steam->connected && !steam->client_opened;
spin_unlock_irqrestore(&steam->lock, flags);
schedule_work(&steam->unregister_work);
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index 3b81468..0bf7066 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -174,6 +174,7 @@ static void thrustmaster_interrupts(struct hid_device *hdev)
u8 ep_addr[2] = {b_ep, 0};
if (!usb_check_int_endpoints(usbif, ep_addr)) {
+ kfree(send_buf);
hid_err(hdev, "Unexpected non-int endpoint\n");
return;
}
diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c
index a367df6..61a4019 100644
--- a/drivers/hid/hid-uclogic-core.c
+++ b/drivers/hid/hid-uclogic-core.c
@@ -142,11 +142,12 @@ static int uclogic_input_configured(struct hid_device *hdev,
suffix = "System Control";
break;
}
- }
-
- if (suffix)
+ } else {
hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL,
"%s %s", hdev->name, suffix);
+ if (!hi->input->name)
+ return -ENOMEM;
+ }
return 0;
}
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 1556d4287..eaf099b2 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -70,10 +70,16 @@ static void wacom_wac_queue_flush(struct hid_device *hdev,
{
while (!kfifo_is_empty(fifo)) {
int size = kfifo_peek_len(fifo);
- u8 *buf = kzalloc(size, GFP_KERNEL);
+ u8 *buf;
unsigned int count;
int err;
+ buf = kzalloc(size, GFP_KERNEL);
+ if (!buf) {
+ kfifo_skip(fifo);
+ continue;
+ }
+
count = kfifo_out(fifo, buf, size);
if (count != size) {
// Hard to say what is the "right" action in this
@@ -81,6 +87,7 @@ static void wacom_wac_queue_flush(struct hid_device *hdev,
// to flush seems reasonable enough, however.
hid_warn(hdev, "%s: removed fifo entry with unexpected size\n",
__func__);
+ kfree(buf);
continue;
}
err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, false);
@@ -2361,6 +2368,8 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
unsigned int connect_mask = HID_CONNECT_HIDRAW;
features->pktlen = wacom_compute_pktlen(hdev);
+ if (!features->pktlen)
+ return -ENODEV;
if (!devres_open_group(&hdev->dev, wacom, GFP_KERNEL))
return -ENOMEM;
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index fb8cd84..35f26fa 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -1077,68 +1077,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
EXPORT_SYMBOL(vmbus_sendpacket);
/*
- * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer
- * packets using a GPADL Direct packet type. This interface allows you
- * to control notifying the host. This will be useful for sending
- * batched data. Also the sender can control the send flags
- * explicitly.
- */
-int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
- struct hv_page_buffer pagebuffers[],
- u32 pagecount, void *buffer, u32 bufferlen,
- u64 requestid)
-{
- int i;
- struct vmbus_channel_packet_page_buffer desc;
- u32 descsize;
- u32 packetlen;
- u32 packetlen_aligned;
- struct kvec bufferlist[3];
- u64 aligned_data = 0;
-
- if (pagecount > MAX_PAGE_BUFFER_COUNT)
- return -EINVAL;
-
- /*
- * Adjust the size down since vmbus_channel_packet_page_buffer is the
- * largest size we support
- */
- descsize = sizeof(struct vmbus_channel_packet_page_buffer) -
- ((MAX_PAGE_BUFFER_COUNT - pagecount) *
- sizeof(struct hv_page_buffer));
- packetlen = descsize + bufferlen;
- packetlen_aligned = ALIGN(packetlen, sizeof(u64));
-
- /* Setup the descriptor */
- desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
- desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
- desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */
- desc.length8 = (u16)(packetlen_aligned >> 3);
- desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
- desc.reserved = 0;
- desc.rangecount = pagecount;
-
- for (i = 0; i < pagecount; i++) {
- desc.range[i].len = pagebuffers[i].len;
- desc.range[i].offset = pagebuffers[i].offset;
- desc.range[i].pfn = pagebuffers[i].pfn;
- }
-
- bufferlist[0].iov_base = &desc;
- bufferlist[0].iov_len = descsize;
- bufferlist[1].iov_base = buffer;
- bufferlist[1].iov_len = bufferlen;
- bufferlist[2].iov_base = &aligned_data;
- bufferlist[2].iov_len = (packetlen_aligned - packetlen);
-
- return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL);
-}
-EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
-
-/*
- * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
+ * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets
* using a GPADL Direct packet type.
- * The buffer includes the vmbus descriptor.
+ * The desc argument must include space for the VMBus descriptor. The
+ * rangecount field must already be set.
*/
int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
struct vmbus_packet_mpb_array *desc,
@@ -1160,7 +1102,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
desc->length8 = (u16)(packetlen_aligned >> 3);
desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
desc->reserved = 0;
- desc->rangecount = 1;
bufferlist[0].iov_base = desc;
bufferlist[0].iov_len = desc_size;
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index b3b11be..59792e0 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -307,7 +307,7 @@ void __init hv_get_partition_id(void)
local_irq_save(flags);
output = *this_cpu_ptr(hyperv_pcpu_input_arg);
- status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, &output);
+ status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output);
pt_id = output->partition_id;
local_irq_restore(flags);
@@ -566,9 +566,11 @@ int hv_common_cpu_die(unsigned int cpu)
* originally allocated memory is reused in hv_common_cpu_init().
*/
- synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
- kfree(*synic_eventring_tail);
- *synic_eventring_tail = NULL;
+ if (hv_root_partition()) {
+ synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
+ kfree(*synic_eventring_tail);
+ *synic_eventring_tail = NULL;
+ }
return 0;
}
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 29780f3..0b450e5 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev)
#endif /* CONFIG_HYPERV_TESTING */
+/* Create and remove sysfs entry for memory mapped ring buffers for a channel */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+ int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+ struct vm_area_struct *vma));
+int hv_remove_ring_sysfs(struct vmbus_channel *channel);
+
#endif /* _HYPERV_VMBUS_H */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 8d3cff4..e3d51a3 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1802,6 +1802,26 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel,
}
static VMBUS_CHAN_ATTR_RO(subchannel_id);
+static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj,
+ const struct bin_attribute *attr,
+ struct vm_area_struct *vma)
+{
+ struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj);
+
+ /*
+ * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer
+ * is not NULL.
+ */
+ return channel->mmap_ring_buffer(channel, vma);
+}
+
+static struct bin_attribute chan_attr_ring_buffer = {
+ .attr = {
+ .name = "ring",
+ .mode = 0600,
+ },
+ .mmap = hv_mmap_ring_buffer_wrapper,
+};
static struct attribute *vmbus_chan_attrs[] = {
&chan_attr_out_mask.attr,
&chan_attr_in_mask.attr,
@@ -1821,6 +1841,11 @@ static struct attribute *vmbus_chan_attrs[] = {
NULL
};
+static struct bin_attribute *vmbus_chan_bin_attrs[] = {
+ &chan_attr_ring_buffer,
+ NULL
+};
+
/*
* Channel-level attribute_group callback function. Returns the permission for
* each attribute, and returns 0 if an attribute is not visible.
@@ -1841,9 +1866,34 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj,
return attr->mode;
}
+static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj,
+ const struct bin_attribute *attr, int idx)
+{
+ const struct vmbus_channel *channel =
+ container_of(kobj, struct vmbus_channel, kobj);
+
+ /* Hide ring attribute if channel's ring_sysfs_visible is set to false */
+ if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible)
+ return 0;
+
+ return attr->attr.mode;
+}
+
+static size_t vmbus_chan_bin_size(struct kobject *kobj,
+ const struct bin_attribute *bin_attr, int a)
+{
+ const struct vmbus_channel *channel =
+ container_of(kobj, struct vmbus_channel, kobj);
+
+ return channel->ringbuffer_pagecount << PAGE_SHIFT;
+}
+
static const struct attribute_group vmbus_chan_group = {
.attrs = vmbus_chan_attrs,
- .is_visible = vmbus_chan_attr_is_visible
+ .bin_attrs = vmbus_chan_bin_attrs,
+ .is_visible = vmbus_chan_attr_is_visible,
+ .is_bin_visible = vmbus_chan_bin_attr_is_visible,
+ .bin_size = vmbus_chan_bin_size,
};
static const struct kobj_type vmbus_chan_ktype = {
@@ -1851,6 +1901,63 @@ static const struct kobj_type vmbus_chan_ktype = {
.release = vmbus_chan_release,
};
+/**
+ * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of
+ * channel's "ring" sysfs node, which is for the ring buffer of that channel.
+ * Function pointer is of below type:
+ * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+ * struct vm_area_struct *vma))
+ * This has a pointer to the channel and a pointer to vm_area_struct,
+ * used for mmap, as arguments.
+ *
+ * Sysfs node for ring buffer of a channel is created along with other fields, however its
+ * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case
+ * is running.
+ * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of
+ * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid
+ * exposing the ring buffer by default, this function is reponsible to enable visibility of
+ * ring for userspace to use.
+ * Note: Race conditions can happen with userspace and it is not encouraged to create new
+ * use-cases for this. This was added to maintain backward compatibility, while solving
+ * one of the race conditions in uio_hv_generic while creating sysfs.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+ int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+ struct vm_area_struct *vma))
+{
+ struct kobject *kobj = &channel->kobj;
+
+ channel->mmap_ring_buffer = hv_mmap_ring_buffer;
+ channel->ring_sysfs_visible = true;
+
+ return sysfs_update_group(kobj, &vmbus_chan_group);
+}
+EXPORT_SYMBOL_GPL(hv_create_ring_sysfs);
+
+/**
+ * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ *
+ * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_remove_ring_sysfs(struct vmbus_channel *channel)
+{
+ struct kobject *kobj = &channel->kobj;
+ int ret;
+
+ channel->ring_sysfs_visible = false;
+ ret = sysfs_update_group(kobj, &vmbus_chan_group);
+ channel->mmap_ring_buffer = NULL;
+ return ret;
+}
+EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs);
+
/*
* vmbus_add_channel_kobj - setup a sub-directory under device/channels
*/
diff --git a/drivers/hwtracing/intel_th/Kconfig b/drivers/hwtracing/intel_th/Kconfig
index 4b63593..4f7d2b6 100644
--- a/drivers/hwtracing/intel_th/Kconfig
+++ b/drivers/hwtracing/intel_th/Kconfig
@@ -60,6 +60,7 @@
config INTEL_TH_MSU
tristate "Intel(R) Trace Hub Memory Storage Unit"
+ depends on MMU
help
Memory Storage Unit (MSU) trace output device enables
storing STP traces to system memory. It supports single
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index bf99d79..7163950 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -19,6 +19,7 @@
#include <linux/io.h>
#include <linux/workqueue.h>
#include <linux/dma-mapping.h>
+#include <linux/pfn_t.h>
#ifdef CONFIG_X86
#include <asm/set_memory.h>
@@ -976,7 +977,6 @@ static void msc_buffer_contig_free(struct msc *msc)
for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
struct page *page = virt_to_page(msc->base + off);
- page->mapping = NULL;
__free_page(page);
}
@@ -1158,9 +1158,6 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
int i;
for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
- struct page *page = msc_sg_page(sg);
-
- page->mapping = NULL;
dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
sg_virt(sg), sg_dma_address(sg));
}
@@ -1601,22 +1598,10 @@ static void msc_mmap_close(struct vm_area_struct *vma)
{
struct msc_iter *iter = vma->vm_file->private_data;
struct msc *msc = iter->msc;
- unsigned long pg;
if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
return;
- /* drop page _refcounts */
- for (pg = 0; pg < msc->nr_pages; pg++) {
- struct page *page = msc_buffer_get_page(msc, pg);
-
- if (WARN_ON_ONCE(!page))
- continue;
-
- if (page->mapping)
- page->mapping = NULL;
- }
-
/* last mapping -- drop user_count */
atomic_dec(&msc->user_count);
mutex_unlock(&msc->buf_mutex);
@@ -1626,16 +1611,14 @@ static vm_fault_t msc_mmap_fault(struct vm_fault *vmf)
{
struct msc_iter *iter = vmf->vma->vm_file->private_data;
struct msc *msc = iter->msc;
+ struct page *page;
- vmf->page = msc_buffer_get_page(msc, vmf->pgoff);
- if (!vmf->page)
+ page = msc_buffer_get_page(msc, vmf->pgoff);
+ if (!page)
return VM_FAULT_SIGBUS;
- get_page(vmf->page);
- vmf->page->mapping = vmf->vma->vm_file->f_mapping;
- vmf->page->index = vmf->pgoff;
-
- return 0;
+ get_page(page);
+ return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn_t(page));
}
static const struct vm_operations_struct msc_mmap_ops = {
@@ -1676,7 +1659,7 @@ static int intel_th_msc_mmap(struct file *file, struct vm_area_struct *vma)
atomic_dec(&msc->user_count);
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
+ vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY | VM_MIXEDMAP);
vma->vm_ops = &msc_mmap_ops;
return ret;
}
diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c
index 8e0267c..f21f987 100644
--- a/drivers/i2c/busses/i2c-designware-pcidrv.c
+++ b/drivers/i2c/busses/i2c-designware-pcidrv.c
@@ -278,9 +278,11 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev,
if ((dev->flags & MODEL_MASK) == MODEL_AMD_NAVI_GPU) {
dev->slave = i2c_new_ccgx_ucsi(&dev->adapter, dev->irq, &dgpu_node);
- if (IS_ERR(dev->slave))
+ if (IS_ERR(dev->slave)) {
+ i2c_del_adapter(&dev->adapter);
return dev_err_probe(device, PTR_ERR(dev->slave),
"register UCSI failed\n");
+ }
}
pm_runtime_set_autosuspend_delay(device, 1000);
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index 0d4b393..342d47e 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -1380,9 +1380,9 @@ static int lpi2c_imx_probe(struct platform_device *pdev)
return 0;
rpm_disable:
- pm_runtime_put(&pdev->dev);
- pm_runtime_disable(&pdev->dev);
pm_runtime_dont_use_autosuspend(&pdev->dev);
+ pm_runtime_put_sync(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
return ret;
}
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 16afb9c..876791d 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1454,7 +1454,7 @@ omap_i2c_probe(struct platform_device *pdev)
(1000 * omap->speed / 8);
}
- if (of_property_read_bool(node, "mux-states")) {
+ if (of_property_present(node, "mux-states")) {
struct mux_state *mux_state;
mux_state = devm_mux_state_get(&pdev->dev, NULL);
diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c
index 8601b9a8..5127e58 100644
--- a/drivers/iio/accel/adis16201.c
+++ b/drivers/iio/accel/adis16201.c
@@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = {
BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12),
ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X,
- BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+ BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y,
- BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+ BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
IIO_CHAN_SOFT_TIMESTAMP(7)
};
diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c
index e8cd21fa..cbac622 100644
--- a/drivers/iio/accel/adxl355_core.c
+++ b/drivers/iio/accel/adxl355_core.c
@@ -231,7 +231,7 @@ struct adxl355_data {
u8 transf_buf[3];
struct {
u8 buf[14];
- s64 ts;
+ aligned_s64 ts;
} buffer;
} __aligned(IIO_DMA_MINALIGN);
};
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index add4053..0c04b2b 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -601,18 +601,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr)
if (ret)
return ret;
+ st->odr = odr;
+
/* Activity timers depend on ODR */
ret = _adxl367_set_act_time_ms(st, st->act_time_ms);
if (ret)
return ret;
- ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms);
- if (ret)
- return ret;
-
- st->odr = odr;
-
- return 0;
+ return _adxl367_set_inact_time_ms(st, st->inact_time_ms);
}
static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr)
diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c
index 48e4282..bf1d392 100644
--- a/drivers/iio/accel/fxls8962af-core.c
+++ b/drivers/iio/accel/fxls8962af-core.c
@@ -1226,8 +1226,11 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq)
if (ret)
return ret;
- if (device_property_read_bool(dev, "wakeup-source"))
- device_init_wakeup(dev, true);
+ if (device_property_read_bool(dev, "wakeup-source")) {
+ ret = devm_device_init_wakeup(dev);
+ if (ret)
+ return dev_err_probe(dev, ret, "Failed to init wakeup\n");
+ }
return devm_iio_device_register(dev, indio_dev);
}
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 1855975..7fef272 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -45,7 +45,7 @@ struct ad7266_state {
*/
struct {
__be16 sample[2];
- s64 timestamp;
+ aligned_s64 timestamp;
} data __aligned(IIO_DMA_MINALIGN);
};
diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c
index 4fcb49f..aef8509 100644
--- a/drivers/iio/adc/ad7380.c
+++ b/drivers/iio/adc/ad7380.c
@@ -1211,6 +1211,9 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev)
struct ad7380_state *st = iio_priv(indio_dev);
int ret;
+ spi_offload_trigger_disable(st->offload, st->offload_trigger);
+ spi_unoptimize_message(&st->offload_msg);
+
if (st->seq) {
ret = regmap_update_bits(st->regmap,
AD7380_REG_ADDR_CONFIG1,
@@ -1222,10 +1225,6 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev)
st->seq = false;
}
- spi_offload_trigger_disable(st->offload, st->offload_trigger);
-
- spi_unoptimize_message(&st->offload_msg);
-
return 0;
}
@@ -1611,11 +1610,25 @@ static int ad7380_write_event_config(struct iio_dev *indio_dev,
return ret;
}
-static int ad7380_get_alert_th(struct ad7380_state *st,
+static int ad7380_get_alert_th(struct iio_dev *indio_dev,
+ const struct iio_chan_spec *chan,
enum iio_event_direction dir,
int *val)
{
- int ret, tmp;
+ struct ad7380_state *st = iio_priv(indio_dev);
+ const struct iio_scan_type *scan_type;
+ int ret, tmp, shift;
+
+ scan_type = iio_get_current_scan_type(indio_dev, chan);
+ if (IS_ERR(scan_type))
+ return PTR_ERR(scan_type);
+
+ /*
+ * The register value is 12-bits and is compared to the most significant
+ * bits of raw value, therefore a shift is required to convert this to
+ * the same scale as the raw value.
+ */
+ shift = scan_type->realbits - 12;
switch (dir) {
case IIO_EV_DIR_RISING:
@@ -1625,7 +1638,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st,
if (ret)
return ret;
- *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp);
+ *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp) << shift;
return IIO_VAL_INT;
case IIO_EV_DIR_FALLING:
ret = regmap_read(st->regmap,
@@ -1634,7 +1647,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st,
if (ret)
return ret;
- *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp);
+ *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp) << shift;
return IIO_VAL_INT;
default:
return -EINVAL;
@@ -1648,7 +1661,6 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev,
enum iio_event_info info,
int *val, int *val2)
{
- struct ad7380_state *st = iio_priv(indio_dev);
int ret;
switch (info) {
@@ -1656,7 +1668,7 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev,
if (!iio_device_claim_direct(indio_dev))
return -EBUSY;
- ret = ad7380_get_alert_th(st, dir, val);
+ ret = ad7380_get_alert_th(indio_dev, chan, dir, val);
iio_device_release_direct(indio_dev);
return ret;
diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
index 1a314fd..703556e 100644
--- a/drivers/iio/adc/ad7606.c
+++ b/drivers/iio/adc/ad7606.c
@@ -1236,9 +1236,11 @@ static int ad7616_sw_mode_setup(struct iio_dev *indio_dev)
st->write_scale = ad7616_write_scale_sw;
st->write_os = &ad7616_write_os_sw;
- ret = st->bops->sw_mode_config(indio_dev);
- if (ret)
- return ret;
+ if (st->bops->sw_mode_config) {
+ ret = st->bops->sw_mode_config(indio_dev);
+ if (ret)
+ return ret;
+ }
/* Activate Burst mode and SEQEN MODE */
return ad7606_write_mask(st, AD7616_CONFIGURATION_REGISTER,
@@ -1268,6 +1270,9 @@ static int ad7606b_sw_mode_setup(struct iio_dev *indio_dev)
st->write_scale = ad7606_write_scale_sw;
st->write_os = &ad7606_write_os_sw;
+ if (!st->bops->sw_mode_config)
+ return 0;
+
return st->bops->sw_mode_config(indio_dev);
}
diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c
index 885bf0b..179115e 100644
--- a/drivers/iio/adc/ad7606_spi.c
+++ b/drivers/iio/adc/ad7606_spi.c
@@ -131,7 +131,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr)
{
.tx_buf = &st->d16[0],
.len = 2,
- .cs_change = 0,
+ .cs_change = 1,
}, {
.rx_buf = &st->d16[1],
.len = 2,
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index 5a86300..5e0be36 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -168,7 +168,7 @@ struct ad7768_state {
union {
struct {
__be32 chan;
- s64 timestamp;
+ aligned_s64 timestamp;
} scan;
__be32 d32;
u8 d8[2];
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index a1e48a7..359e26e 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -466,7 +466,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p)
struct iio_dev *indio_dev = pf->indio_dev;
struct {
__le16 values[DLN2_ADC_MAX_CHANNELS];
- int64_t timestamp_space;
+ aligned_s64 timestamp_space;
} data;
struct dln2_adc_get_all_vals dev_data;
struct dln2_adc *dln2 = iio_priv(indio_dev);
diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c
index 7fb8b24..b64a8a4 100644
--- a/drivers/iio/adc/qcom-spmi-iadc.c
+++ b/drivers/iio/adc/qcom-spmi-iadc.c
@@ -543,7 +543,9 @@ static int iadc_probe(struct platform_device *pdev)
else
return ret;
} else {
- device_init_wakeup(iadc->dev, 1);
+ ret = devm_device_init_wakeup(iadc->dev);
+ if (ret)
+ return dev_err_probe(iadc->dev, ret, "Failed to init wakeup\n");
}
ret = iadc_update_offset(iadc);
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index 9a099df..5e28bd2 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -520,15 +520,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
if (info->reset)
rockchip_saradc_reset_controller(info->reset);
- /*
- * Use a default value for the converter clock.
- * This may become user-configurable in the future.
- */
- ret = clk_set_rate(info->clk, info->data->clk_rate);
- if (ret < 0)
- return dev_err_probe(&pdev->dev, ret,
- "failed to set adc clk rate\n");
-
ret = regulator_enable(info->vref);
if (ret < 0)
return dev_err_probe(&pdev->dev, ret,
@@ -555,6 +546,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
if (IS_ERR(info->clk))
return dev_err_probe(&pdev->dev, PTR_ERR(info->clk),
"failed to get adc clock\n");
+ /*
+ * Use a default value for the converter clock.
+ * This may become user-configurable in the future.
+ */
+ ret = clk_set_rate(info->clk, info->data->clk_rate);
+ if (ret < 0)
+ return dev_err_probe(&pdev->dev, ret,
+ "failed to set adc clk rate\n");
platform_set_drvdata(pdev, indio_dev);
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index d0bd949..e05ce1f 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -5,7 +5,6 @@
* Copyright (c) Tomasz Duszynski <tduszyns@gmail.com>
*/
-#include <linux/unaligned.h>
#include <linux/completion.h>
#include <linux/device.h>
#include <linux/errno.h>
@@ -19,6 +18,8 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/serdev.h>
+#include <linux/types.h>
+#include <linux/unaligned.h>
#define PMS7003_DRIVER_NAME "pms7003"
@@ -76,7 +77,7 @@ struct pms7003_state {
/* Used to construct scan to push to the IIO buffer */
struct {
u16 data[3]; /* PM1, PM2P5, PM10 */
- s64 ts;
+ aligned_s64 ts;
} scan;
};
diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c
index 6f4f2ba..a788814 100644
--- a/drivers/iio/chemical/sps30.c
+++ b/drivers/iio/chemical/sps30.c
@@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p)
int ret;
struct {
s32 data[4]; /* PM1, PM2P5, PM4, PM10 */
- s64 ts;
+ aligned_s64 ts;
} scan;
mutex_lock(&state->lock);
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index ad1882f..2055a03 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -66,6 +66,10 @@ static struct {
{HID_USAGE_SENSOR_HUMIDITY, 0, 1000, 0},
{HID_USAGE_SENSOR_HINGE, 0, 0, 17453293},
{HID_USAGE_SENSOR_HINGE, HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293},
+
+ {HID_USAGE_SENSOR_HUMAN_PRESENCE, 0, 1, 0},
+ {HID_USAGE_SENSOR_HUMAN_PROXIMITY, 0, 1, 0},
+ {HID_USAGE_SENSOR_HUMAN_ATTENTION, 0, 1, 0},
};
static void simple_div(int dividend, int divisor, int *whole,
diff --git a/drivers/iio/imu/adis16550.c b/drivers/iio/imu/adis16550.c
index b14ea89..28f0dbd 100644
--- a/drivers/iio/imu/adis16550.c
+++ b/drivers/iio/imu/adis16550.c
@@ -836,7 +836,7 @@ static irqreturn_t adis16550_trigger_handler(int irq, void *p)
u16 dummy;
bool valid;
struct iio_poll_func *pf = p;
- __be32 data[ADIS16550_MAX_SCAN_DATA];
+ __be32 data[ADIS16550_MAX_SCAN_DATA] __aligned(8);
struct iio_dev *indio_dev = pf->indio_dev;
struct adis16550 *st = iio_priv(indio_dev);
struct adis *adis = iio_device_get_drvdata(indio_dev);
diff --git a/drivers/iio/imu/bmi270/bmi270_core.c b/drivers/iio/imu/bmi270/bmi270_core.c
index a86be5a..2e4469f 100644
--- a/drivers/iio/imu/bmi270/bmi270_core.c
+++ b/drivers/iio/imu/bmi270/bmi270_core.c
@@ -918,8 +918,7 @@ static int bmi270_configure_imu(struct bmi270_data *data)
FIELD_PREP(BMI270_ACC_CONF_ODR_MSK,
BMI270_ACC_CONF_ODR_100HZ) |
FIELD_PREP(BMI270_ACC_CONF_BWP_MSK,
- BMI270_ACC_CONF_BWP_NORMAL_MODE) |
- BMI270_PWR_CONF_ADV_PWR_SAVE_MSK);
+ BMI270_ACC_CONF_BWP_NORMAL_MODE));
if (ret)
return dev_err_probe(dev, ret, "Failed to configure accelerometer");
@@ -927,8 +926,7 @@ static int bmi270_configure_imu(struct bmi270_data *data)
FIELD_PREP(BMI270_GYR_CONF_ODR_MSK,
BMI270_GYR_CONF_ODR_200HZ) |
FIELD_PREP(BMI270_GYR_CONF_BWP_MSK,
- BMI270_GYR_CONF_BWP_NORMAL_MODE) |
- BMI270_PWR_CONF_ADV_PWR_SAVE_MSK);
+ BMI270_GYR_CONF_BWP_NORMAL_MODE));
if (ret)
return dev_err_probe(dev, ret, "Failed to configure gyroscope");
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 3d3b27f..273196e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
u16 fifo_count;
u32 fifo_period;
s64 timestamp;
- u8 data[INV_MPU6050_OUTPUT_DATA_SIZE];
+ u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8);
size_t i, nb;
mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 0a7cd8c..8a9d259 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK))
return 0;
+ if (!pattern_len)
+ pattern_len = ST_LSM6DSX_SAMPLE_SIZE;
+
fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) *
ST_LSM6DSX_CHAN_SIZE;
fifo_len = (fifo_len / pattern_len) * pattern_len;
@@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw)
if (!fifo_len)
return 0;
+ if (!pattern_len)
+ pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE;
+
for (read_len = 0; read_len < fifo_len; read_len += pattern_len) {
err = st_lsm6dsx_read_block(hw,
ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR,
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
index 4fdcc2a..96c6106 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
@@ -2719,8 +2719,11 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id,
}
if (device_property_read_bool(dev, "wakeup-source") ||
- (pdata && pdata->wakeup_source))
- device_init_wakeup(dev, true);
+ (pdata && pdata->wakeup_source)) {
+ err = devm_device_init_wakeup(dev);
+ if (err)
+ return dev_err_probe(dev, err, "Failed to init wakeup\n");
+ }
return 0;
}
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 76b76d1..4c65b32 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -34,9 +34,9 @@ struct prox_state {
struct iio_chan_spec channels[MAX_CHANNELS];
u32 channel2usage[MAX_CHANNELS];
u32 human_presence[MAX_CHANNELS];
- int scale_pre_decml;
- int scale_post_decml;
- int scale_precision;
+ int scale_pre_decml[MAX_CHANNELS];
+ int scale_post_decml[MAX_CHANNELS];
+ int scale_precision[MAX_CHANNELS];
unsigned long scan_mask[2]; /* One entry plus one terminator. */
int num_channels;
};
@@ -116,13 +116,15 @@ static int prox_read_raw(struct iio_dev *indio_dev,
ret_type = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SCALE:
- *val = prox_state->scale_pre_decml;
- *val2 = prox_state->scale_post_decml;
- ret_type = prox_state->scale_precision;
+ if (chan->scan_index >= prox_state->num_channels)
+ return -EINVAL;
+
+ *val = prox_state->scale_pre_decml[chan->scan_index];
+ *val2 = prox_state->scale_post_decml[chan->scan_index];
+ ret_type = prox_state->scale_precision[chan->scan_index];
break;
case IIO_CHAN_INFO_OFFSET:
- *val = hid_sensor_convert_exponent(
- prox_state->prox_attr[chan->scan_index].unit_expo);
+ *val = 0;
ret_type = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SAMP_FREQ:
@@ -249,6 +251,10 @@ static int prox_parse_report(struct platform_device *pdev,
st->prox_attr[index].size);
dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr[index].index,
st->prox_attr[index].report_id);
+ st->scale_precision[index] =
+ hid_sensor_format_scale(usage_id, &st->prox_attr[index],
+ &st->scale_pre_decml[index],
+ &st->scale_post_decml[index]);
index++;
}
diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c
index 65b2958..393a3d2 100644
--- a/drivers/iio/light/opt3001.c
+++ b/drivers/iio/light/opt3001.c
@@ -788,8 +788,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
int ret;
bool wake_result_ready_queue = false;
enum iio_chan_type chan_type = opt->chip_info->chan_type;
+ bool ok_to_ignore_lock = opt->ok_to_ignore_lock;
- if (!opt->ok_to_ignore_lock)
+ if (!ok_to_ignore_lock)
mutex_lock(&opt->lock);
ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION);
@@ -826,7 +827,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
}
out:
- if (!opt->ok_to_ignore_lock)
+ if (!ok_to_ignore_lock)
mutex_unlock(&opt->lock);
if (wake_result_ready_queue)
diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h
index 9d5c30a..d62a018 100644
--- a/drivers/iio/pressure/mprls0025pa.h
+++ b/drivers/iio/pressure/mprls0025pa.h
@@ -34,16 +34,6 @@ struct iio_dev;
struct mpr_data;
struct mpr_ops;
-/**
- * struct mpr_chan
- * @pres: pressure value
- * @ts: timestamp
- */
-struct mpr_chan {
- s32 pres;
- s64 ts;
-};
-
enum mpr_func_id {
MPR_FUNCTION_A,
MPR_FUNCTION_B,
@@ -69,6 +59,8 @@ enum mpr_func_id {
* reading in a loop until data is ready
* @completion: handshake from irq to read
* @chan: channel values for buffered mode
+ * @chan.pres: pressure value
+ * @chan.ts: timestamp
* @buffer: raw conversion data
*/
struct mpr_data {
@@ -87,7 +79,10 @@ struct mpr_data {
struct gpio_desc *gpiod_reset;
int irq;
struct completion completion;
- struct mpr_chan chan;
+ struct {
+ s32 pres;
+ aligned_s64 ts;
+ } chan;
u8 buffer[MPR_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
};
diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index c28a7a6..555a61e 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = {
struct maxim_thermocouple_data {
struct spi_device *spi;
const struct maxim_thermocouple_chip *chip;
+ char tc_type;
u8 buffer[16] __aligned(IIO_DMA_MINALIGN);
- char tc_type;
};
static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index b4e3e4b..d426338 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1352,6 +1352,9 @@ static void ib_device_notify_register(struct ib_device *device)
down_read(&devices_rwsem);
+ /* Mark for userspace that device is ready */
+ kobject_uevent(&device->dev.kobj, KOBJ_ADD);
+
ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT);
if (ret)
goto out;
@@ -1468,10 +1471,9 @@ int ib_register_device(struct ib_device *device, const char *name,
return ret;
}
dev_set_uevent_suppress(&device->dev, false);
- /* Mark for userspace that device is ready */
- kobject_uevent(&device->dev.kobj, KOBJ_ADD);
ib_device_notify_register(device);
+
ib_device_put(device);
return 0;
diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index 1ee8969..7599e31 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -221,7 +221,7 @@ static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
break;
if (i < IRDMA_MIN_MSIX) {
- for (; i > 0; i--)
+ while (--i >= 0)
ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
kfree(rf->msix_entries);
@@ -255,6 +255,8 @@ static void irdma_remove(struct auxiliary_device *aux_dev)
ice_rdma_update_vsi_filter(pf, iwdev->vsi_num, false);
irdma_deinit_interrupts(iwdev->rf, pf);
+ kfree(iwdev->rf);
+
pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
}
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index eeb932e..1e8c928 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -4871,5 +4871,4 @@ void irdma_ib_dealloc_device(struct ib_device *ibdev)
irdma_rt_deinit_hw(iwdev);
irdma_ctrl_deinit_hw(iwdev->rf);
- kfree(iwdev->rf);
}
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index fec87c9..fffd144 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -56,11 +56,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata,
cq->queue->buf, cq->queue->buf_size, &cq->queue->ip);
- if (err) {
- vfree(cq->queue->buf);
- kfree(cq->queue);
+ if (err)
return err;
- }
cq->is_user = uresp;
diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c
index d73389a..7622638 100644
--- a/drivers/input/joystick/magellan.c
+++ b/drivers/input/joystick/magellan.c
@@ -48,7 +48,7 @@ struct magellan {
static int magellan_crunch_nibbles(unsigned char *data, int count)
{
- static unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?";
+ static const unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?";
do {
if (data[count] == nibbles[data[count] & 0xf])
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index c33e6f3..57a5ff3 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -77,12 +77,13 @@
* xbox d-pads should map to buttons, as is required for DDR pads
* but we map them to axes when possible to simplify things
*/
-#define MAP_DPAD_TO_BUTTONS (1 << 0)
-#define MAP_TRIGGERS_TO_BUTTONS (1 << 1)
-#define MAP_STICKS_TO_NULL (1 << 2)
-#define MAP_SELECT_BUTTON (1 << 3)
-#define MAP_PADDLES (1 << 4)
-#define MAP_PROFILE_BUTTON (1 << 5)
+#define MAP_DPAD_TO_BUTTONS BIT(0)
+#define MAP_TRIGGERS_TO_BUTTONS BIT(1)
+#define MAP_STICKS_TO_NULL BIT(2)
+#define MAP_SHARE_BUTTON BIT(3)
+#define MAP_PADDLES BIT(4)
+#define MAP_PROFILE_BUTTON BIT(5)
+#define MAP_SHARE_OFFSET BIT(6)
#define DANCEPAD_MAP_CONFIG (MAP_DPAD_TO_BUTTONS | \
MAP_TRIGGERS_TO_BUTTONS | MAP_STICKS_TO_NULL)
@@ -135,14 +136,14 @@ static const struct xpad_device {
{ 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wireless */
{ 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },
{ 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE },
- { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, /* v2 */
+ { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, /* v2 */
{ 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE },
{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
- { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
{ 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX },
{ 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 },
+ { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
{ 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX },
{ 0x045e, 0x0285, "Microsoft X-Box pad (Japan)", 0, XTYPE_XBOX },
{ 0x045e, 0x0287, "Microsoft Xbox Controller S", 0, XTYPE_XBOX },
@@ -159,7 +160,7 @@ static const struct xpad_device {
{ 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
{ 0x045e, 0x0b00, "Microsoft X-Box One Elite 2 pad", MAP_PADDLES, XTYPE_XBOXONE },
{ 0x045e, 0x0b0a, "Microsoft X-Box Adaptive Controller", MAP_PROFILE_BUTTON, XTYPE_XBOXONE },
- { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+ { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SHARE_BUTTON | MAP_SHARE_OFFSET, XTYPE_XBOXONE },
{ 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 },
{ 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 },
{ 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 },
@@ -205,13 +206,13 @@ static const struct xpad_device {
{ 0x0738, 0x9871, "Mad Catz Portable Drum", 0, XTYPE_XBOX360 },
{ 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 },
{ 0x0738, 0xb738, "Mad Catz MVC2TE Stick 2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
- { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 },
+ { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", 0, XTYPE_XBOX360 },
{ 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
{ 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
{ 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 },
{ 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 },
{ 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 },
- { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE },
+ { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE },
{ 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX },
{ 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX },
@@ -240,7 +241,7 @@ static const struct xpad_device {
{ 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
- { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", XTYPE_XBOXONE },
+ { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
{ 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
@@ -281,6 +282,7 @@ static const struct xpad_device {
{ 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
{ 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
+ { 0x0f0d, 0x01b2, "HORI Taiko No Tatsujin Drum Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX },
{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
@@ -353,6 +355,8 @@ static const struct xpad_device {
{ 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE },
{ 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE },
{ 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 },
+ { 0x20d6, 0x400b, "PowerA FUSION Pro 4 Wired Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
+ { 0x20d6, 0x890b, "PowerA MOGA XP-Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 },
{ 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 },
@@ -384,13 +388,16 @@ static const struct xpad_device {
{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
{ 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
+ { 0x2dc8, 0x200f, "8BitDo Ultimate 3-mode Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
+ { 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 },
{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
+ { 0x2e24, 0x0423, "Hyperkin DuchesS Xbox One pad", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
- { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+ { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
{ 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 },
{ 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 },
{ 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 },
@@ -714,8 +721,10 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init),
XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on),
+ XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_led_on),
XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on),
XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth),
+ XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_auth),
XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth),
XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init),
@@ -1027,7 +1036,7 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha
* The report format was gleaned from
* https://github.com/kylelemons/xbox/blob/master/xbox.go
*/
-static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data)
+static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data, u32 len)
{
struct input_dev *dev = xpad->dev;
bool do_sync = false;
@@ -1068,8 +1077,12 @@ static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char
/* menu/view buttons */
input_report_key(dev, BTN_START, data[4] & BIT(2));
input_report_key(dev, BTN_SELECT, data[4] & BIT(3));
- if (xpad->mapping & MAP_SELECT_BUTTON)
- input_report_key(dev, KEY_RECORD, data[22] & BIT(0));
+ if (xpad->mapping & MAP_SHARE_BUTTON) {
+ if (xpad->mapping & MAP_SHARE_OFFSET)
+ input_report_key(dev, KEY_RECORD, data[len - 26] & BIT(0));
+ else
+ input_report_key(dev, KEY_RECORD, data[len - 18] & BIT(0));
+ }
/* buttons A,B,X,Y */
input_report_key(dev, BTN_A, data[4] & BIT(4));
@@ -1217,7 +1230,7 @@ static void xpad_irq_in(struct urb *urb)
xpad360w_process_packet(xpad, 0, xpad->idata);
break;
case XTYPE_XBOXONE:
- xpadone_process_packet(xpad, 0, xpad->idata);
+ xpadone_process_packet(xpad, 0, xpad->idata, urb->actual_length);
break;
default:
xpad_process_packet(xpad, 0, xpad->idata);
@@ -1944,7 +1957,7 @@ static int xpad_init_input(struct usb_xpad *xpad)
xpad->xtype == XTYPE_XBOXONE) {
for (i = 0; xpad360_btn[i] >= 0; i++)
input_set_capability(input_dev, EV_KEY, xpad360_btn[i]);
- if (xpad->mapping & MAP_SELECT_BUTTON)
+ if (xpad->mapping & MAP_SHARE_BUTTON)
input_set_capability(input_dev, EV_KEY, KEY_RECORD);
} else {
for (i = 0; xpad_btn[i] >= 0; i++)
diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 5ad6be9..061d483 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys,
u32 value, mask;
int error;
- kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs;
- kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs;
+ kregs_home = ®s->keys_regs[MTK_PMIC_HOMEKEY_INDEX];
+ kregs_pwr = ®s->keys_regs[MTK_PMIC_PWRKEY_INDEX];
error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec",
&long_press_debounce);
diff --git a/drivers/input/misc/hisi_powerkey.c b/drivers/input/misc/hisi_powerkey.c
index d3c293a..d315017 100644
--- a/drivers/input/misc/hisi_powerkey.c
+++ b/drivers/input/misc/hisi_powerkey.c
@@ -30,7 +30,7 @@ static irqreturn_t hi65xx_power_press_isr(int irq, void *q)
{
struct input_dev *input = q;
- pm_wakeup_event(input->dev.parent, MAX_HELD_TIME);
+ pm_wakeup_dev_event(input->dev.parent, MAX_HELD_TIME, true);
input_report_key(input, KEY_POWER, 1);
input_sync(input);
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 8d7303f..1cfadd7 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -74,9 +74,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
return -1;
switch (code) {
- case SND_BELL: if (value) value = 1000;
- case SND_TONE: break;
- default: return -1;
+ case SND_BELL:
+ if (value)
+ value = 1000;
+ break;
+ case SND_TONE:
+ break;
+ default:
+ return -1;
}
if (value > 20 && value < 32767)
@@ -109,9 +114,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
return -1;
switch (code) {
- case SND_BELL: if (value) value = 1000;
- case SND_TONE: break;
- default: return -1;
+ case SND_BELL:
+ if (value)
+ value = 1000;
+ break;
+ case SND_TONE:
+ break;
+ default:
+ return -1;
}
if (value > 20 && value < 32767)
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 309c360..c5c88a7 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -164,6 +164,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
#ifdef CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS
static const char * const smbus_pnp_ids[] = {
/* all of the topbuttonpad_pnp_ids are valid, we just add some extras */
+ "DLL060d", /* Dell Precision M3800 */
"LEN0048", /* X1 Carbon 3 */
"LEN0046", /* X250 */
"LEN0049", /* Yoga 11e */
@@ -190,11 +191,15 @@ static const char * const smbus_pnp_ids[] = {
"LEN2054", /* E480 */
"LEN2055", /* E580 */
"LEN2068", /* T14 Gen 1 */
+ "SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */
+ "SYN3003", /* HP EliteBook 850 G1 */
"SYN3015", /* HP EliteBook 840 G2 */
"SYN3052", /* HP EliteBook 840 G4 */
"SYN3221", /* HP 15-ay000 */
"SYN323d", /* HP Spectre X360 13-w013dx */
"SYN3257", /* HP Envy 13-ad105ng */
+ "TOS01f6", /* Dynabook Portege X30L-G */
+ "TOS0213", /* Dynabook Portege X30-D */
NULL
};
#endif
diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c
index eafe5a9..071b7c9 100644
--- a/drivers/input/touchscreen/cyttsp5.c
+++ b/drivers/input/touchscreen/cyttsp5.c
@@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on)
int rc;
SET_CMD_REPORT_TYPE(cmd[0], 0);
- SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP);
+ SET_CMD_REPORT_ID(cmd[0], state);
SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER);
rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd));
@@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq,
ts->input->phys = ts->phys;
input_set_drvdata(ts->input, ts);
- /* Reset the gpio to be in a reset state */
+ /* Assert gpio to be in a reset state */
ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(ts->reset_gpio)) {
error = PTR_ERR(ts->reset_gpio);
dev_err(dev, "Failed to request reset gpio, error %d\n", error);
return error;
}
+
+ fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */
+
gpiod_set_value_cansleep(ts->reset_gpio, 0);
/* Need a delay to have device up */
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index a94a199..af0fb38 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -366,12 +366,7 @@ static struct platform_driver stmpe_ts_driver = {
};
module_platform_driver(stmpe_ts_driver);
-static const struct of_device_id stmpe_ts_ids[] = {
- { .compatible = "st,stmpe-ts", },
- { },
-};
-MODULE_DEVICE_TABLE(of, stmpe_ts_ids);
-
+MODULE_ALIAS("platform:stmpe-ts");
MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>");
MODULE_DESCRIPTION("STMPEXXX touchscreen driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index dd9e26b..14aa0d7 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -3664,6 +3664,14 @@ static int __init parse_ivrs_acpihid(char *str)
while (*uid == '0' && *(uid + 1))
uid++;
+ if (strlen(hid) >= ACPIHID_HID_LEN) {
+ pr_err("Invalid command line: hid is too long\n");
+ return 1;
+ } else if (strlen(uid) >= ACPIHID_UID_LEN) {
+ pr_err("Invalid command line: uid is too long\n");
+ return 1;
+ }
+
i = early_acpihid_map_size++;
memcpy(early_acpihid_map[i].hid, hid, strlen(hid));
memcpy(early_acpihid_map[i].uid, uid, strlen(uid));
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index be8761b..f34209b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3869,6 +3869,9 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
struct iommu_dev_data *dev_data;
+ if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+ return -EINVAL;
+
if (ir_data->iommu == NULL)
return -EINVAL;
@@ -3879,21 +3882,11 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
* we should not modify the IRTE
*/
if (!dev_data || !dev_data->use_vapic)
- return 0;
+ return -EINVAL;
ir_data->cfg = irqd_cfg(data);
pi_data->ir_data = ir_data;
- /* Note:
- * SVM tries to set up for VAPIC mode, but we are in
- * legacy mode. So, we force legacy mode instead.
- */
- if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
- pr_debug("%s: Fall back to using intr legacy remap\n",
- __func__);
- pi_data->is_guest_mode = false;
- }
-
pi_data->prev_ga_tag = ir_data->cached_ga_tag;
if (pi_data->is_guest_mode) {
ir_data->ga_root_ptr = (pi_data->base >> 12);
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 9ba5964..980cc6b 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -411,6 +411,12 @@ struct iommu_domain *arm_smmu_sva_domain_alloc(struct device *dev,
return ERR_CAST(smmu_domain);
smmu_domain->domain.type = IOMMU_DOMAIN_SVA;
smmu_domain->domain.ops = &arm_smmu_sva_domain_ops;
+
+ /*
+ * Choose page_size as the leaf page size for invalidation when
+ * ARM_SMMU_FEAT_RANGE_INV is present
+ */
+ smmu_domain->domain.pgsize_bitmap = PAGE_SIZE;
smmu_domain->smmu = smmu;
ret = xa_alloc(&arm_smmu_asid_xa, &asid, smmu_domain,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index b4c21aa..48d9103 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3388,6 +3388,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
mutex_lock(&smmu->streams_mutex);
for (i = 0; i < fwspec->num_ids; i++) {
struct arm_smmu_stream *new_stream = &master->streams[i];
+ struct rb_node *existing;
u32 sid = fwspec->ids[i];
new_stream->id = sid;
@@ -3398,11 +3399,21 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
break;
/* Insert into SID tree */
- if (rb_find_add(&new_stream->node, &smmu->streams,
- arm_smmu_streams_cmp_node)) {
- dev_warn(master->dev, "stream %u already in tree\n",
- sid);
- ret = -EINVAL;
+ existing = rb_find_add(&new_stream->node, &smmu->streams,
+ arm_smmu_streams_cmp_node);
+ if (existing) {
+ struct arm_smmu_master *existing_master =
+ rb_entry(existing, struct arm_smmu_stream, node)
+ ->master;
+
+ /* Bridged PCI devices may end up with duplicated IDs */
+ if (existing_master == master)
+ continue;
+
+ dev_warn(master->dev,
+ "Aliasing StreamID 0x%x (from %s) unsupported, expect DMA to be broken\n",
+ sid, dev_name(existing_master->dev));
+ ret = -ENODEV;
break;
}
}
@@ -4429,6 +4440,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3);
if (FIELD_GET(IDR3_RIL, reg))
smmu->features |= ARM_SMMU_FEAT_RANGE_INV;
+ if (FIELD_GET(IDR3_FWB, reg))
+ smmu->features |= ARM_SMMU_FEAT_S2FWB;
/* IDR5 */
reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index b29da2d..cb0b993 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3785,20 +3785,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
intel_iommu_debugfs_create_dev(info);
- /*
- * The PCIe spec, in its wisdom, declares that the behaviour of the
- * device is undefined if you enable PASID support after ATS support.
- * So always enable PASID support on devices which have it, even if
- * we can't yet know if we're ever going to use it.
- */
- if (info->pasid_supported &&
- !pci_enable_pasid(pdev, info->pasid_supported & ~1))
- info->pasid_enabled = 1;
-
- if (sm_supported(iommu))
- iommu_enable_pci_ats(info);
- iommu_enable_pci_pri(info);
-
return &iommu->iommu;
free_table:
intel_pasid_free_table(dev);
@@ -3810,6 +3796,26 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
return ERR_PTR(ret);
}
+static void intel_iommu_probe_finalize(struct device *dev)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+
+ /*
+ * The PCIe spec, in its wisdom, declares that the behaviour of the
+ * device is undefined if you enable PASID support after ATS support.
+ * So always enable PASID support on devices which have it, even if
+ * we can't yet know if we're ever going to use it.
+ */
+ if (info->pasid_supported &&
+ !pci_enable_pasid(to_pci_dev(dev), info->pasid_supported & ~1))
+ info->pasid_enabled = 1;
+
+ if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev))
+ iommu_enable_pci_ats(info);
+ iommu_enable_pci_pri(info);
+}
+
static void intel_iommu_release_device(struct device *dev)
{
struct device_domain_info *info = dev_iommu_priv_get(dev);
@@ -4391,6 +4397,7 @@ const struct iommu_ops intel_iommu_ops = {
.domain_alloc_sva = intel_svm_domain_alloc,
.domain_alloc_nested = intel_iommu_domain_alloc_nested,
.probe_device = intel_iommu_probe_device,
+ .probe_finalize = intel_iommu_probe_finalize,
.release_device = intel_iommu_release_device,
.get_resv_regions = intel_iommu_get_resv_regions,
.device_group = intel_iommu_device_group,
@@ -4432,6 +4439,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
+/* QM57/QS57 integrated gfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_iommu_igfx);
+
/* Broadwell igfx malfunctions with dmar */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
@@ -4509,7 +4519,6 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
}
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index c698948..cc6a6c1 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -252,7 +252,7 @@ static void __init gicv2m_teardown(void)
static struct msi_parent_ops gicv2m_msi_parent_ops = {
.supported_flags = GICV2M_MSI_FLAGS_SUPPORTED,
.required_flags = GICV2M_MSI_FLAGS_REQUIRED,
- .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+ .chip_flags = MSI_CHIP_FLAG_SET_EOI,
.bus_select_token = DOMAIN_BUS_NEXUS,
.bus_select_mask = MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
.prefix = "GICv2m-",
@@ -421,7 +421,7 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
#ifdef CONFIG_ACPI
static int acpi_num_msi;
-static __init struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
+static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
{
struct v2m_data *data;
diff --git a/drivers/irqchip/irq-gic-v3-its-msi-parent.c b/drivers/irqchip/irq-gic-v3-its-msi-parent.c
index bdb04c8..c5a7eb1 100644
--- a/drivers/irqchip/irq-gic-v3-its-msi-parent.c
+++ b/drivers/irqchip/irq-gic-v3-its-msi-parent.c
@@ -203,7 +203,7 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
const struct msi_parent_ops gic_v3_its_msi_parent_ops = {
.supported_flags = ITS_MSI_FLAGS_SUPPORTED,
.required_flags = ITS_MSI_FLAGS_REQUIRED,
- .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+ .chip_flags = MSI_CHIP_FLAG_SET_EOI,
.bus_select_token = DOMAIN_BUS_NEXUS,
.bus_select_mask = MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
.prefix = "ITS-",
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
index 34e9ca7..647b18e 100644
--- a/drivers/irqchip/irq-gic-v3-mbi.c
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -197,7 +197,7 @@ static bool mbi_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
static const struct msi_parent_ops gic_v3_mbi_msi_parent_ops = {
.supported_flags = MBI_MSI_FLAGS_SUPPORTED,
.required_flags = MBI_MSI_FLAGS_REQUIRED,
- .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+ .chip_flags = MSI_CHIP_FLAG_SET_EOI,
.bus_select_token = DOMAIN_BUS_NEXUS,
.bus_select_mask = MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
.prefix = "MBI-",
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index d67f93f..60b9762 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -161,7 +161,7 @@ static const struct irq_domain_ops gicp_domain_ops = {
static const struct msi_parent_ops gicp_msi_parent_ops = {
.supported_flags = GICP_MSI_FLAGS_SUPPORTED,
.required_flags = GICP_MSI_FLAGS_REQUIRED,
- .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+ .chip_flags = MSI_CHIP_FLAG_SET_EOI,
.bus_select_token = DOMAIN_BUS_GENERIC_MSI,
.bus_select_mask = MATCH_PLATFORM_MSI,
.prefix = "GICP-",
diff --git a/drivers/irqchip/irq-mvebu-odmi.c b/drivers/irqchip/irq-mvebu-odmi.c
index 28f7e81..54f6f08 100644
--- a/drivers/irqchip/irq-mvebu-odmi.c
+++ b/drivers/irqchip/irq-mvebu-odmi.c
@@ -157,7 +157,7 @@ static const struct irq_domain_ops odmi_domain_ops = {
static const struct msi_parent_ops odmi_msi_parent_ops = {
.supported_flags = ODMI_MSI_FLAGS_SUPPORTED,
.required_flags = ODMI_MSI_FLAGS_REQUIRED,
- .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK,
+ .chip_flags = MSI_CHIP_FLAG_SET_EOI,
.bus_select_token = DOMAIN_BUS_GENERIC_MSI,
.bus_select_mask = MATCH_PLATFORM_MSI,
.prefix = "ODMI-",
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index 7942d8e..f772deb 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -227,6 +227,9 @@ static int qcom_mpm_alloc(struct irq_domain *domain, unsigned int virq,
if (ret)
return ret;
+ if (pin == GPIO_NO_WAKE_IRQ)
+ return irq_domain_disconnect_hierarchy(domain, virq);
+
ret = irq_domain_set_hwirq_and_chip(domain, virq, pin,
&qcom_mpm_chip, priv);
if (ret)
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index bdf5cd2..62f7695 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -208,17 +208,17 @@ static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
}
#ifdef CONFIG_SMP
-static void __imsic_local_timer_start(struct imsic_local_priv *lpriv)
+static void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu)
{
lockdep_assert_held(&lpriv->lock);
if (!timer_pending(&lpriv->timer)) {
lpriv->timer.expires = jiffies + 1;
- add_timer_on(&lpriv->timer, smp_processor_id());
+ add_timer_on(&lpriv->timer, cpu);
}
}
#else
-static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv)
+static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu)
{
}
#endif
@@ -233,7 +233,7 @@ void imsic_local_sync_all(bool force_all)
if (force_all)
bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
if (!__imsic_local_sync(lpriv))
- __imsic_local_timer_start(lpriv);
+ __imsic_local_timer_start(lpriv, smp_processor_id());
raw_spin_unlock_irqrestore(&lpriv->lock, flags);
}
@@ -278,7 +278,7 @@ static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu
return;
}
- __imsic_local_timer_start(lpriv);
+ __imsic_local_timer_start(lpriv, cpu);
}
}
#else
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index 02a680c..bf0d7d5 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -96,7 +96,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus,
ret = mcb_device_register(bus, mdev);
if (ret < 0)
- goto err;
+ return ret;
return 0;
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c8ed65..f0b5a69 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -68,6 +68,8 @@
#define LIST_DIRTY 1
#define LIST_SIZE 2
+#define SCAN_RESCHED_CYCLE 16
+
/*--------------------------------------------------------------*/
/*
@@ -2424,7 +2426,12 @@ static void __scan(struct dm_bufio_client *c)
atomic_long_dec(&c->need_shrink);
freed++;
- cond_resched();
+
+ if (unlikely(freed % SCAN_RESCHED_CYCLE == 0)) {
+ dm_bufio_unlock(c);
+ cond_resched();
+ dm_bufio_lock(c);
+ }
}
}
}
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 2a283fe..cc3d389 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -5164,7 +5164,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
BUG_ON(!list_empty(&ic->wait_list));
- if (ic->mode == 'B')
+ if (ic->mode == 'B' && ic->bitmap_flush_work.work.func)
cancel_delayed_work_sync(&ic->bitmap_flush_work);
if (ic->metadata_wq)
destroy_workqueue(ic->metadata_wq);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 35100a4..6b23e77 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -523,8 +523,9 @@ static char **realloc_argv(unsigned int *size, char **old_argv)
gfp = GFP_NOIO;
}
argv = kmalloc_array(new_size, sizeof(*argv), gfp);
- if (argv && old_argv) {
- memcpy(argv, old_argv, *size * sizeof(*argv));
+ if (argv) {
+ if (old_argv)
+ memcpy(argv, old_argv, *size * sizeof(*argv));
*size = new_size;
}
@@ -1049,7 +1050,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
unsigned int min_pool_size = 0, pool_size;
struct dm_md_mempools *pools;
unsigned int bioset_flags = 0;
- bool mempool_needs_integrity = t->integrity_supported;
if (unlikely(type == DM_TYPE_NONE)) {
DMERR("no table type is set, can't allocate mempools");
@@ -1074,8 +1074,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
per_io_data_size = max(per_io_data_size, ti->per_io_data_size);
min_pool_size = max(min_pool_size, ti->num_flush_bios);
-
- mempool_needs_integrity |= ti->mempool_needs_integrity;
}
pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
front_pad = roundup(per_io_data_size,
@@ -1175,7 +1173,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile,
t = dm_get_live_table(md, &srcu_idx);
if (!t)
- return 0;
+ goto put_live_table;
for (unsigned int i = 0; i < t->num_targets; i++) {
struct dm_target *ti = dm_table_get_target(t, i);
@@ -1186,6 +1184,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile,
(void *)key);
}
+put_live_table:
dm_put_live_table(md, srcu_idx);
return 0;
}
diff --git a/drivers/media/cec/i2c/Kconfig b/drivers/media/cec/i2c/Kconfig
index b9d2164..c31abc2 100644
--- a/drivers/media/cec/i2c/Kconfig
+++ b/drivers/media/cec/i2c/Kconfig
@@ -16,6 +16,7 @@
config CEC_NXP_TDA9950
tristate "NXP Semiconductors TDA9950/TDA998X HDMI CEC"
+ depends on I2C
select CEC_NOTIFIER
select CEC_CORE
default DRM_I2C_NXP_TDA998X
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index e576b21..e45ba12 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -1149,8 +1149,11 @@
config VIDEO_LT6911UXE
tristate "Lontium LT6911UXE decoder"
- depends on ACPI && VIDEO_DEV
+ depends on ACPI && VIDEO_DEV && I2C
select V4L2_FWNODE
+ select V4L2_CCI_I2C
+ select MEDIA_CONTROLLER
+ select VIDEO_V4L2_SUBDEV_API
help
This is a Video4Linux2 sensor-level driver for the Lontium
LT6911UXE HDMI to MIPI CSI-2 bridge.
diff --git a/drivers/media/platform/synopsys/hdmirx/Kconfig b/drivers/media/platform/synopsys/hdmirx/Kconfig
index 27e6706..4321f98 100644
--- a/drivers/media/platform/synopsys/hdmirx/Kconfig
+++ b/drivers/media/platform/synopsys/hdmirx/Kconfig
@@ -2,6 +2,7 @@
config VIDEO_SYNOPSYS_HDMIRX
tristate "Synopsys DesignWare HDMI Receiver driver"
+ depends on ARCH_ROCKCHIP || COMPILE_TEST
depends on VIDEO_DEV
select MEDIA_CONTROLLER
select VIDEO_V4L2_SUBDEV_API
diff --git a/drivers/media/test-drivers/vivid/Kconfig b/drivers/media/test-drivers/vivid/Kconfig
index e95edc0..cc47007 100644
--- a/drivers/media/test-drivers/vivid/Kconfig
+++ b/drivers/media/test-drivers/vivid/Kconfig
@@ -32,7 +32,8 @@
config VIDEO_VIVID_OSD
bool "Enable Framebuffer for testing Output Overlay"
- depends on VIDEO_VIVID && FB
+ depends on VIDEO_VIVID && FB_CORE
+ depends on VIDEO_VIVID=m || FB_CORE=y
default y
select FB_IOMEM_HELPERS
help
diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
index 0475630..98d3d12 100644
--- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
+++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
@@ -37,6 +37,7 @@
struct pci1xxxx_gpio {
struct auxiliary_device *aux_dev;
void __iomem *reg_base;
+ raw_spinlock_t wa_lock;
struct gpio_chip gpio;
spinlock_t lock;
int irq_base;
@@ -167,7 +168,7 @@ static void pci1xxxx_gpio_irq_ack(struct irq_data *data)
unsigned long flags;
spin_lock_irqsave(&priv->lock, flags);
- pci1xxx_assign_bit(priv->reg_base, INTR_STAT_OFFSET(gpio), (gpio % 32), true);
+ writel(BIT(gpio % 32), priv->reg_base + INTR_STAT_OFFSET(gpio));
spin_unlock_irqrestore(&priv->lock, flags);
}
@@ -257,6 +258,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
struct pci1xxxx_gpio *priv = dev_id;
struct gpio_chip *gc = &priv->gpio;
unsigned long int_status = 0;
+ unsigned long wa_flags;
unsigned long flags;
u8 pincount;
int bit;
@@ -280,7 +282,9 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank));
spin_unlock_irqrestore(&priv->lock, flags);
irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32)));
- handle_nested_irq(irq);
+ raw_spin_lock_irqsave(&priv->wa_lock, wa_flags);
+ generic_handle_irq(irq);
+ raw_spin_unlock_irqrestore(&priv->wa_lock, wa_flags);
}
}
spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index a5f88ec..bc40b94 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -117,6 +117,7 @@
#define MEI_DEV_ID_LNL_M 0xA870 /* Lunar Lake Point M */
+#define MEI_DEV_ID_PTL_H 0xE370 /* Panther Lake H */
#define MEI_DEV_ID_PTL_P 0xE470 /* Panther Lake P */
/*
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index d6ff9d8..3f9c60b 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -124,6 +124,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_PTL_H, MEI_ME_PCH15_CFG)},
{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
/* required last entry */
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 7be1649..da26a08 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -36,20 +36,24 @@
#define VSC_TP_XFER_TIMEOUT_BYTES 700
#define VSC_TP_PACKET_PADDING_SIZE 1
#define VSC_TP_PACKET_SIZE(pkt) \
- (sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+ (sizeof(struct vsc_tp_packet_hdr) + le16_to_cpu((pkt)->hdr.len) + VSC_TP_CRC_SIZE)
#define VSC_TP_MAX_PACKET_SIZE \
- (sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+ (sizeof(struct vsc_tp_packet_hdr) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
#define VSC_TP_MAX_XFER_SIZE \
(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
#define VSC_TP_NEXT_XFER_LEN(len, offset) \
- (len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+ (len + sizeof(struct vsc_tp_packet_hdr) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
-struct vsc_tp_packet {
+struct vsc_tp_packet_hdr {
__u8 sync;
__u8 cmd;
__le16 len;
__le32 seq;
- __u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp_packet {
+ struct vsc_tp_packet_hdr hdr;
+ __u8 buf[VSC_TP_MAX_XFER_SIZE - sizeof(struct vsc_tp_packet_hdr)];
};
struct vsc_tp {
@@ -67,8 +71,8 @@ struct vsc_tp {
u32 seq;
/* command buffer */
- void *tx_buf;
- void *rx_buf;
+ struct vsc_tp_packet *tx_buf;
+ struct vsc_tp_packet *rx_buf;
atomic_t assert_cnt;
wait_queue_head_t xfer_wait;
@@ -158,12 +162,12 @@ static int vsc_tp_dev_xfer(struct vsc_tp *tp, void *obuf, void *ibuf, size_t len
static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
void *ibuf, u16 ilen)
{
- int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+ int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet_hdr);
int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
- u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+ u8 *src, *crc_src, *rx_buf = (u8 *)tp->rx_buf;
int count_down = VSC_TP_MAX_XFER_COUNT;
u32 recv_crc = 0, crc = ~0;
- struct vsc_tp_packet ack;
+ struct vsc_tp_packet_hdr ack;
u8 *dst = (u8 *)&ack;
bool synced = false;
@@ -280,10 +284,10 @@ int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
guard(mutex)(&tp->mutex);
- pkt->sync = VSC_TP_PACKET_SYNC;
- pkt->cmd = cmd;
- pkt->len = cpu_to_le16(olen);
- pkt->seq = cpu_to_le32(++tp->seq);
+ pkt->hdr.sync = VSC_TP_PACKET_SYNC;
+ pkt->hdr.cmd = cmd;
+ pkt->hdr.len = cpu_to_le16(olen);
+ pkt->hdr.seq = cpu_to_le32(++tp->seq);
memcpy(pkt->buf, obuf, olen);
crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
@@ -320,7 +324,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
guard(mutex)(&tp->mutex);
/* rom xfer is big endian */
- cpu_to_be32_array(tp->tx_buf, obuf, words);
+ cpu_to_be32_array((u32 *)tp->tx_buf, obuf, words);
ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
@@ -336,7 +340,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
return ret;
if (ibuf)
- be32_to_cpu_array(ibuf, tp->rx_buf, words);
+ be32_to_cpu_array(ibuf, (u32 *)tp->rx_buf, words);
return ret;
}
@@ -490,11 +494,11 @@ static int vsc_tp_probe(struct spi_device *spi)
if (!tp)
return -ENOMEM;
- tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+ tp->tx_buf = devm_kzalloc(dev, sizeof(*tp->tx_buf), GFP_KERNEL);
if (!tp->tx_buf)
return -ENOMEM;
- tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+ tp->rx_buf = devm_kzalloc(dev, sizeof(*tp->rx_buf), GFP_KERNEL);
if (!tp->rx_buf)
return -ENOMEM;
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index d294850..c4e5e2c 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -122,7 +122,6 @@ struct pci_endpoint_test {
struct pci_endpoint_test_data {
enum pci_barno test_reg_bar;
size_t alignment;
- int irq_type;
};
static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test,
@@ -948,7 +947,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
test_reg_bar = data->test_reg_bar;
test->test_reg_bar = test_reg_bar;
test->alignment = data->alignment;
- test->irq_type = data->irq_type;
}
init_completion(&test->irq_raised);
@@ -970,10 +968,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
pci_set_master(pdev);
- ret = pci_endpoint_test_alloc_irq_vectors(test, test->irq_type);
- if (ret)
- goto err_disable_irq;
-
for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
base = pci_ioremap_bar(pdev, bar);
@@ -1009,10 +1003,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
goto err_ida_remove;
}
- ret = pci_endpoint_test_request_irq(test);
- if (ret)
- goto err_kfree_test_name;
-
pci_endpoint_test_get_capabilities(test);
misc_device = &test->miscdev;
@@ -1020,7 +1010,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
misc_device->name = kstrdup(name, GFP_KERNEL);
if (!misc_device->name) {
ret = -ENOMEM;
- goto err_release_irq;
+ goto err_kfree_test_name;
}
misc_device->parent = &pdev->dev;
misc_device->fops = &pci_endpoint_test_fops;
@@ -1036,9 +1026,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
err_kfree_name:
kfree(misc_device->name);
-err_release_irq:
- pci_endpoint_test_release_irq(test);
-
err_kfree_test_name:
kfree(test->name);
@@ -1051,8 +1038,6 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
pci_iounmap(pdev, test->bar[bar]);
}
-err_disable_irq:
- pci_endpoint_test_free_irq_vectors(test);
pci_release_regions(pdev);
err_disable_pdev:
@@ -1092,23 +1077,19 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
static const struct pci_endpoint_test_data default_data = {
.test_reg_bar = BAR_0,
.alignment = SZ_4K,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
static const struct pci_endpoint_test_data am654_data = {
.test_reg_bar = BAR_2,
.alignment = SZ_64K,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
static const struct pci_endpoint_test_data j721e_data = {
.alignment = 256,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
static const struct pci_endpoint_test_data rk3588_data = {
.alignment = SZ_64K,
- .irq_type = PCITEST_IRQ_TYPE_MSI,
};
/*
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 6824131..264e11f 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -691,8 +691,8 @@
config MMC_SDHI
tristate "Renesas SDHI SD/SDIO controller support"
depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
+ depends on (RESET_CONTROLLER && REGULATOR) || !OF
select MMC_TMIO_CORE
- select RESET_CONTROLLER if ARCH_RENESAS
help
This provides support for the SDHI SD/SDIO controller found in
Renesas SuperH, ARM and ARM64 based SoCs
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index fa6526b..8c83e20 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -1179,7 +1179,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
if (IS_ERR(rdev)) {
dev_err(dev, "regulator register failed err=%ld", PTR_ERR(rdev));
ret = PTR_ERR(rdev);
- goto efree;
+ goto edisclk;
}
priv->rdev = rdev;
}
@@ -1243,26 +1243,26 @@ int renesas_sdhi_probe(struct platform_device *pdev,
num_irqs = platform_irq_count(pdev);
if (num_irqs < 0) {
ret = num_irqs;
- goto eirq;
+ goto edisclk;
}
/* There must be at least one IRQ source */
if (!num_irqs) {
ret = -ENXIO;
- goto eirq;
+ goto edisclk;
}
for (i = 0; i < num_irqs; i++) {
irq = platform_get_irq(pdev, i);
if (irq < 0) {
ret = irq;
- goto eirq;
+ goto edisclk;
}
ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
dev_name(&pdev->dev), host);
if (ret)
- goto eirq;
+ goto edisclk;
}
ret = tmio_mmc_host_probe(host);
@@ -1274,8 +1274,6 @@ int renesas_sdhi_probe(struct platform_device *pdev,
return ret;
-eirq:
- tmio_mmc_host_remove(host);
edisclk:
renesas_sdhi_clk_disable(host);
efree:
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index 09b9ab1..a20d03f 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -17,6 +17,7 @@
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
#include <linux/pm_runtime.h>
#include <linux/reset.h>
#include <linux/sizes.h>
@@ -745,6 +746,29 @@ static void dwcmshc_rk35xx_postinit(struct sdhci_host *host, struct dwcmshc_priv
}
}
+static void dwcmshc_rk3576_postinit(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv)
+{
+ struct device *dev = mmc_dev(host->mmc);
+ int ret;
+
+ /*
+ * This works around the design of the RK3576's power domains, which
+ * makes the PD_NVM power domain, which the sdhci controller on the
+ * RK3576 is in, never come back the same way once it's run-time
+ * suspended once. This can happen during early kernel boot if no driver
+ * is using either PD_NVM or its child power domain PD_SDGMAC for a
+ * short moment, leading to it being turned off to save power. By
+ * keeping it on, sdhci suspending won't lead to PD_NVM becoming a
+ * candidate for getting turned off.
+ */
+ ret = dev_pm_genpd_rpm_always_on(dev, true);
+ if (ret && ret != -EOPNOTSUPP)
+ dev_warn(dev, "failed to set PD rpm always on, SoC may hang later: %pe\n",
+ ERR_PTR(ret));
+
+ dwcmshc_rk35xx_postinit(host, dwc_priv);
+}
+
static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode)
{
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -1176,6 +1200,18 @@ static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk35xx_pdata = {
.postinit = dwcmshc_rk35xx_postinit,
};
+static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk3576_pdata = {
+ .pdata = {
+ .ops = &sdhci_dwcmshc_rk35xx_ops,
+ .quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
+ SDHCI_QUIRK_BROKEN_TIMEOUT_VAL,
+ .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+ SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
+ },
+ .init = dwcmshc_rk35xx_init,
+ .postinit = dwcmshc_rk3576_postinit,
+};
+
static const struct dwcmshc_pltfm_data sdhci_dwcmshc_th1520_pdata = {
.pdata = {
.ops = &sdhci_dwcmshc_th1520_ops,
@@ -1275,6 +1311,10 @@ static const struct of_device_id sdhci_dwcmshc_dt_ids[] = {
.data = &sdhci_dwcmshc_rk35xx_pdata,
},
{
+ .compatible = "rockchip,rk3576-dwcmshc",
+ .data = &sdhci_dwcmshc_rk3576_pdata,
+ },
+ {
.compatible = "rockchip,rk3568-dwcmshc",
.data = &sdhci_dwcmshc_rk35xx_pdata,
},
diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index f75c318..73385ff 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -155,6 +155,7 @@ struct sdhci_am654_data {
u32 tuning_loop;
#define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0)
+#define SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA BIT(1)
};
struct window {
@@ -166,6 +167,7 @@ struct window {
struct sdhci_am654_driver_data {
const struct sdhci_pltfm_data *pdata;
u32 flags;
+ u32 quirks;
#define IOMUX_PRESENT (1 << 0)
#define FREQSEL_2_BIT (1 << 1)
#define STRBSEL_4_BIT (1 << 2)
@@ -356,6 +358,29 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host,
sdhci_set_clock(host, clock);
}
+static int sdhci_am654_start_signal_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+ struct sdhci_host *host = mmc_priv(mmc);
+ struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+ struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host);
+ int ret;
+
+ if ((sdhci_am654->quirks & SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA) &&
+ ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) {
+ if (!IS_ERR(mmc->supply.vqmmc)) {
+ ret = mmc_regulator_set_vqmmc(mmc, ios);
+ if (ret < 0) {
+ pr_err("%s: Switching to 1.8V signalling voltage failed,\n",
+ mmc_hostname(mmc));
+ return -EIO;
+ }
+ }
+ return 0;
+ }
+
+ return sdhci_start_signal_voltage_switch(mmc, ios);
+}
+
static u8 sdhci_am654_write_power_on(struct sdhci_host *host, u8 val, int reg)
{
writeb(val, host->ioaddr + reg);
@@ -650,6 +675,12 @@ static const struct sdhci_am654_driver_data sdhci_j721e_4bit_drvdata = {
.flags = IOMUX_PRESENT,
};
+static const struct sdhci_am654_driver_data sdhci_am62_4bit_drvdata = {
+ .pdata = &sdhci_j721e_4bit_pdata,
+ .flags = IOMUX_PRESENT,
+ .quirks = SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA,
+};
+
static const struct soc_device_attribute sdhci_am654_devices[] = {
{ .family = "AM65X",
.revision = "SR1.0",
@@ -872,7 +903,7 @@ static const struct of_device_id sdhci_am654_of_match[] = {
},
{
.compatible = "ti,am62-sdhci",
- .data = &sdhci_j721e_4bit_drvdata,
+ .data = &sdhci_am62_4bit_drvdata,
},
{ /* sentinel */ }
};
@@ -906,6 +937,7 @@ static int sdhci_am654_probe(struct platform_device *pdev)
pltfm_host = sdhci_priv(host);
sdhci_am654 = sdhci_pltfm_priv(pltfm_host);
sdhci_am654->flags = drvdata->flags;
+ sdhci_am654->quirks = drvdata->quirks;
clk_xin = devm_clk_get(dev, "clk_xin");
if (IS_ERR(clk_xin)) {
@@ -940,6 +972,7 @@ static int sdhci_am654_probe(struct platform_device *pdev)
goto err_pltfm_free;
}
+ host->mmc_host_ops.start_signal_voltage_switch = sdhci_am654_start_signal_voltage_switch;
host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning;
pm_runtime_get_noresume(dev);
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index cf0d518..f692136 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -16,6 +16,7 @@
#include <linux/netdevice.h>
#include <linux/pci.h>
#include <linux/timer.h>
+#include <net/netdev_queues.h>
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
@@ -410,10 +411,13 @@ struct kvaser_pciefd_can {
void __iomem *reg_base;
struct can_berr_counter bec;
u8 cmd_seq;
+ u8 tx_max_count;
+ u8 tx_idx;
+ u8 ack_idx;
int err_rep_cnt;
- int echo_idx;
+ unsigned int completed_tx_pkts;
+ unsigned int completed_tx_bytes;
spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */
- spinlock_t echo_lock; /* Locks the message echo buffer */
struct timer_list bec_poll_timer;
struct completion start_comp, flush_comp;
};
@@ -714,6 +718,9 @@ static int kvaser_pciefd_open(struct net_device *netdev)
int ret;
struct kvaser_pciefd_can *can = netdev_priv(netdev);
+ can->tx_idx = 0;
+ can->ack_idx = 0;
+
ret = open_candev(netdev);
if (ret)
return ret;
@@ -745,21 +752,26 @@ static int kvaser_pciefd_stop(struct net_device *netdev)
timer_delete(&can->bec_poll_timer);
}
can->can.state = CAN_STATE_STOPPED;
+ netdev_reset_queue(netdev);
close_candev(netdev);
return ret;
}
+static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can)
+{
+ return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx));
+}
+
static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
- struct kvaser_pciefd_can *can,
+ struct can_priv *can, u8 seq,
struct sk_buff *skb)
{
struct canfd_frame *cf = (struct canfd_frame *)skb->data;
int packet_size;
- int seq = can->echo_idx;
memset(p, 0, sizeof(*p));
- if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+ if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT)
p->header[1] |= KVASER_PCIEFD_TPACKET_SMS;
if (cf->can_id & CAN_RTR_FLAG)
@@ -782,7 +794,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
} else {
p->header[1] |=
FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK,
- can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode));
+ can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode));
}
p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq);
@@ -797,22 +809,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
struct net_device *netdev)
{
struct kvaser_pciefd_can *can = netdev_priv(netdev);
- unsigned long irq_flags;
struct kvaser_pciefd_tx_packet packet;
+ unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1);
+ unsigned int frame_len;
int nr_words;
- u8 count;
if (can_dev_dropped_skb(netdev, skb))
return NETDEV_TX_OK;
+ if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1))
+ return NETDEV_TX_BUSY;
- nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb);
+ nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb);
- spin_lock_irqsave(&can->echo_lock, irq_flags);
/* Prepare and save echo skb in internal slot */
- can_put_echo_skb(skb, netdev, can->echo_idx, 0);
-
- /* Move echo index to the next slot */
- can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max;
+ WRITE_ONCE(can->can.echo_skb[seq], NULL);
+ frame_len = can_skb_get_frame_len(skb);
+ can_put_echo_skb(skb, netdev, seq, frame_len);
+ netdev_sent_queue(netdev, frame_len);
+ WRITE_ONCE(can->tx_idx, can->tx_idx + 1);
/* Write header to fifo */
iowrite32(packet.header[0],
@@ -836,14 +850,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
KVASER_PCIEFD_KCAN_FIFO_LAST_REG);
}
- count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
- ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
- /* No room for a new message, stop the queue until at least one
- * successful transmit
- */
- if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx])
- netif_stop_queue(netdev);
- spin_unlock_irqrestore(&can->echo_lock, irq_flags);
+ netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1);
return NETDEV_TX_OK;
}
@@ -970,6 +977,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
can->kv_pcie = pcie;
can->cmd_seq = 0;
can->err_rep_cnt = 0;
+ can->completed_tx_pkts = 0;
+ can->completed_tx_bytes = 0;
can->bec.txerr = 0;
can->bec.rxerr = 0;
@@ -983,11 +992,10 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
tx_nr_packets_max =
FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK,
ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+ can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
can->can.clock.freq = pcie->freq;
- can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
- can->echo_idx = 0;
- spin_lock_init(&can->echo_lock);
+ can->can.echo_skb_max = roundup_pow_of_two(can->tx_max_count);
spin_lock_init(&can->lock);
can->can.bittiming_const = &kvaser_pciefd_bittiming_const;
@@ -1201,7 +1209,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
skb = alloc_canfd_skb(priv->dev, &cf);
if (!skb) {
priv->dev->stats.rx_dropped++;
- return -ENOMEM;
+ return 0;
}
cf->len = can_fd_dlc2len(dlc);
@@ -1213,7 +1221,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf);
if (!skb) {
priv->dev->stats.rx_dropped++;
- return -ENOMEM;
+ return 0;
}
can_frame_set_cc_len((struct can_frame *)cf, dlc, priv->ctrlmode);
}
@@ -1231,7 +1239,9 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
priv->dev->stats.rx_packets++;
kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
- return netif_rx(skb);
+ netif_rx(skb);
+
+ return 0;
}
static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can,
@@ -1510,19 +1520,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie,
netdev_dbg(can->can.dev, "Packet was flushed\n");
} else {
int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]);
- int len;
- u8 count;
+ unsigned int len, frame_len = 0;
struct sk_buff *skb;
+ if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1)))
+ return 0;
skb = can->can.echo_skb[echo_idx];
- if (skb)
- kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
- len = can_get_echo_skb(can->can.dev, echo_idx, NULL);
- count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
- ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+ if (!skb)
+ return 0;
+ kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
+ len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len);
- if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev))
- netif_wake_queue(can->can.dev);
+ /* Pairs with barrier in kvaser_pciefd_start_xmit() */
+ smp_store_release(&can->ack_idx, can->ack_idx + 1);
+ can->completed_tx_pkts++;
+ can->completed_tx_bytes += frame_len;
if (!one_shot_fail) {
can->can.dev->stats.tx_bytes += len;
@@ -1638,32 +1650,51 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
{
int pos = 0;
int res = 0;
+ unsigned int i;
do {
res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf);
} while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE);
+ /* Report ACKs in this buffer to BQL en masse for correct periods */
+ for (i = 0; i < pcie->nr_channels; ++i) {
+ struct kvaser_pciefd_can *can = pcie->can[i];
+
+ if (!can->completed_tx_pkts)
+ continue;
+ netif_subqueue_completed_wake(can->can.dev, 0,
+ can->completed_tx_pkts,
+ can->completed_tx_bytes,
+ kvaser_pciefd_tx_avail(can), 1);
+ can->completed_tx_pkts = 0;
+ can->completed_tx_bytes = 0;
+ }
+
return res;
}
-static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
{
+ void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG;
u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
- if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
- kvaser_pciefd_read_buffer(pcie, 0);
+ iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
- if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
+ if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
+ kvaser_pciefd_read_buffer(pcie, 0);
+ iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */
+ }
+
+ if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
kvaser_pciefd_read_buffer(pcie, 1);
+ iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */
+ }
if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
irq & KVASER_PCIEFD_SRB_IRQ_DOF1 ||
irq & KVASER_PCIEFD_SRB_IRQ_DUF0 ||
irq & KVASER_PCIEFD_SRB_IRQ_DUF1))
dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
-
- iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
- return irq;
}
static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
@@ -1691,29 +1722,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
- u32 srb_irq = 0;
- u32 srb_release = 0;
int i;
if (!(pci_irq & irq_mask->all))
return IRQ_NONE;
+ iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+
if (pci_irq & irq_mask->kcan_rx0)
- srb_irq = kvaser_pciefd_receive_irq(pcie);
+ kvaser_pciefd_receive_irq(pcie);
for (i = 0; i < pcie->nr_channels; i++) {
if (pci_irq & irq_mask->kcan_tx[i])
kvaser_pciefd_transmit_irq(pcie->can[i]);
}
- if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
- srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
-
- if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
- srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1;
-
- if (srb_release)
- iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+ iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
return IRQ_HANDLED;
}
@@ -1733,13 +1757,22 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie)
}
}
+static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie)
+{
+ unsigned int i;
+
+ /* Masking PCI_IRQ is insufficient as running ISR will unmask it */
+ iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
+ for (i = 0; i < pcie->nr_channels; ++i)
+ iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
+}
+
static int kvaser_pciefd_probe(struct pci_dev *pdev,
const struct pci_device_id *id)
{
int ret;
struct kvaser_pciefd *pcie;
const struct kvaser_pciefd_irq_mask *irq_mask;
- void __iomem *irq_en_base;
pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
if (!pcie)
@@ -1805,8 +1838,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
/* Enable PCI interrupts */
- irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie);
- iowrite32(irq_mask->all, irq_en_base);
+ iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
/* Ready the DMA buffers */
iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
@@ -1820,8 +1852,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
return 0;
err_free_irq:
- /* Disable PCI interrupts */
- iowrite32(0, irq_en_base);
+ kvaser_pciefd_disable_irq_srcs(pcie);
free_irq(pcie->pci->irq, pcie);
err_pci_free_irq_vectors:
@@ -1844,35 +1875,26 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
return ret;
}
-static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie)
-{
- int i;
-
- for (i = 0; i < pcie->nr_channels; i++) {
- struct kvaser_pciefd_can *can = pcie->can[i];
-
- if (can) {
- iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
- unregister_candev(can->can.dev);
- timer_delete(&can->bec_poll_timer);
- kvaser_pciefd_pwm_stop(can);
- free_candev(can->can.dev);
- }
- }
-}
-
static void kvaser_pciefd_remove(struct pci_dev *pdev)
{
struct kvaser_pciefd *pcie = pci_get_drvdata(pdev);
+ unsigned int i;
- kvaser_pciefd_remove_all_ctrls(pcie);
+ for (i = 0; i < pcie->nr_channels; ++i) {
+ struct kvaser_pciefd_can *can = pcie->can[i];
- /* Disable interrupts */
- iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
- iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+ unregister_candev(can->can.dev);
+ timer_delete(&can->bec_poll_timer);
+ kvaser_pciefd_pwm_stop(can);
+ }
+ kvaser_pciefd_disable_irq_srcs(pcie);
free_irq(pcie->pci->irq, pcie);
pci_free_irq_vectors(pcie->pci);
+
+ for (i = 0; i < pcie->nr_channels; ++i)
+ free_candev(pcie->can[i]->can.dev);
+
pci_iounmap(pdev, pcie->reg_base);
pci_release_regions(pdev);
pci_disable_device(pdev);
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 884a635..c2c116c 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -2379,6 +2379,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
SET_NETDEV_DEV(net_dev, dev);
m_can_of_parse_mram(class_dev, mram_config_vals);
+ spin_lock_init(&class_dev->tx_handling_spinlock);
out:
return class_dev;
}
@@ -2462,9 +2463,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register);
void m_can_class_unregister(struct m_can_classdev *cdev)
{
+ unregister_candev(cdev->net);
if (cdev->is_peripheral)
can_rx_offload_del(&cdev->offload);
- unregister_candev(cdev->net);
}
EXPORT_SYMBOL_GPL(m_can_class_unregister);
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 7107a37..c3fb317 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -937,8 +937,8 @@ static void rkcanfd_remove(struct platform_device *pdev)
struct rkcanfd_priv *priv = platform_get_drvdata(pdev);
struct net_device *ndev = priv->ndev;
- can_rx_offload_del(&priv->offload);
rkcanfd_unregister(priv);
+ can_rx_offload_del(&priv->offload);
free_candev(ndev);
}
diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c
index 24c6622..58ff2ec 100644
--- a/drivers/net/can/slcan/slcan-core.c
+++ b/drivers/net/can/slcan/slcan-core.c
@@ -71,12 +71,21 @@ MODULE_AUTHOR("Dario Binacchi <dario.binacchi@amarulasolutions.com>");
#define SLCAN_CMD_LEN 1
#define SLCAN_SFF_ID_LEN 3
#define SLCAN_EFF_ID_LEN 8
+#define SLCAN_DATA_LENGTH_LEN 1
+#define SLCAN_ERROR_LEN 1
#define SLCAN_STATE_LEN 1
#define SLCAN_STATE_BE_RXCNT_LEN 3
#define SLCAN_STATE_BE_TXCNT_LEN 3
-#define SLCAN_STATE_FRAME_LEN (1 + SLCAN_CMD_LEN + \
- SLCAN_STATE_BE_RXCNT_LEN + \
- SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_STATE_MSG_LEN (SLCAN_CMD_LEN + \
+ SLCAN_STATE_LEN + \
+ SLCAN_STATE_BE_RXCNT_LEN + \
+ SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_ERROR_MSG_LEN_MIN (SLCAN_CMD_LEN + \
+ SLCAN_ERROR_LEN + \
+ SLCAN_DATA_LENGTH_LEN)
+#define SLCAN_FRAME_MSG_LEN_MIN (SLCAN_CMD_LEN + \
+ SLCAN_SFF_ID_LEN + \
+ SLCAN_DATA_LENGTH_LEN)
struct slcan {
struct can_priv can;
@@ -176,6 +185,9 @@ static void slcan_bump_frame(struct slcan *sl)
u32 tmpid;
char *cmd = sl->rbuff;
+ if (sl->rcount < SLCAN_FRAME_MSG_LEN_MIN)
+ return;
+
skb = alloc_can_skb(sl->dev, &cf);
if (unlikely(!skb)) {
sl->dev->stats.rx_dropped++;
@@ -281,7 +293,7 @@ static void slcan_bump_state(struct slcan *sl)
return;
}
- if (state == sl->can.state || sl->rcount < SLCAN_STATE_FRAME_LEN)
+ if (state == sl->can.state || sl->rcount != SLCAN_STATE_MSG_LEN)
return;
cmd += SLCAN_STATE_BE_RXCNT_LEN + SLCAN_CMD_LEN + 1;
@@ -328,6 +340,9 @@ static void slcan_bump_err(struct slcan *sl)
bool rx_errors = false, tx_errors = false, rx_over_errors = false;
int i, len;
+ if (sl->rcount < SLCAN_ERROR_MSG_LEN_MIN)
+ return;
+
/* get len from sanitized ASCII value */
len = cmd[1];
if (len >= '0' && len < '9')
@@ -456,8 +471,7 @@ static void slcan_bump(struct slcan *sl)
static void slcan_unesc(struct slcan *sl, unsigned char s)
{
if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */
- if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
- sl->rcount > 4)
+ if (!test_and_clear_bit(SLF_ERROR, &sl->flags))
slcan_bump(sl);
sl->rcount = 0;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3bc5651..c30b04f 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = {
.brp_inc = 1,
};
+/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of
+ * [-64,63] for TDCO, indicating a relative TDCO.
+ *
+ * Manual tests have shown, that using a relative TDCO configuration
+ * results in bus off, while an absolute configuration works.
+ *
+ * For TDCO use the max value (63) from the data sheet, but 0 as the
+ * minimum.
+ */
+static const struct can_tdc_const mcp251xfd_tdc_const = {
+ .tdcv_min = 0,
+ .tdcv_max = 63,
+ .tdco_min = 0,
+ .tdco_max = 63,
+ .tdcf_min = 0,
+ .tdcf_max = 0,
+};
+
static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model)
{
switch (model) {
@@ -510,8 +528,7 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
{
const struct can_bittiming *bt = &priv->can.bittiming;
const struct can_bittiming *dbt = &priv->can.data_bittiming;
- u32 val = 0;
- s8 tdco;
+ u32 tdcmod, val = 0;
int err;
/* CAN Control Register
@@ -575,11 +592,16 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
return err;
/* Transmitter Delay Compensation */
- tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1),
- -64, 63);
- val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK,
- MCP251XFD_REG_TDC_TDCMOD_AUTO) |
- FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco);
+ if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO)
+ tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO;
+ else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL)
+ tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL;
+ else
+ tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED;
+
+ val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) |
+ FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.tdc.tdcv) |
+ FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.tdc.tdco);
return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val);
}
@@ -2083,10 +2105,12 @@ static int mcp251xfd_probe(struct spi_device *spi)
priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter;
priv->can.bittiming_const = &mcp251xfd_bittiming_const;
priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+ priv->can.tdc_const = &mcp251xfd_tdc_const;
priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING |
CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO |
- CAN_CTRLMODE_CC_LEN8_DLC;
+ CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO |
+ CAN_CTRLMODE_TDC_MANUAL;
set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
priv->ndev = ndev;
priv->spi = spi;
@@ -2174,8 +2198,8 @@ static void mcp251xfd_remove(struct spi_device *spi)
struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
struct net_device *ndev = priv->ndev;
- can_rx_offload_del(&priv->offload);
mcp251xfd_unregister(priv);
+ can_rx_offload_del(&priv->offload);
spi->max_speed_hz = priv->spi_max_speed_hz_orig;
free_candev(ndev);
}
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index e5ba718..7216eb8 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -326,6 +326,26 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
}
}
+static void b53_set_eap_mode(struct b53_device *dev, int port, int mode)
+{
+ u64 eap_conf;
+
+ if (is5325(dev) || is5365(dev) || dev->chip_id == BCM5389_DEVICE_ID)
+ return;
+
+ b53_read64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), &eap_conf);
+
+ if (is63xx(dev)) {
+ eap_conf &= ~EAP_MODE_MASK_63XX;
+ eap_conf |= (u64)mode << EAP_MODE_SHIFT_63XX;
+ } else {
+ eap_conf &= ~EAP_MODE_MASK;
+ eap_conf |= (u64)mode << EAP_MODE_SHIFT;
+ }
+
+ b53_write64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), eap_conf);
+}
+
static void b53_set_forwarding(struct b53_device *dev, int enable)
{
u8 mgmt;
@@ -373,15 +393,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
}
+ vc1 &= ~VC1_RX_MCST_FWD_EN;
+
if (enable) {
vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
- vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+ vc1 |= VC1_RX_MCST_UNTAG_EN;
vc4 &= ~VC4_ING_VID_CHECK_MASK;
if (enable_filtering) {
vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
vc5 |= VC5_DROP_VTABLE_MISS;
} else {
- vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+ vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S;
vc5 &= ~VC5_DROP_VTABLE_MISS;
}
@@ -393,7 +415,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
} else {
vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
- vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+ vc1 &= ~VC1_RX_MCST_UNTAG_EN;
vc4 &= ~VC4_ING_VID_CHECK_MASK;
vc5 &= ~VC5_DROP_VTABLE_MISS;
@@ -576,6 +598,25 @@ static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
}
+int b53_setup_port(struct dsa_switch *ds, int port)
+{
+ struct b53_device *dev = ds->priv;
+
+ b53_port_set_ucast_flood(dev, port, true);
+ b53_port_set_mcast_flood(dev, port, true);
+ b53_port_set_learning(dev, port, false);
+
+ /* Force all traffic to go to the CPU port to prevent the ASIC from
+ * trying to forward to bridged ports on matching FDB entries, then
+ * dropping frames because it isn't allowed to forward there.
+ */
+ if (dsa_is_user_port(ds, port))
+ b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
+ return 0;
+}
+EXPORT_SYMBOL(b53_setup_port);
+
int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
{
struct b53_device *dev = ds->priv;
@@ -588,10 +629,6 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
- b53_port_set_ucast_flood(dev, port, true);
- b53_port_set_mcast_flood(dev, port, true);
- b53_port_set_learning(dev, port, false);
-
if (dev->ops->irq_enable)
ret = dev->ops->irq_enable(dev, port);
if (ret)
@@ -722,10 +759,6 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port)
b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
b53_brcm_hdr_setup(dev->ds, port);
-
- b53_port_set_ucast_flood(dev, port, true);
- b53_port_set_mcast_flood(dev, port, true);
- b53_port_set_learning(dev, port, false);
}
static void b53_enable_mib(struct b53_device *dev)
@@ -761,6 +794,22 @@ static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port);
}
+static bool b53_vlan_port_may_join_untagged(struct dsa_switch *ds, int port)
+{
+ struct b53_device *dev = ds->priv;
+ struct dsa_port *dp;
+
+ if (!dev->vlan_filtering)
+ return true;
+
+ dp = dsa_to_port(ds, port);
+
+ if (dsa_port_is_cpu(dp))
+ return true;
+
+ return dp->bridge == NULL;
+}
+
int b53_configure_vlan(struct dsa_switch *ds)
{
struct b53_device *dev = ds->priv;
@@ -779,7 +828,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
b53_do_vlan_op(dev, VTA_CMD_CLEAR);
}
- b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering);
+ b53_enable_vlan(dev, -1, dev->vlan_enabled, dev->vlan_filtering);
/* Create an untagged VLAN entry for the default PVID in case
* CONFIG_VLAN_8021Q is disabled and there are no calls to
@@ -787,26 +836,39 @@ int b53_configure_vlan(struct dsa_switch *ds)
* entry. Do this only when the tagging protocol is not
* DSA_TAG_PROTO_NONE
*/
+ v = &dev->vlans[def_vid];
b53_for_each_port(dev, i) {
- v = &dev->vlans[def_vid];
- v->members |= BIT(i);
- if (!b53_vlan_port_needs_forced_tagged(ds, i))
- v->untag = v->members;
- b53_write16(dev, B53_VLAN_PAGE,
- B53_VLAN_PORT_DEF_TAG(i), def_vid);
- }
-
- /* Upon initial call we have not set-up any VLANs, but upon
- * system resume, we need to restore all VLAN entries.
- */
- for (vid = def_vid; vid < dev->num_vlans; vid++) {
- v = &dev->vlans[vid];
-
- if (!v->members)
+ if (!b53_vlan_port_may_join_untagged(ds, i))
continue;
- b53_set_vlan_entry(dev, vid, v);
- b53_fast_age_vlan(dev, vid);
+ vl.members |= BIT(i);
+ if (!b53_vlan_port_needs_forced_tagged(ds, i))
+ vl.untag = vl.members;
+ b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i),
+ def_vid);
+ }
+ b53_set_vlan_entry(dev, def_vid, &vl);
+
+ if (dev->vlan_filtering) {
+ /* Upon initial call we have not set-up any VLANs, but upon
+ * system resume, we need to restore all VLAN entries.
+ */
+ for (vid = def_vid + 1; vid < dev->num_vlans; vid++) {
+ v = &dev->vlans[vid];
+
+ if (!v->members)
+ continue;
+
+ b53_set_vlan_entry(dev, vid, v);
+ b53_fast_age_vlan(dev, vid);
+ }
+
+ b53_for_each_port(dev, i) {
+ if (!dsa_is_cpu_port(ds, i))
+ b53_write16(dev, B53_VLAN_PAGE,
+ B53_VLAN_PORT_DEF_TAG(i),
+ dev->ports[i].pvid);
+ }
}
return 0;
@@ -1125,7 +1187,9 @@ EXPORT_SYMBOL(b53_setup_devlink_resources);
static int b53_setup(struct dsa_switch *ds)
{
struct b53_device *dev = ds->priv;
+ struct b53_vlan *vl;
unsigned int port;
+ u16 pvid;
int ret;
/* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set
@@ -1133,12 +1197,26 @@ static int b53_setup(struct dsa_switch *ds)
*/
ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE;
+ /* The switch does not tell us the original VLAN for untagged
+ * packets, so keep the CPU port always tagged.
+ */
+ ds->untag_vlan_aware_bridge_pvid = true;
+
ret = b53_reset_switch(dev);
if (ret) {
dev_err(ds->dev, "failed to reset switch\n");
return ret;
}
+ /* setup default vlan for filtering mode */
+ pvid = b53_default_pvid(dev);
+ vl = &dev->vlans[pvid];
+ b53_for_each_port(dev, port) {
+ vl->members |= BIT(port);
+ if (!b53_vlan_port_needs_forced_tagged(ds, port))
+ vl->untag |= BIT(port);
+ }
+
b53_reset_mib(dev);
ret = b53_apply_config(dev);
@@ -1492,7 +1570,10 @@ int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
{
struct b53_device *dev = ds->priv;
- b53_enable_vlan(dev, port, dev->vlan_enabled, vlan_filtering);
+ if (dev->vlan_filtering != vlan_filtering) {
+ dev->vlan_filtering = vlan_filtering;
+ b53_apply_config(dev);
+ }
return 0;
}
@@ -1517,7 +1598,7 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
if (vlan->vid >= dev->num_vlans)
return -ERANGE;
- b53_enable_vlan(dev, port, true, ds->vlan_filtering);
+ b53_enable_vlan(dev, port, true, dev->vlan_filtering);
return 0;
}
@@ -1530,18 +1611,29 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
struct b53_vlan *vl;
+ u16 old_pvid, new_pvid;
int err;
err = b53_vlan_prepare(ds, port, vlan);
if (err)
return err;
+ if (vlan->vid == 0)
+ return 0;
+
+ old_pvid = dev->ports[port].pvid;
+ if (pvid)
+ new_pvid = vlan->vid;
+ else if (!pvid && vlan->vid == old_pvid)
+ new_pvid = b53_default_pvid(dev);
+ else
+ new_pvid = old_pvid;
+ dev->ports[port].pvid = new_pvid;
+
vl = &dev->vlans[vlan->vid];
- b53_get_vlan_entry(dev, vlan->vid, vl);
-
- if (vlan->vid == 0 && vlan->vid == b53_default_pvid(dev))
- untagged = true;
+ if (dsa_is_cpu_port(ds, port))
+ untagged = false;
vl->members |= BIT(port);
if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
@@ -1549,13 +1641,16 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
else
vl->untag &= ~BIT(port);
+ if (!dev->vlan_filtering)
+ return 0;
+
b53_set_vlan_entry(dev, vlan->vid, vl);
b53_fast_age_vlan(dev, vlan->vid);
- if (pvid && !dsa_is_cpu_port(ds, port)) {
+ if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) {
b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
- vlan->vid);
- b53_fast_age_vlan(dev, vlan->vid);
+ new_pvid);
+ b53_fast_age_vlan(dev, old_pvid);
}
return 0;
@@ -1570,20 +1665,25 @@ int b53_vlan_del(struct dsa_switch *ds, int port,
struct b53_vlan *vl;
u16 pvid;
- b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+ if (vlan->vid == 0)
+ return 0;
+
+ pvid = dev->ports[port].pvid;
vl = &dev->vlans[vlan->vid];
- b53_get_vlan_entry(dev, vlan->vid, vl);
-
vl->members &= ~BIT(port);
if (pvid == vlan->vid)
pvid = b53_default_pvid(dev);
+ dev->ports[port].pvid = pvid;
if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
vl->untag &= ~(BIT(port));
+ if (!dev->vlan_filtering)
+ return 0;
+
b53_set_vlan_entry(dev, vlan->vid, vl);
b53_fast_age_vlan(dev, vlan->vid);
@@ -1916,8 +2016,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
bool *tx_fwd_offload, struct netlink_ext_ack *extack)
{
struct b53_device *dev = ds->priv;
+ struct b53_vlan *vl;
s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
- u16 pvlan, reg;
+ u16 pvlan, reg, pvid;
unsigned int i;
/* On 7278, port 7 which connects to the ASP should only receive
@@ -1926,15 +2027,29 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
if (dev->chip_id == BCM7278_DEVICE_ID && port == 7)
return -EINVAL;
- /* Make this port leave the all VLANs join since we will have proper
- * VLAN entries from now on
- */
- if (is58xx(dev)) {
- b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®);
- reg &= ~BIT(port);
- if ((reg & BIT(cpu_port)) == BIT(cpu_port))
- reg &= ~BIT(cpu_port);
- b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+ pvid = b53_default_pvid(dev);
+ vl = &dev->vlans[pvid];
+
+ if (dev->vlan_filtering) {
+ /* Make this port leave the all VLANs join since we will have
+ * proper VLAN entries from now on
+ */
+ if (is58xx(dev)) {
+ b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+ ®);
+ reg &= ~BIT(port);
+ if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+ reg &= ~BIT(cpu_port);
+ b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+ reg);
+ }
+
+ b53_get_vlan_entry(dev, pvid, vl);
+ vl->members &= ~BIT(port);
+ if (vl->members == BIT(cpu_port))
+ vl->members &= ~BIT(cpu_port);
+ vl->untag = vl->members;
+ b53_set_vlan_entry(dev, pvid, vl);
}
b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
@@ -1954,6 +2069,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
pvlan |= BIT(i);
}
+ /* Disable redirection of unknown SA to the CPU port */
+ b53_set_eap_mode(dev, port, EAP_MODE_BASIC);
+
/* Configure the local port VLAN control membership to include
* remote ports and update the local port bitmask
*/
@@ -1967,7 +2085,7 @@ EXPORT_SYMBOL(b53_br_join);
void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
{
struct b53_device *dev = ds->priv;
- struct b53_vlan *vl = &dev->vlans[0];
+ struct b53_vlan *vl;
s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
unsigned int i;
u16 pvlan, reg, pvid;
@@ -1989,19 +2107,25 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
pvlan &= ~BIT(i);
}
+ /* Enable redirection of unknown SA to the CPU port */
+ b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
dev->ports[port].vlan_ctl_mask = pvlan;
pvid = b53_default_pvid(dev);
+ vl = &dev->vlans[pvid];
- /* Make this port join all VLANs without VLAN entries */
- if (is58xx(dev)) {
- b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®);
- reg |= BIT(port);
- if (!(reg & BIT(cpu_port)))
- reg |= BIT(cpu_port);
- b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
- } else {
+ if (dev->vlan_filtering) {
+ /* Make this port join all VLANs without VLAN entries */
+ if (is58xx(dev)) {
+ b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®);
+ reg |= BIT(port);
+ if (!(reg & BIT(cpu_port)))
+ reg |= BIT(cpu_port);
+ b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+ }
+
b53_get_vlan_entry(dev, pvid, vl);
vl->members |= BIT(port) | BIT(cpu_port);
vl->untag |= BIT(port) | BIT(cpu_port);
@@ -2300,6 +2424,7 @@ static const struct dsa_switch_ops b53_switch_ops = {
.phy_read = b53_phy_read16,
.phy_write = b53_phy_write16,
.phylink_get_caps = b53_phylink_get_caps,
+ .port_setup = b53_setup_port,
.port_enable = b53_enable_port,
.port_disable = b53_disable_port,
.support_eee = b53_support_eee,
@@ -2757,6 +2882,7 @@ struct b53_device *b53_switch_alloc(struct device *base,
ds->ops = &b53_switch_ops;
ds->phylink_mac_ops = &b53_phylink_mac_ops;
dev->vlan_enabled = true;
+ dev->vlan_filtering = false;
/* Let DSA handle the case were multiple bridges span the same switch
* device and different VLAN awareness settings are requested, which
* would be breaking filtering semantics for any of the other bridge
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 0166c37..2cf3e6a8 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -96,6 +96,7 @@ struct b53_pcs {
struct b53_port {
u16 vlan_ctl_mask;
+ u16 pvid;
struct ethtool_keee eee;
};
@@ -147,6 +148,7 @@ struct b53_device {
unsigned int num_vlans;
struct b53_vlan *vlans;
bool vlan_enabled;
+ bool vlan_filtering;
unsigned int num_ports;
struct b53_port *ports;
@@ -382,6 +384,7 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
enum dsa_tag_protocol mprot);
void b53_mirror_del(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
+int b53_setup_port(struct dsa_switch *ds, int port);
int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
void b53_disable_port(struct dsa_switch *ds, int port);
void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index bfbcb66..5f7a0e5 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -50,6 +50,9 @@
/* Jumbo Frame Registers */
#define B53_JUMBO_PAGE 0x40
+/* EAP Registers */
+#define B53_EAP_PAGE 0x42
+
/* EEE Control Registers Page */
#define B53_EEE_PAGE 0x92
@@ -481,6 +484,17 @@
#define JMS_MAX_SIZE 9724
/*************************************************************************
+ * EAP Page Registers
+ *************************************************************************/
+#define B53_PORT_EAP_CONF(i) (0x20 + 8 * (i))
+#define EAP_MODE_SHIFT 51
+#define EAP_MODE_SHIFT_63XX 50
+#define EAP_MODE_MASK (0x3ull << EAP_MODE_SHIFT)
+#define EAP_MODE_MASK_63XX (0x3ull << EAP_MODE_SHIFT_63XX)
+#define EAP_MODE_BASIC 0
+#define EAP_MODE_SIMPLIFIED 3
+
+/*************************************************************************
* EEE Configuration Page Registers
*************************************************************************/
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index fa2bf3f..454a8c7 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1230,6 +1230,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
.resume = bcm_sf2_sw_resume,
.get_wol = bcm_sf2_sw_get_wol,
.set_wol = bcm_sf2_sw_set_wol,
+ .port_setup = b53_setup_port,
.port_enable = bcm_sf2_port_setup,
.port_disable = bcm_sf2_port_disable,
.support_eee = b53_support_eee,
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 89f0796..f95a9aa 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -265,16 +265,70 @@ static void ksz_phylink_mac_link_down(struct phylink_config *config,
unsigned int mode,
phy_interface_t interface);
+/**
+ * ksz_phylink_mac_disable_tx_lpi() - Callback to signal LPI support (Dummy)
+ * @config: phylink config structure
+ *
+ * This function is a dummy handler. See ksz_phylink_mac_enable_tx_lpi() for
+ * a detailed explanation of EEE/LPI handling in KSZ switches.
+ */
+static void ksz_phylink_mac_disable_tx_lpi(struct phylink_config *config)
+{
+}
+
+/**
+ * ksz_phylink_mac_enable_tx_lpi() - Callback to signal LPI support (Dummy)
+ * @config: phylink config structure
+ * @timer: timer value before entering LPI (unused)
+ * @tx_clock_stop: whether to stop the TX clock in LPI mode (unused)
+ *
+ * This function signals to phylink that the driver architecture supports
+ * LPI management, enabling phylink to control EEE advertisement during
+ * negotiation according to IEEE Std 802.3 (Clause 78).
+ *
+ * Hardware Management of EEE/LPI State:
+ * For KSZ switch ports with integrated PHYs (e.g., KSZ9893R ports 1-2),
+ * observation and testing suggest that the actual EEE / Low Power Idle (LPI)
+ * state transitions are managed autonomously by the hardware based on
+ * the auto-negotiation results. (Note: While the datasheet describes EEE
+ * operation based on negotiation, it doesn't explicitly detail the internal
+ * MAC/PHY interaction, so autonomous hardware management of the MAC state
+ * for LPI is inferred from observed behavior).
+ * This hardware control, consistent with the switch's ability to operate
+ * autonomously via strapping, means MAC-level software intervention is not
+ * required or exposed for managing the LPI state once EEE is negotiated.
+ * (Ref: KSZ9893R Data Sheet DS00002420D, primarily Section 4.7.5 explaining
+ * EEE, also Sections 4.1.7 on Auto-Negotiation and 3.2.1 on Configuration
+ * Straps).
+ *
+ * Additionally, ports configured as MAC interfaces (e.g., KSZ9893R port 3)
+ * lack documented MAC-level LPI control.
+ *
+ * Therefore, this callback performs no action and serves primarily to inform
+ * phylink of LPI awareness and to document the inferred hardware behavior.
+ *
+ * Returns: 0 (Always success)
+ */
+static int ksz_phylink_mac_enable_tx_lpi(struct phylink_config *config,
+ u32 timer, bool tx_clock_stop)
+{
+ return 0;
+}
+
static const struct phylink_mac_ops ksz88x3_phylink_mac_ops = {
.mac_config = ksz88x3_phylink_mac_config,
.mac_link_down = ksz_phylink_mac_link_down,
.mac_link_up = ksz8_phylink_mac_link_up,
+ .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+ .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
};
static const struct phylink_mac_ops ksz8_phylink_mac_ops = {
.mac_config = ksz_phylink_mac_config,
.mac_link_down = ksz_phylink_mac_link_down,
.mac_link_up = ksz8_phylink_mac_link_up,
+ .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+ .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
};
static const struct ksz_dev_ops ksz88xx_dev_ops = {
@@ -358,6 +412,8 @@ static const struct phylink_mac_ops ksz9477_phylink_mac_ops = {
.mac_config = ksz_phylink_mac_config,
.mac_link_down = ksz_phylink_mac_link_down,
.mac_link_up = ksz9477_phylink_mac_link_up,
+ .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+ .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
};
static const struct ksz_dev_ops ksz9477_dev_ops = {
@@ -401,6 +457,8 @@ static const struct phylink_mac_ops lan937x_phylink_mac_ops = {
.mac_config = ksz_phylink_mac_config,
.mac_link_down = ksz_phylink_mac_link_down,
.mac_link_up = ksz9477_phylink_mac_link_up,
+ .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi,
+ .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
};
static const struct ksz_dev_ops lan937x_dev_ops = {
@@ -2016,6 +2074,18 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port,
if (dev->dev_ops->get_caps)
dev->dev_ops->get_caps(dev, port, config);
+
+ if (ds->ops->support_eee && ds->ops->support_eee(ds, port)) {
+ memcpy(config->lpi_interfaces, config->supported_interfaces,
+ sizeof(config->lpi_interfaces));
+
+ config->lpi_capabilities = MAC_100FD;
+ if (dev->info->gbit_capable[port])
+ config->lpi_capabilities |= MAC_1000FD;
+
+ /* EEE is fully operational */
+ config->eee_enabled_default = true;
+ }
}
void ksz_r_mib_stats64(struct ksz_device *dev, int port)
@@ -3008,31 +3078,6 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
if (!port)
return MICREL_KSZ8_P1_ERRATA;
break;
- case KSZ8567_CHIP_ID:
- /* KSZ8567R Errata DS80000752C Module 4 */
- case KSZ8765_CHIP_ID:
- case KSZ8794_CHIP_ID:
- case KSZ8795_CHIP_ID:
- /* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
- case KSZ9477_CHIP_ID:
- /* KSZ9477S Errata DS80000754A Module 4 */
- case KSZ9567_CHIP_ID:
- /* KSZ9567S Errata DS80000756A Module 4 */
- case KSZ9896_CHIP_ID:
- /* KSZ9896C Errata DS80000757A Module 3 */
- case KSZ9897_CHIP_ID:
- case LAN9646_CHIP_ID:
- /* KSZ9897R Errata DS80000758C Module 4 */
- /* Energy Efficient Ethernet (EEE) feature select must be manually disabled
- * The EEE feature is enabled by default, but it is not fully
- * operational. It must be manually disabled through register
- * controls. If not disabled, the PHY ports can auto-negotiate
- * to enable EEE, and this feature can cause link drops when
- * linked to another device supporting EEE.
- *
- * The same item appears in the errata for all switches above.
- */
- return MICREL_NO_EEE;
}
return 0;
@@ -3466,6 +3511,20 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
return -EOPNOTSUPP;
}
+/**
+ * ksz_support_eee - Determine Energy Efficient Ethernet (EEE) support for a
+ * port
+ * @ds: Pointer to the DSA switch structure
+ * @port: Port number to check
+ *
+ * This function also documents devices where EEE was initially advertised but
+ * later withdrawn due to reliability issues, as described in official errata
+ * documents. These devices are explicitly listed to record known limitations,
+ * even if there is no technical necessity for runtime checks.
+ *
+ * Returns: true if the internal PHY on the given port supports fully
+ * operational EEE, false otherwise.
+ */
static bool ksz_support_eee(struct dsa_switch *ds, int port)
{
struct ksz_device *dev = ds->priv;
@@ -3475,15 +3534,35 @@ static bool ksz_support_eee(struct dsa_switch *ds, int port)
switch (dev->chip_id) {
case KSZ8563_CHIP_ID:
- case KSZ8567_CHIP_ID:
- case KSZ9477_CHIP_ID:
case KSZ9563_CHIP_ID:
- case KSZ9567_CHIP_ID:
case KSZ9893_CHIP_ID:
+ return true;
+ case KSZ8567_CHIP_ID:
+ /* KSZ8567R Errata DS80000752C Module 4 */
+ case KSZ8765_CHIP_ID:
+ case KSZ8794_CHIP_ID:
+ case KSZ8795_CHIP_ID:
+ /* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
+ case KSZ9477_CHIP_ID:
+ /* KSZ9477S Errata DS80000754A Module 4 */
+ case KSZ9567_CHIP_ID:
+ /* KSZ9567S Errata DS80000756A Module 4 */
case KSZ9896_CHIP_ID:
+ /* KSZ9896C Errata DS80000757A Module 3 */
case KSZ9897_CHIP_ID:
case LAN9646_CHIP_ID:
- return true;
+ /* KSZ9897R Errata DS80000758C Module 4 */
+ /* Energy Efficient Ethernet (EEE) feature select must be
+ * manually disabled
+ * The EEE feature is enabled by default, but it is not fully
+ * operational. It must be manually disabled through register
+ * controls. If not disabled, the PHY ports can auto-negotiate
+ * to enable EEE, and this feature can cause link drops when
+ * linked to another device supporting EEE.
+ *
+ * The same item appears in the errata for all switches above.
+ */
+ break;
}
return false;
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index d70399b..c5d6628 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2419,6 +2419,9 @@ mt7531_setup_common(struct dsa_switch *ds)
struct mt7530_priv *priv = ds->priv;
int ret, i;
+ ds->assisted_learning_on_cpu_port = true;
+ ds->mtu_enforcement_ingress = true;
+
mt753x_trap_frames(priv);
/* Enable and reset MIB counters */
@@ -2571,9 +2574,6 @@ mt7531_setup(struct dsa_switch *ds)
if (ret)
return ret;
- ds->assisted_learning_on_cpu_port = true;
- ds->mtu_enforcement_ingress = true;
-
return 0;
}
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 940f1b7..7b35d24 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1543,7 +1543,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
struct tc_taprio_qopt_offload *taprio;
struct ocelot_port *ocelot_port;
struct timespec64 base_ts;
- int port;
+ int i, port;
u32 val;
mutex_lock(&ocelot->fwd_domain_lock);
@@ -1575,6 +1575,9 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB_M,
QSYS_PARAM_CFG_REG_3);
+ for (i = 0; i < taprio->num_entries; i++)
+ vsc9959_tas_gcl_set(ocelot, i, &taprio->entries[i]);
+
ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
QSYS_TAS_PARAM_CFG_CTRL);
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index f8454f3..f674c40 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2081,6 +2081,7 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
switch (state) {
case BR_STATE_DISABLED:
case BR_STATE_BLOCKING:
+ case BR_STATE_LISTENING:
/* From UM10944 description of DRPDTAG (why put this there?):
* "Management traffic flows to the port regardless of the state
* of the INGRESS flag". So BPDUs are still be allowed to pass.
@@ -2090,11 +2091,6 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
mac[port].egress = false;
mac[port].dyn_learn = false;
break;
- case BR_STATE_LISTENING:
- mac[port].ingress = true;
- mac[port].egress = false;
- mac[port].dyn_learn = false;
- break;
case BR_STATE_LEARNING:
mac[port].ingress = true;
mac[port].egress = false;
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index d748dc6d..1e9ab65 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -614,7 +614,6 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
struct airoha_queue_entry *e = &q->entry[q->tail];
struct airoha_qdma_desc *desc = &q->desc[q->tail];
u32 hash, reason, msg1 = le32_to_cpu(desc->msg1);
- dma_addr_t dma_addr = le32_to_cpu(desc->addr);
struct page *page = virt_to_head_page(e->buf);
u32 desc_ctrl = le32_to_cpu(desc->ctrl);
struct airoha_gdm_port *port;
@@ -623,22 +622,16 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
if (!(desc_ctrl & QDMA_DESC_DONE_MASK))
break;
- if (!dma_addr)
- break;
-
- len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
- if (!len)
- break;
-
q->tail = (q->tail + 1) % q->ndesc;
q->queued--;
- dma_sync_single_for_cpu(eth->dev, dma_addr,
+ dma_sync_single_for_cpu(eth->dev, e->dma_addr,
SKB_WITH_OVERHEAD(q->buf_size), dir);
+ len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
data_len = q->skb ? q->buf_size
: SKB_WITH_OVERHEAD(q->buf_size);
- if (data_len < len)
+ if (!len || data_len < len)
goto free_frag;
p = airoha_qdma_get_gdm_port(eth, desc);
@@ -701,9 +694,12 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
q->skb = NULL;
continue;
free_frag:
- page_pool_put_full_page(q->page_pool, page, true);
- dev_kfree_skb(q->skb);
- q->skb = NULL;
+ if (q->skb) {
+ dev_kfree_skb(q->skb);
+ q->skb = NULL;
+ } else {
+ page_pool_put_full_page(q->page_pool, page, true);
+ }
}
airoha_qdma_fill_rx_queue(q);
diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
index 7a5710f..ead0625 100644
--- a/drivers/net/ethernet/airoha/airoha_npu.c
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -104,12 +104,14 @@ struct ppe_mbox_data {
u8 xpon_hal_api;
u8 wan_xsi;
u8 ct_joyme4;
- int ppe_type;
- int wan_mode;
- int wan_sel;
+ u8 max_packet;
+ u8 rsv[3];
+ u32 ppe_type;
+ u32 wan_mode;
+ u32 wan_sel;
} init_info;
struct {
- int func_id;
+ u32 func_id;
u32 size;
u32 data;
} set_info;
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index c83a0a8..506f682 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -5,11 +5,6 @@
#include "core.h"
-struct pdsc_wait_context {
- struct pdsc_qcq *qcq;
- struct completion wait_completion;
-};
-
static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
{
union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
q_info = &q->info[q->tail_idx];
q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
- /* Copy out the completion data */
- memcpy(q_info->dest, comp, sizeof(*comp));
-
- complete_all(&q_info->wc->wait_completion);
+ if (!completion_done(&q_info->completion)) {
+ memcpy(q_info->dest, comp, sizeof(*comp));
+ complete(&q_info->completion);
+ }
if (cq->tail_idx == cq->num_descs - 1)
cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
static int __pdsc_adminq_post(struct pdsc *pdsc,
struct pdsc_qcq *qcq,
union pds_core_adminq_cmd *cmd,
- union pds_core_adminq_comp *comp,
- struct pdsc_wait_context *wc)
+ union pds_core_adminq_comp *comp)
{
struct pdsc_queue *q = &qcq->q;
struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
/* Post the request */
index = q->head_idx;
q_info = &q->info[index];
- q_info->wc = wc;
q_info->dest = comp;
memcpy(q_info->desc, cmd, sizeof(*cmd));
+ reinit_completion(&q_info->completion);
dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
union pds_core_adminq_comp *comp,
bool fast_poll)
{
- struct pdsc_wait_context wc = {
- .wait_completion =
- COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
- };
unsigned long poll_interval = 1;
unsigned long poll_jiffies;
unsigned long time_limit;
unsigned long time_start;
unsigned long time_done;
unsigned long remaining;
+ struct completion *wc;
int err = 0;
int index;
@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
return -ENXIO;
}
- wc.qcq = &pdsc->adminqcq;
- index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+ index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
if (index < 0) {
err = index;
goto err_out;
}
+ wc = &pdsc->adminqcq.q.info[index].completion;
time_start = jiffies;
time_limit = time_start + HZ * pdsc->devcmd_timeout;
do {
/* Timeslice the actual wait to catch IO errors etc early */
poll_jiffies = msecs_to_jiffies(poll_interval);
- remaining = wait_for_completion_timeout(&wc.wait_completion,
- poll_jiffies);
+ remaining = wait_for_completion_timeout(wc, poll_jiffies);
if (remaining)
break;
@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
__func__, jiffies_to_msecs(time_done - time_start));
- /* Check the results */
- if (time_after_eq(time_done, time_limit))
+ /* Check the results and clear an un-completed timeout */
+ if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
err = -ETIMEDOUT;
+ complete(wc);
+ }
dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index eeb72b1..92f359f 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
dev_dbg(pf->dev, "%s: %s opcode %d\n",
__func__, dev_name(&padev->aux_dev.dev), req->opcode);
- if (pf->state)
- return -ENXIO;
-
/* Wrap the client's request */
cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -189,7 +186,6 @@ void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
pds_client_unregister(pf, padev->client_id);
auxiliary_device_delete(&padev->aux_dev);
auxiliary_device_uninit(&padev->aux_dev);
- padev->client_id = 0;
*pd_ptr = NULL;
mutex_unlock(&pf->config_lock);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 1eb0d92..9512aa4 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
q->base = base;
q->base_pa = base_pa;
- for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+ for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
cur->desc = base + (i * q->desc_size);
+ init_completion(&cur->completion);
+ }
}
static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
size_t sz;
int err;
- /* Scale the descriptor ring length based on number of CPUs and VFs */
- numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
- numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
- numdescs = roundup_pow_of_two(numdescs);
+ numdescs = PDSC_ADMINQ_MAX_LENGTH;
err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
numdescs,
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 0bf320c..0b53a1f 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -16,7 +16,7 @@
#define PDSC_WATCHDOG_SECS 5
#define PDSC_QUEUE_NAME_MAX_SZ 16
-#define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH 16 /* must be a power of two */
#define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */
#define PDSC_TEARDOWN_RECOVERY false
#define PDSC_TEARDOWN_REMOVING true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
unsigned int bytes;
unsigned int nbufs;
struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
- struct pdsc_wait_context *wc;
+ struct completion completion;
void *dest;
};
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index c5c787d..d8dc39d 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -105,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
.fw_control.oper = PDS_CORE_FW_GET_LIST,
};
- struct pds_core_fw_list_info fw_list;
+ struct pds_core_fw_list_info fw_list = {};
struct pdsc *pdsc = devlink_priv(dl);
union pds_core_dev_comp comp;
char buf[32];
@@ -118,8 +118,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
if (!err)
memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
mutex_unlock(&pdsc->devcmd_lock);
- if (err && err != -EIO)
- return err;
listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
for (i = 0; i < listlen; i++) {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 230726d..d41b58f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -373,8 +373,13 @@ static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
}
/* Set up the header page info */
- xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
- XGBE_SKB_ALLOC_SIZE);
+ if (pdata->netdev->features & NETIF_F_RXCSUM) {
+ xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+ XGBE_SKB_ALLOC_SIZE);
+ } else {
+ xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+ pdata->rx_buf_size);
+ }
/* Set up the buffer page info */
xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index f393228..f1b0fb0 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -320,6 +320,18 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata)
XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE);
}
+static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata)
+{
+ unsigned int i;
+
+ for (i = 0; i < pdata->channel_count; i++) {
+ if (!pdata->channel[i]->rx_ring)
+ break;
+
+ XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0);
+ }
+}
+
static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type,
unsigned int index, unsigned int val)
{
@@ -3545,8 +3557,12 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
xgbe_config_tx_coalesce(pdata);
xgbe_config_rx_buffer_size(pdata);
xgbe_config_tso_mode(pdata);
- xgbe_config_sph_mode(pdata);
- xgbe_config_rss(pdata);
+
+ if (pdata->netdev->features & NETIF_F_RXCSUM) {
+ xgbe_config_sph_mode(pdata);
+ xgbe_config_rss(pdata);
+ }
+
desc_if->wrapper_tx_desc_init(pdata);
desc_if->wrapper_rx_desc_init(pdata);
xgbe_enable_dma_interrupts(pdata);
@@ -3702,5 +3718,9 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
hw_if->disable_vxlan = xgbe_disable_vxlan;
hw_if->set_vxlan_id = xgbe_set_vxlan_id;
+ /* For Split Header*/
+ hw_if->enable_sph = xgbe_config_sph_mode;
+ hw_if->disable_sph = xgbe_disable_sph_mode;
+
DBGPR("<--xgbe_init_function_ptrs\n");
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index d84a310..8e09ad8 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2257,10 +2257,17 @@ static int xgbe_set_features(struct net_device *netdev,
if (ret)
return ret;
- if ((features & NETIF_F_RXCSUM) && !rxcsum)
+ if ((features & NETIF_F_RXCSUM) && !rxcsum) {
+ hw_if->enable_sph(pdata);
+ hw_if->enable_vxlan(pdata);
hw_if->enable_rx_csum(pdata);
- else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+ schedule_work(&pdata->restart_work);
+ } else if (!(features & NETIF_F_RXCSUM) && rxcsum) {
+ hw_if->disable_sph(pdata);
+ hw_if->disable_vxlan(pdata);
hw_if->disable_rx_csum(pdata);
+ schedule_work(&pdata->restart_work);
+ }
if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
hw_if->enable_rx_vlan_stripping(pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index d85386c..ed5d43c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -865,6 +865,10 @@ struct xgbe_hw_if {
void (*enable_vxlan)(struct xgbe_prv_data *);
void (*disable_vxlan)(struct xgbe_prv_data *);
void (*set_vxlan_id)(struct xgbe_prv_data *);
+
+ /* For Split Header */
+ void (*enable_sph)(struct xgbe_prv_data *pdata);
+ void (*disable_sph)(struct xgbe_prv_data *pdata);
};
/* This structure represents implementation specific routines for an
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c8e3468..6afc2ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2015,6 +2015,7 @@ static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
}
return skb;
vlan_err:
+ skb_mark_for_recycle(skb);
dev_kfree_skb(skb);
return NULL;
}
@@ -3414,6 +3415,9 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
bnxt_free_one_tx_ring_skbs(bp, txr, i);
}
+
+ if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
+ bnxt_ptp_free_txts_skbs(bp->ptp_cfg);
}
static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
@@ -11599,6 +11603,9 @@ static void bnxt_init_napi(struct bnxt *bp)
poll_fn = bnxt_poll_p5;
else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
cp_nr_rings--;
+
+ set_bit(BNXT_STATE_NAPI_DISABLED, &bp->state);
+
for (i = 0; i < cp_nr_rings; i++) {
bnapi = bp->bnapi[i];
netif_napi_add_config_locked(bp->dev, &bnapi->napi, poll_fn,
@@ -12318,12 +12325,15 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
{
struct hwrm_func_drv_if_change_output *resp;
struct hwrm_func_drv_if_change_input *req;
- bool fw_reset = !bp->irq_tbl;
bool resc_reinit = false;
bool caps_change = false;
int rc, retry = 0;
+ bool fw_reset;
u32 flags = 0;
+ fw_reset = (bp->fw_reset_state == BNXT_FW_RESET_STATE_ABORT);
+ bp->fw_reset_state = 0;
+
if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
return 0;
@@ -12392,13 +12402,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
return rc;
}
+ /* IRQ will be initialized later in bnxt_request_irq()*/
bnxt_clear_int_mode(bp);
- rc = bnxt_init_int_mode(bp);
- if (rc) {
- clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
- netdev_err(bp->dev, "init int mode failed\n");
- return rc;
- }
}
rc = bnxt_cancel_reservations(bp, fw_reset);
}
@@ -12797,8 +12802,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
/* VF-reps may need to be re-opened after the PF is re-opened */
if (BNXT_PF(bp))
bnxt_vf_reps_open(bp);
- if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
- WRITE_ONCE(bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
bnxt_ptp_init_rtc(bp, true);
bnxt_ptp_cfg_tstamp_filters(bp);
if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
@@ -14010,13 +14013,28 @@ static void bnxt_unlock_sp(struct bnxt *bp)
netdev_unlock(bp->dev);
}
+/* Same as bnxt_lock_sp() with additional rtnl_lock */
+static void bnxt_rtnl_lock_sp(struct bnxt *bp)
+{
+ clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+ rtnl_lock();
+ netdev_lock(bp->dev);
+}
+
+static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+{
+ set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+ netdev_unlock(bp->dev);
+ rtnl_unlock();
+}
+
/* Only called from bnxt_sp_task() */
static void bnxt_reset(struct bnxt *bp, bool silent)
{
- bnxt_lock_sp(bp);
+ bnxt_rtnl_lock_sp(bp);
if (test_bit(BNXT_STATE_OPEN, &bp->state))
bnxt_reset_task(bp, silent);
- bnxt_unlock_sp(bp);
+ bnxt_rtnl_unlock_sp(bp);
}
/* Only called from bnxt_sp_task() */
@@ -14024,9 +14042,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
{
int i;
- bnxt_lock_sp(bp);
+ bnxt_rtnl_lock_sp(bp);
if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
- bnxt_unlock_sp(bp);
+ bnxt_rtnl_unlock_sp(bp);
return;
}
/* Disable and flush TPA before resetting the RX ring */
@@ -14065,7 +14083,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
}
if (bp->flags & BNXT_FLAG_TPA)
bnxt_set_tpa(bp, true);
- bnxt_unlock_sp(bp);
+ bnxt_rtnl_unlock_sp(bp);
}
static void bnxt_fw_fatal_close(struct bnxt *bp)
@@ -14833,7 +14851,7 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
bnxt_dl_health_fw_status_update(bp, false);
- bp->fw_reset_state = 0;
+ bp->fw_reset_state = BNXT_FW_RESET_STATE_ABORT;
netif_close(bp->dev);
}
@@ -14957,15 +14975,17 @@ static void bnxt_fw_reset_task(struct work_struct *work)
bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
fallthrough;
case BNXT_FW_RESET_STATE_OPENING:
- while (!netdev_trylock(bp->dev)) {
+ while (!rtnl_trylock()) {
bnxt_queue_fw_reset_work(bp, HZ / 10);
return;
}
+ netdev_lock(bp->dev);
rc = bnxt_open(bp->dev);
if (rc) {
netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
bnxt_fw_reset_abort(bp, rc);
netdev_unlock(bp->dev);
+ rtnl_unlock();
goto ulp_start;
}
@@ -14985,6 +15005,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
bnxt_dl_health_fw_status_update(bp, true);
}
netdev_unlock(bp->dev);
+ rtnl_unlock();
bnxt_ulp_start(bp, 0);
bnxt_reenable_sriov(bp);
netdev_lock(bp->dev);
@@ -15933,7 +15954,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
rc);
napi_enable_locked(&bnapi->napi);
bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
- bnxt_reset_task(bp, true);
+ netif_close(dev);
return rc;
}
@@ -16003,8 +16024,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
bnxt_rdma_aux_device_del(bp);
- bnxt_ptp_clear(bp);
unregister_netdev(dev);
+ bnxt_ptp_clear(bp);
bnxt_rdma_aux_device_uninit(bp);
@@ -16749,6 +16770,7 @@ static int bnxt_resume(struct device *device)
struct bnxt *bp = netdev_priv(dev);
int rc = 0;
+ rtnl_lock();
netdev_lock(dev);
rc = pci_enable_device(bp->pdev);
if (rc) {
@@ -16793,6 +16815,7 @@ static int bnxt_resume(struct device *device)
resume_exit:
netdev_unlock(bp->dev);
+ rtnl_unlock();
bnxt_ulp_start(bp, rc);
if (!rc)
bnxt_reenable_sriov(bp);
@@ -16931,10 +16954,9 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
if (!err)
result = PCI_ERS_RESULT_RECOVERED;
+ /* IRQ will be initialized later in bnxt_io_resume */
bnxt_ulp_irq_stop(bp);
bnxt_clear_int_mode(bp);
- err = bnxt_init_int_mode(bp);
- bnxt_ulp_irq_restart(bp, err);
}
reset_exit:
@@ -16959,20 +16981,25 @@ static void bnxt_io_resume(struct pci_dev *pdev)
int err;
netdev_info(bp->dev, "PCI Slot Resume\n");
+ rtnl_lock();
netdev_lock(netdev);
err = bnxt_hwrm_func_qcaps(bp);
if (!err) {
- if (netif_running(netdev))
+ if (netif_running(netdev)) {
err = bnxt_open(netdev);
- else
+ } else {
err = bnxt_reserve_rings(bp, true);
+ if (!err)
+ err = bnxt_init_int_mode(bp);
+ }
}
if (!err)
netif_device_attach(netdev);
netdev_unlock(netdev);
+ rtnl_unlock();
bnxt_ulp_start(bp, err);
if (!err)
bnxt_reenable_sriov(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 21726cf..bc8b3b7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2614,6 +2614,7 @@ struct bnxt {
#define BNXT_FW_RESET_STATE_POLL_FW 4
#define BNXT_FW_RESET_STATE_OPENING 5
#define BNXT_FW_RESET_STATE_POLL_FW_DOWN 6
+#define BNXT_FW_RESET_STATE_ABORT 7
u16 fw_reset_min_dsecs;
#define BNXT_DFLT_FW_RST_MIN_DSECS 20
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 5576e7c..a000d3f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -110,20 +110,30 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
}
}
- if (info->dest_buf) {
- if ((info->seg_start + off + len) <=
- BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
- memcpy(info->dest_buf + off, dma_buf, len);
- } else {
- rc = -ENOBUFS;
- break;
- }
- }
-
if (cmn_req->req_type ==
cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
info->dest_buf_size += len;
+ if (info->dest_buf) {
+ if ((info->seg_start + off + len) <=
+ BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
+ u16 copylen = min_t(u16, len,
+ info->dest_buf_size - off);
+
+ memcpy(info->dest_buf + off, dma_buf, copylen);
+ if (copylen < len)
+ break;
+ } else {
+ rc = -ENOBUFS;
+ if (cmn_req->req_type ==
+ cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+ kfree(info->dest_buf);
+ info->dest_buf = NULL;
+ }
+ break;
+ }
+ }
+
if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
break;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 48dd592..f5d490b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2062,6 +2062,17 @@ static int bnxt_get_regs_len(struct net_device *dev)
return reg_len;
}
+#define BNXT_PCIE_32B_ENTRY(start, end) \
+ { offsetof(struct pcie_ctx_hw_stats, start), \
+ offsetof(struct pcie_ctx_hw_stats, end) }
+
+static const struct {
+ u16 start;
+ u16 end;
+} bnxt_pcie_32b_entries[] = {
+ BNXT_PCIE_32B_ENTRY(pcie_ltssm_histogram[0], pcie_ltssm_histogram[3]),
+};
+
static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
void *_p)
{
@@ -2094,12 +2105,27 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
rc = hwrm_req_send(bp, req);
if (!rc) {
- __le64 *src = (__le64 *)hw_pcie_stats;
- u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN);
- int i;
+ u8 *dst = (u8 *)(_p + BNXT_PXP_REG_LEN);
+ u8 *src = (u8 *)hw_pcie_stats;
+ int i, j;
- for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
- dst[i] = le64_to_cpu(src[i]);
+ for (i = 0, j = 0; i < sizeof(*hw_pcie_stats); ) {
+ if (i >= bnxt_pcie_32b_entries[j].start &&
+ i <= bnxt_pcie_32b_entries[j].end) {
+ u32 *dst32 = (u32 *)(dst + i);
+
+ *dst32 = le32_to_cpu(*(__le32 *)(src + i));
+ i += 4;
+ if (i > bnxt_pcie_32b_entries[j].end &&
+ j < ARRAY_SIZE(bnxt_pcie_32b_entries) - 1)
+ j++;
+ } else {
+ u64 *dst64 = (u64 *)(dst + i);
+
+ *dst64 = le64_to_cpu(*(__le64 *)(src + i));
+ i += 8;
+ }
+ }
}
hwrm_req_drop(bp, req);
}
@@ -4991,6 +5017,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
if (!bp->num_tests || !BNXT_PF(bp))
return;
+ memset(buf, 0, sizeof(u64) * bp->num_tests);
if (etest->flags & ETH_TEST_FL_OFFLINE &&
bnxt_ulp_registered(bp->edev)) {
etest->flags |= ETH_TEST_FL_FAILED;
@@ -4998,7 +5025,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
return;
}
- memset(buf, 0, sizeof(u64) * bp->num_tests);
if (!netif_running(dev)) {
etest->flags |= ETH_TEST_FL_FAILED;
return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 2d4e19b..0669d43 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -794,6 +794,27 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
return HZ;
}
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp)
+{
+ struct bnxt_ptp_tx_req *txts_req;
+ u16 cons = ptp->txts_cons;
+
+ /* make sure ptp aux worker finished with
+ * possible BNXT_STATE_OPEN set
+ */
+ ptp_cancel_worker_sync(ptp->ptp_clock);
+
+ ptp->tx_avail = BNXT_MAX_TX_TS;
+ while (cons != ptp->txts_prod) {
+ txts_req = &ptp->txts_req[cons];
+ if (!IS_ERR_OR_NULL(txts_req->tx_skb))
+ dev_kfree_skb_any(txts_req->tx_skb);
+ cons = NEXT_TXTS(cons);
+ }
+ ptp->txts_cons = cons;
+ ptp_schedule_worker(ptp->ptp_clock, 0);
+}
+
int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod)
{
spin_lock_bh(&ptp->ptp_tx_lock);
@@ -1105,7 +1126,6 @@ int bnxt_ptp_init(struct bnxt *bp)
void bnxt_ptp_clear(struct bnxt *bp)
{
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
- int i;
if (!ptp)
return;
@@ -1117,12 +1137,5 @@ void bnxt_ptp_clear(struct bnxt *bp)
kfree(ptp->ptp_info.pin_config);
ptp->ptp_info.pin_config = NULL;
- for (i = 0; i < BNXT_MAX_TX_TS; i++) {
- if (ptp->txts_req[i].tx_skb) {
- dev_kfree_skb_any(ptp->txts_req[i].tx_skb);
- ptp->txts_req[i].tx_skb = NULL;
- }
- }
-
bnxt_unmap_ptp_regs(bp);
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index a95f05e..0481161 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -162,6 +162,7 @@ int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
void bnxt_ptp_reapply_pps(struct bnxt *bp);
int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp);
int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod);
void bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb, u16 prod);
int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index a8e930d..7564705 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -20,6 +20,7 @@
#include <asm/byteorder.h>
#include <linux/bitmap.h>
#include <linux/auxiliary_bus.h>
+#include <net/netdev_lock.h>
#include "bnxt_hsi.h"
#include "bnxt.h"
@@ -309,14 +310,12 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
if (!ulp->msix_requested)
return;
- netdev_lock(bp->dev);
- ops = rcu_dereference(ulp->ulp_ops);
+ ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
if (!ops || !ops->ulp_irq_stop)
return;
if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state))
reset = true;
ops->ulp_irq_stop(ulp->handle, reset);
- netdev_unlock(bp->dev);
}
}
@@ -335,8 +334,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
if (!ulp->msix_requested)
return;
- netdev_lock(bp->dev);
- ops = rcu_dereference(ulp->ulp_ops);
+ ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev);
if (!ops || !ops->ulp_irq_restart)
return;
@@ -348,7 +346,6 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
bnxt_fill_msix_vecs(bp, ent);
}
ops->ulp_irq_restart(ulp->handle, ent);
- netdev_unlock(bp->dev);
kfree(ent);
}
}
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1fe8ec37..e1e8bd2 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -997,22 +997,15 @@ static void macb_update_stats(struct macb *bp)
static int macb_halt_tx(struct macb *bp)
{
- unsigned long halt_time, timeout;
- u32 status;
+ u32 status;
macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
- timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
- do {
- halt_time = jiffies;
- status = macb_readl(bp, TSR);
- if (!(status & MACB_BIT(TGO)))
- return 0;
-
- udelay(250);
- } while (time_before(halt_time, timeout));
-
- return -ETIMEDOUT;
+ /* Poll TSR until TGO is cleared or timeout. */
+ return read_poll_timeout_atomic(macb_readl, status,
+ !(status & MACB_BIT(TGO)),
+ 250, MACB_HALT_TIMEOUT, false,
+ bp, TSR);
}
static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget)
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d88fbec..232e839 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -352,7 +352,7 @@ parse_eeprom (struct net_device *dev)
eth_hw_addr_set(dev, psrom->mac_addr);
if (np->chip_id == CHIP_IP1000A) {
- np->led_mode = psrom->led_mode;
+ np->led_mode = le16_to_cpu(psrom->led_mode);
return 0;
}
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 195dc6c..0e33e2e 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -335,7 +335,7 @@ typedef struct t_SROM {
u16 sub_system_id; /* 0x06 */
u16 pci_base_1; /* 0x08 (IP1000A only) */
u16 pci_base_2; /* 0x0a (IP1000A only) */
- u16 led_mode; /* 0x0c (IP1000A only) */
+ __le16 led_mode; /* 0x0c (IP1000A only) */
u16 reserved1[9]; /* 0x0e-0x1f */
u8 mac_addr[6]; /* 0x20-0x25 */
u8 reserved2[10]; /* 0x26-0x2f */
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 625245b..eba7324 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -67,6 +67,8 @@
#define TSNEP_TX_TYPE_XDP_NDO_MAP_PAGE (TSNEP_TX_TYPE_XDP_NDO | TSNEP_TX_TYPE_MAP_PAGE)
#define TSNEP_TX_TYPE_XDP (TSNEP_TX_TYPE_XDP_TX | TSNEP_TX_TYPE_XDP_NDO)
#define TSNEP_TX_TYPE_XSK BIT(12)
+#define TSNEP_TX_TYPE_TSTAMP BIT(13)
+#define TSNEP_TX_TYPE_SKB_TSTAMP (TSNEP_TX_TYPE_SKB | TSNEP_TX_TYPE_TSTAMP)
#define TSNEP_XDP_TX BIT(0)
#define TSNEP_XDP_REDIRECT BIT(1)
@@ -386,8 +388,7 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length,
if (entry->skb) {
entry->properties = length & TSNEP_DESC_LENGTH_MASK;
entry->properties |= TSNEP_DESC_INTERRUPT_FLAG;
- if ((entry->type & TSNEP_TX_TYPE_SKB) &&
- (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS))
+ if ((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP)
entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG;
/* toggle user flag to prevent false acknowledge
@@ -479,7 +480,8 @@ static int tsnep_tx_map_frag(skb_frag_t *frag, struct tsnep_tx_entry *entry,
return mapped;
}
-static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
+static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count,
+ bool do_tstamp)
{
struct device *dmadev = tx->adapter->dmadev;
struct tsnep_tx_entry *entry;
@@ -505,6 +507,9 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
entry->type = TSNEP_TX_TYPE_SKB_INLINE;
mapped = 0;
}
+
+ if (do_tstamp)
+ entry->type |= TSNEP_TX_TYPE_TSTAMP;
} else {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
@@ -558,11 +563,12 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count)
static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
struct tsnep_tx *tx)
{
- int count = 1;
struct tsnep_tx_entry *entry;
+ bool do_tstamp = false;
+ int count = 1;
int length;
- int i;
int retval;
+ int i;
if (skb_shinfo(skb)->nr_frags > 0)
count += skb_shinfo(skb)->nr_frags;
@@ -579,7 +585,13 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
entry = &tx->entry[tx->write];
entry->skb = skb;
- retval = tsnep_tx_map(skb, tx, count);
+ if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+ tx->adapter->hwtstamp_config.tx_type == HWTSTAMP_TX_ON) {
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+ do_tstamp = true;
+ }
+
+ retval = tsnep_tx_map(skb, tx, count, do_tstamp);
if (retval < 0) {
tsnep_tx_unmap(tx, tx->write, count);
dev_kfree_skb_any(entry->skb);
@@ -591,9 +603,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
}
length = retval;
- if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
- skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-
for (i = 0; i < count; i++)
tsnep_tx_activate(tx, (tx->write + i) & TSNEP_RING_MASK, length,
i == count - 1);
@@ -844,8 +853,7 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
length = tsnep_tx_unmap(tx, tx->read, count);
- if ((entry->type & TSNEP_TX_TYPE_SKB) &&
- (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) &&
+ if (((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) &&
(__le32_to_cpu(entry->desc_wb->properties) &
TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) {
struct skb_shared_hwtstamps hwtstamps;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 2106861..3ee52f4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1850,6 +1850,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
}
}
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+ int rx_ring_last)
+{
+ while (rx_ring_first != rx_ring_last) {
+ enetc_flip_rx_buff(rx_ring,
+ &rx_ring->rx_swbd[rx_ring_first]);
+ enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+ }
+}
+
static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
struct napi_struct *napi, int work_limit,
struct bpf_prog *prog)
@@ -1868,11 +1878,10 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
while (likely(rx_frm_cnt < work_limit)) {
union enetc_rx_bd *rxbd, *orig_rxbd;
- int orig_i, orig_cleaned_cnt;
struct xdp_buff xdp_buff;
struct sk_buff *skb;
+ int orig_i, err;
u32 bd_status;
- int err;
rxbd = enetc_rxbd(rx_ring, i);
bd_status = le32_to_cpu(rxbd->r.lstatus);
@@ -1887,7 +1896,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
break;
orig_rxbd = rxbd;
- orig_cleaned_cnt = cleaned_cnt;
orig_i = i;
enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
@@ -1915,15 +1923,21 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
rx_ring->stats.xdp_drops++;
break;
case XDP_PASS:
- rxbd = orig_rxbd;
- cleaned_cnt = orig_cleaned_cnt;
- i = orig_i;
-
- skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
- &i, &cleaned_cnt,
- ENETC_RXB_DMA_SIZE_XDP);
- if (unlikely(!skb))
+ skb = xdp_build_skb_from_buff(&xdp_buff);
+ /* Probably under memory pressure, stop NAPI */
+ if (unlikely(!skb)) {
+ enetc_xdp_drop(rx_ring, orig_i, i);
+ rx_ring->stats.xdp_drops++;
goto out;
+ }
+
+ enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+ /* These buffers are about to be owned by the stack.
+ * Update our buffer cache (the rx_swbd array elements)
+ * with their other page halves.
+ */
+ enetc_bulk_flip_buff(rx_ring, orig_i, i);
napi_gro_receive(napi, skb);
break;
@@ -1965,11 +1979,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
enetc_xdp_drop(rx_ring, orig_i, i);
rx_ring->stats.xdp_redirect_failures++;
} else {
- while (orig_i != i) {
- enetc_flip_rx_buff(rx_ring,
- &rx_ring->rx_swbd[orig_i]);
- enetc_bdr_idx_inc(rx_ring, &orig_i);
- }
+ enetc_bulk_flip_buff(rx_ring, orig_i, i);
xdp_redirect_frm_cnt++;
rx_ring->stats.xdp_redirect++;
}
@@ -3362,7 +3372,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
bdr->buffer_offset = ENETC_RXB_PAD;
priv->rx_ring[i] = bdr;
- err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+ err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+ ENETC_RXB_DMA_SIZE_XDP);
if (err)
goto free_vector;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index a86cfeb..17e9bdd 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -714,7 +714,12 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
txq->bd.cur = bdp;
/* Trigger transmission start */
- writel(0, txq->bd.reg_desc_active);
+ if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+ !readl(txq->bd.reg_desc_active) ||
+ !readl(txq->bd.reg_desc_active) ||
+ !readl(txq->bd.reg_desc_active) ||
+ !readl(txq->bd.reg_desc_active))
+ writel(0, txq->bd.reg_desc_active);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
index a0bcfb5..ff3295b 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -61,6 +61,8 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
return -EBUSY;
}
+ netif_device_detach(priv->netdev);
+
priv->reset_type = type;
set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
@@ -91,6 +93,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
return ret;
}
+ netif_device_attach(priv->netdev);
+
dev_info(&priv->pdev->dev, "reset done\n");
return ret;
}
@@ -117,16 +121,13 @@ void hbg_err_reset(struct hbg_priv *priv)
if (running)
dev_close(priv->netdev);
- hbg_reset(priv);
-
- /* in hbg_pci_err_detected(), we will detach first,
- * so we need to attach before open
- */
- if (!netif_device_present(priv->netdev))
- netif_device_attach(priv->netdev);
+ if (hbg_reset(priv))
+ goto err_unlock;
if (running)
dev_open(priv->netdev, NULL);
+
+err_unlock:
rtnl_unlock();
}
@@ -160,7 +161,6 @@ static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev)
pci_save_state(pdev);
hbg_err_reset(priv);
- netif_device_attach(netdev);
return PCI_ERS_RESULT_RECOVERED;
}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
index 8f1107b..5552005 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
@@ -317,6 +317,9 @@ static void hbg_update_stats_by_info(struct hbg_priv *priv,
const struct hbg_ethtool_stats *stats;
u32 i;
+ if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+ return;
+
for (i = 0; i < info_len; i++) {
stats = &info[i];
if (!stats->reg)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 09749e9..4e5d8bc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -61,7 +61,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "tm_qset",
.cmd = HNAE3_DBG_CMD_TM_QSET,
.dentry = HNS3_DBG_DENTRY_TM,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_1MB,
.init = hns3_dbg_common_file_init,
},
{
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 9ff797f..b03b8758 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -473,20 +473,14 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
writel(mask_en, tqp_vector->mask_addr);
}
-static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_enable(struct hns3_enet_tqp_vector *tqp_vector)
{
napi_enable(&tqp_vector->napi);
enable_irq(tqp_vector->vector_irq);
-
- /* enable vector */
- hns3_mask_vector_irq(tqp_vector, 1);
}
-static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_disable(struct hns3_enet_tqp_vector *tqp_vector)
{
- /* disable vector */
- hns3_mask_vector_irq(tqp_vector, 0);
-
disable_irq(tqp_vector->vector_irq);
napi_disable(&tqp_vector->napi);
cancel_work_sync(&tqp_vector->rx_group.dim.work);
@@ -707,11 +701,42 @@ static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
return 0;
}
+static void hns3_enable_irqs_and_tqps(struct net_device *netdev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+ struct hnae3_handle *h = priv->ae_handle;
+ u16 i;
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_irq_enable(&priv->tqp_vector[i]);
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_mask_vector_irq(&priv->tqp_vector[i], 1);
+
+ for (i = 0; i < h->kinfo.num_tqps; i++)
+ hns3_tqp_enable(h->kinfo.tqp[i]);
+}
+
+static void hns3_disable_irqs_and_tqps(struct net_device *netdev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+ struct hnae3_handle *h = priv->ae_handle;
+ u16 i;
+
+ for (i = 0; i < h->kinfo.num_tqps; i++)
+ hns3_tqp_disable(h->kinfo.tqp[i]);
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_mask_vector_irq(&priv->tqp_vector[i], 0);
+
+ for (i = 0; i < priv->vector_num; i++)
+ hns3_irq_disable(&priv->tqp_vector[i]);
+}
+
static int hns3_nic_net_up(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
- int i, j;
int ret;
ret = hns3_nic_reset_all_ring(h);
@@ -720,23 +745,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- /* enable the vectors */
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_enable(&priv->tqp_vector[i]);
-
- /* enable rcb */
- for (j = 0; j < h->kinfo.num_tqps; j++)
- hns3_tqp_enable(h->kinfo.tqp[j]);
+ hns3_enable_irqs_and_tqps(netdev);
/* start the ae_dev */
ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
if (ret) {
set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- while (j--)
- hns3_tqp_disable(h->kinfo.tqp[j]);
-
- for (j = i - 1; j >= 0; j--)
- hns3_vector_disable(&priv->tqp_vector[j]);
+ hns3_disable_irqs_and_tqps(netdev);
}
return ret;
@@ -823,17 +838,9 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
static void hns3_nic_net_down(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
- struct hnae3_handle *h = hns3_get_handle(netdev);
const struct hnae3_ae_ops *ops;
- int i;
- /* disable vectors */
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_disable(&priv->tqp_vector[i]);
-
- /* disable rcb */
- for (i = 0; i < h->kinfo.num_tqps; i++)
- hns3_tqp_disable(h->kinfo.tqp[i]);
+ hns3_disable_irqs_and_tqps(netdev);
/* stop ae_dev */
ops = priv->ae_handle->ae_algo->ops;
@@ -5864,8 +5871,6 @@ int hns3_set_channels(struct net_device *netdev,
void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
{
struct hns3_nic_priv *priv = netdev_priv(ndev);
- struct hnae3_handle *h = priv->ae_handle;
- int i;
if (!if_running)
return;
@@ -5876,11 +5881,7 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
netif_carrier_off(ndev);
netif_tx_disable(ndev);
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_disable(&priv->tqp_vector[i]);
-
- for (i = 0; i < h->kinfo.num_tqps; i++)
- hns3_tqp_disable(h->kinfo.tqp[i]);
+ hns3_disable_irqs_and_tqps(ndev);
/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
* during reset process, because driver may not be able
@@ -5896,7 +5897,6 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
{
struct hns3_nic_priv *priv = netdev_priv(ndev);
struct hnae3_handle *h = priv->ae_handle;
- int i;
if (!if_running)
return;
@@ -5912,11 +5912,7 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
- for (i = 0; i < priv->vector_num; i++)
- hns3_vector_enable(&priv->tqp_vector[i]);
-
- for (i = 0; i < h->kinfo.num_tqps; i++)
- hns3_tqp_enable(h->kinfo.tqp[i]);
+ hns3_enable_irqs_and_tqps(ndev);
netif_tx_wake_all_queues(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 59cc922..ec581d4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -440,6 +440,13 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
ptp->info.settime64 = hclge_ptp_settime;
ptp->info.n_alarm = 0;
+
+ spin_lock_init(&ptp->lock);
+ ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
+ ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+ ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+ hdev->ptp = ptp;
+
ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
if (IS_ERR(ptp->clock)) {
dev_err(&hdev->pdev->dev,
@@ -451,12 +458,6 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
return -ENODEV;
}
- spin_lock_init(&ptp->lock);
- ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
- ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
- ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
- hdev->ptp = ptp;
-
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 9ba7677..dada42e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1292,9 +1292,8 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
rtnl_unlock();
}
-static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+static int hclgevf_en_hw_strip_rxvtag_cmd(struct hclgevf_dev *hdev, bool enable)
{
- struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
struct hclge_vf_to_pf_msg send_msg;
hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1303,6 +1302,19 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
}
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ int ret;
+
+ ret = hclgevf_en_hw_strip_rxvtag_cmd(hdev, enable);
+ if (ret)
+ return ret;
+
+ hdev->rxvtag_strip_en = enable;
+ return 0;
+}
+
static int hclgevf_reset_tqp(struct hnae3_handle *handle)
{
#define HCLGEVF_RESET_ALL_QUEUE_DONE 1U
@@ -2204,12 +2216,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
tc_valid, tc_size);
}
-static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
+static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev,
+ bool rxvtag_strip_en)
{
struct hnae3_handle *nic = &hdev->nic;
int ret;
- ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+ ret = hclgevf_en_hw_strip_rxvtag(nic, rxvtag_strip_en);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed to enable rx vlan offload, ret = %d\n", ret);
@@ -2879,7 +2892,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
if (ret)
return ret;
- ret = hclgevf_init_vlan_config(hdev);
+ ret = hclgevf_init_vlan_config(hdev, hdev->rxvtag_strip_en);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed(%d) to initialize VLAN config\n", ret);
@@ -2994,7 +3007,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
goto err_config;
}
- ret = hclgevf_init_vlan_config(hdev);
+ ret = hclgevf_init_vlan_config(hdev, true);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed(%d) to initialize VLAN config\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index cccef32..0208425 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -253,6 +253,7 @@ struct hclgevf_dev {
int *vector_irq;
bool gro_en;
+ bool rxvtag_strip_en;
unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 01a08cf..66e0700 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -1,7 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
// SPDX-FileCopyrightText: Copyright Red Hat
-#include <linux/bitfield.h>
#include <linux/cleanup.h>
#include <linux/mutex.h>
#include <linux/pci.h>
@@ -14,32 +13,16 @@
static DEFINE_XARRAY(ice_adapters);
static DEFINE_MUTEX(ice_adapters_mutex);
-/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
-#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
-#define INDEX_FIELD_DEV GENMASK(31, 16)
-#define INDEX_FIELD_BUS GENMASK(12, 5)
-#define INDEX_FIELD_SLOT GENMASK(4, 0)
-
-static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+static unsigned long ice_adapter_index(u64 dsn)
{
- unsigned int domain = pci_domain_nr(pdev->bus);
-
- WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
-
- switch (pdev->device) {
- case ICE_DEV_ID_E825C_BACKPLANE:
- case ICE_DEV_ID_E825C_QSFP:
- case ICE_DEV_ID_E825C_SFP:
- case ICE_DEV_ID_E825C_SGMII:
- return FIELD_PREP(INDEX_FIELD_DEV, pdev->device);
- default:
- return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
- FIELD_PREP(INDEX_FIELD_BUS, pdev->bus->number) |
- FIELD_PREP(INDEX_FIELD_SLOT, PCI_SLOT(pdev->devfn));
- }
+#if BITS_PER_LONG == 64
+ return dsn;
+#else
+ return (u32)dsn ^ (u32)(dsn >> 32);
+#endif
}
-static struct ice_adapter *ice_adapter_new(void)
+static struct ice_adapter *ice_adapter_new(u64 dsn)
{
struct ice_adapter *adapter;
@@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void)
if (!adapter)
return NULL;
+ adapter->device_serial_number = dsn;
spin_lock_init(&adapter->ptp_gltsyn_time_lock);
refcount_set(&adapter->refcount, 1);
@@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter)
* Return: Pointer to ice_adapter on success.
* ERR_PTR() on error. -ENOMEM is the only possible error.
*/
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
{
- unsigned long index = ice_adapter_index(pdev);
+ u64 dsn = pci_get_dsn(pdev);
struct ice_adapter *adapter;
+ unsigned long index;
int err;
+ index = ice_adapter_index(dsn);
scoped_guard(mutex, &ice_adapters_mutex) {
err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
if (err == -EBUSY) {
adapter = xa_load(&ice_adapters, index);
refcount_inc(&adapter->refcount);
+ WARN_ON_ONCE(adapter->device_serial_number != dsn);
return adapter;
}
if (err)
return ERR_PTR(err);
- adapter = ice_adapter_new();
+ adapter = ice_adapter_new(dsn);
if (!adapter)
return ERR_PTR(-ENOMEM);
xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
*
* Context: Process, may sleep.
*/
-void ice_adapter_put(const struct pci_dev *pdev)
+void ice_adapter_put(struct pci_dev *pdev)
{
- unsigned long index = ice_adapter_index(pdev);
+ u64 dsn = pci_get_dsn(pdev);
struct ice_adapter *adapter;
+ unsigned long index;
+ index = ice_adapter_index(dsn);
scoped_guard(mutex, &ice_adapters_mutex) {
adapter = xa_load(&ice_adapters, index);
if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index e233225..ac15c0d 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -32,6 +32,7 @@ struct ice_port_list {
* @refcount: Reference count. struct ice_pf objects hold the references.
* @ctrl_pf: Control PF of the adapter
* @ports: Ports list
+ * @device_serial_number: DSN cached for collision detection on 32bit systems
*/
struct ice_adapter {
refcount_t refcount;
@@ -40,9 +41,10 @@ struct ice_adapter {
struct ice_pf *ctrl_pf;
struct ice_port_list ports;
+ u64 device_serial_number;
};
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
-void ice_adapter_put(const struct pci_dev *pdev);
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
+void ice_adapter_put(struct pci_dev *pdev);
#endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 69d5b1a..59323c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2345,15 +2345,15 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
- if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
} else {
ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
- }
- if (hw->mac_type != ICE_MAC_GENERIC_3K_E825)
- desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ if (hw->mac_type == ICE_MAC_E810 ||
+ hw->mac_type == ICE_MAC_GENERIC)
+ desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+ }
status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 2237101..2410aee 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1321,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
*/
if (!primary_lag) {
lag->primary = true;
+ if (!ice_is_switchdev_running(lag->pf))
+ return;
+
/* Configure primary's SWID to be shared */
ice_lag_primary_swid(lag, true);
primary_lag = lag;
} else {
u16 swid;
+ if (!ice_is_switchdev_running(primary_lag->pf))
+ return;
+
swid = primary_lag->pf->hw.port_info->sw_id;
ice_lag_set_swid(swid, lag, true);
ice_lag_add_prune_list(primary_lag, lag->pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 7c3006e..6446d0f 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -4275,7 +4275,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg)
}
ice_vfhw_mac_add(vf, &al->list[i]);
- vf->num_mac++;
break;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 7752920..1cca9b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -2097,6 +2097,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
pf = vf->pf;
dev = ice_pf_to_dev(pf);
vf_vsi = ice_get_vf_vsi(vf);
+ if (!vf_vsi) {
+ dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+ goto err_exit;
+ }
#define ICE_VF_MAX_FDIR_FILTERS 128
if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544fa..70dbf80f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -143,6 +143,7 @@ enum idpf_vport_state {
* @vport_id: Vport identifier
* @link_speed_mbps: Link speed in mbps
* @vport_idx: Relative vport index
+ * @max_tx_hdr_size: Max header length hardware can support
* @state: See enum idpf_vport_state
* @netstats: Packet and byte stats
* @stats_lock: Lock to protect stats update
@@ -153,6 +154,7 @@ struct idpf_netdev_priv {
u32 vport_id;
u32 link_speed_mbps;
u16 vport_idx;
+ u16 max_tx_hdr_size;
enum idpf_vport_state state;
struct rtnl_link_stats64 netstats;
spinlock_t stats_lock;
@@ -629,13 +631,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4 |\
VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6)
-#define IDPF_CAP_RX_CSUM_L4V4 (\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP)
+#define IDPF_CAP_TX_CSUM_L4V4 (\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP |\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP)
-#define IDPF_CAP_RX_CSUM_L4V6 (\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
+#define IDPF_CAP_TX_CSUM_L4V6 (\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP |\
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP)
#define IDPF_CAP_RX_CSUM (\
VIRTCHNL2_CAP_RX_CSUM_L3_IPV4 |\
@@ -644,11 +646,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP |\
VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
-#define IDPF_CAP_SCTP_CSUM (\
+#define IDPF_CAP_TX_SCTP_CSUM (\
VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP |\
- VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP |\
- VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP)
+ VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP)
#define IDPF_CAP_TUNNEL_TX_CSUM (\
VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL |\
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index aa755de..3a033ce 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -703,8 +703,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
{
struct idpf_adapter *adapter = vport->adapter;
struct idpf_vport_config *vport_config;
+ netdev_features_t other_offloads = 0;
+ netdev_features_t csum_offloads = 0;
+ netdev_features_t tso_offloads = 0;
netdev_features_t dflt_features;
- netdev_features_t offloads = 0;
struct idpf_netdev_priv *np;
struct net_device *netdev;
u16 idx = vport->idx;
@@ -721,6 +723,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
np->vport = vport;
np->vport_idx = vport->idx;
np->vport_id = vport->vport_id;
+ np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
vport->netdev = netdev;
return idpf_init_mac_addr(vport, netdev);
@@ -738,6 +741,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
np->adapter = adapter;
np->vport_idx = vport->idx;
np->vport_id = vport->vport_id;
+ np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
spin_lock_init(&np->stats_lock);
@@ -766,53 +770,32 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
dflt_features |= NETIF_F_RXHASH;
- if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4))
- dflt_features |= NETIF_F_IP_CSUM;
- if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6))
- dflt_features |= NETIF_F_IPV6_CSUM;
+ if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4))
+ csum_offloads |= NETIF_F_IP_CSUM;
+ if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6))
+ csum_offloads |= NETIF_F_IPV6_CSUM;
if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM))
- dflt_features |= NETIF_F_RXCSUM;
- if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM))
- dflt_features |= NETIF_F_SCTP_CRC;
+ csum_offloads |= NETIF_F_RXCSUM;
+ if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM))
+ csum_offloads |= NETIF_F_SCTP_CRC;
if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP))
- dflt_features |= NETIF_F_TSO;
+ tso_offloads |= NETIF_F_TSO;
if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP))
- dflt_features |= NETIF_F_TSO6;
+ tso_offloads |= NETIF_F_TSO6;
if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS,
VIRTCHNL2_CAP_SEG_IPV4_UDP |
VIRTCHNL2_CAP_SEG_IPV6_UDP))
- dflt_features |= NETIF_F_GSO_UDP_L4;
+ tso_offloads |= NETIF_F_GSO_UDP_L4;
if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC))
- offloads |= NETIF_F_GRO_HW;
- /* advertise to stack only if offloads for encapsulated packets is
- * supported
- */
- if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS,
- VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) {
- offloads |= NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_PARTIAL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM |
- NETIF_F_GSO_IPXIP4 |
- NETIF_F_GSO_IPXIP6 |
- 0;
-
- if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS,
- IDPF_CAP_TUNNEL_TX_CSUM))
- netdev->gso_partial_features |=
- NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
- netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
- offloads |= NETIF_F_TSO_MANGLEID;
- }
+ other_offloads |= NETIF_F_GRO_HW;
if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK))
- offloads |= NETIF_F_LOOPBACK;
+ other_offloads |= NETIF_F_LOOPBACK;
- netdev->features |= dflt_features;
- netdev->hw_features |= dflt_features | offloads;
- netdev->hw_enc_features |= dflt_features | offloads;
+ netdev->features |= dflt_features | csum_offloads | tso_offloads;
+ netdev->hw_features |= netdev->features | other_offloads;
+ netdev->vlan_features |= netdev->features | other_offloads;
+ netdev->hw_enc_features |= dflt_features | other_offloads;
idpf_set_ethtool_ops(netdev);
netif_set_affinity_auto(netdev);
SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
@@ -1132,11 +1115,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
num_max_q = max(max_q->max_txq, max_q->max_rxq);
vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL);
- if (!vport->q_vector_idxs) {
- kfree(vport);
+ if (!vport->q_vector_idxs)
+ goto free_vport;
- return NULL;
- }
idpf_vport_init(vport, max_q);
/* This alloc is done separate from the LUT because it's not strictly
@@ -1146,11 +1127,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
*/
rss_data = &adapter->vport_config[idx]->user_config.rss_data;
rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL);
- if (!rss_data->rss_key) {
- kfree(vport);
+ if (!rss_data->rss_key)
+ goto free_vector_idxs;
- return NULL;
- }
/* Initialize default rss key */
netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size);
@@ -1163,6 +1142,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
adapter->next_vport = idpf_get_free_slot(adapter);
return vport;
+
+free_vector_idxs:
+ kfree(vport->q_vector_idxs);
+free_vport:
+ kfree(vport);
+
+ return NULL;
}
/**
@@ -2219,8 +2205,8 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
struct net_device *netdev,
netdev_features_t features)
{
- struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
- struct idpf_adapter *adapter = vport->adapter;
+ struct idpf_netdev_priv *np = netdev_priv(netdev);
+ u16 max_tx_hdr_size = np->max_tx_hdr_size;
size_t len;
/* No point in doing any of this if neither checksum nor GSO are
@@ -2243,7 +2229,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
goto unsupported;
len = skb_network_header_len(skb);
- if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+ if (unlikely(len > max_tx_hdr_size))
goto unsupported;
if (!skb->encapsulation)
@@ -2256,7 +2242,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
/* IPLEN can support at most 127 dwords */
len = skb_inner_network_header_len(skb);
- if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+ if (unlikely(len > max_tx_hdr_size))
goto unsupported;
/* No need to validate L4LEN as TCP is the only protocol with a
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index bec4a02..b357130 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -89,6 +89,7 @@ static void idpf_shutdown(struct pci_dev *pdev)
{
struct idpf_adapter *adapter = pci_get_drvdata(pdev);
+ cancel_delayed_work_sync(&adapter->serv_task);
cancel_delayed_work_sync(&adapter->vc_event_task);
idpf_vc_core_deinit(adapter);
idpf_deinit_dflt_mbx(adapter);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index bdf52ce..2d5f5c9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -4025,6 +4025,14 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
return budget;
}
+ /* Switch to poll mode in the tear-down path after sending disable
+ * queues virtchnl message, as the interrupts will be disabled after
+ * that.
+ */
+ if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
+ q_vector->tx[0])))
+ return budget;
+
work_done = min_t(int, work_done, budget - 1);
/* Exit the polling mode, but don't re-enable interrupts if stack might
@@ -4035,15 +4043,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
else
idpf_vport_intr_set_wb_on_itr(q_vector);
- /* Switch to poll mode in the tear-down path after sending disable
- * queues virtchnl message, as the interrupts will be disabled after
- * that
- */
- if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
- q_vector->tx[0])))
- return budget;
- else
- return work_done;
+ return work_done;
}
/**
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 612ed26..efc7b30 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -1290,6 +1290,8 @@ void igc_ptp_reset(struct igc_adapter *adapter)
/* reset the tstamp_config */
igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
+ mutex_lock(&adapter->ptm_lock);
+
spin_lock_irqsave(&adapter->tmreg_lock, flags);
switch (adapter->hw.mac.type) {
@@ -1308,7 +1310,6 @@ void igc_ptp_reset(struct igc_adapter *adapter)
if (!igc_is_crosststamp_supported(adapter))
break;
- mutex_lock(&adapter->ptm_lock);
wr32(IGC_PCIE_DIG_DELAY, IGC_PCIE_DIG_DELAY_DEFAULT);
wr32(IGC_PCIE_PHY_DELAY, IGC_PCIE_PHY_DELAY_DEFAULT);
@@ -1332,7 +1333,6 @@ void igc_ptp_reset(struct igc_adapter *adapter)
netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
igc_ptm_reset(hw);
- mutex_unlock(&adapter->ptm_lock);
break;
default:
/* No work to do. */
@@ -1349,5 +1349,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
out:
spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+ mutex_unlock(&adapter->ptm_lock);
+
wrfl();
}
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 0a679e9..24499bb 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1223,7 +1223,7 @@ static void octep_hb_timeout_task(struct work_struct *work)
miss_cnt);
rtnl_lock();
if (netif_running(oct->netdev))
- octep_stop(oct->netdev);
+ dev_close(oct->netdev);
rtnl_unlock();
}
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 18c922d..ccb69bc 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -835,7 +835,9 @@ static void octep_vf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
struct octep_vf_device *oct = netdev_priv(netdev);
netdev_hold(netdev, NULL, GFP_ATOMIC);
- schedule_work(&oct->tx_timeout_task);
+ if (!schedule_work(&oct->tx_timeout_task))
+ netdev_put(netdev, NULL);
+
}
static int octep_vf_set_mac(struct net_device *netdev, void *p)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 0b27a69..9719935 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -717,6 +717,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat)
if (!is_lmac_valid(cgx, lmac_id))
return -ENODEV;
+
+ /* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */
+ if (idx >= CGX_RX_STAT_GLOBAL_INDEX)
+ lmac_id = 0;
+
*rx_stat = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8));
return 0;
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 7fa98ae..4a3370a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -13,19 +13,26 @@
/* RVU LMTST */
#define LMT_TBL_OP_READ 0
#define LMT_TBL_OP_WRITE 1
-#define LMT_MAP_TABLE_SIZE (128 * 1024)
#define LMT_MAPTBL_ENTRY_SIZE 16
+#define LMT_MAX_VFS 256
+
+#define LMT_MAP_ENTRY_ENA BIT_ULL(20)
+#define LMT_MAP_ENTRY_LINES GENMASK_ULL(18, 16)
/* Function to perform operations (read/write) on lmtst map table */
static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
int lmt_tbl_op)
{
void __iomem *lmt_map_base;
- u64 tbl_base;
+ u64 tbl_base, cfg;
+ int pfs, vfs;
tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+ cfg = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+ vfs = 1 << (cfg & 0xF);
+ pfs = 1 << ((cfg >> 4) & 0x7);
- lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+ lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE);
if (!lmt_map_base) {
dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
return -ENOMEM;
@@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
*val = readq(lmt_map_base + index);
} else {
writeq((*val), (lmt_map_base + index));
+
+ cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1);
+ /* 2048 LMTLINES */
+ cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6);
+
+ writeq(cfg, (lmt_map_base + (index + 8)));
+
/* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
* changes effective. Write 1 for flush and read is being used as a
* barrier and sets up a data dependency. Write to 0 after a write
@@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
#define LMT_MAP_TBL_W1_OFF 8
static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
{
- return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+ return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) +
(pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
}
@@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
mutex_lock(&rvu->rsrc_lock);
rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
- pf = rvu_get_pf(pcifunc) & 0x1F;
+ pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK;
val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index a1f9ec0..c827da6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -553,6 +553,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
u64 lmt_addr, val, tbl_base;
int pf, vf, num_vfs, hw_vfs;
void __iomem *lmt_map_base;
+ int apr_pfs, apr_vfs;
int buf_size = 10240;
size_t off = 0;
int index = 0;
@@ -568,8 +569,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
return -ENOMEM;
tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+ val = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+ apr_vfs = 1 << (val & 0xF);
+ apr_pfs = 1 << ((val >> 4) & 0x7);
- lmt_map_base = ioremap_wc(tbl_base, 128 * 1024);
+ lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs *
+ LMT_MAPTBL_ENTRY_SIZE);
if (!lmt_map_base) {
dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
kfree(buf);
@@ -591,7 +596,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d \t\t\t",
pf);
- index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE;
+ index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE;
off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t",
(tbl_base + index));
lmt_addr = readq(lmt_map_base + index);
@@ -604,7 +609,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
/* Reading num of VFs per PF */
rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs);
for (vf = 0; vf < num_vfs; vf++) {
- index = (pf * rvu->hw->total_vfs * 16) +
+ index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) +
((vf + 1) * LMT_MAPTBL_ENTRY_SIZE);
off += scnprintf(&buf[off], buf_size - 1 - off,
"PF%d:VF%d \t\t", pf, vf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
index f3b9daf..4c7e0f3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
@@ -531,7 +531,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf,
if (sw_tx_sc->encrypt)
sectag_tci |= (MCS_TCI_E | MCS_TCI_C);
- policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu);
+ policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU,
+ pfvf->netdev->mtu + OTX2_ETH_HLEN);
/* Write SecTag excluding AN bits(1..0) */
policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2);
policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 1e88422..d6b4b74 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -356,6 +356,7 @@ struct otx2_flow_config {
struct list_head flow_list_tc;
u8 ucast_flt_cnt;
bool ntuple;
+ u16 ntuple_cnt;
};
struct dev_hw_ops {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 33ec9a7..e13ae548 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -41,6 +41,7 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
if (!pfvf->flow_cfg)
return 0;
+ pfvf->flow_cfg->ntuple_cnt = ctx->val.vu16;
otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 010385b..45b8c92 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -315,7 +315,7 @@ static void otx2_get_pauseparam(struct net_device *netdev,
struct otx2_nic *pfvf = netdev_priv(netdev);
struct cgx_pause_frm_cfg *req, *rsp;
- if (is_otx2_lbkvf(pfvf->pdev))
+ if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
return;
mutex_lock(&pfvf->mbox.lock);
@@ -347,7 +347,7 @@ static int otx2_set_pauseparam(struct net_device *netdev,
if (pause->autoneg)
return -EOPNOTSUPP;
- if (is_otx2_lbkvf(pfvf->pdev))
+ if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
return -EOPNOTSUPP;
if (pause->rx_pause)
@@ -941,8 +941,8 @@ static u32 otx2_get_link(struct net_device *netdev)
{
struct otx2_nic *pfvf = netdev_priv(netdev);
- /* LBK link is internal and always UP */
- if (is_otx2_lbkvf(pfvf->pdev))
+ /* LBK and SDP links are internal and always UP */
+ if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev))
return 1;
return pfvf->linfo.link_up;
}
@@ -1413,7 +1413,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
{
struct otx2_nic *pfvf = netdev_priv(netdev);
- if (is_otx2_lbkvf(pfvf->pdev)) {
+ if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) {
cmd->base.duplex = DUPLEX_FULL;
cmd->base.speed = SPEED_100000;
} else {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 47bfd1f..64c6d916 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -247,7 +247,7 @@ int otx2_mcam_entry_init(struct otx2_nic *pfvf)
mutex_unlock(&pfvf->mbox.lock);
/* Allocate entries for Ntuple filters */
- count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+ count = otx2_alloc_mcam_entries(pfvf, flow_cfg->ntuple_cnt);
if (count <= 0) {
otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
return 0;
@@ -307,6 +307,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc);
pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS;
+ pf->flow_cfg->ntuple_cnt = OTX2_DEFAULT_FLOWCOUNT;
/* Allocate bare minimum number of MCAM entries needed for
* unicast and ntuple filters.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 7ef3ba4..9b28be4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -729,9 +729,12 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
}
#ifdef CONFIG_DCB
- err = otx2_dcbnl_set_ops(netdev);
- if (err)
- goto err_free_zc_bmap;
+ /* Priority flow control is not supported for LBK and SDP vf(s) */
+ if (!(is_otx2_lbkvf(vf->pdev) || is_otx2_sdp_rep(vf->pdev))) {
+ err = otx2_dcbnl_set_ops(netdev);
+ if (err)
+ goto err_free_zc_bmap;
+ }
#endif
otx2_qos_init(vf, qos_txqs);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index bdb98c9..6c92072 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -269,12 +269,8 @@ static const char * const mtk_clks_source_name[] = {
"ethwarp_wocpu2",
"ethwarp_wocpu1",
"ethwarp_wocpu0",
- "top_usxgmii0_sel",
- "top_usxgmii1_sel",
"top_sgm0_sel",
"top_sgm1_sel",
- "top_xfi_phy0_xtal_sel",
- "top_xfi_phy1_xtal_sel",
"top_eth_gmii_sel",
"top_eth_refck_50m_sel",
"top_eth_sys_200m_sel",
@@ -2252,14 +2248,18 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
ring->data[idx] = new_data;
rxd->rxd1 = (unsigned int)dma_addr;
release_desc:
+ if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+ if (unlikely(dma_addr == DMA_MAPPING_ERROR))
+ addr64 = FIELD_GET(RX_DMA_ADDR64_MASK,
+ rxd->rxd2);
+ else
+ addr64 = RX_DMA_PREP_ADDR64(dma_addr);
+ }
+
if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
rxd->rxd2 = RX_DMA_LSO;
else
- rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
-
- if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
- likely(dma_addr != DMA_MAPPING_ERROR))
- rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+ rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size) | addr64;
ring->calc_idx = idx;
done++;
@@ -3186,11 +3186,19 @@ static int mtk_dma_init(struct mtk_eth *eth)
static void mtk_dma_free(struct mtk_eth *eth)
{
const struct mtk_soc_data *soc = eth->soc;
- int i;
+ int i, j, txqs = 1;
- for (i = 0; i < MTK_MAX_DEVS; i++)
- if (eth->netdev[i])
- netdev_reset_queue(eth->netdev[i]);
+ if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+ txqs = MTK_QDMA_NUM_QUEUES;
+
+ for (i = 0; i < MTK_MAX_DEVS; i++) {
+ if (!eth->netdev[i])
+ continue;
+
+ for (j = 0; j < txqs; j++)
+ netdev_tx_reset_subqueue(eth->netdev[i], j);
+ }
+
if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
dma_free_coherent(eth->dma_dev,
MTK_QDMA_RING_SIZE * soc->tx.desc_size,
@@ -3465,9 +3473,6 @@ static int mtk_open(struct net_device *dev)
}
mtk_gdm_config(eth, target_mac->id, gdm_config);
}
- /* Reset and enable PSE */
- mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
- mtk_w32(eth, 0, MTK_RST_GL);
napi_enable(ð->tx_napi);
napi_enable(ð->rx_napi);
@@ -4043,11 +4048,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
if (mtk_is_netsys_v3_or_greater(eth)) {
- /* PSE should not drop port1, port8 and port9 packets */
- mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+ /* PSE dummy page mechanism */
+ mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+ PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+ /* PSE free buffer drop threshold */
+ mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+ /* PSE should not drop port8, port9 and port13 packets from
+ * WDMA Tx
+ */
+ mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+ /* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+ * ring full
+ */
+ mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+ mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+ mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
/* GDM and CDM Threshold */
- mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+ mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
/* Disable GDM1 RX CRC stripping */
@@ -4064,7 +4085,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
- mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+ mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
/* PSE Free Queue Flow Control */
mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
@@ -4727,7 +4748,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
}
if (mtk_is_netsys_v3_or_greater(mac->hw) &&
- MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) &&
+ MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW) &&
id == MTK_GMAC1_ID) {
mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
MAC_SYM_PAUSE |
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 3970964..88ef2e9 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -151,7 +151,15 @@
#define PSE_FQFC_CFG1 0x100
#define PSE_FQFC_CFG2 0x104
#define PSE_DROP_CFG 0x108
-#define PSE_PPE0_DROP 0x110
+#define PSE_PPE_DROP(x) (0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ 0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x) BIT(16 + (x))
+#define DUMMY_PAGE_THR 0x1
/* PSE Input Queue Reservation Register*/
#define PSE_IQ_REV(x) (0x140 + (((x) - 1) << 2))
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 76f202d..b175119 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1163,6 +1163,7 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
struct net_device *ndev = priv->ndev;
unsigned int head = ring->head;
unsigned int entry = ring->tail;
+ unsigned long flags;
while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
ret = mtk_star_tx_complete_one(priv);
@@ -1182,9 +1183,9 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
netif_wake_queue(ndev);
if (napi_complete(napi)) {
- spin_lock(&priv->lock);
+ spin_lock_irqsave(&priv->lock, flags);
mtk_star_enable_dma_irq(priv, false, true);
- spin_unlock(&priv->lock);
+ spin_unlock_irqrestore(&priv->lock, flags);
}
return 0;
@@ -1341,16 +1342,16 @@ static int mtk_star_rx(struct mtk_star_priv *priv, int budget)
static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
{
struct mtk_star_priv *priv;
+ unsigned long flags;
int work_done = 0;
priv = container_of(napi, struct mtk_star_priv, rx_napi);
work_done = mtk_star_rx(priv, budget);
- if (work_done < budget) {
- napi_complete_done(napi, work_done);
- spin_lock(&priv->lock);
+ if (work_done < budget && napi_complete_done(napi, work_done)) {
+ spin_lock_irqsave(&priv->lock, flags);
mtk_star_enable_dma_irq(priv, true, false);
- spin_unlock(&priv->lock);
+ spin_unlock_irqrestore(&priv->lock, flags);
}
return work_done;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 532c7fa..dbd9482 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -176,6 +176,7 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
priv = ptpsq->txqsq.priv;
+ rtnl_lock();
mutex_lock(&priv->state_lock);
chs = &priv->channels;
netdev = priv->netdev;
@@ -183,22 +184,19 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
carrier_ok = netif_carrier_ok(netdev);
netif_carrier_off(netdev);
- rtnl_lock();
mlx5e_deactivate_priv_channels(priv);
- rtnl_unlock();
mlx5e_ptp_close(chs->ptp);
err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
- rtnl_lock();
mlx5e_activate_priv_channels(priv);
- rtnl_unlock();
/* return carrier back if needed */
if (carrier_ok)
netif_carrier_on(netdev);
mutex_unlock(&priv->state_lock);
+ rtnl_unlock();
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index 5c762a7..7a18a46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -165,9 +165,6 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
struct flow_match_enc_keyid enc_keyid;
void *misc_c, *misc_v;
- misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-
if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
return 0;
@@ -182,6 +179,30 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
if (err)
return err;
+
+ /* We can't mix custom tunnel headers with symbolic ones and we
+ * don't have a symbolic field name for GBP, so we use custom
+ * tunnel headers in this case. We need hardware support to
+ * match on custom tunnel headers, but we already know it's
+ * supported because the previous call successfully checked for
+ * that.
+ */
+ misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters_5);
+ misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters_5);
+
+ /* Shift by 8 to account for the reserved bits in the vxlan
+ * header after the VNI.
+ */
+ MLX5_SET(fte_match_set_misc5, misc_c, tunnel_header_1,
+ be32_to_cpu(enc_keyid.mask->keyid) << 8);
+ MLX5_SET(fte_match_set_misc5, misc_v, tunnel_header_1,
+ be32_to_cpu(enc_keyid.key->keyid) << 8);
+
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
+
+ return 0;
}
/* match on VNI is required */
@@ -195,6 +216,11 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
return -EOPNOTSUPP;
}
+ misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters);
+ misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
+
MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
be32_to_cpu(enc_keyid.mask->keyid));
MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3506024..9bd166f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4349,6 +4349,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev
if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n");
+ features &= ~NETIF_F_HW_MACSEC;
+ if (netdev->features & NETIF_F_HW_MACSEC)
+ netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n");
+
return features;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9ba9960..f1d908f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1750,9 +1750,6 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
!list_is_first(&attr->list, &flow->attrs))
return 0;
- if (flow_flag_test(flow, SLOW))
- return 0;
-
esw_attr = attr->esw_attr;
if (!esw_attr->split_count ||
esw_attr->split_count == esw_attr->out_count - 1)
@@ -1766,7 +1763,7 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
/* external dest with encap is considered as internal by firmware */
if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
- !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+ !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
ext_dest = true;
else
int_dest = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a6a8eea..0e3a977 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3533,7 +3533,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
int err;
mutex_init(&esw->offloads.termtbl_mutex);
- mlx5_rdma_enable_roce(esw->dev);
+ err = mlx5_rdma_enable_roce(esw->dev);
+ if (err)
+ goto err_roce;
err = mlx5_esw_host_number_init(esw);
if (err)
@@ -3594,6 +3596,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
esw_offloads_metadata_uninit(esw);
err_metadata:
mlx5_rdma_disable_roce(esw->dev);
+err_roce:
mutex_destroy(&esw->offloads.termtbl_mutex);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index eb3bd9c..ca9ecec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -637,10 +637,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
bool use_l4_type;
int err;
- ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
- if (!ttc)
- return ERR_PTR(-ENOMEM);
-
switch (params->ns_type) {
case MLX5_FLOW_NAMESPACE_PORT_SEL:
use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -654,7 +650,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
return ERR_PTR(-EINVAL);
}
+ ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+ if (!ttc)
+ return ERR_PTR(-ENOMEM);
+
ns = mlx5_get_flow_namespace(dev, params->ns_type);
+ if (!ns) {
+ kvfree(ttc);
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
&inner_ttc_groups[TTC_GROUPS_DEFAULT];
@@ -710,10 +715,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
bool use_l4_type;
int err;
- ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
- if (!ttc)
- return ERR_PTR(-ENOMEM);
-
switch (params->ns_type) {
case MLX5_FLOW_NAMESPACE_PORT_SEL:
use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -727,7 +728,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
return ERR_PTR(-EINVAL);
}
+ ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+ if (!ttc)
+ return ERR_PTR(-ENOMEM);
+
ns = mlx5_get_flow_namespace(dev, params->ns_type);
+ if (!ns) {
+ kvfree(ttc);
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
&ttc_groups[TTC_GROUPS_DEFAULT];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index a42f6cd..5c552b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -118,8 +118,8 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
{
+ u8 mac[ETH_ALEN] = {};
union ib_gid gid;
- u8 mac[ETH_ALEN];
mlx5_rdma_make_default_gid(dev, &gid);
return mlx5_core_roce_gid_set(dev, 0,
@@ -140,17 +140,17 @@ void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
mlx5_nic_vport_disable_roce(dev);
}
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
{
int err;
if (!MLX5_CAP_GEN(dev, roce))
- return;
+ return 0;
err = mlx5_nic_vport_enable_roce(dev);
if (err) {
mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
- return;
+ return err;
}
err = mlx5_rdma_add_roce_addr(dev);
@@ -165,10 +165,11 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
goto del_roce_addr;
}
- return;
+ return err;
del_roce_addr:
mlx5_rdma_del_roce_addr(dev);
disable_roce:
mlx5_nic_vport_disable_roce(dev);
+ return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
index 750cff2..3d9e76c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -8,12 +8,12 @@
#ifdef CONFIG_MLX5_ESWITCH
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
#else /* CONFIG_MLX5_ESWITCH */
-static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { return 0; }
static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
#endif /* CONFIG_MLX5_ESWITCH */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 464821d..a203383 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3014,6 +3014,9 @@ static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
.rif = rif,
};
+ if (!mlxsw_sp_dev_lower_is_port(mlxsw_sp_rif_dev(rif)))
+ return 0;
+
neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
if (rms.err)
goto err_arp;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 4ca7b99..de6b1a3 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -154,14 +154,14 @@ struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
void fbnic_devlink_register(struct fbnic_dev *fbd);
void fbnic_devlink_unregister(struct fbnic_dev *fbd);
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
void fbnic_hwmon_register(struct fbnic_dev *fbd);
void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd);
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd);
void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
int fbnic_napi_request_irq(struct fbnic_dev *fbd,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 3b12a0a..51bee80 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -796,8 +796,10 @@ enum {
/* PUL User Registers */
#define FBNIC_CSR_START_PUL_USER 0x31000 /* CSR section delimiter */
#define FBNIC_PUL_OB_TLP_HDR_AW_CFG 0x3103d /* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH CSR_BIT(19)
#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME CSR_BIT(18)
#define FBNIC_PUL_OB_TLP_HDR_AR_CFG 0x3103e /* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH CSR_BIT(19)
#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME CSR_BIT(18)
#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
0x3106e /* 0xc41b8 */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 88db3da..3d9636a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
{
u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+ /* Write the upper 32b and then the lower 32b. Doing this the
+ * FW can then read lower, upper, lower to verify that the state
+ * of the descriptor wasn't changed mid-transaction.
+ */
fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
fw_wrfl(fbd);
fw_wr32(fbd, desc_offset, lower_32_bits(desc));
}
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+ int desc_idx, u32 desc)
+{
+ u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+ /* For initialization we write the lower 32b of the descriptor first.
+ * This way we can set the state to mark it invalid before we clear the
+ * upper 32b.
+ */
+ fw_wr32(fbd, desc_offset, desc);
+ fw_wrfl(fbd);
+ fw_wr32(fbd, desc_offset + 1, 0);
+}
+
static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
{
u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
return desc;
}
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
{
int desc_idx;
+ /* Disable DMA transactions from the device,
+ * and flush any transactions triggered during cleaning
+ */
+ switch (mbx_idx) {
+ case FBNIC_IPC_MBX_RX_IDX:
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+ break;
+ case FBNIC_IPC_MBX_TX_IDX:
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+ break;
+ }
+
+ wrfl(fbd);
+
/* Initialize first descriptor to all 0s. Doing this gives us a
* solid stop for the firmware to hit when it is done looping
* through the ring.
*/
- __fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
- fw_wrfl(fbd);
+ __fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
/* We then fill the rest of the ring starting at the end and moving
* back toward descriptor 0 with skip descriptors that have no
* length nor address, and tell the firmware that they can skip
* them and just move past them to the one we initialized to 0.
*/
- for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
- __fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
- FBNIC_IPC_MBX_DESC_FW_CMPL |
- FBNIC_IPC_MBX_DESC_HOST_CMPL);
- fw_wrfl(fbd);
- }
+ for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+ __fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+ FBNIC_IPC_MBX_DESC_FW_CMPL |
+ FBNIC_IPC_MBX_DESC_HOST_CMPL);
}
void fbnic_mbx_init(struct fbnic_dev *fbd)
@@ -76,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
- fbnic_mbx_init_desc_ring(fbd, i);
+ fbnic_mbx_reset_desc_ring(fbd, i);
}
static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -141,7 +171,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
{
int i;
- fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+ fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -322,67 +352,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
return err;
}
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
- int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
- /* Return 0 if we are not calling this on ASIC */
- return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
{
struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
- /* This is a one time init, so just exit if it is completed */
- if (mbx->ready)
- return;
-
mbx->ready = true;
switch (mbx_idx) {
case FBNIC_IPC_MBX_RX_IDX:
+ /* Enable DMA writes from the device */
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
/* Make sure we have a page for the FW to write to */
fbnic_mbx_alloc_rx_msgs(fbd);
break;
case FBNIC_IPC_MBX_TX_IDX:
- /* Force version to 1 if we successfully requested an update
- * from the firmware. This should be overwritten once we get
- * the actual version from the firmware in the capabilities
- * request message.
- */
- if (!fbnic_fw_xmit_cap_msg(fbd) &&
- !fbd->fw_cap.running.mgmt.version)
- fbd->fw_cap.running.mgmt.version = 1;
+ /* Enable DMA reads from the device */
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
break;
}
}
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
{
- int i;
-
- /* We only need to do this on the first interrupt following init.
+ /* We only need to do this on the first interrupt following reset.
* this primes the mailbox so that we will have cleared all the
* skip descriptors.
*/
if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
- return;
+ return false;
wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
- for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
- fbnic_mbx_postinit_desc_ring(fbd, i);
+ return true;
}
/**
@@ -859,7 +863,7 @@ static void fbnic_mbx_process_rx_msgs(struct fbnic_dev *fbd)
void fbnic_mbx_poll(struct fbnic_dev *fbd)
{
- fbnic_mbx_postinit(fbd);
+ fbnic_mbx_event(fbd);
fbnic_mbx_process_tx_msgs(fbd);
fbnic_mbx_process_rx_msgs(fbd);
@@ -867,60 +871,97 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
{
- struct fbnic_fw_mbx *tx_mbx;
- int attempts = 50;
+ unsigned long timeout = jiffies + 10 * HZ + 1;
+ int err, i;
- /* Immediate fail if BAR4 isn't there */
- if (!fbnic_fw_present(fbd))
- return -ENODEV;
+ do {
+ if (!time_is_after_jiffies(timeout))
+ return -ETIMEDOUT;
- tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
- while (!tx_mbx->ready && --attempts) {
/* Force the firmware to trigger an interrupt response to
* avoid the mailbox getting stuck closed if the interrupt
* is reset.
*/
- fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
+ fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
- msleep(200);
+ /* Immediate fail if BAR4 went away */
+ if (!fbnic_fw_present(fbd))
+ return -ENODEV;
- fbnic_mbx_poll(fbd);
+ msleep(20);
+ } while (!fbnic_mbx_event(fbd));
+
+ /* FW has shown signs of life. Enable DMA and start Tx/Rx */
+ for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
+ fbnic_mbx_init_desc_ring(fbd, i);
+
+ /* Request an update from the firmware. This should overwrite
+ * mgmt.version once we get the actual version from the firmware
+ * in the capabilities request message.
+ */
+ err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
+ if (err)
+ goto clean_mbx;
+
+ /* Use "1" to indicate we entered the state waiting for a response */
+ fbd->fw_cap.running.mgmt.version = 1;
+
+ return 0;
+clean_mbx:
+ /* Cleanup Rx buffers and disable mailbox */
+ fbnic_mbx_clean(fbd);
+ return err;
+}
+
+static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
+{
+ cmpl_data->result = -EPIPE;
+ complete(&cmpl_data->done);
+}
+
+static void fbnic_mbx_evict_all_cmpl(struct fbnic_dev *fbd)
+{
+ if (fbd->cmpl_data) {
+ __fbnic_fw_evict_cmpl(fbd->cmpl_data);
+ fbd->cmpl_data = NULL;
}
-
- return attempts ? 0 : -ETIMEDOUT;
}
void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
{
+ unsigned long timeout = jiffies + 10 * HZ + 1;
struct fbnic_fw_mbx *tx_mbx;
- int attempts = 50;
- u8 count = 0;
-
- /* Nothing to do if there is no mailbox */
- if (!fbnic_fw_present(fbd))
- return;
+ u8 tail;
/* Record current Rx stats */
tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
- /* Nothing to do if mailbox never got to ready */
- if (!tx_mbx->ready)
- return;
+ spin_lock_irq(&fbd->fw_tx_lock);
+
+ /* Clear ready to prevent any further attempts to transmit */
+ tx_mbx->ready = false;
+
+ /* Read tail to determine the last tail state for the ring */
+ tail = tx_mbx->tail;
+
+ /* Flush any completions as we are no longer processing Rx */
+ fbnic_mbx_evict_all_cmpl(fbd);
+
+ spin_unlock_irq(&fbd->fw_tx_lock);
/* Give firmware time to process packet,
- * we will wait up to 10 seconds which is 50 waits of 200ms.
+ * we will wait up to 10 seconds which is 500 waits of 20ms.
*/
do {
u8 head = tx_mbx->head;
- if (head == tx_mbx->tail)
+ /* Tx ring is empty once head == tail */
+ if (head == tail)
break;
- msleep(200);
+ msleep(20);
fbnic_mbx_process_tx_msgs(fbd);
-
- count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
- } while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
+ } while (time_is_after_jiffies(timeout));
}
void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
index 1bbc0e5..1c88a2b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
@@ -19,69 +19,105 @@ static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data)
return IRQ_HANDLED;
}
-/**
- * fbnic_fw_enable_mbx - Configure and initialize Firmware Mailbox
- * @fbd: Pointer to device to initialize
- *
- * This function will initialize the firmware mailbox rings, enable the IRQ
- * and initialize the communication between the Firmware and the host. The
- * firmware is expected to respond to the initialization by sending an
- * interrupt essentially notifying the host that it has seen the
- * initialization and is now synced up.
- *
- * Return: non-zero on failure.
- **/
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd)
+static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector)
{
- u32 vector = fbd->fw_msix_vector;
int err;
- /* Request the IRQ for FW Mailbox vector. */
- err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
- IRQF_ONESHOT, dev_name(fbd->dev), fbd);
- if (err)
- return err;
-
/* Initialize mailbox and attempt to poll it into ready state */
fbnic_mbx_init(fbd);
err = fbnic_mbx_poll_tx_ready(fbd);
if (err) {
dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
- free_irq(vector, fbd);
return err;
}
- /* Enable interrupts */
+ /* Enable interrupt and unmask the vector */
+ enable_irq(vector);
fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
return 0;
}
/**
- * fbnic_fw_disable_mbx - Disable mailbox and place it in standby state
- * @fbd: Pointer to device to disable
+ * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox
+ * @fbd: Pointer to device to initialize
*
- * This function will disable the mailbox interrupt, free any messages still
- * in the mailbox and place it into a standby state. The firmware is
- * expected to see the update and assume that the host is in the reset state.
+ * This function will allocate the IRQ and then reinitialize the mailbox
+ * starting communication between the host and firmware.
+ *
+ * Return: non-zero on failure.
**/
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd)
{
- /* Disable interrupt and free vector */
- fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
+ struct pci_dev *pdev = to_pci_dev(fbd->dev);
+ int vector, err;
- /* Free the vector */
- free_irq(fbd->fw_msix_vector, fbd);
+ WARN_ON(fbd->fw_msix_vector);
+
+ vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
+ if (vector < 0)
+ return vector;
+
+ /* Request the IRQ for FW Mailbox vector. */
+ err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
+ IRQF_ONESHOT | IRQF_NO_AUTOEN,
+ dev_name(fbd->dev), fbd);
+ if (err)
+ return err;
+
+ /* Initialize mailbox and attempt to poll it into ready state */
+ err = __fbnic_fw_enable_mbx(fbd, vector);
+ if (err)
+ free_irq(vector, fbd);
+
+ fbd->fw_msix_vector = vector;
+
+ return err;
+}
+
+/**
+ * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state
+ * @fbd: Pointer to device
+ *
+ * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask
+ * and synchronize the IRQ, and then clean up the rings.
+ **/
+static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+{
+ /* Disable interrupt and synchronize the IRQ */
+ disable_irq(fbd->fw_msix_vector);
+
+ /* Mask the vector */
+ fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
/* Make sure disabling logs message is sent, must be done here to
* avoid risk of completing without a running interrupt.
*/
fbnic_mbx_flush_tx(fbd);
-
- /* Reset the mailboxes to the initialized state */
fbnic_mbx_clean(fbd);
}
+/**
+ * fbnic_fw_free_mbx - Disable mailbox and place it in standby state
+ * @fbd: Pointer to device to disable
+ *
+ * This function will disable the mailbox interrupt, free any messages still
+ * in the mailbox and place it into a disabled state. The firmware is
+ * expected to see the update and assume that the host is in the reset state.
+ **/
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd)
+{
+ /* Vector has already been freed */
+ if (!fbd->fw_msix_vector)
+ return;
+
+ fbnic_fw_disable_mbx(fbd);
+
+ /* Free the vector */
+ free_irq(fbd->fw_msix_vector, fbd);
+ fbd->fw_msix_vector = 0;
+}
+
static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
{
struct fbnic_dev *fbd = data;
@@ -101,7 +137,7 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
}
/**
- * fbnic_pcs_irq_enable - Configure the MAC to enable it to advertise link
+ * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link
* @fbd: Pointer to device to initialize
*
* This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ
@@ -109,41 +145,61 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
*
* Return: non-zero on failure.
**/
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd)
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd)
{
- u32 vector = fbd->pcs_msix_vector;
- int err;
+ struct pci_dev *pdev = to_pci_dev(fbd->dev);
+ int vector, err;
- /* Request the IRQ for MAC link vector.
- * Map MAC cause to it, and unmask it
+ WARN_ON(fbd->pcs_msix_vector);
+
+ vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
+ if (vector < 0)
+ return vector;
+
+ /* Request the IRQ for PCS link vector.
+ * Map PCS cause to it, and unmask it
*/
err = request_irq(vector, &fbnic_pcs_msix_intr, 0,
fbd->netdev->name, fbd);
if (err)
return err;
+ /* Map and enable interrupt, unmask vector after link is configured */
fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE);
+ fbd->pcs_msix_vector = vector;
+
return 0;
}
/**
- * fbnic_pcs_irq_disable - Teardown the MAC IRQ to prepare for stopping
+ * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping
* @fbd: Pointer to device that is stopping
*
- * This function undoes the work done in fbnic_pcs_irq_enable and prepares
+ * This function undoes the work done in fbnic_pcs_request_irq and prepares
* the device to no longer receive traffic on the host interface.
**/
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd)
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd)
{
+ /* Vector has already been freed */
+ if (!fbd->pcs_msix_vector)
+ return;
+
/* Disable interrupt */
fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
FBNIC_PCS_MSIX_ENTRY);
+ fbnic_wrfl(fbd);
+
+ /* Synchronize IRQ to prevent race that would unmask vector */
+ synchronize_irq(fbd->pcs_msix_vector);
+
+ /* Mask the vector */
fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY);
/* Free the vector */
free_irq(fbd->pcs_msix_vector, fbd);
+ fbd->pcs_msix_vector = 0;
}
void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr)
@@ -226,9 +282,6 @@ void fbnic_free_irqs(struct fbnic_dev *fbd)
{
struct pci_dev *pdev = to_pci_dev(fbd->dev);
- fbd->pcs_msix_vector = 0;
- fbd->fw_msix_vector = 0;
-
fbd->num_irqs = 0;
pci_free_irq_vectors(pdev);
@@ -254,8 +307,5 @@ int fbnic_alloc_irqs(struct fbnic_dev *fbd)
fbd->num_irqs = num_irqs;
- fbd->pcs_msix_vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
- fbd->fw_msix_vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
-
return 0;
}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 1429140..dde4a37 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd)
fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq);
fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps);
fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps);
-
- /* Enable XALI AR/AW outbound */
- wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
- FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
- wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
- FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
}
static void fbnic_mac_init_qm(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 79a01fd..2524d9b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -44,9 +44,10 @@ int __fbnic_open(struct fbnic_net *fbn)
if (err)
goto time_stop;
- err = fbnic_pcs_irq_enable(fbd);
+ err = fbnic_pcs_request_irq(fbd);
if (err)
goto time_stop;
+
/* Pull the BMC config and initialize the RPC */
fbnic_bmc_rpc_init(fbd);
fbnic_rss_reinit(fbd, fbn);
@@ -82,7 +83,7 @@ static int fbnic_stop(struct net_device *netdev)
struct fbnic_net *fbn = netdev_priv(netdev);
fbnic_down(fbn);
- fbnic_pcs_irq_disable(fbn->fbd);
+ fbnic_pcs_free_irq(fbn->fbd);
fbnic_time_stop(fbn);
fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index 6cbbc2e..4e859523 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -283,7 +283,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto free_irqs;
}
- err = fbnic_fw_enable_mbx(fbd);
+ err = fbnic_fw_request_mbx(fbd);
if (err) {
dev_err(&pdev->dev,
"Firmware mailbox initialization failure\n");
@@ -363,7 +363,7 @@ static void fbnic_remove(struct pci_dev *pdev)
fbnic_hwmon_unregister(fbd);
fbnic_dbg_fbd_exit(fbd);
fbnic_devlink_unregister(fbd);
- fbnic_fw_disable_mbx(fbd);
+ fbnic_fw_free_mbx(fbd);
fbnic_free_irqs(fbd);
fbnic_devlink_free(fbd);
@@ -387,7 +387,7 @@ static int fbnic_pm_suspend(struct device *dev)
rtnl_unlock();
null_uc_addr:
- fbnic_fw_disable_mbx(fbd);
+ fbnic_fw_free_mbx(fbd);
/* Free the IRQs so they aren't trying to occupy sleeping CPUs */
fbnic_free_irqs(fbd);
@@ -420,7 +420,7 @@ static int __fbnic_pm_resume(struct device *dev)
fbd->mac->init_regs(fbd);
/* Re-enable mailbox */
- err = fbnic_fw_enable_mbx(fbd);
+ err = fbnic_fw_request_mbx(fbd);
if (err)
goto err_free_irqs;
@@ -438,15 +438,15 @@ static int __fbnic_pm_resume(struct device *dev)
if (netif_running(netdev)) {
err = __fbnic_open(fbn);
if (err)
- goto err_disable_mbx;
+ goto err_free_mbx;
}
rtnl_unlock();
return 0;
-err_disable_mbx:
+err_free_mbx:
rtnl_unlock();
- fbnic_fw_disable_mbx(fbd);
+ fbnic_fw_free_mbx(fbd);
err_free_irqs:
fbnic_free_irqs(fbd);
err_invalidate_uc_addr:
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 23760b6..a70b880 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1815,6 +1815,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
if (nr_frags <= 0) {
tx->frame_data0 |= TX_DESC_DATA0_LS_;
tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ tx->frame_last = tx->frame_first;
}
tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
@@ -1884,6 +1885,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
tx->frame_first = 0;
tx->frame_data0 = 0;
tx->frame_tail = 0;
+ tx->frame_last = 0;
return -ENOMEM;
}
@@ -1924,16 +1926,18 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
TX_DESC_DATA0_DTYPE_DATA_) {
tx->frame_data0 |= TX_DESC_DATA0_LS_;
tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ tx->frame_last = tx->frame_tail;
}
- tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
- buffer_info = &tx->buffer_info[tx->frame_tail];
+ tx_descriptor = &tx->ring_cpu_ptr[tx->frame_last];
+ buffer_info = &tx->buffer_info[tx->frame_last];
buffer_info->skb = skb;
if (time_stamp)
buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
if (ignore_sync)
buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
+ tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail);
tx->last_tail = tx->frame_tail;
@@ -3491,6 +3495,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
struct pci_dev *pdev)
{
struct lan743x_tx *tx;
+ u32 sgmii_ctl;
int index;
int ret;
@@ -3503,6 +3508,15 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
spin_lock_init(&adapter->eth_syslock_spinlock);
mutex_init(&adapter->sgmii_rw_lock);
pci11x1x_set_rfe_rd_fifo_threshold(adapter);
+ sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+ if (adapter->is_sgmii_en) {
+ sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
+ sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
+ } else {
+ sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
+ sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
+ }
+ lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
} else {
adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS;
adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS;
@@ -3554,7 +3568,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
{
- u32 sgmii_ctl;
int ret;
adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev);
@@ -3566,10 +3579,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
adapter->mdiobus->priv = (void *)adapter;
if (adapter->is_pci11x1x) {
if (adapter->is_sgmii_en) {
- sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
- sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
- sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
- lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
netif_dbg(adapter, drv, adapter->netdev,
"SGMII operation\n");
adapter->mdiobus->read = lan743x_mdiobus_read_c22;
@@ -3580,10 +3589,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
netif_dbg(adapter, drv, adapter->netdev,
"lan743x-mdiobus-c45\n");
} else {
- sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
- sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
- sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
- lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
netif_dbg(adapter, drv, adapter->netdev,
"RGMII operation\n");
// Only C22 support when RGMII I/F
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 7f73d66..db5fc73 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -980,6 +980,7 @@ struct lan743x_tx {
u32 frame_first;
u32 frame_data0;
u32 frame_tail;
+ u32 frame_last;
struct lan743x_tx_buffer_info *buffer_info;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ef93df5..08bee56 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -830,6 +830,7 @@ EXPORT_SYMBOL(ocelot_vlan_prepare);
int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
bool untagged)
{
+ struct ocelot_port *ocelot_port = ocelot->ports[port];
int err;
/* Ignore VID 0 added to our RX filter by the 8021q module, since
@@ -849,6 +850,11 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
ocelot_bridge_vlan_find(ocelot, vid));
if (err)
return err;
+ } else if (ocelot_port->pvid_vlan &&
+ ocelot_bridge_vlan_find(ocelot, vid) == ocelot_port->pvid_vlan) {
+ err = ocelot_port_set_pvid(ocelot, port, NULL);
+ if (err)
+ return err;
}
/* Untagged egress vlan clasification */
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 99df00c..b5d744d 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -203,7 +203,7 @@ static struct pci_driver qede_pci_driver = {
};
static struct qed_eth_cb_ops qede_ll_ops = {
- {
+ .common = {
#ifdef CONFIG_RFS_ACCEL
.arfs_filter_op = qede_arfs_filter_op,
#endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 28d24d5..d57b976 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -1484,8 +1484,11 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_o
}
cmd_op = (cmd.rsp.arg[0] & 0xff);
- if (cmd.rsp.arg[0] >> 25 == 2)
- return 2;
+ if (cmd.rsp.arg[0] >> 25 == 2) {
+ ret = 2;
+ goto out;
+ }
+
if (cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT)
set_bit(QLC_BC_VF_STATE, &vf->state);
else
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 2aacc19..55b8d36 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1925,8 +1925,8 @@ static u16 rtase_calc_time_mitigation(u32 time_us)
time_us = min_t(int, time_us, RTASE_MITI_MAX_TIME);
- msb = fls(time_us);
- if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+ if (time_us > RTASE_MITI_TIME_COUNT_MASK) {
+ msb = fls(time_us);
time_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
time_count = time_us >> (msb - RTASE_MITI_COUNT_BIT_NUM);
} else {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 85723a7..6c7e865 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -964,7 +964,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev,
/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
* address. No need to mask it again.
*/
- reg |= 1 << H3_EPHY_ADDR_SHIFT;
+ reg |= ret << H3_EPHY_ADDR_SHIFT;
} else {
/* For SoCs without internal PHY the PHY selection bit should be
* set to 0 (external PHY).
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 967a162..0c011a4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -320,8 +320,8 @@ enum rtc_control {
/* PTP and timestamping registers */
-#define GMAC3_X_ATSNS GENMASK(19, 16)
-#define GMAC3_X_ATSNS_SHIFT 16
+#define GMAC3_X_ATSNS GENMASK(29, 25)
+#define GMAC3_X_ATSNS_SHIFT 25
#define GMAC_PTP_TCR_ATSFC BIT(24)
#define GMAC_PTP_TCR_ATSEN0 BIT(25)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index a8b901c..56b76aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -553,7 +553,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
u64 ns;
ns = readl(ptpaddr + GMAC_PTP_ATNR);
- ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
+ ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
*ptp_time = ns;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 0f59aa9..e2840fa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
u64 ns;
ns = readl(ptpaddr + PTP_ATNR);
- ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
+ ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
*ptp_time = ns;
}
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 1e6d233..30665ff 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2685,7 +2685,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
port->slave.mac_addr);
if (!is_valid_ether_addr(port->slave.mac_addr)) {
eth_random_addr(port->slave.mac_addr);
- dev_err(dev, "Use random MAC address\n");
+ dev_info(dev, "Use random MAC address\n");
}
}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index b4be76e..d88a018 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -187,7 +187,6 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
xdp_return_frame(xdpf);
break;
default:
- netdev_err(ndev, "tx_complete: invalid swdata type %d\n", swdata->type);
prueth_xmit_free(tx_chn, desc_tx);
ndev->stats.tx_dropped++;
continue;
@@ -567,6 +566,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
{
struct cppi5_host_desc_t *first_desc;
struct net_device *ndev = emac->ndev;
+ struct netdev_queue *netif_txq;
struct prueth_tx_chn *tx_chn;
dma_addr_t desc_dma, buf_dma;
struct prueth_swdata *swdata;
@@ -620,12 +620,17 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
swdata->data.xdpf = xdpf;
}
+ /* Report BQL before sending the packet */
+ netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+ netdev_tx_sent_queue(netif_txq, xdpf->len);
+
cppi5_hdesc_set_pktlen(first_desc, xdpf->len);
desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
if (ret) {
netdev_err(ndev, "xdp tx: push failed: %d\n", ret);
+ netdev_tx_completed_queue(netif_txq, 1, xdpf->len);
goto drop_free_descs;
}
@@ -650,6 +655,8 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
struct page *page, u32 *len)
{
struct net_device *ndev = emac->ndev;
+ struct netdev_queue *netif_txq;
+ int cpu = smp_processor_id();
struct bpf_prog *xdp_prog;
struct xdp_frame *xdpf;
u32 pkt_len = *len;
@@ -669,8 +676,11 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
goto drop;
}
- q_idx = smp_processor_id() % emac->tx_ch_num;
+ q_idx = cpu % emac->tx_ch_num;
+ netif_txq = netdev_get_tx_queue(ndev, q_idx);
+ __netif_tx_lock(netif_txq, cpu);
result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
+ __netif_tx_unlock(netif_txq);
if (result == ICSSG_XDP_CONSUMED) {
ndev->stats.tx_dropped++;
goto drop;
@@ -979,6 +989,7 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
if (ret) {
netdev_err(ndev, "tx: push failed: %d\n", ret);
+ netdev_tx_completed_queue(netif_txq, 1, pkt_len);
goto drop_free_descs;
}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 443f90f..86fc127 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1075,17 +1075,21 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
{
struct prueth_emac *emac = netdev_priv(dev);
struct net_device *ndev = emac->ndev;
+ struct netdev_queue *netif_txq;
+ int cpu = smp_processor_id();
struct xdp_frame *xdpf;
unsigned int q_idx;
int nxmit = 0;
u32 err;
int i;
- q_idx = smp_processor_id() % emac->tx_ch_num;
+ q_idx = cpu % emac->tx_ch_num;
+ netif_txq = netdev_get_tx_queue(ndev, q_idx);
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
return -EINVAL;
+ __netif_tx_lock(netif_txq, cpu);
for (i = 0; i < n; i++) {
xdpf = frames[i];
err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx);
@@ -1095,6 +1099,7 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
}
nxmit++;
}
+ __netif_tx_unlock(netif_txq);
return nxmit;
}
@@ -1109,11 +1114,6 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf)
{
struct bpf_prog *prog = bpf->prog;
- xdp_features_t val;
-
- val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
- NETDEV_XDP_ACT_NDO_XMIT;
- xdp_set_features_flag(emac->ndev, val);
if (!emac->xdpi.prog && !prog)
return 0;
@@ -1291,6 +1291,10 @@ static int prueth_netdev_init(struct prueth *prueth,
ndev->hw_features = NETIF_F_SG;
ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES;
+ xdp_set_features_flag(ndev,
+ NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT);
netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll);
hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC,
diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 89dc4c4..e4d993f 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -6,6 +6,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/if_vlan.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/kernel.h>
@@ -33,7 +34,7 @@
#define CMD_CTR (0x2 << CMD_SHIFT)
#define CMD_MASK GENMASK(15, CMD_SHIFT)
-#define LEN_MASK GENMASK(CMD_SHIFT - 1, 0)
+#define LEN_MASK GENMASK(CMD_SHIFT - 2, 0)
#define DET_CMD_LEN 4
#define DET_SOF_LEN 2
@@ -262,7 +263,7 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp,
}
static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
- unsigned int frame_len)
+ unsigned int frame_len, bool drop)
{
struct mse102x_net_spi *mses = to_mse102x_spi(mse);
struct spi_transfer *xfer = &mses->spi_xfer;
@@ -280,6 +281,9 @@ static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n",
__func__, ret);
mse->stats.xfer_err++;
+ } else if (drop) {
+ netdev_dbg(mse->ndev, "%s: Drop frame\n", __func__);
+ ret = -EINVAL;
} else if (*sof != cpu_to_be16(DET_SOF)) {
netdev_dbg(mse->ndev, "%s: SPI start of frame is invalid (0x%04x)\n",
__func__, *sof);
@@ -307,6 +311,7 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
struct sk_buff *skb;
unsigned int rxalign;
unsigned int rxlen;
+ bool drop = false;
__be16 rx = 0;
u16 cmd_resp;
u8 *rxpkt;
@@ -329,7 +334,8 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
__func__, cmd_resp);
mse->stats.invalid_rts++;
- return;
+ drop = true;
+ goto drop;
}
net_dbg_ratelimited("%s: Unexpected response to first CMD\n",
@@ -337,12 +343,20 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
}
rxlen = cmd_resp & LEN_MASK;
- if (!rxlen) {
- net_dbg_ratelimited("%s: No frame length defined\n", __func__);
+ if (rxlen < ETH_ZLEN || rxlen > VLAN_ETH_FRAME_LEN) {
+ net_dbg_ratelimited("%s: Invalid frame length: %d\n", __func__,
+ rxlen);
mse->stats.invalid_len++;
- return;
+ drop = true;
}
+ /* In case of a invalid CMD_RTS, the frame must be consumed anyway.
+ * So assume the maximum possible frame length.
+ */
+drop:
+ if (drop)
+ rxlen = VLAN_ETH_FRAME_LEN;
+
rxalign = ALIGN(rxlen + DET_SOF_LEN + DET_DFT_LEN, 4);
skb = netdev_alloc_skb_ip_align(mse->ndev, rxalign);
if (!skb)
@@ -353,7 +367,7 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
* They are copied, but ignored.
*/
rxpkt = skb_put(skb, rxlen) - DET_SOF_LEN;
- if (mse102x_rx_frame_spi(mse, rxpkt, rxlen)) {
+ if (mse102x_rx_frame_spi(mse, rxpkt, rxlen, drop)) {
mse->ndev->stats.rx_errors++;
dev_kfree_skb(skb);
return;
@@ -509,6 +523,7 @@ static irqreturn_t mse102x_irq(int irq, void *_mse)
static int mse102x_net_open(struct net_device *ndev)
{
struct mse102x_net *mse = netdev_priv(ndev);
+ struct mse102x_net_spi *mses = to_mse102x_spi(mse);
int ret;
ret = request_threaded_irq(ndev->irq, NULL, mse102x_irq, IRQF_ONESHOT,
@@ -524,6 +539,13 @@ static int mse102x_net_open(struct net_device *ndev)
netif_carrier_on(ndev);
+ /* The SPI interrupt can stuck in case of pending packet(s).
+ * So poll for possible packet(s) to re-arm the interrupt.
+ */
+ mutex_lock(&mses->lock);
+ mse102x_rx_pkt_spi(mse);
+ mutex_unlock(&mses->lock);
+
netif_dbg(mse, ifup, ndev, "network device up\n");
return 0;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index aed45aba..490d342 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -434,14 +434,20 @@ static int wx_host_interface_command_r(struct wx *wx, u32 *buffer,
wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, WX_SW2FW_MBOX_CMD_VLD);
/* polling reply from FW */
- err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 1000, 50000,
- true, wx, buffer, send_cmd);
+ err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 2000,
+ timeout * 1000, true, wx, buffer, send_cmd);
if (err) {
wx_err(wx, "Polling from FW messages timeout, cmd: 0x%x, index: %d\n",
send_cmd, wx->swfw_index);
goto rel_out;
}
+ if (hdr->cmd_or_resp.ret_status == 0x80) {
+ wx_err(wx, "Unknown FW command: 0x%x\n", send_cmd);
+ err = -EINVAL;
+ goto rel_out;
+ }
+
/* expect no reply from FW then return */
if (!return_data)
goto rel_out;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index 4b9921b..a054b25 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -99,9 +99,15 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum)
}
local_buffer = eeprom_ptrs;
- for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++)
+ for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) {
+ if (wx->mac.type == wx_mac_aml) {
+ if (i >= TXGBE_EEPROM_I2C_SRART_PTR &&
+ i < TXGBE_EEPROM_I2C_END_PTR)
+ local_buffer[i] = 0xffff;
+ }
if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM)
*checksum += local_buffer[i];
+ }
kvfree(eeprom_ptrs);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 9c1c262..f423012 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -158,6 +158,8 @@
#define TXGBE_EEPROM_VERSION_L 0x1D
#define TXGBE_EEPROM_VERSION_H 0x1E
#define TXGBE_ISCSI_BOOT_CONFIG 0x07
+#define TXGBE_EEPROM_I2C_SRART_PTR 0x580
+#define TXGBE_EEPROM_I2C_END_PTR 0x800
#define TXGBE_MAX_MSIX_VECTORS 64
#define TXGBE_MAX_FDIR_INDICES 63
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 70f7cb3..cb6f548 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -158,7 +158,6 @@ struct hv_netvsc_packet {
u8 cp_partial; /* partial copy into send buffer */
u8 rmsg_size; /* RNDIS header and PPI size */
- u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */
u8 page_buf_cnt;
u16 q_idx;
@@ -893,6 +892,18 @@ struct nvsp_message {
sizeof(struct nvsp_message))
#define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
+/* Maximum # of contiguous data ranges that can make up a trasmitted packet.
+ * Typically it's the max SKB fragments plus 2 for the rndis packet and the
+ * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may
+ * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries
+ * in a GPA direct packet sent to netvsp over VMBus.
+ */
+#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT
+#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2)
+#else
+#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT
+#endif
+
/* Estimated requestor size:
* out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
*/
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d6f5b9e..7201046 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -953,8 +953,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
+ pend_size;
int i;
u32 padding = 0;
- u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
- packet->page_buf_cnt;
+ u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt;
u32 remain;
/* Add padding */
@@ -1055,6 +1054,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev,
return 0;
}
+/* Build an "array" of mpb entries describing the data to be transferred
+ * over VMBus. After the desc header fields, each "array" entry is variable
+ * size, and each entry starts after the end of the previous entry. The
+ * "offset" and "len" fields for each entry imply the size of the entry.
+ *
+ * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V
+ * uses that granularity, even if the system page size of the guest is larger.
+ * Each entry in the input "pb" array must describe a contiguous range of
+ * guest physical memory so that the pfns are sequential if the range crosses
+ * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE.
+ */
+static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb,
+ u32 page_buffer_count,
+ struct vmbus_packet_mpb_array *desc,
+ u32 *desc_size)
+{
+ struct hv_mpb_array *mpb_entry = &desc->range;
+ int i, j;
+
+ for (i = 0; i < page_buffer_count; i++) {
+ u32 offset = pb[i].offset;
+ u32 len = pb[i].len;
+
+ mpb_entry->offset = offset;
+ mpb_entry->len = len;
+
+ for (j = 0; j < HVPFN_UP(offset + len); j++)
+ mpb_entry->pfn_array[j] = pb[i].pfn + j;
+
+ mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j];
+ }
+
+ desc->rangecount = page_buffer_count;
+ *desc_size = (char *)mpb_entry - (char *)desc;
+}
+
static inline int netvsc_send_pkt(
struct hv_device *device,
struct hv_netvsc_packet *packet,
@@ -1097,8 +1132,11 @@ static inline int netvsc_send_pkt(
packet->dma_range = NULL;
if (packet->page_buf_cnt) {
+ struct vmbus_channel_packet_page_buffer desc;
+ u32 desc_size;
+
if (packet->cp_partial)
- pb += packet->rmsg_pgcnt;
+ pb++;
ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
if (ret) {
@@ -1106,11 +1144,12 @@ static inline int netvsc_send_pkt(
goto exit;
}
- ret = vmbus_sendpacket_pagebuffer(out_channel,
- pb, packet->page_buf_cnt,
- &nvmsg, sizeof(nvmsg),
- req_id);
-
+ netvsc_build_mpb_array(pb, packet->page_buf_cnt,
+ (struct vmbus_packet_mpb_array *)&desc,
+ &desc_size);
+ ret = vmbus_sendpacket_mpb_desc(out_channel,
+ (struct vmbus_packet_mpb_array *)&desc,
+ desc_size, &nvmsg, sizeof(nvmsg), req_id);
if (ret)
netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
} else {
@@ -1259,7 +1298,7 @@ int netvsc_send(struct net_device *ndev,
packet->send_buf_index = section_index;
if (packet->cp_partial) {
- packet->page_buf_cnt -= packet->rmsg_pgcnt;
+ packet->page_buf_cnt--;
packet->total_data_buflen = msd_len + packet->rmsg_size;
} else {
packet->page_buf_cnt = 0;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c51b318..d8b169a 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -326,43 +326,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
return txq;
}
-static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
- struct hv_page_buffer *pb)
-{
- int j = 0;
-
- hvpfn += offset >> HV_HYP_PAGE_SHIFT;
- offset = offset & ~HV_HYP_PAGE_MASK;
-
- while (len > 0) {
- unsigned long bytes;
-
- bytes = HV_HYP_PAGE_SIZE - offset;
- if (bytes > len)
- bytes = len;
- pb[j].pfn = hvpfn;
- pb[j].offset = offset;
- pb[j].len = bytes;
-
- offset += bytes;
- len -= bytes;
-
- if (offset == HV_HYP_PAGE_SIZE && len) {
- hvpfn++;
- offset = 0;
- j++;
- }
- }
-
- return j + 1;
-}
-
static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
struct hv_netvsc_packet *packet,
struct hv_page_buffer *pb)
{
- u32 slots_used = 0;
- char *data = skb->data;
int frags = skb_shinfo(skb)->nr_frags;
int i;
@@ -371,28 +338,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
* 2. skb linear data
* 3. skb fragment data
*/
- slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
- offset_in_hvpage(hdr),
- len,
- &pb[slots_used]);
+ pb[0].offset = offset_in_hvpage(hdr);
+ pb[0].len = len;
+ pb[0].pfn = virt_to_hvpfn(hdr);
packet->rmsg_size = len;
- packet->rmsg_pgcnt = slots_used;
- slots_used += fill_pg_buf(virt_to_hvpfn(data),
- offset_in_hvpage(data),
- skb_headlen(skb),
- &pb[slots_used]);
+ pb[1].offset = offset_in_hvpage(skb->data);
+ pb[1].len = skb_headlen(skb);
+ pb[1].pfn = virt_to_hvpfn(skb->data);
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+ struct hv_page_buffer *cur_pb = &pb[i + 2];
+ u64 pfn = page_to_hvpfn(skb_frag_page(frag));
+ u32 offset = skb_frag_off(frag);
- slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
- skb_frag_off(frag),
- skb_frag_size(frag),
- &pb[slots_used]);
+ cur_pb->offset = offset_in_hvpage(offset);
+ cur_pb->len = skb_frag_size(frag);
+ cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT);
}
- return slots_used;
+ return frags + 2;
}
static int count_skb_frag_slots(struct sk_buff *skb)
@@ -483,7 +449,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
struct net_device *vf_netdev;
u32 rndis_msg_size;
u32 hash;
- struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
+ struct hv_page_buffer pb[MAX_DATA_RANGES];
/* If VF is present and up then redirect packets to it.
* Skip the VF if it is marked down or has no carrier.
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 82747df..9e73959 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
struct rndis_request *req)
{
struct hv_netvsc_packet *packet;
- struct hv_page_buffer page_buf[2];
- struct hv_page_buffer *pb = page_buf;
+ struct hv_page_buffer pb;
int ret;
/* Setup the packet to send it */
@@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev,
packet->total_data_buflen = req->request_msg.msg_len;
packet->page_buf_cnt = 1;
- pb[0].pfn = virt_to_phys(&req->request_msg) >>
- HV_HYP_PAGE_SHIFT;
- pb[0].len = req->request_msg.msg_len;
- pb[0].offset = offset_in_hvpage(&req->request_msg);
-
- /* Add one page_buf when request_msg crossing page boundary */
- if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) {
- packet->page_buf_cnt++;
- pb[0].len = HV_HYP_PAGE_SIZE -
- pb[0].offset;
- pb[1].pfn = virt_to_phys((void *)&req->request_msg
- + pb[0].len) >> HV_HYP_PAGE_SHIFT;
- pb[1].offset = 0;
- pb[1].len = req->request_msg.msg_len -
- pb[0].len;
- }
+ pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT;
+ pb.len = req->request_msg.msg_len;
+ pb.offset = offset_in_hvpage(&req->request_msg);
trace_rndis_send(dev->ndev, 0, &req->request_msg);
rcu_read_lock_bh();
- ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false);
+ ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false);
rcu_read_unlock_bh();
return ret;
diff --git a/drivers/net/mdio/mdio-mux-meson-gxl.c b/drivers/net/mdio/mdio-mux-meson-gxl.c
index 00c6624..3dd12a8 100644
--- a/drivers/net/mdio/mdio-mux-meson-gxl.c
+++ b/drivers/net/mdio/mdio-mux-meson-gxl.c
@@ -17,6 +17,7 @@
#define REG2_LEDACT GENMASK(23, 22)
#define REG2_LEDLINK GENMASK(25, 24)
#define REG2_DIV4SEL BIT(27)
+#define REG2_REVERSED BIT(28)
#define REG2_ADCBYPASS BIT(30)
#define REG2_CLKINSEL BIT(31)
#define ETH_REG3 0x4
@@ -65,7 +66,7 @@ static void gxl_enable_internal_mdio(struct gxl_mdio_mux *priv)
* The only constraint is that it must match the one in
* drivers/net/phy/meson-gxl.c to properly match the PHY.
*/
- writel(FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
+ writel(REG2_REVERSED | FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
priv->regs + ETH_REG2);
/* Enable the internal phy */
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 14f3615..e32013e 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -730,7 +730,7 @@ static int dp83822_phy_reset(struct phy_device *phydev)
return phydev->drv->config_init(phydev);
}
-#ifdef CONFIG_OF_MDIO
+#if IS_ENABLED(CONFIG_OF_MDIO)
static const u32 tx_amplitude_100base_tx_gain[] = {
80, 82, 83, 85, 87, 88, 90, 92,
93, 95, 97, 98, 100, 102, 103, 105,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 24882d3..e2c6569 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -2027,12 +2027,6 @@ static int ksz9477_config_init(struct phy_device *phydev)
return err;
}
- /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes
- * in this switch shall be regarded as broken.
- */
- if (phydev->dev_flags & MICREL_NO_EEE)
- phy_disable_eee(phydev);
-
return kszphy_config_init(phydev);
}
@@ -5705,7 +5699,6 @@ static struct phy_driver ksphy_driver[] = {
.handle_interrupt = kszphy_handle_interrupt,
.suspend = genphy_suspend,
.resume = ksz9477_resume,
- .get_features = ksz9477_get_features,
} };
module_phy_driver(ksphy_driver);
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 0e17cc4..93de88c 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -37,47 +37,6 @@ static int lan88xx_write_page(struct phy_device *phydev, int page)
return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
}
-static int lan88xx_phy_config_intr(struct phy_device *phydev)
-{
- int rc;
-
- if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
- /* unmask all source and clear them before enable */
- rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF);
- rc = phy_read(phydev, LAN88XX_INT_STS);
- rc = phy_write(phydev, LAN88XX_INT_MASK,
- LAN88XX_INT_MASK_MDINTPIN_EN_ |
- LAN88XX_INT_MASK_LINK_CHANGE_);
- } else {
- rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
- if (rc)
- return rc;
-
- /* Ack interrupts after they have been disabled */
- rc = phy_read(phydev, LAN88XX_INT_STS);
- }
-
- return rc < 0 ? rc : 0;
-}
-
-static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
-{
- int irq_status;
-
- irq_status = phy_read(phydev, LAN88XX_INT_STS);
- if (irq_status < 0) {
- phy_error(phydev);
- return IRQ_NONE;
- }
-
- if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
- return IRQ_NONE;
-
- phy_trigger_machine(phydev);
-
- return IRQ_HANDLED;
-}
-
static int lan88xx_suspend(struct phy_device *phydev)
{
struct lan88xx_priv *priv = phydev->priv;
@@ -528,8 +487,9 @@ static struct phy_driver microchip_phy_driver[] = {
.config_aneg = lan88xx_config_aneg,
.link_change_notify = lan88xx_link_change_notify,
- .config_intr = lan88xx_phy_config_intr,
- .handle_interrupt = lan88xx_handle_interrupt,
+ /* Interrupt handling is broken, do not define related
+ * functions to force polling.
+ */
.suspend = lan88xx_suspend,
.resume = genphy_resume,
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index bd3c955..6089369 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -93,9 +93,8 @@ int phy_led_triggers_register(struct phy_device *phy)
if (!phy->phy_num_led_triggers)
return 0;
- phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev,
- sizeof(*phy->led_link_trigger),
- GFP_KERNEL);
+ phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger),
+ GFP_KERNEL);
if (!phy->led_link_trigger) {
err = -ENOMEM;
goto out_clear;
@@ -105,10 +104,9 @@ int phy_led_triggers_register(struct phy_device *phy)
if (err)
goto out_free_link;
- phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev,
- phy->phy_num_led_triggers,
- sizeof(struct phy_led_trigger),
- GFP_KERNEL);
+ phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers,
+ sizeof(struct phy_led_trigger),
+ GFP_KERNEL);
if (!phy->phy_led_triggers) {
err = -ENOMEM;
goto out_unreg_link;
@@ -129,11 +127,11 @@ int phy_led_triggers_register(struct phy_device *phy)
out_unreg:
while (i--)
phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
- devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+ kfree(phy->phy_led_triggers);
out_unreg_link:
phy_led_trigger_unregister(phy->led_link_trigger);
out_free_link:
- devm_kfree(&phy->mdio.dev, phy->led_link_trigger);
+ kfree(phy->led_link_trigger);
phy->led_link_trigger = NULL;
out_clear:
phy->phy_num_led_triggers = 0;
@@ -147,8 +145,13 @@ void phy_led_triggers_unregister(struct phy_device *phy)
for (i = 0; i < phy->phy_num_led_triggers; i++)
phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
+ kfree(phy->phy_led_triggers);
+ phy->phy_led_triggers = NULL;
- if (phy->led_link_trigger)
+ if (phy->led_link_trigger) {
phy_led_trigger_unregister(phy->led_link_trigger);
+ kfree(phy->led_link_trigger);
+ phy->led_link_trigger = NULL;
+ }
}
EXPORT_SYMBOL_GPL(phy_led_triggers_unregister);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index b68369e..1bdd5d8 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -81,6 +81,7 @@ struct phylink {
unsigned int pcs_state;
bool link_failed;
+ bool suspend_link_up;
bool major_config_failed;
bool mac_supports_eee_ops;
bool mac_supports_eee;
@@ -2545,14 +2546,16 @@ void phylink_suspend(struct phylink *pl, bool mac_wol)
/* Stop the resolver bringing the link up */
__set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state);
- /* Disable the carrier, to prevent transmit timeouts,
- * but one would hope all packets have been sent. This
- * also means phylink_resolve() will do nothing.
- */
- if (pl->netdev)
- netif_carrier_off(pl->netdev);
- else
+ pl->suspend_link_up = phylink_link_is_up(pl);
+ if (pl->suspend_link_up) {
+ /* Disable the carrier, to prevent transmit timeouts,
+ * but one would hope all packets have been sent. This
+ * also means phylink_resolve() will do nothing.
+ */
+ if (pl->netdev)
+ netif_carrier_off(pl->netdev);
pl->old_link_state = false;
+ }
/* We do not call mac_link_down() here as we want the
* link to remain up to receive the WoL packets.
@@ -2603,15 +2606,18 @@ void phylink_resume(struct phylink *pl)
if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) {
/* Wake-on-Lan enabled, MAC handling */
- /* Call mac_link_down() so we keep the overall state balanced.
- * Do this under the state_mutex lock for consistency. This
- * will cause a "Link Down" message to be printed during
- * resume, which is harmless - the true link state will be
- * printed when we run a resolve.
- */
- mutex_lock(&pl->state_mutex);
- phylink_link_down(pl);
- mutex_unlock(&pl->state_mutex);
+ if (pl->suspend_link_up) {
+ /* Call mac_link_down() so we keep the overall state
+ * balanced. Do this under the state_mutex lock for
+ * consistency. This will cause a "Link Down" message
+ * to be printed during resume, which is harmless -
+ * the true link state will be printed when we run a
+ * resolve.
+ */
+ mutex_lock(&pl->state_mutex);
+ phylink_link_down(pl);
+ mutex_unlock(&pl->state_mutex);
+ }
/* Re-apply the link parameters so that all the settings get
* restored to the MAC.
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index d8fc0c7..b75ceb9 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -1778,8 +1778,8 @@ static void team_change_rx_flags(struct net_device *dev, int change)
struct team_port *port;
int inc;
- rcu_read_lock();
- list_for_each_entry_rcu(port, &team->port_list, list) {
+ mutex_lock(&team->lock);
+ list_for_each_entry(port, &team->port_list, list) {
if (change & IFF_PROMISC) {
inc = dev->flags & IFF_PROMISC ? 1 : -1;
dev_set_promiscuity(port->dev, inc);
@@ -1789,7 +1789,7 @@ static void team_change_rx_flags(struct net_device *dev, int change)
dev_set_allmulti(port->dev, inc);
}
}
- rcu_read_unlock();
+ mutex_unlock(&team->lock);
}
static void team_set_rx_mode(struct net_device *dev)
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index bb0bf14..7b3739b 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -630,16 +630,6 @@ static const struct driver_info zte_rndis_info = {
.tx_fixup = rndis_tx_fixup,
};
-static const struct driver_info wwan_rndis_info = {
- .description = "Mobile Broadband RNDIS device",
- .flags = FLAG_WWAN | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT,
- .bind = rndis_bind,
- .unbind = rndis_unbind,
- .status = rndis_status,
- .rx_fixup = rndis_rx_fixup,
- .tx_fixup = rndis_tx_fixup,
-};
-
/*-------------------------------------------------------------------------*/
static const struct usb_device_id products [] = {
@@ -676,11 +666,9 @@ static const struct usb_device_id products [] = {
USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
.driver_info = (unsigned long) &rndis_info,
}, {
- /* Mobile Broadband Modem, seen in Novatel Verizon USB730L and
- * Telit FN990A (RNDIS)
- */
+ /* Novatel Verizon USB730L */
USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1),
- .driver_info = (unsigned long)&wwan_rndis_info,
+ .driver_info = (unsigned long) &rndis_info,
},
{ }, // END
};
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7e46172..e53ba60 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+static void __virtnet_rx_pause(struct virtnet_info *vi,
+ struct receive_queue *rq)
{
bool running = netif_running(vi->dev);
@@ -3352,15 +3353,64 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
}
}
-static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
+{
+ int i;
+
+ /*
+ * Make sure refill_work does not run concurrently to
+ * avoid napi_disable race which leads to deadlock.
+ */
+ disable_delayed_refill(vi);
+ cancel_delayed_work_sync(&vi->refill);
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ __virtnet_rx_pause(vi, &vi->rq[i]);
+}
+
+static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+{
+ /*
+ * Make sure refill_work does not run concurrently to
+ * avoid napi_disable race which leads to deadlock.
+ */
+ disable_delayed_refill(vi);
+ cancel_delayed_work_sync(&vi->refill);
+ __virtnet_rx_pause(vi, rq);
+}
+
+static void __virtnet_rx_resume(struct virtnet_info *vi,
+ struct receive_queue *rq,
+ bool refill)
{
bool running = netif_running(vi->dev);
+ bool schedule_refill = false;
- if (!try_fill_recv(vi, rq, GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
+ if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
+ schedule_refill = true;
if (running)
virtnet_napi_enable(rq);
+
+ if (schedule_refill)
+ schedule_delayed_work(&vi->refill, 0);
+}
+
+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+ int i;
+
+ enable_delayed_refill(vi);
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ if (i < vi->curr_queue_pairs)
+ __virtnet_rx_resume(vi, &vi->rq[i], true);
+ else
+ __virtnet_rx_resume(vi, &vi->rq[i], false);
+ }
+}
+
+static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+{
+ enable_delayed_refill(vi);
+ __virtnet_rx_resume(vi, rq, true);
}
static int virtnet_rx_resize(struct virtnet_info *vi,
@@ -3681,8 +3731,10 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
succ:
vi->curr_queue_pairs = queue_pairs;
/* virtnet_open() will refill when device is going to up. */
- if (dev->flags & IFF_UP)
+ spin_lock_bh(&vi->refill_lock);
+ if (dev->flags & IFF_UP && vi->refill_enabled)
schedule_delayed_work(&vi->refill, 0);
+ spin_unlock_bh(&vi->refill_lock);
return 0;
}
@@ -5626,6 +5678,10 @@ static void virtnet_get_base_stats(struct net_device *dev,
if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED)
tx->hw_drop_ratelimits = 0;
+
+ netdev_stat_queue_sum(dev,
+ dev->real_num_rx_queues, vi->max_queue_pairs, rx,
+ dev->real_num_tx_queues, vi->max_queue_pairs, tx);
}
static const struct netdev_stat_ops virtnet_stat_ops = {
@@ -5838,8 +5894,10 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len,
DMA_TO_DEVICE, 0);
- if (virtqueue_dma_mapping_error(sq->vq, hdr_dma))
- return -ENOMEM;
+ if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) {
+ err = -ENOMEM;
+ goto err_free_buffs;
+ }
err = xsk_pool_dma_map(pool, dma_dev, 0);
if (err)
@@ -5867,6 +5925,8 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
err_xsk_map:
virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len,
DMA_TO_DEVICE, 0);
+err_free_buffs:
+ kvfree(rq->xsk_buffs);
return err;
}
@@ -5959,12 +6019,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
if (prog)
bpf_prog_add(prog, vi->max_queue_pairs - 1);
+ virtnet_rx_pause_all(vi);
+
/* Make sure NAPI is not using any XDP TX queues for RX. */
if (netif_running(dev)) {
- for (i = 0; i < vi->max_queue_pairs; i++) {
- virtnet_napi_disable(&vi->rq[i]);
+ for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_tx_disable(&vi->sq[i]);
- }
}
if (!prog) {
@@ -5996,13 +6056,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
vi->xdp_enabled = false;
}
+ virtnet_rx_resume_all(vi);
for (i = 0; i < vi->max_queue_pairs; i++) {
if (old_prog)
bpf_prog_put(old_prog);
- if (netif_running(dev)) {
- virtnet_napi_enable(&vi->rq[i]);
+ if (netif_running(dev))
virtnet_napi_tx_enable(&vi->sq[i]);
- }
}
return 0;
@@ -6014,11 +6073,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
}
+ virtnet_rx_resume_all(vi);
if (netif_running(dev)) {
- for (i = 0; i < vi->max_queue_pairs; i++) {
- virtnet_napi_enable(&vi->rq[i]);
+ for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_tx_enable(&vi->sq[i]);
- }
}
if (prog)
bpf_prog_sub(prog, vi->max_queue_pairs - 1);
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 3df6aab..c676979 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3607,8 +3607,6 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
int err = 0;
- WRITE_ONCE(netdev->mtu, new_mtu);
-
/*
* Reset_work may be in the middle of resetting the device, wait for its
* completion.
@@ -3622,6 +3620,7 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
/* we need to re-create the rx queue based on the new mtu */
vmxnet3_rq_destroy_all(adapter);
+ WRITE_ONCE(netdev->mtu, new_mtu);
vmxnet3_adjust_rx_ring_size(adapter);
err = vmxnet3_rq_create_all(adapter);
if (err) {
@@ -3638,6 +3637,8 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
"Closing it\n", err);
goto out;
}
+ } else {
+ WRITE_ONCE(netdev->mtu, new_mtu);
}
out:
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
index 616ecc3..5f47049 100644
--- a/drivers/net/vmxnet3/vmxnet3_xdp.c
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -397,7 +397,7 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
- rbi->len, false);
+ rcd->len, false);
xdp_buff_clear_frags_flag(&xdp);
xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c
index 6e6e9f0..06d19e9 100644
--- a/drivers/net/vxlan/vxlan_vnifilter.c
+++ b/drivers/net/vxlan/vxlan_vnifilter.c
@@ -627,7 +627,11 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
* default dst remote_ip previously added for this vni
*/
if (!vxlan_addr_any(&vninode->remote_ip) ||
- !vxlan_addr_any(&dst->remote_ip))
+ !vxlan_addr_any(&dst->remote_ip)) {
+ u32 hash_index = fdb_head_index(vxlan, all_zeros_mac,
+ vninode->vni);
+
+ spin_lock_bh(&vxlan->hash_lock[hash_index]);
__vxlan_fdb_delete(vxlan, all_zeros_mac,
(vxlan_addr_any(&vninode->remote_ip) ?
dst->remote_ip : vninode->remote_ip),
@@ -635,6 +639,8 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
vninode->vni, vninode->vni,
dst->remote_ifindex,
true);
+ spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+ }
if (vxlan->dev->flags & IFF_UP) {
if (vxlan_addr_multicast(&vninode->remote_ip) &&
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 2821c27..d06c724 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -896,14 +896,16 @@ brcmf_usb_dl_writeimage(struct brcmf_usbdev_info *devinfo, u8 *fw, int fwlen)
}
/* 1) Prepare USB boot loader for runtime image */
- brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+ err = brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+ if (err)
+ goto fail;
rdlstate = le32_to_cpu(state.state);
rdlbytes = le32_to_cpu(state.bytes);
/* 2) Check we are in the Waiting state */
if (rdlstate != DL_WAITING) {
- brcmf_err("Failed to DL_START\n");
+ brcmf_err("Invalid DL state: %u\n", rdlstate);
err = -EINVAL;
goto fail;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 670031f..59af369 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -142,8 +142,6 @@ const struct iwl_cfg_trans_params iwl_sc_trans_cfg = {
.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
};
-const char iwl_sp_name[] = "Intel(R) Wi-Fi 7 BE213 160MHz";
-
const struct iwl_cfg iwl_cfg_sc = {
.fw_name_mac = "sc",
IWL_DEVICE_SC,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index b9bd89b..acafee5 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -2,7 +2,7 @@
/*
* Copyright (C) 2005-2014, 2018-2021 Intel Corporation
* Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2025 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*/
#ifndef __IWL_CONFIG_H__
#define __IWL_CONFIG_H__
@@ -451,8 +451,11 @@ struct iwl_cfg {
#define IWL_CFG_RF_ID_HR 0x7
#define IWL_CFG_RF_ID_HR1 0x4
-#define IWL_CFG_BW_NO_LIM (U16_MAX - 1)
-#define IWL_CFG_BW_ANY U16_MAX
+#define IWL_CFG_NO_160 0x1
+#define IWL_CFG_160 0x0
+
+#define IWL_CFG_NO_320 0x1
+#define IWL_CFG_320 0x0
#define IWL_CFG_CORES_BT 0x0
#define IWL_CFG_CORES_BT_GNSS 0x5
@@ -464,7 +467,7 @@ struct iwl_cfg {
#define IWL_CFG_IS_JACKET 0x1
#define IWL_SUBDEVICE_RF_ID(subdevice) ((u16)((subdevice) & 0x00F0) >> 4)
-#define IWL_SUBDEVICE_BW_LIM(subdevice) ((u16)((subdevice) & 0x0200) >> 9)
+#define IWL_SUBDEVICE_NO_160(subdevice) ((u16)((subdevice) & 0x0200) >> 9)
#define IWL_SUBDEVICE_CORES(subdevice) ((u16)((subdevice) & 0x1C00) >> 10)
struct iwl_dev_info {
@@ -472,10 +475,10 @@ struct iwl_dev_info {
u16 subdevice;
u16 mac_type;
u16 rf_type;
- u16 bw_limit;
u8 mac_step;
u8 rf_step;
u8 rf_id;
+ u8 no_160;
u8 cores;
u8 cdb;
u8 jacket;
@@ -489,7 +492,7 @@ extern const unsigned int iwl_dev_info_table_size;
const struct iwl_dev_info *
iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
- u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step);
+ u8 jacket, u8 rf_id, u8 no_160, u8 cores, u8 rf_step);
extern const struct pci_device_id iwl_hw_card_ids[];
#endif
@@ -550,7 +553,6 @@ extern const char iwl_ax231_name[];
extern const char iwl_ax411_name[];
extern const char iwl_fm_name[];
extern const char iwl_wh_name[];
-extern const char iwl_sp_name[];
extern const char iwl_gl_name[];
extern const char iwl_mtp_name[];
extern const char iwl_dr_name[];
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index be9e464..3ff493e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -148,6 +148,7 @@
* during a error FW error.
*/
#define CSR_FUNC_SCRATCH_INIT_VALUE (0x01010101)
+#define CSR_FUNC_SCRATCH_POWER_OFF_MASK 0xFFFF
/* Bits for CSR_HW_IF_CONFIG_REG */
#define CSR_HW_IF_CONFIG_REG_MSK_MAC_STEP_DASH (0x0000000F)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index cd1b004..c381511 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2016-2017 Intel Deutschland GmbH
*/
@@ -944,8 +944,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK);
break;
case NL80211_BAND_6GHZ:
- if (!trans->reduced_cap_sku &&
- trans->bw_limit >= 320) {
+ if (!trans->reduced_cap_sku) {
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[0] |=
IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[1] |=
@@ -1095,22 +1094,19 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
iftype_data->eht_cap.eht_mcs_nss_supp.bw._320.rx_tx_mcs13_max_nss = 0;
}
- if (trans->bw_limit < 160)
+ if (trans->no_160)
iftype_data->he_cap.he_cap_elem.phy_cap_info[0] &=
~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
- if (trans->bw_limit < 320 || trans->reduced_cap_sku) {
+ if (trans->reduced_cap_sku) {
memset(&iftype_data->eht_cap.eht_mcs_nss_supp.bw._320, 0,
sizeof(iftype_data->eht_cap.eht_mcs_nss_supp.bw._320));
- iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
- ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK;
- }
-
- if (trans->reduced_cap_sku) {
iftype_data->eht_cap.eht_mcs_nss_supp.bw._80.rx_tx_mcs13_max_nss = 0;
iftype_data->eht_cap.eht_mcs_nss_supp.bw._160.rx_tx_mcs13_max_nss = 0;
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[8] &=
~IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA;
+ iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
+ ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK;
}
}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index c1607b6..e7b2e08 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -21,6 +21,7 @@ struct iwl_trans_dev_restart_data {
struct list_head list;
unsigned int restart_count;
time64_t last_error;
+ bool backoff;
char name[];
};
@@ -125,13 +126,20 @@ iwl_trans_determine_restart_mode(struct iwl_trans *trans)
if (!data)
return at_least;
- if (ktime_get_boottime_seconds() - data->last_error >=
+ if (!data->backoff &&
+ ktime_get_boottime_seconds() - data->last_error >=
IWL_TRANS_RESET_OK_TIME)
data->restart_count = 0;
index = data->restart_count;
- if (index >= ARRAY_SIZE(escalation_list))
+ if (index >= ARRAY_SIZE(escalation_list)) {
index = ARRAY_SIZE(escalation_list) - 1;
+ if (!data->backoff) {
+ data->backoff = true;
+ return IWL_RESET_MODE_BACKOFF;
+ }
+ data->backoff = false;
+ }
return max(at_least, escalation_list[index]);
}
@@ -140,7 +148,8 @@ iwl_trans_determine_restart_mode(struct iwl_trans *trans)
static void iwl_trans_restart_wk(struct work_struct *wk)
{
- struct iwl_trans *trans = container_of(wk, typeof(*trans), restart.wk);
+ struct iwl_trans *trans = container_of(wk, typeof(*trans),
+ restart.wk.work);
struct iwl_trans_reprobe *reprobe;
enum iwl_reset_mode mode;
@@ -168,6 +177,12 @@ static void iwl_trans_restart_wk(struct work_struct *wk)
return;
mode = iwl_trans_determine_restart_mode(trans);
+ if (mode == IWL_RESET_MODE_BACKOFF) {
+ IWL_ERR(trans, "Too many device errors - delay next reset\n");
+ queue_delayed_work(system_unbound_wq, &trans->restart.wk,
+ IWL_TRANS_RESET_DELAY);
+ return;
+ }
iwl_trans_inc_restart_count(trans->dev);
@@ -227,7 +242,7 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
trans->dev = dev;
trans->num_rx_queues = 1;
- INIT_WORK(&trans->restart.wk, iwl_trans_restart_wk);
+ INIT_DELAYED_WORK(&trans->restart.wk, iwl_trans_restart_wk);
return trans;
}
@@ -271,7 +286,7 @@ int iwl_trans_init(struct iwl_trans *trans)
void iwl_trans_free(struct iwl_trans *trans)
{
- cancel_work_sync(&trans->restart.wk);
+ cancel_delayed_work_sync(&trans->restart.wk);
kmem_cache_destroy(trans->dev_cmd_pool);
}
@@ -403,7 +418,7 @@ void iwl_trans_op_mode_leave(struct iwl_trans *trans)
iwl_trans_pcie_op_mode_leave(trans);
- cancel_work_sync(&trans->restart.wk);
+ cancel_delayed_work_sync(&trans->restart.wk);
trans->op_mode = NULL;
@@ -540,7 +555,6 @@ void __releases(nic_access)
iwl_trans_release_nic_access(struct iwl_trans *trans)
{
iwl_trans_pcie_release_nic_access(trans);
- __release(nic_access);
}
IWL_EXPORT_SYMBOL(iwl_trans_release_nic_access);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 25fb4c5..ce4954b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
/*
- * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2016-2017 Intel Deutschland GmbH
*/
@@ -876,7 +876,7 @@ struct iwl_txq {
* only valid for discrete (not integrated) NICs
* @invalid_tx_cmd: invalid TX command buffer
* @reduced_cap_sku: reduced capability supported SKU
- * @bw_limit: the max bandwidth
+ * @no_160: device not supporting 160 MHz
* @step_urm: STEP is in URM, no support for MCS>9 in 320 MHz
* @restart: restart worker data
* @restart.wk: restart worker
@@ -911,8 +911,7 @@ struct iwl_trans {
char hw_id_str[52];
u32 sku_id[3];
bool reduced_cap_sku;
- u16 bw_limit;
- bool step_urm;
+ u8 no_160:1, step_urm:1;
u8 dsbr_urm_fw_dependent:1,
dsbr_urm_permanent:1;
@@ -962,7 +961,7 @@ struct iwl_trans {
struct iwl_dma_ptr invalid_tx_cmd;
struct {
- struct work_struct wk;
+ struct delayed_work wk;
struct iwl_fw_error_dump_mode mode;
bool during_reset;
} restart;
@@ -1163,7 +1162,7 @@ static inline void iwl_trans_schedule_reset(struct iwl_trans *trans,
*/
trans->restart.during_reset = test_bit(STATUS_IN_SW_RESET,
&trans->status);
- queue_work(system_unbound_wq, &trans->restart.wk);
+ queue_delayed_work(system_unbound_wq, &trans->restart.wk, 0);
}
static inline void iwl_trans_fw_error(struct iwl_trans *trans,
@@ -1262,6 +1261,9 @@ enum iwl_reset_mode {
IWL_RESET_MODE_RESCAN,
IWL_RESET_MODE_FUNC_RESET,
IWL_RESET_MODE_PROD_RESET,
+
+ /* keep last - special backoff value */
+ IWL_RESET_MODE_BACKOFF,
};
void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
index db9e0f04..687a945 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/agg.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
@@ -124,9 +124,9 @@ void iwl_mld_handle_bar_frame_release_notif(struct iwl_mld *mld,
rcu_read_lock();
baid_data = rcu_dereference(mld->fw_id_to_ba[baid]);
- if (!IWL_FW_CHECK(mld, !baid_data,
- "Got valid BAID %d but not allocated, invalid BAR release!\n",
- baid))
+ if (IWL_FW_CHECK(mld, !baid_data,
+ "Got valid BAID %d but not allocated, invalid BAR release!\n",
+ baid))
goto out_unlock;
if (IWL_FW_CHECK(mld, tid != baid_data->tid ||
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index 89d95e9..93f9f78e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -949,8 +949,9 @@ void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
snprintf(name, sizeof(name), "%pd", vif->debugfs_dir);
snprintf(target, sizeof(target), "../../../%pd3/iwlmld",
vif->debugfs_dir);
- mld_vif->dbgfs_slink =
- debugfs_create_symlink(name, mld->debugfs_dir, target);
+ if (!mld_vif->dbgfs_slink)
+ mld_vif->dbgfs_slink =
+ debugfs_create_symlink(name, mld->debugfs_dir, target);
if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
vif->type == NL80211_IFTYPE_STATION) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
index 62da137..4b083d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -333,19 +333,22 @@ int iwl_mld_load_fw(struct iwl_mld *mld)
ret = iwl_trans_start_hw(mld->trans);
if (ret)
- return ret;
+ goto err;
ret = iwl_mld_run_fw_init_sequence(mld);
if (ret)
- return ret;
+ goto err;
ret = iwl_mld_init_mcc(mld);
if (ret)
- return ret;
+ goto err;
mld->fw_status.running = true;
return 0;
+err:
+ iwl_mld_stop_fw(mld);
+ return ret;
}
void iwl_mld_stop_fw(struct iwl_mld *mld)
@@ -358,6 +361,10 @@ void iwl_mld_stop_fw(struct iwl_mld *mld)
iwl_trans_stop_device(mld->trans);
+ wiphy_work_cancel(mld->wiphy, &mld->async_handlers_wk);
+
+ iwl_mld_purge_async_handlers_list(mld);
+
mld->fw_status.running = false;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 99e13cf..68d97d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -651,6 +651,7 @@ void iwl_mld_mac80211_remove_interface(struct ieee80211_hw *hw,
#ifdef CONFIG_IWLWIFI_DEBUGFS
debugfs_remove(iwl_mld_vif_from_mac80211(vif)->dbgfs_slink);
+ iwl_mld_vif_from_mac80211(vif)->dbgfs_slink = NULL;
#endif
iwl_mld_rm_vif(mld, vif);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index d4a99ae..73d2166 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -75,6 +75,7 @@ void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
/* Setup async RX handling */
spin_lock_init(&mld->async_handlers_lock);
+ INIT_LIST_HEAD(&mld->async_handlers_list);
wiphy_work_init(&mld->async_handlers_wk,
iwl_mld_async_handlers_wk);
@@ -414,9 +415,14 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
wiphy_unlock(mld->wiphy);
rtnl_unlock();
iwl_fw_flush_dumps(&mld->fwrt);
- goto free_hw;
+ goto err;
}
+ /* We are about to stop the FW. Notifications may require an
+ * operational FW, so handle them all here before we stop.
+ */
+ wiphy_work_flush(mld->wiphy, &mld->async_handlers_wk);
+
iwl_mld_stop_fw(mld);
wiphy_unlock(mld->wiphy);
@@ -455,7 +461,8 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
iwl_mld_leds_exit(mld);
free_nvm:
kfree(mld->nvm_data);
-free_hw:
+err:
+ iwl_trans_op_mode_leave(mld->trans);
ieee80211_free_hw(mld->hw);
return ERR_PTR(ret);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
index 5eceaaf..a4a16da 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -298,11 +298,6 @@ iwl_cleanup_mld(struct iwl_mld *mld)
#endif
iwl_mld_low_latency_restart_cleanup(mld);
-
- /* Empty the list of async notification handlers so we won't process
- * notifications from the dead fw after the reconfig flow.
- */
- iwl_mld_purge_async_handlers_list(mld);
}
enum iwl_power_scheme {
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 93446c3..00056e7 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2016-2017 Intel Deutschland GmbH
*/
@@ -552,17 +552,16 @@ MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_hw_card_ids);
#define _IWL_DEV_INFO(_device, _subdevice, _mac_type, _mac_step, _rf_type, \
- _rf_id, _rf_step, _bw_limit, _cores, _cdb, _cfg, _name) \
+ _rf_id, _rf_step, _no_160, _cores, _cdb, _cfg, _name) \
{ .device = (_device), .subdevice = (_subdevice), .cfg = &(_cfg), \
.name = _name, .mac_type = _mac_type, .rf_type = _rf_type, .rf_step = _rf_step, \
- .bw_limit = _bw_limit, .cores = _cores, .rf_id = _rf_id, \
+ .no_160 = _no_160, .cores = _cores, .rf_id = _rf_id, \
.mac_step = _mac_step, .cdb = _cdb, .jacket = IWL_CFG_ANY }
#define IWL_DEV_INFO(_device, _subdevice, _cfg, _name) \
_IWL_DEV_INFO(_device, _subdevice, IWL_CFG_ANY, IWL_CFG_ANY, \
- IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, \
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY, \
- _cfg, _name)
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, \
+ IWL_CFG_ANY, _cfg, _name)
VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
#if IS_ENABLED(CONFIG_IWLMVM)
@@ -589,6 +588,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
+ IWL_DEV_INFO(0x7F70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
+ IWL_DEV_INFO(0x7F70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name),
IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma, iwl_ax411_killer_1690s_name),
@@ -725,66 +726,66 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_2ac_cfg_soc, iwl9560_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9270_160_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9270_name),
_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9162_160_name),
_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9162_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9260_160_name),
_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9260_2ac_cfg, iwl9260_name),
/* Qu with Jf */
@@ -792,132 +793,132 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550s_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550i_name),
/* Qu C step */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550s_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550i_name),
/* QuZ */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9462_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550s_name),
_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550i_name),
/* Qu with Hr */
@@ -925,189 +926,189 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_b0_hr1_b0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_b0_hr_b0, iwl_ax203_name),
/* Qu C step */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_c0_hr1_b0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_c0_hr_b0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_qu_c0_hr_b0, iwl_ax201_name),
/* QuZ */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_quz_a0_hr1_b0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_quz_a0_hr_b0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_quz_a0_hr_b0, iwl_ax201_name),
/* Ma */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_ma, iwl_ax201_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_ma, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_ma, iwl_ax231_name),
/* So with Hr */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
/* So-F with Hr */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
- 80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
/* So-F with Gf */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
/* SoF with JF2 */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
/* SoF with JF */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
/* So with GF */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
/* So with JF2 */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
/* So with JF */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
- 80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
#endif /* CONFIG_IWLMVM */
@@ -1116,13 +1117,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax201_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
@@ -1134,119 +1135,104 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_wh_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax201_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_bz, iwl_wh_name),
/* Ga (Gl) */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_gl, iwl_gl_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ IWL_CFG_NO_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
iwl_cfg_gl, iwl_mtp_name),
/* Sc */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc, iwl_wh_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
- IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_ANY,
- iwl_cfg_sc, iwl_sp_name),
- _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2, iwl_wh_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
- IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_ANY,
- iwl_cfg_sc2, iwl_sp_name),
- _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2f, iwl_ax211_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2f, iwl_fm_name),
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_sc2f, iwl_wh_name),
- _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
- IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
- 160, IWL_CFG_ANY, IWL_CFG_ANY,
- iwl_cfg_sc2f, iwl_sp_name),
/* Dr */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY,
IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_dr, iwl_dr_name),
/* Br */
_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
IWL_CFG_MAC_TYPE_BR, IWL_CFG_ANY,
IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
- IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
iwl_cfg_br, iwl_br_name),
#endif /* CONFIG_IWLMLD */
};
@@ -1398,7 +1384,7 @@ static int map_crf_id(struct iwl_trans *iwl_trans)
VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info *
iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
- u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step)
+ u8 jacket, u8 rf_id, u8 no_160, u8 cores, u8 rf_step)
{
int num_devices = ARRAY_SIZE(iwl_dev_info_table);
int i;
@@ -1441,15 +1427,8 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
dev_info->rf_id != rf_id)
continue;
- /*
- * Check that bw_limit have the same "boolean" value since
- * IWL_SUBDEVICE_BW_LIM can only return a boolean value and
- * dev_info->bw_limit encodes a non-boolean value.
- * dev_info->bw_limit == IWL_CFG_BW_NO_LIM must be equal to
- * !bw_limit to have a match.
- */
- if (dev_info->bw_limit != IWL_CFG_BW_ANY &&
- (dev_info->bw_limit == IWL_CFG_BW_NO_LIM) == !!bw_limit)
+ if (dev_info->no_160 != (u8)IWL_CFG_ANY &&
+ dev_info->no_160 != no_160)
continue;
if (dev_info->cores != (u8)IWL_CFG_ANY &&
@@ -1587,13 +1566,13 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
CSR_HW_RFID_IS_CDB(iwl_trans->hw_rf_id),
CSR_HW_RFID_IS_JACKET(iwl_trans->hw_rf_id),
IWL_SUBDEVICE_RF_ID(pdev->subsystem_device),
- IWL_SUBDEVICE_BW_LIM(pdev->subsystem_device),
+ IWL_SUBDEVICE_NO_160(pdev->subsystem_device),
IWL_SUBDEVICE_CORES(pdev->subsystem_device),
CSR_HW_RFID_STEP(iwl_trans->hw_rf_id));
if (dev_info) {
iwl_trans->cfg = dev_info->cfg;
iwl_trans->name = dev_info->name;
- iwl_trans->bw_limit = dev_info->bw_limit;
+ iwl_trans->no_160 = dev_info->no_160 == IWL_CFG_NO_160;
}
#if IS_ENABLED(CONFIG_IWLMVM)
@@ -1759,11 +1738,27 @@ static int _iwl_pci_resume(struct device *device, bool restore)
* Scratch value was altered, this means the device was powered off, we
* need to reset it completely.
* Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
- * so assume that any bits there mean that the device is usable.
+ * but not bits [15:8]. So if we have bits set in lower word, assume
+ * the device is alive.
+ * For older devices, just try silently to grab the NIC.
*/
- if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
- !iwl_read32(trans, CSR_FUNC_SCRATCH))
- device_was_powered_off = true;
+ if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+ if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) &
+ CSR_FUNC_SCRATCH_POWER_OFF_MASK))
+ device_was_powered_off = true;
+ } else {
+ /*
+ * bh are re-enabled by iwl_trans_pcie_release_nic_access,
+ * so re-enable them if _iwl_trans_pcie_grab_nic_access fails.
+ */
+ local_bh_disable();
+ if (_iwl_trans_pcie_grab_nic_access(trans, true)) {
+ iwl_trans_pcie_release_nic_access(trans);
+ } else {
+ device_was_powered_off = true;
+ local_bh_enable();
+ }
+ }
if (restore || device_was_powered_off) {
trans->state = IWL_TRANS_NO_FW;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 45460f9..114a919 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -558,10 +558,10 @@ void iwl_trans_pcie_free(struct iwl_trans *trans);
void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions,
struct device *dev);
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-#define _iwl_trans_pcie_grab_nic_access(trans) \
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent);
+#define _iwl_trans_pcie_grab_nic_access(trans, silent) \
__cond_lock(nic_access_nobh, \
- likely(__iwl_trans_pcie_grab_nic_access(trans)))
+ likely(__iwl_trans_pcie_grab_nic_access(trans, silent)))
void iwl_trans_pcie_check_product_reset_status(struct pci_dev *pdev);
void iwl_trans_pcie_check_product_reset_mode(struct pci_dev *pdev);
@@ -1105,7 +1105,8 @@ void iwl_trans_pcie_set_bits_mask(struct iwl_trans *trans, u32 reg,
int iwl_trans_pcie_read_config32(struct iwl_trans *trans, u32 ofs,
u32 *val);
bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
/* transport gen 1 exported functions */
void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index c917ed4..102a612 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2351,7 +2351,8 @@ void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode)
struct iwl_trans_pcie_removal *removal;
char _msg = 0, *msg = &_msg;
- if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY))
+ if (WARN_ON(mode < IWL_RESET_MODE_REMOVE_ONLY ||
+ mode == IWL_RESET_MODE_BACKOFF))
return;
if (test_bit(STATUS_TRANS_DEAD, &trans->status))
@@ -2405,7 +2406,7 @@ EXPORT_SYMBOL(iwl_trans_pcie_reset);
* This version doesn't disable BHs but rather assumes they're
* already disabled.
*/
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent)
{
int ret;
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2457,6 +2458,11 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
if (unlikely(ret < 0)) {
u32 cntrl = iwl_read32(trans, CSR_GP_CNTRL);
+ if (silent) {
+ spin_unlock(&trans_pcie->reg_lock);
+ return false;
+ }
+
WARN_ONCE(1,
"Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n",
cntrl);
@@ -2488,7 +2494,7 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
bool ret;
local_bh_disable();
- ret = __iwl_trans_pcie_grab_nic_access(trans);
+ ret = __iwl_trans_pcie_grab_nic_access(trans, false);
if (ret) {
/* keep BHs disabled until iwl_trans_pcie_release_nic_access */
return ret;
@@ -2497,7 +2503,8 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
return false;
}
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2524,6 +2531,7 @@ void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
* scheduled on different CPUs (after we drop reg_lock).
*/
out:
+ __release(nic_access_nobh);
spin_unlock_bh(&trans_pcie->reg_lock);
}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index bb90bcf..9fc4e98 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1021,7 +1021,7 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans,
* returned. This needs to be done only on NICs that have
* apmg_wake_up_wa set (see above.)
*/
- if (!_iwl_trans_pcie_grab_nic_access(trans))
+ if (!_iwl_trans_pcie_grab_nic_access(trans, false))
return -EIO;
/*
diff --git a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
index 7ef5e89..d0bda23 100644
--- a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
+++ b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
@@ -2,7 +2,7 @@
/*
* KUnit tests for the iwlwifi device info table
*
- * Copyright (C) 2023-2025 Intel Corporation
+ * Copyright (C) 2023-2024 Intel Corporation
*/
#include <kunit/test.h>
#include <linux/pci.h>
@@ -13,9 +13,9 @@ MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
static void iwl_pci_print_dev_info(const char *pfx, const struct iwl_dev_info *di)
{
- printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,bw_limit=%d,cores=%.2x\n",
+ printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,no_160=%d,cores=%.2x\n",
pfx, di->device, di->subdevice, di->mac_type, di->mac_step,
- di->rf_type, di->cdb, di->jacket, di->rf_id, di->bw_limit,
+ di->rf_type, di->cdb, di->jacket, di->rf_id, di->no_160,
di->cores);
}
@@ -31,13 +31,8 @@ static void devinfo_table_order(struct kunit *test)
di->mac_type, di->mac_step,
di->rf_type, di->cdb,
di->jacket, di->rf_id,
- di->bw_limit != IWL_CFG_BW_NO_LIM,
- di->cores, di->rf_step);
- if (!ret) {
- iwl_pci_print_dev_info("No entry found for: ", di);
- KUNIT_FAIL(test,
- "No entry found for entry at index %d\n", idx);
- } else if (ret != di) {
+ di->no_160, di->cores, di->rf_step);
+ if (ret != di) {
iwl_pci_print_dev_info("searched: ", di);
iwl_pci_print_dev_info("found: ", ret);
KUNIT_FAIL(test,
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 844af16..35b4ec9 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -1011,6 +1011,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
int i;
mt76_worker_disable(&dev->tx_worker);
+ napi_disable(&dev->tx_napi);
netif_napi_del(&dev->tx_napi);
for (i = 0; i < ARRAY_SIZE(dev->phys); i++) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index e61da76..14b1f60 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -1924,14 +1924,14 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy,
mt7925_mcu_sta_mld_tlv(skb, info->vif, info->link_sta->sta);
mt7925_mcu_sta_eht_mld_tlv(skb, info->vif, info->link_sta->sta);
}
-
- mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta);
}
if (!info->enable) {
mt7925_mcu_sta_remove_tlv(skb);
mt76_connac_mcu_add_tlv(skb, STA_REC_MLD_OFF,
sizeof(struct tlv));
+ } else {
+ mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta);
}
return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true);
diff --git a/drivers/net/wireless/purelifi/plfxlc/mac.c b/drivers/net/wireless/purelifi/plfxlc/mac.c
index eae93ef..82d1bf7 100644
--- a/drivers/net/wireless/purelifi/plfxlc/mac.c
+++ b/drivers/net/wireless/purelifi/plfxlc/mac.c
@@ -102,7 +102,6 @@ int plfxlc_mac_init_hw(struct ieee80211_hw *hw)
void plfxlc_mac_release(struct plfxlc_mac *mac)
{
plfxlc_chip_release(&mac->chip);
- lockdep_assert_held(&mac->lock);
}
int plfxlc_op_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index fc52d5c..5091e1f 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -985,20 +985,27 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
act = bpf_prog_run_xdp(prog, xdp);
switch (act) {
case XDP_TX:
- get_page(pdata);
xdpf = xdp_convert_buff_to_frame(xdp);
- err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
- if (unlikely(!err))
- xdp_return_frame_rx_napi(xdpf);
- else if (unlikely(err < 0))
+ if (unlikely(!xdpf)) {
trace_xdp_exception(queue->info->netdev, prog, act);
+ break;
+ }
+ get_page(pdata);
+ err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
+ if (unlikely(err <= 0)) {
+ if (err < 0)
+ trace_xdp_exception(queue->info->netdev, prog, act);
+ xdp_return_frame_rx_napi(xdpf);
+ }
break;
case XDP_REDIRECT:
get_page(pdata);
err = xdp_do_redirect(queue->info->netdev, xdp, prog);
*need_xdp_flush = true;
- if (unlikely(err))
+ if (unlikely(err)) {
trace_xdp_exception(queue->info->netdev, prog, act);
+ xdp_return_buff(xdp);
+ }
break;
case XDP_PASS:
case XDP_DROP:
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index d47dfa8..4d64b69 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -102,6 +102,7 @@
depends on NVME_TCP
select NET_HANDSHAKE
select KEYS
+ select TLS
help
Enables TLS encryption for NVMe TCP using the netlink handshake API.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index eb6ea8a..6b04473 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2059,7 +2059,21 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
else
- atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+ atomic_bs = (1 + ns->ctrl->awupf) * bs;
+
+ /*
+ * Set subsystem atomic bs.
+ */
+ if (ns->ctrl->subsys->atomic_bs) {
+ if (atomic_bs != ns->ctrl->subsys->atomic_bs) {
+ dev_err_ratelimited(ns->ctrl->device,
+ "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
+ ns->disk ? ns->disk->disk_name : "?",
+ ns->ctrl->subsys->atomic_bs,
+ atomic_bs);
+ }
+ } else
+ ns->ctrl->subsys->atomic_bs = atomic_bs;
nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
}
@@ -2201,6 +2215,17 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
nvme_set_chunk_sectors(ns, id, &lim);
if (!nvme_update_disk_info(ns, id, &lim))
capacity = 0;
+
+ /*
+ * Validate the max atomic write size fits within the subsystem's
+ * atomic write capabilities.
+ */
+ if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) {
+ blk_mq_unfreeze_queue(ns->disk->queue, memflags);
+ ret = -ENXIO;
+ goto out;
+ }
+
nvme_config_discard(ns, &lim);
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
ns->head->ids.csi == NVME_CSI_ZNS)
@@ -3031,7 +3056,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
kfree(subsys);
return -EINVAL;
}
- subsys->awupf = le16_to_cpu(id->awupf);
nvme_mpath_default_iopolicy(subsys);
subsys->dev.class = &nvme_subsys_class;
@@ -3441,7 +3465,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
dev_pm_qos_expose_latency_tolerance(ctrl->device);
else if (!ctrl->apst_enabled && prev_apst_enabled)
dev_pm_qos_hide_latency_tolerance(ctrl->device);
-
+ ctrl->awupf = le16_to_cpu(id->awupf);
out_free:
kfree(id);
return ret;
@@ -4493,7 +4517,8 @@ static void nvme_fw_act_work(struct work_struct *work)
msleep(100);
}
- if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
+ if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) ||
+ !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
return;
nvme_unquiesce_io_queues(ctrl);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 250f3da..cf0ef47 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -638,7 +638,8 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
blk_set_stacking_limits(&lim);
lim.dma_alignment = 3;
- lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+ lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT |
+ BLK_FEAT_POLL | BLK_FEAT_ATOMIC_WRITES;
if (head->ids.csi == NVME_CSI_ZNS)
lim.features |= BLK_FEAT_ZONED;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 51e0786..8fc4683 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -410,6 +410,7 @@ struct nvme_ctrl {
enum nvme_ctrl_type cntrltype;
enum nvme_dctype dctype;
+ u16 awupf; /* 0's based value. */
};
static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -442,11 +443,11 @@ struct nvme_subsystem {
u8 cmic;
enum nvme_subsys_type subtype;
u16 vendor_id;
- u16 awupf; /* 0's based awupf value. */
struct ida ns_ida;
#ifdef CONFIG_NVME_MULTIPATH
enum nvme_iopolicy iopolicy;
#endif
+ u32 atomic_bs;
};
/*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index b178d52..f1dd804 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -390,7 +390,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
* as it only leads to a small amount of wasted memory for the lifetime of
* the I/O.
*/
-static int nvme_pci_npages_prp(void)
+static __always_inline int nvme_pci_npages_prp(void)
{
unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
@@ -1202,7 +1202,9 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+ spin_lock(&nvmeq->cq_poll_lock);
nvme_poll_cq(nvmeq, NULL);
+ spin_unlock(&nvmeq->cq_poll_lock);
enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
}
@@ -3575,7 +3577,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
dev_info(dev->ctrl.device, "restart after slot reset\n");
pci_restore_state(pdev);
- if (!nvme_try_sched_reset(&dev->ctrl))
+ if (nvme_try_sched_reset(&dev->ctrl))
nvme_unquiesce_io_queues(&dev->ctrl);
return PCI_ERS_RESULT_RECOVERED;
}
@@ -3623,6 +3625,9 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */
.driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, },
+ { PCI_DEVICE(0x126f, 0x1001), /* Silicon Motion generic */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */
.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
NVME_QUIRK_BOGUS_NID, },
@@ -3646,6 +3651,9 @@ static const struct pci_device_id nvme_id_table[] = {
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x15b7, 0x5008), /* Sandisk SN530 */
.driver_data = NVME_QUIRK_BROKEN_MSI },
+ { PCI_DEVICE(0x15b7, 0x5009), /* Sandisk SN550 */
+ .driver_data = NVME_QUIRK_BROKEN_MSI |
+ NVME_QUIRK_NO_DEEPEST_PS },
{ PCI_DEVICE(0x1987, 0x5012), /* Phison E12 */
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */
@@ -3731,6 +3739,8 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
{ PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+ { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
{ PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 6d31226..a5bc3bb 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -306,13 +306,41 @@ static const struct attribute_group nvme_ns_attr_group = {
};
#ifdef CONFIG_NVME_MULTIPATH
+/*
+ * NOTE: The dummy attribute does not appear in sysfs. It exists solely to allow
+ * control over the visibility of the multipath sysfs node. Without at least one
+ * attribute defined in nvme_ns_mpath_attrs[], the sysfs implementation does not
+ * invoke the multipath_sysfs_group_visible() method. As a result, we would not
+ * be able to control the visibility of the multipath sysfs node.
+ */
+static struct attribute dummy_attr = {
+ .name = "dummy",
+};
+
static struct attribute *nvme_ns_mpath_attrs[] = {
+ &dummy_attr,
NULL,
};
+static bool multipath_sysfs_group_visible(struct kobject *kobj)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+
+ return nvme_disk_is_ns_head(dev_to_disk(dev));
+}
+
+static bool multipath_sysfs_attr_visible(struct kobject *kobj,
+ struct attribute *attr, int n)
+{
+ return false;
+}
+
+DEFINE_SYSFS_GROUP_VISIBLE(multipath_sysfs)
+
const struct attribute_group nvme_ns_mpath_attr_group = {
.name = "multipath",
.attrs = nvme_ns_mpath_attrs,
+ .is_visible = SYSFS_GROUP_VISIBLE(multipath_sysfs),
};
#endif
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 72d2602..aba365f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1946,7 +1946,7 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
cancel_work_sync(&queue->io_work);
}
-static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+static void nvme_tcp_stop_queue_nowait(struct nvme_ctrl *nctrl, int qid)
{
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
@@ -1965,6 +1965,31 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
mutex_unlock(&queue->queue_lock);
}
+static void nvme_tcp_wait_queue(struct nvme_ctrl *nctrl, int qid)
+{
+ struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+ struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+ int timeout = 100;
+
+ while (timeout > 0) {
+ if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags) ||
+ !sk_wmem_alloc_get(queue->sock->sk))
+ return;
+ msleep(2);
+ timeout -= 2;
+ }
+ dev_warn(nctrl->device,
+ "qid %d: timeout draining sock wmem allocation expired\n",
+ qid);
+}
+
+static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+{
+ nvme_tcp_stop_queue_nowait(nctrl, qid);
+ nvme_tcp_wait_queue(nctrl, qid);
+}
+
+
static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue)
{
write_lock_bh(&queue->sock->sk->sk_callback_lock);
@@ -2032,7 +2057,9 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
int i;
for (i = 1; i < ctrl->queue_count; i++)
- nvme_tcp_stop_queue(ctrl, i);
+ nvme_tcp_stop_queue_nowait(ctrl, i);
+ for (i = 1; i < ctrl->queue_count; i++)
+ nvme_tcp_wait_queue(ctrl, i);
}
static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index fb7446d..4c253b4 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -98,6 +98,7 @@
bool "NVMe over Fabrics TCP target TLS encryption support"
depends on NVME_TARGET_TCP
select NET_HANDSHAKE
+ select TLS
help
Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index cef8d77..9429b82 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -600,13 +600,12 @@ void nvmet_auth_insert_psk(struct nvmet_sq *sq)
pr_warn("%s: ctrl %d qid %d failed to refresh key, error %ld\n",
__func__, sq->ctrl->cntlid, sq->qid, PTR_ERR(tls_key));
tls_key = NULL;
- kfree_sensitive(tls_psk);
}
if (sq->ctrl->tls_key)
key_put(sq->ctrl->tls_key);
sq->ctrl->tls_key = tls_key;
#endif
-
+ kfree_sensitive(tls_psk);
out_free_digest:
kfree_sensitive(digest);
out_free_psk:
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 71f8d06..245475c 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -324,6 +324,9 @@ int nvmet_enable_port(struct nvmet_port *port)
lockdep_assert_held(&nvmet_config_sem);
+ if (port->disc_addr.trtype == NVMF_TRTYPE_MAX)
+ return -EINVAL;
+
ops = nvmet_transports[port->disc_addr.trtype];
if (!ops) {
up_write(&nvmet_config_sem);
diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index 7fab7f3..7123c85 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -62,8 +62,7 @@ static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex);
#define NVMET_PCI_EPF_CQ_RETRY_INTERVAL msecs_to_jiffies(1)
enum nvmet_pci_epf_queue_flags {
- NVMET_PCI_EPF_Q_IS_SQ = 0, /* The queue is a submission queue */
- NVMET_PCI_EPF_Q_LIVE, /* The queue is live */
+ NVMET_PCI_EPF_Q_LIVE = 0, /* The queue is live */
NVMET_PCI_EPF_Q_IRQ_ENABLED, /* IRQ is enabled for this queue */
};
@@ -596,9 +595,6 @@ static bool nvmet_pci_epf_should_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
struct nvmet_pci_epf_irq_vector *iv = cq->iv;
bool ret;
- if (!test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
- return false;
-
/* IRQ coalescing for the admin queue is not allowed. */
if (!cq->qid)
return true;
@@ -625,7 +621,8 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
struct pci_epf *epf = nvme_epf->epf;
int ret = 0;
- if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+ if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags) ||
+ !test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
return;
mutex_lock(&ctrl->irq_lock);
@@ -636,14 +633,16 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
switch (nvme_epf->irq_type) {
case PCI_IRQ_MSIX:
case PCI_IRQ_MSI:
+ /*
+ * If we fail to raise an MSI or MSI-X interrupt, it is likely
+ * because the host is using legacy INTX IRQs (e.g. BIOS,
+ * grub), but we can fallback to the INTX type only if the
+ * endpoint controller supports this type.
+ */
ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
nvme_epf->irq_type, cq->vector + 1);
- if (!ret)
+ if (!ret || !nvme_epf->epc_features->intx_capable)
break;
- /*
- * If we got an error, it is likely because the host is using
- * legacy IRQs (e.g. BIOS, grub).
- */
fallthrough;
case PCI_IRQ_INTX:
ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
@@ -656,7 +655,9 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
}
if (ret)
- dev_err(ctrl->dev, "Failed to raise IRQ (err=%d)\n", ret);
+ dev_err_ratelimited(ctrl->dev,
+ "CQ[%u]: Failed to raise IRQ (err=%d)\n",
+ cq->qid, ret);
unlock:
mutex_unlock(&ctrl->irq_lock);
@@ -1319,8 +1320,14 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags);
- dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
- cqid, qsize, cq->qes, cq->vector);
+ if (test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+ dev_dbg(ctrl->dev,
+ "CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
+ cqid, qsize, cq->qes, cq->vector);
+ else
+ dev_dbg(ctrl->dev,
+ "CQ[%u]: %u entries of %zu B, IRQ disabled\n",
+ cqid, qsize, cq->qes);
return NVME_SC_SUCCESS;
@@ -1344,7 +1351,8 @@ static u16 nvmet_pci_epf_delete_cq(struct nvmet_ctrl *tctrl, u16 cqid)
cancel_delayed_work_sync(&cq->work);
nvmet_pci_epf_drain_queue(cq);
- nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
+ if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+ nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &cq->pci_map);
return NVME_SC_SUCCESS;
@@ -1533,7 +1541,6 @@ static void nvmet_pci_epf_init_queue(struct nvmet_pci_epf_ctrl *ctrl,
if (sq) {
queue = &ctrl->sq[qid];
- set_bit(NVMET_PCI_EPF_Q_IS_SQ, &queue->flags);
} else {
queue = &ctrl->cq[qid];
INIT_DELAYED_WORK(&queue->work, nvmet_pci_epf_cq_work);
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f2d0c92..12a5cb8 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1560,6 +1560,9 @@ static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue)
{
struct socket *sock = queue->sock;
+ if (!queue->state_change)
+ return;
+
write_lock_bh(&sock->sk->sk_callback_lock);
sock->sk->sk_data_ready = queue->data_ready;
sock->sk->sk_state_change = queue->state_change;
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index fff85bb..e206efc 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -594,9 +594,11 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
cell->nbits = info->nbits;
cell->np = info->np;
- if (cell->nbits)
+ if (cell->nbits) {
cell->bytes = DIV_ROUND_UP(cell->nbits + cell->bit_offset,
BITS_PER_BYTE);
+ cell->raw_len = ALIGN(cell->bytes, nvmem->word_size);
+ }
if (!IS_ALIGNED(cell->offset, nvmem->stride)) {
dev_err(&nvmem->dev,
@@ -605,6 +607,18 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
return -EINVAL;
}
+ if (!IS_ALIGNED(cell->raw_len, nvmem->word_size)) {
+ dev_err(&nvmem->dev,
+ "cell %s raw len %zd unaligned to nvmem word size %d\n",
+ cell->name ?: "<unknown>", cell->raw_len,
+ nvmem->word_size);
+
+ if (info->raw_len)
+ return -EINVAL;
+
+ cell->raw_len = ALIGN(cell->raw_len, nvmem->word_size);
+ }
+
return 0;
}
@@ -837,7 +851,9 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
if (addr && len == (2 * sizeof(u32))) {
info.bit_offset = be32_to_cpup(addr++);
info.nbits = be32_to_cpup(addr);
- if (info.bit_offset >= BITS_PER_BYTE || info.nbits < 1) {
+ if (info.bit_offset >= BITS_PER_BYTE * info.bytes ||
+ info.nbits < 1 ||
+ info.bit_offset + info.nbits > BITS_PER_BYTE * info.bytes) {
dev_err(dev, "nvmem: invalid bits on %pOF\n", child);
of_node_put(child);
return -EINVAL;
@@ -1630,21 +1646,29 @@ EXPORT_SYMBOL_GPL(nvmem_cell_put);
static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void *buf)
{
u8 *p, *b;
- int i, extra, bit_offset = cell->bit_offset;
+ int i, extra, bytes_offset;
+ int bit_offset = cell->bit_offset;
p = b = buf;
- if (bit_offset) {
+
+ bytes_offset = bit_offset / BITS_PER_BYTE;
+ b += bytes_offset;
+ bit_offset %= BITS_PER_BYTE;
+
+ if (bit_offset % BITS_PER_BYTE) {
/* First shift */
- *b++ >>= bit_offset;
+ *p = *b++ >> bit_offset;
/* setup rest of the bytes if any */
for (i = 1; i < cell->bytes; i++) {
/* Get bits from next byte and shift them towards msb */
- *p |= *b << (BITS_PER_BYTE - bit_offset);
+ *p++ |= *b << (BITS_PER_BYTE - bit_offset);
- p = b;
- *b++ >>= bit_offset;
+ *p = *b++ >> bit_offset;
}
+ } else if (p != b) {
+ memmove(p, b, cell->bytes - bytes_offset);
+ p += cell->bytes - 1;
} else {
/* point to the msb */
p += cell->bytes - 1;
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index 116a39e..a872c640 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -321,19 +321,32 @@ static int qfprom_reg_read(void *context,
unsigned int reg, void *_val, size_t bytes)
{
struct qfprom_priv *priv = context;
- u8 *val = _val;
- int i = 0, words = bytes;
+ u32 *val = _val;
void __iomem *base = priv->qfpcorrected;
+ int words = DIV_ROUND_UP(bytes, sizeof(u32));
+ int i;
if (read_raw_data && priv->qfpraw)
base = priv->qfpraw;
- while (words--)
- *val++ = readb(base + reg + i++);
+ for (i = 0; i < words; i++)
+ *val++ = readl(base + reg + i * sizeof(u32));
return 0;
}
+/* Align reads to word boundary */
+static void qfprom_fixup_dt_cell_info(struct nvmem_device *nvmem,
+ struct nvmem_cell_info *cell)
+{
+ unsigned int byte_offset = cell->offset % sizeof(u32);
+
+ cell->bit_offset += byte_offset * BITS_PER_BYTE;
+ cell->offset -= byte_offset;
+ if (byte_offset && !cell->nbits)
+ cell->nbits = cell->bytes * BITS_PER_BYTE;
+}
+
static void qfprom_runtime_disable(void *data)
{
pm_runtime_disable(data);
@@ -358,10 +371,11 @@ static int qfprom_probe(struct platform_device *pdev)
struct nvmem_config econfig = {
.name = "qfprom",
.add_legacy_fixed_of_cells = true,
- .stride = 1,
- .word_size = 1,
+ .stride = 4,
+ .word_size = 4,
.id = NVMEM_DEVID_AUTO,
.reg_read = qfprom_reg_read,
+ .fixup_dt_cell_info = qfprom_fixup_dt_cell_info,
};
struct device *dev = &pdev->dev;
struct resource *res;
diff --git a/drivers/nvmem/rockchip-otp.c b/drivers/nvmem/rockchip-otp.c
index ebc3f0b..d88f12c 100644
--- a/drivers/nvmem/rockchip-otp.c
+++ b/drivers/nvmem/rockchip-otp.c
@@ -59,7 +59,6 @@
#define RK3588_OTPC_AUTO_EN 0x08
#define RK3588_OTPC_INT_ST 0x84
#define RK3588_OTPC_DOUT0 0x20
-#define RK3588_NO_SECURE_OFFSET 0x300
#define RK3588_NBYTES 4
#define RK3588_BURST_NUM 1
#define RK3588_BURST_SHIFT 8
@@ -69,6 +68,7 @@
struct rockchip_data {
int size;
+ int read_offset;
const char * const *clks;
int num_clks;
nvmem_reg_read_t reg_read;
@@ -196,7 +196,7 @@ static int rk3588_otp_read(void *context, unsigned int offset,
addr_start = round_down(offset, RK3588_NBYTES) / RK3588_NBYTES;
addr_end = round_up(offset + bytes, RK3588_NBYTES) / RK3588_NBYTES;
addr_len = addr_end - addr_start;
- addr_start += RK3588_NO_SECURE_OFFSET;
+ addr_start += otp->data->read_offset / RK3588_NBYTES;
buf = kzalloc(array_size(addr_len, RK3588_NBYTES), GFP_KERNEL);
if (!buf)
@@ -274,12 +274,21 @@ static const struct rockchip_data px30_data = {
.reg_read = px30_otp_read,
};
+static const struct rockchip_data rk3576_data = {
+ .size = 0x100,
+ .read_offset = 0x700,
+ .clks = px30_otp_clocks,
+ .num_clks = ARRAY_SIZE(px30_otp_clocks),
+ .reg_read = rk3588_otp_read,
+};
+
static const char * const rk3588_otp_clocks[] = {
"otp", "apb_pclk", "phy", "arb",
};
static const struct rockchip_data rk3588_data = {
.size = 0x400,
+ .read_offset = 0xc00,
.clks = rk3588_otp_clocks,
.num_clks = ARRAY_SIZE(rk3588_otp_clocks),
.reg_read = rk3588_otp_read,
@@ -295,6 +304,10 @@ static const struct of_device_id rockchip_otp_match[] = {
.data = &px30_data,
},
{
+ .compatible = "rockchip,rk3576-otp",
+ .data = &rk3576_data,
+ },
+ {
.compatible = "rockchip,rk3588-otp",
.data = &rk3588_data,
},
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index 055518e..e9e9aaa 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -59,7 +59,6 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
if (pdev && pci_num_vf(pdev)) {
- pci_dev_put(pdev);
rc = -EBUSY;
goto out;
}
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 54d6f4f..e994c54 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -187,6 +187,9 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
panic("%s: kzalloc() failed!\n", __func__);
tmp->res = r;
tmp->dev = dev;
+ tmp->start = r->start;
+ tmp->end = r->end;
+ tmp->flags = r->flags;
/* Fallback is smallest one or list is empty */
n = head;
@@ -545,6 +548,7 @@ static void __assign_resources_sorted(struct list_head *head,
pci_dbg(dev, "%s %pR: releasing\n", res_name, res);
release_resource(res);
+ restore_dev_resource(dev_res);
}
/* Restore start/end/flags from saved list */
list_for_each_entry(save_res, &save_head, list)
diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c
index 2bec706..f59caff 100644
--- a/drivers/phy/phy-can-transceiver.c
+++ b/drivers/phy/phy-can-transceiver.c
@@ -93,6 +93,16 @@ static const struct of_device_id can_transceiver_phy_ids[] = {
};
MODULE_DEVICE_TABLE(of, can_transceiver_phy_ids);
+/* Temporary wrapper until the multiplexer subsystem supports optional muxes */
+static inline struct mux_state *
+devm_mux_state_get_optional(struct device *dev, const char *mux_name)
+{
+ if (!of_property_present(dev->of_node, "mux-states"))
+ return NULL;
+
+ return devm_mux_state_get(dev, mux_name);
+}
+
static int can_transceiver_phy_probe(struct platform_device *pdev)
{
struct phy_provider *phy_provider;
@@ -114,13 +124,11 @@ static int can_transceiver_phy_probe(struct platform_device *pdev)
match = of_match_node(can_transceiver_phy_ids, pdev->dev.of_node);
drvdata = match->data;
- mux_state = devm_mux_state_get(dev, NULL);
- if (IS_ERR(mux_state)) {
- if (PTR_ERR(mux_state) == -EPROBE_DEFER)
- return PTR_ERR(mux_state);
- } else {
- can_transceiver_phy->mux_state = mux_state;
- }
+ mux_state = devm_mux_state_get_optional(dev, NULL);
+ if (IS_ERR(mux_state))
+ return PTR_ERR(mux_state);
+
+ can_transceiver_phy->mux_state = mux_state;
phy = devm_phy_create(dev, dev->of_node,
&can_transceiver_phy_ops);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index 45b3b79..b33e2e2 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -1754,7 +1754,8 @@ static void qmp_ufs_init_registers(struct qmp_ufs *qmp, const struct qmp_phy_cfg
qmp_ufs_init_all(qmp, &cfg->tbls_hs_overlay[i]);
}
- qmp_ufs_init_all(qmp, &cfg->tbls_hs_b);
+ if (qmp->mode == PHY_MODE_UFS_HS_B)
+ qmp_ufs_init_all(qmp, &cfg->tbls_hs_b);
}
static int qmp_ufs_com_init(struct qmp_ufs *qmp)
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 775f4f9..9fdf17e 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -9,6 +9,7 @@
* Copyright (C) 2014 Cogent Embedded, Inc.
*/
+#include <linux/cleanup.h>
#include <linux/extcon-provider.h>
#include <linux/interrupt.h>
#include <linux/io.h>
@@ -107,7 +108,6 @@ struct rcar_gen3_phy {
struct rcar_gen3_chan *ch;
u32 int_enable_bits;
bool initialized;
- bool otg_initialized;
bool powered;
};
@@ -119,9 +119,8 @@ struct rcar_gen3_chan {
struct regulator *vbus;
struct reset_control *rstc;
struct work_struct work;
- struct mutex lock; /* protects rphys[...].powered */
+ spinlock_t lock; /* protects access to hardware and driver data structure. */
enum usb_dr_mode dr_mode;
- int irq;
u32 obint_enable_bits;
bool extcon_host;
bool is_otg_channel;
@@ -320,16 +319,15 @@ static bool rcar_gen3_is_any_rphy_initialized(struct rcar_gen3_chan *ch)
return false;
}
-static bool rcar_gen3_needs_init_otg(struct rcar_gen3_chan *ch)
+static bool rcar_gen3_is_any_otg_rphy_initialized(struct rcar_gen3_chan *ch)
{
- int i;
-
- for (i = 0; i < NUM_OF_PHYS; i++) {
- if (ch->rphys[i].otg_initialized)
- return false;
+ for (enum rcar_gen3_phy_index i = PHY_INDEX_BOTH_HC; i <= PHY_INDEX_EHCI;
+ i++) {
+ if (ch->rphys[i].initialized)
+ return true;
}
- return true;
+ return false;
}
static bool rcar_gen3_are_all_rphys_power_off(struct rcar_gen3_chan *ch)
@@ -351,7 +349,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr,
bool is_b_device;
enum phy_mode cur_mode, new_mode;
- if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
+ guard(spinlock_irqsave)(&ch->lock);
+
+ if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch))
return -EIO;
if (sysfs_streq(buf, "host"))
@@ -389,7 +389,7 @@ static ssize_t role_show(struct device *dev, struct device_attribute *attr,
{
struct rcar_gen3_chan *ch = dev_get_drvdata(dev);
- if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
+ if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch))
return -EIO;
return sprintf(buf, "%s\n", rcar_gen3_is_host(ch) ? "host" :
@@ -402,6 +402,9 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
void __iomem *usb2_base = ch->base;
u32 val;
+ if (!ch->is_otg_channel || rcar_gen3_is_any_otg_rphy_initialized(ch))
+ return;
+
/* Should not use functions of read-modify-write a register */
val = readl(usb2_base + USB2_LINECTRL1);
val = (val & ~USB2_LINECTRL1_DP_RPD) | USB2_LINECTRL1_DPRPD_EN |
@@ -415,7 +418,7 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
val = readl(usb2_base + USB2_ADPCTRL);
writel(val | USB2_ADPCTRL_IDPULLUP, usb2_base + USB2_ADPCTRL);
}
- msleep(20);
+ mdelay(20);
writel(0xffffffff, usb2_base + USB2_OBINTSTA);
writel(ch->obint_enable_bits, usb2_base + USB2_OBINTEN);
@@ -427,16 +430,27 @@ static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch)
{
struct rcar_gen3_chan *ch = _ch;
void __iomem *usb2_base = ch->base;
- u32 status = readl(usb2_base + USB2_OBINTSTA);
+ struct device *dev = ch->dev;
irqreturn_t ret = IRQ_NONE;
+ u32 status;
- if (status & ch->obint_enable_bits) {
- dev_vdbg(ch->dev, "%s: %08x\n", __func__, status);
- writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA);
- rcar_gen3_device_recognition(ch);
- ret = IRQ_HANDLED;
+ pm_runtime_get_noresume(dev);
+
+ if (pm_runtime_suspended(dev))
+ goto rpm_put;
+
+ scoped_guard(spinlock, &ch->lock) {
+ status = readl(usb2_base + USB2_OBINTSTA);
+ if (status & ch->obint_enable_bits) {
+ dev_vdbg(dev, "%s: %08x\n", __func__, status);
+ writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA);
+ rcar_gen3_device_recognition(ch);
+ ret = IRQ_HANDLED;
+ }
}
+rpm_put:
+ pm_runtime_put_noidle(dev);
return ret;
}
@@ -446,32 +460,23 @@ static int rcar_gen3_phy_usb2_init(struct phy *p)
struct rcar_gen3_chan *channel = rphy->ch;
void __iomem *usb2_base = channel->base;
u32 val;
- int ret;
- if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) {
- INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
- ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq,
- IRQF_SHARED, dev_name(channel->dev), channel);
- if (ret < 0) {
- dev_err(channel->dev, "No irq handler (%d)\n", channel->irq);
- return ret;
- }
- }
+ guard(spinlock_irqsave)(&channel->lock);
/* Initialize USB2 part */
val = readl(usb2_base + USB2_INT_ENABLE);
val |= USB2_INT_ENABLE_UCOM_INTEN | rphy->int_enable_bits;
writel(val, usb2_base + USB2_INT_ENABLE);
- writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET);
- writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET);
- /* Initialize otg part */
- if (channel->is_otg_channel) {
- if (rcar_gen3_needs_init_otg(channel))
- rcar_gen3_init_otg(channel);
- rphy->otg_initialized = true;
+ if (!rcar_gen3_is_any_rphy_initialized(channel)) {
+ writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET);
+ writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET);
}
+ /* Initialize otg part (only if we initialize a PHY with IRQs). */
+ if (rphy->int_enable_bits)
+ rcar_gen3_init_otg(channel);
+
rphy->initialized = true;
return 0;
@@ -484,10 +489,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
void __iomem *usb2_base = channel->base;
u32 val;
- rphy->initialized = false;
+ guard(spinlock_irqsave)(&channel->lock);
- if (channel->is_otg_channel)
- rphy->otg_initialized = false;
+ rphy->initialized = false;
val = readl(usb2_base + USB2_INT_ENABLE);
val &= ~rphy->int_enable_bits;
@@ -495,9 +499,6 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
val &= ~USB2_INT_ENABLE_UCOM_INTEN;
writel(val, usb2_base + USB2_INT_ENABLE);
- if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel))
- free_irq(channel->irq, channel);
-
return 0;
}
@@ -509,16 +510,17 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p)
u32 val;
int ret = 0;
- mutex_lock(&channel->lock);
- if (!rcar_gen3_are_all_rphys_power_off(channel))
- goto out;
-
if (channel->vbus) {
ret = regulator_enable(channel->vbus);
if (ret)
- goto out;
+ return ret;
}
+ guard(spinlock_irqsave)(&channel->lock);
+
+ if (!rcar_gen3_are_all_rphys_power_off(channel))
+ goto out;
+
val = readl(usb2_base + USB2_USBCTR);
val |= USB2_USBCTR_PLL_RST;
writel(val, usb2_base + USB2_USBCTR);
@@ -528,7 +530,6 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p)
out:
/* The powered flag should be set for any other phys anyway */
rphy->powered = true;
- mutex_unlock(&channel->lock);
return 0;
}
@@ -539,18 +540,20 @@ static int rcar_gen3_phy_usb2_power_off(struct phy *p)
struct rcar_gen3_chan *channel = rphy->ch;
int ret = 0;
- mutex_lock(&channel->lock);
- rphy->powered = false;
+ scoped_guard(spinlock_irqsave, &channel->lock) {
+ rphy->powered = false;
- if (!rcar_gen3_are_all_rphys_power_off(channel))
- goto out;
+ if (rcar_gen3_are_all_rphys_power_off(channel)) {
+ u32 val = readl(channel->base + USB2_USBCTR);
+
+ val |= USB2_USBCTR_PLL_RST;
+ writel(val, channel->base + USB2_USBCTR);
+ }
+ }
if (channel->vbus)
ret = regulator_disable(channel->vbus);
-out:
- mutex_unlock(&channel->lock);
-
return ret;
}
@@ -703,7 +706,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct rcar_gen3_chan *channel;
struct phy_provider *provider;
- int ret = 0, i;
+ int ret = 0, i, irq;
if (!dev->of_node) {
dev_err(dev, "This driver needs device tree\n");
@@ -719,8 +722,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
return PTR_ERR(channel->base);
channel->obint_enable_bits = USB2_OBINT_BITS;
- /* get irq number here and request_irq for OTG in phy_init */
- channel->irq = platform_get_irq_optional(pdev, 0);
channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
channel->is_otg_channel = true;
@@ -763,7 +764,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
if (phy_data->no_adp_ctrl)
channel->obint_enable_bits = USB2_OBINT_IDCHG_EN;
- mutex_init(&channel->lock);
+ spin_lock_init(&channel->lock);
for (i = 0; i < NUM_OF_PHYS; i++) {
channel->rphys[i].phy = devm_phy_create(dev, NULL,
phy_data->phy_usb2_ops);
@@ -789,6 +790,20 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
channel->vbus = NULL;
}
+ irq = platform_get_irq_optional(pdev, 0);
+ if (irq < 0 && irq != -ENXIO) {
+ ret = irq;
+ goto error;
+ } else if (irq > 0) {
+ INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
+ ret = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq,
+ IRQF_SHARED, dev_name(dev), channel);
+ if (ret < 0) {
+ dev_err(dev, "Failed to request irq (%d)\n", irq);
+ goto error;
+ }
+ }
+
provider = devm_of_phy_provider_register(dev, rcar_gen3_phy_usb2_xlate);
if (IS_ERR(provider)) {
dev_err(dev, "Failed to register PHY provider\n");
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
index 08c78c1..28a052e 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c
@@ -1653,7 +1653,7 @@ static __maybe_unused int samsung_mipi_dcphy_runtime_resume(struct device *dev)
return ret;
}
- clk_prepare_enable(samsung->ref_clk);
+ ret = clk_prepare_enable(samsung->ref_clk);
if (ret) {
dev_err(samsung->dev, "Failed to enable reference clock, %d\n", ret);
clk_disable_unprepare(samsung->pclk);
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
index fe7c057..77236f0 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
@@ -476,6 +476,8 @@ static const struct ropll_config ropll_tmds_cfg[] = {
1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
{ 650000, 162, 162, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 54, 0, 16, 4, 1,
1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
+ { 502500, 84, 84, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 11, 1, 4, 5,
+ 4, 11, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
{ 337500, 0x70, 0x70, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 0x2, 0, 0x01, 5,
1, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
{ 400000, 100, 100, 1, 1, 11, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
diff --git a/drivers/phy/starfive/phy-jh7110-usb.c b/drivers/phy/starfive/phy-jh7110-usb.c
index cb5454f..b505d89 100644
--- a/drivers/phy/starfive/phy-jh7110-usb.c
+++ b/drivers/phy/starfive/phy-jh7110-usb.c
@@ -18,6 +18,8 @@
#include <linux/usb/of.h>
#define USB_125M_CLK_RATE 125000000
+#define USB_CLK_MODE_OFF 0x0
+#define USB_CLK_MODE_RX_NORMAL_PWR BIT(1)
#define USB_LS_KEEPALIVE_OFF 0x4
#define USB_LS_KEEPALIVE_ENABLE BIT(4)
@@ -78,6 +80,7 @@ static int jh7110_usb2_phy_init(struct phy *_phy)
{
struct jh7110_usb2_phy *phy = phy_get_drvdata(_phy);
int ret;
+ unsigned int val;
ret = clk_set_rate(phy->usb_125m_clk, USB_125M_CLK_RATE);
if (ret)
@@ -87,6 +90,10 @@ static int jh7110_usb2_phy_init(struct phy *_phy)
if (ret)
return ret;
+ val = readl(phy->regs + USB_CLK_MODE_OFF);
+ val |= USB_CLK_MODE_RX_NORMAL_PWR;
+ writel(val, phy->regs + USB_CLK_MODE_OFF);
+
return 0;
}
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index fae6242..23a23f2 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -237,6 +237,8 @@
#define DATA0_VAL_PD BIT(1)
#define USE_XUSB_AO BIT(4)
+#define TEGRA_UTMI_PAD_MAX 4
+
#define TEGRA186_LANE(_name, _offset, _shift, _mask, _type) \
{ \
.name = _name, \
@@ -269,7 +271,7 @@ struct tegra186_xusb_padctl {
/* UTMI bias and tracking */
struct clk *usb2_trk_clk;
- unsigned int bias_pad_enable;
+ DECLARE_BITMAP(utmi_pad_enabled, TEGRA_UTMI_PAD_MAX);
/* padctl context */
struct tegra186_xusb_padctl_context context;
@@ -603,12 +605,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
u32 value;
int err;
- mutex_lock(&padctl->lock);
-
- if (priv->bias_pad_enable++ > 0) {
- mutex_unlock(&padctl->lock);
+ if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
return;
- }
err = clk_prepare_enable(priv->usb2_trk_clk);
if (err < 0)
@@ -658,8 +656,6 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
} else {
clk_disable_unprepare(priv->usb2_trk_clk);
}
-
- mutex_unlock(&padctl->lock);
}
static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
@@ -667,17 +663,8 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
u32 value;
- mutex_lock(&padctl->lock);
-
- if (WARN_ON(priv->bias_pad_enable == 0)) {
- mutex_unlock(&padctl->lock);
+ if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
return;
- }
-
- if (--priv->bias_pad_enable > 0) {
- mutex_unlock(&padctl->lock);
- return;
- }
value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL1);
value |= USB2_PD_TRK;
@@ -690,13 +677,13 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
clk_disable_unprepare(priv->usb2_trk_clk);
}
- mutex_unlock(&padctl->lock);
}
static void tegra186_utmi_pad_power_on(struct phy *phy)
{
struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+ struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
struct tegra_xusb_usb2_port *port;
struct device *dev = padctl->dev;
unsigned int index = lane->index;
@@ -705,9 +692,16 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
if (!phy)
return;
+ mutex_lock(&padctl->lock);
+ if (test_bit(index, priv->utmi_pad_enabled)) {
+ mutex_unlock(&padctl->lock);
+ return;
+ }
+
port = tegra_xusb_find_usb2_port(padctl, index);
if (!port) {
dev_err(dev, "no port found for USB2 lane %u\n", index);
+ mutex_unlock(&padctl->lock);
return;
}
@@ -724,18 +718,28 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
value &= ~USB2_OTG_PD_DR;
padctl_writel(padctl, value, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
+
+ set_bit(index, priv->utmi_pad_enabled);
+ mutex_unlock(&padctl->lock);
}
static void tegra186_utmi_pad_power_down(struct phy *phy)
{
struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+ struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
unsigned int index = lane->index;
u32 value;
if (!phy)
return;
+ mutex_lock(&padctl->lock);
+ if (!test_bit(index, priv->utmi_pad_enabled)) {
+ mutex_unlock(&padctl->lock);
+ return;
+ }
+
dev_dbg(padctl->dev, "power down UTMI pad %u\n", index);
value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL0(index));
@@ -748,7 +752,11 @@ static void tegra186_utmi_pad_power_down(struct phy *phy)
udelay(2);
+ clear_bit(index, priv->utmi_pad_enabled);
+
tegra186_utmi_bias_pad_power_off(padctl);
+
+ mutex_unlock(&padctl->lock);
}
static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 79d4814..c89df95a 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -548,16 +548,16 @@ static int tegra_xusb_port_init(struct tegra_xusb_port *port,
err = dev_set_name(&port->dev, "%s-%u", name, index);
if (err < 0)
- goto unregister;
+ goto put_device;
err = device_add(&port->dev);
if (err < 0)
- goto unregister;
+ goto put_device;
return 0;
-unregister:
- device_unregister(&port->dev);
+put_device:
+ put_device(&port->dev);
return err;
}
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 842a1e6..18de313 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -37,16 +37,16 @@ static inline const struct group_desc *imx_pinctrl_find_group_by_name(
struct pinctrl_dev *pctldev,
const char *name)
{
- const struct group_desc *grp = NULL;
+ const struct group_desc *grp;
int i;
for (i = 0; i < pctldev->num_groups; i++) {
grp = pinctrl_generic_get_group(pctldev, i);
if (grp && !strcmp(grp->grp.name, name))
- break;
+ return grp;
}
- return grp;
+ return NULL;
}
static void imx_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s,
diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c
index ced4ee5..b4eb2be 100644
--- a/drivers/pinctrl/mediatek/mtk-eint.c
+++ b/drivers/pinctrl/mediatek/mtk-eint.c
@@ -449,7 +449,7 @@ int mtk_eint_set_debounce(struct mtk_eint *eint, unsigned long eint_num,
return -EOPNOTSUPP;
virq = irq_find_mapping(eint->domain, eint_num);
- eint_offset = (eint_num % 4) * 8;
+ eint_offset = (idx % 4) * 8;
d = irq_get_irq_data(virq);
set_offset = (idx / 4) * 4 + eint->regs->dbnc_set;
diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
index 547a798..5d84a77 100644
--- a/drivers/pinctrl/mediatek/pinctrl-airoha.c
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -6,6 +6,7 @@
*/
#include <dt-bindings/pinctrl/mt65xx.h>
+#include <linux/bitfield.h>
#include <linux/bits.h>
#include <linux/cleanup.h>
#include <linux/gpio/driver.h>
@@ -112,39 +113,19 @@
#define REG_LAN_LED1_MAPPING 0x0280
#define LAN4_LED_MAPPING_MASK GENMASK(18, 16)
-#define LAN4_PHY4_LED_MAP BIT(18)
-#define LAN4_PHY2_LED_MAP BIT(17)
-#define LAN4_PHY1_LED_MAP BIT(16)
-#define LAN4_PHY0_LED_MAP 0
-#define LAN4_PHY3_LED_MAP GENMASK(17, 16)
+#define LAN4_PHY_LED_MAP(_n) FIELD_PREP_CONST(LAN4_LED_MAPPING_MASK, (_n))
#define LAN3_LED_MAPPING_MASK GENMASK(14, 12)
-#define LAN3_PHY4_LED_MAP BIT(14)
-#define LAN3_PHY2_LED_MAP BIT(13)
-#define LAN3_PHY1_LED_MAP BIT(12)
-#define LAN3_PHY0_LED_MAP 0
-#define LAN3_PHY3_LED_MAP GENMASK(13, 12)
+#define LAN3_PHY_LED_MAP(_n) FIELD_PREP_CONST(LAN3_LED_MAPPING_MASK, (_n))
#define LAN2_LED_MAPPING_MASK GENMASK(10, 8)
-#define LAN2_PHY4_LED_MAP BIT(12)
-#define LAN2_PHY2_LED_MAP BIT(11)
-#define LAN2_PHY1_LED_MAP BIT(10)
-#define LAN2_PHY0_LED_MAP 0
-#define LAN2_PHY3_LED_MAP GENMASK(11, 10)
+#define LAN2_PHY_LED_MAP(_n) FIELD_PREP_CONST(LAN2_LED_MAPPING_MASK, (_n))
#define LAN1_LED_MAPPING_MASK GENMASK(6, 4)
-#define LAN1_PHY4_LED_MAP BIT(6)
-#define LAN1_PHY2_LED_MAP BIT(5)
-#define LAN1_PHY1_LED_MAP BIT(4)
-#define LAN1_PHY0_LED_MAP 0
-#define LAN1_PHY3_LED_MAP GENMASK(5, 4)
+#define LAN1_PHY_LED_MAP(_n) FIELD_PREP_CONST(LAN1_LED_MAPPING_MASK, (_n))
#define LAN0_LED_MAPPING_MASK GENMASK(2, 0)
-#define LAN0_PHY4_LED_MAP BIT(3)
-#define LAN0_PHY2_LED_MAP BIT(2)
-#define LAN0_PHY1_LED_MAP BIT(1)
-#define LAN0_PHY0_LED_MAP 0
-#define LAN0_PHY3_LED_MAP GENMASK(2, 1)
+#define LAN0_PHY_LED_MAP(_n) FIELD_PREP_CONST(LAN0_LED_MAPPING_MASK, (_n))
/* CONF */
#define REG_I2C_SDA_E2 0x001c
@@ -1476,8 +1457,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY1_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(0)
},
.regmap_size = 2,
}, {
@@ -1491,8 +1472,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY1_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(0)
},
.regmap_size = 2,
}, {
@@ -1506,8 +1487,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY1_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(0)
},
.regmap_size = 2,
}, {
@@ -1521,8 +1502,8 @@ static const struct airoha_pinctrl_func_group phy1_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY1_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(0)
},
.regmap_size = 2,
},
@@ -1540,8 +1521,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY2_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(1)
},
.regmap_size = 2,
}, {
@@ -1555,8 +1536,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY2_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(1)
},
.regmap_size = 2,
}, {
@@ -1570,8 +1551,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY2_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(1)
},
.regmap_size = 2,
}, {
@@ -1585,8 +1566,8 @@ static const struct airoha_pinctrl_func_group phy2_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY2_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(1)
},
.regmap_size = 2,
},
@@ -1604,8 +1585,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY3_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(2)
},
.regmap_size = 2,
}, {
@@ -1619,8 +1600,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY3_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(2)
},
.regmap_size = 2,
}, {
@@ -1634,8 +1615,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY3_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(2)
},
.regmap_size = 2,
}, {
@@ -1649,8 +1630,8 @@ static const struct airoha_pinctrl_func_group phy3_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY3_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(2)
},
.regmap_size = 2,
},
@@ -1668,8 +1649,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY4_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(3)
},
.regmap_size = 2,
}, {
@@ -1683,8 +1664,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY4_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(3)
},
.regmap_size = 2,
}, {
@@ -1698,8 +1679,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY4_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(3)
},
.regmap_size = 2,
}, {
@@ -1713,8 +1694,8 @@ static const struct airoha_pinctrl_func_group phy4_led0_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED0_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY4_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(3)
},
.regmap_size = 2,
},
@@ -1732,8 +1713,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY1_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(0)
},
.regmap_size = 2,
}, {
@@ -1747,8 +1728,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY1_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(0)
},
.regmap_size = 2,
}, {
@@ -1762,8 +1743,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY1_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(0)
},
.regmap_size = 2,
}, {
@@ -1777,8 +1758,8 @@ static const struct airoha_pinctrl_func_group phy1_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY1_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(0)
},
.regmap_size = 2,
},
@@ -1796,8 +1777,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY2_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(1)
},
.regmap_size = 2,
}, {
@@ -1811,8 +1792,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY2_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(1)
},
.regmap_size = 2,
}, {
@@ -1826,8 +1807,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY2_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(1)
},
.regmap_size = 2,
}, {
@@ -1841,8 +1822,8 @@ static const struct airoha_pinctrl_func_group phy2_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY2_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(1)
},
.regmap_size = 2,
},
@@ -1860,8 +1841,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY3_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(2)
},
.regmap_size = 2,
}, {
@@ -1875,8 +1856,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY3_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(2)
},
.regmap_size = 2,
}, {
@@ -1890,8 +1871,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY3_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(2)
},
.regmap_size = 2,
}, {
@@ -1905,8 +1886,8 @@ static const struct airoha_pinctrl_func_group phy3_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY3_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(2)
},
.regmap_size = 2,
},
@@ -1924,8 +1905,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN1_LED_MAPPING_MASK,
- LAN1_PHY4_LED_MAP
+ LAN0_LED_MAPPING_MASK,
+ LAN0_PHY_LED_MAP(3)
},
.regmap_size = 2,
}, {
@@ -1939,8 +1920,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN2_LED_MAPPING_MASK,
- LAN2_PHY4_LED_MAP
+ LAN1_LED_MAPPING_MASK,
+ LAN1_PHY_LED_MAP(3)
},
.regmap_size = 2,
}, {
@@ -1954,8 +1935,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN3_LED_MAPPING_MASK,
- LAN3_PHY4_LED_MAP
+ LAN2_LED_MAPPING_MASK,
+ LAN2_PHY_LED_MAP(3)
},
.regmap_size = 2,
}, {
@@ -1969,8 +1950,8 @@ static const struct airoha_pinctrl_func_group phy4_led1_func_group[] = {
.regmap[1] = {
AIROHA_FUNC_MUX,
REG_LAN_LED1_MAPPING,
- LAN4_LED_MAPPING_MASK,
- LAN4_PHY4_LED_MAP
+ LAN3_LED_MAPPING_MASK,
+ LAN3_PHY_LED_MAP(3)
},
.regmap_size = 2,
},
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 91edb539..8596f35 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1015,9 +1015,15 @@ static int mtk_eint_init(struct mtk_pinctrl *pctl, struct platform_device *pdev)
if (!pctl->eint)
return -ENOMEM;
- pctl->eint->base = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(pctl->eint->base))
- return PTR_ERR(pctl->eint->base);
+ pctl->eint->nbase = 1;
+ /* mtk-eint expects an array */
+ pctl->eint->base = devm_kzalloc(pctl->dev, sizeof(pctl->eint->base), GFP_KERNEL);
+ if (!pctl->eint->base)
+ return -ENOMEM;
+
+ pctl->eint->base[0] = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(pctl->eint->base[0]))
+ return PTR_ERR(pctl->eint->base[0]);
pctl->eint->irq = irq_of_parse_and_map(np, 0);
if (!pctl->eint->irq)
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index 253a0cc..e5a32a0 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -487,7 +487,7 @@ static int meson_pinconf_get(struct pinctrl_dev *pcdev, unsigned int pin,
case PIN_CONFIG_BIAS_PULL_DOWN:
case PIN_CONFIG_BIAS_PULL_UP:
if (meson_pinconf_get_pull(pc, pin) == param)
- arg = 1;
+ arg = 60000;
else
return -EINVAL;
break;
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 82f0cc4..0eb8163 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -44,7 +44,6 @@
* @pctrl: pinctrl handle.
* @chip: gpiochip handle.
* @desc: pin controller descriptor
- * @restart_nb: restart notifier block.
* @irq: parent irq for the TLMM irq_chip.
* @intr_target_use_scm: route irq to application cpu using scm calls
* @lock: Spinlock to protect register resources as well
@@ -64,7 +63,6 @@ struct msm_pinctrl {
struct pinctrl_dev *pctrl;
struct gpio_chip chip;
struct pinctrl_desc desc;
- struct notifier_block restart_nb;
int irq;
@@ -1471,10 +1469,9 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
return 0;
}
-static int msm_ps_hold_restart(struct notifier_block *nb, unsigned long action,
- void *data)
+static int msm_ps_hold_restart(struct sys_off_data *data)
{
- struct msm_pinctrl *pctrl = container_of(nb, struct msm_pinctrl, restart_nb);
+ struct msm_pinctrl *pctrl = data->cb_data;
writel(0, pctrl->regs[0] + PS_HOLD_OFFSET);
mdelay(1000);
@@ -1485,7 +1482,11 @@ static struct msm_pinctrl *poweroff_pctrl;
static void msm_ps_hold_poweroff(void)
{
- msm_ps_hold_restart(&poweroff_pctrl->restart_nb, 0, NULL);
+ struct sys_off_data data = {
+ .cb_data = poweroff_pctrl,
+ };
+
+ msm_ps_hold_restart(&data);
}
static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
@@ -1495,9 +1496,11 @@ static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
for (i = 0; i < pctrl->soc->nfunctions; i++)
if (!strcmp(func[i].name, "ps_hold")) {
- pctrl->restart_nb.notifier_call = msm_ps_hold_restart;
- pctrl->restart_nb.priority = 128;
- if (register_restart_handler(&pctrl->restart_nb))
+ if (devm_register_sys_off_handler(pctrl->dev,
+ SYS_OFF_MODE_RESTART,
+ 128,
+ msm_ps_hold_restart,
+ pctrl))
dev_err(pctrl->dev,
"failed to setup restart handler.\n");
poweroff_pctrl = pctrl;
@@ -1599,8 +1602,6 @@ void msm_pinctrl_remove(struct platform_device *pdev)
struct msm_pinctrl *pctrl = platform_get_drvdata(pdev);
gpiochip_remove(&pctrl->chip);
-
- unregister_restart_handler(&pctrl->restart_nb);
}
EXPORT_SYMBOL(msm_pinctrl_remove);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8750.c b/drivers/pinctrl/qcom/pinctrl-sm8750.c
index 1af11cd..b94fb4ee 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8750.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8750.c
@@ -46,7 +46,9 @@
.out_bit = 1, \
.intr_enable_bit = 0, \
.intr_status_bit = 0, \
- .intr_target_bit = 5, \
+ .intr_wakeup_present_bit = 6, \
+ .intr_wakeup_enable_bit = 7, \
+ .intr_target_bit = 8, \
.intr_target_kpss_val = 3, \
.intr_raw_status_bit = 4, \
.intr_polarity_bit = 1, \
diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c
index c1eccb3..eaae044 100644
--- a/drivers/platform/x86/amd/hsmp/acpi.c
+++ b/drivers/platform/x86/amd/hsmp/acpi.c
@@ -27,9 +27,8 @@
#include "hsmp.h"
-#define DRIVER_NAME "amd_hsmp"
+#define DRIVER_NAME "hsmp_acpi"
#define DRIVER_VERSION "2.3"
-#define ACPI_HSMP_DEVICE_HID "AMDI0097"
/* These are the strings specified in ACPI table */
#define MSG_IDOFF_STR "MsgIdOffset"
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.h b/drivers/platform/x86/amd/hsmp/hsmp.h
index af8b21f..d58d4f0 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.h
+++ b/drivers/platform/x86/amd/hsmp/hsmp.h
@@ -23,6 +23,7 @@
#define HSMP_CDEV_NAME "hsmp_cdev"
#define HSMP_DEVNODE_NAME "hsmp"
+#define ACPI_HSMP_DEVICE_HID "AMDI0097"
struct hsmp_mbaddr_info {
u32 base_addr;
diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c
index b9782a0..81931e8 100644
--- a/drivers/platform/x86/amd/hsmp/plat.c
+++ b/drivers/platform/x86/amd/hsmp/plat.c
@@ -11,6 +11,7 @@
#include <asm/amd_hsmp.h>
+#include <linux/acpi.h>
#include <linux/build_bug.h>
#include <linux/device.h>
#include <linux/module.h>
@@ -266,7 +267,7 @@ static bool legacy_hsmp_support(void)
}
case 0x1A:
switch (boot_cpu_data.x86_model) {
- case 0x00 ... 0x1F:
+ case 0x00 ... 0x0F:
return true;
default:
return false;
@@ -288,6 +289,9 @@ static int __init hsmp_plt_init(void)
return ret;
}
+ if (acpi_dev_present(ACPI_HSMP_DEVICE_HID, NULL, -1))
+ return -ENODEV;
+
hsmp_pdev = get_hsmp_pdev();
if (!hsmp_pdev)
return -ENOMEM;
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index b4f4972..2e3f6fc 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -217,6 +217,13 @@ static const struct dmi_system_id fwbug_list[] = {
DMI_MATCH(DMI_BIOS_VERSION, "03.05"),
}
},
+ {
+ .ident = "MECHREVO Wujie 14X (GX4HRXL)",
+ .driver_data = &quirk_spurious_8042,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"),
+ }
+ },
{}
};
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index d789d6c..0329faf 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -644,10 +644,9 @@ static void amd_pmc_s2idle_check(void)
struct smu_metrics table;
int rc;
- /* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */
- if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) &&
- table.s0i3_last_entry_status)
- usleep_range(10000, 20000);
+ /* Avoid triggering OVP */
+ if (!get_metrics_table(pdev, &table) && table.s0i3_last_entry_status)
+ msleep(2500);
/* Dump the IdleMask before we add to the STB */
amd_pmc_idlemask_read(pdev, pdev->dev, NULL);
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 14b99d8..d3bd12a 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -334,6 +334,11 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
return 0;
}
+static inline bool amd_pmf_pb_valid(struct amd_pmf_dev *dev)
+{
+ return memchr_inv(dev->policy_buf, 0xff, dev->policy_sz);
+}
+
#ifdef CONFIG_AMD_PMF_DEBUG
static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev)
{
@@ -361,12 +366,22 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
dev->policy_buf = new_policy_buf;
dev->policy_sz = length;
+ if (!amd_pmf_pb_valid(dev)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
+
amd_pmf_hex_dump_pb(dev);
ret = amd_pmf_start_policy_engine(dev);
if (ret < 0)
- return ret;
+ goto cleanup;
return length;
+
+cleanup:
+ kfree(dev->policy_buf);
+ dev->policy_buf = NULL;
+ return ret;
}
static const struct file_operations pb_fops = {
@@ -528,6 +543,12 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
+ if (!amd_pmf_pb_valid(dev)) {
+ dev_info(dev->dev, "No Smart PC policy present\n");
+ ret = -EINVAL;
+ goto err_free_policy;
+ }
+
amd_pmf_hex_dump_pb(dev);
dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 38ef778..47cc766 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -304,6 +304,7 @@ struct asus_wmi {
u32 kbd_rgb_dev;
bool kbd_rgb_state_available;
+ bool oobe_state_available;
u8 throttle_thermal_policy_mode;
u32 throttle_thermal_policy_dev;
@@ -1826,7 +1827,7 @@ static int asus_wmi_led_init(struct asus_wmi *asus)
goto error;
}
- if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE)) {
+ if (asus->oobe_state_available) {
/*
* Disable OOBE state, so that e.g. the keyboard backlight
* works.
@@ -4723,6 +4724,7 @@ static int asus_wmi_add(struct platform_device *pdev)
asus->egpu_enable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_EGPU);
asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU);
asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE);
+ asus->oobe_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE);
asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
&& dmi_check_system(asus_ally_mcu_quirk);
@@ -4777,7 +4779,8 @@ static int asus_wmi_add(struct platform_device *pdev)
goto fail_leds;
asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
- if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
+ if ((result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) ==
+ (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
asus->driver->wlan_ctrl_by_user = 1;
if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) {
@@ -4970,6 +4973,13 @@ static int asus_hotk_restore(struct device *device)
}
if (!IS_ERR_OR_NULL(asus->kbd_led.dev))
kbd_led_update(asus);
+ if (asus->oobe_state_available) {
+ /*
+ * Disable OOBE state, so that e.g. the keyboard backlight
+ * works.
+ */
+ asus_wmi_set_devstate(ASUS_WMI_DEVID_OOBE, 1, NULL);
+ }
if (asus_wmi_has_fnlock_key(asus))
asus_wmi_fnlock_update(asus);
diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index 0c3be03..08b82c1 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -70,6 +70,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
.driver_data = &generic_quirks,
},
{
+ .ident = "Alienware m15 R7",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R7"),
+ },
+ .driver_data = &generic_quirks,
+ },
+ {
.ident = "Alienware m16 R1",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
@@ -655,12 +663,10 @@ static int thermal_profile_probe(void *drvdata, unsigned long *choices)
for (u32 i = 0; i < sys_desc[3]; i++) {
ret = wmax_thermal_information(priv->wdev, WMAX_OPERATION_LIST_IDS,
i + first_mode, &out_data);
-
- if (ret == -EIO)
- return ret;
-
if (ret == -EBADRQC)
break;
+ if (ret)
+ return ret;
if (!is_wmax_thermal_code(out_data))
continue;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 17a09b7..ede4835 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1294,6 +1294,16 @@ static const struct key_entry ideapad_keymap[] = {
/* Specific to some newer models */
{ KE_KEY, 0x3e | IDEAPAD_WMI_KEY, { KEY_MICMUTE } },
{ KE_KEY, 0x3f | IDEAPAD_WMI_KEY, { KEY_RFKILL } },
+ /* Star- (User Assignable Key) */
+ { KE_KEY, 0x44 | IDEAPAD_WMI_KEY, { KEY_PROG1 } },
+ /* Eye */
+ { KE_KEY, 0x45 | IDEAPAD_WMI_KEY, { KEY_PROG3 } },
+ /* Performance toggle also Fn+Q, handled inside ideapad_wmi_notify() */
+ { KE_KEY, 0x3d | IDEAPAD_WMI_KEY, { KEY_PROG4 } },
+ /* shift + prtsc */
+ { KE_KEY, 0x2d | IDEAPAD_WMI_KEY, { KEY_CUT } },
+ { KE_KEY, 0x29 | IDEAPAD_WMI_KEY, { KEY_TOUCHPAD_TOGGLE } },
+ { KE_KEY, 0x2a | IDEAPAD_WMI_KEY, { KEY_ROOT_MENU } },
{ KE_END },
};
@@ -2080,6 +2090,12 @@ static void ideapad_wmi_notify(struct wmi_device *wdev, union acpi_object *data)
dev_dbg(&wdev->dev, "WMI fn-key event: 0x%llx\n",
data->integer.value);
+ /* performance button triggered by 0x3d */
+ if (data->integer.value == 0x3d && priv->dytc) {
+ platform_profile_cycle();
+ break;
+ }
+
/* 0x02 FnLock, 0x03 Esc */
if (data->integer.value == 0x02 || data->integer.value == 0x03)
ideapad_fn_lock_led_notify(priv, data->integer.value == 0x02);
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 88a1a9f..0b5e434 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -44,16 +44,17 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Alex Hung");
static const struct acpi_device_id intel_hid_ids[] = {
- {"INT33D5", 0},
- {"INTC1051", 0},
- {"INTC1054", 0},
- {"INTC1070", 0},
- {"INTC1076", 0},
- {"INTC1077", 0},
- {"INTC1078", 0},
- {"INTC107B", 0},
- {"INTC10CB", 0},
- {"", 0},
+ { "INT33D5" },
+ { "INTC1051" },
+ { "INTC1054" },
+ { "INTC1070" },
+ { "INTC1076" },
+ { "INTC1077" },
+ { "INTC1078" },
+ { "INTC107B" },
+ { "INTC10CB" },
+ { "INTC10CC" },
+ { }
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
index 40bbf8e..bdee5d0 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
@@ -146,15 +146,13 @@ static int uncore_event_cpu_online(unsigned int cpu)
{
struct uncore_data *data;
int target;
+ int ret;
/* Check if there is an online cpu in the package for uncore MSR */
target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
- /* Use this CPU on this die as a control CPU */
- cpumask_set_cpu(cpu, &uncore_cpu_mask);
-
data = uncore_get_instance(cpu);
if (!data)
return 0;
@@ -163,7 +161,14 @@ static int uncore_event_cpu_online(unsigned int cpu)
data->die_id = topology_die_id(cpu);
data->domain_id = UNCORE_DOMAIN_ID_INVALID;
- return uncore_freq_add_entry(data, cpu);
+ ret = uncore_freq_add_entry(data, cpu);
+ if (ret)
+ return ret;
+
+ /* Use this CPU on this die as a control CPU */
+ cpumask_set_cpu(cpu, &uncore_cpu_mask);
+
+ return 0;
}
static int uncore_event_cpu_offline(unsigned int cpu)
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 5790095..92b21e4 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -11478,6 +11478,8 @@ static int __must_check __init get_thinkpad_model_data(
tp->vendor = PCI_VENDOR_ID_IBM;
else if (dmi_name_in_vendors("LENOVO"))
tp->vendor = PCI_VENDOR_ID_LENOVO;
+ else if (dmi_name_in_vendors("NEC"))
+ tp->vendor = PCI_VENDOR_ID_LENOVO;
else
return 0;
diff --git a/drivers/pps/generators/pps_gen_tio.c b/drivers/pps/generators/pps_gen_tio.c
index 1d5ffe0..de00a85 100644
--- a/drivers/pps/generators/pps_gen_tio.c
+++ b/drivers/pps/generators/pps_gen_tio.c
@@ -230,7 +230,7 @@ static int pps_gen_tio_probe(struct platform_device *pdev)
hrtimer_setup(&tio->timer, hrtimer_callback, CLOCK_REALTIME,
HRTIMER_MODE_ABS);
spin_lock_init(&tio->lock);
- platform_set_drvdata(pdev, &tio);
+ platform_set_drvdata(pdev, tio);
return 0;
}
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index faf6e027..e63481f 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -315,6 +315,8 @@ struct ptp_ocp_serial_port {
#define OCP_BOARD_ID_LEN 13
#define OCP_SERIAL_LEN 6
#define OCP_SMA_NUM 4
+#define OCP_SIGNAL_NUM 4
+#define OCP_FREQ_NUM 4
enum {
PORT_GNSS,
@@ -342,8 +344,8 @@ struct ptp_ocp {
struct dcf_master_reg __iomem *dcf_out;
struct dcf_slave_reg __iomem *dcf_in;
struct tod_reg __iomem *nmea_out;
- struct frequency_reg __iomem *freq_in[4];
- struct ptp_ocp_ext_src *signal_out[4];
+ struct frequency_reg __iomem *freq_in[OCP_FREQ_NUM];
+ struct ptp_ocp_ext_src *signal_out[OCP_SIGNAL_NUM];
struct ptp_ocp_ext_src *pps;
struct ptp_ocp_ext_src *ts0;
struct ptp_ocp_ext_src *ts1;
@@ -378,10 +380,12 @@ struct ptp_ocp {
u32 utc_tai_offset;
u32 ts_window_adjust;
u64 fw_cap;
- struct ptp_ocp_signal signal[4];
+ struct ptp_ocp_signal signal[OCP_SIGNAL_NUM];
struct ptp_ocp_sma_connector sma[OCP_SMA_NUM];
const struct ocp_sma_op *sma_op;
struct dpll_device *dpll;
+ int signals_nr;
+ int freq_in_nr;
};
#define OCP_REQ_TIMESTAMP BIT(0)
@@ -2578,12 +2582,60 @@ static const struct ocp_sma_op ocp_fb_sma_op = {
.set_output = ptp_ocp_sma_fb_set_output,
};
+static int
+ptp_ocp_sma_adva_set_output(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+ u32 reg, mask, shift;
+ unsigned long flags;
+ u32 __iomem *gpio;
+
+ gpio = sma_nr > 2 ? &bp->sma_map1->gpio2 : &bp->sma_map2->gpio2;
+ shift = sma_nr & 1 ? 0 : 16;
+
+ mask = 0xffff << (16 - shift);
+
+ spin_lock_irqsave(&bp->lock, flags);
+
+ reg = ioread32(gpio);
+ reg = (reg & mask) | (val << shift);
+
+ iowrite32(reg, gpio);
+
+ spin_unlock_irqrestore(&bp->lock, flags);
+
+ return 0;
+}
+
+static int
+ptp_ocp_sma_adva_set_inputs(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+ u32 reg, mask, shift;
+ unsigned long flags;
+ u32 __iomem *gpio;
+
+ gpio = sma_nr > 2 ? &bp->sma_map2->gpio1 : &bp->sma_map1->gpio1;
+ shift = sma_nr & 1 ? 0 : 16;
+
+ mask = 0xffff << (16 - shift);
+
+ spin_lock_irqsave(&bp->lock, flags);
+
+ reg = ioread32(gpio);
+ reg = (reg & mask) | (val << shift);
+
+ iowrite32(reg, gpio);
+
+ spin_unlock_irqrestore(&bp->lock, flags);
+
+ return 0;
+}
+
static const struct ocp_sma_op ocp_adva_sma_op = {
.tbl = { ptp_ocp_adva_sma_in, ptp_ocp_adva_sma_out },
.init = ptp_ocp_sma_fb_init,
.get = ptp_ocp_sma_fb_get,
- .set_inputs = ptp_ocp_sma_fb_set_inputs,
- .set_output = ptp_ocp_sma_fb_set_output,
+ .set_inputs = ptp_ocp_sma_adva_set_inputs,
+ .set_output = ptp_ocp_sma_adva_set_output,
};
static int
@@ -2649,6 +2701,8 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
bp->eeprom_map = fb_eeprom_map;
bp->fw_version = ioread32(&bp->image->version);
bp->sma_op = &ocp_fb_sma_op;
+ bp->signals_nr = 4;
+ bp->freq_in_nr = 4;
ptp_ocp_fb_set_version(bp);
@@ -2814,6 +2868,8 @@ ptp_ocp_art_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
bp->fw_version = ioread32(&bp->reg->version);
bp->fw_tag = 2;
bp->sma_op = &ocp_art_sma_op;
+ bp->signals_nr = 4;
+ bp->freq_in_nr = 4;
/* Enable MAC serial port during initialisation */
iowrite32(1, &bp->board_config->mro50_serial_activate);
@@ -2840,6 +2896,8 @@ ptp_ocp_adva_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
bp->flash_start = 0xA00000;
bp->eeprom_map = fb_eeprom_map;
bp->sma_op = &ocp_adva_sma_op;
+ bp->signals_nr = 2;
+ bp->freq_in_nr = 2;
version = ioread32(&bp->image->version);
/* if lower 16 bits are empty, this is the fw loader. */
@@ -3960,7 +4018,7 @@ _signal_summary_show(struct seq_file *s, struct ptp_ocp *bp, int nr)
{
struct signal_reg __iomem *reg = bp->signal_out[nr]->mem;
struct ptp_ocp_signal *signal = &bp->signal[nr];
- char label[8];
+ char label[16];
bool on;
u32 val;
@@ -3983,7 +4041,7 @@ static void
_frequency_summary_show(struct seq_file *s, int nr,
struct frequency_reg __iomem *reg)
{
- char label[8];
+ char label[16];
bool on;
u32 val;
@@ -4127,11 +4185,11 @@ ptp_ocp_summary_show(struct seq_file *s, void *data)
}
if (bp->fw_cap & OCP_CAP_SIGNAL)
- for (i = 0; i < 4; i++)
+ for (i = 0; i < bp->signals_nr; i++)
_signal_summary_show(s, bp, i);
if (bp->fw_cap & OCP_CAP_FREQ)
- for (i = 0; i < 4; i++)
+ for (i = 0; i < bp->freq_in_nr; i++)
_frequency_summary_show(s, i, bp->freq_in[i]);
if (bp->irig_out) {
diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c
index 59eb23d..198d45f 100644
--- a/drivers/regulator/max20086-regulator.c
+++ b/drivers/regulator/max20086-regulator.c
@@ -132,7 +132,7 @@ static int max20086_regulators_register(struct max20086 *chip)
static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
{
- struct of_regulator_match matches[MAX20086_MAX_REGULATORS] = { };
+ struct of_regulator_match *matches;
struct device_node *node;
unsigned int i;
int ret;
@@ -143,6 +143,11 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
return -ENODEV;
}
+ matches = devm_kcalloc(chip->dev, chip->info->num_outputs,
+ sizeof(*matches), GFP_KERNEL);
+ if (!matches)
+ return -ENOMEM;
+
for (i = 0; i < chip->info->num_outputs; ++i)
matches[i].name = max20086_output_names[i];
diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index 775b056..2c7e519 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -456,7 +456,8 @@ static int wcnss_init_regulators(struct qcom_wcnss *wcnss,
if (wcnss->num_pds) {
info += wcnss->num_pds;
/* Handle single power domain case */
- num_vregs += num_pd_vregs - wcnss->num_pds;
+ if (wcnss->num_pds < num_pd_vregs)
+ num_vregs += num_pd_vregs - wcnss->num_pds;
} else {
num_vregs += num_pd_vregs;
}
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index 4bfe469..8c1c908 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -5,7 +5,7 @@
config DCSSBLK
def_tristate m
prompt "DCSSBLK support"
- depends on S390 && BLOCK
+ depends on S390 && BLOCK && (DAX || DAX=n)
help
Support for dcss block device
@@ -14,7 +14,6 @@
depends on DCSSBLK
# requires S390 ZONE_DEVICE support
depends on BROKEN
- select DAX
prompt "DCSSBLK DAX support"
help
Enable DAX operation for the dcss block device
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 3fcb1ad..1d7901a 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -174,6 +174,9 @@ static void mpi3mr_print_event_data(struct mpi3mr_ioc *mrioc,
char *desc = NULL;
u16 event;
+ if (!(mrioc->logging_level & MPI3_DEBUG_EVENT))
+ return;
+
event = event_reply->event;
switch (event) {
@@ -451,6 +454,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc)
return 0;
}
+ atomic_set(&mrioc->admin_pend_isr, 0);
reply_desc = (struct mpi3_default_reply_descriptor *)mrioc->admin_reply_base +
admin_reply_ci;
@@ -565,7 +569,7 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc,
WRITE_ONCE(op_req_q->ci, le16_to_cpu(reply_desc->request_queue_ci));
mpi3mr_process_op_reply_desc(mrioc, reply_desc, &reply_dma,
reply_qidx);
- atomic_dec(&op_reply_q->pend_ios);
+
if (reply_dma)
mpi3mr_repost_reply_buf(mrioc, reply_dma);
num_op_reply++;
@@ -2925,6 +2929,7 @@ static int mpi3mr_setup_admin_qpair(struct mpi3mr_ioc *mrioc)
mrioc->admin_reply_ci = 0;
mrioc->admin_reply_ephase = 1;
atomic_set(&mrioc->admin_reply_q_in_use, 0);
+ atomic_set(&mrioc->admin_pend_isr, 0);
if (!mrioc->admin_req_base) {
mrioc->admin_req_base = dma_alloc_coherent(&mrioc->pdev->dev,
@@ -4653,6 +4658,7 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc)
if (mrioc->admin_reply_base)
memset(mrioc->admin_reply_base, 0, mrioc->admin_reply_q_sz);
atomic_set(&mrioc->admin_reply_q_in_use, 0);
+ atomic_set(&mrioc->admin_pend_isr, 0);
if (mrioc->init_cmds.reply) {
memset(mrioc->init_cmds.reply, 0, sizeof(*mrioc->init_cmds.reply));
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index dc4bd42..486db5b 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -891,7 +891,7 @@ static bool myrb_enable_mmio(struct myrb_hba *cb, mbox_mmio_init_t mmio_init_fn)
status = mmio_init_fn(pdev, base, &mbox);
if (status != MYRB_STATUS_SUCCESS) {
dev_err(&pdev->dev,
- "Failed to enable mailbox, statux %02X\n",
+ "Failed to enable mailbox, status %02X\n",
status);
return false;
}
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 53daf92..518a252 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -707,26 +707,23 @@ void scsi_cdl_check(struct scsi_device *sdev)
*/
int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
{
- struct scsi_mode_data data;
- struct scsi_sense_hdr sshdr;
- struct scsi_vpd *vpd;
- bool is_ata = false;
char buf[64];
+ bool is_ata;
int ret;
if (!sdev->cdl_supported)
return -EOPNOTSUPP;
rcu_read_lock();
- vpd = rcu_dereference(sdev->vpd_pg89);
- if (vpd)
- is_ata = true;
+ is_ata = rcu_dereference(sdev->vpd_pg89);
rcu_read_unlock();
/*
* For ATA devices, CDL needs to be enabled with a SET FEATURES command.
*/
if (is_ata) {
+ struct scsi_mode_data data;
+ struct scsi_sense_hdr sshdr;
char *buf_data;
int len;
@@ -735,16 +732,30 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
if (ret)
return -EINVAL;
- /* Enable CDL using the ATA feature page */
+ /* Enable or disable CDL using the ATA feature page */
len = min_t(size_t, sizeof(buf),
data.length - data.header_length -
data.block_descriptor_length);
buf_data = buf + data.header_length +
data.block_descriptor_length;
- if (enable)
- buf_data[4] = 0x02;
- else
- buf_data[4] = 0;
+
+ /*
+ * If we want to enable CDL and CDL is already enabled on the
+ * device, do nothing. This avoids needlessly resetting the CDL
+ * statistics on the device as that is implied by the CDL enable
+ * action. Similar to this, there is no need to do anything if
+ * we want to disable CDL and CDL is already disabled.
+ */
+ if (enable) {
+ if ((buf_data[4] & 0x03) == 0x02)
+ goto out;
+ buf_data[4] &= ~0x03;
+ buf_data[4] |= 0x02;
+ } else {
+ if ((buf_data[4] & 0x03) == 0x00)
+ goto out;
+ buf_data[4] &= ~0x03;
+ }
ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3,
&data, &sshdr);
@@ -756,6 +767,7 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
}
}
+out:
sdev->cdl_enable = enable;
return 0;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0d29470..1b43013 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1253,8 +1253,12 @@ EXPORT_SYMBOL_GPL(scsi_alloc_request);
*/
static void scsi_cleanup_rq(struct request *rq)
{
+ struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+ cmd->flags = 0;
+
if (rq->rq_flags & RQF_DONTPREP) {
- scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+ scsi_mq_uninit_cmd(cmd);
rq->rq_flags &= ~RQF_DONTPREP;
}
}
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 7a447ff..a8db664 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -169,6 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
unsigned int nr_zones, size_t *buflen)
{
struct request_queue *q = sdkp->disk->queue;
+ unsigned int max_segments;
size_t bufsize;
void *buf;
@@ -180,12 +181,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
* Furthermore, since the report zone command cannot be split, make
* sure that the allocated buffer can always be mapped by limiting the
* number of pages allocated to the HBA max segments limit.
+ * Since max segments can be larger than the max inline bio vectors,
+ * further limit the allocated buffer to BIO_MAX_INLINE_VECS.
*/
nr_zones = min(nr_zones, sdkp->zone_info.nr_zones);
bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE);
bufsize = min_t(size_t, bufsize,
queue_max_hw_sectors(q) << SECTOR_SHIFT);
- bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+ max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q));
+ bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT);
while (bufsize >= SECTOR_SIZE) {
buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 35db061..2e6b241 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1819,6 +1819,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
return SCSI_MLQUEUE_DEVICE_BUSY;
}
+ payload->rangecount = 1;
payload->range.len = length;
payload->range.offset = offset_in_hvpg;
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 6f8a200..39aecd3 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -122,6 +122,10 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
set_bit(SDW_GROUP13_DEV_NUM, bus->assigned);
set_bit(SDW_MASTER_DEV_NUM, bus->assigned);
+ ret = sdw_irq_create(bus, fwnode);
+ if (ret)
+ return ret;
+
/*
* SDW is an enumerable bus, but devices can be powered off. So,
* they won't be able to report as present.
@@ -138,6 +142,7 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
if (ret < 0) {
dev_err(bus->dev, "Finding slaves failed:%d\n", ret);
+ sdw_irq_delete(bus);
return ret;
}
@@ -156,10 +161,6 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
bus->params.curr_bank = SDW_BANK0;
bus->params.next_bank = SDW_BANK1;
- ret = sdw_irq_create(bus, fwnode);
- if (ret)
- return ret;
-
return 0;
}
EXPORT_SYMBOL(sdw_bus_master_add);
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index 5ea6399..10a602d 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -353,9 +353,6 @@ static int intel_link_probe(struct auxiliary_device *auxdev,
/* use generic bandwidth allocation algorithm */
sdw->cdns.bus.compute_params = sdw_compute_params;
- /* avoid resuming from pm_runtime suspend if it's not required */
- dev_pm_set_driver_flags(dev, DPM_FLAG_SMART_SUSPEND);
-
ret = sdw_bus_master_add(bus, dev, dev->fwnode);
if (ret) {
dev_err(dev, "sdw_bus_master_add fail: %d\n", ret);
@@ -640,7 +637,10 @@ static int __maybe_unused intel_suspend(struct device *dev)
return 0;
}
- if (pm_runtime_suspended(dev)) {
+ /* Prevent runtime PM from racing with the code below. */
+ pm_runtime_disable(dev);
+
+ if (pm_runtime_status_suspended(dev)) {
dev_dbg(dev, "pm_runtime status: suspended\n");
clock_stop_quirks = sdw->link_res->clock_stop_quirks;
@@ -648,7 +648,7 @@ static int __maybe_unused intel_suspend(struct device *dev)
if ((clock_stop_quirks & SDW_INTEL_CLK_STOP_BUS_RESET) ||
!clock_stop_quirks) {
- if (pm_runtime_suspended(dev->parent)) {
+ if (pm_runtime_status_suspended(dev->parent)) {
/*
* paranoia check: this should not happen with the .prepare
* resume to full power
@@ -715,7 +715,6 @@ static int __maybe_unused intel_resume(struct device *dev)
struct sdw_cdns *cdns = dev_get_drvdata(dev);
struct sdw_intel *sdw = cdns_to_intel(cdns);
struct sdw_bus *bus = &cdns->bus;
- int link_flags;
int ret;
if (bus->prop.hw_disabled || !sdw->startup_done) {
@@ -724,23 +723,6 @@ static int __maybe_unused intel_resume(struct device *dev)
return 0;
}
- if (pm_runtime_suspended(dev)) {
- dev_dbg(dev, "pm_runtime status was suspended, forcing active\n");
-
- /* follow required sequence from runtime_pm.rst */
- pm_runtime_disable(dev);
- pm_runtime_set_active(dev);
- pm_runtime_mark_last_busy(dev);
- pm_runtime_enable(dev);
-
- pm_runtime_resume(bus->dev);
-
- link_flags = md_flags >> (bus->link_id * 8);
-
- if (!(link_flags & SDW_INTEL_MASTER_DISABLE_PM_RUNTIME_IDLE))
- pm_runtime_idle(dev);
- }
-
ret = sdw_intel_link_power_up(sdw);
if (ret) {
dev_err(dev, "%s failed: %d\n", __func__, ret);
@@ -761,6 +743,14 @@ static int __maybe_unused intel_resume(struct device *dev)
}
/*
+ * Runtime PM has been disabled in intel_suspend(), so set the status
+ * to active because the device has just been resumed and re-enable
+ * runtime PM.
+ */
+ pm_runtime_set_active(dev);
+ pm_runtime_enable(dev);
+
+ /*
* after system resume, the pm_runtime suspend() may kick in
* during the enumeration, before any children device force the
* master device to remain active. Using pm_runtime_get()
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 31a878d..7740f94 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -420,7 +420,7 @@ MODULE_LICENSE("GPL");
static void spi_test_print_hex_dump(char *pre, const void *ptr, size_t len)
{
/* limit the hex_dump */
- if (len < 1024) {
+ if (len <= 1024) {
print_hex_dump(KERN_INFO, pre,
DUMP_PREFIX_OFFSET, 16, 1,
ptr, len, 0);
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index a31a1db..5db0639 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -596,7 +596,11 @@ u64 spi_mem_calc_op_duration(struct spi_mem_op *op)
ns_per_cycles = 1000000000 / op->max_freq;
ncycles += ((op->cmd.nbytes * 8) / op->cmd.buswidth) / (op->cmd.dtr ? 2 : 1);
ncycles += ((op->addr.nbytes * 8) / op->addr.buswidth) / (op->addr.dtr ? 2 : 1);
- ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+
+ /* Dummy bytes are optional for some SPI flash memory operations */
+ if (op->dummy.nbytes)
+ ncycles += ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+
ncycles += ((op->data.nbytes * 8) / op->data.buswidth) / (op->data.dtr ? 2 : 1);
return ncycles * ns_per_cycles;
diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 17eb67e..94948c8 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -142,7 +142,7 @@ static void qcom_spi_set_read_loc_first(struct qcom_nand_controller *snandc,
else if (reg == NAND_READ_LOCATION_1)
snandc->regs->read_location1 = locreg_val;
else if (reg == NAND_READ_LOCATION_2)
- snandc->regs->read_location1 = locreg_val;
+ snandc->regs->read_location2 = locreg_val;
else if (reg == NAND_READ_LOCATION_3)
snandc->regs->read_location3 = locreg_val;
}
@@ -1307,8 +1307,7 @@ static int qcom_spi_send_cmdaddr(struct qcom_nand_controller *snandc,
snandc->qspi->addr1 = cpu_to_le32(s_op.addr1_reg << 16);
snandc->qspi->addr2 = cpu_to_le32(s_op.addr2_reg);
snandc->qspi->cmd = cpu_to_le32(cmd);
- qcom_spi_block_erase(snandc);
- return 0;
+ return qcom_spi_block_erase(snandc);
default:
break;
}
diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index 6680220..9ec9823 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -960,6 +960,10 @@ static int stm32_ospi_probe(struct platform_device *pdev)
err_pm_enable:
pm_runtime_force_suspend(ospi->dev);
mutex_destroy(&ospi->lock);
+ if (ospi->dma_chtx)
+ dma_release_channel(ospi->dma_chtx);
+ if (ospi->dma_chrx)
+ dma_release_channel(ospi->dma_chrx);
return ret;
}
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index f89826d..aa92fd5 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -264,6 +264,9 @@ static int sun4i_spi_transfer_one(struct spi_controller *host,
else
reg |= SUN4I_CTL_DHB;
+ /* Now that the settings are correct, enable the interface */
+ reg |= SUN4I_CTL_ENABLE;
+
sun4i_spi_write(sspi, SUN4I_CTL_REG, reg);
/* Ensure that we have a parent clock fast enough */
@@ -404,7 +407,7 @@ static int sun4i_spi_runtime_resume(struct device *dev)
}
sun4i_spi_write(sspi, SUN4I_CTL_REG,
- SUN4I_CTL_ENABLE | SUN4I_CTL_MASTER | SUN4I_CTL_TP);
+ SUN4I_CTL_MASTER | SUN4I_CTL_TP);
return 0;
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index 3822d7c..795a848 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -728,9 +728,9 @@ static int tegra_spi_set_hw_cs_timing(struct spi_device *spi)
u32 inactive_cycles;
u8 cs_state;
- if (setup->unit != SPI_DELAY_UNIT_SCK ||
- hold->unit != SPI_DELAY_UNIT_SCK ||
- inactive->unit != SPI_DELAY_UNIT_SCK) {
+ if ((setup->value && setup->unit != SPI_DELAY_UNIT_SCK) ||
+ (hold->value && hold->unit != SPI_DELAY_UNIT_SCK) ||
+ (inactive->value && inactive->unit != SPI_DELAY_UNIT_SCK)) {
dev_err(&spi->dev,
"Invalid delay unit %d, should be SPI_DELAY_UNIT_SCK\n",
SPI_DELAY_UNIT_SCK);
diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c
index 7540c20..351f983 100644
--- a/drivers/staging/axis-fifo/axis-fifo.c
+++ b/drivers/staging/axis-fifo/axis-fifo.c
@@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET);
if (!bytes_available) {
- dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n");
- reset_ip_core(fifo);
+ dev_err(fifo->dt_device, "received a packet of length 0\n");
ret = -EIO;
goto end_unlock;
}
if (bytes_available > len) {
- dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n",
+ dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n",
bytes_available, len);
- reset_ip_core(fifo);
ret = -EINVAL;
goto end_unlock;
}
@@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
/* this probably can't happen unless IP
* registers were previously mishandled
*/
- dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n");
- reset_ip_core(fifo);
+ dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n");
ret = -EIO;
goto end_unlock;
}
@@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
if (copy_to_user(buf + copied * sizeof(u32), tmp_buf,
copy * sizeof(u32))) {
- reset_ip_core(fifo);
ret = -EFAULT;
goto end_unlock;
}
@@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf,
if (copy_from_user(tmp_buf, buf + copied * sizeof(u32),
copy * sizeof(u32))) {
- reset_ip_core(fifo);
ret = -EFAULT;
goto end_unlock;
}
@@ -775,9 +770,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo)
goto end;
}
- /* IP sets TDFV to fifo depth - 4 so we will do the same */
- fifo->tx_fifo_depth -= 4;
-
ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo);
if (ret) {
dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n");
diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c
index 6c14d7b..081b17f 100644
--- a/drivers/staging/iio/adc/ad7816.c
+++ b/drivers/staging/iio/adc/ad7816.c
@@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev,
struct iio_dev *indio_dev = dev_to_iio_dev(dev);
struct ad7816_chip_info *chip = iio_priv(indio_dev);
- if (strcmp(buf, "full")) {
+ if (strcmp(buf, "full") == 0) {
gpiod_set_value(chip->rdwr_pin, 1);
chip->mode = AD7816_FULL;
} else {
diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
index b839b50..fa7ea4c 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
@@ -1900,6 +1900,7 @@ static int bcm2835_mmal_probe(struct vchiq_device *device)
__func__, ret);
goto free_dev;
}
+ dev->v4l2_dev.dev = &device->dev;
/* setup v4l controls */
ret = bcm2835_mmal_init_controls(dev, &dev->ctrl_handler);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 1244ef3..620ba6e0 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4263,8 +4263,8 @@ int iscsit_close_connection(
spin_unlock(&iscsit_global->ts_bitmap_lock);
iscsit_stop_timers_for_cmds(conn);
- iscsit_stop_nopin_response_timer(conn);
iscsit_stop_nopin_timer(conn);
+ iscsit_stop_nopin_response_timer(conn);
if (conn->conn_transport->iscsit_wait_conn)
conn->conn_transport->iscsit_wait_conn(conn);
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 1b137e0..3449945 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1746,6 +1746,12 @@ msm_serial_early_console_setup_dm(struct earlycon_device *device,
if (!device->port.membase)
return -ENODEV;
+ /* Disable DM / single-character modes */
+ msm_write(&device->port, 0, UARTDM_DMEN);
+ msm_write(&device->port, MSM_UART_CR_CMD_RESET_RX, MSM_UART_CR);
+ msm_write(&device->port, MSM_UART_CR_CMD_RESET_TX, MSM_UART_CR);
+ msm_write(&device->port, MSM_UART_CR_TX_ENABLE, MSM_UART_CR);
+
device->con->write = msm_serial_early_write_dm;
return 0;
}
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 5904a2d..054a8e6 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -563,8 +563,11 @@ static void sifive_serial_break_ctl(struct uart_port *port, int break_state)
static int sifive_serial_startup(struct uart_port *port)
{
struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+ unsigned long flags;
+ uart_port_lock_irqsave(&ssp->port, &flags);
__ssp_enable_rxwm(ssp);
+ uart_port_unlock_irqrestore(&ssp->port, flags);
return 0;
}
@@ -572,9 +575,12 @@ static int sifive_serial_startup(struct uart_port *port)
static void sifive_serial_shutdown(struct uart_port *port)
{
struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+ unsigned long flags;
+ uart_port_lock_irqsave(&ssp->port, &flags);
__ssp_disable_rxwm(ssp);
__ssp_disable_txwm(ssp);
+ uart_port_unlock_irqrestore(&ssp->port, flags);
}
/**
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 0bd6544..791e2f1 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -193,13 +193,12 @@ int set_selection_user(const struct tiocl_selection __user *sel,
return -EFAULT;
/*
- * TIOCL_SELCLEAR, TIOCL_SELPOINTER and TIOCL_SELMOUSEREPORT are OK to
- * use without CAP_SYS_ADMIN as they do not modify the selection.
+ * TIOCL_SELCLEAR and TIOCL_SELPOINTER are OK to use without
+ * CAP_SYS_ADMIN as they do not modify the selection.
*/
switch (v.sel_mode) {
case TIOCL_SELCLEAR:
case TIOCL_SELPOINTER:
- case TIOCL_SELMOUSEREPORT:
break;
default:
if (!capable(CAP_SYS_ADMIN))
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 240ce13..f1294c2 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -677,13 +677,6 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
unsigned long flags;
int err;
- if (!ufshcd_cmd_inflight(lrbp->cmd)) {
- dev_err(hba->dev,
- "%s: skip abort. cmd at tag %d already completed.\n",
- __func__, tag);
- return FAILED;
- }
-
/* Skip task abort in case previous aborts failed and report failure */
if (lrbp->req_abort_skip) {
dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n",
@@ -692,6 +685,11 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
}
hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+ if (!hwq) {
+ dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n",
+ __func__, tag);
+ return FAILED;
+ }
if (ufshcd_mcq_sqe_search(hba, hwq, tag)) {
/*
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 4415604..7735421 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -278,6 +278,7 @@ static const struct ufs_dev_quirk ufs_fixups[] = {
.model = UFS_ANY_MODEL,
.quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE |
+ UFS_DEVICE_QUIRK_PA_HIBER8TIME |
UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS },
{ .wmanufacturerid = UFS_VENDOR_SKHYNIX,
.model = UFS_ANY_MODEL,
@@ -5677,6 +5678,8 @@ static void ufshcd_mcq_compl_pending_transfer(struct ufs_hba *hba,
continue;
hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+ if (!hwq)
+ continue;
if (force_compl) {
ufshcd_mcq_compl_all_cqes_lock(hba, hwq);
@@ -7262,8 +7265,6 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
err = -EINVAL;
}
}
- ufshcd_add_query_upiu_trace(hba, err ? UFS_QUERY_ERR : UFS_QUERY_COMP,
- (struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
return err;
}
@@ -8470,6 +8471,31 @@ static int ufshcd_quirk_tune_host_pa_tactivate(struct ufs_hba *hba)
return ret;
}
+/**
+ * ufshcd_quirk_override_pa_h8time - Ensures proper adjustment of PA_HIBERN8TIME.
+ * @hba: per-adapter instance
+ *
+ * Some UFS devices require specific adjustments to the PA_HIBERN8TIME parameter
+ * to ensure proper hibernation timing. This function retrieves the current
+ * PA_HIBERN8TIME value and increments it by 100us.
+ */
+static void ufshcd_quirk_override_pa_h8time(struct ufs_hba *hba)
+{
+ u32 pa_h8time;
+ int ret;
+
+ ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_HIBERN8TIME), &pa_h8time);
+ if (ret) {
+ dev_err(hba->dev, "Failed to get PA_HIBERN8TIME: %d\n", ret);
+ return;
+ }
+
+ /* Increment by 1 to increase hibernation time by 100 µs */
+ ret = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HIBERN8TIME), pa_h8time + 1);
+ if (ret)
+ dev_err(hba->dev, "Failed updating PA_HIBERN8TIME: %d\n", ret);
+}
+
static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
{
ufshcd_vops_apply_dev_quirks(hba);
@@ -8480,6 +8506,9 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+ if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_HIBER8TIME)
+ ufshcd_quirk_override_pa_h8time(hba);
}
static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 1b37449..c0761cc 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -33,6 +33,10 @@
((((c) >> 16) & MCQ_QCFGPTR_MASK) * MCQ_QCFGPTR_UNIT)
#define MCQ_QCFG_SIZE 0x40
+/* De-emphasis for gear-5 */
+#define DEEMPHASIS_3_5_dB 0x04
+#define NO_DEEMPHASIS 0x0
+
enum {
TSTBUS_UAWM,
TSTBUS_UARM,
@@ -795,6 +799,23 @@ static int ufs_qcom_icc_update_bw(struct ufs_qcom_host *host)
return ufs_qcom_icc_set_bw(host, bw_table.mem_bw, bw_table.cfg_bw);
}
+static void ufs_qcom_set_tx_hs_equalizer(struct ufs_hba *hba, u32 gear, u32 tx_lanes)
+{
+ u32 equalizer_val;
+ int ret, i;
+
+ /* Determine the equalizer value based on the gear */
+ equalizer_val = (gear == 5) ? DEEMPHASIS_3_5_dB : NO_DEEMPHASIS;
+
+ for (i = 0; i < tx_lanes; i++) {
+ ret = ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(TX_HS_EQUALIZER, i),
+ equalizer_val);
+ if (ret)
+ dev_err(hba->dev, "%s: failed equalizer lane %d\n",
+ __func__, i);
+ }
+}
+
static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
enum ufs_notify_change_status status,
const struct ufs_pa_layer_attr *dev_max_params,
@@ -846,6 +867,11 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
dev_req_params->gear_tx,
PA_INITIAL_ADAPT);
}
+
+ if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING)
+ ufs_qcom_set_tx_hs_equalizer(hba,
+ dev_req_params->gear_tx, dev_req_params->lane_tx);
+
break;
case POST_CHANGE:
if (ufs_qcom_cfg_timers(hba, false)) {
@@ -893,6 +919,16 @@ static int ufs_qcom_quirk_host_pa_saveconfigtime(struct ufs_hba *hba)
(pa_vs_config_reg1 | (1 << 12)));
}
+static void ufs_qcom_override_pa_tx_hsg1_sync_len(struct ufs_hba *hba)
+{
+ int err;
+
+ err = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TX_HSG1_SYNC_LENGTH),
+ PA_TX_HSG1_SYNC_LENGTH_VAL);
+ if (err)
+ dev_err(hba->dev, "Failed (%d) set PA_TX_HSG1_SYNC_LENGTH\n", err);
+}
+
static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
{
int err = 0;
@@ -900,6 +936,9 @@ static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
+ if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH)
+ ufs_qcom_override_pa_tx_hsg1_sync_len(hba);
+
return err;
}
@@ -914,6 +953,10 @@ static struct ufs_dev_quirk ufs_qcom_dev_fixups[] = {
{ .wmanufacturerid = UFS_VENDOR_WDC,
.model = UFS_ANY_MODEL,
.quirk = UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE },
+ { .wmanufacturerid = UFS_VENDOR_SAMSUNG,
+ .model = UFS_ANY_MODEL,
+ .quirk = UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH |
+ UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING },
{}
};
diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h
index d0e6ec9..05d4cb5 100644
--- a/drivers/ufs/host/ufs-qcom.h
+++ b/drivers/ufs/host/ufs-qcom.h
@@ -122,8 +122,11 @@ enum {
TMRLUT_HW_CGC_EN | OCSC_HW_CGC_EN)
/* QUniPro Vendor specific attributes */
+#define PA_TX_HSG1_SYNC_LENGTH 0x1552
#define PA_VS_CONFIG_REG1 0x9000
#define DME_VS_CORE_CLK_CTRL 0xD002
+#define TX_HS_EQUALIZER 0x0037
+
/* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */
#define CLK_1US_CYCLES_MASK_V4 GENMASK(27, 16)
#define CLK_1US_CYCLES_MASK GENMASK(7, 0)
@@ -141,6 +144,21 @@ enum {
#define UNIPRO_CORE_CLK_FREQ_201_5_MHZ 202
#define UNIPRO_CORE_CLK_FREQ_403_MHZ 403
+/* TX_HSG1_SYNC_LENGTH attr value */
+#define PA_TX_HSG1_SYNC_LENGTH_VAL 0x4A
+
+/*
+ * Some ufs device vendors need a different TSync length.
+ * Enable this quirk to give an additional TX_HS_SYNC_LENGTH.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH BIT(16)
+
+/*
+ * Some ufs device vendors need a different Deemphasis setting.
+ * Enable this quirk to tune TX Deemphasis parameters.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING BIT(17)
+
/* ICE allocator type to share AES engines among TX stream and RX stream */
#define ICE_ALLOCATOR_TYPE 2
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 1b19b56..69c1df0 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
vmbus_device_unregister(channel->device_obj);
}
-/* Sysfs API to allow mmap of the ring buffers
+/* Function used for mmap of ring buffer sysfs interface.
* The ring buffer is allocated as contiguous memory by vmbus_open
*/
-static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
- const struct bin_attribute *attr,
- struct vm_area_struct *vma)
+static int
+hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma)
{
- struct vmbus_channel *channel
- = container_of(kobj, struct vmbus_channel, kobj);
void *ring_buffer = page_address(channel->ringbuffer_page);
if (channel->state != CHANNEL_OPENED_STATE)
@@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
channel->ringbuffer_pagecount << PAGE_SHIFT);
}
-static const struct bin_attribute ring_buffer_bin_attr = {
- .attr = {
- .name = "ring",
- .mode = 0600,
- },
- .size = 2 * SZ_2M,
- .mmap = hv_uio_ring_mmap,
-};
-
/* Callback from VMBUS subsystem when new channel created. */
static void
hv_uio_new_channel(struct vmbus_channel *new_sc)
@@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
/* Disable interrupts on sub channel */
new_sc->inbound.ring_buffer->interrupt_mask = 1;
set_channel_read_mode(new_sc, HV_CALL_ISR);
-
- ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr);
+ ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap);
if (ret) {
dev_err(device, "sysfs create ring bin file failed; %d\n", ret);
vmbus_close(new_sc);
@@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev,
goto fail_close;
}
- ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr);
- if (ret)
- dev_notice(&dev->device,
- "sysfs create ring bin file failed; %d\n", ret);
+ /*
+ * This internally calls sysfs_update_group, which returns a non-zero value if it executes
+ * before sysfs_create_group. This is expected as the 'ring' will be created later in
+ * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return
+ * value and print warning.
+ *
+ * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race
+ * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed
+ * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify
+ * APIs to make sure that ring is created.
+ */
+ hv_create_ring_sysfs(channel, hv_uio_ring_mmap);
hv_set_drvdata(dev, pdata);
@@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev)
if (!pdata)
return;
- sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+ hv_remove_ring_sysfs(dev->channel);
uio_unregister_device(&pdata->info);
hv_uio_cleanup(dev, pdata);
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 694aa14..d9d8dc0 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1963,6 +1963,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
unsigned int bit;
unsigned long reg;
+ local_bh_disable();
spin_lock_irqsave(&priv_dev->lock, flags);
reg = readl(&priv_dev->regs->usb_ists);
@@ -2004,6 +2005,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
irqend:
writel(~0, &priv_dev->regs->ep_ien);
spin_unlock_irqrestore(&priv_dev->lock, flags);
+ local_bh_enable();
return ret;
}
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index 87f3108..4824a10 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -139,6 +139,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev,
(portsc & PORT_CHANGE_BITS), port_regs);
}
+static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev)
+{
+ struct cdns *cdns = dev_get_drvdata(pdev->dev);
+ __le32 __iomem *reg;
+ void __iomem *base;
+ u32 offset = 0;
+ u32 val;
+
+ if (!cdns->override_apb_timeout)
+ return;
+
+ base = &pdev->cap_regs->hc_capbase;
+ offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP);
+ reg = base + offset + REG_CHICKEN_BITS_3_OFFSET;
+
+ val = le32_to_cpu(readl(reg));
+ val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout);
+ writel(cpu_to_le32(val), reg);
+}
+
static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit)
{
__le32 __iomem *reg;
@@ -1773,6 +1793,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev)
reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP);
pdev->rev_cap = reg;
+ pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision);
+
dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n",
readl(&pdev->rev_cap->ctrl_revision),
readl(&pdev->rev_cap->rtl_revision),
@@ -1798,6 +1820,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev)
pdev->hci_version = HC_VERSION(pdev->hcc_params);
pdev->hcc_params = readl(&pdev->cap_regs->hcc_params);
+ /*
+ * Override the APB timeout value to give the controller more time for
+ * enabling UTMI clock and synchronizing APB and UTMI clock domains.
+ * This fix is platform specific and is required to fixes issue with
+ * reading incorrect value from PORTSC register after resuming
+ * from L1 state.
+ */
+ cdnsp_set_apb_timeout_value(pdev);
+
cdnsp_get_rev_cap(pdev);
/* Make sure the Device Controller is halted. */
diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
index 84887df..12534be 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.h
+++ b/drivers/usb/cdns3/cdnsp-gadget.h
@@ -520,6 +520,9 @@ struct cdnsp_rev_cap {
#define REG_CHICKEN_BITS_2_OFFSET 0x48
#define CHICKEN_XDMA_2_TP_CACHE_DIS BIT(28)
+#define REG_CHICKEN_BITS_3_OFFSET 0x4C
+#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val))
+
/* XBUF Extended Capability ID. */
#define XBUF_CAP_ID 0xCB
#define XBUF_RX_TAG_MASK_0_OFFSET 0x1C
@@ -1357,6 +1360,7 @@ struct cdnsp_port {
* @rev_cap: Controller Capabilities Registers.
* @hcs_params1: Cached register copies of read-only HCSPARAMS1
* @hcc_params: Cached register copies of read-only HCCPARAMS1
+ * @rtl_revision: Cached controller rtl revision.
* @setup: Temporary buffer for setup packet.
* @ep0_preq: Internal allocated request used during enumeration.
* @ep0_stage: ep0 stage during enumeration process.
@@ -1411,6 +1415,8 @@ struct cdnsp_device {
__u32 hcs_params1;
__u32 hcs_params3;
__u32 hcc_params;
+ #define RTL_REVISION_NEW_LPM 0x2700
+ __u32 rtl_revision;
/* Lock used in interrupt thread context. */
spinlock_t lock;
struct usb_ctrlrequest setup;
diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c
index a511445..8c361b8 100644
--- a/drivers/usb/cdns3/cdnsp-pci.c
+++ b/drivers/usb/cdns3/cdnsp-pci.c
@@ -28,6 +28,8 @@
#define PCI_DRIVER_NAME "cdns-pci-usbssp"
#define PLAT_DRIVER_NAME "cdns-usbssp"
+#define CHICKEN_APB_TIMEOUT_VALUE 0x1C20
+
static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev)
{
/*
@@ -139,6 +141,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
cdnsp->otg_irq = pdev->irq;
}
+ /*
+ * Cadence PCI based platform require some longer timeout for APB
+ * to fixes domain clock synchronization issue after resuming
+ * controller from L1 state.
+ */
+ cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE;
+ pci_set_drvdata(pdev, cdnsp);
+
if (pci_is_enabled(func)) {
cdnsp->dev = dev;
cdnsp->gadget_init = cdnsp_gadget_init;
@@ -148,8 +158,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
goto free_cdnsp;
}
- pci_set_drvdata(pdev, cdnsp);
-
device_wakeup_enable(&pdev->dev);
if (pci_dev_run_wake(pdev))
pm_runtime_put_noidle(&pdev->dev);
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 4685252..fd06cb8 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev,
writel(db_value, reg_addr);
- cdnsp_force_l0_go(pdev);
+ if (pdev->rtl_revision < RTL_REVISION_NEW_LPM)
+ cdnsp_force_l0_go(pdev);
/* Doorbell was set. */
return true;
diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h
index 921cccf..801be9e 100644
--- a/drivers/usb/cdns3/core.h
+++ b/drivers/usb/cdns3/core.h
@@ -79,6 +79,8 @@ struct cdns3_platform_data {
* @pdata: platform data from glue layer
* @lock: spinlock structure
* @xhci_plat_data: xhci private data structure pointer
+ * @override_apb_timeout: hold value of APB timeout. For value 0 the default
+ * value in CHICKEN_BITS_3 will be preserved.
* @gadget_init: pointer to gadget initialization function
*/
struct cdns {
@@ -117,6 +119,7 @@ struct cdns {
struct cdns3_platform_data *pdata;
spinlock_t lock;
struct xhci_plat_priv *xhci_plat_data;
+ u32 override_apb_timeout;
int (*gadget_init)(struct cdns *cdns);
};
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 1a7fc63..4f8bfd2 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -336,6 +336,13 @@ static int ci_hdrc_imx_notify_event(struct ci_hdrc *ci, unsigned int event)
return ret;
}
+static void ci_hdrc_imx_disable_regulator(void *arg)
+{
+ struct ci_hdrc_imx_data *data = arg;
+
+ regulator_disable(data->hsic_pad_regulator);
+}
+
static int ci_hdrc_imx_probe(struct platform_device *pdev)
{
struct ci_hdrc_imx_data *data;
@@ -394,6 +401,13 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
"Failed to enable HSIC pad regulator\n");
goto err_put;
}
+ ret = devm_add_action_or_reset(dev,
+ ci_hdrc_imx_disable_regulator, data);
+ if (ret) {
+ dev_err(dev,
+ "Failed to add regulator devm action\n");
+ goto err_put;
+ }
}
}
@@ -432,11 +446,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
ret = imx_get_clks(dev);
if (ret)
- goto disable_hsic_regulator;
+ goto qos_remove_request;
ret = imx_prepare_enable_clks(dev);
if (ret)
- goto disable_hsic_regulator;
+ goto qos_remove_request;
ret = clk_prepare_enable(data->clk_wakeup);
if (ret)
@@ -470,7 +484,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) {
pdata.flags |= CI_HDRC_OVERRIDE_PHY_CONTROL;
data->override_phy_control = true;
- usb_phy_init(pdata.usb_phy);
+ ret = usb_phy_init(pdata.usb_phy);
+ if (ret) {
+ dev_err(dev, "Failed to init phy\n");
+ goto err_clk;
+ }
}
if (pdata.flags & CI_HDRC_SUPPORTS_RUNTIME_PM)
@@ -479,7 +497,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
ret = imx_usbmisc_init(data->usbmisc_data);
if (ret) {
dev_err(dev, "usbmisc init failed, ret=%d\n", ret);
- goto err_clk;
+ goto phy_shutdown;
}
data->ci_pdev = ci_hdrc_add_device(dev,
@@ -488,7 +506,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
if (IS_ERR(data->ci_pdev)) {
ret = PTR_ERR(data->ci_pdev);
dev_err_probe(dev, ret, "ci_hdrc_add_device failed\n");
- goto err_clk;
+ goto phy_shutdown;
}
if (data->usbmisc_data) {
@@ -522,19 +540,20 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
disable_device:
ci_hdrc_remove_device(data->ci_pdev);
+phy_shutdown:
+ if (data->override_phy_control)
+ usb_phy_shutdown(data->phy);
err_clk:
clk_disable_unprepare(data->clk_wakeup);
err_wakeup_clk:
imx_disable_unprepare_clks(dev);
-disable_hsic_regulator:
- if (data->hsic_pad_regulator)
- /* don't overwrite original ret (cf. EPROBE_DEFER) */
- regulator_disable(data->hsic_pad_regulator);
+qos_remove_request:
if (pdata.flags & CI_HDRC_PMQOS)
cpu_latency_qos_remove_request(&data->pm_qos_req);
data->ci_pdev = NULL;
err_put:
- put_device(data->usbmisc_data->dev);
+ if (data->usbmisc_data)
+ put_device(data->usbmisc_data->dev);
return ret;
}
@@ -556,10 +575,9 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev)
clk_disable_unprepare(data->clk_wakeup);
if (data->plat_data->flags & CI_HDRC_PMQOS)
cpu_latency_qos_remove_request(&data->pm_qos_req);
- if (data->hsic_pad_regulator)
- regulator_disable(data->hsic_pad_regulator);
}
- put_device(data->usbmisc_data->dev);
+ if (data->usbmisc_data)
+ put_device(data->usbmisc_data->dev);
}
static void ci_hdrc_imx_shutdown(struct platform_device *pdev)
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 86ee39d..16e7fa4 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -726,7 +726,7 @@ static int wdm_open(struct inode *inode, struct file *file)
rv = -EBUSY;
goto out;
}
-
+ smp_rmb(); /* ordered against wdm_wwan_port_stop() */
rv = usb_autopm_get_interface(desc->intf);
if (rv < 0) {
dev_err(&desc->intf->dev, "Error autopm - %d\n", rv);
@@ -829,6 +829,7 @@ static struct usb_class_driver wdm_class = {
static int wdm_wwan_port_start(struct wwan_port *port)
{
struct wdm_device *desc = wwan_port_get_drvdata(port);
+ int rv;
/* The interface is both exposed via the WWAN framework and as a
* legacy usbmisc chardev. If chardev is already open, just fail
@@ -848,7 +849,15 @@ static int wdm_wwan_port_start(struct wwan_port *port)
wwan_port_txon(port);
/* Start getting events */
- return usb_submit_urb(desc->validity, GFP_KERNEL);
+ rv = usb_submit_urb(desc->validity, GFP_KERNEL);
+ if (rv < 0) {
+ wwan_port_txoff(port);
+ desc->manage_power(desc->intf, 0);
+ /* this must be last lest we race with chardev open */
+ clear_bit(WDM_WWAN_IN_USE, &desc->flags);
+ }
+
+ return rv;
}
static void wdm_wwan_port_stop(struct wwan_port *port)
@@ -859,8 +868,10 @@ static void wdm_wwan_port_stop(struct wwan_port *port)
poison_urbs(desc);
desc->manage_power(desc->intf, 0);
clear_bit(WDM_READ, &desc->flags);
- clear_bit(WDM_WWAN_IN_USE, &desc->flags);
unpoison_urbs(desc);
+ smp_wmb(); /* ordered against wdm_open() */
+ /* this must be last lest we open a poisoned device */
+ clear_bit(WDM_WWAN_IN_USE, &desc->flags);
}
static void wdm_wwan_port_tx_complete(struct urb *urb)
@@ -868,7 +879,7 @@ static void wdm_wwan_port_tx_complete(struct urb *urb)
struct sk_buff *skb = urb->context;
struct wdm_device *desc = skb_shinfo(skb)->destructor_arg;
- usb_autopm_put_interface(desc->intf);
+ usb_autopm_put_interface_async(desc->intf);
wwan_port_txon(desc->wwanp);
kfree_skb(skb);
}
@@ -898,7 +909,7 @@ static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb)
req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
req->wValue = 0;
- req->wIndex = desc->inum;
+ req->wIndex = desc->inum; /* already converted */
req->wLength = cpu_to_le16(skb->len);
skb_shinfo(skb)->destructor_arg = desc;
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 34e46ef..740d2d2 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -482,6 +482,7 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
u8 *buffer;
u8 tag;
int rv;
+ long wait_rv;
dev_dbg(dev, "Enter ioctl_read_stb iin_ep_present: %d\n",
data->iin_ep_present);
@@ -511,16 +512,17 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
}
if (data->iin_ep_present) {
- rv = wait_event_interruptible_timeout(
+ wait_rv = wait_event_interruptible_timeout(
data->waitq,
atomic_read(&data->iin_data_valid) != 0,
file_data->timeout);
- if (rv < 0) {
- dev_dbg(dev, "wait interrupted %d\n", rv);
+ if (wait_rv < 0) {
+ dev_dbg(dev, "wait interrupted %ld\n", wait_rv);
+ rv = wait_rv;
goto exit;
}
- if (rv == 0) {
+ if (wait_rv == 0) {
dev_dbg(dev, "wait timed out\n");
rv = -ETIMEDOUT;
goto exit;
@@ -539,6 +541,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
dev_dbg(dev, "stb:0x%02x received %d\n", (unsigned int)*stb, rv);
+ rv = 0;
+
exit:
/* bump interrupt bTag */
data->iin_bTag += 1;
@@ -602,9 +606,9 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data,
{
struct usbtmc_device_data *data = file_data->data;
struct device *dev = &data->intf->dev;
- int rv;
u32 timeout;
unsigned long expire;
+ long wait_rv;
if (!data->iin_ep_present) {
dev_dbg(dev, "no interrupt endpoint present\n");
@@ -618,25 +622,24 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data,
mutex_unlock(&data->io_mutex);
- rv = wait_event_interruptible_timeout(
- data->waitq,
- atomic_read(&file_data->srq_asserted) != 0 ||
- atomic_read(&file_data->closing),
- expire);
+ wait_rv = wait_event_interruptible_timeout(
+ data->waitq,
+ atomic_read(&file_data->srq_asserted) != 0 ||
+ atomic_read(&file_data->closing),
+ expire);
mutex_lock(&data->io_mutex);
/* Note! disconnect or close could be called in the meantime */
if (atomic_read(&file_data->closing) || data->zombie)
- rv = -ENODEV;
+ return -ENODEV;
- if (rv < 0) {
- /* dev can be invalid now! */
- pr_debug("%s - wait interrupted %d\n", __func__, rv);
- return rv;
+ if (wait_rv < 0) {
+ dev_dbg(dev, "%s - wait interrupted %ld\n", __func__, wait_rv);
+ return wait_rv;
}
- if (rv == 0) {
+ if (wait_rv == 0) {
dev_dbg(dev, "%s - wait timed out\n", __func__);
return -ETIMEDOUT;
}
@@ -830,6 +833,7 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data,
unsigned long expire;
int bufcount = 1;
int again = 0;
+ long wait_rv;
/* mutex already locked */
@@ -942,19 +946,24 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data,
if (!(flags & USBTMC_FLAG_ASYNC)) {
dev_dbg(dev, "%s: before wait time %lu\n",
__func__, expire);
- retval = wait_event_interruptible_timeout(
+ wait_rv = wait_event_interruptible_timeout(
file_data->wait_bulk_in,
usbtmc_do_transfer(file_data),
expire);
- dev_dbg(dev, "%s: wait returned %d\n",
- __func__, retval);
+ dev_dbg(dev, "%s: wait returned %ld\n",
+ __func__, wait_rv);
- if (retval <= 0) {
- if (retval == 0)
- retval = -ETIMEDOUT;
+ if (wait_rv < 0) {
+ retval = wait_rv;
goto error;
}
+
+ if (wait_rv == 0) {
+ retval = -ETIMEDOUT;
+ goto error;
+ }
+
}
urb = usb_get_from_anchor(&file_data->in_anchor);
@@ -1380,7 +1389,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
if (!buffer)
return -ENOMEM;
- mutex_lock(&data->io_mutex);
+ retval = mutex_lock_interruptible(&data->io_mutex);
+ if (retval < 0)
+ goto exit_nolock;
+
if (data->zombie) {
retval = -ENODEV;
goto exit;
@@ -1503,6 +1515,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
exit:
mutex_unlock(&data->io_mutex);
+exit_nolock:
kfree(buffer);
return retval;
}
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8efbacc..36d3df7 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -369,6 +369,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x0781, 0x5583), .driver_info = USB_QUIRK_NO_LPM },
{ USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM },
+ /* SanDisk Corp. SanDisk 3.2Gen1 */
+ { USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Realforce 87U Keyboard */
{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
@@ -383,6 +386,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x0904, 0x6103), .driver_info =
USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+ /* Silicon Motion Flash Drive */
+ { USB_DEVICE(0x090c, 0x1000), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Sound Devices USBPre2 */
{ USB_DEVICE(0x0926, 0x0202), .driver_info =
USB_QUIRK_ENDPOINT_IGNORE },
@@ -539,6 +545,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x2040, 0x7200), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
+ /* VLI disk */
+ { USB_DEVICE(0x2109, 0x0711), .driver_info = USB_QUIRK_NO_LPM },
+
/* Raydium Touchscreen */
{ USB_DEVICE(0x2386, 0x3114), .driver_info = USB_QUIRK_NO_LPM },
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index aaa39e6..27eae4c 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1164,6 +1164,9 @@ struct dwc3_scratchpad_array {
* @gsbuscfg0_reqinfo: store GSBUSCFG0.DATRDREQINFO, DESRDREQINFO,
* DATWRREQINFO, and DESWRREQINFO value passed from
* glue driver.
+ * @wakeup_pending_funcs: Indicates whether any interface has requested for
+ * function wakeup in bitmap format where bit position
+ * represents interface_id.
*/
struct dwc3 {
struct work_struct drd_work;
@@ -1394,6 +1397,7 @@ struct dwc3 {
int num_ep_resized;
struct dentry *debug_root;
u32 gsbuscfg0_reqinfo;
+ u32 wakeup_pending_funcs;
};
#define INCRX_BURST_MODE 0
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index a33a42b..4ca7f62 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -207,15 +207,13 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data)
skip_usb3_phy:
/* ulpi reset via gpio-modepin or gpio-framework driver */
- reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+ reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(reset_gpio)) {
return dev_err_probe(dev, PTR_ERR(reset_gpio),
"Failed to request reset GPIO\n");
}
if (reset_gpio) {
- /* Toggle ulpi to reset the phy. */
- gpiod_set_value_cansleep(reset_gpio, 1);
usleep_range(5000, 10000);
gpiod_set_value_cansleep(reset_gpio, 0);
usleep_range(5000, 10000);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 47e73c4..3213612 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -276,8 +276,6 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd,
return ret;
}
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async);
-
/**
* dwc3_send_gadget_ep_cmd - issue an endpoint command
* @dep: the endpoint to which the command is going to be issued
@@ -2359,10 +2357,8 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g)
return __dwc3_gadget_get_frame(dwc);
}
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
+static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
{
- int retries;
-
int ret;
u32 reg;
@@ -2390,8 +2386,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
return -EINVAL;
}
- if (async)
- dwc3_gadget_enable_linksts_evts(dwc, true);
+ dwc3_gadget_enable_linksts_evts(dwc, true);
ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV);
if (ret < 0) {
@@ -2410,27 +2405,8 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
/*
* Since link status change events are enabled we will receive
- * an U0 event when wakeup is successful. So bail out.
+ * an U0 event when wakeup is successful.
*/
- if (async)
- return 0;
-
- /* poll until Link State changes to ON */
- retries = 20000;
-
- while (retries--) {
- reg = dwc3_readl(dwc->regs, DWC3_DSTS);
-
- /* in HS, means ON */
- if (DWC3_DSTS_USBLNKST(reg) == DWC3_LINK_STATE_U0)
- break;
- }
-
- if (DWC3_DSTS_USBLNKST(reg) != DWC3_LINK_STATE_U0) {
- dev_err(dwc->dev, "failed to send remote wakeup\n");
- return -EINVAL;
- }
-
return 0;
}
@@ -2451,7 +2427,7 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g)
spin_unlock_irqrestore(&dwc->lock, flags);
return -EINVAL;
}
- ret = __dwc3_gadget_wakeup(dwc, true);
+ ret = __dwc3_gadget_wakeup(dwc);
spin_unlock_irqrestore(&dwc->lock, flags);
@@ -2479,14 +2455,10 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id)
*/
link_state = dwc3_gadget_get_link_state(dwc);
if (link_state == DWC3_LINK_STATE_U3) {
- ret = __dwc3_gadget_wakeup(dwc, false);
- if (ret) {
- spin_unlock_irqrestore(&dwc->lock, flags);
- return -EINVAL;
- }
- dwc3_resume_gadget(dwc);
- dwc->suspended = false;
- dwc->link_state = DWC3_LINK_STATE_U0;
+ dwc->wakeup_pending_funcs |= BIT(intf_id);
+ ret = __dwc3_gadget_wakeup(dwc);
+ spin_unlock_irqrestore(&dwc->lock, flags);
+ return ret;
}
ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
@@ -4353,6 +4325,8 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
{
enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK;
unsigned int pwropt;
+ int ret;
+ int intf_id;
/*
* WORKAROUND: DWC3 < 2.50a have an issue when configured without
@@ -4428,7 +4402,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
switch (next) {
case DWC3_LINK_STATE_U0:
- if (dwc->gadget->wakeup_armed) {
+ if (dwc->gadget->wakeup_armed || dwc->wakeup_pending_funcs) {
dwc3_gadget_enable_linksts_evts(dwc, false);
dwc3_resume_gadget(dwc);
dwc->suspended = false;
@@ -4451,6 +4425,18 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
}
dwc->link_state = next;
+
+ /* Proceed with func wakeup if any interfaces that has requested */
+ while (dwc->wakeup_pending_funcs && (next == DWC3_LINK_STATE_U0)) {
+ intf_id = ffs(dwc->wakeup_pending_funcs) - 1;
+ ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
+ DWC3_DGCMDPAR_DN_FUNC_WAKE |
+ DWC3_DGCMDPAR_INTF_SEL(intf_id));
+ if (ret)
+ dev_err(dwc->dev, "Failed to send DN wake for intf %d\n", intf_id);
+
+ dwc->wakeup_pending_funcs &= ~BIT(intf_id);
+ }
}
static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc,
@@ -4617,6 +4603,12 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt)
if (!count)
return IRQ_NONE;
+ if (count > evt->length) {
+ dev_err_ratelimited(dwc->dev, "invalid count(%u) > evt->length(%u)\n",
+ count, evt->length);
+ return IRQ_NONE;
+ }
+
evt->count = count;
evt->flags |= DWC3_EVENT_PENDING;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 869ad99..8dbc132 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2011,15 +2011,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
if (f->get_status) {
status = f->get_status(f);
+
if (status < 0)
break;
- } else {
- /* Set D0 and D1 bits based on func wakeup capability */
- if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) {
- status |= USB_INTRF_STAT_FUNC_RW_CAP;
- if (f->func_wakeup_armed)
- status |= USB_INTRF_STAT_FUNC_RW;
- }
+
+ /* if D5 is not set, then device is not wakeup capable */
+ if (!(f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP))
+ status &= ~(USB_INTRF_STAT_FUNC_RW_CAP | USB_INTRF_STAT_FUNC_RW);
}
put_unaligned_le16(status & 0x0000ffff, req->buf);
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index 80841de..0272263 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -892,6 +892,12 @@ static void ecm_resume(struct usb_function *f)
gether_resume(&ecm->port);
}
+static int ecm_get_status(struct usb_function *f)
+{
+ return (f->func_wakeup_armed ? USB_INTRF_STAT_FUNC_RW : 0) |
+ USB_INTRF_STAT_FUNC_RW_CAP;
+}
+
static void ecm_free(struct usb_function *f)
{
struct f_ecm *ecm;
@@ -960,6 +966,7 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi)
ecm->port.func.disable = ecm_disable;
ecm->port.func.free_func = ecm_free;
ecm->port.func.suspend = ecm_suspend;
+ ecm->port.func.get_status = ecm_get_status;
ecm->port.func.resume = ecm_resume;
return &ecm->port.func;
diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
index 12e866f..0a800ba 100644
--- a/drivers/usb/gadget/function/f_midi2.c
+++ b/drivers/usb/gadget/function/f_midi2.c
@@ -475,7 +475,7 @@ static void reply_ump_stream_ep_info(struct f_midi2_ep *ep)
/* reply a UMP EP device info */
static void reply_ump_stream_ep_device(struct f_midi2_ep *ep)
{
- struct snd_ump_stream_msg_devince_info rep = {
+ struct snd_ump_stream_msg_device_info rep = {
.type = UMP_MSG_TYPE_STREAM,
.status = UMP_STREAM_MSG_STATUS_DEVICE_INFO,
.manufacture_id = ep->info.manufacturer,
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index c7fdbc5..2957316 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -1749,6 +1749,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep)
val = xudc_readl(xudc, CTRL);
val &= ~CTRL_RUN;
xudc_writel(xudc, val, CTRL);
+
+ val = xudc_readl(xudc, ST);
+ if (val & ST_RC)
+ xudc_writel(xudc, ST_RC, ST);
}
dev_info(xudc->dev, "ep %u disabled\n", ep->index);
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index 900ea0d..9f0a6b2 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -165,6 +165,25 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
return 0;
}
+static int ohci_quirk_loongson(struct usb_hcd *hcd)
+{
+ struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+
+ /*
+ * Loongson's LS7A OHCI controller (rev 0x02) has a
+ * flaw. MMIO register with offset 0x60/64 is treated
+ * as legacy PS2-compatible keyboard/mouse interface.
+ * Since OHCI only use 4KB BAR resource, LS7A OHCI's
+ * 32KB BAR is wrapped around (the 2nd 4KB BAR space
+ * is the same as the 1st 4KB internally). So add 4KB
+ * offset (0x1000) to the OHCI registers as a quirk.
+ */
+ if (pdev->revision == 0x2)
+ hcd->regs += SZ_4K; /* SZ_4K = 0x1000 */
+
+ return 0;
+}
+
static int ohci_quirk_qemu(struct usb_hcd *hcd)
{
struct ohci_hcd *ohci = hcd_to_ohci(hcd);
@@ -225,6 +244,10 @@ static const struct pci_device_id ohci_pci_quirks[] = {
.driver_data = (unsigned long)ohci_quirk_amd700,
},
{
+ PCI_DEVICE(PCI_VENDOR_ID_LOONGSON, 0x7a24),
+ .driver_data = (unsigned long)ohci_quirk_loongson,
+ },
+ {
.vendor = PCI_VENDOR_ID_APPLE,
.device = 0x003f,
.subvendor = PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c
index a7c9344..6231829 100644
--- a/drivers/usb/host/uhci-platform.c
+++ b/drivers/usb/host/uhci-platform.c
@@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev)
}
/* Get and enable clock if any specified */
- uhci->clk = devm_clk_get(&pdev->dev, NULL);
+ uhci->clk = devm_clk_get_optional(&pdev->dev, NULL);
if (IS_ERR(uhci->clk)) {
ret = PTR_ERR(uhci->clk);
goto err_rmr;
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index fd7895b..0d4ce57 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -823,6 +823,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
{
dma_addr_t deq;
union xhci_trb *evt;
+ enum evtreturn ret = EVT_DONE;
u32 ctrl, portsc;
bool update_erdp = false;
@@ -909,6 +910,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
break;
case TRB_TYPE(TRB_TRANSFER):
dbc_handle_xfer_event(dbc, evt);
+ ret = EVT_XFER_DONE;
break;
default:
break;
@@ -927,7 +929,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
lo_hi_writeq(deq, &dbc->regs->erdp);
}
- return EVT_DONE;
+ return ret;
}
static void xhci_dbc_handle_events(struct work_struct *work)
@@ -936,6 +938,7 @@ static void xhci_dbc_handle_events(struct work_struct *work)
struct xhci_dbc *dbc;
unsigned long flags;
unsigned int poll_interval;
+ unsigned long busypoll_timelimit;
dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work);
poll_interval = dbc->poll_interval;
@@ -954,11 +957,21 @@ static void xhci_dbc_handle_events(struct work_struct *work)
dbc->driver->disconnect(dbc);
break;
case EVT_DONE:
- /* set fast poll rate if there are pending data transfers */
+ /*
+ * Set fast poll rate if there are pending out transfers, or
+ * a transfer was recently processed
+ */
+ busypoll_timelimit = dbc->xfer_timestamp +
+ msecs_to_jiffies(DBC_XFER_INACTIVITY_TIMEOUT);
+
if (!list_empty(&dbc->eps[BULK_OUT].list_pending) ||
- !list_empty(&dbc->eps[BULK_IN].list_pending))
+ time_is_after_jiffies(busypoll_timelimit))
poll_interval = 0;
break;
+ case EVT_XFER_DONE:
+ dbc->xfer_timestamp = jiffies;
+ poll_interval = 0;
+ break;
default:
dev_info(dbc->dev, "stop handling dbc events\n");
return;
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index 9dc8f4d..47ac72c 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -96,6 +96,7 @@ struct dbc_ep {
#define DBC_WRITE_BUF_SIZE 8192
#define DBC_POLL_INTERVAL_DEFAULT 64 /* milliseconds */
#define DBC_POLL_INTERVAL_MAX 5000 /* milliseconds */
+#define DBC_XFER_INACTIVITY_TIMEOUT 10 /* milliseconds */
/*
* Private structure for DbC hardware state:
*/
@@ -142,6 +143,7 @@ struct xhci_dbc {
enum dbc_state state;
struct delayed_work event_work;
unsigned int poll_interval; /* ms */
+ unsigned long xfer_timestamp;
unsigned resume_required:1;
struct dbc_ep eps[2];
@@ -187,6 +189,7 @@ struct dbc_request {
enum evtreturn {
EVT_ERR = -1,
EVT_DONE,
+ EVT_XFER_DONE,
EVT_GSER,
EVT_DISC,
};
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index c0f2265..4863477 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1878,9 +1878,10 @@ int xhci_bus_resume(struct usb_hcd *hcd)
int max_ports, port_index;
int sret;
u32 next_state;
- u32 temp, portsc;
+ u32 portsc;
struct xhci_hub *rhub;
struct xhci_port **ports;
+ bool disabled_irq = false;
rhub = xhci_get_rhub(hcd);
ports = rhub->ports;
@@ -1896,17 +1897,20 @@ int xhci_bus_resume(struct usb_hcd *hcd)
return -ESHUTDOWN;
}
- /* delay the irqs */
- temp = readl(&xhci->op_regs->command);
- temp &= ~CMD_EIE;
- writel(temp, &xhci->op_regs->command);
-
/* bus specific resume for ports we suspended at bus_suspend */
- if (hcd->speed >= HCD_USB3)
+ if (hcd->speed >= HCD_USB3) {
next_state = XDEV_U0;
- else
+ } else {
next_state = XDEV_RESUME;
-
+ if (bus_state->bus_suspended) {
+ /*
+ * prevent port event interrupts from interfering
+ * with usb2 port resume process
+ */
+ xhci_disable_interrupter(xhci->interrupters[0]);
+ disabled_irq = true;
+ }
+ }
port_index = max_ports;
while (port_index--) {
portsc = readl(ports[port_index]->addr);
@@ -1974,11 +1978,9 @@ int xhci_bus_resume(struct usb_hcd *hcd)
(void) readl(&xhci->op_regs->command);
bus_state->next_statechange = jiffies + msecs_to_jiffies(5);
- /* re-enable irqs */
- temp = readl(&xhci->op_regs->command);
- temp |= CMD_EIE;
- writel(temp, &xhci->op_regs->command);
- temp = readl(&xhci->op_regs->command);
+ /* re-enable interrupter */
+ if (disabled_irq)
+ xhci_enable_interrupter(xhci->interrupters[0]);
spin_unlock_irqrestore(&xhci->lock, flags);
return 0;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 5d64c29..423bf36 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -561,8 +561,8 @@ void xhci_ring_ep_doorbell(struct xhci_hcd *xhci,
* pointer command pending because the device can choose to start any
* stream once the endpoint is on the HW schedule.
*/
- if (ep_state & (EP_STOP_CMD_PENDING | SET_DEQ_PENDING | EP_HALTED |
- EP_CLEARING_TT | EP_STALLED))
+ if ((ep_state & EP_STOP_CMD_PENDING) || (ep_state & SET_DEQ_PENDING) ||
+ (ep_state & EP_HALTED) || (ep_state & EP_CLEARING_TT))
return;
trace_xhci_ring_ep_doorbell(slot_id, DB_VALUE(ep_index, stream_id));
@@ -699,7 +699,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci,
int new_cycle;
dma_addr_t addr;
u64 hw_dequeue;
- bool cycle_found = false;
+ bool hw_dequeue_found = false;
bool td_last_trb_found = false;
u32 trb_sct = 0;
int ret;
@@ -715,25 +715,24 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci,
hw_dequeue = xhci_get_hw_deq(xhci, dev, ep_index, stream_id);
new_seg = ep_ring->deq_seg;
new_deq = ep_ring->dequeue;
- new_cycle = hw_dequeue & 0x1;
+ new_cycle = le32_to_cpu(td->end_trb->generic.field[3]) & TRB_CYCLE;
/*
- * We want to find the pointer, segment and cycle state of the new trb
- * (the one after current TD's end_trb). We know the cycle state at
- * hw_dequeue, so walk the ring until both hw_dequeue and end_trb are
- * found.
+ * Walk the ring until both the next TRB and hw_dequeue are found (don't
+ * move hw_dequeue back if it went forward due to a HW bug). Cycle state
+ * is loaded from a known good TRB, track later toggles to maintain it.
*/
do {
- if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq)
+ if (!hw_dequeue_found && xhci_trb_virt_to_dma(new_seg, new_deq)
== (dma_addr_t)(hw_dequeue & ~0xf)) {
- cycle_found = true;
+ hw_dequeue_found = true;
if (td_last_trb_found)
break;
}
if (new_deq == td->end_trb)
td_last_trb_found = true;
- if (cycle_found && trb_is_link(new_deq) &&
+ if (td_last_trb_found && trb_is_link(new_deq) &&
link_trb_toggles_cycle(new_deq))
new_cycle ^= 0x1;
@@ -745,7 +744,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci,
return -EINVAL;
}
- } while (!cycle_found || !td_last_trb_found);
+ } while (!hw_dequeue_found || !td_last_trb_found);
/* Don't update the ring cycle state for the producer (us). */
addr = xhci_trb_virt_to_dma(new_seg, new_deq);
@@ -2573,9 +2572,6 @@ static void process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
xhci_handle_halted_endpoint(xhci, ep, td, EP_SOFT_RESET);
return;
- case COMP_STALL_ERROR:
- ep->ep_state |= EP_STALLED;
- break;
default:
/* do nothing */
break;
@@ -2916,7 +2912,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
if (xhci_spurious_success_tx_event(xhci, ep_ring)) {
xhci_dbg(xhci, "Spurious event dma %pad, comp_code %u after %u\n",
&ep_trb_dma, trb_comp_code, ep_ring->old_trb_comp_code);
- ep_ring->old_trb_comp_code = trb_comp_code;
+ ep_ring->old_trb_comp_code = 0;
return 0;
}
@@ -3780,7 +3776,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
* enqueue a No Op TRB, this can prevent the Setup and Data Stage
* TRB to be breaked by the Link TRB.
*/
- if (trb_is_link(ep_ring->enqueue + 1)) {
+ if (last_trb_on_seg(ep_ring->enq_seg, ep_ring->enqueue + 1)) {
field = TRB_TYPE(TRB_TR_NOOP) | ep_ring->cycle_state;
queue_trb(xhci, ep_ring, false, 0, 0,
TRB_INTR_TARGET(0), field);
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index b5c362c..0c7af44 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1364,6 +1364,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl,
tegra->otg_usb2_port);
+ pm_runtime_get_sync(tegra->dev);
if (tegra->host_mode) {
/* switch to host mode */
if (tegra->otg_usb3_port >= 0) {
@@ -1393,6 +1394,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
}
tegra_xhci_set_port_power(tegra, true, true);
+ pm_runtime_mark_last_busy(tegra->dev);
} else {
if (tegra->otg_usb3_port >= 0)
@@ -1400,6 +1402,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
tegra_xhci_set_port_power(tegra, true, false);
}
+ pm_runtime_put_autosuspend(tegra->dev);
}
#if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 0452b8d..90eb491 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -322,7 +322,7 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci)
xhci_info(xhci, "Fault detected\n");
}
-static int xhci_enable_interrupter(struct xhci_interrupter *ir)
+int xhci_enable_interrupter(struct xhci_interrupter *ir)
{
u32 iman;
@@ -335,7 +335,7 @@ static int xhci_enable_interrupter(struct xhci_interrupter *ir)
return 0;
}
-static int xhci_disable_interrupter(struct xhci_interrupter *ir)
+int xhci_disable_interrupter(struct xhci_interrupter *ir)
{
u32 iman;
@@ -1605,11 +1605,6 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
goto free_priv;
}
- /* Class driver might not be aware ep halted due to async URB giveback */
- if (*ep_state & EP_STALLED)
- dev_dbg(&urb->dev->dev, "URB %p queued before clearing halt\n",
- urb);
-
switch (usb_endpoint_type(&urb->ep->desc)) {
case USB_ENDPOINT_XFER_CONTROL:
@@ -1770,8 +1765,8 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
goto done;
}
- /* In these cases no commands are pending but the endpoint is stopped */
- if (ep->ep_state & (EP_CLEARING_TT | EP_STALLED)) {
+ /* In this case no commands are pending but the endpoint is stopped */
+ if (ep->ep_state & EP_CLEARING_TT) {
/* and cancelled TDs can be given back right away */
xhci_dbg(xhci, "Invalidating TDs instantly on slot %d ep %d in state 0x%x\n",
urb->dev->slot_id, ep_index, ep->ep_state);
@@ -3209,11 +3204,8 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
ep = &vdev->eps[ep_index];
- spin_lock_irqsave(&xhci->lock, flags);
-
- ep->ep_state &= ~EP_STALLED;
-
/* Bail out if toggle is already being cleared by a endpoint reset */
+ spin_lock_irqsave(&xhci->lock, flags);
if (ep->ep_state & EP_HARD_CLEAR_TOGGLE) {
ep->ep_state &= ~EP_HARD_CLEAR_TOGGLE;
spin_unlock_irqrestore(&xhci->lock, flags);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 37860f1..242ab9f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -664,7 +664,7 @@ struct xhci_virt_ep {
unsigned int err_count;
unsigned int ep_state;
#define SET_DEQ_PENDING (1 << 0)
-#define EP_HALTED (1 << 1) /* Halted host ep handling */
+#define EP_HALTED (1 << 1) /* For stall handling */
#define EP_STOP_CMD_PENDING (1 << 2) /* For URB cancellation */
/* Transitioning the endpoint to using streams, don't enqueue URBs */
#define EP_GETTING_STREAMS (1 << 3)
@@ -675,7 +675,6 @@ struct xhci_virt_ep {
#define EP_SOFT_CLEAR_TOGGLE (1 << 7)
/* usb_hub_clear_tt_buffer is in progress */
#define EP_CLEARING_TT (1 << 8)
-#define EP_STALLED (1 << 9) /* For stall handling */
/* ---- Related to URB cancellation ---- */
struct list_head cancelled_td_list;
struct xhci_hcd *xhci;
@@ -1891,6 +1890,8 @@ int xhci_alloc_tt_info(struct xhci_hcd *xhci,
struct usb_tt *tt, gfp_t mem_flags);
int xhci_set_interrupter_moderation(struct xhci_interrupter *ir,
u32 imod_interval);
+int xhci_enable_interrupter(struct xhci_interrupter *ir);
+int xhci_disable_interrupter(struct xhci_interrupter *ir);
/* xHCI ring, segment, TRB, and TD functions */
dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, union xhci_trb *trb);
diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c
index 75ac3c6..f5372dfa 100644
--- a/drivers/usb/misc/onboard_usb_dev.c
+++ b/drivers/usb/misc/onboard_usb_dev.c
@@ -569,8 +569,14 @@ static void onboard_dev_usbdev_disconnect(struct usb_device *udev)
}
static const struct usb_device_id onboard_dev_id_table[] = {
- { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 HUB */
- { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6500) }, /* CYUSB330x 3.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6502) }, /* CYUSB330x 2.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6503) }, /* CYUSB33{0,1}x 2.0 HUB, Vendor Mode */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB331x 3.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB331x 2.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6507) }, /* CYUSB332x 2.0 HUB, Vendor Mode */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6508) }, /* CYUSB332x 3.0 HUB */
+ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x650a) }, /* CYUSB332x 2.0 HUB */
{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 HUB */
{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 HUB */
{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 HUB */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 9b34e23b7..6ac7a0a 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1093,6 +1093,8 @@ static const struct usb_device_id id_table_combined[] = {
{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 1) },
{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 2) },
{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 3) },
+ /* Abacus Electrics */
+ { USB_DEVICE(FTDI_VID, ABACUS_OPTICAL_PROBE_PID) },
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 52be47d..9acb6f8 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -443,6 +443,11 @@
#define LINX_FUTURE_2_PID 0xF44C /* Linx future device */
/*
+ * Abacus Electrics
+ */
+#define ABACUS_OPTICAL_PROBE_PID 0xf458 /* ABACUS ELECTRICS Optical Probe */
+
+/*
* Oceanic product ids
*/
#define FTDI_OCEANIC_PID 0xF460 /* Oceanic dive instrument */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 5cd26da..27879cc 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -611,6 +611,7 @@ static void option_instat_callback(struct urb *urb);
/* Sierra Wireless products */
#define SIERRA_VENDOR_ID 0x1199
#define SIERRA_PRODUCT_EM9191 0x90d3
+#define SIERRA_PRODUCT_EM9291 0x90e3
/* UNISOC (Spreadtrum) products */
#define UNISOC_VENDOR_ID 0x1782
@@ -2432,6 +2433,8 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 2c12449..a0afaf2 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -100,6 +100,11 @@ DEVICE(nokia, NOKIA_IDS);
{ USB_DEVICE(0x09d7, 0x0100) } /* NovAtel FlexPack GPS */
DEVICE_N(novatel_gps, NOVATEL_IDS, 3);
+/* OWON electronic test and measurement equipment driver */
+#define OWON_IDS() \
+ { USB_DEVICE(0x5345, 0x1234) } /* HDS200 oscilloscopes and others */
+DEVICE(owon, OWON_IDS);
+
/* Siemens USB/MPI adapter */
#define SIEMENS_IDS() \
{ USB_DEVICE(0x908, 0x0004) }
@@ -134,6 +139,7 @@ static struct usb_serial_driver * const serial_drivers[] = {
&motorola_tetra_device,
&nokia_device,
&novatel_gps_device,
+ &owon_device,
&siemens_mpi_device,
&suunto_device,
&vivopay_device,
@@ -153,6 +159,7 @@ static const struct usb_device_id id_table[] = {
MOTOROLA_TETRA_IDS(),
NOKIA_IDS(),
NOVATEL_IDS(),
+ OWON_IDS(),
SIEMENS_IDS(),
SUUNTO_IDS(),
VIVOPAY_IDS(),
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 1f8c9b1..d460d71 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -83,6 +83,13 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NO_REPORT_LUNS),
+/* Reported-by: Oliver Neukum <oneukum@suse.com> */
+UNUSUAL_DEV(0x125f, 0xa94a, 0x0160, 0x0160,
+ "ADATA",
+ "Portable HDD CH94",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_NO_ATA_1X),
+
/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
"Initio Corporation",
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 9c76c3d..67a533e 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1052,9 +1052,11 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
partner->usb_mode = USB_MODE_USB3;
}
+ mutex_lock(&port->partner_link_lock);
ret = device_register(&partner->dev);
if (ret) {
dev_err(&port->dev, "failed to register partner (%d)\n", ret);
+ mutex_unlock(&port->partner_link_lock);
put_device(&partner->dev);
return ERR_PTR(ret);
}
@@ -1063,6 +1065,7 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
typec_partner_link_device(partner, port->usb2_dev);
if (port->usb3_dev)
typec_partner_link_device(partner, port->usb3_dev);
+ mutex_unlock(&port->partner_link_lock);
return partner;
}
@@ -1083,12 +1086,18 @@ void typec_unregister_partner(struct typec_partner *partner)
port = to_typec_port(partner->dev.parent);
- if (port->usb2_dev)
+ mutex_lock(&port->partner_link_lock);
+ if (port->usb2_dev) {
typec_partner_unlink_device(partner, port->usb2_dev);
- if (port->usb3_dev)
+ port->usb2_dev = NULL;
+ }
+ if (port->usb3_dev) {
typec_partner_unlink_device(partner, port->usb3_dev);
+ port->usb3_dev = NULL;
+ }
device_unregister(&partner->dev);
+ mutex_unlock(&port->partner_link_lock);
}
EXPORT_SYMBOL_GPL(typec_unregister_partner);
@@ -2041,10 +2050,11 @@ static struct typec_partner *typec_get_partner(struct typec_port *port)
static void typec_partner_attach(struct typec_connector *con, struct device *dev)
{
struct typec_port *port = container_of(con, struct typec_port, con);
- struct typec_partner *partner = typec_get_partner(port);
+ struct typec_partner *partner;
struct usb_device *udev = to_usb_device(dev);
enum usb_mode usb_mode;
+ mutex_lock(&port->partner_link_lock);
if (udev->speed < USB_SPEED_SUPER) {
usb_mode = USB_MODE_USB2;
port->usb2_dev = dev;
@@ -2053,18 +2063,22 @@ static void typec_partner_attach(struct typec_connector *con, struct device *dev
port->usb3_dev = dev;
}
+ partner = typec_get_partner(port);
if (partner) {
typec_partner_set_usb_mode(partner, usb_mode);
typec_partner_link_device(partner, dev);
put_device(&partner->dev);
}
+ mutex_unlock(&port->partner_link_lock);
}
static void typec_partner_deattach(struct typec_connector *con, struct device *dev)
{
struct typec_port *port = container_of(con, struct typec_port, con);
- struct typec_partner *partner = typec_get_partner(port);
+ struct typec_partner *partner;
+ mutex_lock(&port->partner_link_lock);
+ partner = typec_get_partner(port);
if (partner) {
typec_partner_unlink_device(partner, dev);
put_device(&partner->dev);
@@ -2074,6 +2088,7 @@ static void typec_partner_deattach(struct typec_connector *con, struct device *d
port->usb2_dev = NULL;
else if (port->usb3_dev == dev)
port->usb3_dev = NULL;
+ mutex_unlock(&port->partner_link_lock);
}
/**
@@ -2614,6 +2629,7 @@ struct typec_port *typec_register_port(struct device *parent,
ida_init(&port->mode_ids);
mutex_init(&port->port_type_lock);
+ mutex_init(&port->partner_link_lock);
port->id = id;
port->ops = cap->ops;
diff --git a/drivers/usb/typec/class.h b/drivers/usb/typec/class.h
index b3076a2..db2fe96 100644
--- a/drivers/usb/typec/class.h
+++ b/drivers/usb/typec/class.h
@@ -59,6 +59,7 @@ struct typec_port {
enum typec_port_type port_type;
enum usb_mode usb_mode;
struct mutex port_type_lock;
+ struct mutex partner_link_lock;
enum typec_orientation orientation;
struct typec_switch *sw;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a99db4e..8adf6f9 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -5965,7 +5965,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
case SNK_TRY_WAIT_DEBOUNCE:
if (!tcpm_port_is_sink(port)) {
port->max_wait = 0;
- tcpm_set_state(port, SRC_TRYWAIT, 0);
+ tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE);
}
break;
case SRC_TRY_WAIT:
diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index 420af51..8aae80b 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
u8 cur = 0;
int ret;
- mutex_lock(&dp->con->lock);
+ if (!ucsi_con_mutex_lock(dp->con))
+ return -ENOTCONN;
if (!dp->override && dp->initialized) {
const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
schedule_work(&dp->work);
ret = 0;
err_unlock:
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return ret;
}
@@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
u64 command;
int ret = 0;
- mutex_lock(&dp->con->lock);
+ if (!ucsi_con_mutex_lock(dp->con))
+ return -ENOTCONN;
if (!dp->override) {
const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
schedule_work(&dp->work);
out_unlock:
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return ret;
}
@@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
int cmd = PD_VDO_CMD(header);
int svdm_version;
- mutex_lock(&dp->con->lock);
+ if (!ucsi_con_mutex_lock(dp->con))
+ return -ENOTCONN;
if (!dp->override && dp->initialized) {
const struct typec_altmode *p = typec_altmode_get_partner(alt);
dev_warn(&p->dev,
"firmware doesn't support alternate mode overriding\n");
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return -EOPNOTSUPP;
}
svdm_version = typec_altmode_get_svdm_version(alt);
if (svdm_version < 0) {
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return svdm_version;
}
@@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
break;
}
- mutex_unlock(&dp->con->lock);
+ ucsi_con_mutex_unlock(dp->con);
return 0;
}
@@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt)
if (!dp)
return;
+ cancel_work_sync(&dp->work);
+
dp->data.conf = 0;
dp->data.status = 0;
dp->initialized = false;
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index e8c7e9d..01ce858 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1923,6 +1923,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data)
EXPORT_SYMBOL_GPL(ucsi_set_drvdata);
/**
+ * ucsi_con_mutex_lock - Acquire the connector mutex
+ * @con: The connector interface to lock
+ *
+ * Returns true on success, false if the connector is disconnected
+ */
+bool ucsi_con_mutex_lock(struct ucsi_connector *con)
+{
+ bool mutex_locked = false;
+ bool connected = true;
+
+ while (connected && !mutex_locked) {
+ mutex_locked = mutex_trylock(&con->lock) != 0;
+ connected = UCSI_CONSTAT(con, CONNECTED);
+ if (connected && !mutex_locked)
+ msleep(20);
+ }
+
+ connected = connected && con->partner;
+ if (!connected && mutex_locked)
+ mutex_unlock(&con->lock);
+
+ return connected;
+}
+
+/**
+ * ucsi_con_mutex_unlock - Release the connector mutex
+ * @con: The connector interface to unlock
+ */
+void ucsi_con_mutex_unlock(struct ucsi_connector *con)
+{
+ mutex_unlock(&con->lock);
+}
+
+/**
* ucsi_create - Allocate UCSI instance
* @dev: Device interface to the PPM (Platform Policy Manager)
* @ops: I/O routines
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 3a2c176..9c5278a 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -94,6 +94,8 @@ int ucsi_register(struct ucsi *ucsi);
void ucsi_unregister(struct ucsi *ucsi);
void *ucsi_get_drvdata(struct ucsi *ucsi);
void ucsi_set_drvdata(struct ucsi *ucsi, void *data);
+bool ucsi_con_mutex_lock(struct ucsi_connector *con);
+void ucsi_con_mutex_unlock(struct ucsi_connector *con);
void ucsi_connector_change(struct ucsi *ucsi, u8 num);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 35f9046..6328c3a 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1646,14 +1646,14 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
{
struct vm_area_struct *vma = vmf->vma;
struct vfio_pci_core_device *vdev = vma->vm_private_data;
- unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff;
+ unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1);
+ unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+ unsigned long pfn = vma_to_pfn(vma) + pgoff;
vm_fault_t ret = VM_FAULT_SIGBUS;
- pfn = vma_to_pfn(vma) + pgoff;
-
- if (order && (pfn & ((1 << order) - 1) ||
- vmf->address & ((PAGE_SIZE << order) - 1) ||
- vmf->address + (PAGE_SIZE << order) > vma->vm_end)) {
+ if (order && (addr < vma->vm_start ||
+ addr + (PAGE_SIZE << order) > vma->vm_end ||
+ pfn & ((1 << order) - 1))) {
ret = VM_FAULT_FALLBACK;
goto out;
}
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index f6f5a7a..26bcf3a 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -627,6 +627,9 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
int ret;
llnode = llist_del_all(&svq->completion_list);
+
+ mutex_lock(&svq->vq.mutex);
+
llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
se_cmd = &cmd->tvc_se_cmd;
@@ -660,6 +663,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
vhost_scsi_release_cmd_res(se_cmd);
}
+ mutex_unlock(&svq->vq.mutex);
+
if (signal)
vhost_signal(&svq->vs->dev, &svq->vq);
}
@@ -994,39 +999,66 @@ static void vhost_scsi_target_queue_cmd(struct vhost_scsi_nexus *nexus,
static void
vhost_scsi_send_status(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
- int head, unsigned int out, u8 status)
+ struct vhost_scsi_ctx *vc, u8 status)
{
- struct virtio_scsi_cmd_resp __user *resp;
struct virtio_scsi_cmd_resp rsp;
+ struct iov_iter iov_iter;
int ret;
memset(&rsp, 0, sizeof(rsp));
rsp.status = status;
- resp = vq->iov[out].iov_base;
- ret = __copy_to_user(resp, &rsp, sizeof(rsp));
- if (!ret)
- vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+ iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+ sizeof(rsp));
+
+ ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+
+ if (likely(ret == sizeof(rsp)))
+ vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
}
+#define TYPE_IO_CMD 0
+#define TYPE_CTRL_TMF 1
+#define TYPE_CTRL_AN 2
+
static void
vhost_scsi_send_bad_target(struct vhost_scsi *vs,
struct vhost_virtqueue *vq,
- int head, unsigned out)
+ struct vhost_scsi_ctx *vc, int type)
{
- struct virtio_scsi_cmd_resp __user *resp;
- struct virtio_scsi_cmd_resp rsp;
+ union {
+ struct virtio_scsi_cmd_resp cmd;
+ struct virtio_scsi_ctrl_tmf_resp tmf;
+ struct virtio_scsi_ctrl_an_resp an;
+ } rsp;
+ struct iov_iter iov_iter;
+ size_t rsp_size;
int ret;
memset(&rsp, 0, sizeof(rsp));
- rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
- resp = vq->iov[out].iov_base;
- ret = __copy_to_user(resp, &rsp, sizeof(rsp));
- if (!ret)
- vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+ if (type == TYPE_IO_CMD) {
+ rsp_size = sizeof(struct virtio_scsi_cmd_resp);
+ rsp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+ } else if (type == TYPE_CTRL_TMF) {
+ rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+ rsp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET;
+ } else {
+ rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+ rsp.an.response = VIRTIO_SCSI_S_BAD_TARGET;
+ }
+
+ iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+ rsp_size);
+
+ ret = copy_to_iter(&rsp, rsp_size, &iov_iter);
+
+ if (likely(ret == rsp_size))
+ vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
else
- pr_err("Faulted on virtio_scsi_cmd_resp\n");
+ pr_err("Faulted on virtio scsi type=%d\n", type);
}
static int
@@ -1390,9 +1422,9 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
if (ret == -ENXIO)
break;
else if (ret == -EIO)
- vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+ vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD);
else if (ret == -ENOMEM)
- vhost_scsi_send_status(vs, vq, vc.head, vc.out,
+ vhost_scsi_send_status(vs, vq, &vc,
SAM_STAT_TASK_SET_FULL);
} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
@@ -1432,8 +1464,11 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
else
resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+ mutex_lock(&tmf->svq->vq.mutex);
vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
tmf->vq_desc, &tmf->resp_iov, resp_code);
+ mutex_unlock(&tmf->svq->vq.mutex);
+
vhost_scsi_release_tmf_res(tmf);
}
@@ -1623,7 +1658,10 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
if (ret == -ENXIO)
break;
else if (ret == -EIO)
- vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+ vhost_scsi_send_bad_target(vs, vq, &vc,
+ v_req.type == VIRTIO_SCSI_T_TMF ?
+ TYPE_CTRL_TMF :
+ TYPE_CTRL_AN);
} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
mutex_unlock(&vq->mutex);
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 150753c..95d5d79 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -407,6 +407,12 @@ static void virtio_dev_shutdown(struct device *_d)
if (!drv)
return;
+ /* If the driver has its own shutdown method, use that. */
+ if (drv->shutdown) {
+ drv->shutdown(dev);
+ return;
+ }
+
/*
* Some devices get wedged if you kick them after they are
* reset. Mark all vqs as broken to make sure we don't.
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 5eaade7..d50fe03 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -247,7 +247,7 @@ virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev)
sg_init_one(&data_sg, get_data, sizeof(*get_data));
sg_init_one(&result_sg, result, sizeof(*result));
cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET);
- cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+ cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
cmd.data_sg = &data_sg;
cmd.result_sg = &result_sg;
ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
@@ -305,7 +305,7 @@ static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev)
sg_init_one(&result_sg, data, sizeof(*data));
cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY);
- cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+ cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
cmd.result_sg = &result_sg;
ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index fdd2d2b..b784aab 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2650,7 +2650,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
struct vring_virtqueue *vq = to_vvq(_vq);
if (vq->event_triggered)
- vq->event_triggered = false;
+ data_race(vq->event_triggered = false);
return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
virtqueue_enable_cb_delayed_split(_vq);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1f65795..ef56a25 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -217,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
* buffering it.
*/
if (dma_capable(dev, dev_addr, size, true) &&
+ !dma_kmalloc_needs_bounce(dev, size, dir) &&
!range_straddles_page_boundary(phys, size) &&
!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
!is_swiotlb_force_bounce(dev))
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 13821e7..9ac0427 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -77,6 +77,7 @@ enum xb_req_state {
struct xb_req_data {
struct list_head list;
wait_queue_head_t wq;
+ struct kref kref;
struct xsd_sockmsg msg;
uint32_t caller_req_id;
enum xsd_sockmsg_type type;
@@ -103,6 +104,7 @@ int xb_init_comms(void);
void xb_deinit_comms(void);
int xs_watch_msg(struct xs_watch_event *event);
void xs_request_exit(struct xb_req_data *req);
+void xs_free_req(struct kref *kref);
int xenbus_match(struct device *_dev, const struct device_driver *_drv);
int xenbus_dev_probe(struct device *_dev);
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index e5fda02..82df2da 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -309,8 +309,8 @@ static int process_msg(void)
virt_wmb();
req->state = xb_req_state_got_reply;
req->cb(req);
- } else
- kfree(req);
+ }
+ kref_put(&req->kref, xs_free_req);
}
mutex_unlock(&xs_response_mutex);
@@ -386,14 +386,13 @@ static int process_writes(void)
state.req->msg.type = XS_ERROR;
state.req->err = err;
list_del(&state.req->list);
- if (state.req->state == xb_req_state_aborted)
- kfree(state.req);
- else {
+ if (state.req->state != xb_req_state_aborted) {
/* write err, then update state */
virt_wmb();
state.req->state = xb_req_state_got_reply;
wake_up(&state.req->wq);
}
+ kref_put(&state.req->kref, xs_free_req);
mutex_unlock(&xb_write_mutex);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 46f8916..f5c21ba 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req)
mutex_unlock(&u->reply_mutex);
kfree(req->body);
- kfree(req);
+ kref_put(&req->kref, xs_free_req);
kref_put(&u->kref, xenbus_file_free);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 6d32ffb..86fe6e7 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -966,9 +966,15 @@ static int __init xenbus_init(void)
if (xen_pv_domain())
xen_store_domain_type = XS_PV;
if (xen_hvm_domain())
+ {
xen_store_domain_type = XS_HVM;
- if (xen_hvm_domain() && xen_initial_domain())
- xen_store_domain_type = XS_LOCAL;
+ err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+ if (err)
+ goto out_error;
+ xen_store_evtchn = (int)v;
+ if (!v && xen_initial_domain())
+ xen_store_domain_type = XS_LOCAL;
+ }
if (xen_pv_domain() && !xen_start_info->store_evtchn)
xen_store_domain_type = XS_LOCAL;
if (xen_pv_domain() && xen_start_info->store_evtchn)
@@ -987,10 +993,6 @@ static int __init xenbus_init(void)
xen_store_interface = gfn_to_virt(xen_store_gfn);
break;
case XS_HVM:
- err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
- if (err)
- goto out_error;
- xen_store_evtchn = (int)v;
err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
if (err)
goto out_error;
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index d32c726..dcf9182 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -112,6 +112,12 @@ static void xs_suspend_exit(void)
wake_up_all(&xs_state_enter_wq);
}
+void xs_free_req(struct kref *kref)
+{
+ struct xb_req_data *req = container_of(kref, struct xb_req_data, kref);
+ kfree(req);
+}
+
static uint32_t xs_request_enter(struct xb_req_data *req)
{
uint32_t rq_id;
@@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg)
req->caller_req_id = req->msg.req_id;
req->msg.req_id = xs_request_enter(req);
+ /*
+ * Take 2nd ref. One for this thread, and the second for the
+ * xenbus_thread.
+ */
+ kref_get(&req->kref);
+
mutex_lock(&xb_write_mutex);
list_add_tail(&req->list, &xb_write_list);
notify = list_is_singular(&xb_write_list);
@@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg)
if (req->state == xb_req_state_queued ||
req->state == xb_req_state_wait_reply)
req->state = xb_req_state_aborted;
- else
- kfree(req);
+
+ kref_put(&req->kref, xs_free_req);
mutex_unlock(&xb_write_mutex);
return ret;
@@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par)
req->cb = xenbus_dev_queue_reply;
req->par = par;
req->user_req = true;
+ kref_init(&req->kref);
xs_send(req, msg);
@@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t,
req->num_vecs = num_vecs;
req->cb = xs_wake_up;
req->user_req = false;
+ kref_init(&req->kref);
msg.req_id = 0;
msg.tx_id = t.id;
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 7c930ef..7ec022e 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1422,8 +1422,30 @@ int bch2_alloc_sectors_start_trans(struct btree_trans *trans,
wp->sectors_free = UINT_MAX;
- open_bucket_for_each(c, &wp->ptrs, ob, i)
+ open_bucket_for_each(c, &wp->ptrs, ob, i) {
+ /*
+ * Ensure proper write alignment - either due to misaligned
+ * bucket sizes (from buggy bcachefs-tools), or writes that mix
+ * logical/physical alignment:
+ */
+ struct bch_dev *ca = ob_dev(c, ob);
+ u64 offset = bucket_to_sector(ca, ob->bucket) +
+ ca->mi.bucket_size -
+ ob->sectors_free;
+ unsigned align = round_up(offset, block_sectors(c)) - offset;
+
+ ob->sectors_free = max_t(int, 0, ob->sectors_free - align);
+
wp->sectors_free = min(wp->sectors_free, ob->sectors_free);
+ }
+
+ wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c));
+
+ /* Did alignment use up space in an open_bucket? */
+ if (unlikely(!wp->sectors_free)) {
+ bch2_alloc_sectors_done(c, wp);
+ goto retry;
+ }
BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX);
diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h
index 69ec6a0..4c1e33c 100644
--- a/fs/bcachefs/alloc_foreground.h
+++ b/fs/bcachefs/alloc_foreground.h
@@ -110,7 +110,9 @@ static inline void bch2_alloc_sectors_done_inlined(struct bch_fs *c, struct writ
unsigned i;
open_bucket_for_each(c, &wp->ptrs, ob, i)
- ob_push(c, !ob->sectors_free ? &ptrs : &keep, ob);
+ ob_push(c, ob->sectors_free < block_sectors(c)
+ ? &ptrs
+ : &keep, ob);
wp->ptrs = keep;
mutex_unlock(&wp->lock);
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index ff26bb5..5f195d2 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -192,7 +192,8 @@ static inline int bch2_backpointers_maybe_flush(struct btree_trans *trans,
static int backpointer_target_not_found(struct btree_trans *trans,
struct bkey_s_c_backpointer bp,
struct bkey_s_c target_k,
- struct bkey_buf *last_flushed)
+ struct bkey_buf *last_flushed,
+ bool commit)
{
struct bch_fs *c = trans->c;
struct printbuf buf = PRINTBUF;
@@ -228,18 +229,77 @@ static int backpointer_target_not_found(struct btree_trans *trans,
}
if (fsck_err(trans, backpointer_to_missing_ptr,
- "%s", buf.buf))
+ "%s", buf.buf)) {
ret = bch2_backpointer_del(trans, bp.k->p);
+ if (ret || !commit)
+ goto out;
+
+ /*
+ * Normally, on transaction commit from inside a transaction,
+ * we'll return -BCH_ERR_transaction_restart_nested, since a
+ * transaction commit invalidates pointers given out by peek().
+ *
+ * However, since we're updating a write buffer btree, if we
+ * return a transaction restart and loop we won't see that the
+ * backpointer has been deleted without an additional write
+ * buffer flush - and those are expensive.
+ *
+ * So we're relying on the caller immediately advancing to the
+ * next backpointer and starting a new transaction immediately
+ * after backpointer_get_key() returns NULL:
+ */
+ ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+ }
+out:
fsck_err:
printbuf_exit(&buf);
return ret;
}
-struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans,
- struct bkey_s_c_backpointer bp,
- struct btree_iter *iter,
- unsigned iter_flags,
- struct bkey_buf *last_flushed)
+static struct btree *__bch2_backpointer_get_node(struct btree_trans *trans,
+ struct bkey_s_c_backpointer bp,
+ struct btree_iter *iter,
+ struct bkey_buf *last_flushed,
+ bool commit)
+{
+ struct bch_fs *c = trans->c;
+
+ BUG_ON(!bp.v->level);
+
+ bch2_trans_node_iter_init(trans, iter,
+ bp.v->btree_id,
+ bp.v->pos,
+ 0,
+ bp.v->level - 1,
+ 0);
+ struct btree *b = bch2_btree_iter_peek_node(trans, iter);
+ if (IS_ERR_OR_NULL(b))
+ goto err;
+
+ BUG_ON(b->c.level != bp.v->level - 1);
+
+ if (extent_matches_bp(c, bp.v->btree_id, bp.v->level,
+ bkey_i_to_s_c(&b->key), bp))
+ return b;
+
+ if (btree_node_will_make_reachable(b)) {
+ b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
+ } else {
+ int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key),
+ last_flushed, commit);
+ b = ret ? ERR_PTR(ret) : NULL;
+ }
+err:
+ bch2_trans_iter_exit(trans, iter);
+ return b;
+}
+
+static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans,
+ struct bkey_s_c_backpointer bp,
+ struct btree_iter *iter,
+ unsigned iter_flags,
+ struct bkey_buf *last_flushed,
+ bool commit)
{
struct bch_fs *c = trans->c;
@@ -277,10 +337,10 @@ struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans,
bch2_trans_iter_exit(trans, iter);
if (!bp.v->level) {
- int ret = backpointer_target_not_found(trans, bp, k, last_flushed);
+ int ret = backpointer_target_not_found(trans, bp, k, last_flushed, commit);
return ret ? bkey_s_c_err(ret) : bkey_s_c_null;
} else {
- struct btree *b = bch2_backpointer_get_node(trans, bp, iter, last_flushed);
+ struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit);
if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node))
return bkey_s_c_null;
if (IS_ERR_OR_NULL(b))
@@ -295,35 +355,16 @@ struct btree *bch2_backpointer_get_node(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_buf *last_flushed)
{
- struct bch_fs *c = trans->c;
+ return __bch2_backpointer_get_node(trans, bp, iter, last_flushed, true);
+}
- BUG_ON(!bp.v->level);
-
- bch2_trans_node_iter_init(trans, iter,
- bp.v->btree_id,
- bp.v->pos,
- 0,
- bp.v->level - 1,
- 0);
- struct btree *b = bch2_btree_iter_peek_node(trans, iter);
- if (IS_ERR_OR_NULL(b))
- goto err;
-
- BUG_ON(b->c.level != bp.v->level - 1);
-
- if (extent_matches_bp(c, bp.v->btree_id, bp.v->level,
- bkey_i_to_s_c(&b->key), bp))
- return b;
-
- if (btree_node_will_make_reachable(b)) {
- b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
- } else {
- int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key), last_flushed);
- b = ret ? ERR_PTR(ret) : NULL;
- }
-err:
- bch2_trans_iter_exit(trans, iter);
- return b;
+struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans,
+ struct bkey_s_c_backpointer bp,
+ struct btree_iter *iter,
+ unsigned iter_flags,
+ struct bkey_buf *last_flushed)
+{
+ return __bch2_backpointer_get_key(trans, bp, iter, iter_flags, last_flushed, true);
}
static int bch2_check_backpointer_has_valid_bucket(struct btree_trans *trans, struct bkey_s_c k,
@@ -521,7 +562,7 @@ static int check_bp_exists(struct btree_trans *trans,
struct bkey_s_c_backpointer other_bp = bkey_s_c_to_backpointer(bp_k);
struct bkey_s_c other_extent =
- bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL);
+ __bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL, false);
ret = bkey_err(other_extent);
if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node)
ret = 0;
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index a3db328..d6e4a49 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -366,6 +366,10 @@ static inline void bkey_init(struct bkey *k)
#define __BKEY_PADDED(key, pad) \
struct bkey_i key; __u64 key ## _pad[pad]
+enum bch_bkey_type_flags {
+ BKEY_TYPE_strict_btree_checks = BIT(0),
+};
+
/*
* - DELETED keys are used internally to mark keys that should be ignored but
* override keys in composition order. Their version number is ignored.
@@ -383,46 +387,46 @@ static inline void bkey_init(struct bkey *k)
*
* - WHITEOUT: for hash table btrees
*/
-#define BCH_BKEY_TYPES() \
- x(deleted, 0) \
- x(whiteout, 1) \
- x(error, 2) \
- x(cookie, 3) \
- x(hash_whiteout, 4) \
- x(btree_ptr, 5) \
- x(extent, 6) \
- x(reservation, 7) \
- x(inode, 8) \
- x(inode_generation, 9) \
- x(dirent, 10) \
- x(xattr, 11) \
- x(alloc, 12) \
- x(quota, 13) \
- x(stripe, 14) \
- x(reflink_p, 15) \
- x(reflink_v, 16) \
- x(inline_data, 17) \
- x(btree_ptr_v2, 18) \
- x(indirect_inline_data, 19) \
- x(alloc_v2, 20) \
- x(subvolume, 21) \
- x(snapshot, 22) \
- x(inode_v2, 23) \
- x(alloc_v3, 24) \
- x(set, 25) \
- x(lru, 26) \
- x(alloc_v4, 27) \
- x(backpointer, 28) \
- x(inode_v3, 29) \
- x(bucket_gens, 30) \
- x(snapshot_tree, 31) \
- x(logged_op_truncate, 32) \
- x(logged_op_finsert, 33) \
- x(accounting, 34) \
- x(inode_alloc_cursor, 35)
+#define BCH_BKEY_TYPES() \
+ x(deleted, 0, 0) \
+ x(whiteout, 1, 0) \
+ x(error, 2, 0) \
+ x(cookie, 3, 0) \
+ x(hash_whiteout, 4, BKEY_TYPE_strict_btree_checks) \
+ x(btree_ptr, 5, BKEY_TYPE_strict_btree_checks) \
+ x(extent, 6, BKEY_TYPE_strict_btree_checks) \
+ x(reservation, 7, BKEY_TYPE_strict_btree_checks) \
+ x(inode, 8, BKEY_TYPE_strict_btree_checks) \
+ x(inode_generation, 9, BKEY_TYPE_strict_btree_checks) \
+ x(dirent, 10, BKEY_TYPE_strict_btree_checks) \
+ x(xattr, 11, BKEY_TYPE_strict_btree_checks) \
+ x(alloc, 12, BKEY_TYPE_strict_btree_checks) \
+ x(quota, 13, BKEY_TYPE_strict_btree_checks) \
+ x(stripe, 14, BKEY_TYPE_strict_btree_checks) \
+ x(reflink_p, 15, BKEY_TYPE_strict_btree_checks) \
+ x(reflink_v, 16, BKEY_TYPE_strict_btree_checks) \
+ x(inline_data, 17, BKEY_TYPE_strict_btree_checks) \
+ x(btree_ptr_v2, 18, BKEY_TYPE_strict_btree_checks) \
+ x(indirect_inline_data, 19, BKEY_TYPE_strict_btree_checks) \
+ x(alloc_v2, 20, BKEY_TYPE_strict_btree_checks) \
+ x(subvolume, 21, BKEY_TYPE_strict_btree_checks) \
+ x(snapshot, 22, BKEY_TYPE_strict_btree_checks) \
+ x(inode_v2, 23, BKEY_TYPE_strict_btree_checks) \
+ x(alloc_v3, 24, BKEY_TYPE_strict_btree_checks) \
+ x(set, 25, 0) \
+ x(lru, 26, BKEY_TYPE_strict_btree_checks) \
+ x(alloc_v4, 27, BKEY_TYPE_strict_btree_checks) \
+ x(backpointer, 28, BKEY_TYPE_strict_btree_checks) \
+ x(inode_v3, 29, BKEY_TYPE_strict_btree_checks) \
+ x(bucket_gens, 30, BKEY_TYPE_strict_btree_checks) \
+ x(snapshot_tree, 31, BKEY_TYPE_strict_btree_checks) \
+ x(logged_op_truncate, 32, BKEY_TYPE_strict_btree_checks) \
+ x(logged_op_finsert, 33, BKEY_TYPE_strict_btree_checks) \
+ x(accounting, 34, BKEY_TYPE_strict_btree_checks) \
+ x(inode_alloc_cursor, 35, BKEY_TYPE_strict_btree_checks)
enum bch_bkey_type {
-#define x(name, nr) KEY_TYPE_##name = nr,
+#define x(name, nr, ...) KEY_TYPE_##name = nr,
BCH_BKEY_TYPES()
#undef x
KEY_TYPE_MAX,
@@ -863,6 +867,7 @@ LE64_BITMASK(BCH_SB_VERSION_INCOMPAT_ALLOWED,
LE64_BITMASK(BCH_SB_SHARD_INUMS_NBITS, struct bch_sb, flags[6], 0, 4);
LE64_BITMASK(BCH_SB_WRITE_ERROR_TIMEOUT,struct bch_sb, flags[6], 4, 14);
LE64_BITMASK(BCH_SB_CSUM_ERR_RETRY_NR, struct bch_sb, flags[6], 14, 20);
+LE64_BITMASK(BCH_SB_CASEFOLD, struct bch_sb, flags[6], 22, 23);
static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb)
{
diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 15c9357..00d05cc 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -21,7 +21,7 @@
#include "xattr.h"
const char * const bch2_bkey_types[] = {
-#define x(name, nr) #name,
+#define x(name, nr, ...) #name,
BCH_BKEY_TYPES()
#undef x
NULL
@@ -115,7 +115,7 @@ static bool key_type_set_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_
})
const struct bkey_ops bch2_bkey_ops[] = {
-#define x(name, nr) [KEY_TYPE_##name] = bch2_bkey_ops_##name,
+#define x(name, nr, ...) [KEY_TYPE_##name] = bch2_bkey_ops_##name,
BCH_BKEY_TYPES()
#undef x
};
@@ -155,6 +155,12 @@ static u64 bch2_key_types_allowed[] = {
#undef x
};
+static const enum bch_bkey_type_flags bch2_bkey_type_flags[] = {
+#define x(name, nr, flags) [KEY_TYPE_##name] = flags,
+ BCH_BKEY_TYPES()
+#undef x
+};
+
const char *bch2_btree_node_type_str(enum btree_node_type type)
{
return type == BKEY_TYPE_btree ? "internal btree node" : bch2_btree_id_str(type - 1);
@@ -177,8 +183,18 @@ int __bch2_bkey_validate(struct bch_fs *c, struct bkey_s_c k,
if (type >= BKEY_TYPE_NR)
return 0;
- bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX &&
- (type == BKEY_TYPE_btree || (from.flags & BCH_VALIDATE_commit)) &&
+ enum bch_bkey_type_flags bkey_flags = k.k->type < KEY_TYPE_MAX
+ ? bch2_bkey_type_flags[k.k->type]
+ : 0;
+
+ bool strict_key_type_allowed =
+ (from.flags & BCH_VALIDATE_commit) ||
+ type == BKEY_TYPE_btree ||
+ (from.btree < BTREE_ID_NR &&
+ (bkey_flags & BKEY_TYPE_strict_btree_checks));
+
+ bkey_fsck_err_on(strict_key_type_allowed &&
+ k.k->type < KEY_TYPE_MAX &&
!(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)),
c, bkey_invalid_type_for_btree,
"invalid key type for btree %s (%s)",
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 9b80201..8998912 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -852,7 +852,6 @@ struct btree *bch2_btree_node_mem_alloc(struct btree_trans *trans, bool pcpu_rea
b->sib_u64s[1] = 0;
b->whiteout_u64s = 0;
bch2_btree_keys_init(b);
- set_btree_node_accessed(b);
bch2_time_stats_update(&c->times[BCH_TIME_btree_node_mem_alloc],
start_time);
@@ -1286,6 +1285,10 @@ struct btree *bch2_btree_node_get_noiter(struct btree_trans *trans,
six_unlock_read(&b->c.lock);
goto retry;
}
+
+ /* avoid atomic set bit if it's not needed: */
+ if (!btree_node_accessed(b))
+ set_btree_node_accessed(b);
}
/* XXX: waiting on IO with btree locks held: */
@@ -1301,10 +1304,6 @@ struct btree *bch2_btree_node_get_noiter(struct btree_trans *trans,
prefetch(p + L1_CACHE_BYTES * 2);
}
- /* avoid atomic set bit if it's not needed: */
- if (!btree_node_accessed(b))
- set_btree_node_accessed(b);
-
if (unlikely(btree_node_read_error(b))) {
six_unlock_read(&b->c.lock);
b = ERR_PTR(-BCH_ERR_btree_node_read_err_cached);
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 7b98ba2..37b69d8 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -47,6 +47,27 @@
#define DROP_PREV_NODE 11
#define DID_FILL_FROM_SCAN 12
+/*
+ * Returns true if it's a btree we can easily reconstruct, or otherwise won't
+ * cause data loss if it's missing:
+ */
+static bool btree_id_important(enum btree_id btree)
+{
+ if (btree_id_is_alloc(btree))
+ return false;
+
+ switch (btree) {
+ case BTREE_ID_quotas:
+ case BTREE_ID_snapshot_trees:
+ case BTREE_ID_logged_ops:
+ case BTREE_ID_rebalance_work:
+ case BTREE_ID_subvolume_children:
+ return false;
+ default:
+ return true;
+ }
+}
+
static const char * const bch2_gc_phase_strs[] = {
#define x(n) #n,
GC_PHASES()
@@ -534,8 +555,10 @@ int bch2_check_topology(struct bch_fs *c)
r->error = 0;
if (!bch2_btree_has_scanned_nodes(c, i)) {
- mustfix_fsck_err(trans, btree_root_unreadable_and_scan_found_nothing,
- "no nodes found for btree %s, continue?", buf.buf);
+ __fsck_err(trans,
+ FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+ btree_root_unreadable_and_scan_found_nothing,
+ "no nodes found for btree %s, continue?", buf.buf);
bch2_btree_root_alloc_fake_trans(trans, i, 0);
} else {
bch2_btree_root_alloc_fake_trans(trans, i, 1);
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 5fd4a58..60782f3 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -41,6 +41,7 @@ void bch2_btree_node_io_unlock(struct btree *b)
clear_btree_node_write_in_flight_inner(b);
clear_btree_node_write_in_flight(b);
+ smp_mb__after_atomic();
wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
}
@@ -1400,6 +1401,7 @@ static void btree_node_read_work(struct work_struct *work)
printbuf_exit(&buf);
clear_btree_node_read_in_flight(b);
+ smp_mb__after_atomic();
wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
}
@@ -1595,6 +1597,7 @@ static CLOSURE_CALLBACK(btree_node_read_all_replicas_done)
printbuf_exit(&buf);
clear_btree_node_read_in_flight(b);
+ smp_mb__after_atomic();
wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
}
@@ -1721,6 +1724,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
set_btree_node_read_error(b);
bch2_btree_lost_data(c, b->c.btree_id);
clear_btree_node_read_in_flight(b);
+ smp_mb__after_atomic();
wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
printbuf_exit(&buf);
return;
@@ -2061,8 +2065,10 @@ static void __btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start
if (new & (1U << BTREE_NODE_write_in_flight))
__bch2_btree_node_write(c, b, BTREE_WRITE_ALREADY_STARTED|type);
- else
+ else {
+ smp_mb__after_atomic();
wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
+ }
}
static void btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start_time)
@@ -2175,6 +2181,7 @@ static void btree_node_write_endio(struct bio *bio)
}
clear_btree_node_write_in_flight_inner(b);
+ smp_mb__after_atomic();
wake_up_bit(&b->flags, BTREE_NODE_write_in_flight_inner);
INIT_WORK(&wb->work, btree_node_write_work);
queue_work(c->btree_io_complete_wq, &wb->work);
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index e34e959..a873ec1 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -1971,6 +1971,12 @@ struct btree *bch2_btree_iter_next_node(struct btree_trans *trans, struct btree_
return NULL;
}
+ /*
+ * We don't correctly handle nodes with extra intent locks here:
+ * downgrade so we don't violate locking invariants
+ */
+ bch2_btree_path_downgrade(trans, path);
+
if (!bch2_btree_node_relock(trans, path, path->level + 1)) {
__bch2_btree_path_unlock(trans, path);
path->l[path->level].b = ERR_PTR(-BCH_ERR_no_btree_node_relock);
@@ -2577,7 +2583,10 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_trans *trans, struct
struct bpos end)
{
if ((iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots)) &&
- !bkey_eq(iter->pos, POS_MAX)) {
+ !bkey_eq(iter->pos, POS_MAX) &&
+ !((iter->flags & BTREE_ITER_is_extents) &&
+ iter->pos.offset == U64_MAX)) {
+
/*
* bkey_start_pos(), for extents, is not monotonically
* increasing until after filtering for snapshots:
@@ -2602,7 +2611,7 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_trans *trans, struct
bch2_trans_verify_not_unlocked_or_in_restart(trans);
bch2_btree_iter_verify_entry_exit(iter);
- EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN));
+ EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && iter->pos.inode != end.inode);
int ret = trans_maybe_inject_restart(trans, _RET_IP_);
if (unlikely(ret)) {
@@ -2740,7 +2749,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
ret = trans_maybe_inject_restart(trans, _RET_IP_);
if (unlikely(ret)) {
k = bkey_s_c_err(ret);
- goto out_no_locked;
+ goto out;
}
/* extents can't span inode numbers: */
@@ -2760,13 +2769,15 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
ret = bch2_btree_path_traverse(trans, iter->path, iter->flags);
if (unlikely(ret)) {
k = bkey_s_c_err(ret);
- goto out_no_locked;
+ goto out;
}
struct btree_path *path = btree_iter_path(trans, iter);
if (unlikely(!btree_path_node(path, path->level)))
return bkey_s_c_null;
+ btree_path_set_should_be_locked(trans, path);
+
if ((iter->flags & BTREE_ITER_cached) ||
!(iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots))) {
k = bkey_s_c_null;
@@ -2787,12 +2798,12 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
if (!bkey_err(k))
iter->k = *k.k;
/* We're not returning a key from iter->path: */
- goto out_no_locked;
+ goto out;
}
- k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k);
+ k = bch2_btree_path_peek_slot(btree_iter_path(trans, iter), &iter->k);
if (unlikely(!k.k))
- goto out_no_locked;
+ goto out;
if (unlikely(k.k->type == KEY_TYPE_whiteout &&
(iter->flags & BTREE_ITER_filter_snapshots) &&
@@ -2830,7 +2841,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
}
if (unlikely(bkey_err(k)))
- goto out_no_locked;
+ goto out;
next = k.k ? bkey_start_pos(k.k) : POS_MAX;
@@ -2852,8 +2863,6 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
}
}
out:
- btree_path_set_should_be_locked(trans, btree_iter_path(trans, iter));
-out_no_locked:
bch2_btree_iter_verify_entry_exit(iter);
bch2_btree_iter_verify(trans, iter);
ret = bch2_btree_iter_verify_ret(trans, iter, k);
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index 7d6c971..ade3b5a 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -288,7 +288,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
.size = max_t(size_t, keys->size, 8) * 2,
};
- new_keys.data = kvmalloc_array(new_keys.size, sizeof(new_keys.data[0]), GFP_KERNEL);
+ new_keys.data = bch2_kvmalloc(new_keys.size * sizeof(new_keys.data[0]), GFP_KERNEL);
if (!new_keys.data) {
bch_err(c, "%s: error allocating new key array (size %zu)",
__func__, new_keys.size);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 44b5fe4..0030735 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1389,7 +1389,7 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as,
printbuf_exit(&buf);
}
-static void
+static int
bch2_btree_insert_keys_interior(struct btree_update *as,
struct btree_trans *trans,
struct btree_path *path,
@@ -1411,7 +1411,8 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
insert = bkey_next(insert))
bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert);
- if (bch2_btree_node_check_topology(trans, b)) {
+ int ret = bch2_btree_node_check_topology(trans, b);
+ if (ret) {
struct printbuf buf = PRINTBUF;
for (struct bkey_i *k = keys->keys;
@@ -1421,11 +1422,15 @@ bch2_btree_insert_keys_interior(struct btree_update *as,
prt_newline(&buf);
}
- panic("%s(): check_topology error: inserted keys\n%s", __func__, buf.buf);
+ bch2_fs_fatal_error(as->c, "%ps -> %s(): check_topology error %s: inserted keys\n%s",
+ (void *) _RET_IP_, __func__, bch2_err_str(ret), buf.buf);
+ dump_stack();
+ return ret;
}
memmove_u64s_down(keys->keys, insert, keys->top_p - insert->_data);
keys->top_p -= insert->_data - keys->keys_p;
+ return 0;
}
static bool key_deleted_in_insert(struct keylist *insert_keys, struct bpos pos)
@@ -1559,11 +1564,11 @@ static void __btree_split_node(struct btree_update *as,
* nodes that were coalesced, and thus in the middle of a child node post
* coalescing:
*/
-static void btree_split_insert_keys(struct btree_update *as,
- struct btree_trans *trans,
- btree_path_idx_t path_idx,
- struct btree *b,
- struct keylist *keys)
+static int btree_split_insert_keys(struct btree_update *as,
+ struct btree_trans *trans,
+ btree_path_idx_t path_idx,
+ struct btree *b,
+ struct keylist *keys)
{
struct btree_path *path = trans->paths + path_idx;
@@ -1573,8 +1578,12 @@ static void btree_split_insert_keys(struct btree_update *as,
bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p);
- bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
+ int ret = bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
+ if (ret)
+ return ret;
}
+
+ return 0;
}
static int btree_split(struct btree_update *as, struct btree_trans *trans,
@@ -1607,8 +1616,10 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
__btree_split_node(as, trans, b, n, keys);
if (keys) {
- btree_split_insert_keys(as, trans, path, n1, keys);
- btree_split_insert_keys(as, trans, path, n2, keys);
+ ret = btree_split_insert_keys(as, trans, path, n1, keys) ?:
+ btree_split_insert_keys(as, trans, path, n2, keys);
+ if (ret)
+ goto err;
BUG_ON(!bch2_keylist_empty(keys));
}
@@ -1654,7 +1665,9 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
n3->sib_u64s[0] = U16_MAX;
n3->sib_u64s[1] = U16_MAX;
- btree_split_insert_keys(as, trans, path, n3, &as->parent_keys);
+ ret = btree_split_insert_keys(as, trans, path, n3, &as->parent_keys);
+ if (ret)
+ goto err;
}
} else {
trace_and_count(c, btree_node_compact, trans, b);
@@ -1662,7 +1675,9 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans,
n1 = bch2_btree_node_alloc_replacement(as, trans, b);
if (keys) {
- btree_split_insert_keys(as, trans, path, n1, keys);
+ ret = btree_split_insert_keys(as, trans, path, n1, keys);
+ if (ret)
+ goto err;
BUG_ON(!bch2_keylist_empty(keys));
}
@@ -1809,15 +1824,15 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
goto split;
}
- ret = bch2_btree_node_check_topology(trans, b);
+
+ ret = bch2_btree_node_check_topology(trans, b) ?:
+ bch2_btree_insert_keys_interior(as, trans, path, b,
+ path->l[b->c.level].iter, keys);
if (ret) {
bch2_btree_node_unlock_write(trans, path, b);
return ret;
}
- bch2_btree_insert_keys_interior(as, trans, path, b,
- path->l[b->c.level].iter, keys);
-
trans_for_each_path_with_node(trans, b, linked, i)
bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 4ef261e..31fbc27 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -604,6 +604,13 @@ static int bch2_trigger_pointer(struct btree_trans *trans,
}
struct bpos bucket = PTR_BUCKET_POS(ca, &p.ptr);
+ if (!bucket_valid(ca, bucket.offset)) {
+ if (insert) {
+ bch2_dev_bucket_missing(ca, bucket.offset);
+ ret = -BCH_ERR_trigger_pointer;
+ }
+ goto err;
+ }
if (flags & BTREE_TRIGGER_transactional) {
struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update(trans, bucket, 0);
@@ -1307,13 +1314,11 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
old_bucket_gens = rcu_dereference_protected(ca->bucket_gens, 1);
if (resize) {
- bucket_gens->nbuckets = min(bucket_gens->nbuckets,
- old_bucket_gens->nbuckets);
- bucket_gens->nbuckets_minus_first =
- bucket_gens->nbuckets - bucket_gens->first_bucket;
+ u64 copy = min(bucket_gens->nbuckets,
+ old_bucket_gens->nbuckets);
memcpy(bucket_gens->b,
old_bucket_gens->b,
- bucket_gens->nbuckets);
+ sizeof(bucket_gens->b[0]) * copy);
}
rcu_assign_pointer(ca->bucket_gens, bucket_gens);
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 8d75b27..af1532d 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -44,6 +44,7 @@ static inline void bucket_unlock(struct bucket *b)
BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock);
+ smp_mb__after_atomic();
wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR);
}
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index 8488a75..8a680e5 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -13,8 +13,8 @@
#include <linux/dcache.h>
-static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
- const struct qstr *str, struct qstr *out_cf)
+int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
+ const struct qstr *str, struct qstr *out_cf)
{
*out_cf = (struct qstr) QSTR_INIT(NULL, 0);
@@ -35,18 +35,6 @@ static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *
#endif
}
-static inline int bch2_maybe_casefold(struct btree_trans *trans,
- const struct bch_hash_info *info,
- const struct qstr *str, struct qstr *out_cf)
-{
- if (likely(!info->cf_encoding)) {
- *out_cf = *str;
- return 0;
- } else {
- return bch2_casefold(trans, info, str, out_cf);
- }
-}
-
static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d)
{
if (bkey_val_bytes(d.k) < offsetof(struct bch_dirent, d_name))
@@ -697,7 +685,7 @@ static int bch2_dir_emit(struct dir_context *ctx, struct bkey_s_c_dirent d, subv
vfs_d_type(d.v->d_type));
if (ret)
ctx->pos = d.k->p.offset + 1;
- return ret;
+ return !ret;
}
int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
@@ -722,7 +710,7 @@ int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
if (ret2 > 0)
continue;
- ret2 ?: drop_locks_do(trans, bch2_dir_emit(ctx, dirent, target));
+ ret2 ?: (bch2_trans_unlock(trans), bch2_dir_emit(ctx, dirent, target));
})));
bch2_bkey_buf_exit(&sk, c);
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index 0880772..9838a7b 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -23,6 +23,21 @@ struct bch_fs;
struct bch_hash_info;
struct bch_inode_info;
+int bch2_casefold(struct btree_trans *, const struct bch_hash_info *,
+ const struct qstr *, struct qstr *);
+
+static inline int bch2_maybe_casefold(struct btree_trans *trans,
+ const struct bch_hash_info *info,
+ const struct qstr *str, struct qstr *out_cf)
+{
+ if (likely(!info->cf_encoding)) {
+ *out_cf = *str;
+ return 0;
+ } else {
+ return bch2_casefold(trans, info, str, out_cf);
+ }
+}
+
struct qstr bch2_dirent_get_name(struct bkey_s_c_dirent d);
static inline unsigned dirent_val_u64s(unsigned len, unsigned cf_len)
diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index b007319..1f0422b 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -376,6 +376,19 @@ int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a,
return ret;
}
+int bch2_accounting_mem_insert_locked(struct bch_fs *c, struct bkey_s_c_accounting a,
+ enum bch_accounting_mode mode)
+{
+ struct bch_replicas_padded r;
+
+ if (mode != BCH_ACCOUNTING_read &&
+ accounting_to_replicas(&r.e, a.k->p) &&
+ !bch2_replicas_marked_locked(c, &r.e))
+ return -BCH_ERR_btree_insert_need_mark_replicas;
+
+ return __bch2_accounting_mem_insert(c, a);
+}
+
static bool accounting_mem_entry_is_zero(struct accounting_mem_entry *e)
{
for (unsigned i = 0; i < e->nr_counters; i++)
@@ -583,7 +596,7 @@ int bch2_gc_accounting_done(struct bch_fs *c)
accounting_key_init(&k_i.k, &acc_k, src_v, nr);
bch2_accounting_mem_mod_locked(trans,
bkey_i_to_s_c_accounting(&k_i.k),
- BCH_ACCOUNTING_normal);
+ BCH_ACCOUNTING_normal, true);
preempt_disable();
struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage);
@@ -612,7 +625,7 @@ static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k)
percpu_down_read(&c->mark_lock);
int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k),
- BCH_ACCOUNTING_read);
+ BCH_ACCOUNTING_read, false);
percpu_up_read(&c->mark_lock);
return ret;
}
diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h
index abb1f62..d557b99 100644
--- a/fs/bcachefs/disk_accounting.h
+++ b/fs/bcachefs/disk_accounting.h
@@ -136,6 +136,7 @@ enum bch_accounting_mode {
};
int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode);
+int bch2_accounting_mem_insert_locked(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode);
void bch2_accounting_mem_gc(struct bch_fs *);
static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc)
@@ -150,7 +151,8 @@ static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc)
*/
static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
struct bkey_s_c_accounting a,
- enum bch_accounting_mode mode)
+ enum bch_accounting_mode mode,
+ bool write_locked)
{
struct bch_fs *c = trans->c;
struct bch_accounting_mem *acc = &c->accounting;
@@ -189,7 +191,11 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
while ((idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]),
accounting_pos_cmp, &a.k->p)) >= acc->k.nr) {
- int ret = bch2_accounting_mem_insert(c, a, mode);
+ int ret = 0;
+ if (unlikely(write_locked))
+ ret = bch2_accounting_mem_insert_locked(c, a, mode);
+ else
+ ret = bch2_accounting_mem_insert(c, a, mode);
if (ret)
return ret;
}
@@ -206,7 +212,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc)
{
percpu_down_read(&trans->c->mark_lock);
- int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal);
+ int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal, false);
percpu_up_read(&trans->c->mark_lock);
return ret;
}
@@ -259,7 +265,7 @@ static inline int bch2_accounting_trans_commit_hook(struct btree_trans *trans,
EBUG_ON(bversion_zero(a->k.bversion));
return likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply))
- ? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal)
+ ? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal, false)
: 0;
}
@@ -271,7 +277,7 @@ static inline void bch2_accounting_trans_commit_revert(struct btree_trans *trans
struct bkey_s_accounting a = accounting_i_to_s(a_i);
bch2_accounting_neg(a);
- bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal);
+ bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal, false);
bch2_accounting_neg(a);
}
}
diff --git a/fs/bcachefs/disk_groups.c b/fs/bcachefs/disk_groups.c
index 1186280..2ca3cbf 100644
--- a/fs/bcachefs/disk_groups.c
+++ b/fs/bcachefs/disk_groups.c
@@ -470,23 +470,22 @@ void bch2_disk_path_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned
int __bch2_dev_group_set(struct bch_fs *c, struct bch_dev *ca, const char *name)
{
- struct bch_member *mi;
- int ret, v = -1;
+ lockdep_assert_held(&c->sb_lock);
- if (!strlen(name) || !strcmp(name, "none"))
- return 0;
- v = bch2_disk_path_find_or_create(&c->disk_sb, name);
- if (v < 0)
- return v;
+ if (!strlen(name) || !strcmp(name, "none")) {
+ struct bch_member *mi = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
+ SET_BCH_MEMBER_GROUP(mi, 0);
+ } else {
+ int v = bch2_disk_path_find_or_create(&c->disk_sb, name);
+ if (v < 0)
+ return v;
- ret = bch2_sb_disk_groups_to_cpu(c);
- if (ret)
- return ret;
+ struct bch_member *mi = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
+ SET_BCH_MEMBER_GROUP(mi, v + 1);
+ }
- mi = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
- SET_BCH_MEMBER_GROUP(mi, v + 1);
- return 0;
+ return bch2_sb_disk_groups_to_cpu(c);
}
int bch2_dev_group_set(struct bch_fs *c, struct bch_dev *ca, const char *name)
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index a396865..fff58b7 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -2204,10 +2204,10 @@ void bch2_fs_ec_stop(struct bch_fs *c)
static bool bch2_fs_ec_flush_done(struct bch_fs *c)
{
- bool ret;
+ sched_annotate_sleep();
mutex_lock(&c->ec_stripe_new_lock);
- ret = list_empty(&c->ec_stripe_new_list);
+ bool ret = list_empty(&c->ec_stripe_new_list);
mutex_unlock(&c->ec_stripe_new_lock);
return ret;
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index 62d27e0..51893e1 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -160,6 +160,7 @@ static inline void gc_stripe_unlock(struct gc_stripe *s)
BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &s->lock);
+ smp_mb__after_atomic();
wake_up_bit((void *) &s->lock, BUCKET_LOCK_BITNR);
}
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index a615e48..d9ebffa 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -269,7 +269,7 @@
x(BCH_ERR_invalid_sb, invalid_sb_downgrade) \
x(BCH_ERR_invalid, invalid_bkey) \
x(BCH_ERR_operation_blocked, nocow_lock_blocked) \
- x(EIO, journal_shutdown) \
+ x(EROFS, journal_shutdown) \
x(EIO, journal_flush_err) \
x(EIO, journal_write_err) \
x(EIO, btree_node_read_err) \
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index baf5dfb..6b8695b 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -272,9 +272,6 @@ static struct fsck_err_state *fsck_err_get(struct bch_fs *c,
{
struct fsck_err_state *s;
- if (!test_bit(BCH_FS_fsck_running, &c->flags))
- return NULL;
-
list_for_each_entry(s, &c->fsck_error_msgs, list)
if (s->id == id) {
/*
@@ -481,7 +478,9 @@ int __bch2_fsck_err(struct bch_fs *c,
} else if (!test_bit(BCH_FS_fsck_running, &c->flags)) {
if (c->opts.errors != BCH_ON_ERROR_continue ||
!(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) {
- prt_str(out, ", shutting down");
+ prt_str_indented(out, ", shutting down\n"
+ "error not marked as autofix and not in fsck\n"
+ "run fsck, and forward to devs so error can be marked for self-healing");
inconsistent = true;
print = true;
ret = -BCH_ERR_fsck_errors_not_fixed;
@@ -639,14 +638,14 @@ int __bch2_bkey_fsck_err(struct bch_fs *c,
return ret;
}
-void bch2_flush_fsck_errs(struct bch_fs *c)
+static void __bch2_flush_fsck_errs(struct bch_fs *c, bool print)
{
struct fsck_err_state *s, *n;
mutex_lock(&c->fsck_error_msgs_lock);
list_for_each_entry_safe(s, n, &c->fsck_error_msgs, list) {
- if (s->ratelimited && s->last_msg)
+ if (print && s->ratelimited && s->last_msg)
bch_err(c, "Saw %llu errors like:\n %s", s->nr, s->last_msg);
list_del(&s->list);
@@ -657,6 +656,16 @@ void bch2_flush_fsck_errs(struct bch_fs *c)
mutex_unlock(&c->fsck_error_msgs_lock);
}
+void bch2_flush_fsck_errs(struct bch_fs *c)
+{
+ __bch2_flush_fsck_errs(c, true);
+}
+
+void bch2_free_fsck_errs(struct bch_fs *c)
+{
+ __bch2_flush_fsck_errs(c, false);
+}
+
int bch2_inum_offset_err_msg_trans(struct btree_trans *trans, struct printbuf *out,
subvol_inum inum, u64 offset)
{
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index d0d024d..4a364fd 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -93,6 +93,7 @@ int __bch2_fsck_err(struct bch_fs *, struct btree_trans *,
_flags, BCH_FSCK_ERR_##_err_type, __VA_ARGS__)
void bch2_flush_fsck_errs(struct bch_fs *);
+void bch2_free_fsck_errs(struct bch_fs *);
#define fsck_err_wrap(_do) \
({ \
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index dca2b84..e597fb9 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -1056,8 +1056,9 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke
static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts,
struct bch_extent_ptr *ptr)
{
- if (!opts->promote_target ||
- !bch2_dev_in_target(c, ptr->dev, opts->promote_target))
+ unsigned target = opts->promote_target ?: opts->foreground_target;
+
+ if (target && !bch2_dev_in_target(c, ptr->dev, target))
return false;
struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev);
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 65c2c33..9657144 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -144,10 +144,25 @@ int __must_check bch2_write_inode_size(struct bch_fs *c,
void __bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode,
struct quota_res *quota_res, s64 sectors)
{
- bch2_fs_inconsistent_on((s64) inode->v.i_blocks + sectors < 0, c,
- "inode %lu i_blocks underflow: %llu + %lli < 0 (ondisk %lli)",
- inode->v.i_ino, (u64) inode->v.i_blocks, sectors,
- inode->ei_inode.bi_sectors);
+ if (unlikely((s64) inode->v.i_blocks + sectors < 0)) {
+ struct printbuf buf = PRINTBUF;
+ bch2_log_msg_start(c, &buf);
+ prt_printf(&buf, "inode %lu i_blocks underflow: %llu + %lli < 0 (ondisk %lli)",
+ inode->v.i_ino, (u64) inode->v.i_blocks, sectors,
+ inode->ei_inode.bi_sectors);
+
+ bool repeat = false, print = false, suppress = false;
+ bch2_count_fsck_err(c, vfs_inode_i_blocks_underflow, buf.buf, &repeat, &print, &suppress);
+ if (print)
+ bch2_print_str(c, buf.buf);
+ printbuf_exit(&buf);
+
+ if (sectors < 0)
+ sectors = -inode->v.i_blocks;
+ else
+ sectors = 0;
+ }
+
inode->v.i_blocks += sectors;
#ifdef CONFIG_BCACHEFS_QUOTA
@@ -502,11 +517,22 @@ int bchfs_truncate(struct mnt_idmap *idmap,
goto err;
}
- bch2_fs_inconsistent_on(!inode->v.i_size && inode->v.i_blocks &&
- !bch2_journal_error(&c->journal), c,
- "inode %lu truncated to 0 but i_blocks %llu (ondisk %lli)",
- inode->v.i_ino, (u64) inode->v.i_blocks,
- inode->ei_inode.bi_sectors);
+ if (unlikely(!inode->v.i_size && inode->v.i_blocks &&
+ !bch2_journal_error(&c->journal))) {
+ struct printbuf buf = PRINTBUF;
+ bch2_log_msg_start(c, &buf);
+ prt_printf(&buf,
+ "inode %lu truncated to 0 but i_blocks %llu (ondisk %lli)",
+ inode->v.i_ino, (u64) inode->v.i_blocks,
+ inode->ei_inode.bi_sectors);
+
+ bool repeat = false, print = false, suppress = false;
+ bch2_count_fsck_err(c, vfs_inode_i_blocks_not_zero_at_truncate, buf.buf,
+ &repeat, &print, &suppress);
+ if (print)
+ bch2_print_str(c, buf.buf);
+ printbuf_exit(&buf);
+ }
ret = bch2_setattr_nonsize(idmap, inode, iattr);
err:
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 14886e1d..a82dfce 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -21,206 +21,6 @@
#define FSOP_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */
#define FSOP_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */
-struct flags_set {
- unsigned mask;
- unsigned flags;
-
- unsigned projid;
-
- bool set_projinherit;
- bool projinherit;
-};
-
-static int bch2_inode_flags_set(struct btree_trans *trans,
- struct bch_inode_info *inode,
- struct bch_inode_unpacked *bi,
- void *p)
-{
- struct bch_fs *c = inode->v.i_sb->s_fs_info;
- /*
- * We're relying on btree locking here for exclusion with other ioctl
- * calls - use the flags in the btree (@bi), not inode->i_flags:
- */
- struct flags_set *s = p;
- unsigned newflags = s->flags;
- unsigned oldflags = bi->bi_flags & s->mask;
-
- if (((newflags ^ oldflags) & (BCH_INODE_append|BCH_INODE_immutable)) &&
- !capable(CAP_LINUX_IMMUTABLE))
- return -EPERM;
-
- if (!S_ISREG(bi->bi_mode) &&
- !S_ISDIR(bi->bi_mode) &&
- (newflags & (BCH_INODE_nodump|BCH_INODE_noatime)) != newflags)
- return -EINVAL;
-
- if ((newflags ^ oldflags) & BCH_INODE_casefolded) {
-#ifdef CONFIG_UNICODE
- int ret = 0;
- /* Not supported on individual files. */
- if (!S_ISDIR(bi->bi_mode))
- return -EOPNOTSUPP;
-
- /*
- * Make sure the dir is empty, as otherwise we'd need to
- * rehash everything and update the dirent keys.
- */
- ret = bch2_empty_dir_trans(trans, inode_inum(inode));
- if (ret < 0)
- return ret;
-
- ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding);
- if (ret)
- return ret;
-
- bch2_check_set_feature(c, BCH_FEATURE_casefolding);
-#else
- printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
- return -EOPNOTSUPP;
-#endif
- }
-
- if (s->set_projinherit) {
- bi->bi_fields_set &= ~(1 << Inode_opt_project);
- bi->bi_fields_set |= ((int) s->projinherit << Inode_opt_project);
- }
-
- bi->bi_flags &= ~s->mask;
- bi->bi_flags |= newflags;
-
- bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
- return 0;
-}
-
-static int bch2_ioc_getflags(struct bch_inode_info *inode, int __user *arg)
-{
- unsigned flags = map_flags(bch_flags_to_uflags, inode->ei_inode.bi_flags);
-
- return put_user(flags, arg);
-}
-
-static int bch2_ioc_setflags(struct bch_fs *c,
- struct file *file,
- struct bch_inode_info *inode,
- void __user *arg)
-{
- struct flags_set s = { .mask = map_defined(bch_flags_to_uflags) };
- unsigned uflags;
- int ret;
-
- if (get_user(uflags, (int __user *) arg))
- return -EFAULT;
-
- s.flags = map_flags_rev(bch_flags_to_uflags, uflags);
- if (uflags)
- return -EOPNOTSUPP;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- inode_lock(&inode->v);
- if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
- ret = -EACCES;
- goto setflags_out;
- }
-
- mutex_lock(&inode->ei_update_lock);
- ret = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
- bch2_write_inode(c, inode, bch2_inode_flags_set, &s,
- ATTR_CTIME);
- mutex_unlock(&inode->ei_update_lock);
-
-setflags_out:
- inode_unlock(&inode->v);
- mnt_drop_write_file(file);
- return ret;
-}
-
-static int bch2_ioc_fsgetxattr(struct bch_inode_info *inode,
- struct fsxattr __user *arg)
-{
- struct fsxattr fa = { 0 };
-
- fa.fsx_xflags = map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags);
-
- if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
- fa.fsx_xflags |= FS_XFLAG_PROJINHERIT;
-
- fa.fsx_projid = inode->ei_qid.q[QTYP_PRJ];
-
- if (copy_to_user(arg, &fa, sizeof(fa)))
- return -EFAULT;
-
- return 0;
-}
-
-static int fssetxattr_inode_update_fn(struct btree_trans *trans,
- struct bch_inode_info *inode,
- struct bch_inode_unpacked *bi,
- void *p)
-{
- struct flags_set *s = p;
-
- if (s->projid != bi->bi_project) {
- bi->bi_fields_set |= 1U << Inode_opt_project;
- bi->bi_project = s->projid;
- }
-
- return bch2_inode_flags_set(trans, inode, bi, p);
-}
-
-static int bch2_ioc_fssetxattr(struct bch_fs *c,
- struct file *file,
- struct bch_inode_info *inode,
- struct fsxattr __user *arg)
-{
- struct flags_set s = { .mask = map_defined(bch_flags_to_xflags) };
- struct fsxattr fa;
- int ret;
-
- if (copy_from_user(&fa, arg, sizeof(fa)))
- return -EFAULT;
-
- s.set_projinherit = true;
- s.projinherit = (fa.fsx_xflags & FS_XFLAG_PROJINHERIT) != 0;
- fa.fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
-
- s.flags = map_flags_rev(bch_flags_to_xflags, fa.fsx_xflags);
- if (fa.fsx_xflags)
- return -EOPNOTSUPP;
-
- if (fa.fsx_projid >= U32_MAX)
- return -EINVAL;
-
- /*
- * inode fields accessible via the xattr interface are stored with a +1
- * bias, so that 0 means unset:
- */
- s.projid = fa.fsx_projid + 1;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- inode_lock(&inode->v);
- if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
- ret = -EACCES;
- goto err;
- }
-
- mutex_lock(&inode->ei_update_lock);
- ret = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
- bch2_set_projid(c, inode, fa.fsx_projid) ?:
- bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
- ATTR_CTIME);
- mutex_unlock(&inode->ei_update_lock);
-err:
- inode_unlock(&inode->v);
- mnt_drop_write_file(file);
- return ret;
-}
-
static int bch2_reinherit_attrs_fn(struct btree_trans *trans,
struct bch_inode_info *inode,
struct bch_inode_unpacked *bi,
@@ -558,23 +358,6 @@ long bch2_fs_file_ioctl(struct file *file, unsigned cmd, unsigned long arg)
long ret;
switch (cmd) {
- case FS_IOC_GETFLAGS:
- ret = bch2_ioc_getflags(inode, (int __user *) arg);
- break;
-
- case FS_IOC_SETFLAGS:
- ret = bch2_ioc_setflags(c, file, inode, (int __user *) arg);
- break;
-
- case FS_IOC_FSGETXATTR:
- ret = bch2_ioc_fsgetxattr(inode, (void __user *) arg);
- break;
-
- case FS_IOC_FSSETXATTR:
- ret = bch2_ioc_fssetxattr(c, file, inode,
- (void __user *) arg);
- break;
-
case BCHFS_IOC_REINHERIT_ATTRS:
ret = bch2_ioc_reinherit_attrs(c, file, inode,
(void __user *) arg);
diff --git a/fs/bcachefs/fs-ioctl.h b/fs/bcachefs/fs-ioctl.h
index ecd3bfd..a657e49 100644
--- a/fs/bcachefs/fs-ioctl.h
+++ b/fs/bcachefs/fs-ioctl.h
@@ -2,81 +2,6 @@
#ifndef _BCACHEFS_FS_IOCTL_H
#define _BCACHEFS_FS_IOCTL_H
-/* Inode flags: */
-
-/* bcachefs inode flags -> vfs inode flags: */
-static const __maybe_unused unsigned bch_flags_to_vfs[] = {
- [__BCH_INODE_sync] = S_SYNC,
- [__BCH_INODE_immutable] = S_IMMUTABLE,
- [__BCH_INODE_append] = S_APPEND,
- [__BCH_INODE_noatime] = S_NOATIME,
- [__BCH_INODE_casefolded] = S_CASEFOLD,
-};
-
-/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
-static const __maybe_unused unsigned bch_flags_to_uflags[] = {
- [__BCH_INODE_sync] = FS_SYNC_FL,
- [__BCH_INODE_immutable] = FS_IMMUTABLE_FL,
- [__BCH_INODE_append] = FS_APPEND_FL,
- [__BCH_INODE_nodump] = FS_NODUMP_FL,
- [__BCH_INODE_noatime] = FS_NOATIME_FL,
- [__BCH_INODE_casefolded] = FS_CASEFOLD_FL,
-};
-
-/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
-static const __maybe_unused unsigned bch_flags_to_xflags[] = {
- [__BCH_INODE_sync] = FS_XFLAG_SYNC,
- [__BCH_INODE_immutable] = FS_XFLAG_IMMUTABLE,
- [__BCH_INODE_append] = FS_XFLAG_APPEND,
- [__BCH_INODE_nodump] = FS_XFLAG_NODUMP,
- [__BCH_INODE_noatime] = FS_XFLAG_NOATIME,
- //[__BCH_INODE_PROJINHERIT] = FS_XFLAG_PROJINHERIT;
-};
-
-#define set_flags(_map, _in, _out) \
-do { \
- unsigned _i; \
- \
- for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
- if ((_in) & (1 << _i)) \
- (_out) |= _map[_i]; \
- else \
- (_out) &= ~_map[_i]; \
-} while (0)
-
-#define map_flags(_map, _in) \
-({ \
- unsigned _out = 0; \
- \
- set_flags(_map, _in, _out); \
- _out; \
-})
-
-#define map_flags_rev(_map, _in) \
-({ \
- unsigned _i, _out = 0; \
- \
- for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
- if ((_in) & _map[_i]) { \
- (_out) |= 1 << _i; \
- (_in) &= ~_map[_i]; \
- } \
- (_out); \
-})
-
-#define map_defined(_map) \
-({ \
- unsigned _in = ~0; \
- \
- map_flags_rev(_map, _in); \
-})
-
-/* Set VFS inode flags from bcachefs inode: */
-static inline void bch2_inode_flags_to_vfs(struct bch_inode_info *inode)
-{
- set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
-}
-
long bch2_fs_file_ioctl(struct file *, unsigned, unsigned long);
long bch2_compat_fs_ioctl(struct file *, unsigned, unsigned long);
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 5a41b1a..4b742e6 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -33,6 +33,7 @@
#include <linux/backing-dev.h>
#include <linux/exportfs.h>
#include <linux/fiemap.h>
+#include <linux/fileattr.h>
#include <linux/fs_context.h>
#include <linux/module.h>
#include <linux/pagemap.h>
@@ -51,6 +52,24 @@ static void bch2_vfs_inode_init(struct btree_trans *, subvol_inum,
struct bch_inode_unpacked *,
struct bch_subvolume *);
+/* Set VFS inode flags from bcachefs inode: */
+static inline void bch2_inode_flags_to_vfs(struct bch_fs *c, struct bch_inode_info *inode)
+{
+ static const __maybe_unused unsigned bch_flags_to_vfs[] = {
+ [__BCH_INODE_sync] = S_SYNC,
+ [__BCH_INODE_immutable] = S_IMMUTABLE,
+ [__BCH_INODE_append] = S_APPEND,
+ [__BCH_INODE_noatime] = S_NOATIME,
+ };
+
+ set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
+
+ if (bch2_inode_casefold(c, &inode->ei_inode))
+ inode->v.i_flags |= S_CASEFOLD;
+ else
+ inode->v.i_flags &= ~S_CASEFOLD;
+}
+
void bch2_inode_update_after_write(struct btree_trans *trans,
struct bch_inode_info *inode,
struct bch_inode_unpacked *bi,
@@ -79,7 +98,7 @@ void bch2_inode_update_after_write(struct btree_trans *trans,
inode->ei_inode = *bi;
- bch2_inode_flags_to_vfs(inode);
+ bch2_inode_flags_to_vfs(c, inode);
}
int __must_check bch2_write_inode(struct bch_fs *c,
@@ -631,13 +650,18 @@ static struct bch_inode_info *bch2_lookup_trans(struct btree_trans *trans,
const struct qstr *name)
{
struct bch_fs *c = trans->c;
- struct btree_iter dirent_iter = {};
subvol_inum inum = {};
struct printbuf buf = PRINTBUF;
+ struct qstr lookup_name;
+ int ret = bch2_maybe_casefold(trans, dir_hash_info, name, &lookup_name);
+ if (ret)
+ return ERR_PTR(ret);
+
+ struct btree_iter dirent_iter = {};
struct bkey_s_c k = bch2_hash_lookup(trans, &dirent_iter, bch2_dirent_hash_desc,
- dir_hash_info, dir, name, 0);
- int ret = bkey_err(k);
+ dir_hash_info, dir, &lookup_name, 0);
+ ret = bkey_err(k);
if (ret)
return ERR_PTR(ret);
@@ -825,6 +849,9 @@ int __bch2_unlink(struct inode *vdir, struct dentry *dentry,
*/
set_nlink(&inode->v, 0);
}
+
+ if (IS_CASEFOLDED(vdir))
+ d_invalidate(dentry);
err:
bch2_trans_put(trans);
bch2_unlock_inodes(INODE_UPDATE_LOCK, dir, inode);
@@ -1235,10 +1262,20 @@ static int bch2_tmpfile(struct mnt_idmap *idmap,
return finish_open_simple(file, 0);
}
+struct bch_fiemap_extent {
+ struct bkey_buf kbuf;
+ unsigned flags;
+};
+
static int bch2_fill_extent(struct bch_fs *c,
struct fiemap_extent_info *info,
- struct bkey_s_c k, unsigned flags)
+ struct bch_fiemap_extent *fe)
{
+ struct bkey_s_c k = bkey_i_to_s_c(fe->kbuf.k);
+ unsigned flags = fe->flags;
+
+ BUG_ON(!k.k->size);
+
if (bkey_extent_is_direct_data(k.k)) {
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
const union bch_extent_entry *entry;
@@ -1291,110 +1328,225 @@ static int bch2_fill_extent(struct bch_fs *c,
}
}
+/*
+ * Scan a range of an inode for data in pagecache.
+ *
+ * Intended to be retryable, so don't modify the output params until success is
+ * imminent.
+ */
+static int
+bch2_fiemap_hole_pagecache(struct inode *vinode, u64 *start, u64 *end,
+ bool nonblock)
+{
+ loff_t dstart, dend;
+
+ dstart = bch2_seek_pagecache_data(vinode, *start, *end, 0, nonblock);
+ if (dstart < 0)
+ return dstart;
+
+ if (dstart == *end) {
+ *start = dstart;
+ return 0;
+ }
+
+ dend = bch2_seek_pagecache_hole(vinode, dstart, *end, 0, nonblock);
+ if (dend < 0)
+ return dend;
+
+ /* race */
+ BUG_ON(dstart == dend);
+
+ *start = dstart;
+ *end = dend;
+ return 0;
+}
+
+/*
+ * Scan a range of pagecache that corresponds to a file mapping hole in the
+ * extent btree. If data is found, fake up an extent key so it looks like a
+ * delalloc extent to the rest of the fiemap processing code.
+ */
+static int
+bch2_next_fiemap_pagecache_extent(struct btree_trans *trans, struct bch_inode_info *inode,
+ u64 start, u64 end, struct bch_fiemap_extent *cur)
+{
+ struct bch_fs *c = trans->c;
+ struct bkey_i_extent *delextent;
+ struct bch_extent_ptr ptr = {};
+ loff_t dstart = start << 9, dend = end << 9;
+ int ret;
+
+ /*
+ * We hold btree locks here so we cannot block on folio locks without
+ * dropping trans locks first. Run a nonblocking scan for the common
+ * case of no folios over holes and fall back on failure.
+ *
+ * Note that dropping locks like this is technically racy against
+ * writeback inserting to the extent tree, but a non-sync fiemap scan is
+ * fundamentally racy with writeback anyways. Therefore, just report the
+ * range as delalloc regardless of whether we have to cycle trans locks.
+ */
+ ret = bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, true);
+ if (ret == -EAGAIN)
+ ret = drop_locks_do(trans,
+ bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, false));
+ if (ret < 0)
+ return ret;
+
+ /*
+ * Create a fake extent key in the buffer. We have to add a dummy extent
+ * pointer for the fill code to add an extent entry. It's explicitly
+ * zeroed to reflect delayed allocation (i.e. phys offset 0).
+ */
+ bch2_bkey_buf_realloc(&cur->kbuf, c, sizeof(*delextent) / sizeof(u64));
+ delextent = bkey_extent_init(cur->kbuf.k);
+ delextent->k.p = POS(inode->ei_inum.inum, dend >> 9);
+ delextent->k.size = (dend - dstart) >> 9;
+ bch2_bkey_append_ptr(&delextent->k_i, ptr);
+
+ cur->flags = FIEMAP_EXTENT_DELALLOC;
+
+ return 0;
+}
+
+static int bch2_next_fiemap_extent(struct btree_trans *trans,
+ struct bch_inode_info *inode,
+ u64 start, u64 end,
+ struct bch_fiemap_extent *cur)
+{
+ u32 snapshot;
+ int ret = bch2_subvolume_get_snapshot(trans, inode->ei_inum.subvol, &snapshot);
+ if (ret)
+ return ret;
+
+ struct btree_iter iter;
+ bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
+ SPOS(inode->ei_inum.inum, start, snapshot), 0);
+
+ struct bkey_s_c k =
+ bch2_btree_iter_peek_max(trans, &iter, POS(inode->ei_inum.inum, end));
+ ret = bkey_err(k);
+ if (ret)
+ goto err;
+
+ u64 pagecache_end = k.k ? max(start, bkey_start_offset(k.k)) : end;
+
+ ret = bch2_next_fiemap_pagecache_extent(trans, inode, start, pagecache_end, cur);
+ if (ret)
+ goto err;
+
+ struct bpos pagecache_start = bkey_start_pos(&cur->kbuf.k->k);
+
+ /*
+ * Does the pagecache or the btree take precedence?
+ *
+ * It _should_ be the pagecache, so that we correctly report delalloc
+ * extents when dirty in the pagecache (we're COW, after all).
+ *
+ * But we'd have to add per-sector writeback tracking to
+ * bch_folio_state, otherwise we report delalloc extents for clean
+ * cached data in the pagecache.
+ *
+ * We should do this, but even then fiemap won't report stable mappings:
+ * on bcachefs data moves around in the background (copygc, rebalance)
+ * and we don't provide a way for userspace to lock that out.
+ */
+ if (k.k &&
+ bkey_le(bpos_max(iter.pos, bkey_start_pos(k.k)),
+ pagecache_start)) {
+ bch2_bkey_buf_reassemble(&cur->kbuf, trans->c, k);
+ bch2_cut_front(iter.pos, cur->kbuf.k);
+ bch2_cut_back(POS(inode->ei_inum.inum, end), cur->kbuf.k);
+ cur->flags = 0;
+ } else if (k.k) {
+ bch2_cut_back(bkey_start_pos(k.k), cur->kbuf.k);
+ }
+
+ if (cur->kbuf.k->k.type == KEY_TYPE_reflink_p) {
+ unsigned sectors = cur->kbuf.k->k.size;
+ s64 offset_into_extent = 0;
+ enum btree_id data_btree = BTREE_ID_extents;
+ ret = bch2_read_indirect_extent(trans, &data_btree, &offset_into_extent,
+ &cur->kbuf);
+ if (ret)
+ goto err;
+
+ struct bkey_i *k = cur->kbuf.k;
+ sectors = min_t(unsigned, sectors, k->k.size - offset_into_extent);
+
+ bch2_cut_front(POS(k->k.p.inode,
+ bkey_start_offset(&k->k) + offset_into_extent),
+ k);
+ bch2_key_resize(&k->k, sectors);
+ k->k.p = iter.pos;
+ k->k.p.offset += k->k.size;
+ }
+err:
+ bch2_trans_iter_exit(trans, &iter);
+ return ret;
+}
+
static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
u64 start, u64 len)
{
struct bch_fs *c = vinode->i_sb->s_fs_info;
struct bch_inode_info *ei = to_bch_ei(vinode);
struct btree_trans *trans;
- struct btree_iter iter;
- struct bkey_s_c k;
- struct bkey_buf cur, prev;
- bool have_extent = false;
+ struct bch_fiemap_extent cur, prev;
int ret = 0;
- ret = fiemap_prep(&ei->v, info, start, &len, FIEMAP_FLAG_SYNC);
+ ret = fiemap_prep(&ei->v, info, start, &len, 0);
if (ret)
return ret;
- struct bpos end = POS(ei->v.i_ino, (start + len) >> 9);
if (start + len < start)
return -EINVAL;
start >>= 9;
+ u64 end = (start + len) >> 9;
- bch2_bkey_buf_init(&cur);
- bch2_bkey_buf_init(&prev);
+ bch2_bkey_buf_init(&cur.kbuf);
+ bch2_bkey_buf_init(&prev.kbuf);
+ bkey_init(&prev.kbuf.k->k);
+
trans = bch2_trans_get(c);
- bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
- POS(ei->v.i_ino, start), 0);
-
- while (!ret || bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
- enum btree_id data_btree = BTREE_ID_extents;
-
- bch2_trans_begin(trans);
-
- u32 snapshot;
- ret = bch2_subvolume_get_snapshot(trans, ei->ei_inum.subvol, &snapshot);
+ while (start < end) {
+ ret = lockrestart_do(trans,
+ bch2_next_fiemap_extent(trans, ei, start, end, &cur));
if (ret)
- continue;
+ goto err;
- bch2_btree_iter_set_snapshot(trans, &iter, snapshot);
+ BUG_ON(bkey_start_offset(&cur.kbuf.k->k) < start);
+ BUG_ON(cur.kbuf.k->k.p.offset > end);
- k = bch2_btree_iter_peek_max(trans, &iter, end);
- ret = bkey_err(k);
- if (ret)
- continue;
-
- if (!k.k)
+ if (bkey_start_offset(&cur.kbuf.k->k) == end)
break;
- if (!bkey_extent_is_data(k.k) &&
- k.k->type != KEY_TYPE_reservation) {
- bch2_btree_iter_advance(trans, &iter);
- continue;
- }
+ start = cur.kbuf.k->k.p.offset;
- s64 offset_into_extent = iter.pos.offset - bkey_start_offset(k.k);
- unsigned sectors = k.k->size - offset_into_extent;
-
- bch2_bkey_buf_reassemble(&cur, c, k);
-
- ret = bch2_read_indirect_extent(trans, &data_btree,
- &offset_into_extent, &cur);
- if (ret)
- continue;
-
- k = bkey_i_to_s_c(cur.k);
- bch2_bkey_buf_realloc(&prev, c, k.k->u64s);
-
- sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent);
-
- bch2_cut_front(POS(k.k->p.inode,
- bkey_start_offset(k.k) +
- offset_into_extent),
- cur.k);
- bch2_key_resize(&cur.k->k, sectors);
- cur.k->k.p = iter.pos;
- cur.k->k.p.offset += cur.k->k.size;
-
- if (have_extent) {
+ if (!bkey_deleted(&prev.kbuf.k->k)) {
bch2_trans_unlock(trans);
- ret = bch2_fill_extent(c, info,
- bkey_i_to_s_c(prev.k), 0);
+ ret = bch2_fill_extent(c, info, &prev);
if (ret)
- break;
+ goto err;
}
- bkey_copy(prev.k, cur.k);
- have_extent = true;
-
- bch2_btree_iter_set_pos(trans, &iter,
- POS(iter.pos.inode, iter.pos.offset + sectors));
+ bch2_bkey_buf_copy(&prev.kbuf, c, cur.kbuf.k);
+ prev.flags = cur.flags;
}
- bch2_trans_iter_exit(trans, &iter);
- if (!ret && have_extent) {
+ if (!bkey_deleted(&prev.kbuf.k->k)) {
bch2_trans_unlock(trans);
- ret = bch2_fill_extent(c, info, bkey_i_to_s_c(prev.k),
- FIEMAP_EXTENT_LAST);
+ prev.flags |= FIEMAP_EXTENT_LAST;
+ ret = bch2_fill_extent(c, info, &prev);
}
-
+err:
bch2_trans_put(trans);
- bch2_bkey_buf_exit(&cur, c);
- bch2_bkey_buf_exit(&prev, c);
- return ret < 0 ? ret : 0;
+ bch2_bkey_buf_exit(&cur.kbuf, c);
+ bch2_bkey_buf_exit(&prev.kbuf, c);
+
+ return bch2_err_class(ret < 0 ? ret : 0);
}
static const struct vm_operations_struct bch_vm_ops = {
@@ -1449,6 +1601,165 @@ static int bch2_open(struct inode *vinode, struct file *file)
return generic_file_open(vinode, file);
}
+/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
+static const __maybe_unused unsigned bch_flags_to_uflags[] = {
+ [__BCH_INODE_sync] = FS_SYNC_FL,
+ [__BCH_INODE_immutable] = FS_IMMUTABLE_FL,
+ [__BCH_INODE_append] = FS_APPEND_FL,
+ [__BCH_INODE_nodump] = FS_NODUMP_FL,
+ [__BCH_INODE_noatime] = FS_NOATIME_FL,
+};
+
+/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
+static const __maybe_unused unsigned bch_flags_to_xflags[] = {
+ [__BCH_INODE_sync] = FS_XFLAG_SYNC,
+ [__BCH_INODE_immutable] = FS_XFLAG_IMMUTABLE,
+ [__BCH_INODE_append] = FS_XFLAG_APPEND,
+ [__BCH_INODE_nodump] = FS_XFLAG_NODUMP,
+ [__BCH_INODE_noatime] = FS_XFLAG_NOATIME,
+};
+
+static int bch2_fileattr_get(struct dentry *dentry,
+ struct fileattr *fa)
+{
+ struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+ struct bch_fs *c = inode->v.i_sb->s_fs_info;
+
+ fileattr_fill_xflags(fa, map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags));
+
+ if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
+ fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+
+ if (bch2_inode_casefold(c, &inode->ei_inode))
+ fa->flags |= FS_CASEFOLD_FL;
+
+ fa->fsx_projid = inode->ei_qid.q[QTYP_PRJ];
+ return 0;
+}
+
+struct flags_set {
+ unsigned mask;
+ unsigned flags;
+ unsigned projid;
+ bool set_project;
+ bool set_casefold;
+ bool casefold;
+};
+
+static int fssetxattr_inode_update_fn(struct btree_trans *trans,
+ struct bch_inode_info *inode,
+ struct bch_inode_unpacked *bi,
+ void *p)
+{
+ struct bch_fs *c = trans->c;
+ struct flags_set *s = p;
+
+ /*
+ * We're relying on btree locking here for exclusion with other ioctl
+ * calls - use the flags in the btree (@bi), not inode->i_flags:
+ */
+ if (!S_ISREG(bi->bi_mode) &&
+ !S_ISDIR(bi->bi_mode) &&
+ (s->flags & (BCH_INODE_nodump|BCH_INODE_noatime)) != s->flags)
+ return -EINVAL;
+
+ if (s->casefold != bch2_inode_casefold(c, bi)) {
+#ifdef CONFIG_UNICODE
+ int ret = 0;
+ /* Not supported on individual files. */
+ if (!S_ISDIR(bi->bi_mode))
+ return -EOPNOTSUPP;
+
+ /*
+ * Make sure the dir is empty, as otherwise we'd need to
+ * rehash everything and update the dirent keys.
+ */
+ ret = bch2_empty_dir_trans(trans, inode_inum(inode));
+ if (ret < 0)
+ return ret;
+
+ ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding);
+ if (ret)
+ return ret;
+
+ bch2_check_set_feature(c, BCH_FEATURE_casefolding);
+
+ bi->bi_casefold = s->casefold + 1;
+ bi->bi_fields_set |= BIT(Inode_opt_casefold);
+
+#else
+ printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
+ return -EOPNOTSUPP;
+#endif
+ }
+
+ if (s->set_project) {
+ bi->bi_project = s->projid;
+ bi->bi_fields_set |= BIT(Inode_opt_project);
+ }
+
+ bi->bi_flags &= ~s->mask;
+ bi->bi_flags |= s->flags;
+
+ bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
+ return 0;
+}
+
+static int bch2_fileattr_set(struct mnt_idmap *idmap,
+ struct dentry *dentry,
+ struct fileattr *fa)
+{
+ struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+ struct bch_fs *c = inode->v.i_sb->s_fs_info;
+ struct flags_set s = {};
+ int ret;
+
+ if (fa->fsx_valid) {
+ fa->fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
+
+ s.mask = map_defined(bch_flags_to_xflags);
+ s.flags |= map_flags_rev(bch_flags_to_xflags, fa->fsx_xflags);
+ if (fa->fsx_xflags)
+ return -EOPNOTSUPP;
+
+ if (fa->fsx_projid >= U32_MAX)
+ return -EINVAL;
+
+ /*
+ * inode fields accessible via the xattr interface are stored with a +1
+ * bias, so that 0 means unset:
+ */
+ if ((inode->ei_inode.bi_project ||
+ fa->fsx_projid) &&
+ inode->ei_inode.bi_project != fa->fsx_projid + 1) {
+ s.projid = fa->fsx_projid + 1;
+ s.set_project = true;
+ }
+ }
+
+ if (fa->flags_valid) {
+ s.mask = map_defined(bch_flags_to_uflags);
+
+ s.set_casefold = true;
+ s.casefold = (fa->flags & FS_CASEFOLD_FL) != 0;
+ fa->flags &= ~FS_CASEFOLD_FL;
+
+ s.flags |= map_flags_rev(bch_flags_to_uflags, fa->flags);
+ if (fa->flags)
+ return -EOPNOTSUPP;
+ }
+
+ mutex_lock(&inode->ei_update_lock);
+ ret = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
+ (s.set_project
+ ? bch2_set_projid(c, inode, fa->fsx_projid)
+ : 0) ?:
+ bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
+ ATTR_CTIME);
+ mutex_unlock(&inode->ei_update_lock);
+ return ret;
+}
+
static const struct file_operations bch_file_operations = {
.open = bch2_open,
.llseek = bch2_llseek,
@@ -1476,6 +1787,8 @@ static const struct inode_operations bch_file_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct inode_operations bch_dir_inode_operations = {
@@ -1496,6 +1809,8 @@ static const struct inode_operations bch_dir_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct file_operations bch_dir_file_operations = {
@@ -1518,6 +1833,8 @@ static const struct inode_operations bch_symlink_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct inode_operations bch_special_inode_operations = {
@@ -1528,6 +1845,8 @@ static const struct inode_operations bch_special_inode_operations = {
.get_inode_acl = bch2_get_acl,
.set_acl = bch2_set_acl,
#endif
+ .fileattr_get = bch2_fileattr_get,
+ .fileattr_set = bch2_fileattr_set,
};
static const struct address_space_operations bch_address_space_operations = {
@@ -2185,10 +2504,9 @@ static int bch2_fs_get_tree(struct fs_context *fc)
bch2_opts_apply(&c->opts, opts);
- /*
- * need to initialise sb and set c->vfs_sb _before_ starting fs,
- * for blk_holder_ops
- */
+ ret = bch2_fs_start(c);
+ if (ret)
+ goto err_stop_fs;
sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
ret = PTR_ERR_OR_ZERO(sb);
@@ -2250,9 +2568,10 @@ static int bch2_fs_get_tree(struct fs_context *fc)
sb->s_shrink->seeks = 0;
- ret = bch2_fs_start(c);
- if (ret)
- goto err_put_super;
+#ifdef CONFIG_UNICODE
+ sb->s_encoding = c->cf_encoding;
+#endif
+ generic_set_sb_d_ops(sb);
vinode = bch2_vfs_inode_get(c, BCACHEFS_ROOT_SUBVOL_INUM);
ret = PTR_ERR_OR_ZERO(vinode);
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 7b25ced..71d428f 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2446,7 +2446,7 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
u32 parent = le32_to_cpu(s.v->fs_path_parent);
if (darray_u32_has(&subvol_path, parent)) {
- if (fsck_err(c, subvol_loop, "subvolume loop"))
+ if (fsck_err(trans, subvol_loop, "subvolume loop"))
ret = reattach_subvol(trans, s);
break;
}
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index f82cfbf..c74af15 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -243,6 +243,14 @@ static inline unsigned bkey_inode_mode(struct bkey_s_c k)
}
}
+static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_unpacked *bi)
+{
+ /* inode apts are stored with a +1 bias: 0 means "unset, use fs opt" */
+ return bi->bi_casefold
+ ? bi->bi_casefold - 1
+ : c->opts.casefold;
+}
+
/* i_nlink: */
static inline unsigned nlink_bias(umode_t mode)
diff --git a/fs/bcachefs/inode_format.h b/fs/bcachefs/inode_format.h
index 117110a..87e193e 100644
--- a/fs/bcachefs/inode_format.h
+++ b/fs/bcachefs/inode_format.h
@@ -103,7 +103,8 @@ struct bch_inode_generation {
x(bi_parent_subvol, 32) \
x(bi_nocow, 8) \
x(bi_depth, 32) \
- x(bi_inodes_32bit, 8)
+ x(bi_inodes_32bit, 8) \
+ x(bi_casefold, 8)
/* subset of BCH_INODE_FIELDS */
#define BCH_INODE_OPTS() \
@@ -117,7 +118,8 @@ struct bch_inode_generation {
x(background_target, 16) \
x(erasure_code, 16) \
x(nocow, 8) \
- x(inodes_32bit, 8)
+ x(inodes_32bit, 8) \
+ x(casefold, 8)
enum inode_opt_id {
#define x(name, ...) \
@@ -137,8 +139,7 @@ enum inode_opt_id {
x(i_sectors_dirty, 6) \
x(unlinked, 7) \
x(backptr_untrusted, 8) \
- x(has_child_snapshot, 9) \
- x(casefolded, 10)
+ x(has_child_snapshot, 9)
/* bits 20+ reserved for packed fields below: */
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index a418fa62..c1237da 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -255,6 +255,27 @@ static inline int bch2_extent_update_i_size_sectors(struct btree_trans *trans,
}
if (i_sectors_delta) {
+ s64 bi_sectors = le64_to_cpu(inode->v.bi_sectors);
+ if (unlikely(bi_sectors + i_sectors_delta < 0)) {
+ struct bch_fs *c = trans->c;
+ struct printbuf buf = PRINTBUF;
+ bch2_log_msg_start(c, &buf);
+ prt_printf(&buf, "inode %llu i_sectors underflow: %lli + %lli < 0",
+ extent_iter->pos.inode, bi_sectors, i_sectors_delta);
+
+ bool repeat = false, print = false, suppress = false;
+ bch2_count_fsck_err(c, inode_i_sectors_underflow, buf.buf,
+ &repeat, &print, &suppress);
+ if (print)
+ bch2_print_str(c, buf.buf);
+ printbuf_exit(&buf);
+
+ if (i_sectors_delta < 0)
+ i_sectors_delta = -bi_sectors;
+ else
+ i_sectors_delta = 0;
+ }
+
le64_add_cpu(&inode->v.bi_sectors, i_sectors_delta);
inode_update_flags = 0;
}
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index d8f74b6..bb45d36 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -281,7 +281,24 @@ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool t
sectors = vstruct_blocks_plus(buf->data, c->block_bits,
buf->u64s_reserved) << c->block_bits;
- BUG_ON(sectors > buf->sectors);
+ if (unlikely(sectors > buf->sectors)) {
+ struct printbuf err = PRINTBUF;
+ err.atomic++;
+
+ prt_printf(&err, "journal entry overran reserved space: %u > %u\n",
+ sectors, buf->sectors);
+ prt_printf(&err, "buf u64s %u u64s reserved %u cur_entry_u64s %u block_bits %u\n",
+ le32_to_cpu(buf->data->u64s), buf->u64s_reserved,
+ j->cur_entry_u64s,
+ c->block_bits);
+ prt_printf(&err, "fatal error - emergency read only");
+ bch2_journal_halt_locked(j);
+
+ bch_err(c, "%s", err.buf);
+ printbuf_exit(&err);
+ return;
+ }
+
buf->sectors = sectors;
/*
@@ -1462,8 +1479,6 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
j->last_empty_seq = cur_seq - 1; /* to match j->seq */
spin_lock(&j->lock);
-
- set_bit(JOURNAL_running, &j->flags);
j->last_flush_write = jiffies;
j->reservations.idx = journal_cur_seq(j);
@@ -1474,6 +1489,21 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
return 0;
}
+void bch2_journal_set_replay_done(struct journal *j)
+{
+ /*
+ * journal_space_available must happen before setting JOURNAL_running
+ * JOURNAL_running must happen before JOURNAL_replay_done
+ */
+ spin_lock(&j->lock);
+ bch2_journal_space_available(j);
+
+ set_bit(JOURNAL_need_flush_write, &j->flags);
+ set_bit(JOURNAL_running, &j->flags);
+ set_bit(JOURNAL_replay_done, &j->flags);
+ spin_unlock(&j->lock);
+}
+
/* init/exit: */
void bch2_dev_journal_exit(struct bch_dev *ca)
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 4782877..641e20c 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -437,12 +437,6 @@ static inline int bch2_journal_error(struct journal *j)
struct bch_dev;
-static inline void bch2_journal_set_replay_done(struct journal *j)
-{
- BUG_ON(!test_bit(JOURNAL_running, &j->flags));
- set_bit(JOURNAL_replay_done, &j->flags);
-}
-
void bch2_journal_unblock(struct journal *);
void bch2_journal_block(struct journal *);
struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u64, bool *);
@@ -459,6 +453,7 @@ void bch2_dev_journal_stop(struct journal *, struct bch_dev *);
void bch2_fs_journal_stop(struct journal *);
int bch2_fs_journal_start(struct journal *, u64);
+void bch2_journal_set_replay_done(struct journal *);
void bch2_dev_journal_exit(struct bch_dev *);
int bch2_dev_journal_init(struct bch_dev *, struct bch_sb *);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 2a54ac7..ded18a9 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -19,6 +19,7 @@
#include <linux/ioprio.h>
#include <linux/string_choices.h>
+#include <linux/sched/sysctl.h>
void bch2_journal_pos_from_member_info_set(struct bch_fs *c)
{
@@ -1262,7 +1263,8 @@ int bch2_journal_read(struct bch_fs *c,
degraded = true;
}
- closure_sync(&jlist.cl);
+ while (closure_sync_timeout(&jlist.cl, sysctl_hung_task_timeout_secs * HZ / 2))
+ ;
if (jlist.ret)
return jlist.ret;
@@ -1782,7 +1784,7 @@ static CLOSURE_CALLBACK(journal_write_submit)
struct bch_dev *ca = bch2_dev_get_ioref(c, ptr->dev, WRITE);
if (!ca) {
/* XXX: fix this */
- bch_err(c, "missing device for journal write\n");
+ bch_err(c, "missing device %u for journal write", ptr->dev);
continue;
}
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 5d1547a..cc00b0f 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -17,6 +17,8 @@
#include <linux/kthread.h>
#include <linux/sched/mm.h>
+static bool __should_discard_bucket(struct journal *, struct journal_device *);
+
/* Free space calculations: */
static unsigned journal_space_from(struct journal_device *ja,
@@ -203,8 +205,7 @@ void bch2_journal_space_available(struct journal *j)
ja->bucket_seq[ja->dirty_idx_ondisk] < j->last_seq_ondisk)
ja->dirty_idx_ondisk = (ja->dirty_idx_ondisk + 1) % ja->nr;
- if (ja->discard_idx != ja->dirty_idx_ondisk)
- can_discard = true;
+ can_discard |= __should_discard_bucket(j, ja);
max_entry_size = min_t(unsigned, max_entry_size, ca->mi.bucket_size);
nr_online++;
@@ -252,7 +253,10 @@ void bch2_journal_space_available(struct journal *j)
bch2_journal_set_watermark(j);
out:
- j->cur_entry_sectors = !ret ? j->space[journal_space_discarded].next_entry : 0;
+ j->cur_entry_sectors = !ret
+ ? round_down(j->space[journal_space_discarded].next_entry,
+ block_sectors(c))
+ : 0;
j->cur_entry_error = ret;
if (!ret)
@@ -261,12 +265,19 @@ void bch2_journal_space_available(struct journal *j)
/* Discards - last part of journal reclaim: */
+static bool __should_discard_bucket(struct journal *j, struct journal_device *ja)
+{
+ unsigned min_free = max(4, ja->nr / 8);
+
+ return bch2_journal_dev_buckets_available(j, ja, journal_space_discarded) <
+ min_free &&
+ ja->discard_idx != ja->dirty_idx_ondisk;
+}
+
static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
{
- bool ret;
-
spin_lock(&j->lock);
- ret = ja->discard_idx != ja->dirty_idx_ondisk;
+ bool ret = __should_discard_bucket(j, ja);
spin_unlock(&j->lock);
return ret;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index fc396b9..dfdbb92 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -784,7 +784,8 @@ static int __bch2_move_data_phys(struct moving_context *ctxt,
goto err;
ret = bch2_btree_write_buffer_tryflush(trans);
- bch_err_msg(c, ret, "flushing btree write buffer");
+ if (!bch2_err_matches(ret, EROFS))
+ bch_err_msg(c, ret, "flushing btree write buffer");
if (ret)
goto err;
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 159410c..9687337 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -356,6 +356,13 @@ static int bch2_copygc_thread(void *arg)
set_freezable();
+ /*
+ * Data move operations can't run until after check_snapshots has
+ * completed, and bch2_snapshot_is_ancestor() is available.
+ */
+ kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+ kthread_should_stop());
+
bch2_move_stats_init(&move_stats, "copygc");
bch2_moving_ctxt_init(&ctxt, c, NULL, &move_stats,
writepoint_ptr(&c->copygc_write_point),
diff --git a/fs/bcachefs/movinggc.h b/fs/bcachefs/movinggc.h
index ea181fe..d1885cf6 100644
--- a/fs/bcachefs/movinggc.h
+++ b/fs/bcachefs/movinggc.h
@@ -5,6 +5,15 @@
unsigned long bch2_copygc_wait_amount(struct bch_fs *);
void bch2_copygc_wait_to_text(struct printbuf *, struct bch_fs *);
+static inline void bch2_copygc_wakeup(struct bch_fs *c)
+{
+ rcu_read_lock();
+ struct task_struct *p = rcu_dereference(c->copygc_thread);
+ if (p)
+ wake_up_process(p);
+ rcu_read_unlock();
+}
+
void bch2_copygc_stop(struct bch_fs *);
int bch2_copygc_start(struct bch_fs *);
void bch2_fs_copygc_init(struct bch_fs *);
diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 0d65ea9..52c58c6 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -47,10 +47,6 @@ int bch2_create_trans(struct btree_trans *trans,
if (ret)
goto err;
- /* Inherit casefold state from parent. */
- if (S_ISDIR(mode))
- new_inode->bi_flags |= dir_u->bi_flags & BCH_INODE_casefolded;
-
if (!(flags & BCH_CREATE_SNAPSHOT)) {
/* Normal create path - allocate a new inode: */
bch2_inode_init_late(new_inode, now, uid, gid, mode, rdev, dir_u);
@@ -347,6 +343,9 @@ bool bch2_reinherit_attrs(struct bch_inode_unpacked *dst_u,
bool ret = false;
for (id = 0; id < Inode_opt_nr; id++) {
+ if (!S_ISDIR(dst_u->bi_mode) && id == Inode_opt_casefold)
+ continue;
+
/* Skip attributes that were explicitly set on this inode */
if (dst_u->bi_fields_set & (1 << id))
continue;
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 4d06313..dfb1481 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -228,6 +228,11 @@ enum fsck_err_opts {
OPT_BOOL(), \
BCH_SB_ERASURE_CODE, false, \
NULL, "Enable erasure coding (DO NOT USE YET)") \
+ x(casefold, u8, \
+ OPT_FS|OPT_INODE|OPT_FORMAT, \
+ OPT_BOOL(), \
+ BCH_SB_CASEFOLD, false, \
+ NULL, "Dirent lookups are casefolded") \
x(inodes_32bit, u8, \
OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \
OPT_BOOL(), \
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index c63fa53..62327355 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -262,7 +262,7 @@ int bch2_set_rebalance_needs_scan(struct bch_fs *c, u64 inum)
int ret = bch2_trans_commit_do(c, NULL, NULL,
BCH_TRANS_COMMIT_no_enospc,
bch2_set_rebalance_needs_scan_trans(trans, inum));
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
return ret;
}
@@ -309,7 +309,7 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_s_c k)
{
- if (!bch2_bkey_rebalance_opts(k))
+ if (k.k->type == KEY_TYPE_reflink_v || !bch2_bkey_rebalance_opts(k))
return 0;
struct bkey_i *n = bch2_bkey_make_mut(trans, iter, &k, 0);
@@ -581,6 +581,13 @@ static int bch2_rebalance_thread(void *arg)
set_freezable();
+ /*
+ * Data move operations can't run until after check_snapshots has
+ * completed, and bch2_snapshot_is_ancestor() is available.
+ */
+ kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+ kthread_should_stop());
+
bch2_moving_ctxt_init(&ctxt, c, NULL, &r->work_stats,
writepoint_ptr(&c->rebalance_write_point),
true);
@@ -664,7 +671,7 @@ void bch2_rebalance_stop(struct bch_fs *c)
c->rebalance.thread = NULL;
if (p) {
- /* for sychronizing with rebalance_wakeup() */
+ /* for sychronizing with bch2_rebalance_wakeup() */
synchronize_rcu();
kthread_stop(p);
diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h
index 62a3859..e5e8eb4 100644
--- a/fs/bcachefs/rebalance.h
+++ b/fs/bcachefs/rebalance.h
@@ -37,7 +37,7 @@ int bch2_set_rebalance_needs_scan_trans(struct btree_trans *, u64);
int bch2_set_rebalance_needs_scan(struct bch_fs *, u64 inum);
int bch2_set_fs_needs_rebalance(struct bch_fs *);
-static inline void rebalance_wakeup(struct bch_fs *c)
+static inline void bch2_rebalance_wakeup(struct bch_fs *c)
{
struct task_struct *p;
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 606d684..d6c4ef8 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -18,6 +18,7 @@
#include "journal_seq_blacklist.h"
#include "logged_ops.h"
#include "move.h"
+#include "movinggc.h"
#include "namei.h"
#include "quota.h"
#include "rebalance.h"
@@ -1129,13 +1130,13 @@ int bch2_fs_initialize(struct bch_fs *c)
if (ret)
goto err;
- set_bit(BCH_FS_accounting_replay_done, &c->flags);
- bch2_journal_set_replay_done(&c->journal);
-
ret = bch2_fs_read_write_early(c);
if (ret)
goto err;
+ set_bit(BCH_FS_accounting_replay_done, &c->flags);
+ bch2_journal_set_replay_done(&c->journal);
+
for_each_member_device(c, ca) {
ret = bch2_dev_usage_init(ca, false);
if (ret) {
@@ -1194,6 +1195,9 @@ int bch2_fs_initialize(struct bch_fs *c)
c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1;
+ bch2_copygc_wakeup(c);
+ bch2_rebalance_wakeup(c);
+
if (enabled_qtypes(c)) {
ret = bch2_fs_quota_read(c);
if (ret)
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 593ff14..22f72bb 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -12,6 +12,7 @@
#include "journal.h"
#include "lru.h"
#include "logged_ops.h"
+#include "movinggc.h"
#include "rebalance.h"
#include "recovery.h"
#include "recovery_passes.h"
@@ -262,49 +263,52 @@ int bch2_run_recovery_passes(struct bch_fs *c)
*/
c->opts.recovery_passes_exclude &= ~BCH_RECOVERY_PASS_set_may_go_rw;
- while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
- c->next_recovery_pass = c->curr_recovery_pass + 1;
+ spin_lock_irq(&c->recovery_pass_lock);
- spin_lock_irq(&c->recovery_pass_lock);
+ while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
+ unsigned prev_done = c->recovery_pass_done;
unsigned pass = c->curr_recovery_pass;
+ c->next_recovery_pass = pass + 1;
+
if (c->opts.recovery_pass_last &&
- c->curr_recovery_pass > c->opts.recovery_pass_last) {
- spin_unlock_irq(&c->recovery_pass_lock);
+ c->curr_recovery_pass > c->opts.recovery_pass_last)
break;
- }
- if (!should_run_recovery_pass(c, pass)) {
- c->curr_recovery_pass++;
- c->recovery_pass_done = max(c->recovery_pass_done, pass);
+ if (should_run_recovery_pass(c, pass)) {
spin_unlock_irq(&c->recovery_pass_lock);
- continue;
+ ret = bch2_run_recovery_pass(c, pass) ?:
+ bch2_journal_flush(&c->journal);
+
+ if (!ret && !test_bit(BCH_FS_error, &c->flags))
+ bch2_clear_recovery_pass_required(c, pass);
+ spin_lock_irq(&c->recovery_pass_lock);
+
+ if (c->next_recovery_pass < c->curr_recovery_pass) {
+ /*
+ * bch2_run_explicit_recovery_pass() was called: we
+ * can't always catch -BCH_ERR_restart_recovery because
+ * it may have been called from another thread (btree
+ * node read completion)
+ */
+ ret = 0;
+ c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
+ } else {
+ c->recovery_passes_complete |= BIT_ULL(pass);
+ c->recovery_pass_done = max(c->recovery_pass_done, pass);
+ }
}
- spin_unlock_irq(&c->recovery_pass_lock);
- ret = bch2_run_recovery_pass(c, pass) ?:
- bch2_journal_flush(&c->journal);
-
- if (!ret && !test_bit(BCH_FS_error, &c->flags))
- bch2_clear_recovery_pass_required(c, pass);
-
- spin_lock_irq(&c->recovery_pass_lock);
- if (c->next_recovery_pass < c->curr_recovery_pass) {
- /*
- * bch2_run_explicit_recovery_pass() was called: we
- * can't always catch -BCH_ERR_restart_recovery because
- * it may have been called from another thread (btree
- * node read completion)
- */
- ret = 0;
- c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
- } else {
- c->recovery_passes_complete |= BIT_ULL(pass);
- c->recovery_pass_done = max(c->recovery_pass_done, pass);
- }
c->curr_recovery_pass = c->next_recovery_pass;
- spin_unlock_irq(&c->recovery_pass_lock);
+
+ if (prev_done <= BCH_RECOVERY_PASS_check_snapshots &&
+ c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots) {
+ bch2_copygc_wakeup(c);
+ bch2_rebalance_wakeup(c);
+ }
}
+ spin_unlock_irq(&c->recovery_pass_lock);
+
return ret;
}
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index acb5d84..badd0e1 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -20,6 +20,10 @@
* x(version, recovery_passes, errors...)
*/
#define UPGRADE_TABLE() \
+ x(snapshot_2, \
+ RECOVERY_PASS_ALL_FSCK, \
+ BCH_FSCK_ERR_subvol_root_wrong_bi_subvol, \
+ BCH_FSCK_ERR_subvol_not_master_and_not_snapshot) \
x(backpointers, \
RECOVERY_PASS_ALL_FSCK) \
x(inode_v3, \
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index dc53d25..3b69a92 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -46,7 +46,7 @@ enum bch_fsck_flags {
x(btree_node_unsupported_version, 34, 0) \
x(btree_node_bset_older_than_sb_min, 35, 0) \
x(btree_node_bset_newer_than_sb, 36, 0) \
- x(btree_node_data_missing, 37, 0) \
+ x(btree_node_data_missing, 37, FSCK_AUTOFIX) \
x(btree_node_bset_after_end, 38, 0) \
x(btree_node_replicas_sectors_written_mismatch, 39, 0) \
x(btree_node_replicas_data_mismatch, 40, 0) \
@@ -205,9 +205,9 @@ enum bch_fsck_flags {
x(snapshot_bad_depth, 184, 0) \
x(snapshot_bad_skiplist, 185, 0) \
x(subvol_pos_bad, 186, 0) \
- x(subvol_not_master_and_not_snapshot, 187, 0) \
+ x(subvol_not_master_and_not_snapshot, 187, FSCK_AUTOFIX) \
x(subvol_to_missing_root, 188, 0) \
- x(subvol_root_wrong_bi_subvol, 189, 0) \
+ x(subvol_root_wrong_bi_subvol, 189, FSCK_AUTOFIX) \
x(bkey_in_missing_snapshot, 190, 0) \
x(inode_pos_inode_nonzero, 191, 0) \
x(inode_pos_blockdev_range, 192, 0) \
@@ -236,6 +236,9 @@ enum bch_fsck_flags {
x(inode_has_child_snapshots_wrong, 287, 0) \
x(inode_unreachable, 210, FSCK_AUTOFIX) \
x(inode_journal_seq_in_future, 299, FSCK_AUTOFIX) \
+ x(inode_i_sectors_underflow, 312, FSCK_AUTOFIX) \
+ x(vfs_inode_i_blocks_underflow, 311, FSCK_AUTOFIX) \
+ x(vfs_inode_i_blocks_not_zero_at_truncate, 313, FSCK_AUTOFIX) \
x(deleted_inode_but_clean, 211, FSCK_AUTOFIX) \
x(deleted_inode_missing, 212, FSCK_AUTOFIX) \
x(deleted_inode_is_dir, 213, FSCK_AUTOFIX) \
@@ -317,7 +320,9 @@ enum bch_fsck_flags {
x(directory_size_mismatch, 303, FSCK_AUTOFIX) \
x(dirent_cf_name_too_big, 304, 0) \
x(dirent_stray_data_after_cf_name, 305, 0) \
- x(MAX, 308, 0)
+ x(rebalance_work_incorrectly_set, 309, FSCK_AUTOFIX) \
+ x(rebalance_work_incorrectly_unset, 310, FSCK_AUTOFIX) \
+ x(MAX, 314, 0)
enum bch_sb_error_id {
#define x(t, n, ...) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index 116131f..7277991 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -15,9 +15,11 @@ void bch2_dev_missing(struct bch_fs *c, unsigned dev)
bch2_fs_inconsistent(c, "pointer to nonexistent device %u", dev);
}
-void bch2_dev_bucket_missing(struct bch_fs *c, struct bpos bucket)
+void bch2_dev_bucket_missing(struct bch_dev *ca, u64 bucket)
{
- bch2_fs_inconsistent(c, "pointer to nonexistent bucket %llu:%llu", bucket.inode, bucket.offset);
+ bch2_fs_inconsistent(ca->fs,
+ "pointer to nonexistent bucket %llu on device %s (valid range %u-%llu)",
+ bucket, ca->name, ca->mi.first_bucket, ca->mi.nbuckets);
}
#define x(t, n, ...) [n] = #t,
diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h
index 06bb41a..4278665 100644
--- a/fs/bcachefs/sb-members.h
+++ b/fs/bcachefs/sb-members.h
@@ -249,20 +249,23 @@ static inline struct bch_dev *bch2_dev_tryget(struct bch_fs *c, unsigned dev)
static inline struct bch_dev *bch2_dev_bucket_tryget_noerror(struct bch_fs *c, struct bpos bucket)
{
struct bch_dev *ca = bch2_dev_tryget_noerror(c, bucket.inode);
- if (ca && !bucket_valid(ca, bucket.offset)) {
+ if (ca && unlikely(!bucket_valid(ca, bucket.offset))) {
bch2_dev_put(ca);
ca = NULL;
}
return ca;
}
-void bch2_dev_bucket_missing(struct bch_fs *, struct bpos);
+void bch2_dev_bucket_missing(struct bch_dev *, u64);
static inline struct bch_dev *bch2_dev_bucket_tryget(struct bch_fs *c, struct bpos bucket)
{
- struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(c, bucket);
- if (!ca)
- bch2_dev_bucket_missing(c, bucket);
+ struct bch_dev *ca = bch2_dev_tryget(c, bucket.inode);
+ if (ca && unlikely(!bucket_valid(ca, bucket.offset))) {
+ bch2_dev_bucket_missing(ca, bucket.offset);
+ bch2_dev_put(ca);
+ ca = NULL;
+ }
return ca;
}
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index b7de29a..fec569c 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -396,7 +396,7 @@ u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root)
u32 subvol = 0, s;
rcu_read_lock();
- while (id) {
+ while (id && bch2_snapshot_exists(c, id)) {
s = snapshot_t(c, id)->subvol;
if (s && (!subvol || s < subvol))
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 09a354a..0c1a005 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -33,7 +33,7 @@ bch2_str_hash_opt_to_type(struct bch_fs *c, enum bch_str_hash_opts opt)
struct bch_hash_info {
u8 type;
- struct unicode_map *cf_encoding;
+ struct unicode_map *cf_encoding;
/*
* For crc32 or crc64 string hashes the first key value of
* the siphash_key (k0) is used as the key.
@@ -44,11 +44,10 @@ struct bch_hash_info {
static inline struct bch_hash_info
bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
{
- /* XXX ick */
struct bch_hash_info info = {
.type = INODE_STR_HASH(bi),
#ifdef CONFIG_UNICODE
- .cf_encoding = !!(bi->bi_flags & BCH_INODE_casefolded) ? c->cf_encoding : NULL,
+ .cf_encoding = bch2_inode_casefold(c, bi) ? c->cf_encoding : NULL,
#endif
.siphash_key = { .k0 = bi->bi_hash_seed }
};
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index 5537283..d0209f7 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -6,6 +6,7 @@
#include "errcode.h"
#include "error.h"
#include "fs.h"
+#include "recovery_passes.h"
#include "snapshot.h"
#include "subvolume.h"
@@ -44,8 +45,8 @@ static int check_subvol(struct btree_trans *trans,
ret = bch2_snapshot_lookup(trans, snapid, &snapshot);
if (bch2_err_matches(ret, ENOENT))
- bch_err(c, "subvolume %llu points to nonexistent snapshot %u",
- k.k->p.offset, snapid);
+ return bch2_run_explicit_recovery_pass(c,
+ BCH_RECOVERY_PASS_reconstruct_snapshots) ?: ret;
if (ret)
return ret;
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 25b6bce..cb5d960 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -1102,7 +1102,8 @@ int bch2_write_super(struct bch_fs *c)
prt_str(&buf, ")");
bch2_fs_fatal_error(c, ": %s", buf.buf);
printbuf_exit(&buf);
- return -BCH_ERR_sb_not_downgraded;
+ ret = -BCH_ERR_sb_not_downgraded;
+ goto out;
}
darray_for_each(online_devices, ca) {
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index e8a17ed..84a37d9 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -377,6 +377,11 @@ void bch2_fs_read_only(struct bch_fs *c)
bch_verbose(c, "marking filesystem clean");
bch2_fs_mark_clean(c);
} else {
+ /* Make sure error counts/counters are persisted */
+ mutex_lock(&c->sb_lock);
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
+
bch_verbose(c, "done going read-only, filesystem not clean");
}
}
@@ -418,32 +423,6 @@ bool bch2_fs_emergency_read_only_locked(struct bch_fs *c)
return ret;
}
-static int bch2_fs_read_write_late(struct bch_fs *c)
-{
- int ret;
-
- /*
- * Data move operations can't run until after check_snapshots has
- * completed, and bch2_snapshot_is_ancestor() is available.
- *
- * Ideally we'd start copygc/rebalance earlier instead of waiting for
- * all of recovery/fsck to complete:
- */
- ret = bch2_copygc_start(c);
- if (ret) {
- bch_err(c, "error starting copygc thread");
- return ret;
- }
-
- ret = bch2_rebalance_start(c);
- if (ret) {
- bch_err(c, "error starting rebalance thread");
- return ret;
- }
-
- return 0;
-}
-
static int __bch2_fs_read_write(struct bch_fs *c, bool early)
{
int ret;
@@ -466,29 +445,28 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
clear_bit(BCH_FS_clean_shutdown, &c->flags);
- /*
- * First journal write must be a flush write: after a clean shutdown we
- * don't read the journal, so the first journal write may end up
- * overwriting whatever was there previously, and there must always be
- * at least one non-flush write in the journal or recovery will fail:
- */
- set_bit(JOURNAL_need_flush_write, &c->journal.flags);
- set_bit(JOURNAL_running, &c->journal.flags);
-
__for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw), READ) {
bch2_dev_allocator_add(c, ca);
percpu_ref_reinit(&ca->io_ref[WRITE]);
}
bch2_recalc_capacity(c);
+ /*
+ * First journal write must be a flush write: after a clean shutdown we
+ * don't read the journal, so the first journal write may end up
+ * overwriting whatever was there previously, and there must always be
+ * at least one non-flush write in the journal or recovery will fail:
+ */
+ spin_lock(&c->journal.lock);
+ set_bit(JOURNAL_need_flush_write, &c->journal.flags);
+ set_bit(JOURNAL_running, &c->journal.flags);
+ bch2_journal_space_available(&c->journal);
+ spin_unlock(&c->journal.lock);
+
ret = bch2_fs_mark_dirty(c);
if (ret)
goto err;
- spin_lock(&c->journal.lock);
- bch2_journal_space_available(&c->journal);
- spin_unlock(&c->journal.lock);
-
ret = bch2_journal_reclaim_start(&c->journal);
if (ret)
goto err;
@@ -504,10 +482,17 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
atomic_long_inc(&c->writes[i]);
}
#endif
- if (!early) {
- ret = bch2_fs_read_write_late(c);
- if (ret)
- goto err;
+
+ ret = bch2_copygc_start(c);
+ if (ret) {
+ bch_err_msg(c, ret, "error starting copygc thread");
+ goto err;
+ }
+
+ ret = bch2_rebalance_start(c);
+ if (ret) {
+ bch_err_msg(c, ret, "error starting rebalance thread");
+ goto err;
}
bch2_do_discards(c);
@@ -551,8 +536,13 @@ static void __bch2_fs_free(struct bch_fs *c)
for (unsigned i = 0; i < BCH_TIME_STAT_NR; i++)
bch2_time_stats_exit(&c->times[i]);
+#ifdef CONFIG_UNICODE
+ utf8_unload(c->cf_encoding);
+#endif
+
bch2_find_btree_nodes_exit(&c->found_btree_nodes);
bch2_free_pending_node_rewrites(c);
+ bch2_free_fsck_errs(c);
bch2_fs_accounting_exit(c);
bch2_fs_sb_errors_exit(c);
bch2_fs_counters_exit(c);
@@ -842,25 +832,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
if (ret)
goto err;
-#ifdef CONFIG_UNICODE
- /* Default encoding until we can potentially have more as an option. */
- c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
- if (IS_ERR(c->cf_encoding)) {
- printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u",
- unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
- unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
- unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
- ret = -EINVAL;
- goto err;
- }
-#else
- if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) {
- printk(KERN_ERR "Cannot mount a filesystem with casefolding on a kernel without CONFIG_UNICODE\n");
- ret = -EINVAL;
- goto err;
- }
-#endif
-
pr_uuid(&name, c->sb.user_uuid.b);
ret = name.allocation_failure ? -BCH_ERR_ENOMEM_fs_name_alloc : 0;
if (ret)
@@ -960,6 +931,29 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
if (ret)
goto err;
+#ifdef CONFIG_UNICODE
+ /* Default encoding until we can potentially have more as an option. */
+ c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
+ if (IS_ERR(c->cf_encoding)) {
+ printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u",
+ unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+ unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+ unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+ ret = -EINVAL;
+ goto err;
+ }
+ bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
+ unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+ unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+ unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+#else
+ if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) {
+ printk(KERN_ERR "Cannot mount a filesystem with casefolding on a kernel without CONFIG_UNICODE\n");
+ ret = -EINVAL;
+ goto err;
+ }
+#endif
+
for (i = 0; i < c->sb.nr_devices; i++) {
if (!bch2_member_exists(c->disk_sb.sb, i))
continue;
@@ -1023,6 +1017,40 @@ static void print_mount_opts(struct bch_fs *c)
printbuf_exit(&p);
}
+static bool bch2_fs_may_start(struct bch_fs *c)
+{
+ struct bch_dev *ca;
+ unsigned i, flags = 0;
+
+ if (c->opts.very_degraded)
+ flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
+
+ if (c->opts.degraded)
+ flags |= BCH_FORCE_IF_DEGRADED;
+
+ if (!c->opts.degraded &&
+ !c->opts.very_degraded) {
+ mutex_lock(&c->sb_lock);
+
+ for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
+ if (!bch2_member_exists(c->disk_sb.sb, i))
+ continue;
+
+ ca = bch2_dev_locked(c, i);
+
+ if (!bch2_dev_is_online(ca) &&
+ (ca->mi.state == BCH_MEMBER_STATE_rw ||
+ ca->mi.state == BCH_MEMBER_STATE_ro)) {
+ mutex_unlock(&c->sb_lock);
+ return false;
+ }
+ }
+ mutex_unlock(&c->sb_lock);
+ }
+
+ return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
+}
+
int bch2_fs_start(struct bch_fs *c)
{
time64_t now = ktime_get_real_seconds();
@@ -1030,6 +1058,9 @@ int bch2_fs_start(struct bch_fs *c)
print_mount_opts(c);
+ if (!bch2_fs_may_start(c))
+ return -BCH_ERR_insufficient_devices_to_start;
+
down_write(&c->state_lock);
mutex_lock(&c->sb_lock);
@@ -1082,13 +1113,10 @@ int bch2_fs_start(struct bch_fs *c)
wake_up(&c->ro_ref_wait);
down_write(&c->state_lock);
- if (c->opts.read_only) {
+ if (c->opts.read_only)
bch2_fs_read_only(c);
- } else {
- ret = !test_bit(BCH_FS_rw, &c->flags)
- ? bch2_fs_read_write(c)
- : bch2_fs_read_write_late(c);
- }
+ else if (!test_bit(BCH_FS_rw, &c->flags))
+ ret = bch2_fs_read_write(c);
up_write(&c->state_lock);
err:
@@ -1500,7 +1528,7 @@ static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb)
printbuf_exit(&name);
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
return 0;
}
@@ -1559,40 +1587,6 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
}
}
-static bool bch2_fs_may_start(struct bch_fs *c)
-{
- struct bch_dev *ca;
- unsigned i, flags = 0;
-
- if (c->opts.very_degraded)
- flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
-
- if (c->opts.degraded)
- flags |= BCH_FORCE_IF_DEGRADED;
-
- if (!c->opts.degraded &&
- !c->opts.very_degraded) {
- mutex_lock(&c->sb_lock);
-
- for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
- if (!bch2_member_exists(c->disk_sb.sb, i))
- continue;
-
- ca = bch2_dev_locked(c, i);
-
- if (!bch2_dev_is_online(ca) &&
- (ca->mi.state == BCH_MEMBER_STATE_rw ||
- ca->mi.state == BCH_MEMBER_STATE_ro)) {
- mutex_unlock(&c->sb_lock);
- return false;
- }
- }
- mutex_unlock(&c->sb_lock);
- }
-
- return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
-}
-
static void __bch2_dev_read_only(struct bch_fs *c, struct bch_dev *ca)
{
bch2_dev_io_ref_stop(ca, WRITE);
@@ -1646,7 +1640,7 @@ int __bch2_dev_set_state(struct bch_fs *c, struct bch_dev *ca,
if (new_state == BCH_MEMBER_STATE_rw)
__bch2_dev_read_write(c, ca);
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
return ret;
}
@@ -2228,11 +2222,6 @@ struct bch_fs *bch2_fs_open(char * const *devices, unsigned nr_devices,
}
up_write(&c->state_lock);
- if (!bch2_fs_may_start(c)) {
- ret = -BCH_ERR_insufficient_devices_to_start;
- goto err_print;
- }
-
if (!c->opts.nostart) {
ret = bch2_fs_start(c);
if (ret)
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index e5f003c..82ee333 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -654,11 +654,10 @@ static ssize_t sysfs_opt_store(struct bch_fs *c,
bch2_set_rebalance_needs_scan(c, 0);
if (v && id == Opt_rebalance_enabled)
- rebalance_wakeup(c);
+ bch2_rebalance_wakeup(c);
- if (v && id == Opt_copygc_enabled &&
- c->copygc_thread)
- wake_up_process(c->copygc_thread);
+ if (v && id == Opt_copygc_enabled)
+ bch2_copygc_wakeup(c);
if (id == Opt_discard && !ca) {
mutex_lock(&c->sb_lock);
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index c265b10..782a05f 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -342,6 +342,8 @@ static int test_iterate_slots_extents(struct bch_fs *c, u64 nr)
*/
static int test_peek_end(struct bch_fs *c, u64 nr)
{
+ delete_test_keys(c);
+
struct btree_trans *trans = bch2_trans_get(c);
struct btree_iter iter;
struct bkey_s_c k;
@@ -362,6 +364,8 @@ static int test_peek_end(struct bch_fs *c, u64 nr)
static int test_peek_end_extents(struct bch_fs *c, u64 nr)
{
+ delete_test_keys(c);
+
struct btree_trans *trans = bch2_trans_get(c);
struct btree_iter iter;
struct bkey_s_c k;
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index dea73bc..314a24d 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -455,8 +455,10 @@ ssize_t bch2_stdio_redirect_vprintf(struct stdio_redirect *stdio, bool nonblocki
struct stdio_buf *buf = &stdio->output;
unsigned long flags;
ssize_t ret;
-
again:
+ if (stdio->done)
+ return -EPIPE;
+
spin_lock_irqsave(&buf->lock, flags);
ret = bch2_darray_vprintf(&buf->buf, GFP_NOWAIT, fmt, args);
spin_unlock_irqrestore(&buf->lock, flags);
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 6ba5071..3e52c7f 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -739,4 +739,42 @@ static inline void memcpy_swab(void *_dst, void *_src, size_t len)
*--dst = *src++;
}
+#define set_flags(_map, _in, _out) \
+do { \
+ unsigned _i; \
+ \
+ for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
+ if ((_in) & (1 << _i)) \
+ (_out) |= _map[_i]; \
+ else \
+ (_out) &= ~_map[_i]; \
+} while (0)
+
+#define map_flags(_map, _in) \
+({ \
+ unsigned _out = 0; \
+ \
+ set_flags(_map, _in, _out); \
+ _out; \
+})
+
+#define map_flags_rev(_map, _in) \
+({ \
+ unsigned _i, _out = 0; \
+ \
+ for (_i = 0; _i < ARRAY_SIZE(_map); _i++) \
+ if ((_in) & _map[_i]) { \
+ (_out) |= 1 << _i; \
+ (_in) &= ~_map[_i]; \
+ } \
+ (_out); \
+})
+
+#define map_defined(_map) \
+({ \
+ unsigned _in = ~0; \
+ \
+ map_flags_rev(_map, _in); \
+})
+
#endif /* _BCACHEFS_UTIL_H */
diff --git a/fs/bcachefs/xattr_format.h b/fs/bcachefs/xattr_format.h
index c791601..67426e3 100644
--- a/fs/bcachefs/xattr_format.h
+++ b/fs/bcachefs/xattr_format.h
@@ -13,7 +13,13 @@ struct bch_xattr {
__u8 x_type;
__u8 x_name_len;
__le16 x_val_len;
- __u8 x_name[] __counted_by(x_name_len);
+ /*
+ * x_name contains the name and value counted by
+ * x_name_len + x_val_len. The introduction of
+ * __counted_by(x_name_len) caused a false positive
+ * detection of an out of bounds write.
+ */
+ __u8 x_name[];
} __packed __aligned(8);
#endif /* _BCACHEFS_XATTR_FORMAT_H */
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 584fa89..4c1ea6b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -830,6 +830,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
struct elf_phdr *elf_property_phdata = NULL;
unsigned long elf_brk;
+ bool brk_moved = false;
int retval, i;
unsigned long elf_entry;
unsigned long e_entry;
@@ -1097,15 +1098,19 @@ static int load_elf_binary(struct linux_binprm *bprm)
/* Calculate any requested alignment. */
alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
- /*
- * There are effectively two types of ET_DYN
- * binaries: programs (i.e. PIE: ET_DYN with PT_INTERP)
- * and loaders (ET_DYN without PT_INTERP, since they
- * _are_ the ELF interpreter). The loaders must
- * be loaded away from programs since the program
- * may otherwise collide with the loader (especially
- * for ET_EXEC which does not have a randomized
- * position). For example to handle invocations of
+ /**
+ * DOC: PIE handling
+ *
+ * There are effectively two types of ET_DYN ELF
+ * binaries: programs (i.e. PIE: ET_DYN with
+ * PT_INTERP) and loaders (i.e. static PIE: ET_DYN
+ * without PT_INTERP, usually the ELF interpreter
+ * itself). Loaders must be loaded away from programs
+ * since the program may otherwise collide with the
+ * loader (especially for ET_EXEC which does not have
+ * a randomized position).
+ *
+ * For example, to handle invocations of
* "./ld.so someprog" to test out a new version of
* the loader, the subsequent program that the
* loader loads must avoid the loader itself, so
@@ -1118,6 +1123,9 @@ static int load_elf_binary(struct linux_binprm *bprm)
* ELF_ET_DYN_BASE and loaders are loaded into the
* independently randomized mmap region (0 load_bias
* without MAP_FIXED nor MAP_FIXED_NOREPLACE).
+ *
+ * See below for "brk" handling details, which is
+ * also affected by program vs loader and ASLR.
*/
if (interpreter) {
/* On ET_DYN with PT_INTERP, we do the ASLR. */
@@ -1234,8 +1242,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
start_data += load_bias;
end_data += load_bias;
- current->mm->start_brk = current->mm->brk = ELF_PAGEALIGN(elf_brk);
-
if (interpreter) {
elf_entry = load_elf_interp(interp_elf_ex,
interpreter,
@@ -1291,27 +1297,44 @@ static int load_elf_binary(struct linux_binprm *bprm)
mm->end_data = end_data;
mm->start_stack = bprm->p;
- if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) {
+ /**
+ * DOC: "brk" handling
+ *
+ * For architectures with ELF randomization, when executing a
+ * loader directly (i.e. static PIE: ET_DYN without PT_INTERP),
+ * move the brk area out of the mmap region and into the unused
+ * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide
+ * early with the stack growing down or other regions being put
+ * into the mmap region by the kernel (e.g. vdso).
+ *
+ * In the CONFIG_COMPAT_BRK case, though, everything is turned
+ * off because we're not allowed to move the brk at all.
+ */
+ if (!IS_ENABLED(CONFIG_COMPAT_BRK) &&
+ IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
+ elf_ex->e_type == ET_DYN && !interpreter) {
+ elf_brk = ELF_ET_DYN_BASE;
+ /* This counts as moving the brk, so let brk(2) know. */
+ brk_moved = true;
+ }
+ mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk);
+
+ if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) {
/*
- * For architectures with ELF randomization, when executing
- * a loader directly (i.e. no interpreter listed in ELF
- * headers), move the brk area out of the mmap region
- * (since it grows up, and may collide early with the stack
- * growing down), and into the unused ELF_ET_DYN_BASE region.
+ * If we didn't move the brk to ELF_ET_DYN_BASE (above),
+ * leave a gap between .bss and brk.
*/
- if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
- elf_ex->e_type == ET_DYN && !interpreter) {
- mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
- } else {
- /* Otherwise leave a gap between .bss and brk. */
+ if (!brk_moved)
mm->brk = mm->start_brk = mm->brk + PAGE_SIZE;
- }
mm->brk = mm->start_brk = arch_randomize_brk(mm);
+ brk_moved = true;
+ }
+
#ifdef compat_brk_randomized
+ if (brk_moved)
current->brk_randomized = 1;
#endif
- }
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index e7f8ee5..7f11ef5 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -606,7 +606,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
free_extent_map(em);
cb->nr_folios = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
- cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct page *), GFP_NOFS);
+ cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct folio *), GFP_NOFS);
if (!cb->compressed_folios) {
ret = BLK_STS_RESOURCE;
goto out_free_bio;
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index d6eef4b..de23c4b 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -94,8 +94,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
struct btrfs_block_group *block_group)
{
lockdep_assert_held(&discard_ctl->lock);
- if (!btrfs_run_discard_work(discard_ctl))
- return;
if (list_empty(&block_group->discard_list) ||
block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) {
@@ -118,6 +116,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
if (!btrfs_is_block_group_data_only(block_group))
return;
+ if (!btrfs_run_discard_work(discard_ctl))
+ return;
+
spin_lock(&discard_ctl->lock);
__add_to_discard_list(discard_ctl, block_group);
spin_unlock(&discard_ctl->lock);
@@ -244,6 +245,18 @@ static struct btrfs_block_group *peek_discard_list(
block_group->used != 0) {
if (btrfs_is_block_group_data_only(block_group)) {
__add_to_discard_list(discard_ctl, block_group);
+ /*
+ * The block group must have been moved to other
+ * discard list even if discard was disabled in
+ * the meantime or a transaction abort happened,
+ * otherwise we can end up in an infinite loop,
+ * always jumping into the 'again' label and
+ * keep getting this block group over and over
+ * in case there are no other block groups in
+ * the discard lists.
+ */
+ ASSERT(block_group->discard_index !=
+ BTRFS_DISCARD_INDEX_UNUSED);
} else {
list_del_init(&block_group->discard_list);
btrfs_put_block_group(block_group);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 197f5e5..13bdd60 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2047,7 +2047,7 @@ static int submit_eb_subpage(struct folio *folio, struct writeback_control *wbc)
subpage->bitmaps)) {
spin_unlock_irqrestore(&subpage->lock, flags);
spin_unlock(&folio->mapping->i_private_lock);
- bit_start++;
+ bit_start += sectors_per_node;
continue;
}
@@ -3508,8 +3508,8 @@ static void btree_clear_folio_dirty_tag(struct folio *folio)
ASSERT(folio_test_locked(folio));
xa_lock_irq(&folio->mapping->i_pages);
if (!folio_test_dirty(folio))
- __xa_clear_mark(&folio->mapping->i_pages,
- folio_index(folio), PAGECACHE_TAG_DIRTY);
+ __xa_clear_mark(&folio->mapping->i_pages, folio->index,
+ PAGECACHE_TAG_DIRTY);
xa_unlock_irq(&folio->mapping->i_pages);
}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 2e26189..f5b28b5 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -298,6 +298,8 @@ static inline int __pure num_extent_pages(const struct extent_buffer *eb)
*/
static inline int __pure num_extent_folios(const struct extent_buffer *eb)
{
+ if (!eb->folios[0])
+ return 0;
if (folio_order(eb->folios[0]))
return 1;
return num_extent_pages(eb);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 262a707..71b8a82 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2104,15 +2104,20 @@ static void btrfs_punch_hole_lock_range(struct inode *inode,
* will always return true.
* So here we need to do extra page alignment for
* filemap_range_has_page().
+ *
+ * And do not decrease page_lockend right now, as it can be 0.
*/
const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
- const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;
+ const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE);
while (1) {
truncate_pagecache_range(inode, lockstart, lockend);
lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
cached_state);
+ /* The same page or adjacent pages. */
+ if (page_lockend <= page_lockstart)
+ break;
/*
* We can't have ordered extents in the range, nor dirty/writeback
* pages, because we have locked the inode's VFS lock in exclusive
@@ -2124,7 +2129,7 @@ static void btrfs_punch_hole_lock_range(struct inode *inode,
* we do, unlock the range and retry.
*/
if (!filemap_range_has_page(inode->i_mapping, page_lockstart,
- page_lockend))
+ page_lockend - 1))
break;
unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index bcca430..7baa2ed 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -300,6 +300,7 @@ enum {
#define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
+#define BTRFS_WARNING_COMMIT_INTERVAL (300)
#define BTRFS_DEFAULT_MAX_INLINE (2048)
struct btrfs_dev_replace {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cc67d1a..90f5da3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1109,6 +1109,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
struct extent_state *cached = NULL;
struct extent_map *em;
int ret = 0;
+ bool free_pages = false;
u64 start = async_extent->start;
u64 end = async_extent->start + async_extent->ram_size - 1;
@@ -1129,7 +1130,10 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
}
if (async_extent->compress_type == BTRFS_COMPRESS_NONE) {
+ ASSERT(!async_extent->folios);
+ ASSERT(async_extent->nr_folios == 0);
submit_uncompressed_range(inode, async_extent, locked_folio);
+ free_pages = true;
goto done;
}
@@ -1145,6 +1149,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
* fall back to uncompressed.
*/
submit_uncompressed_range(inode, async_extent, locked_folio);
+ free_pages = true;
goto done;
}
@@ -1186,6 +1191,8 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
done:
if (async_chunk->blkcg_css)
kthread_associate_blkcg(NULL);
+ if (free_pages)
+ free_async_extent_pages(async_extent);
kfree(async_extent);
return;
@@ -2129,12 +2136,13 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
/*
* If the found extent starts after requested offset, then
- * adjust extent_end to be right before this extent begins
+ * adjust cur_offset to be right before this extent begins.
*/
if (found_key.offset > cur_offset) {
- extent_end = found_key.offset;
- extent_type = 0;
- goto must_cow;
+ if (cow_start == (u64)-1)
+ cow_start = cur_offset;
+ cur_offset = found_key.offset;
+ goto next_slot;
}
/*
@@ -5681,8 +5689,10 @@ struct btrfs_inode *btrfs_iget(u64 ino, struct btrfs_root *root)
return inode;
path = btrfs_alloc_path();
- if (!path)
+ if (!path) {
+ iget_failed(&inode->vfs_inode);
return ERR_PTR(-ENOMEM);
+ }
ret = btrfs_read_locked_inode(inode, path);
btrfs_free_path(path);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f948f4f..e17bcb0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3803,7 +3803,7 @@ static noinline_for_stack struct inode *create_reloc_inode(
if (ret) {
if (inode)
iput(&inode->vfs_inode);
- inode = ERR_PTR(ret);
+ return ERR_PTR(ret);
}
return &inode->vfs_inode;
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2c5edce..c3b2e29 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1541,8 +1541,8 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
u64 extent_gen;
int ret;
- if (unlikely(!extent_root)) {
- btrfs_err(fs_info, "no valid extent root for scrub");
+ if (unlikely(!extent_root || !csum_root)) {
+ btrfs_err(fs_info, "no valid extent or csum root for scrub");
return -EUCLEAN;
}
memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) *
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 11dbd7b..c0a0b8b 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -204,7 +204,7 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
btrfs_blocks_per_folio(fs_info, folio); \
\
btrfs_subpage_assert(fs_info, folio, start, len); \
- __start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \
+ __start_bit = offset_in_folio(folio, start) >> fs_info->sectorsize_bits; \
__start_bit += blocks_per_folio * btrfs_bitmap_nr_##name; \
__start_bit; \
})
@@ -666,7 +666,7 @@ IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked,
btrfs_blocks_per_folio(fs_info, folio); \
const struct btrfs_subpage *subpage = folio_get_private(folio); \
\
- ASSERT(blocks_per_folio < BITS_PER_LONG); \
+ ASSERT(blocks_per_folio <= BITS_PER_LONG); \
*dst = bitmap_read(subpage->bitmaps, \
blocks_per_folio * btrfs_bitmap_nr_##name, \
blocks_per_folio); \
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 7121d8c..7310e2f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -569,6 +569,10 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
break;
case Opt_commit_interval:
ctx->commit_interval = result.uint_32;
+ if (ctx->commit_interval > BTRFS_WARNING_COMMIT_INTERVAL) {
+ btrfs_warn(NULL, "excessive commit interval %u, use with care",
+ ctx->commit_interval);
+ }
if (ctx->commit_interval == 0)
ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
break;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43979891..2b66a61 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -2235,7 +2235,7 @@ int btrfs_verify_level_key(struct extent_buffer *eb,
btrfs_err(fs_info,
"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
eb->start, check->level, found_level);
- return -EIO;
+ return -EUCLEAN;
}
if (!check->has_first_key)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c8c21c5..8e6b6fed 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -733,82 +733,6 @@ const u8 *btrfs_sb_fsid_ptr(const struct btrfs_super_block *sb)
return has_metadata_uuid ? sb->metadata_uuid : sb->fsid;
}
-/*
- * We can have very weird soft links passed in.
- * One example is "/proc/self/fd/<fd>", which can be a soft link to
- * a block device.
- *
- * But it's never a good idea to use those weird names.
- * Here we check if the path (not following symlinks) is a good one inside
- * "/dev/".
- */
-static bool is_good_dev_path(const char *dev_path)
-{
- struct path path = { .mnt = NULL, .dentry = NULL };
- char *path_buf = NULL;
- char *resolved_path;
- bool is_good = false;
- int ret;
-
- if (!dev_path)
- goto out;
-
- path_buf = kmalloc(PATH_MAX, GFP_KERNEL);
- if (!path_buf)
- goto out;
-
- /*
- * Do not follow soft link, just check if the original path is inside
- * "/dev/".
- */
- ret = kern_path(dev_path, 0, &path);
- if (ret)
- goto out;
- resolved_path = d_path(&path, path_buf, PATH_MAX);
- if (IS_ERR(resolved_path))
- goto out;
- if (strncmp(resolved_path, "/dev/", strlen("/dev/")))
- goto out;
- is_good = true;
-out:
- kfree(path_buf);
- path_put(&path);
- return is_good;
-}
-
-static int get_canonical_dev_path(const char *dev_path, char *canonical)
-{
- struct path path = { .mnt = NULL, .dentry = NULL };
- char *path_buf = NULL;
- char *resolved_path;
- int ret;
-
- if (!dev_path) {
- ret = -EINVAL;
- goto out;
- }
-
- path_buf = kmalloc(PATH_MAX, GFP_KERNEL);
- if (!path_buf) {
- ret = -ENOMEM;
- goto out;
- }
-
- ret = kern_path(dev_path, LOOKUP_FOLLOW, &path);
- if (ret)
- goto out;
- resolved_path = d_path(&path, path_buf, PATH_MAX);
- if (IS_ERR(resolved_path)) {
- ret = PTR_ERR(resolved_path);
- goto out;
- }
- ret = strscpy(canonical, resolved_path, PATH_MAX);
-out:
- kfree(path_buf);
- path_put(&path);
- return ret;
-}
-
static bool is_same_device(struct btrfs_device *device, const char *new_path)
{
struct path old = { .mnt = NULL, .dentry = NULL };
@@ -1513,23 +1437,12 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
bool new_device_added = false;
struct btrfs_device *device = NULL;
struct file *bdev_file;
- char *canonical_path = NULL;
u64 bytenr;
dev_t devt;
int ret;
lockdep_assert_held(&uuid_mutex);
- if (!is_good_dev_path(path)) {
- canonical_path = kmalloc(PATH_MAX, GFP_KERNEL);
- if (canonical_path) {
- ret = get_canonical_dev_path(path, canonical_path);
- if (ret < 0) {
- kfree(canonical_path);
- canonical_path = NULL;
- }
- }
- }
/*
* Avoid an exclusive open here, as the systemd-udev may initiate the
* device scan which may race with the user's mount or mkfs command,
@@ -1574,8 +1487,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
goto free_disk_super;
}
- device = device_list_add(canonical_path ? : path, disk_super,
- &new_device_added);
+ device = device_list_add(path, disk_super, &new_device_added);
if (!IS_ERR(device) && new_device_added)
btrfs_free_stale_devices(device->devt, device);
@@ -1584,7 +1496,6 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
error_bdev_put:
fput(bdev_file);
- kfree(canonical_path);
return device;
}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index fb8b8b2..4a3e02b 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1277,7 +1277,7 @@ struct zone_info {
static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
struct zone_info *info, unsigned long *active,
- struct btrfs_chunk_map *map)
+ struct btrfs_chunk_map *map, bool new)
{
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
struct btrfs_device *device;
@@ -1307,6 +1307,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
return 0;
}
+ ASSERT(!new || btrfs_dev_is_empty_zone(device, info->physical));
+
/* This zone will be used for allocation, so mark this zone non-empty. */
btrfs_dev_clear_zone_empty(device, info->physical);
@@ -1319,6 +1321,18 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
* to determine the allocation offset within the zone.
*/
WARN_ON(!IS_ALIGNED(info->physical, fs_info->zone_size));
+
+ if (new) {
+ sector_t capacity;
+
+ capacity = bdev_zone_capacity(device->bdev, info->physical >> SECTOR_SHIFT);
+ up_read(&dev_replace->rwsem);
+ info->alloc_offset = 0;
+ info->capacity = capacity << SECTOR_SHIFT;
+
+ return 0;
+ }
+
nofs_flag = memalloc_nofs_save();
ret = btrfs_get_dev_zone(device, info->physical, &zone);
memalloc_nofs_restore(nofs_flag);
@@ -1588,7 +1602,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
}
for (i = 0; i < map->num_stripes; i++) {
- ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map);
+ ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map, new);
if (ret)
goto out;
@@ -1659,7 +1673,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
* stripe.
*/
cache->alloc_offset = cache->zone_capacity;
- ret = 0;
}
out:
diff --git a/fs/buffer.c b/fs/buffer.c
index c7abb4a0..7ba1807 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -176,18 +176,8 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
}
EXPORT_SYMBOL(end_buffer_write_sync);
-/*
- * Various filesystems appear to want __find_get_block to be non-blocking.
- * But it's the page lock which protects the buffers. To get around this,
- * we get exclusion from try_to_free_buffers with the blockdev mapping's
- * i_private_lock.
- *
- * Hack idea: for the blockdev mapping, i_private_lock contention
- * may be quite high. This code could TryLock the page, and if that
- * succeeds, there is no need to take i_private_lock.
- */
static struct buffer_head *
-__find_get_block_slow(struct block_device *bdev, sector_t block)
+__find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic)
{
struct address_space *bd_mapping = bdev->bd_mapping;
const int blkbits = bd_mapping->host->i_blkbits;
@@ -204,10 +194,28 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
if (IS_ERR(folio))
goto out;
- spin_lock(&bd_mapping->i_private_lock);
+ /*
+ * Folio lock protects the buffers. Callers that cannot block
+ * will fallback to serializing vs try_to_free_buffers() via
+ * the i_private_lock.
+ */
+ if (atomic)
+ spin_lock(&bd_mapping->i_private_lock);
+ else
+ folio_lock(folio);
+
head = folio_buffers(folio);
if (!head)
goto out_unlock;
+ /*
+ * Upon a noref migration, the folio lock serializes here;
+ * otherwise bail.
+ */
+ if (test_bit_acquire(BH_Migrate, &head->b_state)) {
+ WARN_ON(!atomic);
+ goto out_unlock;
+ }
+
bh = head;
do {
if (!buffer_mapped(bh))
@@ -236,7 +244,10 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
1 << blkbits);
}
out_unlock:
- spin_unlock(&bd_mapping->i_private_lock);
+ if (atomic)
+ spin_unlock(&bd_mapping->i_private_lock);
+ else
+ folio_unlock(folio);
folio_put(folio);
out:
return ret;
@@ -656,7 +667,9 @@ EXPORT_SYMBOL(generic_buffers_fsync);
void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize)
{
- struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
+ struct buffer_head *bh;
+
+ bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
write_dirty_buffer(bh, 0);
@@ -1207,10 +1220,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh)
/* FIXME: do we need to set this in both places? */
if (bh->b_folio && bh->b_folio->mapping)
mapping_set_error(bh->b_folio->mapping, -EIO);
- if (bh->b_assoc_map) {
+ if (bh->b_assoc_map)
mapping_set_error(bh->b_assoc_map, -EIO);
- errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
- }
}
EXPORT_SYMBOL(mark_buffer_write_io_error);
@@ -1386,16 +1397,18 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
/*
* Perform a pagecache lookup for the matching buffer. If it's there, refresh
* it in the LRU and mark it as accessed. If it is not present then return
- * NULL
+ * NULL. Atomic context callers may also return NULL if the buffer is being
+ * migrated; similarly the page is not marked accessed either.
*/
-struct buffer_head *
-__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+static struct buffer_head *
+find_get_block_common(struct block_device *bdev, sector_t block,
+ unsigned size, bool atomic)
{
struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
if (bh == NULL) {
/* __find_get_block_slow will mark the page accessed */
- bh = __find_get_block_slow(bdev, block);
+ bh = __find_get_block_slow(bdev, block, atomic);
if (bh)
bh_lru_install(bh);
} else
@@ -1403,8 +1416,23 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
return bh;
}
+
+struct buffer_head *
+__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+{
+ return find_get_block_common(bdev, block, size, true);
+}
EXPORT_SYMBOL(__find_get_block);
+/* same as __find_get_block() but allows sleeping contexts */
+struct buffer_head *
+__find_get_block_nonatomic(struct block_device *bdev, sector_t block,
+ unsigned size)
+{
+ return find_get_block_common(bdev, block, size, false);
+}
+EXPORT_SYMBOL(__find_get_block_nonatomic);
+
/**
* bdev_getblk - Get a buffer_head in a block device's buffer cache.
* @bdev: The block device.
@@ -1422,7 +1450,12 @@ EXPORT_SYMBOL(__find_get_block);
struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
- struct buffer_head *bh = __find_get_block(bdev, block, size);
+ struct buffer_head *bh;
+
+ if (gfpflags_allow_blocking(gfp))
+ bh = __find_get_block_nonatomic(bdev, block, size);
+ else
+ bh = __find_get_block(bdev, block, size);
might_alloc(gfp);
if (bh)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 6ac2bd5..06cd296 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2367,7 +2367,7 @@ static int fill_fscrypt_truncate(struct inode *inode,
/* Try to writeback the dirty pagecaches */
if (issued & (CEPH_CAP_FILE_BUFFER)) {
- loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SHIFT - 1;
+ loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SIZE - 1;
ret = filemap_write_and_wait_range(inode->i_mapping,
orig_pos, lend);
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 4fa0a01..60c7cc4 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -150,10 +150,10 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio)
io->rq->bio.bi_iter.bi_sector = io->dev.m_pa >> 9;
attached = 0;
}
- if (!attached++)
- erofs_onlinefolio_split(folio);
if (!bio_add_folio(&io->rq->bio, folio, len, cur))
goto io_retry;
+ if (!attached++)
+ erofs_onlinefolio_split(folio);
io->dev.m_pa += len;
}
cur += len;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index cadec6b..da6ee7c 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -357,7 +357,6 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
enum {
Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
Opt_device, Opt_fsid, Opt_domain_id, Opt_directio,
- Opt_err
};
static const struct constant_table erofs_param_cache_strategy[] = {
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 5c061aa..b8e6b76 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -79,9 +79,6 @@ struct z_erofs_pcluster {
/* L: whether partial decompression or not */
bool partial;
- /* L: indicate several pageofs_outs or not */
- bool multibases;
-
/* L: whether extra buffer allocations are best-effort */
bool besteffort;
@@ -1046,8 +1043,6 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
break;
erofs_onlinefolio_split(folio);
- if (f->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
- f->pcl->multibases = true;
if (f->pcl->length < offset + end - map->m_la) {
f->pcl->length = offset + end - map->m_la;
f->pcl->pageofs_out = map->m_la & ~PAGE_MASK;
@@ -1093,7 +1088,6 @@ struct z_erofs_backend {
struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES];
struct super_block *sb;
struct z_erofs_pcluster *pcl;
-
/* pages with the longest decompressed length for deduplication */
struct page **decompressed_pages;
/* pages to keep the compressed data */
@@ -1102,6 +1096,8 @@ struct z_erofs_backend {
struct list_head decompressed_secondary_bvecs;
struct page **pagepool;
unsigned int onstack_used, nr_pages;
+ /* indicate if temporary copies should be preserved for later use */
+ bool keepxcpy;
};
struct z_erofs_bvec_item {
@@ -1112,18 +1108,20 @@ struct z_erofs_bvec_item {
static void z_erofs_do_decompressed_bvec(struct z_erofs_backend *be,
struct z_erofs_bvec *bvec)
{
+ int poff = bvec->offset + be->pcl->pageofs_out;
struct z_erofs_bvec_item *item;
- unsigned int pgnr;
+ struct page **page;
- if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) &&
- (bvec->end == PAGE_SIZE ||
- bvec->offset + bvec->end == be->pcl->length)) {
- pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT;
- DBG_BUGON(pgnr >= be->nr_pages);
- if (!be->decompressed_pages[pgnr]) {
- be->decompressed_pages[pgnr] = bvec->page;
+ if (!(poff & ~PAGE_MASK) && (bvec->end == PAGE_SIZE ||
+ bvec->offset + bvec->end == be->pcl->length)) {
+ DBG_BUGON((poff >> PAGE_SHIFT) >= be->nr_pages);
+ page = be->decompressed_pages + (poff >> PAGE_SHIFT);
+ if (!*page) {
+ *page = bvec->page;
return;
}
+ } else {
+ be->keepxcpy = true;
}
/* (cold path) one pcluster is requested multiple times */
@@ -1289,7 +1287,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
.alg = pcl->algorithmformat,
.inplace_io = overlapped,
.partial_decoding = pcl->partial,
- .fillgaps = pcl->multibases,
+ .fillgaps = be->keepxcpy,
.gfp = pcl->besteffort ? GFP_KERNEL :
GFP_NOWAIT | __GFP_NORETRY
}, be->pagepool);
@@ -1346,7 +1344,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
pcl->length = 0;
pcl->partial = true;
- pcl->multibases = false;
pcl->besteffort = false;
pcl->bvset.nextpage = NULL;
pcl->vcnt = 0;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 4bc264b..d4dbffde 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -2111,9 +2111,10 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
write_unlock_irq(&ep->lock);
- if (!eavail && ep_schedule_timeout(to))
- timed_out = !schedule_hrtimeout_range(to, slack,
- HRTIMER_MODE_ABS);
+ if (!eavail)
+ timed_out = !ep_schedule_timeout(to) ||
+ !schedule_hrtimeout_range(to, slack,
+ HRTIMER_MODE_ABS);
__set_current_state(TASK_RUNNING);
/*
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 38bc8d7..e7ecc7c 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -691,7 +691,8 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
if (!bh || !buffer_uptodate(bh))
/*
* If the block is not in the buffer cache, then it
- * must have been written out.
+ * must have been written out, or, most unlikely, is
+ * being migrated - false failure should be OK here.
*/
goto out;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f88424c..1e98c5b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -6642,7 +6642,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
for (i = 0; i < count; i++) {
cond_resched();
if (is_metadata)
- bh = sb_find_get_block(inode->i_sb, block + i);
+ bh = sb_find_get_block_nonatomic(inode->i_sb,
+ block + i);
ext4_forget(handle, is_metadata, inode, bh, block + i);
}
}
diff --git a/fs/file.c b/fs/file.c
index dc3f7e1..3a31466 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -26,7 +26,7 @@
#include "internal.h"
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
+static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
{
/*
* If the reference count was already in the dead zone, then this
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 0cf0fddb..1467f67 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -345,7 +345,8 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
bh = bh_in;
if (!bh) {
- bh = __find_get_block(bdev, blocknr, journal->j_blocksize);
+ bh = __find_get_block_nonatomic(bdev, blocknr,
+ journal->j_blocksize);
if (bh)
BUFFER_TRACE(bh, "found on hash");
}
@@ -355,7 +356,8 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
/* If there is a different buffer_head lying around in
* memory anywhere... */
- bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize);
+ bh2 = __find_get_block_nonatomic(bdev, blocknr,
+ journal->j_blocksize);
if (bh2) {
/* ... and it has RevokeValid status... */
if (bh2 != bh && buffer_revokevalid(bh2))
@@ -464,7 +466,8 @@ void jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
* state machine will get very upset later on. */
if (need_cancel) {
struct buffer_head *bh2;
- bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size);
+ bh2 = __find_get_block_nonatomic(bh->b_bdev, bh->b_blocknr,
+ bh->b_size);
if (bh2) {
if (bh2 != bh)
clear_buffer_revoked(bh2);
@@ -492,9 +495,9 @@ void jbd2_clear_buffer_revoked_flags(journal_t *journal)
struct jbd2_revoke_record_s *record;
struct buffer_head *bh;
record = (struct jbd2_revoke_record_s *)list_entry;
- bh = __find_get_block(journal->j_fs_dev,
- record->blocknr,
- journal->j_blocksize);
+ bh = __find_get_block_nonatomic(journal->j_fs_dev,
+ record->blocknr,
+ journal->j_blocksize);
if (bh) {
clear_buffer_revoked(bh);
__brelse(bh);
diff --git a/fs/namespace.c b/fs/namespace.c
index d9ca80d..1b466c5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -787,15 +787,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
return 0;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
- smp_mb(); // see mntput_no_expire()
+ smp_mb(); // see mntput_no_expire() and do_umount()
if (likely(!read_seqretry(&mount_lock, seq)))
return 0;
- if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
- mnt_add_count(mnt, -1);
- return 1;
- }
lock_mount_hash();
- if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+ if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) {
mnt_add_count(mnt, -1);
unlock_mount_hash();
return 1;
@@ -2048,6 +2044,7 @@ static int do_umount(struct mount *mnt, int flags)
umount_tree(mnt, UMOUNT_PROPAGATE);
retval = 0;
} else {
+ smp_mb(); // paired with __legitimize_mnt()
shrink_submounts(mnt);
retval = -EBUSY;
if (!propagate_mount_busy(mnt, 2)) {
@@ -2826,56 +2823,62 @@ static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
struct vfsmount *mnt = path->mnt;
struct dentry *dentry;
struct mountpoint *mp = ERR_PTR(-ENOENT);
+ struct path under = {};
for (;;) {
- struct mount *m;
+ struct mount *m = real_mount(mnt);
if (beneath) {
- m = real_mount(mnt);
+ path_put(&under);
read_seqlock_excl(&mount_lock);
- dentry = dget(m->mnt_mountpoint);
+ under.mnt = mntget(&m->mnt_parent->mnt);
+ under.dentry = dget(m->mnt_mountpoint);
read_sequnlock_excl(&mount_lock);
+ dentry = under.dentry;
} else {
dentry = path->dentry;
}
inode_lock(dentry->d_inode);
- if (unlikely(cant_mount(dentry))) {
- inode_unlock(dentry->d_inode);
- goto out;
- }
-
namespace_lock();
- if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) {
+ if (unlikely(cant_mount(dentry) || !is_mounted(mnt)))
+ break; // not to be mounted on
+
+ if (beneath && unlikely(m->mnt_mountpoint != dentry ||
+ &m->mnt_parent->mnt != under.mnt)) {
namespace_unlock();
inode_unlock(dentry->d_inode);
- goto out;
+ continue; // got moved
}
mnt = lookup_mnt(path);
- if (likely(!mnt))
+ if (unlikely(mnt)) {
+ namespace_unlock();
+ inode_unlock(dentry->d_inode);
+ path_put(path);
+ path->mnt = mnt;
+ path->dentry = dget(mnt->mnt_root);
+ continue; // got overmounted
+ }
+ mp = get_mountpoint(dentry);
+ if (IS_ERR(mp))
break;
-
- namespace_unlock();
- inode_unlock(dentry->d_inode);
- if (beneath)
- dput(dentry);
- path_put(path);
- path->mnt = mnt;
- path->dentry = dget(mnt->mnt_root);
+ if (beneath) {
+ /*
+ * @under duplicates the references that will stay
+ * at least until namespace_unlock(), so the path_put()
+ * below is safe (and OK to do under namespace_lock -
+ * we are not dropping the final references here).
+ */
+ path_put(&under);
+ }
+ return mp;
}
-
- mp = get_mountpoint(dentry);
- if (IS_ERR(mp)) {
- namespace_unlock();
- inode_unlock(dentry->d_inode);
- }
-
-out:
+ namespace_unlock();
+ inode_unlock(dentry->d_inode);
if (beneath)
- dput(dentry);
-
+ path_put(&under);
return mp;
}
@@ -2886,14 +2889,11 @@ static inline struct mountpoint *lock_mount(struct path *path)
static void unlock_mount(struct mountpoint *where)
{
- struct dentry *dentry = where->m_dentry;
-
+ inode_unlock(where->m_dentry->d_inode);
read_seqlock_excl(&mount_lock);
put_mountpoint(where);
read_sequnlock_excl(&mount_lock);
-
namespace_unlock();
- inode_unlock(dentry->d_inode);
}
static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
@@ -3557,7 +3557,8 @@ static int can_move_mount_beneath(const struct path *from,
* @mnt_from itself. This defeats the whole purpose of mounting
* @mnt_from beneath @mnt_to.
*/
- if (propagation_would_overmount(parent_mnt_to, mnt_from, mp))
+ if (check_mnt(mnt_from) &&
+ propagation_would_overmount(parent_mnt_to, mnt_from, mp))
return -EINVAL;
return 0;
@@ -3715,15 +3716,14 @@ static int do_move_mount(struct path *old_path,
if (err)
goto out;
- if (is_anon_ns(ns))
- ns->mntns_flags &= ~MNTNS_PROPAGATING;
-
/* if the mount is moved, it should no longer be expire
* automatically */
list_del_init(&old->mnt_expire);
if (attached)
put_mountpoint(old_mp);
out:
+ if (is_anon_ns(ns))
+ ns->mntns_flags &= ~MNTNS_PROPAGATING;
unlock_mount(mp);
if (!err) {
if (attached) {
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 02c916a..6d63b95 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc)
if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
server->namelen = NFS2_MAXNAMLEN;
}
+ /* Linux 'subtree_check' borkenness mandates this setting */
+ server->fh_expire_type = NFS_FH_VOL_RENAME;
if (!(fattr->valid & NFS_ATTR_FATTR)) {
error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh,
@@ -1200,6 +1202,10 @@ void nfs_clients_init(struct net *net)
#if IS_ENABLED(CONFIG_NFS_V4)
idr_init(&nn->cb_ident_idr);
#endif
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+ INIT_LIST_HEAD(&nn->nfs4_data_server_cache);
+ spin_lock_init(&nn->nfs4_data_server_lock);
+#endif
spin_lock_init(&nn->nfs_client_lock);
nn->boot_time = ktime_get_real();
memset(&nn->rpcstats, 0, sizeof(nn->rpcstats));
@@ -1216,6 +1222,9 @@ void nfs_clients_exit(struct net *net)
nfs_cleanup_cb_ident_idr(net);
WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+ WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache));
+#endif
}
#ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index bd23fc7..d0e0b43 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
unblock_revalidate(new_dentry);
}
+static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry,
+ struct dentry *new_dentry)
+{
+ struct nfs_server *server = NFS_SB(old_dentry->d_sb);
+
+ if (old_dentry->d_parent != new_dentry->d_parent)
+ return false;
+ if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE)
+ return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN);
+ return true;
+}
+
/*
* RENAME
* FIXME: Some nfsds, like the Linux user space nfsd, may generate a
@@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
}
- if (S_ISREG(old_inode->i_mode))
+ if (S_ISREG(old_inode->i_mode) &&
+ nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry))
nfs_sync_inode(old_inode);
task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
must_unblock ? nfs_unblock_rename : NULL);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f32f8d7..48d8971 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -757,7 +757,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_direct_req *dreq = hdr->dreq;
struct nfs_commit_info cinfo;
- struct nfs_page *req = nfs_list_entry(hdr->pages.next);
struct inode *inode = dreq->inode;
int flags = NFS_ODIRECT_DONE;
@@ -786,6 +785,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
spin_unlock(&inode->i_lock);
while (!list_empty(&hdr->pages)) {
+ struct nfs_page *req;
req = nfs_list_entry(hdr->pages.next);
nfs_list_remove_request(req);
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 4fa304f..29d9234 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -76,6 +76,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
struct page *scratch;
struct list_head dsaddrs;
struct nfs4_pnfs_ds_addr *da;
+ struct net *net = server->nfs_client->cl_net;
/* set up xdr stream */
scratch = alloc_page(gfp_flags);
@@ -159,8 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
mp_count = be32_to_cpup(p); /* multipath count */
for (j = 0; j < mp_count; j++) {
- da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
- &stream, gfp_flags);
+ da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
@@ -170,7 +170,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
goto out_err_free_deviceid;
}
- dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+ dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
if (!dsaddr->ds_list[i])
goto out_err_drain_dsaddrs;
trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 61ad269..e6909ca 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1329,7 +1329,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
hdr->args.offset, hdr->args.count,
&hdr->res.op_status, OP_READ,
task->tk_status);
- trace_ff_layout_read_error(hdr);
+ trace_ff_layout_read_error(hdr, task->tk_status);
}
err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1502,7 +1502,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
hdr->args.offset, hdr->args.count,
&hdr->res.op_status, OP_WRITE,
task->tk_status);
- trace_ff_layout_write_error(hdr);
+ trace_ff_layout_write_error(hdr, task->tk_status);
}
err = ff_layout_async_handle_error(task, hdr->args.context->state,
@@ -1551,7 +1551,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
data->args.offset, data->args.count,
&data->res.op_status, OP_COMMIT,
task->tk_status);
- trace_ff_layout_commit_error(data);
+ trace_ff_layout_commit_error(data, task->tk_status);
}
err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e58bedf..4a304cf 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
struct nfs4_pnfs_ds_addr *da;
struct nfs4_ff_layout_ds *new_ds = NULL;
struct nfs4_ff_ds_version *ds_versions = NULL;
+ struct net *net = server->nfs_client->cl_net;
u32 mp_count;
u32 version_count;
__be32 *p;
@@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
for (i = 0; i < mp_count; i++) {
/* multipath ds */
- da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
- &stream, gfp_flags);
+ da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags);
if (da)
list_add_tail(&da->da_node, &dsaddrs);
}
@@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
new_ds->ds_versions = ds_versions;
new_ds->ds_versions_cnt = version_count;
- new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+ new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags);
if (!new_ds->ds)
goto out_err_drain_dsaddrs;
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 5c21cae..4ec952f 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -278,6 +278,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
if (IS_ERR(new))
return NULL;
+ rcu_read_lock();
/* try to swap in the pointer */
spin_lock(&clp->cl_uuid.lock);
nf = rcu_dereference_protected(*pnf, 1);
@@ -287,7 +288,6 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
rcu_assign_pointer(*pnf, nf);
}
spin_unlock(&clp->cl_uuid.lock);
- rcu_read_lock();
}
nf = nfs_local_file_get(nf);
rcu_read_unlock();
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index a68b2160..6ba3ea3 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -31,7 +31,11 @@ struct nfs_net {
unsigned short nfs_callback_tcpport;
unsigned short nfs_callback_tcpport6;
int cb_users[NFS4_MAX_MINOR_VERSION + 1];
-#endif
+#endif /* CONFIG_NFS_V4 */
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+ struct list_head nfs4_data_server_cache;
+ spinlock_t nfs4_data_server_lock;
+#endif /* CONFIG_NFS_V4_1 */
struct nfs_netns_client *nfs_client;
spinlock_t nfs_client_lock;
ktime_t boot_time;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 18d8f65..a126eb3 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -104,7 +104,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu)
switch (status) {
case 0:
- status = nfs_refresh_inode(inode, res.fattr);
+ nfs_refresh_inode(inode, res.fattr);
break;
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 970f28d..b1d2122 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -671,6 +671,15 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
struct nfs_client *clp = server->nfs_client;
int ret;
+ if ((task->tk_rpc_status == -ENETDOWN ||
+ task->tk_rpc_status == -ENETUNREACH) &&
+ task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+ exception->delay = 0;
+ exception->recovering = 0;
+ exception->retry = 0;
+ return -EIO;
+ }
+
ret = nfs4_do_handle_exception(server, errorcode, exception);
if (exception->delay) {
int ret2 = nfs4_exception_should_retrans(server, exception);
@@ -7074,10 +7083,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
struct nfs4_unlockdata *p;
struct nfs4_state *state = lsp->ls_state;
struct inode *inode = state->inode;
+ struct nfs_lock_context *l_ctx;
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (p == NULL)
return NULL;
+ l_ctx = nfs_get_lock_context(ctx);
+ if (!IS_ERR(l_ctx)) {
+ p->l_ctx = l_ctx;
+ } else {
+ kfree(p);
+ return NULL;
+ }
p->arg.fh = NFS_FH(inode);
p->arg.fl = &p->fl;
p->arg.seqid = seqid;
@@ -7085,7 +7102,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
p->lsp = lsp;
/* Ensure we don't close file until we're done freeing locks! */
p->ctx = get_nfs_open_context(ctx);
- p->l_ctx = nfs_get_lock_context(ctx);
locks_init_lock(&p->fl);
locks_copy_lock(&p->fl, fl);
p->server = NFS_SERVER(inode);
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index bc67fe6..deab4c0 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -2051,13 +2051,15 @@ TRACE_EVENT(fl_getdevinfo,
DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
TP_PROTO(
- const struct nfs_pgio_header *hdr
+ const struct nfs_pgio_header *hdr,
+ int error
),
- TP_ARGS(hdr),
+ TP_ARGS(hdr, error),
TP_STRUCT__entry(
__field(unsigned long, error)
+ __field(unsigned long, nfs_error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -2073,7 +2075,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
TP_fast_assign(
const struct inode *inode = hdr->inode;
- __entry->error = hdr->res.op_status;
+ __entry->error = -error;
+ __entry->nfs_error = hdr->res.op_status;
__entry->fhandle = nfs_fhandle_hash(hdr->args.fh);
__entry->fileid = NFS_FILEID(inode);
__entry->dev = inode->i_sb->s_dev;
@@ -2088,7 +2091,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
TP_printk(
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
- "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s",
+ "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s "
+ "nfs_error=%lu (%s)",
-__entry->error,
show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -2096,28 +2100,32 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event,
__entry->fhandle,
__entry->offset, __entry->count,
__entry->stateid_seq, __entry->stateid_hash,
- __get_str(dstaddr)
+ __get_str(dstaddr), __entry->nfs_error,
+ show_nfs4_status(__entry->nfs_error)
)
);
#define DEFINE_NFS4_FLEXFILES_IO_EVENT(name) \
DEFINE_EVENT(nfs4_flexfiles_io_event, name, \
TP_PROTO( \
- const struct nfs_pgio_header *hdr \
+ const struct nfs_pgio_header *hdr, \
+ int error \
), \
- TP_ARGS(hdr))
+ TP_ARGS(hdr, error))
DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_read_error);
DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_write_error);
TRACE_EVENT(ff_layout_commit_error,
TP_PROTO(
- const struct nfs_commit_data *data
+ const struct nfs_commit_data *data,
+ int error
),
- TP_ARGS(data),
+ TP_ARGS(data, error),
TP_STRUCT__entry(
__field(unsigned long, error)
+ __field(unsigned long, nfs_error)
__field(dev_t, dev)
__field(u32, fhandle)
__field(u64, fileid)
@@ -2131,7 +2139,8 @@ TRACE_EVENT(ff_layout_commit_error,
TP_fast_assign(
const struct inode *inode = data->inode;
- __entry->error = data->res.op_status;
+ __entry->error = -error;
+ __entry->nfs_error = data->res.op_status;
__entry->fhandle = nfs_fhandle_hash(data->args.fh);
__entry->fileid = NFS_FILEID(inode);
__entry->dev = inode->i_sb->s_dev;
@@ -2142,14 +2151,15 @@ TRACE_EVENT(ff_layout_commit_error,
TP_printk(
"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
- "offset=%llu count=%u dstaddr=%s",
+ "offset=%llu count=%u dstaddr=%s nfs_error=%lu (%s)",
-__entry->error,
show_nfs4_status(__entry->error),
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
__entry->offset, __entry->count,
- __get_str(dstaddr)
+ __get_str(dstaddr), __entry->nfs_error,
+ show_nfs4_status(__entry->nfs_error)
)
);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5f58271..3adb7d0 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -745,6 +745,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
return remaining;
}
+static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo)
+{
+ struct pnfs_layout_segment *lseg;
+
+ list_for_each_entry(lseg, &lo->plh_return_segs, pls_list)
+ pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
+}
+
static void
pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo,
struct list_head *free_me,
@@ -1246,21 +1254,15 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
static void
pnfs_layoutreturn_retry_later_locked(struct pnfs_layout_hdr *lo,
const nfs4_stateid *arg_stateid,
- const struct pnfs_layout_range *range)
+ const struct pnfs_layout_range *range,
+ struct list_head *freeme)
{
- const struct pnfs_layout_segment *lseg;
- u32 seq = be32_to_cpu(arg_stateid->seqid);
-
if (pnfs_layout_is_valid(lo) &&
- nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) {
- list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) {
- if (pnfs_seqid_is_newer(lseg->pls_seq, seq) ||
- !pnfs_should_free_range(&lseg->pls_range, range))
- continue;
- pnfs_set_plh_return_info(lo, range->iomode, seq);
- break;
- }
- }
+ nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+ pnfs_reset_return_info(lo);
+ else
+ pnfs_mark_layout_stateid_invalid(lo, freeme);
+ pnfs_clear_layoutreturn_waitbit(lo);
}
void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
@@ -1268,11 +1270,12 @@ void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo,
const struct pnfs_layout_range *range)
{
struct inode *inode = lo->plh_inode;
+ LIST_HEAD(freeme);
spin_lock(&inode->i_lock);
- pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range);
- pnfs_clear_layoutreturn_waitbit(lo);
+ pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range, &freeme);
spin_unlock(&inode->i_lock);
+ pnfs_free_lseg_list(&freeme);
}
void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
@@ -1292,6 +1295,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
pnfs_free_returned_lsegs(lo, &freeme, range, seq);
pnfs_set_layout_stateid(lo, stateid, NULL, true);
+ pnfs_reset_return_info(lo);
} else
pnfs_mark_layout_stateid_invalid(lo, &freeme);
out_unlock:
@@ -1661,6 +1665,18 @@ int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
/* Was there an RPC level error? If not, retry */
if (task->tk_rpc_status == 0)
break;
+ /*
+ * Is there a fatal network level error?
+ * If so release the layout, but flag the error.
+ */
+ if ((task->tk_rpc_status == -ENETDOWN ||
+ task->tk_rpc_status == -ENETUNREACH) &&
+ task->tk_flags & RPC_TASK_NETUNREACH_FATAL) {
+ *ret = 0;
+ (*respp)->lrs_present = 0;
+ retval = -EIO;
+ break;
+ }
/* If the call was not sent, let caller handle it */
if (!RPC_WAS_SENT(task))
return 0;
@@ -1695,6 +1711,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct inode *inode = args->inode;
const nfs4_stateid *res_stateid = NULL;
struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
+ LIST_HEAD(freeme);
switch (ret) {
case -NFS4ERR_BADSESSION:
@@ -1703,9 +1720,9 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
case -NFS4ERR_NOMATCHING_LAYOUT:
spin_lock(&inode->i_lock);
pnfs_layoutreturn_retry_later_locked(lo, &args->stateid,
- &args->range);
- pnfs_clear_layoutreturn_waitbit(lo);
+ &args->range, &freeme);
spin_unlock(&inode->i_lock);
+ pnfs_free_lseg_list(&freeme);
break;
case 0:
if (res->lrs_present)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 30d2613..91ff877 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -60,6 +60,7 @@ struct nfs4_pnfs_ds {
struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */
char *ds_remotestr; /* comma sep list of addrs */
struct list_head ds_addrs;
+ const struct net *ds_net;
struct nfs_client *ds_clp;
refcount_t ds_count;
unsigned long ds_state;
@@ -415,7 +416,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode,
int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
-struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net,
+ struct list_head *dsaddrs,
gfp_t gfp_flags);
void nfs4_pnfs_v3_ds_connect_unload(void);
int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index dbef837..91ef486 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -16,6 +16,7 @@
#include "nfs4session.h"
#include "internal.h"
#include "pnfs.h"
+#include "netns.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
@@ -504,14 +505,14 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
/*
* Data server cache
*
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
+ * Data servers can be mapped to different device ids, but should
+ * never be shared between net namespaces.
+ *
+ * nfs4_pnfs_ds reference counting:
* - set to 1 on allocation
* - incremented when a device id maps a data server already in the cache.
* - decremented when deviceid is removed from the cache.
*/
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
/* Debug routines */
static void
@@ -604,11 +605,11 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1,
* Lookup DS by addresses. nfs4_ds_cache_lock is held
*/
static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
+_data_server_lookup_locked(const struct nfs_net *nn, const struct list_head *dsaddrs)
{
struct nfs4_pnfs_ds *ds;
- list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+ list_for_each_entry(ds, &nn->nfs4_data_server_cache, ds_node)
if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
return ds;
return NULL;
@@ -653,10 +654,11 @@ static void destroy_ds(struct nfs4_pnfs_ds *ds)
void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
{
- if (refcount_dec_and_lock(&ds->ds_count,
- &nfs4_ds_cache_lock)) {
+ struct nfs_net *nn = net_generic(ds->ds_net, nfs_net_id);
+
+ if (refcount_dec_and_lock(&ds->ds_count, &nn->nfs4_data_server_lock)) {
list_del_init(&ds->ds_node);
- spin_unlock(&nfs4_ds_cache_lock);
+ spin_unlock(&nn->nfs4_data_server_lock);
destroy_ds(ds);
}
}
@@ -716,8 +718,9 @@ nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
* uncached and return cached struct nfs4_pnfs_ds.
*/
struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
+nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags)
{
+ struct nfs_net *nn = net_generic(net, nfs_net_id);
struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
char *remotestr;
@@ -733,16 +736,17 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
/* this is only used for debugging, so it's ok if its NULL */
remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
- spin_lock(&nfs4_ds_cache_lock);
- tmp_ds = _data_server_lookup_locked(dsaddrs);
+ spin_lock(&nn->nfs4_data_server_lock);
+ tmp_ds = _data_server_lookup_locked(nn, dsaddrs);
if (tmp_ds == NULL) {
INIT_LIST_HEAD(&ds->ds_addrs);
list_splice_init(dsaddrs, &ds->ds_addrs);
ds->ds_remotestr = remotestr;
refcount_set(&ds->ds_count, 1);
INIT_LIST_HEAD(&ds->ds_node);
+ ds->ds_net = net;
ds->ds_clp = NULL;
- list_add(&ds->ds_node, &nfs4_data_server_cache);
+ list_add(&ds->ds_node, &nn->nfs4_data_server_cache);
dprintk("%s add new data server %s\n", __func__,
ds->ds_remotestr);
} else {
@@ -754,7 +758,7 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
refcount_read(&tmp_ds->ds_count));
ds = tmp_ds;
}
- spin_unlock(&nfs4_ds_cache_lock);
+ spin_unlock(&nn->nfs4_data_server_lock);
out:
return ds;
}
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index cb01ea8..d0bcf74 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
int blocksize;
int err;
- down_write(&nilfs->ns_sem);
-
blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
if (!blocksize) {
nilfs_err(sb, "unable to set blocksize");
@@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
set_nilfs_init(nilfs);
err = 0;
out:
- up_write(&nilfs->ns_sem);
return err;
failed_sbh:
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index f2d840a..87f861e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1961,12 +1961,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
return -EINVAL;
if (mark_cmd == FAN_MARK_FLUSH) {
- if (mark_type == FAN_MARK_MOUNT)
- fsnotify_clear_vfsmount_marks_by_group(group);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- fsnotify_clear_sb_marks_by_group(group);
- else
- fsnotify_clear_inode_marks_by_group(group);
+ fsnotify_clear_marks_by_group(group, obj_type);
return 0;
}
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b8ac85b..821cb78 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
if (IS_ERR(folios[numfolios])) {
ret = PTR_ERR(folios[numfolios]);
mlog_errno(ret);
+ folios[numfolios] = NULL;
goto out;
}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index f1b4b3e..e5f58ff 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
struct ocfs2_recovery_map *rm;
mutex_init(&osb->recovery_lock);
- osb->disable_recovery = 0;
+ osb->recovery_state = OCFS2_REC_ENABLED;
osb->recovery_thread_task = NULL;
init_waitqueue_head(&osb->recovery_event);
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
return 0;
}
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
{
- mb();
return osb->recovery_thread_task != NULL;
}
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+ enum ocfs2_recovery_state state)
+{
+ mutex_lock(&osb->recovery_lock);
+ /*
+ * If recovery thread is not running, we can directly transition to
+ * final state.
+ */
+ if (!ocfs2_recovery_thread_running(osb)) {
+ osb->recovery_state = state + 1;
+ goto out_lock;
+ }
+ osb->recovery_state = state;
+ /* Wait for recovery thread to acknowledge state transition */
+ wait_event_cmd(osb->recovery_event,
+ !ocfs2_recovery_thread_running(osb) ||
+ osb->recovery_state >= state + 1,
+ mutex_unlock(&osb->recovery_lock),
+ mutex_lock(&osb->recovery_lock));
+out_lock:
+ mutex_unlock(&osb->recovery_lock);
+
+ /*
+ * At this point we know that no more recovery work can be queued so
+ * wait for any recovery completion work to complete.
+ */
+ if (osb->ocfs2_wq)
+ flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+ ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
+}
+
void ocfs2_recovery_exit(struct ocfs2_super *osb)
{
struct ocfs2_recovery_map *rm;
/* disable any new recovery threads and wait for any currently
* running ones to exit. Do this before setting the vol_state. */
- mutex_lock(&osb->recovery_lock);
- osb->disable_recovery = 1;
- mutex_unlock(&osb->recovery_lock);
- wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
-
- /* At this point, we know that no more recovery threads can be
- * launched, so wait for any recovery completion work to
- * complete. */
- if (osb->ocfs2_wq)
- flush_workqueue(osb->ocfs2_wq);
+ ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
/*
* Now that recovery is shut down, and the osb is about to be
@@ -1249,7 +1271,7 @@ static int ocfs2_force_read_journal(struct inode *inode)
}
for (i = 0; i < p_blocks; i++, p_blkno++) {
- bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+ bh = __find_get_block_nonatomic(osb->sb->s_bdev, p_blkno,
osb->sb->s_blocksize);
/* block not cached. */
if (!bh)
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
}
}
restart:
+ if (quota_enabled) {
+ mutex_lock(&osb->recovery_lock);
+ /* Confirm that recovery thread will no longer recover quotas */
+ if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+ osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+ wake_up(&osb->recovery_event);
+ }
+ if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+ quota_enabled = 0;
+ mutex_unlock(&osb->recovery_lock);
+ }
+
status = ocfs2_super_lock(osb, 1);
if (status < 0) {
mlog_errno(status);
@@ -1569,27 +1603,29 @@ static int __ocfs2_recovery_thread(void *arg)
ocfs2_free_replay_slots(osb);
osb->recovery_thread_task = NULL;
- mb(); /* sync with ocfs2_recovery_thread_running */
+ if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+ osb->recovery_state = OCFS2_REC_DISABLED;
wake_up(&osb->recovery_event);
mutex_unlock(&osb->recovery_lock);
- if (quota_enabled)
- kfree(rm_quota);
+ kfree(rm_quota);
return status;
}
void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
{
+ int was_set = -1;
+
mutex_lock(&osb->recovery_lock);
+ if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+ was_set = ocfs2_recovery_map_set(osb, node_num);
trace_ocfs2_recovery_thread(node_num, osb->node_num,
- osb->disable_recovery, osb->recovery_thread_task,
- osb->disable_recovery ?
- -1 : ocfs2_recovery_map_set(osb, node_num));
+ osb->recovery_state, osb->recovery_thread_task, was_set);
- if (osb->disable_recovery)
+ if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
goto out;
if (osb->recovery_thread_task)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35..6397170 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
int ocfs2_recovery_init(struct ocfs2_super *osb);
void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
void ocfs2_free_replay_slots(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c5276..6aaa94c 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
void ocfs2_initialize_journal_triggers(struct super_block *sb,
struct ocfs2_triggers triggers[]);
+enum ocfs2_recovery_state {
+ OCFS2_REC_ENABLED = 0,
+ OCFS2_REC_QUOTA_WANT_DISABLE,
+ /*
+ * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+ * ocfs2_recovery_disable_quota() to work.
+ */
+ OCFS2_REC_QUOTA_DISABLED,
+ OCFS2_REC_WANT_DISABLE,
+ /*
+ * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+ */
+ OCFS2_REC_DISABLED,
+};
+
struct ocfs2_journal;
struct ocfs2_slot_info;
struct ocfs2_recovery_map;
@@ -370,7 +385,7 @@ struct ocfs2_super
struct ocfs2_recovery_map *recovery_map;
struct ocfs2_replay_map *replay_map;
struct task_struct *recovery_thread_task;
- int disable_recovery;
+ enum ocfs2_recovery_state recovery_state;
wait_queue_head_t checkpoint_event;
struct ocfs2_journal *journal;
unsigned long osb_commit_interval;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d88..e272429 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
/* Sync changes in local quota file into global quota file and
* reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
static int ocfs2_recover_local_quota_file(struct inode *lqinode,
int type,
struct ocfs2_quota_recovery *rec)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
{
unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
LOCAL_GROUP_QUOTA_SYSTEM_INODE };
- struct super_block *sb = osb->sb;
struct ocfs2_local_disk_dqinfo *ldinfo;
struct buffer_head *bh;
handle_t *handle;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
"slot %u\n", osb->dev_str, slot_num);
- down_read(&sb->s_umount);
for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
if (list_empty(&(rec->r_list[type])))
continue;
@@ -677,7 +674,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
break;
}
out:
- up_read(&sb->s_umount);
kfree(rec);
return status;
}
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
/*
- * s_umount held in exclusive mode protects us against racing with
- * recovery thread...
+ * ocfs2_dismount_volume() has already aborted quota recovery...
*/
if (oinfo->dqi_rec) {
ocfs2_free_quota_recovery(oinfo->dqi_rec);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f..6ac4dcd 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
ac, cl);
- if (PTR_ERR(bg_bh) == -ENOSPC)
+ if (PTR_ERR(bg_bh) == -ENOSPC) {
+ ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
bg_bh = ocfs2_block_group_alloc_discontig(handle,
alloc_inode,
ac, cl);
+ }
if (IS_ERR(bg_bh)) {
status = PTR_ERR(bg_bh);
bg_bh = NULL;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
{
int status;
u16 chain;
+ u32 contig_bits;
u64 next_group;
struct inode *alloc_inode = ac->ac_inode;
struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
status = -ENOSPC;
/* for now, the chain search is a bit simplistic. We just use
* the 1st group with any empty bits. */
- while ((status = ac->ac_group_search(alloc_inode, group_bh,
- bits_wanted, min_bits,
- ac->ac_max_block,
- res)) == -ENOSPC) {
+ while (1) {
+ if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+ contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+ if (!contig_bits)
+ contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+ le16_to_cpu(bg->bg_bits), 0);
+ if (bits_wanted > contig_bits && contig_bits >= min_bits)
+ bits_wanted = contig_bits;
+ }
+
+ status = ac->ac_group_search(alloc_inode, group_bh,
+ bits_wanted, min_bits,
+ ac->ac_max_block, res);
+ if (status != -ENOSPC)
+ break;
if (!bg->bg_next_group)
break;
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
victim = ocfs2_find_victim_chain(cl);
ac->ac_chain = victim;
+search:
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
res, &bits_left);
if (!status) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
}
}
+ /* Chains can't supply the bits_wanted contiguous space.
+ * We should switch to using every single bit when allocating
+ * from the global bitmap. */
+ if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+ status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+ ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+ ac->ac_chain = victim;
+ goto search;
+ }
+
set_hint:
if (status != -ENOSPC) {
/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
- && ac->ac_which != OCFS2_AC_USE_MAIN);
+ && ac->ac_which != OCFS2_AC_USE_MAIN
+ && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
WARN_ON(min_clusters > 1);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b83..bcf2ed4 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
#define OCFS2_AC_USE_MAIN 2
#define OCFS2_AC_USE_INODE 3
#define OCFS2_AC_USE_META 4
+#define OCFS2_AC_USE_MAIN_DISCONTIG 5
u32 ac_which;
/* these are used by the chain search */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8bb5022..3d25339 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
/* Orphan scan should be stopped as early as possible */
ocfs2_orphan_scan_stop(osb);
+ /* Stop quota recovery so that we can disable quotas */
+ ocfs2_recovery_disable_quota(osb);
+
ocfs2_disable_quotas(osb);
/* All dquots should be freed by now */
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 5ac743c..08a6f37 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -32,12 +32,13 @@ static int orangefs_writepage_locked(struct folio *folio,
len = i_size_read(inode);
if (folio->private) {
wr = folio->private;
- WARN_ON(wr->pos >= len);
off = wr->pos;
- if (off + wr->len > len)
+ if ((off + wr->len > len) && (off <= len))
wlen = len - off;
else
wlen = wr->len;
+ if (wlen == 0)
+ wlen = wr->len;
} else {
WARN_ON(1);
off = folio_pos(folio);
@@ -46,8 +47,6 @@ static int orangefs_writepage_locked(struct folio *folio,
if (wlen > len - off)
wlen = len - off;
}
- /* Should've been handled in orangefs_invalidate_folio. */
- WARN_ON(off == len || off + wlen > len);
WARN_ON(wlen == 0);
bvec_set_folio(&bv, folio, wlen, offset_in_folio(folio, off));
@@ -320,6 +319,8 @@ static int orangefs_write_begin(struct file *file,
wr->len += len;
goto okay;
} else {
+ wr->pos = pos;
+ wr->len = len;
ret = orangefs_launder_folio(folio);
if (ret)
return ret;
diff --git a/fs/pnode.c b/fs/pnode.c
index 7a062a5..fb77427 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -150,7 +150,7 @@ static struct mount *propagation_next(struct mount *m,
struct mount *origin)
{
/* are there any slaves of this mount? */
- if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
return first_slave(m);
while (1) {
@@ -174,7 +174,7 @@ static struct mount *skip_propagation_subtree(struct mount *m,
* Advance m such that propagation_next will not return
* the slaves of m.
*/
- if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
m = last_slave(m);
return m;
@@ -185,7 +185,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
while (1) {
while (1) {
struct mount *next;
- if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list))
+ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
return first_slave(m);
next = next_peer(m);
if (m->mnt_group_id == origin->mnt_group_id) {
@@ -226,11 +226,15 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
struct mount *child;
int type;
/* skip ones added by this propagate_mnt() */
- if (IS_MNT_PROPAGATED(m))
+ if (IS_MNT_NEW(m))
return 0;
- /* skip if mountpoint isn't covered by it */
+ /* skip if mountpoint isn't visible in m */
if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))
return 0;
+ /* skip if m is in the anon_ns we are emptying */
+ if (m->mnt_ns->mntns_flags & MNTNS_PROPAGATING)
+ return 0;
+
if (peers(m, last_dest)) {
type = CL_MAKE_SHARED;
} else {
@@ -380,9 +384,6 @@ bool propagation_would_overmount(const struct mount *from,
if (!IS_MNT_SHARED(from))
return false;
- if (IS_MNT_PROPAGATED(to))
- return false;
-
if (to->mnt.mnt_root != mp->m_dentry)
return false;
diff --git a/fs/pnode.h b/fs/pnode.h
index ddafe0d..34b6247 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -12,7 +12,7 @@
#define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
#define IS_MNT_SLAVE(m) ((m)->mnt_master)
-#define IS_MNT_PROPAGATED(m) (!(m)->mnt_ns || ((m)->mnt_ns->mntns_flags & MNTNS_PROPAGATING))
+#define IS_MNT_NEW(m) (!(m)->mnt_ns)
#define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
#define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index fe73862..240d82c 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -29,7 +29,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
{
struct cached_fid *cfid;
- spin_lock(&cfids->cfid_list_lock);
list_for_each_entry(cfid, &cfids->entries, entry) {
if (!strcmp(cfid->path, path)) {
/*
@@ -38,25 +37,20 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
* being deleted due to a lease break.
*/
if (!cfid->time || !cfid->has_lease) {
- spin_unlock(&cfids->cfid_list_lock);
return NULL;
}
kref_get(&cfid->refcount);
- spin_unlock(&cfids->cfid_list_lock);
return cfid;
}
}
if (lookup_only) {
- spin_unlock(&cfids->cfid_list_lock);
return NULL;
}
if (cfids->num_entries >= max_cached_dirs) {
- spin_unlock(&cfids->cfid_list_lock);
return NULL;
}
cfid = init_cached_dir(path);
if (cfid == NULL) {
- spin_unlock(&cfids->cfid_list_lock);
return NULL;
}
cfid->cfids = cfids;
@@ -74,7 +68,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
*/
cfid->has_lease = true;
- spin_unlock(&cfids->cfid_list_lock);
return cfid;
}
@@ -187,8 +180,10 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
if (!utf16_path)
return -ENOMEM;
+ spin_lock(&cfids->cfid_list_lock);
cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs);
if (cfid == NULL) {
+ spin_unlock(&cfids->cfid_list_lock);
kfree(utf16_path);
return -ENOENT;
}
@@ -197,7 +192,6 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
* Otherwise, it is either a new entry or laundromat worker removed it
* from @cfids->entries. Caller will put last reference if the latter.
*/
- spin_lock(&cfids->cfid_list_lock);
if (cfid->has_lease && cfid->time) {
spin_unlock(&cfids->cfid_list_lock);
*ret_cfid = cfid;
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index 18d67ab..1b79fe0 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -1266,10 +1266,9 @@ typedef struct smb_com_query_information_rsp {
typedef struct smb_com_setattr_req {
struct smb_hdr hdr; /* wct = 8 */
__le16 attr;
- __le16 time_low;
- __le16 time_high;
+ __le32 last_write_time;
__le16 reserved[5]; /* must be zero */
- __u16 ByteCount;
+ __le16 ByteCount;
__u8 BufferFormat; /* 4 = ASCII */
unsigned char fileName[];
} __attribute__((packed)) SETATTR_REQ;
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 59f6fdf..ecf774a 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -395,6 +395,10 @@ extern int CIFSSMBQFSUnixInfo(const unsigned int xid, struct cifs_tcon *tcon);
extern int CIFSSMBQFSPosixInfo(const unsigned int xid, struct cifs_tcon *tcon,
struct kstatfs *FSData);
+extern int SMBSetInformation(const unsigned int xid, struct cifs_tcon *tcon,
+ const char *fileName, __le32 attributes, __le64 write_time,
+ const struct nls_table *nls_codepage,
+ struct cifs_sb_info *cifs_sb);
extern int CIFSSMBSetPathInfo(const unsigned int xid, struct cifs_tcon *tcon,
const char *fileName, const FILE_BASIC_INFO *data,
const struct nls_table *nls_codepage,
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 60cb264..f55457b 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -5171,6 +5171,63 @@ CIFSSMBSetFileSize(const unsigned int xid, struct cifs_tcon *tcon,
return rc;
}
+int
+SMBSetInformation(const unsigned int xid, struct cifs_tcon *tcon,
+ const char *fileName, __le32 attributes, __le64 write_time,
+ const struct nls_table *nls_codepage,
+ struct cifs_sb_info *cifs_sb)
+{
+ SETATTR_REQ *pSMB;
+ SETATTR_RSP *pSMBr;
+ struct timespec64 ts;
+ int bytes_returned;
+ int name_len;
+ int rc;
+
+ cifs_dbg(FYI, "In %s path %s\n", __func__, fileName);
+
+retry:
+ rc = smb_init(SMB_COM_SETATTR, 8, tcon, (void **) &pSMB,
+ (void **) &pSMBr);
+ if (rc)
+ return rc;
+
+ if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
+ name_len =
+ cifsConvertToUTF16((__le16 *) pSMB->fileName,
+ fileName, PATH_MAX, nls_codepage,
+ cifs_remap(cifs_sb));
+ name_len++; /* trailing null */
+ name_len *= 2;
+ } else {
+ name_len = copy_path_name(pSMB->fileName, fileName);
+ }
+ /* Only few attributes can be set by this command, others are not accepted by Win9x. */
+ pSMB->attr = cpu_to_le16(le32_to_cpu(attributes) &
+ (ATTR_READONLY | ATTR_HIDDEN | ATTR_SYSTEM | ATTR_ARCHIVE));
+ /* Zero write time value (in both NT and SETATTR formats) means to not change it. */
+ if (le64_to_cpu(write_time) != 0) {
+ ts = cifs_NTtimeToUnix(write_time);
+ pSMB->last_write_time = cpu_to_le32(ts.tv_sec);
+ }
+ pSMB->BufferFormat = 0x04;
+ name_len++; /* account for buffer type byte */
+ inc_rfc1001_len(pSMB, (__u16)name_len);
+ pSMB->ByteCount = cpu_to_le16(name_len);
+
+ rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
+ (struct smb_hdr *) pSMBr, &bytes_returned, 0);
+ if (rc)
+ cifs_dbg(FYI, "Send error in %s = %d\n", __func__, rc);
+
+ cifs_buf_release(pSMB);
+
+ if (rc == -EAGAIN)
+ goto retry;
+
+ return rc;
+}
+
/* Some legacy servers such as NT4 require that the file times be set on
an open handle, rather than by pathname - this is awkward due to
potential access conflicts on the open, but it is unavoidable for these
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index df976ce..6bf04d9 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -3753,28 +3753,7 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
}
}
- /*
- * Clamp the rsize/wsize mount arguments if they are too big for the server
- * and set the rsize/wsize to the negotiated values if not passed in by
- * the user on mount
- */
- if ((cifs_sb->ctx->wsize == 0) ||
- (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) {
- cifs_sb->ctx->wsize =
- round_down(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
- /*
- * in the very unlikely event that the server sent a max write size under PAGE_SIZE,
- * (which would get rounded down to 0) then reset wsize to absolute minimum eg 4096
- */
- if (cifs_sb->ctx->wsize == 0) {
- cifs_sb->ctx->wsize = PAGE_SIZE;
- cifs_dbg(VFS, "wsize too small, reset to minimum ie PAGE_SIZE, usually 4096\n");
- }
- }
- if ((cifs_sb->ctx->rsize == 0) ||
- (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
- cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
-
+ cifs_negotiate_iosize(server, cifs_sb->ctx, tcon);
/*
* The cookie is initialized from volume info returned above.
* Inside cifs_fscache_get_super_cookie it checks
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 9e8f404..950aa4f 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -160,10 +160,10 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq)
server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
rdata->server = server;
- if (cifs_sb->ctx->rsize == 0)
- cifs_sb->ctx->rsize =
- server->ops->negotiate_rsize(tlink_tcon(req->cfile->tlink),
- cifs_sb->ctx);
+ if (cifs_sb->ctx->rsize == 0) {
+ cifs_negotiate_rsize(server, cifs_sb->ctx,
+ tlink_tcon(req->cfile->tlink));
+ }
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
&size, &rdata->credits);
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 2980941..a634a34d 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1021,6 +1021,7 @@ static int smb3_reconfigure(struct fs_context *fc)
struct dentry *root = fc->root;
struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses;
+ unsigned int rsize = ctx->rsize, wsize = ctx->wsize;
char *new_password = NULL, *new_password2 = NULL;
bool need_recon = false;
int rc;
@@ -1103,11 +1104,8 @@ static int smb3_reconfigure(struct fs_context *fc)
STEAL_STRING(cifs_sb, ctx, iocharset);
/* if rsize or wsize not passed in on remount, use previous values */
- if (ctx->rsize == 0)
- ctx->rsize = cifs_sb->ctx->rsize;
- if (ctx->wsize == 0)
- ctx->wsize = cifs_sb->ctx->wsize;
-
+ ctx->rsize = rsize ? CIFS_ALIGN_RSIZE(fc, rsize) : cifs_sb->ctx->rsize;
+ ctx->wsize = wsize ? CIFS_ALIGN_WSIZE(fc, wsize) : cifs_sb->ctx->wsize;
smb3_cleanup_fs_context_contents(cifs_sb->ctx);
rc = smb3_fs_context_dup(cifs_sb->ctx, ctx);
@@ -1312,7 +1310,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
__func__);
goto cifs_parse_mount_err;
}
- ctx->bsize = result.uint_32;
+ ctx->bsize = CIFS_ALIGN_BSIZE(fc, result.uint_32);
ctx->got_bsize = true;
break;
case Opt_rasize:
@@ -1336,24 +1334,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
ctx->rasize = result.uint_32;
break;
case Opt_rsize:
- ctx->rsize = result.uint_32;
+ ctx->rsize = CIFS_ALIGN_RSIZE(fc, result.uint_32);
ctx->got_rsize = true;
ctx->vol_rsize = ctx->rsize;
break;
case Opt_wsize:
- ctx->wsize = result.uint_32;
+ ctx->wsize = CIFS_ALIGN_WSIZE(fc, result.uint_32);
ctx->got_wsize = true;
- if (ctx->wsize % PAGE_SIZE != 0) {
- ctx->wsize = round_down(ctx->wsize, PAGE_SIZE);
- if (ctx->wsize == 0) {
- ctx->wsize = PAGE_SIZE;
- cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE);
- } else {
- cifs_dbg(VFS,
- "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n",
- ctx->wsize, PAGE_SIZE);
- }
- }
ctx->vol_wsize = ctx->wsize;
break;
case Opt_acregmax:
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index d1d2924..9e83302 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -20,6 +20,21 @@
cifs_dbg(VFS, fmt, ## __VA_ARGS__); \
} while (0)
+static inline size_t cifs_io_align(struct fs_context *fc,
+ const char *name, size_t size)
+{
+ if (!size || !IS_ALIGNED(size, PAGE_SIZE)) {
+ cifs_errorf(fc, "unaligned %s, making it a multiple of %lu bytes\n",
+ name, PAGE_SIZE);
+ size = umax(round_down(size, PAGE_SIZE), PAGE_SIZE);
+ }
+ return size;
+}
+
+#define CIFS_ALIGN_WSIZE(_fc, _size) cifs_io_align(_fc, "wsize", _size)
+#define CIFS_ALIGN_RSIZE(_fc, _size) cifs_io_align(_fc, "rsize", _size)
+#define CIFS_ALIGN_BSIZE(_fc, _size) cifs_io_align(_fc, "bsize", _size)
+
enum smb_version {
Smb_1 = 1,
Smb_20,
@@ -361,4 +376,36 @@ static inline void cifs_mount_unlock(void)
mutex_unlock(&cifs_mount_mutex);
}
+static inline void cifs_negotiate_rsize(struct TCP_Server_Info *server,
+ struct smb3_fs_context *ctx,
+ struct cifs_tcon *tcon)
+{
+ unsigned int size;
+
+ size = umax(server->ops->negotiate_rsize(tcon, ctx), PAGE_SIZE);
+ if (ctx->rsize)
+ size = umax(umin(ctx->rsize, size), PAGE_SIZE);
+ ctx->rsize = round_down(size, PAGE_SIZE);
+}
+
+static inline void cifs_negotiate_wsize(struct TCP_Server_Info *server,
+ struct smb3_fs_context *ctx,
+ struct cifs_tcon *tcon)
+{
+ unsigned int size;
+
+ size = umax(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
+ if (ctx->wsize)
+ size = umax(umin(ctx->wsize, size), PAGE_SIZE);
+ ctx->wsize = round_down(size, PAGE_SIZE);
+}
+
+static inline void cifs_negotiate_iosize(struct TCP_Server_Info *server,
+ struct smb3_fs_context *ctx,
+ struct cifs_tcon *tcon)
+{
+ cifs_negotiate_rsize(server, ctx, tcon);
+ cifs_negotiate_wsize(server, ctx, tcon);
+}
+
#endif
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 50f9625..787d6bc 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -733,7 +733,10 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
else
cifs_buf_release(cfile->srch_inf.
ntwrk_buf_start);
+ /* Reset all pointers to the network buffer to prevent stale references */
cfile->srch_inf.ntwrk_buf_start = NULL;
+ cfile->srch_inf.srch_entries_start = NULL;
+ cfile->srch_inf.last_entry = NULL;
}
rc = initiate_cifs_search(xid, file, full_path);
if (rc) {
@@ -756,11 +759,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
rc = server->ops->query_dir_next(xid, tcon, &cfile->fid,
search_flags,
&cfile->srch_inf);
+ if (rc)
+ return -ENOENT;
/* FindFirst/Next set last_entry to NULL on malformed reply */
if (cfile->srch_inf.last_entry)
cifs_save_resume_key(cfile->srch_inf.last_entry, cfile);
- if (rc)
- return -ENOENT;
}
if (index_to_find < cfile->srch_inf.index_of_last_entry) {
/* we found the buffer that contains the entry */
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 0adeec6..b27a182 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -432,7 +432,7 @@ cifs_negotiate(const unsigned int xid,
}
static unsigned int
-cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
+smb1_negotiate_wsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
{
__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
struct TCP_Server_Info *server = tcon->ses->server;
@@ -467,7 +467,7 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
}
static unsigned int
-cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
+smb1_negotiate_rsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx)
{
__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
struct TCP_Server_Info *server = tcon->ses->server;
@@ -543,24 +543,104 @@ static int cifs_query_path_info(const unsigned int xid,
const char *full_path,
struct cifs_open_info_data *data)
{
- int rc;
+ int rc = -EOPNOTSUPP;
FILE_ALL_INFO fi = {};
+ struct cifs_search_info search_info = {};
+ bool non_unicode_wildcard = false;
data->reparse_point = false;
data->adjust_tz = false;
- /* could do find first instead but this returns more info */
- rc = CIFSSMBQPathInfo(xid, tcon, full_path, &fi, 0 /* not legacy */, cifs_sb->local_nls,
- cifs_remap(cifs_sb));
/*
- * BB optimize code so we do not make the above call when server claims
- * no NT SMB support and the above call failed at least once - set flag
- * in tcon or mount.
+ * First try CIFSSMBQPathInfo() function which returns more info
+ * (NumberOfLinks) than CIFSFindFirst() fallback function.
+ * Some servers like Win9x do not support SMB_QUERY_FILE_ALL_INFO over
+ * TRANS2_QUERY_PATH_INFORMATION, but supports it with filehandle over
+ * TRANS2_QUERY_FILE_INFORMATION (function CIFSSMBQFileInfo(). But SMB
+ * Open command on non-NT servers works only for files, does not work
+ * for directories. And moreover Win9x SMB server returns bogus data in
+ * SMB_QUERY_FILE_ALL_INFO Attributes field. So for non-NT servers,
+ * do not even use CIFSSMBQPathInfo() or CIFSSMBQFileInfo() function.
*/
- if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) {
+ if (tcon->ses->capabilities & CAP_NT_SMBS)
+ rc = CIFSSMBQPathInfo(xid, tcon, full_path, &fi, 0 /* not legacy */,
+ cifs_sb->local_nls, cifs_remap(cifs_sb));
+
+ /*
+ * Non-UNICODE variant of fallback functions below expands wildcards,
+ * so they cannot be used for querying paths with wildcard characters.
+ */
+ if (rc && !(tcon->ses->capabilities & CAP_UNICODE) && strpbrk(full_path, "*?\"><"))
+ non_unicode_wildcard = true;
+
+ /*
+ * Then fallback to CIFSFindFirst() which works also with non-NT servers
+ * but does not does not provide NumberOfLinks.
+ */
+ if ((rc == -EOPNOTSUPP || rc == -EINVAL) &&
+ !non_unicode_wildcard) {
+ if (!(tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find))
+ search_info.info_level = SMB_FIND_FILE_INFO_STANDARD;
+ else
+ search_info.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
+ rc = CIFSFindFirst(xid, tcon, full_path, cifs_sb, NULL,
+ CIFS_SEARCH_CLOSE_ALWAYS | CIFS_SEARCH_CLOSE_AT_END,
+ &search_info, false);
+ if (rc == 0) {
+ if (!(tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find)) {
+ FIND_FILE_STANDARD_INFO *di;
+ int offset = tcon->ses->server->timeAdj;
+
+ di = (FIND_FILE_STANDARD_INFO *)search_info.srch_entries_start;
+ fi.CreationTime = cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(
+ di->CreationDate, di->CreationTime, offset)));
+ fi.LastAccessTime = cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(
+ di->LastAccessDate, di->LastAccessTime, offset)));
+ fi.LastWriteTime = cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(
+ di->LastWriteDate, di->LastWriteTime, offset)));
+ fi.ChangeTime = fi.LastWriteTime;
+ fi.Attributes = cpu_to_le32(le16_to_cpu(di->Attributes));
+ fi.AllocationSize = cpu_to_le64(le32_to_cpu(di->AllocationSize));
+ fi.EndOfFile = cpu_to_le64(le32_to_cpu(di->DataSize));
+ } else {
+ FILE_FULL_DIRECTORY_INFO *di;
+
+ di = (FILE_FULL_DIRECTORY_INFO *)search_info.srch_entries_start;
+ fi.CreationTime = di->CreationTime;
+ fi.LastAccessTime = di->LastAccessTime;
+ fi.LastWriteTime = di->LastWriteTime;
+ fi.ChangeTime = di->ChangeTime;
+ fi.Attributes = di->ExtFileAttributes;
+ fi.AllocationSize = di->AllocationSize;
+ fi.EndOfFile = di->EndOfFile;
+ fi.EASize = di->EaSize;
+ }
+ fi.NumberOfLinks = cpu_to_le32(1);
+ fi.DeletePending = 0;
+ fi.Directory = !!(le32_to_cpu(fi.Attributes) & ATTR_DIRECTORY);
+ cifs_buf_release(search_info.ntwrk_buf_start);
+ } else if (!full_path[0]) {
+ /*
+ * CIFSFindFirst() does not work on root path if the
+ * root path was exported on the server from the top
+ * level path (drive letter).
+ */
+ rc = -EOPNOTSUPP;
+ }
+ }
+
+ /*
+ * If everything failed then fallback to the legacy SMB command
+ * SMB_COM_QUERY_INFORMATION which works with all servers, but
+ * provide just few information.
+ */
+ if ((rc == -EOPNOTSUPP || rc == -EINVAL) && !non_unicode_wildcard) {
rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls,
cifs_remap(cifs_sb));
data->adjust_tz = true;
+ } else if ((rc == -EOPNOTSUPP || rc == -EINVAL) && non_unicode_wildcard) {
+ /* Path with non-UNICODE wildcard character cannot exist. */
+ rc = -ENOENT;
}
if (!rc) {
@@ -639,6 +719,13 @@ static int cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
int rc;
FILE_ALL_INFO fi = {};
+ /*
+ * CIFSSMBQFileInfo() for non-NT servers returns bogus data in
+ * Attributes fields. So do not use this command for non-NT servers.
+ */
+ if (!(tcon->ses->capabilities & CAP_NT_SMBS))
+ return -EOPNOTSUPP;
+
if (cfile->symlink_target) {
data->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL);
if (!data->symlink_target)
@@ -809,6 +896,9 @@ smb_set_file_info(struct inode *inode, const char *full_path,
struct cifs_fid fid;
struct cifs_open_parms oparms;
struct cifsFileInfo *open_file;
+ FILE_BASIC_INFO new_buf;
+ struct cifs_open_info_data query_data;
+ __le64 write_time = buf->LastWriteTime;
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = NULL;
@@ -816,20 +906,58 @@ smb_set_file_info(struct inode *inode, const char *full_path,
/* if the file is already open for write, just use that fileid */
open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+
if (open_file) {
fid.netfid = open_file->fid.netfid;
netpid = open_file->pid;
tcon = tlink_tcon(open_file->tlink);
- goto set_via_filehandle;
+ } else {
+ tlink = cifs_sb_tlink(cifs_sb);
+ if (IS_ERR(tlink)) {
+ rc = PTR_ERR(tlink);
+ tlink = NULL;
+ goto out;
+ }
+ tcon = tlink_tcon(tlink);
}
- tlink = cifs_sb_tlink(cifs_sb);
- if (IS_ERR(tlink)) {
- rc = PTR_ERR(tlink);
- tlink = NULL;
- goto out;
+ /*
+ * Non-NT servers interprets zero time value in SMB_SET_FILE_BASIC_INFO
+ * over TRANS2_SET_FILE_INFORMATION as a valid time value. NT servers
+ * interprets zero time value as do not change existing value on server.
+ * API of ->set_file_info() callback expects that zero time value has
+ * the NT meaning - do not change. Therefore if server is non-NT and
+ * some time values in "buf" are zero, then fetch missing time values.
+ */
+ if (!(tcon->ses->capabilities & CAP_NT_SMBS) &&
+ (!buf->CreationTime || !buf->LastAccessTime ||
+ !buf->LastWriteTime || !buf->ChangeTime)) {
+ rc = cifs_query_path_info(xid, tcon, cifs_sb, full_path, &query_data);
+ if (rc) {
+ if (open_file) {
+ cifsFileInfo_put(open_file);
+ open_file = NULL;
+ }
+ goto out;
+ }
+ /*
+ * Original write_time from buf->LastWriteTime is preserved
+ * as SMBSetInformation() interprets zero as do not change.
+ */
+ new_buf = *buf;
+ buf = &new_buf;
+ if (!buf->CreationTime)
+ buf->CreationTime = query_data.fi.CreationTime;
+ if (!buf->LastAccessTime)
+ buf->LastAccessTime = query_data.fi.LastAccessTime;
+ if (!buf->LastWriteTime)
+ buf->LastWriteTime = query_data.fi.LastWriteTime;
+ if (!buf->ChangeTime)
+ buf->ChangeTime = query_data.fi.ChangeTime;
}
- tcon = tlink_tcon(tlink);
+
+ if (open_file)
+ goto set_via_filehandle;
rc = CIFSSMBSetPathInfo(xid, tcon, full_path, buf, cifs_sb->local_nls,
cifs_sb);
@@ -850,8 +978,45 @@ smb_set_file_info(struct inode *inode, const char *full_path,
.fid = &fid,
};
- cifs_dbg(FYI, "calling SetFileInfo since SetPathInfo for times not supported by this server\n");
- rc = CIFS_open(xid, &oparms, &oplock, NULL);
+ if (S_ISDIR(inode->i_mode) && !(tcon->ses->capabilities & CAP_NT_SMBS)) {
+ /* Opening directory path is not possible on non-NT servers. */
+ rc = -EOPNOTSUPP;
+ } else {
+ /*
+ * Use cifs_open_file() instead of CIFS_open() as the
+ * cifs_open_file() selects the correct function which
+ * works also on non-NT servers.
+ */
+ rc = cifs_open_file(xid, &oparms, &oplock, NULL);
+ /*
+ * Opening path for writing on non-NT servers is not
+ * possible when the read-only attribute is already set.
+ * Non-NT server in this case returns -EACCES. For those
+ * servers the only possible way how to clear the read-only
+ * bit is via SMB_COM_SETATTR command.
+ */
+ if (rc == -EACCES &&
+ (cinode->cifsAttrs & ATTR_READONLY) &&
+ le32_to_cpu(buf->Attributes) != 0 && /* 0 = do not change attrs */
+ !(le32_to_cpu(buf->Attributes) & ATTR_READONLY) &&
+ !(tcon->ses->capabilities & CAP_NT_SMBS))
+ rc = -EOPNOTSUPP;
+ }
+
+ /* Fallback to SMB_COM_SETATTR command when absolutelty needed. */
+ if (rc == -EOPNOTSUPP) {
+ cifs_dbg(FYI, "calling SetInformation since SetPathInfo for attrs/times not supported by this server\n");
+ rc = SMBSetInformation(xid, tcon, full_path,
+ buf->Attributes != 0 ? buf->Attributes : cpu_to_le32(cinode->cifsAttrs),
+ write_time,
+ cifs_sb->local_nls, cifs_sb);
+ if (rc == 0)
+ cinode->cifsAttrs = le32_to_cpu(buf->Attributes);
+ else
+ rc = -EACCES;
+ goto out;
+ }
+
if (rc != 0) {
if (rc == -EIO)
rc = -EINVAL;
@@ -859,6 +1024,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
}
netpid = current->tgid;
+ cifs_dbg(FYI, "calling SetFileInfo since SetPathInfo for attrs/times not supported by this server\n");
set_via_filehandle:
rc = CIFSSMBSetFileInfo(xid, tcon, buf, fid.netfid, netpid);
@@ -869,6 +1035,21 @@ smb_set_file_info(struct inode *inode, const char *full_path,
CIFSSMBClose(xid, tcon, fid.netfid);
else
cifsFileInfo_put(open_file);
+
+ /*
+ * Setting the read-only bit is not honered on non-NT servers when done
+ * via open-semantics. So for setting it, use SMB_COM_SETATTR command.
+ * This command works only after the file is closed, so use it only when
+ * operation was called without the filehandle.
+ */
+ if (open_file == NULL &&
+ !(tcon->ses->capabilities & CAP_NT_SMBS) &&
+ le32_to_cpu(buf->Attributes) & ATTR_READONLY) {
+ SMBSetInformation(xid, tcon, full_path,
+ buf->Attributes,
+ 0 /* do not change write time */,
+ cifs_sb->local_nls, cifs_sb);
+ }
out:
if (tlink != NULL)
cifs_put_tlink(tlink);
@@ -1161,8 +1342,8 @@ struct smb_version_operations smb1_operations = {
.check_trans2 = cifs_check_trans2,
.need_neg = cifs_need_neg,
.negotiate = cifs_negotiate,
- .negotiate_wsize = cifs_negotiate_wsize,
- .negotiate_rsize = cifs_negotiate_rsize,
+ .negotiate_wsize = smb1_negotiate_wsize,
+ .negotiate_rsize = smb1_negotiate_rsize,
.sess_setup = CIFS_SessSetup,
.logoff = CIFSSMBLogoff,
.tree_connect = CIFSTCon,
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 57d9bfba..2a3e46b 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -666,6 +666,8 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
/* smb2_parse_contexts() fills idata->fi.IndexNumber */
rc = smb2_parse_contexts(server, &rsp_iov[0], &oparms->fid->epoch,
oparms->fid->lease_key, &oplock, &idata->fi, NULL);
+ if (rc)
+ cifs_dbg(VFS, "rc: %d parsing context of compound op\n", rc);
}
for (i = 0; i < num_cmds; i++) {
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c4d52be..4e28632 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -2921,6 +2921,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
req->CreateContextsOffset = cpu_to_le32(
sizeof(struct smb2_create_req) +
iov[1].iov_len);
+ le32_add_cpu(&req->CreateContextsLength, iov[n_iov-1].iov_len);
pc_buf = iov[n_iov-1].iov_base;
}
@@ -2967,7 +2968,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
/* Eventually save off posix specific response info and timestamps */
err_free_rsp_buf:
- free_rsp_buf(resp_buftype, rsp);
+ free_rsp_buf(resp_buftype, rsp_iov.iov_base);
kfree(pc_buf);
err_free_req:
cifs_small_buf_release(req);
@@ -4092,12 +4093,8 @@ static void cifs_renegotiate_iosize(struct TCP_Server_Info *server,
return;
spin_lock(&tcon->sb_list_lock);
- list_for_each_entry(cifs_sb, &tcon->cifs_sb_list, tcon_sb_link) {
- cifs_sb->ctx->rsize =
- server->ops->negotiate_rsize(tcon, cifs_sb->ctx);
- cifs_sb->ctx->wsize =
- server->ops->negotiate_wsize(tcon, cifs_sb->ctx);
- }
+ list_for_each_entry(cifs_sb, &tcon->cifs_sb_list, tcon_sb_link)
+ cifs_negotiate_iosize(server, cifs_sb->ctx, tcon);
spin_unlock(&tcon->sb_list_lock);
}
diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 83caa38..b3d1210 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -550,7 +550,19 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob,
retval = -ENOMEM;
goto out;
}
- sess->user = user;
+
+ if (!sess->user) {
+ /* First successful authentication */
+ sess->user = user;
+ } else {
+ if (!ksmbd_compare_user(sess->user, user)) {
+ ksmbd_debug(AUTH, "different user tried to reuse session\n");
+ retval = -EPERM;
+ ksmbd_free_user(user);
+ goto out;
+ }
+ ksmbd_free_user(user);
+ }
memcpy(sess->sess_key, resp->payload, resp->session_key_len);
memcpy(out_blob, resp->payload + resp->session_key_len,
diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
index 3f45f28..9dec4c2 100644
--- a/fs/smb/server/mgmt/user_session.c
+++ b/fs/smb/server/mgmt/user_session.c
@@ -59,10 +59,12 @@ static void ksmbd_session_rpc_clear_list(struct ksmbd_session *sess)
struct ksmbd_session_rpc *entry;
long index;
+ down_write(&sess->rpc_lock);
xa_for_each(&sess->rpc_handle_list, index, entry) {
xa_erase(&sess->rpc_handle_list, index);
__session_rpc_close(sess, entry);
}
+ up_write(&sess->rpc_lock);
xa_destroy(&sess->rpc_handle_list);
}
@@ -92,7 +94,7 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
{
struct ksmbd_session_rpc *entry, *old;
struct ksmbd_rpc_command *resp;
- int method;
+ int method, id;
method = __rpc_method(rpc_name);
if (!method)
@@ -102,26 +104,29 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name)
if (!entry)
return -ENOMEM;
+ down_read(&sess->rpc_lock);
entry->method = method;
- entry->id = ksmbd_ipc_id_alloc();
- if (entry->id < 0)
+ entry->id = id = ksmbd_ipc_id_alloc();
+ if (id < 0)
goto free_entry;
- old = xa_store(&sess->rpc_handle_list, entry->id, entry, KSMBD_DEFAULT_GFP);
+ old = xa_store(&sess->rpc_handle_list, id, entry, KSMBD_DEFAULT_GFP);
if (xa_is_err(old))
goto free_id;
- resp = ksmbd_rpc_open(sess, entry->id);
+ resp = ksmbd_rpc_open(sess, id);
if (!resp)
goto erase_xa;
+ up_read(&sess->rpc_lock);
kvfree(resp);
- return entry->id;
+ return id;
erase_xa:
xa_erase(&sess->rpc_handle_list, entry->id);
free_id:
ksmbd_rpc_id_free(entry->id);
free_entry:
kfree(entry);
+ up_read(&sess->rpc_lock);
return -EINVAL;
}
@@ -129,9 +134,11 @@ void ksmbd_session_rpc_close(struct ksmbd_session *sess, int id)
{
struct ksmbd_session_rpc *entry;
+ down_write(&sess->rpc_lock);
entry = xa_erase(&sess->rpc_handle_list, id);
if (entry)
__session_rpc_close(sess, entry);
+ up_write(&sess->rpc_lock);
}
int ksmbd_session_rpc_method(struct ksmbd_session *sess, int id)
@@ -439,6 +446,7 @@ static struct ksmbd_session *__session_create(int protocol)
sess->sequence_number = 1;
rwlock_init(&sess->tree_conns_lock);
atomic_set(&sess->refcnt, 2);
+ init_rwsem(&sess->rpc_lock);
ret = __init_smb2_session(sess);
if (ret)
diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h
index f213483..c5749d6e 100644
--- a/fs/smb/server/mgmt/user_session.h
+++ b/fs/smb/server/mgmt/user_session.h
@@ -63,6 +63,7 @@ struct ksmbd_session {
rwlock_t tree_conns_lock;
atomic_t refcnt;
+ struct rw_semaphore rpc_lock;
};
static inline int test_session_flag(struct ksmbd_session *sess, int bit)
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 81a29857..03f606a 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1496,7 +1496,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) <
sizeof(struct create_lease_v2) - 4)
- return NULL;
+ goto err_out;
memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
lreq->req_state = lc->lcontext.LeaseState;
@@ -1512,7 +1512,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) <
sizeof(struct create_lease))
- return NULL;
+ goto err_out;
memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
lreq->req_state = lc->lcontext.LeaseState;
@@ -1521,6 +1521,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
lreq->version = 1;
}
return lreq;
+err_out:
+ kfree(lreq);
+ return NULL;
}
/**
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 57839f9..f2a2be8 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -633,6 +633,11 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls)
return name;
}
+ if (*name == '\0') {
+ kfree(name);
+ return ERR_PTR(-EINVAL);
+ }
+
if (*name == '\\') {
pr_err("not allow directory name included leading slash\n");
kfree(name);
@@ -1445,7 +1450,7 @@ static int ntlm_authenticate(struct ksmbd_work *work,
{
struct ksmbd_conn *conn = work->conn;
struct ksmbd_session *sess = work->sess;
- struct channel *chann = NULL;
+ struct channel *chann = NULL, *old;
struct ksmbd_user *user;
u64 prev_id;
int sz, rc;
@@ -1557,7 +1562,12 @@ static int ntlm_authenticate(struct ksmbd_work *work,
return -ENOMEM;
chann->conn = conn;
- xa_store(&sess->ksmbd_chann_list, (long)conn, chann, KSMBD_DEFAULT_GFP);
+ old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann,
+ KSMBD_DEFAULT_GFP);
+ if (xa_is_err(old)) {
+ kfree(chann);
+ return xa_err(old);
+ }
}
}
@@ -1602,11 +1612,6 @@ static int krb5_authenticate(struct ksmbd_work *work,
if (prev_sess_id && prev_sess_id != sess->id)
destroy_previous_session(conn, sess->user, prev_sess_id);
- if (sess->state == SMB2_SESSION_VALID) {
- ksmbd_free_user(sess->user);
- sess->user = NULL;
- }
-
retval = ksmbd_krb5_authenticate(sess, in_blob, in_len,
out_blob, &out_len);
if (retval) {
@@ -2249,10 +2254,6 @@ int smb2_session_logoff(struct ksmbd_work *work)
sess->state = SMB2_SESSION_EXPIRED;
up_write(&conn->session_lock);
- if (sess->user) {
- ksmbd_free_user(sess->user);
- sess->user = NULL;
- }
ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_SETUP);
rsp->StructureSize = cpu_to_le16(4);
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 391d07d..482eba0 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -426,6 +426,13 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos,
goto out;
}
+ if (v_len <= *pos) {
+ pr_err("stream write position %lld is out of bounds (stream length: %zd)\n",
+ *pos, v_len);
+ err = -EINVAL;
+ goto out;
+ }
+
if (v_len < size) {
wbuf = kvzalloc(size, KSMBD_DEFAULT_GFP);
if (!wbuf) {
diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index 1f8fa34..dfed6fc 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -661,21 +661,40 @@ __close_file_table_ids(struct ksmbd_file_table *ft,
bool (*skip)(struct ksmbd_tree_connect *tcon,
struct ksmbd_file *fp))
{
- unsigned int id;
- struct ksmbd_file *fp;
- int num = 0;
+ struct ksmbd_file *fp;
+ unsigned int id = 0;
+ int num = 0;
- idr_for_each_entry(ft->idr, fp, id) {
- if (skip(tcon, fp))
+ while (1) {
+ write_lock(&ft->lock);
+ fp = idr_get_next(ft->idr, &id);
+ if (!fp) {
+ write_unlock(&ft->lock);
+ break;
+ }
+
+ if (skip(tcon, fp) ||
+ !atomic_dec_and_test(&fp->refcount)) {
+ id++;
+ write_unlock(&ft->lock);
continue;
+ }
set_close_state_blocked_works(fp);
+ idr_remove(ft->idr, fp->volatile_id);
+ fp->volatile_id = KSMBD_NO_FID;
+ write_unlock(&ft->lock);
- if (!atomic_dec_and_test(&fp->refcount))
- continue;
+ down_write(&fp->f_ci->m_lock);
+ list_del_init(&fp->node);
+ up_write(&fp->f_ci->m_lock);
+
__ksmbd_close_fd(ft, fp);
+
num++;
+ id++;
}
+
return num;
}
diff --git a/fs/splice.c b/fs/splice.c
index 90d4642..4d6df08 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -45,7 +45,7 @@
* here if set to avoid blocking other users of this pipe if splice is
* being done on it.
*/
-static noinline void noinline pipe_clear_nowait(struct file *file)
+static noinline void pipe_clear_nowait(struct file *file)
{
fmode_t fmode = READ_ONCE(file->f_mode);
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 4f33a4a..b4071c9 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -115,7 +115,7 @@ void udf_truncate_tail_extent(struct inode *inode)
}
/* This inode entry is in-memory only and thus we don't have to mark
* the inode dirty */
- if (ret == 0)
+ if (ret >= 0)
iinfo->i_lenExtents = inode->i_size;
brelse(epos.bh);
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d80f943..22f4bf9 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
user_uffdio_copy = (struct uffdio_copy __user *) arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
user_uffdio_continue = (struct uffdio_continue __user *)arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_continue, user_uffdio_continue,
@@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
user_uffdio_poison = (struct uffdio_poison __user *)arg;
ret = -EAGAIN;
- if (atomic_read(&ctx->mmap_changing))
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+ return -EFAULT;
goto out;
+ }
ret = -EFAULT;
if (copy_from_user(&uffdio_poison, user_uffdio_poison,
@@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
user_uffdio_move = (struct uffdio_move __user *) arg;
- if (atomic_read(&ctx->mmap_changing))
- return -EAGAIN;
+ ret = -EAGAIN;
+ if (unlikely(atomic_read(&ctx->mmap_changing))) {
+ if (unlikely(put_user(ret, &user_uffdio_move->move)))
+ return -EFAULT;
+ goto out;
+ }
if (copy_from_user(&uffdio_move, user_uffdio_move,
/* don't copy "move" last field */
diff --git a/fs/xattr.c b/fs/xattr.c
index 02bee14..8ec5b02 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -703,7 +703,7 @@ static int path_setxattrat(int dfd, const char __user *pathname,
return error;
filename = getname_maybe_null(pathname, at_flags);
- if (!filename) {
+ if (!filename && dfd >= 0) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
error = -EBADF;
@@ -847,7 +847,7 @@ static ssize_t path_getxattrat(int dfd, const char __user *pathname,
return error;
filename = getname_maybe_null(pathname, at_flags);
- if (!filename) {
+ if (!filename && dfd >= 0) {
CLASS(fd, f)(dfd);
if (fd_empty(f))
return -EBADF;
@@ -1428,6 +1428,15 @@ static bool xattr_is_trusted(const char *name)
return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
+static bool xattr_is_maclabel(const char *name)
+{
+ const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+
+ return !strncmp(name, XATTR_SECURITY_PREFIX,
+ XATTR_SECURITY_PREFIX_LEN) &&
+ security_ismaclabel(suffix);
+}
+
/**
* simple_xattr_list - list all xattr objects
* @inode: inode from which to get the xattrs
@@ -1460,6 +1469,17 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
if (err)
return err;
+ err = security_inode_listsecurity(inode, buffer, remaining_size);
+ if (err < 0)
+ return err;
+
+ if (buffer) {
+ if (remaining_size < err)
+ return -ERANGE;
+ buffer += err;
+ }
+ remaining_size -= err;
+
read_lock(&xattrs->lock);
for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
xattr = rb_entry(rbp, struct simple_xattr, rb_node);
@@ -1468,6 +1488,10 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
if (!trusted && xattr_is_trusted(xattr->name))
continue;
+ /* skip MAC labels; these are provided by LSM above */
+ if (xattr_is_maclabel(xattr->name))
+ continue;
+
err = xattr_list_one(&buffer, &remaining_size, xattr->name);
if (err)
break;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index b2dd0c0..4a11ddc 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1149,7 +1149,7 @@ xfs_init_percpu_counters(
return 0;
free_freecounters:
- while (--i > 0)
+ while (--i >= 0)
percpu_counter_destroy(&mp->m_free[i].count);
percpu_counter_destroy(&mp->m_delalloc_rtextents);
free_delalloc:
@@ -2114,6 +2114,21 @@ xfs_fs_reconfigure(
if (error)
return error;
+ /* attr2 -> noattr2 */
+ if (xfs_has_noattr2(new_mp)) {
+ if (xfs_has_crc(mp)) {
+ xfs_warn(mp,
+ "attr2 is always enabled for a V5 filesystem - can't be changed.");
+ return -EINVAL;
+ }
+ mp->m_features &= ~XFS_FEAT_ATTR2;
+ mp->m_features |= XFS_FEAT_NOATTR2;
+ } else if (xfs_has_attr2(new_mp)) {
+ /* noattr2 -> attr2 */
+ mp->m_features &= ~XFS_FEAT_NOATTR2;
+ mp->m_features |= XFS_FEAT_ATTR2;
+ }
+
/* inode32 -> inode64 */
if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) {
mp->m_features &= ~XFS_FEAT_SMALL_INUMS;
@@ -2126,6 +2141,17 @@ xfs_fs_reconfigure(
mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount);
}
+ /*
+ * Now that mp has been modified according to the remount options, we
+ * do a final option validation with xfs_finish_flags() just like it is
+ * just like it is done during mount. We cannot use
+ * done during mount. We cannot use xfs_finish_flags() on new_mp as it
+ * contains only the user given options.
+ */
+ error = xfs_finish_flags(mp);
+ if (error)
+ return error;
+
/* ro -> rw */
if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) {
error = xfs_remount_rw(mp);
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 85a649f..67c328d 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -315,7 +315,7 @@ xfs_ail_splice(
}
/*
- * Delete the given item from the AIL. Return a pointer to the item.
+ * Delete the given item from the AIL.
*/
static void
xfs_ail_delete(
@@ -777,26 +777,28 @@ xfs_ail_update_finish(
}
/*
- * xfs_trans_ail_update - bulk AIL insertion operation.
+ * xfs_trans_ail_update_bulk - bulk AIL insertion operation.
*
- * @xfs_trans_ail_update takes an array of log items that all need to be
+ * @xfs_trans_ail_update_bulk takes an array of log items that all need to be
* positioned at the same LSN in the AIL. If an item is not in the AIL, it will
- * be added. Otherwise, it will be repositioned by removing it and re-adding
- * it to the AIL. If we move the first item in the AIL, update the log tail to
- * match the new minimum LSN in the AIL.
+ * be added. Otherwise, it will be repositioned by removing it and re-adding
+ * it to the AIL.
*
- * This function takes the AIL lock once to execute the update operations on
- * all the items in the array, and as such should not be called with the AIL
- * lock held. As a result, once we have the AIL lock, we need to check each log
- * item LSN to confirm it needs to be moved forward in the AIL.
+ * If we move the first item in the AIL, update the log tail to match the new
+ * minimum LSN in the AIL.
*
- * To optimise the insert operation, we delete all the items from the AIL in
- * the first pass, moving them into a temporary list, then splice the temporary
- * list into the correct position in the AIL. This avoids needing to do an
- * insert operation on every item.
+ * This function should be called with the AIL lock held.
*
- * This function must be called with the AIL lock held. The lock is dropped
- * before returning.
+ * To optimise the insert operation, we add all items to a temporary list, then
+ * splice this list into the correct position in the AIL.
+ *
+ * Items that are already in the AIL are first deleted from their current
+ * location before being added to the temporary list.
+ *
+ * This avoids needing to do an insert operation on every item.
+ *
+ * The AIL lock is dropped by xfs_ail_update_finish() before returning to
+ * the caller.
*/
void
xfs_trans_ail_update_bulk(
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 8c541ca..d613a40 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -170,7 +170,8 @@ bool
xfs_zoned_need_gc(
struct xfs_mount *mp)
{
- s64 available, free;
+ s64 available, free, threshold;
+ s32 remainder;
if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE))
return false;
@@ -183,7 +184,12 @@ xfs_zoned_need_gc(
return true;
free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS);
- if (available < mult_frac(free, mp->m_zonegc_low_space, 100))
+
+ threshold = div_s64_rem(free, 100, &remainder);
+ threshold = threshold * mp->m_zonegc_low_space +
+ remainder * div_s64(mp->m_zonegc_low_space, 100);
+
+ if (available < threshold)
return true;
return false;
@@ -801,7 +807,8 @@ xfs_zone_gc_write_chunk(
{
struct xfs_zone_gc_data *data = chunk->data;
struct xfs_mount *mp = chunk->ip->i_mount;
- unsigned int folio_offset = chunk->bio.bi_io_vec->bv_offset;
+ phys_addr_t bvec_paddr =
+ bvec_phys(bio_first_bvec_all(&chunk->bio));
struct xfs_gc_bio *split_chunk;
if (chunk->bio.bi_status)
@@ -816,7 +823,7 @@ xfs_zone_gc_write_chunk(
bio_reset(&chunk->bio, mp->m_rtdev_targp->bt_bdev, REQ_OP_WRITE);
bio_add_folio_nofail(&chunk->bio, chunk->scratch->folio, chunk->len,
- folio_offset);
+ offset_in_folio(chunk->scratch->folio, bvec_paddr));
while ((split_chunk = xfs_zone_gc_split_write(data, chunk)))
xfs_zone_gc_submit_write(data, split_chunk);
diff --git a/include/cxl/features.h b/include/cxl/features.h
index a3bb346..5f7f842 100644
--- a/include/cxl/features.h
+++ b/include/cxl/features.h
@@ -66,7 +66,7 @@ struct cxl_memdev;
#ifdef CONFIG_CXL_FEATURES
inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
int devm_cxl_setup_features(struct cxl_dev_state *cxlds);
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd);
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd);
#else
static inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
{
@@ -78,7 +78,8 @@ static inline int devm_cxl_setup_features(struct cxl_dev_state *cxlds)
return -EOPNOTSUPP;
}
-static inline int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+static inline int devm_cxl_setup_fwctl(struct device *host,
+ struct cxl_memdev *cxlmd)
{
return -EOPNOTSUPP;
}
diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index df120b4..eaf704d 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -89,6 +89,7 @@ struct drm_gpusvm_devmem_ops {
* @ops: Pointer to the operations structure for GPU SVM device memory
* @dpagemap: The struct drm_pagemap of the pages this allocation belongs to.
* @size: Size of device memory allocation
+ * @timeslice_expiration: Timeslice expiration in jiffies
*/
struct drm_gpusvm_devmem {
struct device *dev;
@@ -97,6 +98,7 @@ struct drm_gpusvm_devmem {
const struct drm_gpusvm_devmem_ops *ops;
struct drm_pagemap *dpagemap;
size_t size;
+ u64 timeslice_expiration;
};
/**
@@ -186,6 +188,31 @@ struct drm_gpusvm_notifier {
};
/**
+ * struct drm_gpusvm_range_flags - Structure representing a GPU SVM range flags
+ *
+ * @migrate_devmem: Flag indicating whether the range can be migrated to device memory
+ * @unmapped: Flag indicating if the range has been unmapped
+ * @partial_unmap: Flag indicating if the range has been partially unmapped
+ * @has_devmem_pages: Flag indicating if the range has devmem pages
+ * @has_dma_mapping: Flag indicating if the range has a DMA mapping
+ * @__flags: Flags for range in u16 form (used for READ_ONCE)
+ */
+struct drm_gpusvm_range_flags {
+ union {
+ struct {
+ /* All flags below must be set upon creation */
+ u16 migrate_devmem : 1;
+ /* All flags below must be set / cleared under notifier lock */
+ u16 unmapped : 1;
+ u16 partial_unmap : 1;
+ u16 has_devmem_pages : 1;
+ u16 has_dma_mapping : 1;
+ };
+ u16 __flags;
+ };
+};
+
+/**
* struct drm_gpusvm_range - Structure representing a GPU SVM range
*
* @gpusvm: Pointer to the GPU SVM structure
@@ -198,11 +225,6 @@ struct drm_gpusvm_notifier {
* @dpagemap: The struct drm_pagemap of the device pages we're dma-mapping.
* Note this is assuming only one drm_pagemap per range is allowed.
* @flags: Flags for range
- * @flags.migrate_devmem: Flag indicating whether the range can be migrated to device memory
- * @flags.unmapped: Flag indicating if the range has been unmapped
- * @flags.partial_unmap: Flag indicating if the range has been partially unmapped
- * @flags.has_devmem_pages: Flag indicating if the range has devmem pages
- * @flags.has_dma_mapping: Flag indicating if the range has a DMA mapping
*
* This structure represents a GPU SVM range used for tracking memory ranges
* mapped in a DRM device.
@@ -216,15 +238,7 @@ struct drm_gpusvm_range {
unsigned long notifier_seq;
struct drm_pagemap_device_addr *dma_addr;
struct drm_pagemap *dpagemap;
- struct {
- /* All flags below must be set upon creation */
- u16 migrate_devmem : 1;
- /* All flags below must be set / cleared under notifier lock */
- u16 unmapped : 1;
- u16 partial_unmap : 1;
- u16 has_devmem_pages : 1;
- u16 has_dma_mapping : 1;
- } flags;
+ struct drm_gpusvm_range_flags flags;
};
/**
@@ -283,17 +297,22 @@ struct drm_gpusvm {
* @check_pages_threshold: Check CPU pages for present if chunk is less than or
* equal to threshold. If not present, reduce chunk
* size.
+ * @timeslice_ms: The timeslice MS which in minimum time a piece of memory
+ * remains with either exclusive GPU or CPU access.
* @in_notifier: entering from a MMU notifier
* @read_only: operating on read-only memory
* @devmem_possible: possible to use device memory
+ * @devmem_only: use only device memory
*
* Context that is DRM GPUSVM is operating in (i.e. user arguments).
*/
struct drm_gpusvm_ctx {
unsigned long check_pages_threshold;
+ unsigned long timeslice_ms;
unsigned int in_notifier :1;
unsigned int read_only :1;
unsigned int devmem_possible :1;
+ unsigned int devmem_only :1;
};
int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
diff --git a/include/drm/ttm/ttm_backup.h b/include/drm/ttm/ttm_backup.h
index 24ad120..c33cba1 100644
--- a/include/drm/ttm/ttm_backup.h
+++ b/include/drm/ttm/ttm_backup.h
@@ -9,14 +9,12 @@
#include <linux/mm_types.h>
#include <linux/shmem_fs.h>
-struct ttm_backup;
-
/**
* ttm_backup_handle_to_page_ptr() - Convert handle to struct page pointer
* @handle: The handle to convert.
*
* Converts an opaque handle received from the
- * struct ttm_backoup_ops::backup_page() function to an (invalid)
+ * ttm_backup_backup_page() function to an (invalid)
* struct page pointer suitable for a struct page array.
*
* Return: An (invalid) struct page pointer.
@@ -45,8 +43,8 @@ static inline bool ttm_backup_page_ptr_is_handle(const struct page *page)
*
* Return: The handle that was previously used in
* ttm_backup_handle_to_page_ptr() to obtain a struct page pointer, suitable
- * for use as argument in the struct ttm_backup_ops drop() or
- * copy_backed_up_page() functions.
+ * for use as argument in the struct ttm_backup_drop() or
+ * ttm_backup_copy_page() functions.
*/
static inline unsigned long
ttm_backup_page_ptr_to_handle(const struct page *page)
@@ -55,20 +53,20 @@ ttm_backup_page_ptr_to_handle(const struct page *page)
return (unsigned long)page >> 1;
}
-void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle);
+void ttm_backup_drop(struct file *backup, pgoff_t handle);
-int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst,
+int ttm_backup_copy_page(struct file *backup, struct page *dst,
pgoff_t handle, bool intr);
s64
-ttm_backup_backup_page(struct ttm_backup *backup, struct page *page,
+ttm_backup_backup_page(struct file *backup, struct page *page,
bool writeback, pgoff_t idx, gfp_t page_gfp,
gfp_t alloc_gfp);
-void ttm_backup_fini(struct ttm_backup *backup);
+void ttm_backup_fini(struct file *backup);
u64 ttm_backup_bytes_avail(void);
-struct ttm_backup *ttm_backup_shmem_create(loff_t size);
+struct file *ttm_backup_shmem_create(loff_t size);
#endif
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 13cf47f..406437a 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -118,7 +118,7 @@ struct ttm_tt {
* ttm_tt_create() callback is responsible for assigning
* this field.
*/
- struct ttm_backup *backup;
+ struct file *backup;
/**
* @caching: The current caching state of the pages, see enum
* ttm_caching.
diff --git a/include/linux/bio.h b/include/linux/bio.h
index cafc7c2..b786ec5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -11,6 +11,7 @@
#include <linux/uio.h>
#define BIO_MAX_VECS 256U
+#define BIO_MAX_INLINE_VECS UIO_MAXIOV
struct queue_limits;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 678dc38..9a1f0ee 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -712,23 +712,6 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
(q->limits.features & BLK_FEAT_ZONED);
}
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
- return disk->nr_zones;
-}
-bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
- return 0;
-}
-static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
-{
- return false;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
{
if (!blk_queue_is_zoned(disk->queue))
@@ -736,11 +719,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
return sector >> ilog2(disk->queue->limits.chunk_sectors);
}
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
- return disk_nr_zones(bdev->bd_disk);
-}
-
static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
return bdev->bd_disk->queue->limits.max_open_zones;
@@ -847,6 +825,51 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
(sb->s_blocksize_bits - SECTOR_SHIFT);
}
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+ return disk->nr_zones;
+}
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
+
+/**
+ * disk_zone_capacity - returns the zone capacity of zone containing @sector
+ * @disk: disk to work with
+ * @sector: sector number within the querying zone
+ *
+ * Returns the zone capacity of a zone containing @sector. @sector can be any
+ * sector in the zone.
+ */
+static inline unsigned int disk_zone_capacity(struct gendisk *disk,
+ sector_t sector)
+{
+ sector_t zone_sectors = disk->queue->limits.chunk_sectors;
+
+ if (sector + zone_sectors >= get_capacity(disk))
+ return disk->last_zone_capacity;
+ return disk->zone_capacity;
+}
+static inline unsigned int bdev_zone_capacity(struct block_device *bdev,
+ sector_t pos)
+{
+ return disk_zone_capacity(bdev->bd_disk, pos);
+}
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+ return 0;
+}
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+ return false;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+ return disk_nr_zones(bdev->bd_disk);
+}
+
int bdev_disk_changed(struct gendisk *disk, bool invalidate);
void put_disk(struct gendisk *disk);
@@ -1614,6 +1637,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
}
+int bdev_validate_blocksize(struct block_device *bdev, int block_size);
int set_blocksize(struct file *file, int size);
int lookup_bdev(const char *pathname, dev_t *dev);
@@ -1670,10 +1694,6 @@ int bd_prepare_to_claim(struct block_device *bdev, void *holder,
const struct blk_holder_ops *hops);
void bd_abort_claiming(struct block_device *bdev, void *holder);
-/* just for blk-cgroup, don't use elsewhere */
-struct block_device *blkdev_get_no_open(dev_t dev);
-void blkdev_put_no_open(struct block_device *bdev);
-
struct block_device *I_BDEV(struct inode *inode);
struct block_device *file_bdev(struct file *bdev_file);
bool disk_live(struct gendisk *disk);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index f0a4ad7..0029ff88 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -34,6 +34,7 @@ enum bh_state_bits {
BH_Meta, /* Buffer contains metadata */
BH_Prio, /* Buffer should be submitted with REQ_PRIO */
BH_Defer_Completion, /* Defer AIO completion to workqueue */
+ BH_Migrate, /* Buffer is being migrated (norefs) */
BH_PrivateStart,/* not a state bit, but the first bit available
* for private allocation by other entities
@@ -222,6 +223,8 @@ void __wait_on_buffer(struct buffer_head *);
wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
unsigned size);
+struct buffer_head *__find_get_block_nonatomic(struct block_device *bdev,
+ sector_t block, unsigned size);
struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp);
void __brelse(struct buffer_head *);
@@ -397,6 +400,12 @@ sb_find_get_block(struct super_block *sb, sector_t block)
return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
}
+static inline struct buffer_head *
+sb_find_get_block_nonatomic(struct super_block *sb, sector_t block)
+{
+ return __find_get_block_nonatomic(sb->s_bdev, block, sb->s_blocksize);
+}
+
static inline void
map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block)
{
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index d55b300..50b14a5 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -490,9 +490,6 @@ extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
struct page **pages, u64 length,
u32 alignment, bool pages_from_pool,
bool own_pages);
-extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
- unsigned int which,
- struct ceph_pagelist *pagelist);
#ifdef CONFIG_BLOCK
void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
unsigned int which,
@@ -509,9 +506,6 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
unsigned int which, struct iov_iter *iter);
-extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
- unsigned int which,
- struct ceph_pagelist *pagelist);
extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e304954..3aa9551 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -78,6 +78,8 @@ extern ssize_t cpu_show_gds(struct device *dev,
extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
+ struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 400fee6..7a5b391 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -776,8 +776,8 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy,
int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy);
int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation);
+ unsigned int target_freq, unsigned int min,
+ unsigned int max, unsigned int relation);
int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
unsigned int freq);
@@ -840,12 +840,12 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
return best;
}
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
- unsigned int target_freq,
- bool efficiencies)
+static inline int find_index_l(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ unsigned int min, unsigned int max,
+ bool efficiencies)
{
- target_freq = clamp_val(target_freq, policy->min, policy->max);
+ target_freq = clamp_val(target_freq, min, max);
if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
return cpufreq_table_find_index_al(policy, target_freq,
@@ -855,6 +855,14 @@ static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
efficiencies);
}
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ bool efficiencies)
+{
+ return find_index_l(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
/* Find highest freq at or below target in a table in ascending order */
static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy,
unsigned int target_freq,
@@ -908,12 +916,12 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy,
return best;
}
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
- unsigned int target_freq,
- bool efficiencies)
+static inline int find_index_h(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ unsigned int min, unsigned int max,
+ bool efficiencies)
{
- target_freq = clamp_val(target_freq, policy->min, policy->max);
+ target_freq = clamp_val(target_freq, min, max);
if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
return cpufreq_table_find_index_ah(policy, target_freq,
@@ -923,6 +931,14 @@ static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
efficiencies);
}
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ bool efficiencies)
+{
+ return find_index_h(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
/* Find closest freq to target in a table in ascending order */
static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy,
unsigned int target_freq,
@@ -993,12 +1009,12 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy,
return best;
}
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
- unsigned int target_freq,
- bool efficiencies)
+static inline int find_index_c(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ unsigned int min, unsigned int max,
+ bool efficiencies)
{
- target_freq = clamp_val(target_freq, policy->min, policy->max);
+ target_freq = clamp_val(target_freq, min, max);
if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
return cpufreq_table_find_index_ac(policy, target_freq,
@@ -1008,7 +1024,17 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
efficiencies);
}
-static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx)
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ bool efficiencies)
+{
+ return find_index_c(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
+static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy,
+ unsigned int min, unsigned int max,
+ int idx)
{
unsigned int freq;
@@ -1017,11 +1043,13 @@ static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx)
freq = policy->freq_table[idx].frequency;
- return freq == clamp_val(freq, policy->min, policy->max);
+ return freq == clamp_val(freq, min, max);
}
static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
unsigned int target_freq,
+ unsigned int min,
+ unsigned int max,
unsigned int relation)
{
bool efficiencies = policy->efficiencies_available &&
@@ -1032,29 +1060,26 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
relation &= ~CPUFREQ_RELATION_E;
if (unlikely(policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED))
- return cpufreq_table_index_unsorted(policy, target_freq,
- relation);
+ return cpufreq_table_index_unsorted(policy, target_freq, min,
+ max, relation);
retry:
switch (relation) {
case CPUFREQ_RELATION_L:
- idx = cpufreq_table_find_index_l(policy, target_freq,
- efficiencies);
+ idx = find_index_l(policy, target_freq, min, max, efficiencies);
break;
case CPUFREQ_RELATION_H:
- idx = cpufreq_table_find_index_h(policy, target_freq,
- efficiencies);
+ idx = find_index_h(policy, target_freq, min, max, efficiencies);
break;
case CPUFREQ_RELATION_C:
- idx = cpufreq_table_find_index_c(policy, target_freq,
- efficiencies);
+ idx = find_index_c(policy, target_freq, min, max, efficiencies);
break;
default:
WARN_ON_ONCE(1);
return 0;
}
- /* Limit frequency index to honor policy->min/max */
- if (!cpufreq_is_in_limits(policy, idx) && efficiencies) {
+ /* Limit frequency index to honor min and max */
+ if (!cpufreq_is_in_limits(policy, min, max, idx) && efficiencies) {
efficiencies = false;
goto retry;
}
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index b79925b..85ab710 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -629,10 +629,14 @@ static inline int dma_mmap_wc(struct device *dev,
#else
#define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)
#define DEFINE_DMA_UNMAP_LEN(LEN_NAME)
-#define dma_unmap_addr(PTR, ADDR_NAME) (0)
-#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
-#define dma_unmap_len(PTR, LEN_NAME) (0)
-#define dma_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0)
+#define dma_unmap_addr(PTR, ADDR_NAME) \
+ ({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+ do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
+#define dma_unmap_len(PTR, LEN_NAME) \
+ ({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_len_set(PTR, LEN_NAME, VAL) \
+ do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
#endif
#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 65655a5..ca42d5e 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/moduleloader.h>
+#include <linux/cleanup.h>
#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
!defined(CONFIG_KASAN_VMALLOC)
@@ -53,7 +54,7 @@ enum execmem_range_flags {
EXECMEM_ROX_CACHE = (1 << 1),
};
-#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
+#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM)
/**
* execmem_fill_trapping_insns - set memory to contain instructions that
* will trap
@@ -93,9 +94,15 @@ int execmem_make_temp_rw(void *ptr, size_t size);
* Return: 0 on success or negative error code on failure.
*/
int execmem_restore_rox(void *ptr, size_t size);
+
+/*
+ * Called from mark_readonly(), where the system transitions to ROX.
+ */
+void execmem_cache_make_ro(void);
#else
static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
+static inline void execmem_cache_make_ro(void) { }
#endif
/**
@@ -170,6 +177,8 @@ void *execmem_alloc(enum execmem_type type, size_t size);
*/
void execmem_free(void *ptr);
+DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T));
+
#ifdef CONFIG_MMU
/**
* execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory
diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h
index 7db62fb..31551e4 100644
--- a/include/linux/file_ref.h
+++ b/include/linux/file_ref.h
@@ -61,7 +61,6 @@ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
atomic_long_set(&ref->refcnt, cnt - 1);
}
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt);
bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
/**
@@ -178,20 +177,14 @@ static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
*/
static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
{
- long old, new;
+ long old;
old = atomic_long_read(&ref->refcnt);
- do {
- if (unlikely(old < 0))
- return __file_ref_put_badval(ref, old);
-
- if (old == FILE_REF_ONEREF)
- new = FILE_REF_DEAD;
- else
- new = old - 1;
- } while (!atomic_long_try_cmpxchg(&ref->refcnt, &old, new));
-
- return new == FILE_REF_DEAD;
+ if (likely(old == FILE_REF_ONEREF)) {
+ if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
+ return true;
+ }
+ return file_ref_put(ref);
}
/**
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6cd8d1d..fc27b53 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -907,21 +907,6 @@ extern void fsnotify_wait_marks_destroyed(void);
/* Clear all of the marks of a group attached to a given object type */
extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
unsigned int obj_type);
-/* run all the marks in a group, and clear all of the vfsmount marks */
-static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
-}
-/* run all the marks in a group, and clear all of the inode marks */
-static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
-}
-/* run all the marks in a group, and clear all of the sn marks */
-static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group)
-{
- fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB);
-}
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 6fa0a26..097be89 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -2,6 +2,11 @@
/*
* fwnode.h - Firmware device node object handle type definition.
*
+ * This header file provides low-level data types and definitions for firmware
+ * and device property providers. The respective API header files supplied by
+ * them should contain all of the requisite data types and definitions for end
+ * users, so including it directly should not be necessary.
+ *
* Copyright (C) 2015, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
*/
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 675959f..b52ac40 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1002,6 +1002,12 @@ struct vmbus_channel {
/* The max size of a packet on this channel */
u32 max_pkt_size;
+
+ /* function to mmap ring buffer memory to the channel's sysfs ring attribute */
+ int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma);
+
+ /* boolean to control visibility of sysfs for ring buffer */
+ bool ring_sysfs_visible;
};
#define lock_requestor(channel, flags) \
@@ -1161,13 +1167,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel,
enum vmbus_packet_type type,
u32 flags);
-extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
- struct hv_page_buffer pagebuffers[],
- u32 pagecount,
- void *buffer,
- u32 bufferlen,
- u64 requestid);
-
extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
struct vmbus_packet_mpb_array *mpb,
u32 desc_size,
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 508d466..457b4fb 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1526,7 +1526,7 @@ struct ieee80211_mgmt {
struct {
u8 action_code;
u8 dialog_token;
- u8 status_code;
+ __le16 status_code;
u8 variable[];
} __packed ttlm_res;
struct {
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ccce8a75..3a8d35d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -440,10 +440,10 @@ static inline int __iommu_copy_struct_from_user(
void *dst_data, const struct iommu_user_data *src_data,
unsigned int data_type, size_t data_len, size_t min_len)
{
- if (src_data->type != data_type)
- return -EINVAL;
if (WARN_ON(!dst_data || !src_data))
return -EINVAL;
+ if (src_data->type != data_type)
+ return -EINVAL;
if (src_data->len < min_len || data_len < src_data->len)
return -EINVAL;
return copy_struct_from_user(dst_data, data_len, src_data->uptr,
@@ -456,8 +456,8 @@ static inline int __iommu_copy_struct_from_user(
* include/uapi/linux/iommufd.h
* @user_data: Pointer to a struct iommu_user_data for user space data info
* @data_type: The data type of the @kdst. Must match with @user_data->type
- * @min_last: The last memember of the data structure @kdst points in the
- * initial version.
+ * @min_last: The last member of the data structure @kdst points in the initial
+ * version.
* Return 0 for success, otherwise -error.
*/
#define iommu_copy_struct_from_user(kdst, user_data, data_type, min_last) \
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index bf2bf40..8d5ac16 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -102,11 +102,11 @@ do { \
l = (local_lock_t *)this_cpu_ptr(lock); \
tl = (local_trylock_t *)l; \
_Generic((lock), \
- local_trylock_t *: ({ \
+ __percpu local_trylock_t *: ({ \
lockdep_assert(tl->acquired == 0); \
WRITE_ONCE(tl->acquired, 1); \
}), \
- default:(void)0); \
+ __percpu local_lock_t *: (void)0); \
local_lock_acquire(l); \
} while (0)
@@ -171,11 +171,11 @@ do { \
tl = (local_trylock_t *)l; \
local_lock_release(l); \
_Generic((lock), \
- local_trylock_t *: ({ \
+ __percpu local_trylock_t *: ({ \
lockdep_assert(tl->acquired == 1); \
WRITE_ONCE(tl->acquired, 0); \
}), \
- default:(void)0); \
+ __percpu local_lock_t *: (void)0); \
} while (0)
#define __local_unlock(lock) \
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 591bf5b..9af01bd 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -44,7 +44,6 @@
#define MICREL_PHY_50MHZ_CLK BIT(0)
#define MICREL_PHY_FXEN BIT(1)
#define MICREL_KSZ8_P1_ERRATA BIT(2)
-#define MICREL_NO_EEE BIT(3)
#define MICREL_KSZ9021_EXTREG_CTRL 0xB
#define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC
diff --git a/include/linux/module.h b/include/linux/module.h
index d94b196..8050f77 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -162,6 +162,8 @@ extern void cleanup_module(void);
#define __INITRODATA_OR_MODULE __INITRODATA
#endif /*CONFIG_MODULES*/
+struct module_kobject *lookup_or_create_module_kobject(const char *name);
+
/* Generic info of form tag = "info" */
#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
@@ -584,6 +586,11 @@ struct module {
atomic_t refcnt;
#endif
+#ifdef CONFIG_MITIGATION_ITS
+ int its_num_pages;
+ void **its_page_array;
+#endif
+
#ifdef CONFIG_CONSTRUCTORS
/* Constructor functions. */
ctor_fn_t *ctors;
diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index 58a2401..0075f6e 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -262,6 +262,11 @@ struct mr_table {
int mroute_reg_vif_num;
};
+static inline bool mr_can_free_table(struct net *net)
+{
+ return !check_net(net) || !net_initialized(net);
+}
+
#ifdef CONFIG_IP_MROUTE_COMMON
void vif_device_init(struct vif_device *v,
struct net_device *dev,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2d11d01..7ea0227 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4972,6 +4972,7 @@ static inline void __dev_mc_unsync(struct net_device *dev,
/* Functions used for secondary unicast and multicast support */
void dev_set_rx_mode(struct net_device *dev);
+int netif_set_promiscuity(struct net_device *dev, int inc);
int dev_set_promiscuity(struct net_device *dev, int inc);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
int dev_set_allmulti(struct net_device *dev, int inc);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7131963..ee03f3c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -213,6 +213,15 @@ struct nfs_server {
char *fscache_uniq; /* Uniquifier (or NULL) */
#endif
+ /* The following #defines numerically match the NFSv4 equivalents */
+#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1)
+#define NFS_FH_VOLATILE_ANY (0x2)
+#define NFS_FH_VOL_MIGRATION (0x4)
+#define NFS_FH_VOL_RENAME (0x8)
+#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME)
+ u32 fh_expire_type; /* V4 bitmask representing file
+ handle volatility type for
+ this filesystem */
u32 pnfs_blksize; /* layout_blksize attr */
#if IS_ENABLED(CONFIG_NFS_V4)
u32 attr_bitmask[3];/* V4 bitmask representing the set
@@ -236,9 +245,6 @@ struct nfs_server {
u32 acl_bitmask; /* V4 bitmask representing the ACEs
that are supported on this
filesystem */
- u32 fh_expire_type; /* V4 bitmask representing file
- handle volatility type for
- this filesystem */
struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */
struct rpc_wait_queue roc_rpcwaitq;
void *pnfs_ld_data; /* per mount point data */
diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
index c740779..8a7f4f8 100644
--- a/include/linux/pgalloc_tag.h
+++ b/include/linux/pgalloc_tag.h
@@ -188,6 +188,13 @@ static inline struct alloc_tag *__pgalloc_tag_get(struct page *page)
return tag;
}
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page)
+{
+ if (mem_alloc_profiling_enabled())
+ return __pgalloc_tag_get(page);
+ return NULL;
+}
+
void pgalloc_tag_split(struct folio *folio, int old_order, int new_order);
void pgalloc_tag_swap(struct folio *new, struct folio *old);
@@ -199,6 +206,7 @@ static inline void clear_page_tag_ref(struct page *page) {}
static inline void alloc_tag_sec_init(void) {}
static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {}
static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {}
+static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; }
#endif /* CONFIG_MEM_ALLOC_PROFILING */
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 1f5773a..30659b6 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -361,23 +361,29 @@ int mac_finish(struct phylink_config *config, unsigned int mode,
phy_interface_t iface);
/**
- * mac_link_down() - take the link down
+ * mac_link_down() - notification that the link has gone down
* @config: a pointer to a &struct phylink_config.
* @mode: link autonegotiation mode
* @interface: link &typedef phy_interface_t mode
*
- * If @mode is not an in-band negotiation mode (as defined by
- * phylink_autoneg_inband()), force the link down and disable any
- * Energy Efficient Ethernet MAC configuration. Interface type
- * selection must be done in mac_config().
+ * Notifies the MAC that the link has gone down. This will not be called
+ * unless mac_link_up() has been previously called.
+ *
+ * The MAC should stop processing packets for transmission and reception.
+ * phylink will have called netif_carrier_off() to notify the networking
+ * stack that the link has gone down, so MAC drivers should not make this
+ * call.
+ *
+ * If @mode is %MLO_AN_INBAND, then this function must not prevent the
+ * link coming up.
*/
void mac_link_down(struct phylink_config *config, unsigned int mode,
phy_interface_t interface);
/**
- * mac_link_up() - allow the link to come up
+ * mac_link_up() - notification that the link has come up
* @config: a pointer to a &struct phylink_config.
- * @phy: any attached phy
+ * @phy: any attached phy (deprecated - please use LPI interfaces)
* @mode: link autonegotiation mode
* @interface: link &typedef phy_interface_t mode
* @speed: link speed
@@ -385,7 +391,10 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
* @tx_pause: link transmit pause enablement status
* @rx_pause: link receive pause enablement status
*
- * Configure the MAC for an established link.
+ * Notifies the MAC that the link has come up, and the parameters of the
+ * link as seen from the MACs point of view. If mac_link_up() has been
+ * called previously, there will be an intervening call to mac_link_down()
+ * before this method will be subsequently called.
*
* @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link
* settings, and should be used to configure the MAC block appropriately
@@ -397,9 +406,9 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
* that the user wishes to override the pause settings, and this should
* be allowed when considering the implementation of this method.
*
- * If in-band negotiation mode is disabled, allow the link to come up. If
- * @phy is non-%NULL, configure Energy Efficient Ethernet by calling
- * phy_init_eee() and perform appropriate MAC configuration for EEE.
+ * Once configured, the MAC may begin to process packets for transmission
+ * and reception.
+ *
* Interface type selection must be done in mac_config().
*/
void mac_link_up(struct phylink_config *config, struct phy_device *phy,
diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h
index 493d9de..dc6ebae 100644
--- a/include/linux/soundwire/sdw_intel.h
+++ b/include/linux/soundwire/sdw_intel.h
@@ -365,7 +365,7 @@ struct sdw_intel_res {
* on e.g. which machine driver to select (I2S mode, HDaudio or
* SoundWire).
*/
-int sdw_intel_acpi_scan(acpi_handle *parent_handle,
+int sdw_intel_acpi_scan(acpi_handle parent_handle,
struct sdw_intel_acpi_info *info);
void sdw_intel_process_wakeen_event(struct sdw_intel_ctx *ctx);
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index e39d4d5..785048a 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -51,7 +51,7 @@ struct tk_read_base {
* @offs_real: Offset clock monotonic -> clock realtime
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
- * @tai_offset: The current UTC to TAI offset in seconds
+ * @coarse_nsec: The nanoseconds part for coarse time getters
* @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW
* @raw_sec: CLOCK_MONOTONIC_RAW time in seconds
* @clock_was_set_seq: The sequence number of clock was set events
@@ -76,6 +76,7 @@ struct tk_read_base {
* ntp shifted nano seconds.
* @ntp_err_mult: Multiplication factor for scaled math conversion
* @skip_second_overflow: Flag used to avoid updating NTP twice with same second
+ * @tai_offset: The current UTC to TAI offset in seconds
*
* Note: For timespec(64) based interfaces wall_to_monotonic is what
* we need to add to xtime (or xtime corrected for sub jiffy times)
@@ -100,7 +101,7 @@ struct tk_read_base {
* which results in the following cacheline layout:
*
* 0: seqcount, tkr_mono
- * 1: xtime_sec ... tai_offset
+ * 1: xtime_sec ... coarse_nsec
* 2: tkr_raw, raw_sec
* 3,4: Internal variables
*
@@ -121,7 +122,7 @@ struct timekeeper {
ktime_t offs_real;
ktime_t offs_boot;
ktime_t offs_tai;
- s32 tai_offset;
+ u32 coarse_nsec;
/* Cacheline 2: */
struct tk_read_base tkr_raw;
@@ -144,6 +145,7 @@ struct timekeeper {
u32 ntp_error_shift;
u32 ntp_err_mult;
u32 skip_second_overflow;
+ s32 tai_offset;
};
#ifdef CONFIG_GENERIC_TIME_VSYSCALL
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 6c312530..a3d8305 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -224,7 +224,7 @@ enum tpm2_const {
enum tpm2_timeouts {
TPM2_TIMEOUT_A = 750,
- TPM2_TIMEOUT_B = 2000,
+ TPM2_TIMEOUT_B = 4000,
TPM2_TIMEOUT_C = 200,
TPM2_TIMEOUT_D = 30,
TPM2_DURATION_SHORT = 20,
@@ -257,6 +257,7 @@ enum tpm2_return_codes {
TPM2_RC_TESTING = 0x090A, /* RC_WARN */
TPM2_RC_REFERENCE_H0 = 0x0910,
TPM2_RC_RETRY = 0x0922,
+ TPM2_RC_SESSION_MEMORY = 0x0903,
};
enum tpm2_command_codes {
@@ -437,6 +438,24 @@ static inline u32 tpm2_rc_value(u32 rc)
return (rc & BIT(7)) ? rc & 0xbf : rc;
}
+/*
+ * Convert a return value from tpm_transmit_cmd() to POSIX error code.
+ */
+static inline ssize_t tpm_ret_to_err(ssize_t ret)
+{
+ if (ret < 0)
+ return ret;
+
+ switch (tpm2_rc_value(ret)) {
+ case TPM2_RC_SUCCESS:
+ return 0;
+ case TPM2_RC_SESSION_MEMORY:
+ return -ENOMEM;
+ default:
+ return -EFAULT;
+ }
+}
+
#if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE)
extern int tpm_is_tpm2(struct tpm_chip *chip);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4d16c13..64cb4b0 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -220,6 +220,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
* occurs.
* @reset_done: optional function to call after transport specific reset
* operation has finished.
+ * @shutdown: synchronize with the device on shutdown. If provided, replaces
+ * the virtio core implementation.
*/
struct virtio_driver {
struct device_driver driver;
@@ -237,6 +239,7 @@ struct virtio_driver {
int (*restore)(struct virtio_device *dev);
int (*reset_prepare)(struct virtio_device *dev);
int (*reset_done)(struct virtio_device *dev);
+ void (*shutdown)(struct virtio_device *dev);
};
#define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 31e9ffd..5ca8d4dd 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -61,6 +61,7 @@ struct vm_struct {
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
+ unsigned long requested_size;
};
struct vmap_area {
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index a8586c3..7979920 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1931,6 +1931,8 @@ struct hci_cp_le_pa_create_sync {
__u8 sync_cte_type;
} __packed;
+#define HCI_OP_LE_PA_CREATE_SYNC_CANCEL 0x2045
+
#define HCI_OP_LE_PA_TERM_SYNC 0x2046
struct hci_cp_le_pa_term_sync {
__le16 handle;
@@ -2830,7 +2832,7 @@ struct hci_evt_le_create_big_complete {
__le16 bis_handle[];
} __packed;
-#define HCI_EVT_LE_BIG_SYNC_ESTABILISHED 0x1d
+#define HCI_EVT_LE_BIG_SYNC_ESTABLISHED 0x1d
struct hci_evt_le_big_sync_estabilished {
__u8 status;
__u8 handle;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5115da3..54bfeea 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1113,10 +1113,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev,
return NULL;
}
-static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev,
- __u8 sid,
- bdaddr_t *dst,
- __u8 dst_type)
+static inline struct hci_conn *
+hci_conn_hash_lookup_create_pa_sync(struct hci_dev *hdev)
{
struct hci_conn_hash *h = &hdev->conn_hash;
struct hci_conn *c;
@@ -1124,8 +1122,10 @@ static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev,
rcu_read_lock();
list_for_each_entry_rcu(c, &h->list, list) {
- if (c->type != ISO_LINK || bacmp(&c->dst, dst) ||
- c->dst_type != dst_type || c->sid != sid)
+ if (c->type != ISO_LINK)
+ continue;
+
+ if (!test_bit(HCI_CONN_CREATE_PA_SYNC, &c->flags))
continue;
rcu_read_unlock();
@@ -1524,8 +1524,6 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
void hci_sco_setup(struct hci_conn *conn, __u8 status);
bool hci_iso_setup_path(struct hci_conn *conn);
int hci_le_create_cis_pending(struct hci_dev *hdev);
-int hci_pa_create_sync_pending(struct hci_dev *hdev);
-int hci_le_big_create_sync_pending(struct hci_dev *hdev);
int hci_conn_check_create_cis(struct hci_conn *conn);
struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,
@@ -1566,9 +1564,9 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
__u8 data_len, __u8 *data);
struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, __u8 sid, struct bt_iso_qos *qos);
-int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
- struct bt_iso_qos *qos,
- __u16 sync_handle, __u8 num_bis, __u8 bis[]);
+int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+ struct bt_iso_qos *qos, __u16 sync_handle,
+ __u8 num_bis, __u8 bis[]);
int hci_conn_check_link_mode(struct hci_conn *conn);
int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level);
int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type,
@@ -1800,6 +1798,7 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list,
void hci_uuids_clear(struct hci_dev *hdev);
void hci_link_keys_clear(struct hci_dev *hdev);
+u8 *hci_conn_key_enc_size(struct hci_conn *conn);
struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr);
struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn,
bdaddr_t *bdaddr, u8 *val, u8 type,
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 7e2cf0c..72558c8 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -185,3 +185,6 @@ int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn);
int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn);
int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn,
struct hci_conn_params *params);
+
+int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn);
+int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn);
diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h
index c316b55..0ee5bc7 100644
--- a/include/net/netdev_lock.h
+++ b/include/net/netdev_lock.h
@@ -98,6 +98,9 @@ static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
&qdisc_xmit_lock_key); \
}
+#define netdev_lock_dereference(p, dev) \
+ rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock))
+
int netdev_debug_event(struct notifier_block *nb, unsigned long event,
void *ptr);
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 825141d..d01c829 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -103,6 +103,12 @@ struct netdev_stat_ops {
struct netdev_queue_stats_tx *tx);
};
+void netdev_stat_queue_sum(struct net_device *netdev,
+ int rx_start, int rx_end,
+ struct netdev_queue_stats_rx *rx_sum,
+ int tx_start, int tx_end,
+ struct netdev_queue_stats_tx *tx_sum);
+
/**
* struct netdev_queue_mgmt_ops - netdev ops for queue management
*
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d48c657..1c05fed 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1031,6 +1031,21 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh)
return skb;
}
+static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct)
+{
+ struct sk_buff *skb;
+
+ skb = __skb_dequeue(&sch->gso_skb);
+ if (skb) {
+ sch->q.qlen--;
+ return skb;
+ }
+ if (direct)
+ return __qdisc_dequeue_head(&sch->q);
+ else
+ return sch->dequeue(sch);
+}
+
static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
{
struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index a58ae75..e8bd6dd 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -71,9 +71,6 @@ struct xdp_sock {
*/
u32 tx_budget_spent;
- /* Protects generic receive. */
- spinlock_t rx_lock;
-
/* Statistics */
u64 rx_dropped;
u64 rx_queue_full;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 39365fd..06ab2a3 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -236,7 +236,6 @@ struct xfrm_state {
/* Data for encapsulator */
struct xfrm_encap_tmpl *encap;
- struct sock __rcu *encap_sk;
/* NAT keepalive */
u32 nat_keepalive_interval; /* seconds */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 1dcd4d7..cac56e6 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -53,6 +53,8 @@ struct xsk_buff_pool {
refcount_t users;
struct xdp_umem *umem;
struct work_struct work;
+ /* Protects generic receive in shared and non-shared umem mode. */
+ spinlock_t rx_lock;
struct list_head free_list;
struct list_head xskb_list;
u32 heads_cnt;
@@ -238,8 +240,8 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb,
return orig_addr;
offset = xskb->xdp.data - xskb->xdp.data_hard_start;
- orig_addr -= offset;
offset += pool->headroom;
+ orig_addr -= offset;
return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
}
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 8becb45..8582d22 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -1404,6 +1404,8 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s
#define snd_pcm_lib_mmap_iomem NULL
#endif
+void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime);
+
/**
* snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer
* @dma: DMA number
diff --git a/include/sound/soc_sdw_utils.h b/include/sound/soc_sdw_utils.h
index 36a4a1e..d8bd5d3 100644
--- a/include/sound/soc_sdw_utils.h
+++ b/include/sound/soc_sdw_utils.h
@@ -226,6 +226,7 @@ int asoc_sdw_cs_amp_init(struct snd_soc_card *card,
bool playback);
int asoc_sdw_cs_spk_feedback_rtd_init(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_dai *dai);
+int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix);
/* MAXIM codec support */
int asoc_sdw_maxim_init(struct snd_soc_card *card,
diff --git a/include/sound/ump_convert.h b/include/sound/ump_convert.h
index d099ae2..682499b 100644
--- a/include/sound/ump_convert.h
+++ b/include/sound/ump_convert.h
@@ -19,7 +19,7 @@ struct ump_cvt_to_ump_bank {
/* context for converting from MIDI1 byte stream to UMP packet */
struct ump_cvt_to_ump {
/* MIDI1 intermediate buffer */
- unsigned char buf[4];
+ unsigned char buf[6]; /* up to 6 bytes for SysEx */
int len;
int cmd_bytes;
diff --git a/include/sound/ump_msg.h b/include/sound/ump_msg.h
index 72f60dd..9556b47 100644
--- a/include/sound/ump_msg.h
+++ b/include/sound/ump_msg.h
@@ -604,7 +604,7 @@ struct snd_ump_stream_msg_ep_info {
} __packed;
/* UMP Stream Message: Device Info Notification (128bit) */
-struct snd_ump_stream_msg_devince_info {
+struct snd_ump_stream_msg_device_info {
#ifdef __BIG_ENDIAN_BITFIELD
/* 0 */
u32 type:4;
@@ -754,7 +754,7 @@ struct snd_ump_stream_msg_fb_name {
union snd_ump_stream_msg {
struct snd_ump_stream_msg_ep_discovery ep_discovery;
struct snd_ump_stream_msg_ep_info ep_info;
- struct snd_ump_stream_msg_devince_info device_info;
+ struct snd_ump_stream_msg_device_info device_info;
struct snd_ump_stream_msg_stream_cfg stream_cfg;
struct snd_ump_stream_msg_fb_discovery fb_discovery;
struct snd_ump_stream_msg_fb_info fb_info;
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 549ab3b..3efc00c 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1928,7 +1928,7 @@ DECLARE_EVENT_CLASS(btrfs__prelim_ref,
TP_PROTO(const struct btrfs_fs_info *fs_info,
const struct prelim_ref *oldref,
const struct prelim_ref *newref, u64 tree_size),
- TP_ARGS(fs_info, newref, oldref, tree_size),
+ TP_ARGS(fs_info, oldref, newref, tree_size),
TP_STRUCT__entry_btrfs(
__field( u64, root_id )
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 28705ae..fd40472 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4968,6 +4968,9 @@ union bpf_attr {
* the netns switch takes place from ingress to ingress without
* going through the CPU's backlog queue.
*
+ * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * the netns switch.
+ *
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types at the
* ingress hook and for veth and netkit target device types. The
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index fe24c34..30c8dad 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -31,11 +31,6 @@ enum ethtool_header_flags {
ETHTOOL_FLAG_STATS = 4,
};
-enum {
- ETHTOOL_PHY_UPSTREAM_TYPE_MAC,
- ETHTOOL_PHY_UPSTREAM_TYPE_PHY,
-};
-
enum ethtool_tcp_data_split {
ETHTOOL_TCP_DATA_SPLIT_UNKNOWN,
ETHTOOL_TCP_DATA_SPLIT_DISABLED,
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
index d9d0cb8..f030adc 100644
--- a/include/uapi/linux/landlock.h
+++ b/include/uapi/linux/landlock.h
@@ -53,43 +53,70 @@ struct landlock_ruleset_attr {
__u64 scoped;
};
-/*
- * sys_landlock_create_ruleset() flags:
+/**
+ * DOC: landlock_create_ruleset_flags
*
- * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI
- * version.
- * - %LANDLOCK_CREATE_RULESET_ERRATA: Get a bitmask of fixed issues.
+ * **Flags**
+ *
+ * %LANDLOCK_CREATE_RULESET_VERSION
+ * Get the highest supported Landlock ABI version (starting at 1).
+ *
+ * %LANDLOCK_CREATE_RULESET_ERRATA
+ * Get a bitmask of fixed issues for the current Landlock ABI version.
*/
/* clang-format off */
#define LANDLOCK_CREATE_RULESET_VERSION (1U << 0)
#define LANDLOCK_CREATE_RULESET_ERRATA (1U << 1)
/* clang-format on */
-/*
- * sys_landlock_restrict_self() flags:
+/**
+ * DOC: landlock_restrict_self_flags
*
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF: Do not create any log related to the
- * enforced restrictions. This should only be set by tools launching unknown
- * or untrusted programs (e.g. a sandbox tool, container runtime, system
- * service manager). Because programs sandboxing themselves should fix any
- * denied access, they should not set this flag to be aware of potential
- * issues reported by system's logs (i.e. audit).
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON: Explicitly ask to continue
- * logging denied access requests even after an :manpage:`execve(2)` call.
- * This flag should only be set if all the programs than can legitimately be
- * executed will not try to request a denied access (which could spam audit
- * logs).
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF: Do not create any log related
- * to the enforced restrictions coming from future nested domains created by
- * the caller or its descendants. This should only be set according to a
- * runtime configuration (i.e. not hardcoded) by programs launching other
- * unknown or untrusted programs that may create their own Landlock domains
- * and spam logs. The main use case is for container runtimes to enable users
- * to mute buggy sandboxed programs for a specific container image. Other use
- * cases include sandboxer tools and init systems. Unlike
- * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF,
- * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF does not impact the requested
- * restriction (if any) but only the future nested domains.
+ * **Flags**
+ *
+ * By default, denied accesses originating from programs that sandbox themselves
+ * are logged via the audit subsystem. Such events typically indicate unexpected
+ * behavior, such as bugs or exploitation attempts. However, to avoid excessive
+ * logging, access requests denied by a domain not created by the originating
+ * program are not logged by default. The rationale is that programs should know
+ * their own behavior, but not necessarily the behavior of other programs. This
+ * default configuration is suitable for most programs that sandbox themselves.
+ * For specific use cases, the following flags allow programs to modify this
+ * default logging behavior.
+ *
+ * The %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF and
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON flags apply to the newly created
+ * Landlock domain.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ * Disables logging of denied accesses originating from the thread creating
+ * the Landlock domain, as well as its children, as long as they continue
+ * running the same executable code (i.e., without an intervening
+ * :manpage:`execve(2)` call). This is intended for programs that execute
+ * unknown code without invoking :manpage:`execve(2)`, such as script
+ * interpreters. Programs that only sandbox themselves should not set this
+ * flag, so users can be notified of unauthorized access attempts via system
+ * logs.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ * Enables logging of denied accesses after an :manpage:`execve(2)` call,
+ * providing visibility into unauthorized access attempts by newly executed
+ * programs within the created Landlock domain. This flag is recommended
+ * only when all potential executables in the domain are expected to comply
+ * with the access restrictions, as excessive audit log entries could make
+ * it more difficult to identify critical events.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ * Disables logging of denied accesses originating from nested Landlock
+ * domains created by the caller or its descendants. This flag should be set
+ * according to runtime configuration, not hardcoded, to avoid suppressing
+ * important security events. It is useful for container runtimes or
+ * sandboxing tools that may launch programs which themselves create
+ * Landlock domains and could otherwise generate excessive logs. Unlike
+ * ``LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF``, this flag only affects
+ * future nested domains, not the one being created. It can also be used
+ * with a @ruleset_fd value of -1 to mute subdomain logs without creating a
+ * domain.
*/
/* clang-format off */
#define LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF (1U << 0)
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index b95dd84..d4b3e2a 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -28,10 +28,10 @@
/* Set current process as the (exclusive) owner of this file descriptor. This
* must be called before any other vhost command. Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+ * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */
#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
/* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+ * Allows subsequent call to VHOST_SET_OWNER to succeed. */
#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
/* Set up/modify memory layout */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 8549d45..c691ac2 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -246,6 +246,7 @@ struct virtio_pci_cfg_cap {
#define VIRTIO_ADMIN_CMD_LIST_USE 0x1
/* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SELF 0x0
#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1
/* Transitional device admin command. */
diff --git a/include/ufs/ufs_quirks.h b/include/ufs/ufs_quirks.h
index 41ff44d..f52de5e 100644
--- a/include/ufs/ufs_quirks.h
+++ b/include/ufs/ufs_quirks.h
@@ -107,4 +107,10 @@ struct ufs_dev_quirk {
*/
#define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM (1 << 11)
+/*
+ * Some ufs devices may need more time to be in hibern8 before exiting.
+ * Enable this quirk to give it an additional 100us.
+ */
+#define UFS_DEVICE_QUIRK_PA_HIBER8TIME (1 << 12)
+
#endif /* UFS_QUIRKS_H_ */
diff --git a/init/Kconfig b/init/Kconfig
index 63f5974..bf3a920 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -87,11 +87,6 @@
default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT
default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag))
-config CC_CAN_LINK_STATIC
- bool
- default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag) -static) if 64BIT
- default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag) -static)
-
# Fixed in GCC 14, 13.3, 12.4 and 11.5
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
config GCC_ASM_GOTO_OUTPUT_BROKEN
@@ -140,6 +135,9 @@
config RUSTC_HAS_COERCE_POINTEE
def_bool RUSTC_VERSION >= 108400
+config RUSTC_HAS_UNNECESSARY_TRANSMUTES
+ def_bool RUSTC_VERSION >= 108800
+
config PAHOLE_VERSION
int
default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index f60d0a9..e0d6a59 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -86,13 +86,8 @@ static inline void napi_show_fdinfo(struct io_ring_ctx *ctx,
}
#endif
-/*
- * Caller holds a reference to the file already, we don't need to do
- * anything else to get an extra reference.
- */
-__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
+static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
{
- struct io_ring_ctx *ctx = file->private_data;
struct io_overflow_cqe *ocqe;
struct io_rings *r = ctx->rings;
struct rusage sq_usage;
@@ -106,7 +101,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
unsigned int sq_entries, cq_entries;
int sq_pid = -1, sq_cpu = -1;
u64 sq_total_time = 0, sq_work_time = 0;
- bool has_lock;
unsigned int i;
if (ctx->flags & IORING_SETUP_CQE32)
@@ -123,11 +117,11 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
seq_printf(m, "SqMask:\t0x%x\n", sq_mask);
seq_printf(m, "SqHead:\t%u\n", sq_head);
seq_printf(m, "SqTail:\t%u\n", sq_tail);
- seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
+ seq_printf(m, "CachedSqHead:\t%u\n", data_race(ctx->cached_sq_head));
seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
seq_printf(m, "CqHead:\t%u\n", cq_head);
seq_printf(m, "CqTail:\t%u\n", cq_tail);
- seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
+ seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail));
seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head);
sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
for (i = 0; i < sq_entries; i++) {
@@ -176,15 +170,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
seq_printf(m, "\n");
}
- /*
- * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
- * since fdinfo case grabs it in the opposite direction of normal use
- * cases. If we fail to get the lock, we just don't iterate any
- * structures that could be going away outside the io_uring mutex.
- */
- has_lock = mutex_trylock(&ctx->uring_lock);
-
- if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
struct io_sq_data *sq = ctx->sq_data;
/*
@@ -206,7 +192,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr);
- for (i = 0; has_lock && i < ctx->file_table.data.nr; i++) {
+ for (i = 0; i < ctx->file_table.data.nr; i++) {
struct file *f = NULL;
if (ctx->file_table.data.nodes[i])
@@ -218,7 +204,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
}
}
seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);
- for (i = 0; has_lock && i < ctx->buf_table.nr; i++) {
+ for (i = 0; i < ctx->buf_table.nr; i++) {
struct io_mapped_ubuf *buf = NULL;
if (ctx->buf_table.nodes[i])
@@ -228,7 +214,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
else
seq_printf(m, "%5u: <none>\n", i);
}
- if (has_lock && !xa_empty(&ctx->personalities)) {
+ if (!xa_empty(&ctx->personalities)) {
unsigned long index;
const struct cred *cred;
@@ -238,7 +224,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
}
seq_puts(m, "PollList:\n");
- for (i = 0; has_lock && i < (1U << ctx->cancel_table.hash_bits); i++) {
+ for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
struct io_kiocb *req;
@@ -247,9 +233,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
task_work_pending(req->tctx->task));
}
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
-
seq_puts(m, "CqOverflowList:\n");
spin_lock(&ctx->completion_lock);
list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
@@ -262,4 +245,23 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
spin_unlock(&ctx->completion_lock);
napi_show_fdinfo(ctx, m);
}
+
+/*
+ * Caller holds a reference to the file already, we don't need to do
+ * anything else to get an extra reference.
+ */
+__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+
+ /*
+ * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
+ * since fdinfo case grabs it in the opposite direction of normal use
+ * cases.
+ */
+ if (mutex_trylock(&ctx->uring_lock)) {
+ __io_uring_show_fdinfo(ctx, m);
+ mutex_unlock(&ctx->uring_lock);
+ }
+}
#endif
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c6209fe..edda31a 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -448,24 +448,6 @@ static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
return req->link;
}
-static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
-{
- if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
- return NULL;
- return __io_prep_linked_timeout(req);
-}
-
-static noinline void __io_arm_ltimeout(struct io_kiocb *req)
-{
- io_queue_linked_timeout(__io_prep_linked_timeout(req));
-}
-
-static inline void io_arm_ltimeout(struct io_kiocb *req)
-{
- if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
- __io_arm_ltimeout(req);
-}
-
static void io_prep_async_work(struct io_kiocb *req)
{
const struct io_issue_def *def = &io_issue_defs[req->opcode];
@@ -518,7 +500,6 @@ static void io_prep_async_link(struct io_kiocb *req)
static void io_queue_iowq(struct io_kiocb *req)
{
- struct io_kiocb *link = io_prep_linked_timeout(req);
struct io_uring_task *tctx = req->tctx;
BUG_ON(!tctx);
@@ -543,8 +524,6 @@ static void io_queue_iowq(struct io_kiocb *req)
trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work));
io_wq_enqueue(tctx->io_wq, &req->work);
- if (link)
- io_queue_linked_timeout(link);
}
static void io_req_queue_iowq_tw(struct io_kiocb *req, io_tw_token_t tw)
@@ -657,6 +636,7 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying)
* to care for a non-real case.
*/
if (need_resched()) {
+ ctx->cqe_sentinel = ctx->cqe_cached;
io_cq_unlock_post(ctx);
mutex_unlock(&ctx->uring_lock);
cond_resched();
@@ -869,13 +849,26 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
struct io_ring_ctx *ctx = req->ctx;
bool posted;
+ /*
+ * If multishot has already posted deferred completions, ensure that
+ * those are flushed first before posting this one. If not, CQEs
+ * could get reordered.
+ */
+ if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+ __io_submit_flush_completions(ctx);
+
lockdep_assert(!io_wq_current_is_worker());
lockdep_assert_held(&ctx->uring_lock);
- __io_cq_lock(ctx);
- posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+ if (!ctx->lockless_cq) {
+ spin_lock(&ctx->completion_lock);
+ posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+ spin_unlock(&ctx->completion_lock);
+ } else {
+ posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+ }
+
ctx->submit_state.cq_flush = true;
- __io_cq_unlock_post(ctx);
return posted;
}
@@ -1078,21 +1071,22 @@ static __cold void __io_fallback_tw(struct llist_node *node, bool sync)
while (node) {
req = container_of(node, struct io_kiocb, io_task_work.node);
node = node->next;
- if (sync && last_ctx != req->ctx) {
+ if (last_ctx != req->ctx) {
if (last_ctx) {
- flush_delayed_work(&last_ctx->fallback_work);
+ if (sync)
+ flush_delayed_work(&last_ctx->fallback_work);
percpu_ref_put(&last_ctx->refs);
}
last_ctx = req->ctx;
percpu_ref_get(&last_ctx->refs);
}
- if (llist_add(&req->io_task_work.node,
- &req->ctx->fallback_llist))
- schedule_delayed_work(&req->ctx->fallback_work, 1);
+ if (llist_add(&req->io_task_work.node, &last_ctx->fallback_llist))
+ schedule_delayed_work(&last_ctx->fallback_work, 1);
}
if (last_ctx) {
- flush_delayed_work(&last_ctx->fallback_work);
+ if (sync)
+ flush_delayed_work(&last_ctx->fallback_work);
percpu_ref_put(&last_ctx->refs);
}
}
@@ -1718,15 +1712,22 @@ static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def,
return !!req->file;
}
+#define REQ_ISSUE_SLOW_FLAGS (REQ_F_CREDS | REQ_F_ARM_LTIMEOUT)
+
static inline int __io_issue_sqe(struct io_kiocb *req,
unsigned int issue_flags,
const struct io_issue_def *def)
{
const struct cred *creds = NULL;
+ struct io_kiocb *link = NULL;
int ret;
- if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
- creds = override_creds(req->creds);
+ if (unlikely(req->flags & REQ_ISSUE_SLOW_FLAGS)) {
+ if ((req->flags & REQ_F_CREDS) && req->creds != current_cred())
+ creds = override_creds(req->creds);
+ if (req->flags & REQ_F_ARM_LTIMEOUT)
+ link = __io_prep_linked_timeout(req);
+ }
if (!def->audit_skip)
audit_uring_entry(req->opcode);
@@ -1736,8 +1737,12 @@ static inline int __io_issue_sqe(struct io_kiocb *req,
if (!def->audit_skip)
audit_uring_exit(!ret, ret);
- if (creds)
- revert_creds(creds);
+ if (unlikely(creds || link)) {
+ if (creds)
+ revert_creds(creds);
+ if (link)
+ io_queue_linked_timeout(link);
+ }
return ret;
}
@@ -1763,7 +1768,6 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (ret == IOU_ISSUE_SKIP_COMPLETE) {
ret = 0;
- io_arm_ltimeout(req);
/* If the op doesn't have a file, we're not polling for it */
if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
@@ -1818,8 +1822,6 @@ void io_wq_submit_work(struct io_wq_work *work)
else
req_ref_get(req);
- io_arm_ltimeout(req);
-
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
if (atomic_read(&work->flags) & IO_WQ_WORK_CANCEL) {
fail:
@@ -1935,15 +1937,11 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd)
static void io_queue_async(struct io_kiocb *req, int ret)
__must_hold(&req->ctx->uring_lock)
{
- struct io_kiocb *linked_timeout;
-
if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
io_req_defer_failed(req, ret);
return;
}
- linked_timeout = io_prep_linked_timeout(req);
-
switch (io_arm_poll_handler(req, 0)) {
case IO_APOLL_READY:
io_kbuf_recycle(req, 0);
@@ -1956,9 +1954,6 @@ static void io_queue_async(struct io_kiocb *req, int ret)
case IO_APOLL_OK:
break;
}
-
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
}
static inline void io_queue_sqe(struct io_kiocb *req)
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 76fcc79..07f8a5c 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -116,7 +116,7 @@ static int io_region_init_ptr(struct io_mapped_region *mr)
void *ptr;
if (io_check_coalesce_buffer(mr->pages, mr->nr_pages, &ifd)) {
- if (ifd.nr_folios == 1) {
+ if (ifd.nr_folios == 1 && !PageHighMem(mr->pages[0])) {
mr->ptr = page_address(mr->pages[0]);
return 0;
}
diff --git a/io_uring/net.c b/io_uring/net.c
index 24040bc..27f37fa 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -827,18 +827,24 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
cflags |= IORING_CQE_F_SOCK_NONEMPTY;
if (sr->flags & IORING_RECVSEND_BUNDLE) {
- cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, *ret),
+ size_t this_ret = *ret - sr->done_io;
+
+ cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, this_ret),
issue_flags);
if (sr->retry)
cflags = req->cqe.flags | (cflags & CQE_F_MASK);
/* bundle with no more immediate buffers, we're done */
if (req->flags & REQ_F_BL_EMPTY)
goto finish;
- /* if more is available, retry and append to this one */
- if (!sr->retry && kmsg->msg.msg_inq > 0 && *ret > 0) {
+ /*
+ * If more is available AND it was a full transfer, retry and
+ * append to this one
+ */
+ if (!sr->retry && kmsg->msg.msg_inq > 0 && this_ret > 0 &&
+ !iov_iter_count(&kmsg->msg.msg_iter)) {
req->cqe.flags = cflags & ~CQE_F_MASK;
sr->len = kmsg->msg.msg_inq;
- sr->done_io += *ret;
+ sr->done_io += this_ret;
sr->retry = true;
return false;
}
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index d037cc6..03c6994 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -20,7 +20,7 @@
#include "sqpoll.h"
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
-#define IORING_TW_CAP_ENTRIES_VALUE 8
+#define IORING_TW_CAP_ENTRIES_VALUE 32
enum {
IO_SQ_THREAD_SHOULD_STOP = 0,
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index a9ea7d2..430ed62 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -254,6 +254,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
return -EOPNOTSUPP;
issue_flags |= IO_URING_F_IOPOLL;
req->iopoll_completed = 0;
+ if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
+ /* make sure every req only blocks once */
+ req->flags &= ~REQ_F_IOPOLL_STATE;
+ req->iopoll_start = ktime_get_ns();
+ }
}
ret = file->f_op->uring_cmd(ioucmd, issue_flags);
diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h
index b04686b..e6a5142 100644
--- a/io_uring/uring_cmd.h
+++ b/io_uring/uring_cmd.h
@@ -17,9 +17,3 @@ bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
struct io_uring_task *tctx, bool cancel_all);
void io_cmd_cache_free(const void *entry);
-
-int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
- const struct iovec __user *uvec,
- size_t uvec_segs,
- int ddir, struct iov_iter *iter,
- unsigned issue_flags);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5a5adc6..92b606d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2189,7 +2189,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
b = &htab->buckets[i];
rcu_read_lock();
head = &b->head;
- hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+ hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
key = elem->key;
if (is_percpu) {
/* current cpu value for percpu map */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 2fdf3c9..774e5a5 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -89,5 +89,6 @@ static void __exit fini(void)
}
late_initcall(load);
module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9794446..64c3393 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1583,7 +1583,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
return map;
}
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
@@ -3364,7 +3364,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
bpf_link_inc(link);
return link;
}
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
static void bpf_tracing_link_release(struct bpf_link *link)
{
@@ -6020,7 +6020,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
return ____bpf_sys_bpf(cmd, attr, size);
}
}
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
static const struct bpf_func_proto bpf_sys_bpf_proto = {
.func = bpf_sys_bpf,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3caf2cd..63e5b90 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
DEFINE_MUTEX(cgroup_mutex);
DEFINE_SPINLOCK(css_set_lock);
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
EXPORT_SYMBOL_GPL(cgroup_mutex);
EXPORT_SYMBOL_GPL(css_set_lock);
#endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
};
#ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+ Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+ fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+ {}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+ struct fs_parse_result result;
+ int opt;
+
+ opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_cpuset_v2_mode:
+ ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+ return 0;
+ }
+ return -EINVAL;
+}
+
static const struct fs_context_operations cpuset_fs_context_ops = {
.get_tree = cgroup1_get_tree,
.free = cgroup_fs_context_free,
+ .parse_param = cpuset_parse_param,
};
/*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
.init_fs_context = cpuset_init_fs_context,
+ .parameters = cpuset_fs_parameters,
.fs_flags = FS_USERNS_MOUNT,
};
#endif
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 306b604..24b70ea 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1116,9 +1116,11 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
if (top_cs) {
/*
- * Percpu kthreads in top_cpuset are ignored
+ * PF_NO_SETAFFINITY tasks are ignored.
+ * All per cpu kthreads should have PF_NO_SETAFFINITY
+ * flag set, see kthread_set_per_cpu().
*/
- if (kthread_is_per_cpu(task))
+ if (task->flags & PF_NO_SETAFFINITY)
continue;
cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus);
} else {
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 3b2bdca..77c8d94 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -336,16 +336,22 @@ static phys_addr_t dma_reserved_default_memory_size __initdata;
static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
{
- if (!rmem->priv) {
- struct dma_coherent_mem *mem;
+ struct dma_coherent_mem *mem = rmem->priv;
+ if (!mem) {
mem = dma_init_coherent_memory(rmem->base, rmem->base,
rmem->size, true);
if (IS_ERR(mem))
return PTR_ERR(mem);
rmem->priv = mem;
}
- dma_assign_coherent_memory(dev, rmem->priv);
+
+ /* Warn if the device potentially can't use the reserved memory */
+ if (mem->device_base + rmem->size - 1 >
+ min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+ dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+ dma_assign_coherent_memory(dev, mem);
return 0;
}
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 055da41..8df0dfa 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -64,8 +64,7 @@ struct cma *dma_contiguous_default_area;
* Users, who want to set the size of global CMA area for their system
* should use cma= kernel parameter.
*/
-static const phys_addr_t size_bytes __initconst =
- (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
static phys_addr_t size_cmdline __initdata = -1;
static phys_addr_t base_cmdline __initdata;
static phys_addr_t limit_cmdline __initdata;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index cda1270..051a329 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -910,15 +910,7 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_set_coherent_mask);
-/**
- * dma_addressing_limited - return if the device is addressing limited
- * @dev: device to check
- *
- * Return %true if the devices DMA mask is too small to address all memory in
- * the system, else %false. Lack of addressing bits is the prime reason for
- * bounce buffering, but might not be the only one.
- */
-bool dma_addressing_limited(struct device *dev)
+static bool __dma_addressing_limited(struct device *dev)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -930,6 +922,23 @@ bool dma_addressing_limited(struct device *dev)
return false;
return !dma_direct_all_ram_mapped(dev);
}
+
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev: device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false. Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+bool dma_addressing_limited(struct device *dev)
+{
+ if (!__dma_addressing_limited(dev))
+ return false;
+
+ dev_dbg(dev, "device is DMA addressing limited\n");
+ return true;
+}
EXPORT_SYMBOL_GPL(dma_addressing_limited);
size_t dma_max_mapping_size(struct device *dev)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e93c1956..95e7038 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3943,7 +3943,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
if (*perf_event_fasync(event))
- event->pending_kill = POLL_HUP;
+ event->pending_kill = POLL_ERR;
perf_event_wakeup(event);
} else {
@@ -6075,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
event->attr.pinned))
- return events;
+ return EPOLLERR;
/*
* Pin the event->rb by taking event->mmap_mutex; otherwise
diff --git a/kernel/fork.c b/kernel/fork.c
index c4b26cd..168681f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -498,10 +498,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
vma_numab_state_init(new);
dup_anon_vma_name(orig, new);
- /* track_pfn_copy() will later take care of copying internal state. */
- if (unlikely(new->vm_flags & VM_PFNMAP))
- untrack_pfn_clear(new);
-
return new;
}
@@ -672,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
+
+ /* track_pfn_copy() will later take care of copying internal state. */
+ if (unlikely(tmp->vm_flags & VM_PFNMAP))
+ untrack_pfn_clear(tmp);
+
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 5c8d43c..c05ba7c 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -761,7 +761,7 @@ static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fw
static void msi_domain_debug_show(struct seq_file *m, struct irq_domain *d,
struct irq_data *irqd, int ind)
{
- struct msi_desc *desc = irq_data_get_msi_desc(irqd);
+ struct msi_desc *desc = irqd ? irq_data_get_msi_desc(irqd) : NULL;
if (!desc)
return;
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index d7762ef..3927873 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -192,6 +192,11 @@
depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT
# Requires ELF object files.
depends on !LTO
+ # To avoid conflicts with the discarded __gendwarfksyms_ptr symbols on
+ # X86, requires pahole before commit 47dcb534e253 ("btf_encoder: Stop
+ # indexing symbols for VARs") or after commit 9810758003ce ("btf_encoder:
+ # Verify 0 address DWARF variables are in ELF section").
+ depends on !X86 || !DEBUG_INFO_BTF || PAHOLE_VERSION < 128 || PAHOLE_VERSION > 129
help
Calculate symbol versions from DWARF debugging information using
gendwarfksyms. Requires DEBUG_INFO to be enabled.
diff --git a/kernel/padata.c b/kernel/padata.c
index b3d4eac..7eee941 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -358,7 +358,8 @@ static void padata_reorder(struct parallel_data *pd)
* To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish.
*/
padata_get_pd(pd);
- queue_work(pinst->serial_wq, &pd->reorder_work);
+ if (!queue_work(pinst->serial_wq, &pd->reorder_work))
+ padata_put_pd(pd);
}
}
diff --git a/kernel/params.c b/kernel/params.c
index 2509f21..b92d6416 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -760,38 +760,35 @@ void destroy_params(const struct kernel_param *params, unsigned num)
params[i].ops->free(params[i].arg);
}
-static struct module_kobject * __init locate_module_kobject(const char *name)
+struct module_kobject __modinit * lookup_or_create_module_kobject(const char *name)
{
struct module_kobject *mk;
struct kobject *kobj;
int err;
kobj = kset_find_obj(module_kset, name);
- if (kobj) {
- mk = to_module_kobject(kobj);
- } else {
- mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
- BUG_ON(!mk);
+ if (kobj)
+ return to_module_kobject(kobj);
- mk->mod = THIS_MODULE;
- mk->kobj.kset = module_kset;
- err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
- "%s", name);
-#ifdef CONFIG_MODULES
- if (!err)
- err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
-#endif
- if (err) {
- kobject_put(&mk->kobj);
- pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
- name, err);
- return NULL;
- }
+ mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
+ if (!mk)
+ return NULL;
- /* So that we hold reference in both cases. */
- kobject_get(&mk->kobj);
+ mk->mod = THIS_MODULE;
+ mk->kobj.kset = module_kset;
+ err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name);
+ if (IS_ENABLED(CONFIG_MODULES) && !err)
+ err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
+ if (err) {
+ kobject_put(&mk->kobj);
+ pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
+ name, err);
+ return NULL;
}
+ /* So that we hold reference in both cases. */
+ kobject_get(&mk->kobj);
+
return mk;
}
@@ -802,7 +799,7 @@ static void __init kernel_add_sysfs_param(const char *name,
struct module_kobject *mk;
int err;
- mk = locate_module_kobject(name);
+ mk = lookup_or_create_module_kobject(name);
if (!mk)
return;
@@ -873,7 +870,7 @@ static void __init version_sysfs_builtin(void)
int err;
for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
- mk = locate_module_kobject(vattr->module_name);
+ mk = lookup_or_create_module_kobject(vattr->module_name);
if (mk) {
err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
WARN_ON_ONCE(err);
@@ -946,7 +943,9 @@ struct kset *module_kset;
static void module_kobj_release(struct kobject *kobj)
{
struct module_kobject *mk = to_module_kobject(kobj);
- complete(mk->kobj_completion);
+
+ if (mk->kobj_completion)
+ complete(mk->kobj_completion);
}
const struct kobj_type module_ktype = {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40..f513324 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
/*
* CPU cgroup support flags
*/
- SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */
+ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* DEPRECATED, will be removed on 6.18 */
SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE |
SCX_OPS_ENQ_LAST |
@@ -1118,8 +1118,38 @@ static void scx_kf_disallow(u32 mask)
current->scx.kf_mask &= ~mask;
}
-#define SCX_CALL_OP(mask, op, args...) \
+/*
+ * Track the rq currently locked.
+ *
+ * This allows kfuncs to safely operate on rq from any scx ops callback,
+ * knowing which rq is already locked.
+ */
+static DEFINE_PER_CPU(struct rq *, locked_rq);
+
+static inline void update_locked_rq(struct rq *rq)
+{
+ /*
+ * Check whether @rq is actually locked. This can help expose bugs
+ * or incorrect assumptions about the context in which a kfunc or
+ * callback is executed.
+ */
+ if (rq)
+ lockdep_assert_rq_held(rq);
+ __this_cpu_write(locked_rq, rq);
+}
+
+/*
+ * Return the rq currently locked from an scx callback, or NULL if no rq is
+ * locked.
+ */
+static inline struct rq *scx_locked_rq(void)
+{
+ return __this_cpu_read(locked_rq);
+}
+
+#define SCX_CALL_OP(mask, op, rq, args...) \
do { \
+ update_locked_rq(rq); \
if (mask) { \
scx_kf_allow(mask); \
scx_ops.op(args); \
@@ -1127,11 +1157,14 @@ do { \
} else { \
scx_ops.op(args); \
} \
+ update_locked_rq(NULL); \
} while (0)
-#define SCX_CALL_OP_RET(mask, op, args...) \
+#define SCX_CALL_OP_RET(mask, op, rq, args...) \
({ \
__typeof__(scx_ops.op(args)) __ret; \
+ \
+ update_locked_rq(rq); \
if (mask) { \
scx_kf_allow(mask); \
__ret = scx_ops.op(args); \
@@ -1139,6 +1172,7 @@ do { \
} else { \
__ret = scx_ops.op(args); \
} \
+ update_locked_rq(NULL); \
__ret; \
})
@@ -1153,31 +1187,31 @@ do { \
* scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on
* the specific task.
*/
-#define SCX_CALL_OP_TASK(mask, op, task, args...) \
+#define SCX_CALL_OP_TASK(mask, op, rq, task, args...) \
do { \
BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \
current->scx.kf_tasks[0] = task; \
- SCX_CALL_OP(mask, op, task, ##args); \
+ SCX_CALL_OP(mask, op, rq, task, ##args); \
current->scx.kf_tasks[0] = NULL; \
} while (0)
-#define SCX_CALL_OP_TASK_RET(mask, op, task, args...) \
+#define SCX_CALL_OP_TASK_RET(mask, op, rq, task, args...) \
({ \
__typeof__(scx_ops.op(task, ##args)) __ret; \
BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \
current->scx.kf_tasks[0] = task; \
- __ret = SCX_CALL_OP_RET(mask, op, task, ##args); \
+ __ret = SCX_CALL_OP_RET(mask, op, rq, task, ##args); \
current->scx.kf_tasks[0] = NULL; \
__ret; \
})
-#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...) \
+#define SCX_CALL_OP_2TASKS_RET(mask, op, rq, task0, task1, args...) \
({ \
__typeof__(scx_ops.op(task0, task1, ##args)) __ret; \
BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \
current->scx.kf_tasks[0] = task0; \
current->scx.kf_tasks[1] = task1; \
- __ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args); \
+ __ret = SCX_CALL_OP_RET(mask, op, rq, task0, task1, ##args); \
current->scx.kf_tasks[0] = NULL; \
current->scx.kf_tasks[1] = NULL; \
__ret; \
@@ -2172,7 +2206,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
WARN_ON_ONCE(*ddsp_taskp);
*ddsp_taskp = p;
- SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags);
+ SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags);
*ddsp_taskp = NULL;
if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
@@ -2269,7 +2303,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
add_nr_running(rq, 1);
if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p))
- SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags);
+ SCX_CALL_OP_TASK(SCX_KF_REST, runnable, rq, p, enq_flags);
if (enq_flags & SCX_ENQ_WAKEUP)
touch_core_sched(rq, p);
@@ -2283,7 +2317,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
__scx_add_event(SCX_EV_SELECT_CPU_FALLBACK, 1);
}
-static void ops_dequeue(struct task_struct *p, u64 deq_flags)
+static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags)
{
unsigned long opss;
@@ -2304,7 +2338,7 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags)
BUG();
case SCX_OPSS_QUEUED:
if (SCX_HAS_OP(dequeue))
- SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags);
+ SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, rq, p, deq_flags);
if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
SCX_OPSS_NONE))
@@ -2337,7 +2371,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
return true;
}
- ops_dequeue(p, deq_flags);
+ ops_dequeue(rq, p, deq_flags);
/*
* A currently running task which is going off @rq first gets dequeued
@@ -2353,11 +2387,11 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
*/
if (SCX_HAS_OP(stopping) && task_current(rq, p)) {
update_curr_scx(rq);
- SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false);
+ SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, false);
}
if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p))
- SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags);
+ SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, rq, p, deq_flags);
if (deq_flags & SCX_DEQ_SLEEP)
p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP;
@@ -2377,7 +2411,7 @@ static void yield_task_scx(struct rq *rq)
struct task_struct *p = rq->curr;
if (SCX_HAS_OP(yield))
- SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL);
+ SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, p, NULL);
else
p->scx.slice = 0;
}
@@ -2387,7 +2421,7 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
struct task_struct *from = rq->curr;
if (SCX_HAS_OP(yield))
- return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to);
+ return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, from, to);
else
return false;
}
@@ -2945,7 +2979,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
* emitted in switch_class().
*/
if (SCX_HAS_OP(cpu_acquire))
- SCX_CALL_OP(SCX_KF_REST, cpu_acquire, cpu_of(rq), NULL);
+ SCX_CALL_OP(SCX_KF_REST, cpu_acquire, rq, cpu_of(rq), NULL);
rq->scx.cpu_released = false;
}
@@ -2990,7 +3024,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
do {
dspc->nr_tasks = 0;
- SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq),
+ SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, rq, cpu_of(rq),
prev_on_scx ? prev : NULL);
flush_dispatch_buf(rq);
@@ -3104,7 +3138,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
* Core-sched might decide to execute @p before it is
* dispatched. Call ops_dequeue() to notify the BPF scheduler.
*/
- ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC);
+ ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC);
dispatch_dequeue(rq, p);
}
@@ -3112,7 +3146,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
/* see dequeue_task_scx() on why we skip when !QUEUED */
if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED))
- SCX_CALL_OP_TASK(SCX_KF_REST, running, p);
+ SCX_CALL_OP_TASK(SCX_KF_REST, running, rq, p);
clr_task_runnable(p, true);
@@ -3193,8 +3227,7 @@ static void switch_class(struct rq *rq, struct task_struct *next)
.task = next,
};
- SCX_CALL_OP(SCX_KF_CPU_RELEASE,
- cpu_release, cpu_of(rq), &args);
+ SCX_CALL_OP(SCX_KF_CPU_RELEASE, cpu_release, rq, cpu_of(rq), &args);
}
rq->scx.cpu_released = true;
}
@@ -3207,7 +3240,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
/* see dequeue_task_scx() on why we skip when !QUEUED */
if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED))
- SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true);
+ SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, true);
if (p->scx.flags & SCX_TASK_QUEUED) {
set_task_runnable(rq, p);
@@ -3348,7 +3381,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
* verifier.
*/
if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a)))
- return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before,
+ return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, NULL,
(struct task_struct *)a,
(struct task_struct *)b);
else
@@ -3385,7 +3418,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
*ddsp_taskp = p;
cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU,
- select_cpu, p, prev_cpu, wake_flags);
+ select_cpu, NULL, p, prev_cpu, wake_flags);
p->scx.selected_cpu = cpu;
*ddsp_taskp = NULL;
if (ops_cpu_valid(cpu, "from ops.select_cpu()"))
@@ -3430,8 +3463,8 @@ static void set_cpus_allowed_scx(struct task_struct *p,
* designation pointless. Cast it away when calling the operation.
*/
if (SCX_HAS_OP(set_cpumask))
- SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
- (struct cpumask *)p->cpus_ptr);
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, NULL,
+ p, (struct cpumask *)p->cpus_ptr);
}
static void handle_hotplug(struct rq *rq, bool online)
@@ -3444,9 +3477,9 @@ static void handle_hotplug(struct rq *rq, bool online)
scx_idle_update_selcpu_topology(&scx_ops);
if (online && SCX_HAS_OP(cpu_online))
- SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, NULL, cpu);
else if (!online && SCX_HAS_OP(cpu_offline))
- SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, NULL, cpu);
else
scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
"cpu %d going %s, exiting scheduler", cpu,
@@ -3550,7 +3583,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
curr->scx.slice = 0;
touch_core_sched(rq, curr);
} else if (SCX_HAS_OP(tick)) {
- SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr);
+ SCX_CALL_OP_TASK(SCX_KF_REST, tick, rq, curr);
}
if (!curr->scx.slice)
@@ -3627,7 +3660,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
.fork = fork,
};
- ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args);
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, NULL, p, &args);
if (unlikely(ret)) {
ret = ops_sanitize_err("init_task", ret);
return ret;
@@ -3668,9 +3701,10 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
static void scx_ops_enable_task(struct task_struct *p)
{
+ struct rq *rq = task_rq(p);
u32 weight;
- lockdep_assert_rq_held(task_rq(p));
+ lockdep_assert_rq_held(rq);
/*
* Set the weight before calling ops.enable() so that the scheduler
@@ -3684,20 +3718,22 @@ static void scx_ops_enable_task(struct task_struct *p)
p->scx.weight = sched_weight_to_cgroup(weight);
if (SCX_HAS_OP(enable))
- SCX_CALL_OP_TASK(SCX_KF_REST, enable, p);
+ SCX_CALL_OP_TASK(SCX_KF_REST, enable, rq, p);
scx_set_task_state(p, SCX_TASK_ENABLED);
if (SCX_HAS_OP(set_weight))
- SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight);
}
static void scx_ops_disable_task(struct task_struct *p)
{
- lockdep_assert_rq_held(task_rq(p));
+ struct rq *rq = task_rq(p);
+
+ lockdep_assert_rq_held(rq);
WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
if (SCX_HAS_OP(disable))
- SCX_CALL_OP_TASK(SCX_KF_REST, disable, p);
+ SCX_CALL_OP_TASK(SCX_KF_REST, disable, rq, p);
scx_set_task_state(p, SCX_TASK_READY);
}
@@ -3726,7 +3762,7 @@ static void scx_ops_exit_task(struct task_struct *p)
}
if (SCX_HAS_OP(exit_task))
- SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args);
+ SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, task_rq(p), p, &args);
scx_set_task_state(p, SCX_TASK_NONE);
}
@@ -3835,7 +3871,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p,
p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
if (SCX_HAS_OP(set_weight))
- SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight);
}
static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
@@ -3851,8 +3887,8 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p)
* different scheduler class. Keep the BPF scheduler up-to-date.
*/
if (SCX_HAS_OP(set_cpumask))
- SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
- (struct cpumask *)p->cpus_ptr);
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, rq,
+ p, (struct cpumask *)p->cpus_ptr);
}
static void switched_from_scx(struct rq *rq, struct task_struct *p)
@@ -3899,35 +3935,6 @@ bool scx_can_stop_tick(struct rq *rq)
DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
- if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
- cgroup_warned_missing_weight)
- return;
-
- if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
- return;
-
- pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
- scx_ops.name);
- cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
- if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
- return;
-
- if (!tg->idle)
- return;
-
- pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
- scx_ops.name);
- cgroup_warned_missing_idle = true;
-}
int scx_tg_online(struct task_group *tg)
{
@@ -3937,14 +3944,12 @@ int scx_tg_online(struct task_group *tg)
percpu_down_read(&scx_cgroup_rwsem);
- scx_cgroup_warn_missing_weight(tg);
-
if (scx_cgroup_enabled) {
if (SCX_HAS_OP(cgroup_init)) {
struct scx_cgroup_init_args args =
{ .weight = tg->scx_weight };
- ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL,
tg->css.cgroup, &args);
if (ret)
ret = ops_sanitize_err("cgroup_init", ret);
@@ -3966,7 +3971,7 @@ void scx_tg_offline(struct task_group *tg)
percpu_down_read(&scx_cgroup_rwsem);
if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED))
- SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, tg->css.cgroup);
tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
percpu_up_read(&scx_cgroup_rwsem);
@@ -3999,7 +4004,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
continue;
if (SCX_HAS_OP(cgroup_prep_move)) {
- ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move,
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, NULL,
p, from, css->cgroup);
if (ret)
goto err;
@@ -4013,8 +4018,8 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
err:
cgroup_taskset_for_each(p, css, tset) {
if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
- SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
- p->scx.cgrp_moving_from, css->cgroup);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL,
+ p, p->scx.cgrp_moving_from, css->cgroup);
p->scx.cgrp_moving_from = NULL;
}
@@ -4032,8 +4037,8 @@ void scx_cgroup_move_task(struct task_struct *p)
* cgrp_moving_from set.
*/
if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
- SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p,
- p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
+ SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, NULL,
+ p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
p->scx.cgrp_moving_from = NULL;
}
@@ -4052,8 +4057,8 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
cgroup_taskset_for_each(p, css, tset) {
if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
- SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
- p->scx.cgrp_moving_from, css->cgroup);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL,
+ p, p->scx.cgrp_moving_from, css->cgroup);
p->scx.cgrp_moving_from = NULL;
}
out_unlock:
@@ -4066,7 +4071,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
if (scx_cgroup_enabled && tg->scx_weight != weight) {
if (SCX_HAS_OP(cgroup_set_weight))
- SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
tg_cgrp(tg), weight);
tg->scx_weight = weight;
}
@@ -4076,9 +4081,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
void scx_group_set_idle(struct task_group *tg, bool idle)
{
- percpu_down_read(&scx_cgroup_rwsem);
- scx_cgroup_warn_missing_idle(tg);
- percpu_up_read(&scx_cgroup_rwsem);
+ /* TODO: Implement ops->cgroup_set_idle() */
}
static void scx_cgroup_lock(void)
@@ -4257,7 +4260,7 @@ static void scx_cgroup_exit(void)
continue;
rcu_read_unlock();
- SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, css->cgroup);
rcu_read_lock();
css_put(css);
@@ -4272,9 +4275,6 @@ static int scx_cgroup_init(void)
percpu_rwsem_assert_held(&scx_cgroup_rwsem);
- cgroup_warned_missing_weight = false;
- cgroup_warned_missing_idle = false;
-
/*
* scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
* cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4284,6 @@ static int scx_cgroup_init(void)
struct task_group *tg = css_tg(css);
struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
- scx_cgroup_warn_missing_weight(tg);
- scx_cgroup_warn_missing_idle(tg);
-
if ((tg->scx_flags &
(SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
continue;
@@ -4300,7 +4297,7 @@ static int scx_cgroup_init(void)
continue;
rcu_read_unlock();
- ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL,
css->cgroup, &args);
if (ret) {
css_put(css);
@@ -4623,7 +4620,7 @@ static void scx_ops_bypass(bool bypass)
static void free_exit_info(struct scx_exit_info *ei)
{
- kfree(ei->dump);
+ kvfree(ei->dump);
kfree(ei->msg);
kfree(ei->bt);
kfree(ei);
@@ -4639,7 +4636,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
- ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+ ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
if (!ei->bt || !ei->msg || !ei->dump) {
free_exit_info(ei);
@@ -4797,7 +4794,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
}
if (scx_ops.exit)
- SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, exit, NULL, ei);
cancel_delayed_work_sync(&scx_watchdog_work);
@@ -5004,7 +5001,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
if (SCX_HAS_OP(dump_task)) {
ops_dump_init(s, " ");
- SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p);
+ SCX_CALL_OP(SCX_KF_REST, dump_task, NULL, dctx, p);
ops_dump_exit();
}
@@ -5051,7 +5048,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
if (SCX_HAS_OP(dump)) {
ops_dump_init(&s, "");
- SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx);
+ SCX_CALL_OP(SCX_KF_UNLOCKED, dump, NULL, &dctx);
ops_dump_exit();
}
@@ -5108,7 +5105,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
used = seq_buf_used(&ns);
if (SCX_HAS_OP(dump_cpu)) {
ops_dump_init(&ns, " ");
- SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle);
+ SCX_CALL_OP(SCX_KF_REST, dump_cpu, NULL, &dctx, cpu, idle);
ops_dump_exit();
}
@@ -5252,6 +5249,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
return -EINVAL;
}
+ if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+ pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
return 0;
}
@@ -5364,7 +5364,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
scx_idle_enable(ops);
if (scx_ops.init) {
- ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init);
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init, NULL);
if (ret) {
ret = ops_sanitize_err("init", ret);
cpus_read_unlock();
@@ -6827,6 +6827,12 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
__alignof__(struct bpf_iter_scx_dsq));
+ /*
+ * next() and destroy() will be called regardless of the return value.
+ * Always clear $kit->dsq.
+ */
+ kit->dsq = NULL;
+
if (flags & ~__SCX_DSQ_ITER_USER_FLAGS)
return -EINVAL;
@@ -7113,13 +7119,32 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
}
if (ops_cpu_valid(cpu, NULL)) {
- struct rq *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq();
+ struct rq_flags rf;
+
+ /*
+ * When called with an rq lock held, restrict the operation
+ * to the corresponding CPU to prevent ABBA deadlocks.
+ */
+ if (locked_rq && rq != locked_rq) {
+ scx_ops_error("Invalid target CPU %d", cpu);
+ return;
+ }
+
+ /*
+ * If no rq lock is held, allow to operate on any CPU by
+ * acquiring the corresponding rq lock.
+ */
+ if (!locked_rq) {
+ rq_lock_irqsave(rq, &rf);
+ update_rq_clock(rq);
+ }
rq->scx.cpuperf_target = perf;
+ cpufreq_update_util(rq, 0);
- rcu_read_lock_sched_notrace();
- cpufreq_update_util(cpu_rq(cpu), 0);
- rcu_read_unlock_sched_notrace();
+ if (!locked_rq)
+ rq_unlock_irqrestore(rq, &rf);
}
}
@@ -7350,12 +7375,6 @@ BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
-BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE)
-BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE)
-BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE)
-BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle)
-BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index cb343ca..e67a19a 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -674,7 +674,7 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
* managed by put_prev_task_idle()/set_next_task_idle().
*/
if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq))
- SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
+ SCX_CALL_OP(SCX_KF_REST, update_idle, rq, cpu_of(rq), idle);
/*
* Update the idle masks:
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e43993a..0fb9bf9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7081,9 +7081,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
h_nr_idle = task_has_idle_policy(p);
if (task_sleep || task_delayed || !se->sched_delayed)
h_nr_runnable = 1;
- } else {
- cfs_rq = group_cfs_rq(se);
- slice = cfs_rq_min_slice(cfs_rq);
}
for_each_sched_entity(se) {
@@ -7093,6 +7090,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
if (p && &p->se == se)
return -1;
+ slice = cfs_rq_min_slice(cfs_rq);
break;
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1e67d07..a009c91 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
return ts;
}
+static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk)
+{
+ struct timespec64 ts;
+
+ ts.tv_sec = tk->xtime_sec;
+ ts.tv_nsec = tk->coarse_nsec;
+ return ts;
+}
+
+/*
+ * Update the nanoseconds part for the coarse time keepers. They can't rely
+ * on xtime_nsec because xtime_nsec could be adjusted by a small negative
+ * amount when the multiplication factor of the clock is adjusted, which
+ * could cause the coarse clocks to go slightly backwards. See
+ * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse
+ * clockids which only is updated when the clock has been set or we have
+ * accumulated time.
+ */
+static inline void tk_update_coarse_nsecs(struct timekeeper *tk)
+{
+ tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+}
+
static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec = ts->tv_sec;
tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
+ tk_update_coarse_nsecs(tk);
}
static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
@@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
tk->xtime_sec += ts->tv_sec;
tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
tk_normalize_xtime(tk);
+ tk_update_coarse_nsecs(tk);
}
static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
@@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
tk_normalize_xtime(tk);
delta -= incr;
}
+ tk_update_coarse_nsecs(tk);
}
/**
@@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset);
ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned int seq;
ktime_t base, *offset = offsets[offs];
+ unsigned int seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
@@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
do {
seq = read_seqcount_begin(&tk_core.seq);
base = ktime_add(tk->tkr_mono.base, *offset);
- nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsecs = tk->coarse_nsec;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
struct timekeeper *real_tk = &tk_core.timekeeper;
unsigned int clock_set = 0;
int shift = 0, maxshift;
- u64 offset;
+ u64 offset, orig_offset;
guard(raw_spinlock_irqsave)(&tk_core.lock);
@@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
tk->tkr_mono.clock->max_raw_delta);
-
+ orig_offset = offset;
/* Check if there's really nothing to do */
if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
return false;
@@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
*/
clock_set |= accumulate_nsecs_to_secs(tk);
+ /*
+ * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls
+ * making small negative adjustments to the base xtime_nsec
+ * value, only update the coarse clocks if we accumulated time
+ */
+ if (orig_offset != offset)
+ tk_update_coarse_nsecs(tk);
+
timekeeping_update_from_shadow(&tk_core, clock_set);
return !!clock_set;
@@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
} while (read_seqcount_retry(&tk_core.seq, seq));
}
EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
@@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
offset = tk_core.timekeeper.offs_real;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tk_xtime(tk);
+ now = tk_xtime_coarse(tk);
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
- now.tv_nsec + mono.tv_nsec);
+ now.tv_nsec + mono.tv_nsec);
}
EXPORT_SYMBOL(ktime_get_coarse_ts64);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 01c2ab1..32ef27c 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk)
/* CLOCK_REALTIME_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
vdso_ts->sec = tk->xtime_sec;
- vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ vdso_ts->nsec = tk->coarse_nsec;
/* CLOCK_MONOTONIC_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsec = tk->coarse_nsec;
nsec = nsec + tk->wall_to_monotonic.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 95c6e34..ba7ff14 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -454,7 +454,8 @@ static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head *
struct fprobe_hlist_node *node;
int ret = 0;
- hlist_for_each_entry_rcu(node, head, hlist) {
+ hlist_for_each_entry_rcu(node, head, hlist,
+ lockdep_is_held(&fprobe_mutex)) {
if (!within_module(node->addr, mod))
continue;
if (delete_fprobe_node(node))
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 61130bb..6981830 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3436,7 +3436,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
/* Copy the subops hash */
*filter_hash = alloc_and_copy_ftrace_hash(size_bits, subops_hash->filter_hash);
- if (!filter_hash)
+ if (!*filter_hash)
return -ENOMEM;
/* Remove any notrace functions from the copy */
remove_hash(*filter_hash, subops_hash->notrace_hash);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c0f877d..3f9bf56 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1887,10 +1887,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
head_page = cpu_buffer->head_page;
- /* If both the head and commit are on the reader_page then we are done. */
- if (head_page == cpu_buffer->reader_page &&
- head_page == cpu_buffer->commit_page)
+ /* If the commit_buffer is the reader page, update the commit page */
+ if (meta->commit_buffer == (unsigned long)cpu_buffer->reader_page->page) {
+ cpu_buffer->commit_page = cpu_buffer->reader_page;
+ /* Nothing more to do, the only page is the reader page */
goto done;
+ }
/* Iterate until finding the commit page */
for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8ddf6b1..5b8db27f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6043,8 +6043,10 @@ unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr)
tscratch = tr->scratch;
/* if there is no tscrach, module_delta must be NULL. */
module_delta = READ_ONCE(tr->module_delta);
- if (!module_delta || tscratch->entries[0].mod_addr > addr)
+ if (!module_delta || !tscratch->nr_entries ||
+ tscratch->entries[0].mod_addr > addr) {
return addr + tr->text_delta;
+ }
/* Note that entries must be sorted. */
nr_entries = tscratch->nr_entries;
@@ -6821,13 +6823,14 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
/* Copy the data into the page, so we can start over. */
ret = trace_seq_to_buffer(&iter->seq,
page_address(spd.pages[i]),
- trace_seq_used(&iter->seq));
+ min((size_t)trace_seq_used(&iter->seq),
+ PAGE_SIZE));
if (ret < 0) {
__free_page(spd.pages[i]);
break;
}
spd.partial[i].offset = 0;
- spd.partial[i].len = trace_seq_used(&iter->seq);
+ spd.partial[i].len = ret;
trace_seq_init(&iter->seq);
}
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index a322e4f2..5d64a18 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -16,7 +16,7 @@
#include "trace_output.h" /* for trace_event_sem */
#include "trace_dynevent.h"
-static DEFINE_MUTEX(dyn_event_ops_mutex);
+DEFINE_MUTEX(dyn_event_ops_mutex);
static LIST_HEAD(dyn_event_ops_list);
bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call)
@@ -116,6 +116,20 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
return ret;
}
+/*
+ * Locked version of event creation. The event creation must be protected by
+ * dyn_event_ops_mutex because of protecting trace_probe_log.
+ */
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type)
+{
+ int ret;
+
+ mutex_lock(&dyn_event_ops_mutex);
+ ret = type->create(raw_command);
+ mutex_unlock(&dyn_event_ops_mutex);
+ return ret;
+}
+
static int create_dyn_event(const char *raw_command)
{
struct dyn_event_operations *ops;
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 936477a..beee3f8 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos);
void dyn_event_seq_stop(struct seq_file *m, void *v);
int dyn_events_release_all(struct dyn_event_operations *type);
int dyn_event_release(const char *raw_command, struct dyn_event_operations *type);
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type);
/*
* for_each_dyn_event - iterate over the dyn_event list
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index c08355c..916555f 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -969,10 +969,13 @@ static int __trace_eprobe_create(int argc, const char *argv[])
goto error;
}
}
+ trace_probe_log_clear();
return ret;
+
parse_error:
ret = -EINVAL;
error:
+ trace_probe_log_clear();
trace_event_probe_cleanup(ep);
return ret;
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index b66b6d2..6e87ae2 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1560,7 +1560,7 @@ stacktrace_trigger(struct event_trigger_data *data,
struct trace_event_file *file = data->private_data;
if (file)
- __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+ __trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP);
else
trace_dump_stack(STACK_SKIP);
}
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 98ccf3f..4e37a0f 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -633,11 +633,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
static __always_inline void trace_stack(struct trace_array *tr)
{
- unsigned int trace_ctx;
-
- trace_ctx = tracing_gen_ctx();
-
- __trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP);
+ __trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP);
}
static void
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2703b96..3e5c47b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1089,7 +1089,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command)
if (raw_command[0] == '-')
return dyn_event_release(raw_command, &trace_kprobe_ops);
- ret = trace_kprobe_create(raw_command);
+ ret = dyn_event_create(raw_command, &trace_kprobe_ops);
return ret == -ECANCELED ? -EINVAL : ret;
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index fee40ff..b9ab06c 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1042,11 +1042,12 @@ enum print_line_t print_event_fields(struct trace_iterator *iter,
struct trace_event_call *call;
struct list_head *head;
+ lockdep_assert_held_read(&trace_event_sem);
+
/* ftrace defined events have separate call structures */
if (event->type <= __TRACE_LAST_TYPE) {
bool found = false;
- down_read(&trace_event_sem);
list_for_each_entry(call, &ftrace_events, list) {
if (call->event.type == event->type) {
found = true;
@@ -1056,7 +1057,6 @@ enum print_line_t print_event_fields(struct trace_iterator *iter,
if (call->event.type > __TRACE_LAST_TYPE)
break;
}
- up_read(&trace_event_sem);
if (!found) {
trace_seq_printf(&iter->seq, "UNKNOWN TYPE %d\n", event->type);
goto out;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 2eeecb6..424751c 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -154,9 +154,12 @@ static const struct fetch_type *find_fetch_type(const char *type, unsigned long
}
static struct trace_probe_log trace_probe_log;
+extern struct mutex dyn_event_ops_mutex;
void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
{
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
trace_probe_log.subsystem = subsystem;
trace_probe_log.argc = argc;
trace_probe_log.argv = argv;
@@ -165,11 +168,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
void trace_probe_log_clear(void)
{
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
memset(&trace_probe_log, 0, sizeof(trace_probe_log));
}
void trace_probe_log_set_index(int index)
{
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
trace_probe_log.index = index;
}
@@ -178,6 +185,8 @@ void __trace_probe_log_err(int offset, int err_type)
char *command, *p;
int i, len = 0, pos = 0;
+ lockdep_assert_held(&dyn_event_ops_mutex);
+
if (!trace_probe_log.argv)
return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 3386439..35cf76c 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -741,7 +741,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command)
if (raw_command[0] == '-')
return dyn_event_release(raw_command, &trace_uprobe_ops);
- ret = trace_uprobe_create(raw_command);
+ ret = dyn_event_create(raw_command, &trace_uprobe_ops);
return ret == -ECANCELED ? -EINVAL : ret;
}
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 2ef2e1b..2f844c2 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop);
* @arg: data to be passed to fn and handled_kill
* @name: the thread's name
*
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
* failure. The returned task is inactive, and the caller must fire it up
* through vhost_task_start().
*/
diff --git a/mm/execmem.c b/mm/execmem.c
index e6c4f50..6f7a265 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -254,6 +254,34 @@ static void *__execmem_cache_alloc(struct execmem_range *range, size_t size)
return ptr;
}
+static bool execmem_cache_rox = false;
+
+void execmem_cache_make_ro(void)
+{
+ struct maple_tree *free_areas = &execmem_cache.free_areas;
+ struct maple_tree *busy_areas = &execmem_cache.busy_areas;
+ MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
+ MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
+ struct mutex *mutex = &execmem_cache.mutex;
+ void *area;
+
+ execmem_cache_rox = true;
+
+ mutex_lock(mutex);
+
+ mas_for_each(&mas_free, area, ULONG_MAX) {
+ unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
+ set_memory_ro(mas_free.index, pages);
+ }
+
+ mas_for_each(&mas_busy, area, ULONG_MAX) {
+ unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
+ set_memory_ro(mas_busy.index, pages);
+ }
+
+ mutex_unlock(mutex);
+}
+
static int execmem_cache_populate(struct execmem_range *range, size_t size)
{
unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
@@ -274,9 +302,15 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
/* fill memory with instructions that will trap */
execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
- err = set_memory_rox((unsigned long)p, vm->nr_pages);
- if (err)
- goto err_free_mem;
+ if (execmem_cache_rox) {
+ err = set_memory_rox((unsigned long)p, vm->nr_pages);
+ if (err)
+ goto err_free_mem;
+ } else {
+ err = set_memory_x((unsigned long)p, vm->nr_pages);
+ if (err)
+ goto err_free_mem;
+ }
err = execmem_cache_add(p, alloc_size);
if (err)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a47682..47d76d0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, bool freeze, struct folio *folio)
{
+ bool pmd_migration = is_pmd_migration_entry(*pmd);
+
VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
@@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
* require a folio to check the PMD against. Otherwise, there
* is a risk of replacing the wrong folio.
*/
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
- is_pmd_migration_entry(*pmd)) {
- if (folio && folio != pmd_folio(*pmd))
+ if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+ /*
+ * Do not apply pmd_folio() to a migration entry; and folio lock
+ * guarantees that it must be of the wrong folio anyway.
+ */
+ if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
return;
__split_huge_pmd_locked(vma, pmd, address, freeze);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e3e6ac9..7ae38bf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
struct hugepage_subpool *spool = subpool_vma(vma);
struct hstate *h = hstate_vma(vma);
struct folio *folio;
- long retval, gbl_chg;
+ long retval, gbl_chg, gbl_reserve;
map_chg_state map_chg;
int ret, idx;
struct hugetlb_cgroup *h_cg = NULL;
@@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
h_cg);
out_subpool_put:
- if (map_chg)
- hugepage_subpool_put_pages(spool, 1);
+ /*
+ * put page to subpool iff the quota of subpool's rsv_hpages is used
+ * during hugepage_subpool_get_pages.
+ */
+ if (map_chg && !gbl_chg) {
+ gbl_reserve = hugepage_subpool_put_pages(spool, 1);
+ hugetlb_acct_memory(h, -gbl_reserve);
+ }
+
+
out_end_reservation:
if (map_chg != MAP_CHG_ENFORCED)
vma_end_reservation(h, vma, addr);
@@ -4034,10 +4042,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
list_for_each_entry_safe(folio, next, src_list, lru) {
int i;
+ bool cma;
if (folio_test_hugetlb_vmemmap_optimized(folio))
continue;
+ cma = folio_test_hugetlb_cma(folio);
+
list_del(&folio->lru);
split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
@@ -4053,6 +4064,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
new_folio->mapping = NULL;
init_new_hugetlb_folio(dst, new_folio);
+ /* Copy the CMA flag so that it is freed correctly */
+ if (cma)
+ folio_set_hugetlb_cma(new_folio);
list_add(&new_folio->lru, &dst_list);
}
}
@@ -7233,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
struct vm_area_struct *vma,
vm_flags_t vm_flags)
{
- long chg = -1, add = -1;
+ long chg = -1, add = -1, spool_resv, gbl_resv;
struct hstate *h = hstate_inode(inode);
struct hugepage_subpool *spool = subpool_inode(inode);
struct resv_map *resv_map;
@@ -7368,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode,
return true;
out_put_pages:
- /* put back original number of pages, chg */
- (void)hugepage_subpool_put_pages(spool, chg);
+ spool_resv = chg - gbl_reserve;
+ if (spool_resv) {
+ /* put sub pool's reservation back, chg - gbl_reserve */
+ gbl_resv = hugepage_subpool_put_pages(spool, spool_resv);
+ /*
+ * subpool's reserved pages can not be put back due to race,
+ * return to hstate.
+ */
+ hugetlb_acct_memory(h, -gbl_resv);
+ }
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
chg * pages_per_huge_page(h), h_cg);
diff --git a/mm/internal.h b/mm/internal.h
index e9695ba..5c7a2b4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -248,11 +248,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
bool *any_writable, bool *any_young, bool *any_dirty)
{
- unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
- const pte_t *end_ptep = start_ptep + max_nr;
pte_t expected_pte, *ptep;
bool writable, young, dirty;
- int nr;
+ int nr, cur_nr;
if (any_writable)
*any_writable = false;
@@ -265,11 +263,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
+ /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */
+ max_nr = min_t(unsigned long, max_nr,
+ folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte));
+
nr = pte_batch_hint(start_ptep, pte);
expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
ptep = start_ptep + nr;
- while (ptep < end_ptep) {
+ while (nr < max_nr) {
pte = ptep_get(ptep);
if (any_writable)
writable = !!pte_write(pte);
@@ -282,14 +284,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
if (!pte_same(pte, expected_pte))
break;
- /*
- * Stop immediately once we reached the end of the folio. In
- * corner cases the next PFN might fall into a different
- * folio.
- */
- if (pte_pfn(pte) >= folio_end_pfn)
- break;
-
if (any_writable)
*any_writable |= writable;
if (any_young)
@@ -297,12 +291,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
if (any_dirty)
*any_dirty |= dirty;
- nr = pte_batch_hint(ptep, pte);
- expected_pte = pte_advance_pfn(expected_pte, nr);
- ptep += nr;
+ cur_nr = pte_batch_hint(ptep, pte);
+ expected_pte = pte_advance_pfn(expected_pte, cur_nr);
+ ptep += cur_nr;
+ nr += cur_nr;
}
- return min(ptep - start_ptep, max_nr);
+ return min(nr, max_nr);
}
/**
@@ -1595,7 +1590,6 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc);
#ifdef CONFIG_UNACCEPTED_MEMORY
void accept_page(struct page *page);
-void unaccepted_cleanup_work(struct work_struct *work);
#else /* CONFIG_UNACCEPTED_MEMORY */
static inline void accept_page(struct page *page)
{
diff --git a/mm/memblock.c b/mm/memblock.c
index 0a53db4d..0e9ebb8 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -457,7 +457,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
min(new_area_start, memblock.current_limit),
new_alloc_size, PAGE_SIZE);
- new_array = addr ? __va(addr) : NULL;
+ if (addr) {
+ /* The memory may not have been accepted, yet. */
+ accept_memory(addr, new_alloc_size);
+
+ new_array = __va(addr);
+ } else {
+ new_array = NULL;
+ }
}
if (!addr) {
pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
@@ -2183,11 +2190,14 @@ static void __init memmap_init_reserved_pages(void)
struct memblock_region *region;
phys_addr_t start, end;
int nid;
+ unsigned long max_reserved;
/*
* set nid on all reserved pages and also treat struct
* pages for the NOMAP regions as PageReserved
*/
+repeat:
+ max_reserved = memblock.reserved.max;
for_each_mem_region(region) {
nid = memblock_get_region_node(region);
start = region->base;
@@ -2196,8 +2206,15 @@ static void __init memmap_init_reserved_pages(void)
if (memblock_is_nomap(region))
reserve_bootmem_region(start, end, nid);
- memblock_set_node(start, end, &memblock.reserved, nid);
+ memblock_set_node(start, region->size, &memblock.reserved, nid);
}
+ /*
+ * 'max' is changed means memblock.reserved has been doubled its
+ * array, which may result a new reserved region before current
+ * 'start'. Now we should repeat the procedure to set its node id.
+ */
+ if (max_reserved != memblock.reserved.max)
+ goto repeat;
/*
* initialize struct pages for reserved regions that don't have
diff --git a/mm/memory.c b/mm/memory.c
index ba3ea0a..4919941 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3751,7 +3751,7 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
/* Stabilize the mapcount vs. refcount and recheck. */
folio_lock_large_mapcount(folio);
- VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+ VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio);
if (folio_test_large_maybe_mapped_shared(folio))
goto unlock;
diff --git a/mm/migrate.c b/mm/migrate.c
index f3ee6d8..676d9cf 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -845,9 +845,11 @@ static int __buffer_migrate_folio(struct address_space *mapping,
return -EAGAIN;
if (check_refs) {
- bool busy;
+ bool busy, migrating;
bool invalidated = false;
+ migrating = test_and_set_bit_lock(BH_Migrate, &head->b_state);
+ VM_WARN_ON_ONCE(migrating);
recheck_buffers:
busy = false;
spin_lock(&mapping->i_private_lock);
@@ -859,12 +861,12 @@ static int __buffer_migrate_folio(struct address_space *mapping,
}
bh = bh->b_this_page;
} while (bh != head);
+ spin_unlock(&mapping->i_private_lock);
if (busy) {
if (invalidated) {
rc = -EAGAIN;
goto unlock_buffers;
}
- spin_unlock(&mapping->i_private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
@@ -883,7 +885,7 @@ static int __buffer_migrate_folio(struct address_space *mapping,
unlock_buffers:
if (check_refs)
- spin_unlock(&mapping->i_private_lock);
+ clear_bit_unlock(BH_Migrate, &head->b_state);
bh = head;
do {
unlock_buffer(bh);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 9659689..eedce93 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1441,7 +1441,6 @@ static void __meminit zone_init_free_lists(struct zone *zone)
#ifdef CONFIG_UNACCEPTED_MEMORY
INIT_LIST_HEAD(&zone->unaccepted_pages);
- INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work);
#endif
}
@@ -1786,7 +1785,7 @@ static bool arch_has_descending_max_zone_pfns(void)
return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
}
-static void set_high_memory(void)
+static void __init set_high_memory(void)
{
phys_addr_t highmem = memblock_end_of_DRAM();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5669baf..8258349 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -290,7 +290,8 @@ EXPORT_SYMBOL(nr_online_nodes);
#endif
static bool page_contains_unaccepted(struct page *page, unsigned int order);
-static bool cond_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+ int alloc_flags);
static bool __free_unaccepted(struct page *page);
int page_group_by_mobility_disabled __read_mostly;
@@ -1151,14 +1152,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
__pgalloc_tag_sub(page, nr);
}
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
+/* When tag is not NULL, assuming mem_alloc_profiling_enabled */
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
{
- struct alloc_tag *tag;
-
- if (!mem_alloc_profiling_enabled())
- return;
-
- tag = __pgalloc_tag_get(page);
if (tag)
this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr);
}
@@ -1168,7 +1164,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr)
static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
unsigned int nr) {}
static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
-static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) {}
+static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
#endif /* CONFIG_MEM_ALLOC_PROFILING */
@@ -3616,7 +3612,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
}
- cond_accept_memory(zone, order);
+ cond_accept_memory(zone, order, alloc_flags);
/*
* Detect whether the number of free pages is below high
@@ -3643,7 +3639,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
gfp_mask)) {
int ret;
- if (cond_accept_memory(zone, order))
+ if (cond_accept_memory(zone, order, alloc_flags))
goto try_this_zone;
/*
@@ -3696,7 +3692,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
return page;
} else {
- if (cond_accept_memory(zone, order))
+ if (cond_accept_memory(zone, order, alloc_flags))
goto try_this_zone;
/* Try again if zone has deferred pages */
@@ -4849,7 +4845,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
goto failed;
}
- cond_accept_memory(zone, 0);
+ cond_accept_memory(zone, 0, alloc_flags);
retry_this_zone:
mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
if (zone_watermark_fast(zone, 0, mark,
@@ -4858,7 +4854,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
break;
}
- if (cond_accept_memory(zone, 0))
+ if (cond_accept_memory(zone, 0, alloc_flags))
goto retry_this_zone;
/* Try again if zone has deferred pages */
@@ -5065,11 +5061,13 @@ static void ___free_pages(struct page *page, unsigned int order,
{
/* get PageHead before we drop reference */
int head = PageHead(page);
+ /* get alloc tag in case the page is released by others */
+ struct alloc_tag *tag = pgalloc_tag_get(page);
if (put_page_testzero(page))
__free_frozen_pages(page, order, fpi_flags);
else if (!head) {
- pgalloc_tag_sub_pages(page, (1 << order) - 1);
+ pgalloc_tag_sub_pages(tag, (1 << order) - 1);
while (order-- > 0)
__free_frozen_pages(page + (1 << order), order,
fpi_flags);
@@ -7174,16 +7172,8 @@ bool has_managed_dma(void)
#ifdef CONFIG_UNACCEPTED_MEMORY
-/* Counts number of zones with unaccepted pages. */
-static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
-
static bool lazy_accept = true;
-void unaccepted_cleanup_work(struct work_struct *work)
-{
- static_branch_dec(&zones_with_unaccepted_pages);
-}
-
static int __init accept_memory_parse(char *p)
{
if (!strcmp(p, "lazy")) {
@@ -7208,11 +7198,7 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
static void __accept_page(struct zone *zone, unsigned long *flags,
struct page *page)
{
- bool last;
-
list_del(&page->lru);
- last = list_empty(&zone->unaccepted_pages);
-
account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
__ClearPageUnaccepted(page);
@@ -7221,28 +7207,6 @@ static void __accept_page(struct zone *zone, unsigned long *flags,
accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER);
__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
-
- if (last) {
- /*
- * There are two corner cases:
- *
- * - If allocation occurs during the CPU bring up,
- * static_branch_dec() cannot be used directly as
- * it causes a deadlock on cpu_hotplug_lock.
- *
- * Instead, use schedule_work() to prevent deadlock.
- *
- * - If allocation occurs before workqueues are initialized,
- * static_branch_dec() should be called directly.
- *
- * Workqueues are initialized before CPU bring up, so this
- * will not conflict with the first scenario.
- */
- if (system_wq)
- schedule_work(&zone->unaccepted_cleanup);
- else
- unaccepted_cleanup_work(&zone->unaccepted_cleanup);
- }
}
void accept_page(struct page *page)
@@ -7279,20 +7243,17 @@ static bool try_to_accept_memory_one(struct zone *zone)
return true;
}
-static inline bool has_unaccepted_memory(void)
-{
- return static_branch_unlikely(&zones_with_unaccepted_pages);
-}
-
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+ int alloc_flags)
{
long to_accept, wmark;
bool ret = false;
- if (!has_unaccepted_memory())
+ if (list_empty(&zone->unaccepted_pages))
return false;
- if (list_empty(&zone->unaccepted_pages))
+ /* Bailout, since try_to_accept_memory_one() needs to take a lock */
+ if (alloc_flags & ALLOC_TRYLOCK)
return false;
wmark = promo_wmark_pages(zone);
@@ -7325,22 +7286,17 @@ static bool __free_unaccepted(struct page *page)
{
struct zone *zone = page_zone(page);
unsigned long flags;
- bool first = false;
if (!lazy_accept)
return false;
spin_lock_irqsave(&zone->lock, flags);
- first = list_empty(&zone->unaccepted_pages);
list_add_tail(&page->lru, &zone->unaccepted_pages);
account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
__mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
__SetPageUnaccepted(page);
spin_unlock_irqrestore(&zone->lock, flags);
- if (first)
- static_branch_inc(&zones_with_unaccepted_pages);
-
return true;
}
@@ -7351,7 +7307,8 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order)
return false;
}
-static bool cond_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order,
+ int alloc_flags)
{
return false;
}
@@ -7422,11 +7379,6 @@ struct page *try_alloc_pages_noprof(int nid, unsigned int order)
if (!pcp_allowed_order(order))
return NULL;
-#ifdef CONFIG_UNACCEPTED_MEMORY
- /* Bailout, since try_to_accept_memory_one() needs to take a lock */
- if (has_unaccepted_memory())
- return NULL;
-#endif
/* Bailout, since _deferred_grow_zone() needs to take a lock */
if (deferred_pages_enabled())
return NULL;
diff --git a/mm/slub.c b/mm/slub.c
index dc9e729..be8b09e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2028,8 +2028,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
return 0;
}
-/* Should be called only if mem_alloc_profiling_enabled() */
-static noinline void free_slab_obj_exts(struct slab *slab)
+static inline void free_slab_obj_exts(struct slab *slab)
{
struct slabobj_ext *obj_exts;
@@ -2049,18 +2048,6 @@ static noinline void free_slab_obj_exts(struct slab *slab)
slab->obj_exts = 0;
}
-static inline bool need_slab_obj_ext(void)
-{
- if (mem_alloc_profiling_enabled())
- return true;
-
- /*
- * CONFIG_MEMCG creates vector of obj_cgroup objects conditionally
- * inside memcg_slab_post_alloc_hook. No other users for now.
- */
- return false;
-}
-
#else /* CONFIG_SLAB_OBJ_EXT */
static inline void init_slab_obj_exts(struct slab *slab)
@@ -2077,11 +2064,6 @@ static inline void free_slab_obj_exts(struct slab *slab)
{
}
-static inline bool need_slab_obj_ext(void)
-{
- return false;
-}
-
#endif /* CONFIG_SLAB_OBJ_EXT */
#ifdef CONFIG_MEM_ALLOC_PROFILING
@@ -2129,7 +2111,7 @@ __alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
static inline void
alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
{
- if (need_slab_obj_ext())
+ if (mem_alloc_profiling_enabled())
__alloc_tagging_slab_alloc_hook(s, object, flags);
}
@@ -2601,8 +2583,12 @@ static __always_inline void account_slab(struct slab *slab, int order,
static __always_inline void unaccount_slab(struct slab *slab, int order,
struct kmem_cache *s)
{
- if (memcg_kmem_online() || need_slab_obj_ext())
- free_slab_obj_exts(slab);
+ /*
+ * The slab object extensions should now be freed regardless of
+ * whether mem_alloc_profiling_enabled() or not because profiling
+ * might have been disabled after slab->obj_exts got allocated.
+ */
+ free_slab_obj_exts(slab);
mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-(PAGE_SIZE << order));
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2eff8b5..412ccd6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
- /*
- * Should not even be attempting large allocations when huge
- * page swap is disabled. Warn and fail the allocation.
- */
- if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
- VM_WARN_ON_ONCE(1);
- return -EINVAL;
+ if (order) {
+ /*
+ * Reject large allocation when THP_SWAP is disabled,
+ * the caller should split the folio and try again.
+ */
+ if (!IS_ENABLED(CONFIG_THP_SWAP))
+ return -EAGAIN;
+
+ /*
+ * Allocation size should never exceed cluster size
+ * (HPAGE_PMD_SIZE).
+ */
+ if (size > SWAPFILE_CLUSTER) {
+ VM_WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
}
local_lock(&percpu_swap_cluster.lock);
@@ -3323,6 +3332,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
}
/*
+ * The swap subsystem needs a major overhaul to support this.
+ * It doesn't work yet so just disable it for now.
+ */
+ if (mapping_min_folio_order(mapping) > 0) {
+ error = -EINVAL;
+ goto bad_swap_unlock_inode;
+ }
+
+ /*
* Read the swap header.
*/
if (!mapping->a_ops->read_folio) {
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 7d5d709..e0db855 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_struct *mm,
src_folio->index = linear_page_index(dst_vma, dst_addr);
orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
- /* Follow mremap() behavior and treat the entry dirty after the move */
- orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+ /* Set soft dirty bit so userspace can notice the pte was moved */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
+#endif
+ if (pte_dirty(orig_src_pte))
+ orig_dst_pte = pte_mkdirty(orig_dst_pte);
+ orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma);
set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
out:
@@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
}
orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
+#endif
set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
double_pt_unlock(dst_ptl, src_ptl);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3ed720a..2d75116 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm,
{
vm->flags = flags;
vm->addr = (void *)va->va_start;
- vm->size = va_size(va);
+ vm->size = vm->requested_size = va_size(va);
vm->caller = caller;
va->vm = vm;
}
@@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size,
area->flags = flags;
area->caller = caller;
+ area->requested_size = requested_size;
va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
if (IS_ERR(va)) {
@@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof);
*/
void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
{
+ struct vm_struct *vm = NULL;
+ size_t alloced_size = 0;
size_t old_size = 0;
void *n;
@@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
}
if (p) {
- struct vm_struct *vm;
-
vm = find_vm_area(p);
if (unlikely(!vm)) {
WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
return NULL;
}
- old_size = get_vm_area_size(vm);
+ alloced_size = get_vm_area_size(vm);
+ old_size = vm->requested_size;
+ if (WARN(alloced_size < old_size,
+ "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
+ return NULL;
}
/*
@@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
* would be a good heuristic for when to shrink the vm_area?
*/
if (size <= old_size) {
- /* Zero out spare memory. */
- if (want_init_on_alloc(flags))
+ /* Zero out "freed" memory. */
+ if (want_init_on_free())
memset((void *)p + size, 0, old_size - size);
+ vm->requested_size = size;
kasan_poison_vmalloc(p + size, old_size - size);
- kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
return (void *)p;
}
+ /*
+ * We already have the bytes available in the allocation; use them.
+ */
+ if (size <= alloced_size) {
+ kasan_unpoison_vmalloc(p + old_size, size - old_size,
+ KASAN_VMALLOC_PROT_NORMAL);
+ /* Zero out "alloced" memory. */
+ if (want_init_on_alloc(flags))
+ memset((void *)p + old_size, 0, size - old_size);
+ vm->requested_size = size;
+ }
+
/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
n = __vmalloc_noprof(size, flags);
if (!n)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 961b270..d14a7e3 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1243,19 +1243,19 @@ void zs_obj_write(struct zs_pool *pool, unsigned long handle,
class = zspage_class(pool, zspage);
off = offset_in_page(class->size * obj_idx);
- if (off + class->size <= PAGE_SIZE) {
+ if (!ZsHugePage(zspage))
+ off += ZS_HANDLE_SIZE;
+
+ if (off + mem_len <= PAGE_SIZE) {
/* this object is contained entirely within a page */
void *dst = kmap_local_zpdesc(zpdesc);
- if (!ZsHugePage(zspage))
- off += ZS_HANDLE_SIZE;
memcpy(dst + off, handle_mem, mem_len);
kunmap_local(dst);
} else {
/* this object spans two pages */
size_t sizes[2];
- off += ZS_HANDLE_SIZE;
sizes[0] = PAGE_SIZE - off;
sizes[1] = mem_len - sizes[0];
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 7cd4bdce..558d39d 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -506,28 +506,32 @@ batadv_hardif_is_iface_up(const struct batadv_hard_iface *hard_iface)
return false;
}
-static void batadv_check_known_mac_addr(const struct net_device *net_dev)
+static void batadv_check_known_mac_addr(const struct batadv_hard_iface *hard_iface)
{
- const struct batadv_hard_iface *hard_iface;
+ const struct net_device *mesh_iface = hard_iface->mesh_iface;
+ const struct batadv_hard_iface *tmp_hard_iface;
- rcu_read_lock();
- list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
- if (hard_iface->if_status != BATADV_IF_ACTIVE &&
- hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
+ if (!mesh_iface)
+ return;
+
+ list_for_each_entry(tmp_hard_iface, &batadv_hardif_list, list) {
+ if (tmp_hard_iface == hard_iface)
continue;
- if (hard_iface->net_dev == net_dev)
+ if (tmp_hard_iface->mesh_iface != mesh_iface)
continue;
- if (!batadv_compare_eth(hard_iface->net_dev->dev_addr,
- net_dev->dev_addr))
+ if (tmp_hard_iface->if_status == BATADV_IF_NOT_IN_USE)
+ continue;
+
+ if (!batadv_compare_eth(tmp_hard_iface->net_dev->dev_addr,
+ hard_iface->net_dev->dev_addr))
continue;
pr_warn("The newly added mac address (%pM) already exists on: %s\n",
- net_dev->dev_addr, hard_iface->net_dev->name);
+ hard_iface->net_dev->dev_addr, tmp_hard_iface->net_dev->name);
pr_warn("It is strongly recommended to keep mac addresses unique to avoid problems!\n");
}
- rcu_read_unlock();
}
/**
@@ -763,6 +767,8 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
hard_iface->net_dev->name, hardif_mtu,
required_mtu);
+ batadv_check_known_mac_addr(hard_iface);
+
if (batadv_hardif_is_iface_up(hard_iface))
batadv_hardif_activate_interface(hard_iface);
else
@@ -901,7 +907,6 @@ batadv_hardif_add_interface(struct net_device *net_dev)
batadv_v_hardif_init(hard_iface);
- batadv_check_known_mac_addr(hard_iface->net_dev);
kref_get(&hard_iface->refcount);
list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list);
batadv_hardif_generation++;
@@ -988,7 +993,7 @@ static int batadv_hard_if_event(struct notifier_block *this,
if (hard_iface->if_status == BATADV_IF_NOT_IN_USE)
goto hardif_put;
- batadv_check_known_mac_addr(hard_iface->net_dev);
+ batadv_check_known_mac_addr(hard_iface);
bat_priv = netdev_priv(hard_iface->mesh_iface);
bat_priv->algo_ops->iface.update_mac(hard_iface);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7e1b538..946d2ae 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -2064,95 +2064,6 @@ static int create_big_sync(struct hci_dev *hdev, void *data)
return hci_le_create_big(conn, &conn->iso_qos);
}
-static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
-{
- bt_dev_dbg(hdev, "");
-
- if (err)
- bt_dev_err(hdev, "Unable to create PA: %d", err);
-}
-
-static bool hci_conn_check_create_pa_sync(struct hci_conn *conn)
-{
- if (conn->type != ISO_LINK || conn->sid == HCI_SID_INVALID)
- return false;
-
- return true;
-}
-
-static int create_pa_sync(struct hci_dev *hdev, void *data)
-{
- struct hci_cp_le_pa_create_sync cp = {0};
- struct hci_conn *conn;
- int err = 0;
-
- hci_dev_lock(hdev);
-
- rcu_read_lock();
-
- /* The spec allows only one pending LE Periodic Advertising Create
- * Sync command at a time. If the command is pending now, don't do
- * anything. We check for pending connections after each PA Sync
- * Established event.
- *
- * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
- * page 2493:
- *
- * If the Host issues this command when another HCI_LE_Periodic_
- * Advertising_Create_Sync command is pending, the Controller shall
- * return the error code Command Disallowed (0x0C).
- */
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (test_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags))
- goto unlock;
- }
-
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (hci_conn_check_create_pa_sync(conn)) {
- struct bt_iso_qos *qos = &conn->iso_qos;
-
- cp.options = qos->bcast.options;
- cp.sid = conn->sid;
- cp.addr_type = conn->dst_type;
- bacpy(&cp.addr, &conn->dst);
- cp.skip = cpu_to_le16(qos->bcast.skip);
- cp.sync_timeout = cpu_to_le16(qos->bcast.sync_timeout);
- cp.sync_cte_type = qos->bcast.sync_cte_type;
-
- break;
- }
- }
-
-unlock:
- rcu_read_unlock();
-
- hci_dev_unlock(hdev);
-
- if (bacmp(&cp.addr, BDADDR_ANY)) {
- hci_dev_set_flag(hdev, HCI_PA_SYNC);
- set_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
-
- err = __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC,
- sizeof(cp), &cp, HCI_CMD_TIMEOUT);
- if (!err)
- err = hci_update_passive_scan_sync(hdev);
-
- if (err) {
- hci_dev_clear_flag(hdev, HCI_PA_SYNC);
- clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
- }
- }
-
- return err;
-}
-
-int hci_pa_create_sync_pending(struct hci_dev *hdev)
-{
- /* Queue start pa_create_sync and scan */
- return hci_cmd_sync_queue(hdev, create_pa_sync,
- NULL, create_pa_complete);
-}
-
struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, __u8 sid,
struct bt_iso_qos *qos)
@@ -2167,97 +2078,18 @@ struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
conn->dst_type = dst_type;
conn->sid = sid;
conn->state = BT_LISTEN;
+ conn->conn_timeout = msecs_to_jiffies(qos->bcast.sync_timeout * 10);
hci_conn_hold(conn);
- hci_pa_create_sync_pending(hdev);
+ hci_connect_pa_sync(hdev, conn);
return conn;
}
-static bool hci_conn_check_create_big_sync(struct hci_conn *conn)
-{
- if (!conn->num_bis)
- return false;
-
- return true;
-}
-
-static void big_create_sync_complete(struct hci_dev *hdev, void *data, int err)
-{
- bt_dev_dbg(hdev, "");
-
- if (err)
- bt_dev_err(hdev, "Unable to create BIG sync: %d", err);
-}
-
-static int big_create_sync(struct hci_dev *hdev, void *data)
-{
- DEFINE_FLEX(struct hci_cp_le_big_create_sync, pdu, bis, num_bis, 0x11);
- struct hci_conn *conn;
-
- rcu_read_lock();
-
- pdu->num_bis = 0;
-
- /* The spec allows only one pending LE BIG Create Sync command at
- * a time. If the command is pending now, don't do anything. We
- * check for pending connections after each BIG Sync Established
- * event.
- *
- * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
- * page 2586:
- *
- * If the Host sends this command when the Controller is in the
- * process of synchronizing to any BIG, i.e. the HCI_LE_BIG_Sync_
- * Established event has not been generated, the Controller shall
- * return the error code Command Disallowed (0x0C).
- */
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (test_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags))
- goto unlock;
- }
-
- list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) {
- if (hci_conn_check_create_big_sync(conn)) {
- struct bt_iso_qos *qos = &conn->iso_qos;
-
- set_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
-
- pdu->handle = qos->bcast.big;
- pdu->sync_handle = cpu_to_le16(conn->sync_handle);
- pdu->encryption = qos->bcast.encryption;
- memcpy(pdu->bcode, qos->bcast.bcode,
- sizeof(pdu->bcode));
- pdu->mse = qos->bcast.mse;
- pdu->timeout = cpu_to_le16(qos->bcast.timeout);
- pdu->num_bis = conn->num_bis;
- memcpy(pdu->bis, conn->bis, conn->num_bis);
-
- break;
- }
- }
-
-unlock:
- rcu_read_unlock();
-
- if (!pdu->num_bis)
- return 0;
-
- return hci_send_cmd(hdev, HCI_OP_LE_BIG_CREATE_SYNC,
- struct_size(pdu, bis, pdu->num_bis), pdu);
-}
-
-int hci_le_big_create_sync_pending(struct hci_dev *hdev)
-{
- /* Queue big_create_sync */
- return hci_cmd_sync_queue_once(hdev, big_create_sync,
- NULL, big_create_sync_complete);
-}
-
-int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
- struct bt_iso_qos *qos,
- __u16 sync_handle, __u8 num_bis, __u8 bis[])
+int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
+ struct bt_iso_qos *qos, __u16 sync_handle,
+ __u8 num_bis, __u8 bis[])
{
int err;
@@ -2274,9 +2106,10 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon,
hcon->num_bis = num_bis;
memcpy(hcon->bis, bis, num_bis);
+ hcon->conn_timeout = msecs_to_jiffies(qos->bcast.timeout * 10);
}
- return hci_le_big_create_sync_pending(hdev);
+ return hci_connect_big_sync(hdev, hcon);
}
static void create_big_complete(struct hci_dev *hdev, void *data, int err)
@@ -3190,3 +3023,27 @@ void hci_conn_tx_dequeue(struct hci_conn *conn)
kfree_skb(skb);
}
+
+u8 *hci_conn_key_enc_size(struct hci_conn *conn)
+{
+ if (conn->type == ACL_LINK) {
+ struct link_key *key;
+
+ key = hci_find_link_key(conn->hdev, &conn->dst);
+ if (!key)
+ return NULL;
+
+ return &key->pin_len;
+ } else if (conn->type == LE_LINK) {
+ struct smp_ltk *ltk;
+
+ ltk = hci_find_ltk(conn->hdev, &conn->dst, conn->dst_type,
+ conn->role);
+ if (!ltk)
+ return NULL;
+
+ return <k->enc_size;
+ }
+
+ return NULL;
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5f808f0..c38ada6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -739,10 +739,17 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data,
handle);
conn->enc_key_size = 0;
} else {
+ u8 *key_enc_size = hci_conn_key_enc_size(conn);
+
conn->enc_key_size = rp->key_size;
status = 0;
- if (conn->enc_key_size < hdev->min_enc_key_size) {
+ /* Attempt to check if the key size is too small or if it has
+ * been downgraded from the last time it was stored as part of
+ * the link_key.
+ */
+ if (conn->enc_key_size < hdev->min_enc_key_size ||
+ (key_enc_size && conn->enc_key_size < *key_enc_size)) {
/* As slave role, the conn->state has been set to
* BT_CONNECTED and l2cap conn req might not be received
* yet, at this moment the l2cap layer almost does
@@ -755,6 +762,10 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data,
clear_bit(HCI_CONN_ENCRYPT, &conn->flags);
clear_bit(HCI_CONN_AES_CCM, &conn->flags);
}
+
+ /* Update the key encryption size with the connection one */
+ if (key_enc_size && *key_enc_size != conn->enc_key_size)
+ *key_enc_size = conn->enc_key_size;
}
hci_encrypt_cfm(conn, status);
@@ -3065,6 +3076,34 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, void *edata,
hci_dev_unlock(hdev);
}
+static int hci_read_enc_key_size(struct hci_dev *hdev, struct hci_conn *conn)
+{
+ struct hci_cp_read_enc_key_size cp;
+ u8 *key_enc_size = hci_conn_key_enc_size(conn);
+
+ if (!read_key_size_capable(hdev)) {
+ conn->enc_key_size = HCI_LINK_KEY_SIZE;
+ return -EOPNOTSUPP;
+ }
+
+ bt_dev_dbg(hdev, "hcon %p", conn);
+
+ memset(&cp, 0, sizeof(cp));
+ cp.handle = cpu_to_le16(conn->handle);
+
+ /* If the key enc_size is already known, use it as conn->enc_key_size,
+ * otherwise use hdev->min_enc_key_size so the likes of
+ * l2cap_check_enc_key_size don't fail while waiting for
+ * HCI_OP_READ_ENC_KEY_SIZE response.
+ */
+ if (key_enc_size && *key_enc_size)
+ conn->enc_key_size = *key_enc_size;
+ else
+ conn->enc_key_size = hdev->min_enc_key_size;
+
+ return hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp);
+}
+
static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
struct sk_buff *skb)
{
@@ -3157,23 +3196,11 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) &&
ev->link_type == ACL_LINK) {
struct link_key *key;
- struct hci_cp_read_enc_key_size cp;
key = hci_find_link_key(hdev, &ev->bdaddr);
if (key) {
set_bit(HCI_CONN_ENCRYPT, &conn->flags);
-
- if (!read_key_size_capable(hdev)) {
- conn->enc_key_size = HCI_LINK_KEY_SIZE;
- } else {
- cp.handle = cpu_to_le16(conn->handle);
- if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE,
- sizeof(cp), &cp)) {
- bt_dev_err(hdev, "sending read key size failed");
- conn->enc_key_size = HCI_LINK_KEY_SIZE;
- }
- }
-
+ hci_read_enc_key_size(hdev, conn);
hci_encrypt_cfm(conn, ev->status);
}
}
@@ -3612,24 +3639,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data,
/* Try reading the encryption key size for encrypted ACL links */
if (!ev->status && ev->encrypt && conn->type == ACL_LINK) {
- struct hci_cp_read_enc_key_size cp;
-
- /* Only send HCI_Read_Encryption_Key_Size if the
- * controller really supports it. If it doesn't, assume
- * the default size (16).
- */
- if (!read_key_size_capable(hdev)) {
- conn->enc_key_size = HCI_LINK_KEY_SIZE;
+ if (hci_read_enc_key_size(hdev, conn))
goto notify;
- }
-
- cp.handle = cpu_to_le16(conn->handle);
- if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE,
- sizeof(cp), &cp)) {
- bt_dev_err(hdev, "sending read key size failed");
- conn->enc_key_size = HCI_LINK_KEY_SIZE;
- goto notify;
- }
goto unlock;
}
@@ -6378,8 +6389,7 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
hci_dev_clear_flag(hdev, HCI_PA_SYNC);
- conn = hci_conn_hash_lookup_sid(hdev, ev->sid, &ev->bdaddr,
- ev->bdaddr_type);
+ conn = hci_conn_hash_lookup_create_pa_sync(hdev);
if (!conn) {
bt_dev_err(hdev,
"Unable to find connection for dst %pMR sid 0x%2.2x",
@@ -6418,9 +6428,6 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data,
}
unlock:
- /* Handle any other pending PA sync command */
- hci_pa_create_sync_pending(hdev);
-
hci_dev_unlock(hdev);
}
@@ -6932,7 +6939,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
- if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABILISHED,
+ if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
flex_array_size(ev, bis, ev->num_bis)))
return;
@@ -7003,9 +7010,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
}
unlock:
- /* Handle any other pending BIG sync command */
- hci_le_big_create_sync_pending(hdev);
-
hci_dev_unlock(hdev);
}
@@ -7127,8 +7131,8 @@ static const struct hci_le_ev {
hci_le_create_big_complete_evt,
sizeof(struct hci_evt_le_create_big_complete),
HCI_MAX_EVENT_SIZE),
- /* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABILISHED] */
- HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABILISHED,
+ /* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABLISHED] */
+ HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
hci_le_big_sync_established_evt,
sizeof(struct hci_evt_le_big_sync_estabilished),
HCI_MAX_EVENT_SIZE),
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 609b035..e56b1cb 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2693,16 +2693,16 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev)
/* Force address filtering if PA Sync is in progress */
if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) {
- struct hci_cp_le_pa_create_sync *sent;
+ struct hci_conn *conn;
- sent = hci_sent_cmd_data(hdev, HCI_OP_LE_PA_CREATE_SYNC);
- if (sent) {
+ conn = hci_conn_hash_lookup_create_pa_sync(hdev);
+ if (conn) {
struct conn_params pa;
memset(&pa, 0, sizeof(pa));
- bacpy(&pa.addr, &sent->addr);
- pa.addr_type = sent->addr_type;
+ bacpy(&pa.addr, &conn->dst);
+ pa.addr_type = conn->dst_type;
/* Clear first since there could be addresses left
* behind.
@@ -6895,3 +6895,143 @@ int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn,
return __hci_cmd_sync_status(hdev, HCI_OP_LE_CONN_UPDATE,
sizeof(cp), &cp, HCI_CMD_TIMEOUT);
}
+
+static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
+{
+ bt_dev_dbg(hdev, "err %d", err);
+
+ if (!err)
+ return;
+
+ hci_dev_clear_flag(hdev, HCI_PA_SYNC);
+
+ if (err == -ECANCELED)
+ return;
+
+ hci_dev_lock(hdev);
+
+ hci_update_passive_scan_sync(hdev);
+
+ hci_dev_unlock(hdev);
+}
+
+static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data)
+{
+ struct hci_cp_le_pa_create_sync cp;
+ struct hci_conn *conn = data;
+ struct bt_iso_qos *qos = &conn->iso_qos;
+ int err;
+
+ if (!hci_conn_valid(hdev, conn))
+ return -ECANCELED;
+
+ if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC))
+ return -EBUSY;
+
+ /* Mark HCI_CONN_CREATE_PA_SYNC so hci_update_passive_scan_sync can
+ * program the address in the allow list so PA advertisements can be
+ * received.
+ */
+ set_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
+
+ hci_update_passive_scan_sync(hdev);
+
+ memset(&cp, 0, sizeof(cp));
+ cp.options = qos->bcast.options;
+ cp.sid = conn->sid;
+ cp.addr_type = conn->dst_type;
+ bacpy(&cp.addr, &conn->dst);
+ cp.skip = cpu_to_le16(qos->bcast.skip);
+ cp.sync_timeout = cpu_to_le16(qos->bcast.sync_timeout);
+ cp.sync_cte_type = qos->bcast.sync_cte_type;
+
+ /* The spec allows only one pending LE Periodic Advertising Create
+ * Sync command at a time so we forcefully wait for PA Sync Established
+ * event since cmd_work can only schedule one command at a time.
+ *
+ * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+ * page 2493:
+ *
+ * If the Host issues this command when another HCI_LE_Periodic_
+ * Advertising_Create_Sync command is pending, the Controller shall
+ * return the error code Command Disallowed (0x0C).
+ */
+ err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_PA_CREATE_SYNC,
+ sizeof(cp), &cp,
+ HCI_EV_LE_PA_SYNC_ESTABLISHED,
+ conn->conn_timeout, NULL);
+ if (err == -ETIMEDOUT)
+ __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL,
+ 0, NULL, HCI_CMD_TIMEOUT);
+
+ return err;
+}
+
+int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn)
+{
+ return hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
+ create_pa_complete);
+}
+
+static void create_big_complete(struct hci_dev *hdev, void *data, int err)
+{
+ struct hci_conn *conn = data;
+
+ bt_dev_dbg(hdev, "err %d", err);
+
+ if (err == -ECANCELED)
+ return;
+
+ if (hci_conn_valid(hdev, conn))
+ clear_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
+}
+
+static int hci_le_big_create_sync(struct hci_dev *hdev, void *data)
+{
+ DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, 0x11);
+ struct hci_conn *conn = data;
+ struct bt_iso_qos *qos = &conn->iso_qos;
+ int err;
+
+ if (!hci_conn_valid(hdev, conn))
+ return -ECANCELED;
+
+ set_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags);
+
+ memset(cp, 0, sizeof(*cp));
+ cp->handle = qos->bcast.big;
+ cp->sync_handle = cpu_to_le16(conn->sync_handle);
+ cp->encryption = qos->bcast.encryption;
+ memcpy(cp->bcode, qos->bcast.bcode, sizeof(cp->bcode));
+ cp->mse = qos->bcast.mse;
+ cp->timeout = cpu_to_le16(qos->bcast.timeout);
+ cp->num_bis = conn->num_bis;
+ memcpy(cp->bis, conn->bis, conn->num_bis);
+
+ /* The spec allows only one pending LE BIG Create Sync command at
+ * a time, so we forcefully wait for BIG Sync Established event since
+ * cmd_work can only schedule one command at a time.
+ *
+ * BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E
+ * page 2586:
+ *
+ * If the Host sends this command when the Controller is in the
+ * process of synchronizing to any BIG, i.e. the HCI_LE_BIG_Sync_
+ * Established event has not been generated, the Controller shall
+ * return the error code Command Disallowed (0x0C).
+ */
+ err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_BIG_CREATE_SYNC,
+ struct_size(cp, bis, cp->num_bis), cp,
+ HCI_EVT_LE_BIG_SYNC_ESTABLISHED,
+ conn->conn_timeout, NULL);
+ if (err == -ETIMEDOUT)
+ hci_le_big_terminate_sync(hdev, cp->handle);
+
+ return err;
+}
+
+int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn)
+{
+ return hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
+ create_big_complete);
+}
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 3501a99..2819cda 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1462,14 +1462,13 @@ static void iso_conn_big_sync(struct sock *sk)
lock_sock(sk);
if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
- err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
- &iso_pi(sk)->qos,
- iso_pi(sk)->sync_handle,
- iso_pi(sk)->bc_num_bis,
- iso_pi(sk)->bc_bis);
+ err = hci_conn_big_create_sync(hdev, iso_pi(sk)->conn->hcon,
+ &iso_pi(sk)->qos,
+ iso_pi(sk)->sync_handle,
+ iso_pi(sk)->bc_num_bis,
+ iso_pi(sk)->bc_bis);
if (err)
- bt_dev_err(hdev, "hci_le_big_create_sync: %d",
- err);
+ bt_dev_err(hdev, "hci_big_create_sync: %d", err);
}
release_sock(sk);
@@ -1922,7 +1921,7 @@ static void iso_conn_ready(struct iso_conn *conn)
hcon);
} else if (test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) {
ev = hci_recv_event_data(hcon->hdev,
- HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
+ HCI_EVT_LE_BIG_SYNC_ESTABLISHED);
/* Get reference to PA sync parent socket, if it exists */
parent = iso_get_sock(&hcon->src, &hcon->dst,
@@ -2113,12 +2112,11 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) &&
!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) {
- err = hci_le_big_create_sync(hdev,
- hcon,
- &iso_pi(sk)->qos,
- iso_pi(sk)->sync_handle,
- iso_pi(sk)->bc_num_bis,
- iso_pi(sk)->bc_bis);
+ err = hci_conn_big_create_sync(hdev, hcon,
+ &iso_pi(sk)->qos,
+ iso_pi(sk)->sync_handle,
+ iso_pi(sk)->bc_num_bis,
+ iso_pi(sk)->bc_bis);
if (err) {
bt_dev_err(hdev, "hci_le_big_create_sync: %d",
err);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 5ca7ac4..042d3ac 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1411,7 +1411,8 @@ static void l2cap_request_info(struct l2cap_conn *conn)
sizeof(req), &req);
}
-static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
+static bool l2cap_check_enc_key_size(struct hci_conn *hcon,
+ struct l2cap_chan *chan)
{
/* The minimum encryption key size needs to be enforced by the
* host stack before establishing any L2CAP connections. The
@@ -1425,7 +1426,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
int min_key_size = hcon->hdev->min_enc_key_size;
/* On FIPS security level, key size must be 16 bytes */
- if (hcon->sec_level == BT_SECURITY_FIPS)
+ if (chan->sec_level == BT_SECURITY_FIPS)
min_key_size = 16;
return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) ||
@@ -1453,7 +1454,7 @@ static void l2cap_do_start(struct l2cap_chan *chan)
!__l2cap_no_conn_pending(chan))
return;
- if (l2cap_check_enc_key_size(conn->hcon))
+ if (l2cap_check_enc_key_size(conn->hcon, chan))
l2cap_start_connection(chan);
else
__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
@@ -1528,7 +1529,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
continue;
}
- if (l2cap_check_enc_key_size(conn->hcon))
+ if (l2cap_check_enc_key_size(conn->hcon, chan))
l2cap_start_connection(chan);
else
l2cap_chan_close(chan, ECONNREFUSED);
@@ -3992,7 +3993,7 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
/* Check if the ACL is secure enough (if not SDP) */
if (psm != cpu_to_le16(L2CAP_PSM_SDP) &&
(!hci_conn_check_link_mode(conn->hcon) ||
- !l2cap_check_enc_key_size(conn->hcon))) {
+ !l2cap_check_enc_key_size(conn->hcon, pchan))) {
conn->disc_reason = HCI_ERROR_AUTH_FAILURE;
result = L2CAP_CR_SEC_BLOCK;
goto response;
@@ -7352,7 +7353,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
}
if (chan->state == BT_CONNECT) {
- if (!status && l2cap_check_enc_key_size(hcon))
+ if (!status && l2cap_check_enc_key_size(hcon, chan))
l2cap_start_connection(chan);
else
__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
@@ -7362,7 +7363,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
struct l2cap_conn_rsp rsp;
__u16 res, stat;
- if (!status && l2cap_check_enc_key_size(hcon)) {
+ if (!status && l2cap_check_enc_key_size(hcon, chan)) {
if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
res = L2CAP_CR_PEND;
stat = L2CAP_CS_AUTHOR_PEND;
@@ -7415,6 +7416,9 @@ static int l2cap_recv_frag(struct l2cap_conn *conn, struct sk_buff *skb,
return -ENOMEM;
/* Init rx_len */
conn->rx_len = len;
+
+ skb_set_delivery_time(conn->rx_skb, skb->tstamp,
+ skb->tstamp_type);
}
/* Copy as much as the rx_skb can hold */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c1e1e52..46b2270 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7506,11 +7506,16 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err)
struct mgmt_cp_add_device *cp = cmd->param;
if (!err) {
+ struct hci_conn_params *params;
+
+ params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr,
+ le_addr_type(cp->addr.type));
+
device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type,
cp->action);
device_flags_changed(NULL, hdev, &cp->addr.bdaddr,
cp->addr.type, hdev->conn_flags,
- PTR_UINT(cmd->user_data));
+ params ? params->flags : 0);
}
mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE,
@@ -7613,8 +7618,6 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
goto unlock;
}
- cmd->user_data = UINT_PTR(current_flags);
-
err = hci_cmd_sync_queue(hdev, add_device_sync, cmd,
add_device_complete);
if (err < 0) {
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
index 98aea54..a8c6703 100644
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -65,17 +65,14 @@ static struct dst_ops fake_dst_ops = {
* ipt_REJECT needs it. Future netfilter modules might
* require us to fill additional fields.
*/
-static const u32 br_dst_default_metrics[RTAX_MAX] = {
- [RTAX_MTU - 1] = 1500,
-};
-
void br_netfilter_rtable_init(struct net_bridge *br)
{
struct rtable *rt = &br->fake_rtable;
rcuref_init(&rt->dst.__rcuref, 1);
rt->dst.dev = br->dev;
- dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
+ dst_init_metrics(&rt->dst, br->metrics, false);
+ dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu);
rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE;
rt->dst.ops = &fake_dst_ops;
}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d5b3c59..4715a8d 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -505,6 +505,7 @@ struct net_bridge {
struct rtable fake_rtable;
struct rt6_info fake_rt6_info;
};
+ u32 metrics[RTAX_MAX];
#endif
u16 group_fwd_mask;
u16 group_fwd_mask_required;
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 0bca1b9b..6bc1cc4 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -58,6 +58,7 @@
#include <linux/can/skb.h>
#include <linux/can/bcm.h>
#include <linux/slab.h>
+#include <linux/spinlock.h>
#include <net/sock.h>
#include <net/net_namespace.h>
@@ -122,6 +123,7 @@ struct bcm_op {
struct canfd_frame last_sframe;
struct sock *sk;
struct net_device *rx_reg_dev;
+ spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */
};
struct bcm_sock {
@@ -217,7 +219,9 @@ static int bcm_proc_show(struct seq_file *m, void *v)
seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex));
seq_printf(m, " <<<\n");
- list_for_each_entry(op, &bo->rx_ops, list) {
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(op, &bo->rx_ops, list) {
unsigned long reduction;
@@ -273,6 +277,9 @@ static int bcm_proc_show(struct seq_file *m, void *v)
seq_printf(m, "# sent %ld\n", op->frames_abs);
}
seq_putc(m, '\n');
+
+ rcu_read_unlock();
+
return 0;
}
#endif /* CONFIG_PROC_FS */
@@ -285,13 +292,18 @@ static void bcm_can_tx(struct bcm_op *op)
{
struct sk_buff *skb;
struct net_device *dev;
- struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe;
+ struct canfd_frame *cf;
int err;
/* no target device? => exit */
if (!op->ifindex)
return;
+ /* read currframe under lock protection */
+ spin_lock_bh(&op->bcm_tx_lock);
+ cf = op->frames + op->cfsiz * op->currframe;
+ spin_unlock_bh(&op->bcm_tx_lock);
+
dev = dev_get_by_index(sock_net(op->sk), op->ifindex);
if (!dev) {
/* RFC: should this bcm_op remove itself here? */
@@ -312,6 +324,10 @@ static void bcm_can_tx(struct bcm_op *op)
skb->dev = dev;
can_skb_set_owner(skb, op->sk);
err = can_send(skb, 1);
+
+ /* update currframe and count under lock protection */
+ spin_lock_bh(&op->bcm_tx_lock);
+
if (!err)
op->frames_abs++;
@@ -320,6 +336,11 @@ static void bcm_can_tx(struct bcm_op *op)
/* reached last frame? */
if (op->currframe >= op->nframes)
op->currframe = 0;
+
+ if (op->count > 0)
+ op->count--;
+
+ spin_unlock_bh(&op->bcm_tx_lock);
out:
dev_put(dev);
}
@@ -430,7 +451,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
struct bcm_msg_head msg_head;
if (op->kt_ival1 && (op->count > 0)) {
- op->count--;
+ bcm_can_tx(op);
if (!op->count && (op->flags & TX_COUNTEVT)) {
/* create notification to user */
@@ -445,7 +466,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
bcm_send_to_user(op, &msg_head, NULL, 0);
}
- bcm_can_tx(op);
} else if (op->kt_ival2) {
bcm_can_tx(op);
@@ -843,7 +863,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
REGMASK(op->can_id),
bcm_rx_handler, op);
- list_del(&op->list);
+ list_del_rcu(&op->list);
bcm_remove_op(op);
return 1; /* done */
}
@@ -863,7 +883,7 @@ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh,
list_for_each_entry_safe(op, n, ops, list) {
if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
(op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
- list_del(&op->list);
+ list_del_rcu(&op->list);
bcm_remove_op(op);
return 1; /* done */
}
@@ -956,6 +976,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
}
op->flags = msg_head->flags;
+ /* only lock for unlikely count/nframes/currframe changes */
+ if (op->nframes != msg_head->nframes ||
+ op->flags & TX_RESET_MULTI_IDX ||
+ op->flags & SETTIMER) {
+
+ spin_lock_bh(&op->bcm_tx_lock);
+
+ if (op->nframes != msg_head->nframes ||
+ op->flags & TX_RESET_MULTI_IDX) {
+ /* potentially update changed nframes */
+ op->nframes = msg_head->nframes;
+ /* restart multiple frame transmission */
+ op->currframe = 0;
+ }
+
+ if (op->flags & SETTIMER)
+ op->count = msg_head->count;
+
+ spin_unlock_bh(&op->bcm_tx_lock);
+ }
+
} else {
/* insert new BCM operation for the given can_id */
@@ -963,9 +1004,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
if (!op)
return -ENOMEM;
+ spin_lock_init(&op->bcm_tx_lock);
op->can_id = msg_head->can_id;
op->cfsiz = CFSIZ(msg_head->flags);
op->flags = msg_head->flags;
+ op->nframes = msg_head->nframes;
+
+ if (op->flags & SETTIMER)
+ op->count = msg_head->count;
/* create array for CAN frames and copy the data */
if (msg_head->nframes > 1) {
@@ -1023,22 +1069,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
} /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */
- if (op->nframes != msg_head->nframes) {
- op->nframes = msg_head->nframes;
- /* start multiple frame transmission with index 0 */
- op->currframe = 0;
- }
-
- /* check flags */
-
- if (op->flags & TX_RESET_MULTI_IDX) {
- /* start multiple frame transmission with index 0 */
- op->currframe = 0;
- }
-
if (op->flags & SETTIMER) {
/* set timer values */
- op->count = msg_head->count;
op->ival1 = msg_head->ival1;
op->ival2 = msg_head->ival2;
op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
@@ -1055,11 +1087,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
op->flags |= TX_ANNOUNCE;
}
- if (op->flags & TX_ANNOUNCE) {
+ if (op->flags & TX_ANNOUNCE)
bcm_can_tx(op);
- if (op->count)
- op->count--;
- }
if (op->flags & STARTTIMER)
bcm_tx_start_timer(op);
@@ -1272,7 +1301,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
bcm_rx_handler, op, "bcm", sk);
if (err) {
/* this bcm rx op is broken -> remove it */
- list_del(&op->list);
+ list_del_rcu(&op->list);
bcm_remove_op(op);
return err;
}
diff --git a/net/can/gw.c b/net/can/gw.c
index ef93293..55eccb1 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -130,7 +130,7 @@ struct cgw_job {
u32 handled_frames;
u32 dropped_frames;
u32 deleted_frames;
- struct cf_mod mod;
+ struct cf_mod __rcu *cf_mod;
union {
/* CAN frame data source */
struct net_device *dev;
@@ -459,6 +459,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
struct cgw_job *gwj = (struct cgw_job *)data;
struct canfd_frame *cf;
struct sk_buff *nskb;
+ struct cf_mod *mod;
int modidx = 0;
/* process strictly Classic CAN or CAN FD frames */
@@ -506,7 +507,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
* When there is at least one modification function activated,
* we need to copy the skb as we want to modify skb->data.
*/
- if (gwj->mod.modfunc[0])
+ mod = rcu_dereference(gwj->cf_mod);
+ if (mod->modfunc[0])
nskb = skb_copy(skb, GFP_ATOMIC);
else
nskb = skb_clone(skb, GFP_ATOMIC);
@@ -529,8 +531,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
cf = (struct canfd_frame *)nskb->data;
/* perform preprocessed modification functions if there are any */
- while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx])
- (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);
+ while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx])
+ (*mod->modfunc[modidx++])(cf, mod);
/* Has the CAN frame been modified? */
if (modidx) {
@@ -546,11 +548,11 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
}
/* check for checksum updates */
- if (gwj->mod.csumfunc.crc8)
- (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8);
+ if (mod->csumfunc.crc8)
+ (*mod->csumfunc.crc8)(cf, &mod->csum.crc8);
- if (gwj->mod.csumfunc.xor)
- (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor);
+ if (mod->csumfunc.xor)
+ (*mod->csumfunc.xor)(cf, &mod->csum.xor);
}
/* clear the skb timestamp if not configured the other way */
@@ -581,9 +583,20 @@ static void cgw_job_free_rcu(struct rcu_head *rcu_head)
{
struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu);
+ /* cgw_job::cf_mod is always accessed from the same cgw_job object within
+ * the same RCU read section. Once cgw_job is scheduled for removal,
+ * cf_mod can also be removed without mandating an additional grace period.
+ */
+ kfree(rcu_access_pointer(gwj->cf_mod));
kmem_cache_free(cgw_cache, gwj);
}
+/* Return cgw_job::cf_mod with RTNL protected section */
+static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj)
+{
+ return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked());
+}
+
static int cgw_notifier(struct notifier_block *nb,
unsigned long msg, void *ptr)
{
@@ -616,6 +629,7 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
{
struct rtcanmsg *rtcan;
struct nlmsghdr *nlh;
+ struct cf_mod *mod;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags);
if (!nlh)
@@ -650,82 +664,83 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
goto cancel;
}
+ mod = cgw_job_cf_mod(gwj);
if (gwj->flags & CGW_FLAGS_CAN_FD) {
struct cgw_fdframe_mod mb;
- if (gwj->mod.modtype.and) {
- memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.and;
+ if (mod->modtype.and) {
+ memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf));
+ mb.modtype = mod->modtype.and;
if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.or) {
- memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.or;
+ if (mod->modtype.or) {
+ memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf));
+ mb.modtype = mod->modtype.or;
if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.xor) {
- memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.xor;
+ if (mod->modtype.xor) {
+ memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf));
+ mb.modtype = mod->modtype.xor;
if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.set) {
- memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.set;
+ if (mod->modtype.set) {
+ memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf));
+ mb.modtype = mod->modtype.set;
if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0)
goto cancel;
}
} else {
struct cgw_frame_mod mb;
- if (gwj->mod.modtype.and) {
- memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.and;
+ if (mod->modtype.and) {
+ memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf));
+ mb.modtype = mod->modtype.and;
if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.or) {
- memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.or;
+ if (mod->modtype.or) {
+ memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf));
+ mb.modtype = mod->modtype.or;
if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.xor) {
- memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.xor;
+ if (mod->modtype.xor) {
+ memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf));
+ mb.modtype = mod->modtype.xor;
if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.set) {
- memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.set;
+ if (mod->modtype.set) {
+ memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf));
+ mb.modtype = mod->modtype.set;
if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0)
goto cancel;
}
}
- if (gwj->mod.uid) {
- if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0)
+ if (mod->uid) {
+ if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0)
goto cancel;
}
- if (gwj->mod.csumfunc.crc8) {
+ if (mod->csumfunc.crc8) {
if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN,
- &gwj->mod.csum.crc8) < 0)
+ &mod->csum.crc8) < 0)
goto cancel;
}
- if (gwj->mod.csumfunc.xor) {
+ if (mod->csumfunc.xor) {
if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN,
- &gwj->mod.csum.xor) < 0)
+ &mod->csum.xor) < 0)
goto cancel;
}
@@ -1059,7 +1074,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct rtcanmsg *r;
struct cgw_job *gwj;
- struct cf_mod mod;
+ struct cf_mod *mod;
struct can_can_gw ccgw;
u8 limhops = 0;
int err = 0;
@@ -1078,37 +1093,48 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
if (r->gwtype != CGW_TYPE_CAN_CAN)
return -EINVAL;
- err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
- if (err < 0)
- return err;
+ mod = kmalloc(sizeof(*mod), GFP_KERNEL);
+ if (!mod)
+ return -ENOMEM;
- if (mod.uid) {
+ err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
+ if (err < 0)
+ goto out_free_cf;
+
+ if (mod->uid) {
ASSERT_RTNL();
/* check for updating an existing job with identical uid */
hlist_for_each_entry(gwj, &net->can.cgw_list, list) {
- if (gwj->mod.uid != mod.uid)
+ struct cf_mod *old_cf;
+
+ old_cf = cgw_job_cf_mod(gwj);
+ if (old_cf->uid != mod->uid)
continue;
/* interfaces & filters must be identical */
- if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw)))
- return -EINVAL;
+ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) {
+ err = -EINVAL;
+ goto out_free_cf;
+ }
- /* update modifications with disabled softirq & quit */
- local_bh_disable();
- memcpy(&gwj->mod, &mod, sizeof(mod));
- local_bh_enable();
+ rcu_assign_pointer(gwj->cf_mod, mod);
+ kfree_rcu_mightsleep(old_cf);
return 0;
}
}
/* ifindex == 0 is not allowed for job creation */
- if (!ccgw.src_idx || !ccgw.dst_idx)
- return -ENODEV;
+ if (!ccgw.src_idx || !ccgw.dst_idx) {
+ err = -ENODEV;
+ goto out_free_cf;
+ }
gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL);
- if (!gwj)
- return -ENOMEM;
+ if (!gwj) {
+ err = -ENOMEM;
+ goto out_free_cf;
+ }
gwj->handled_frames = 0;
gwj->dropped_frames = 0;
@@ -1118,7 +1144,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
gwj->limit_hops = limhops;
/* insert already parsed information */
- memcpy(&gwj->mod, &mod, sizeof(mod));
+ RCU_INIT_POINTER(gwj->cf_mod, mod);
memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw));
err = -ENODEV;
@@ -1152,9 +1178,11 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!err)
hlist_add_head_rcu(&gwj->list, &net->can.cgw_list);
out:
- if (err)
+ if (err) {
kmem_cache_free(cgw_cache, gwj);
-
+out_free_cf:
+ kfree(mod);
+ }
return err;
}
@@ -1214,19 +1242,22 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh,
/* remove only the first matching entry */
hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) {
+ struct cf_mod *cf_mod;
+
if (gwj->flags != r->flags)
continue;
if (gwj->limit_hops != limhops)
continue;
+ cf_mod = cgw_job_cf_mod(gwj);
/* we have a match when uid is enabled and identical */
- if (gwj->mod.uid || mod.uid) {
- if (gwj->mod.uid != mod.uid)
+ if (cf_mod->uid || mod.uid) {
+ if (cf_mod->uid != mod.uid)
continue;
} else {
/* no uid => check for identical modifications */
- if (memcmp(&gwj->mod, &mod, sizeof(mod)))
+ if (memcmp(cf_mod, &mod, sizeof(mod)))
continue;
}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b24afec..6664ea7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -220,16 +220,6 @@ void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req,
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages);
-void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req,
- unsigned int which, struct ceph_pagelist *pagelist)
-{
- struct ceph_osd_data *osd_data;
-
- osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
- ceph_osd_data_pagelist_init(osd_data, pagelist);
-}
-EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist);
-
#ifdef CONFIG_BLOCK
void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
unsigned int which,
@@ -297,19 +287,6 @@ static void osd_req_op_cls_request_info_pagelist(
ceph_osd_data_pagelist_init(osd_data, pagelist);
}
-void osd_req_op_cls_request_data_pagelist(
- struct ceph_osd_request *osd_req,
- unsigned int which, struct ceph_pagelist *pagelist)
-{
- struct ceph_osd_data *osd_data;
-
- osd_data = osd_req_op_data(osd_req, which, cls, request_data);
- ceph_osd_data_pagelist_init(osd_data, pagelist);
- osd_req->r_ops[which].cls.indata_len += pagelist->length;
- osd_req->r_ops[which].indata_len += pagelist->length;
-}
-EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);
-
void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
unsigned int which, struct page **pages, u64 length,
u32 alignment, bool pages_from_pool, bool own_pages)
diff --git a/net/core/dev.c b/net/core/dev.c
index 1be7cb7..0d89163 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9193,18 +9193,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
return 0;
}
-/**
- * dev_set_promiscuity - update promiscuity count on a device
- * @dev: device
- * @inc: modifier
- *
- * Add or remove promiscuity from a device. While the count in the device
- * remains above zero the interface remains promiscuous. Once it hits zero
- * the device reverts back to normal filtering operation. A negative inc
- * value is used to drop promiscuity on the device.
- * Return 0 if successful or a negative errno code on error.
- */
-int dev_set_promiscuity(struct net_device *dev, int inc)
+int netif_set_promiscuity(struct net_device *dev, int inc)
{
unsigned int old_flags = dev->flags;
int err;
@@ -9216,7 +9205,6 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
dev_set_rx_mode(dev);
return err;
}
-EXPORT_SYMBOL(dev_set_promiscuity);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
{
@@ -10453,6 +10441,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
if (!(features & feature) && (lower->features & feature)) {
netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
&feature, lower->name);
+ netdev_lock_ops(lower);
lower->wanted_features &= ~feature;
__netdev_update_features(lower);
@@ -10461,6 +10450,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
&feature, lower->name);
else
netdev_features_change(lower);
+ netdev_unlock_ops(lower);
}
}
}
@@ -11966,9 +11956,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
struct sk_buff *skb = NULL;
/* Shutdown queueing discipline. */
+ netdev_lock_ops(dev);
dev_shutdown(dev);
dev_tcx_uninstall(dev);
- netdev_lock_ops(dev);
dev_xdp_uninstall(dev);
dev_memory_provider_uninstall(dev);
netdev_unlock_ops(dev);
@@ -12161,7 +12151,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
synchronize_net();
/* Shutdown queueing discipline. */
+ netdev_lock_ops(dev);
dev_shutdown(dev);
+ netdev_unlock_ops(dev);
/* Notify protocols, that we are about to destroy
* this device. They should clean all the things.
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90898cd..f9a160a 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -268,6 +268,29 @@ void dev_disable_lro(struct net_device *dev)
EXPORT_SYMBOL(dev_disable_lro);
/**
+ * dev_set_promiscuity() - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove promiscuity from a device. While the count in the device
+ * remains above zero the interface remains promiscuous. Once it hits zero
+ * the device reverts back to normal filtering operation. A negative inc
+ * value is used to drop promiscuity on the device.
+ * Return 0 if successful or a negative errno code on error.
+ */
+int dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ int ret;
+
+ netdev_lock_ops(dev);
+ ret = netif_set_promiscuity(dev, inc);
+ netdev_unlock_ops(dev);
+
+ return ret;
+}
+EXPORT_SYMBOL(dev_set_promiscuity);
+
+/**
* dev_set_allmulti() - update allmulti count on a device
* @dev: device
* @inc: modifier
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 6e27a47..2db428a 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -200,6 +200,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
refcount_set(&binding->ref, 1);
+ mutex_init(&binding->lock);
+
binding->dmabuf = dmabuf;
binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
@@ -379,6 +381,11 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv,
xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) {
if (bound_rxq == rxq) {
xa_erase(&binding->bound_rxqs, xa_idx);
+ if (xa_empty(&binding->bound_rxqs)) {
+ mutex_lock(&binding->lock);
+ binding->dev = NULL;
+ mutex_unlock(&binding->lock);
+ }
break;
}
}
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 7fc158d..a1aabc9 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -20,6 +20,8 @@ struct net_devmem_dmabuf_binding {
struct sg_table *sgt;
struct net_device *dev;
struct gen_pool *chunk_pool;
+ /* Protect dev */
+ struct mutex lock;
/* The user holds a ref (via the netlink API) for as long as they want
* the binding to remain alive. Each page pool using this binding holds
diff --git a/net/core/filter.c b/net/core/filter.c
index 79cab4d..577a450 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2509,6 +2509,7 @@ int skb_do_redirect(struct sk_buff *skb)
goto out_drop;
skb->dev = dev;
dev_sw_netstats_rx_add(dev, skb->len);
+ skb_scrub_packet(skb, false);
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index e39a459..60f27cb4 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -333,6 +333,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -348,8 +350,10 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -364,11 +368,13 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_output);
@@ -380,6 +386,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ local_bh_disable();
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
@@ -396,8 +404,10 @@ int lwtunnel_xmit(struct sk_buff *skb)
lwtstate = dst->lwtstate;
if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
- lwtstate->type > LWTUNNEL_ENCAP_MAX)
- return 0;
+ lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+ ret = 0;
+ goto out;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
@@ -412,11 +422,13 @@ int lwtunnel_xmit(struct sk_buff *skb)
if (ret == -EOPNOTSUPP)
goto drop;
- return ret;
+ goto out;
drop:
kfree_skb(skb);
+out:
+ local_bh_enable();
return ret;
}
EXPORT_SYMBOL_GPL(lwtunnel_xmit);
@@ -428,6 +440,8 @@ int lwtunnel_input(struct sk_buff *skb)
struct dst_entry *dst;
int ret;
+ DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
if (dev_xmit_recursion()) {
net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
__func__);
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 5d7af50..a877693 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -708,25 +708,66 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
return 0;
}
+/**
+ * netdev_stat_queue_sum() - add up queue stats from range of queues
+ * @netdev: net_device
+ * @rx_start: index of the first Rx queue to query
+ * @rx_end: index after the last Rx queue (first *not* to query)
+ * @rx_sum: output Rx stats, should be already initialized
+ * @tx_start: index of the first Tx queue to query
+ * @tx_end: index after the last Tx queue (first *not* to query)
+ * @tx_sum: output Tx stats, should be already initialized
+ *
+ * Add stats from [start, end) range of queue IDs to *x_sum structs.
+ * The sum structs must be already initialized. Usually this
+ * helper is invoked from the .get_base_stats callbacks of drivers
+ * to account for stats of disabled queues. In that case the ranges
+ * are usually [netdev->real_num_*x_queues, netdev->num_*x_queues).
+ */
+void netdev_stat_queue_sum(struct net_device *netdev,
+ int rx_start, int rx_end,
+ struct netdev_queue_stats_rx *rx_sum,
+ int tx_start, int tx_end,
+ struct netdev_queue_stats_tx *tx_sum)
+{
+ const struct netdev_stat_ops *ops;
+ struct netdev_queue_stats_rx rx;
+ struct netdev_queue_stats_tx tx;
+ int i;
+
+ ops = netdev->stat_ops;
+
+ for (i = rx_start; i < rx_end; i++) {
+ memset(&rx, 0xff, sizeof(rx));
+ if (ops->get_queue_stats_rx)
+ ops->get_queue_stats_rx(netdev, i, &rx);
+ netdev_nl_stats_add(rx_sum, &rx, sizeof(rx));
+ }
+ for (i = tx_start; i < tx_end; i++) {
+ memset(&tx, 0xff, sizeof(tx));
+ if (ops->get_queue_stats_tx)
+ ops->get_queue_stats_tx(netdev, i, &tx);
+ netdev_nl_stats_add(tx_sum, &tx, sizeof(tx));
+ }
+}
+EXPORT_SYMBOL(netdev_stat_queue_sum);
+
static int
netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info)
{
- struct netdev_queue_stats_rx rx_sum, rx;
- struct netdev_queue_stats_tx tx_sum, tx;
- const struct netdev_stat_ops *ops;
+ struct netdev_queue_stats_rx rx_sum;
+ struct netdev_queue_stats_tx tx_sum;
void *hdr;
- int i;
- ops = netdev->stat_ops;
/* Netdev can't guarantee any complete counters */
- if (!ops->get_base_stats)
+ if (!netdev->stat_ops->get_base_stats)
return 0;
memset(&rx_sum, 0xff, sizeof(rx_sum));
memset(&tx_sum, 0xff, sizeof(tx_sum));
- ops->get_base_stats(netdev, &rx_sum, &tx_sum);
+ netdev->stat_ops->get_base_stats(netdev, &rx_sum, &tx_sum);
/* The op was there, but nothing reported, don't bother */
if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
@@ -739,18 +780,8 @@ netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
goto nla_put_failure;
- for (i = 0; i < netdev->real_num_rx_queues; i++) {
- memset(&rx, 0xff, sizeof(rx));
- if (ops->get_queue_stats_rx)
- ops->get_queue_stats_rx(netdev, i, &rx);
- netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
- }
- for (i = 0; i < netdev->real_num_tx_queues; i++) {
- memset(&tx, 0xff, sizeof(tx));
- if (ops->get_queue_stats_tx)
- ops->get_queue_stats_tx(netdev, i, &tx);
- netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
- }
+ netdev_stat_queue_sum(netdev, 0, netdev->real_num_rx_queues, &rx_sum,
+ 0, netdev->real_num_tx_queues, &tx_sum);
if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
netdev_nl_stats_write_tx(rsp, &tx_sum))
@@ -861,14 +892,17 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&priv->lock);
+ err = 0;
netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
- if (!netdev || !netif_device_present(netdev)) {
+ if (!netdev) {
err = -ENODEV;
goto err_unlock_sock;
}
-
- if (!netdev_need_ops_lock(netdev)) {
+ if (!netif_device_present(netdev))
+ err = -ENODEV;
+ else if (!netdev_need_ops_lock(netdev))
err = -EOPNOTSUPP;
+ if (err) {
NL_SET_BAD_ATTR(info->extack,
info->attrs[NETDEV_A_DEV_IFINDEX]);
goto err_unlock;
@@ -945,14 +979,25 @@ void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
{
struct net_devmem_dmabuf_binding *binding;
struct net_devmem_dmabuf_binding *temp;
+ netdevice_tracker dev_tracker;
struct net_device *dev;
mutex_lock(&priv->lock);
list_for_each_entry_safe(binding, temp, &priv->bindings, list) {
+ mutex_lock(&binding->lock);
dev = binding->dev;
+ if (!dev) {
+ mutex_unlock(&binding->lock);
+ net_devmem_unbind_dmabuf(binding);
+ continue;
+ }
+ netdev_hold(dev, &dev_tracker, GFP_KERNEL);
+ mutex_unlock(&binding->lock);
+
netdev_lock(dev);
net_devmem_unbind_dmabuf(binding);
netdev_unlock(dev);
+ netdev_put(dev, &dev_tracker);
}
mutex_unlock(&priv->lock);
}
diff --git a/net/core/selftests.c b/net/core/selftests.c
index e99ae98..35f807e 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
ehdr->h_proto = htons(ETH_P_IP);
if (attr->tcp) {
+ memset(thdr, 0, sizeof(*thdr));
thdr->source = htons(attr->sport);
thdr->dest = htons(attr->dport);
thdr->doff = sizeof(struct tcphdr) / 4;
- thdr->check = 0;
} else {
uhdr->source = htons(attr->sport);
uhdr->dest = htons(attr->dport);
@@ -144,10 +144,18 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
attr->id = net_test_next_id;
shdr->id = net_test_next_id++;
- if (attr->size)
- skb_put(skb, attr->size);
- if (attr->max_size && attr->max_size > skb->len)
- skb_put(skb, attr->max_size - skb->len);
+ if (attr->size) {
+ void *payload = skb_put(skb, attr->size);
+
+ memset(payload, 0, attr->size);
+ }
+
+ if (attr->max_size && attr->max_size > skb->len) {
+ size_t pad_len = attr->max_size - skb->len;
+ void *pad = skb_put(skb, pad_len);
+
+ memset(pad, 0, pad_len);
+ }
skb->csum = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index c33d4bf..0b7564b 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -140,7 +140,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev)
{
- u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
+ u8 *tag;
+
+ if (skb_linearize(skb))
+ return NULL;
+
+ tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M,
KSZ_EGRESS_TAG_LEN);
@@ -311,10 +316,16 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev)
{
- /* Tag decoding */
- u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
- unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M;
unsigned int len = KSZ_EGRESS_TAG_LEN;
+ unsigned int port;
+ u8 *tag;
+
+ if (skb_linearize(skb))
+ return NULL;
+
+ /* Tag decoding */
+ tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
+ port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M;
/* Extra 4-bytes PTP timestamp */
if (tag[0] & KSZ9477_PTP_TAG_INDICATION) {
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 0e40768..f14a41e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -120,47 +120,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4,
@@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a8b04d4..85dc208 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -120,11 +120,6 @@ static void ipmr_expire_process(struct timer_list *t);
lockdep_rtnl_is_held() || \
list_empty(&net->ipv4.mr_tables))
-static bool ipmr_can_free_table(struct net *net)
-{
- return !check_net(net) || !net_initialized(net);
-}
-
static struct mr_table *ipmr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -317,11 +312,6 @@ EXPORT_SYMBOL(ipmr_rule_default);
#define ipmr_for_each_table(mrt, net) \
for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
-static bool ipmr_can_free_table(struct net *net)
-{
- return !check_net(net);
-}
-
static struct mr_table *ipmr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -437,7 +427,7 @@ static void ipmr_free_table(struct mr_table *mrt)
{
struct net *net = read_pnet(&mrt->net);
- WARN_ON_ONCE(!ipmr_can_free_table(net));
+ WARN_ON_ONCE(!mr_can_free_table(net));
timer_shutdown_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 934f777..d293087 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -439,7 +439,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2c07255..9a8142c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -247,6 +247,62 @@ static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
return segs;
}
+static void __udpv6_gso_segment_csum(struct sk_buff *seg,
+ struct in6_addr *oldip,
+ const struct in6_addr *newip,
+ __be16 *oldport, __be16 newport)
+{
+ struct udphdr *uh = udp_hdr(seg);
+
+ if (ipv6_addr_equal(oldip, newip) && *oldport == newport)
+ return;
+
+ if (uh->check) {
+ inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32,
+ newip->s6_addr32, true);
+
+ inet_proto_csum_replace2(&uh->check, seg, *oldport, newport,
+ false);
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ }
+
+ *oldip = *newip;
+ *oldport = newport;
+}
+
+static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs)
+{
+ const struct ipv6hdr *iph;
+ const struct udphdr *uh;
+ struct ipv6hdr *iph2;
+ struct sk_buff *seg;
+ struct udphdr *uh2;
+
+ seg = segs;
+ uh = udp_hdr(seg);
+ iph = ipv6_hdr(seg);
+ uh2 = udp_hdr(seg->next);
+ iph2 = ipv6_hdr(seg->next);
+
+ if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) &&
+ ipv6_addr_equal(&iph->saddr, &iph2->saddr) &&
+ ipv6_addr_equal(&iph->daddr, &iph2->daddr))
+ return segs;
+
+ while ((seg = seg->next)) {
+ uh2 = udp_hdr(seg);
+ iph2 = ipv6_hdr(seg);
+
+ __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+ &uh2->source, uh->source);
+ __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+ &uh2->dest, uh->dest);
+ }
+
+ return segs;
+}
+
static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6)
@@ -259,7 +315,10 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
- return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
+ if (is_ipv6)
+ return __udpv6_gso_segment_list_csum(skb);
+ else
+ return __udpv4_gso_segment_list_csum(skb);
}
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index b5b0632..0d31a8c 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
- offset = offset - sizeof(struct udphdr);
-
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm4_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9ba83f0..c6b2217 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3214,16 +3214,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
- int scope, plen, offset = 0;
+ int scope, plen;
u32 pflags = 0;
ASSERT_RTNL();
memset(&addr, 0, sizeof(struct in6_addr));
- /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
- if (idev->dev->addr_len == sizeof(struct in6_addr))
- offset = sizeof(struct in6_addr) - 4;
- memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+ memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
scope = IPV6_ADDR_COMPATv4;
@@ -3534,7 +3531,13 @@ static void addrconf_gre_config(struct net_device *dev)
return;
}
- if (dev->type == ARPHRD_ETHER) {
+ /* Generate the IPv6 link-local address using addrconf_addr_gen(),
+ * unless we have an IPv4 GRE device not bound to an IP address and
+ * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+ * case). Such devices fall back to add_v4_addrs() instead.
+ */
+ if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
addrconf_addr_gen(idev, true);
return;
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9e73944..72adfc1 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp6_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index b413c9c..3276cde 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -108,11 +108,6 @@ static void ipmr_expire_process(struct timer_list *t);
lockdep_rtnl_is_held() || \
list_empty(&net->ipv6.mr6_tables))
-static bool ip6mr_can_free_table(struct net *net)
-{
- return !check_net(net) || !net_initialized(net);
-}
-
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -306,11 +301,6 @@ EXPORT_SYMBOL(ip6mr_rule_default);
#define ip6mr_for_each_table(mrt, net) \
for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
-static bool ip6mr_can_free_table(struct net *net)
-{
- return !check_net(net);
-}
-
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -416,7 +406,7 @@ static void ip6mr_free_table(struct mr_table *mrt)
{
struct net *net = read_pnet(&mrt->net);
- WARN_ON_ONCE(!ip6mr_can_free_table(net));
+ WARN_ON_ONCE(!mr_can_free_table(net));
timer_shutdown_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d9b11fe..a8a04f4 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
}
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4abc5e9..841c81a 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
if (skb->protocol == htons(ETH_P_IP))
return xfrm4_gro_udp_encap_rcv(sk, head, skb);
- offset = offset - sizeof(struct udphdr);
-
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm6_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 0259cde..cc77ec5 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -887,15 +887,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
if (sk->sk_type != SOCK_STREAM)
goto copy_uaddr;
+ /* Partial read */
+ if (used + offset < skb_len)
+ continue;
+
if (!(flags & MSG_PEEK)) {
skb_unlink(skb, &sk->sk_receive_queue);
kfree_skb(skb);
*seq = 0;
}
-
- /* Partial read */
- if (used + offset < skb_len)
- continue;
} while (len > 0);
out:
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 741e6c7..6b6de43 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1354,10 +1354,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
hw->wiphy->software_iftypes |= BIT(NL80211_IFTYPE_MONITOR);
- local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) +
- sizeof(void *) * channels, GFP_KERNEL);
+ local->int_scan_req = kzalloc(struct_size(local->int_scan_req,
+ channels, channels),
+ GFP_KERNEL);
if (!local->int_scan_req)
return -ENOMEM;
+ local->int_scan_req->n_channels = channels;
eth_broadcast_addr(local->int_scan_req->bssid);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 5d1f2d6..35eaf08 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7675,6 +7675,7 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_res);
int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 +
2 * 2 * IEEE80211_TTLM_NUM_TIDS;
+ u16 status_code;
skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len);
if (!skb)
@@ -7697,19 +7698,18 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
WARN_ON(1);
fallthrough;
case NEG_TTLM_RES_REJECT:
- mgmt->u.action.u.ttlm_res.status_code =
- WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING;
+ status_code = WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING;
break;
case NEG_TTLM_RES_ACCEPT:
- mgmt->u.action.u.ttlm_res.status_code = WLAN_STATUS_SUCCESS;
+ status_code = WLAN_STATUS_SUCCESS;
break;
case NEG_TTLM_RES_SUGGEST_PREFERRED:
- mgmt->u.action.u.ttlm_res.status_code =
- WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED;
+ status_code = WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED;
ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm);
break;
}
+ mgmt->u.action.u.ttlm_res.status_code = cpu_to_le16(status_code);
ieee80211_tx_skb(sdata, skb);
}
@@ -7875,7 +7875,7 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
* This can be better implemented in the future, to handle request
* rejections.
*/
- if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS)
+ if (le16_to_cpu(mgmt->u.action.u.ttlm_res.status_code) != WLAN_STATUS_SUCCESS)
__ieee80211_disconnect(sdata);
}
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index b17b3cc..a362254b 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -1085,7 +1085,13 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
ieee80211_report_used_skb(local, skb, false, status->ack_hwtstamp);
- if (status->free_list)
+ /*
+ * This is a bit racy but we can avoid a lot of work
+ * with this test...
+ */
+ if (local->tx_mntrs)
+ ieee80211_tx_monitor(local, skb, retry_count, status);
+ else if (status->free_list)
list_add_tail(&skb->list, status->free_list);
else
dev_kfree_skb(skb);
diff --git a/net/mctp/device.c b/net/mctp/device.c
index 8e0724c..7c0dcf3 100644
--- a/net/mctp/device.c
+++ b/net/mctp/device.c
@@ -117,11 +117,18 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
struct net_device *dev;
struct ifaddrmsg *hdr;
struct mctp_dev *mdev;
- int ifindex, rc;
+ int ifindex = 0, rc;
- hdr = nlmsg_data(cb->nlh);
- // filter by ifindex if requested
- ifindex = hdr->ifa_index;
+ /* Filter by ifindex if a header is provided */
+ if (cb->nlh->nlmsg_len >= nlmsg_msg_size(sizeof(*hdr))) {
+ hdr = nlmsg_data(cb->nlh);
+ ifindex = hdr->ifa_index;
+ } else {
+ if (cb->strict_check) {
+ NL_SET_ERR_MSG(cb->extack, "mctp: Invalid header for addr dump request");
+ return -EINVAL;
+ }
+ }
rcu_read_lock();
for_each_netdev_dump(net, dev, mcb->ifindex) {
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 4c46016..d9c8e5a 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -313,8 +313,10 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
key = flow->key;
- if (WARN_ON(key->dev && key->dev != dev))
+ if (key->dev) {
+ WARN_ON(key->dev != dev);
return;
+ }
mctp_dev_set_key(dev, key);
}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 2cb62f0..a715dcb 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -337,7 +337,11 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
release_sock(sk);
- sock_kfree_s(sk, match, sizeof(*match));
+ kfree_rcu_mightsleep(match);
+ /* Adjust sk_omem_alloc like sock_kfree_s() does, to match
+ * with allocation of this memory by sock_kmemdup()
+ */
+ atomic_sub(sizeof(*match), &sk->sk_omem_alloc);
err = 0;
out:
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index cf3ce72..5251524 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -64,7 +64,7 @@ struct hbucket {
#define ahash_sizeof_regions(htable_bits) \
(ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region))
#define ahash_region(n, htable_bits) \
- ((n) % ahash_numof_locks(htable_bits))
+ ((n) / jhash_size(HTABLE_REGION_BITS))
#define ahash_bucket_start(h, htable_bits) \
((htable_bits) < HTABLE_REGION_BITS ? 0 \
: (h) * jhash_size(HTABLE_REGION_BITS))
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 3313bce..014f077 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
return false;
}
-/* Get route to daddr, update *saddr, optionally bind route to saddr */
+/* Get route to daddr, optionally bind route to saddr */
static struct rtable *do_output_route4(struct net *net, __be32 daddr,
- int rt_mode, __be32 *saddr)
+ int rt_mode, __be32 *ret_saddr)
{
struct flowi4 fl4;
struct rtable *rt;
- bool loop = false;
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
@@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
retry:
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
- /* Invalid saddr ? */
- if (PTR_ERR(rt) == -EINVAL && *saddr &&
- rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
- *saddr = 0;
- flowi4_update_output(&fl4, 0, daddr, 0);
- goto retry;
- }
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
return NULL;
- } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+ }
+ if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
ip_rt_put(rt);
- *saddr = fl4.saddr;
flowi4_update_output(&fl4, 0, daddr, fl4.saddr);
- loop = true;
+ rt_mode = 0;
goto retry;
}
- *saddr = fl4.saddr;
+ if (ret_saddr)
+ *ret_saddr = fl4.saddr;
return rt;
}
@@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.ip;
} else {
- __be32 saddr = htonl(INADDR_ANY);
-
noref = 0;
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
- rt = do_output_route4(net, daddr, rt_mode, &saddr);
+ rt = do_output_route4(net, daddr, rt_mode, ret_saddr);
if (!rt)
goto err_unreach;
- if (ret_saddr)
- *ret_saddr = saddr;
}
local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 61fea7b..2f22ca5 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -975,8 +975,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
upcall.cmd = OVS_PACKET_CMD_ACTION;
upcall.mru = OVS_CB(skb)->mru;
- for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
- a = nla_next(a, &rem)) {
+ nla_for_each_nested(a, attr, rem) {
switch (nla_type(a)) {
case OVS_USERSPACE_ATTR_USERDATA:
upcall.userdata = a;
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 12dd711..c937610 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -144,7 +144,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt,
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index e0a81d3..9b6d79b 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -35,6 +35,11 @@ struct drr_sched {
struct Qdisc_class_hash clhash;
};
+static bool cl_is_active(struct drr_class *cl)
+{
+ return !list_empty(&cl->alist);
+}
+
static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
{
struct drr_sched *q = qdisc_priv(sch);
@@ -337,7 +342,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
int err = 0;
- bool first;
cl = drr_classify(skb, sch, &err);
if (cl == NULL) {
@@ -347,7 +351,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
@@ -357,7 +360,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- if (first) {
+ if (!cl_is_active(cl)) {
list_add_tail(&cl->alist, &q->active);
cl->deficit = cl->quantum;
}
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index c3bdeb1..2c069f0 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -74,6 +74,11 @@ static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = {
[TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 },
};
+static bool cl_is_active(struct ets_class *cl)
+{
+ return !list_empty(&cl->alist);
+}
+
static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr,
unsigned int *quantum,
struct netlink_ext_ack *extack)
@@ -416,7 +421,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct ets_sched *q = qdisc_priv(sch);
struct ets_class *cl;
int err = 0;
- bool first;
cl = ets_classify(skb, sch, &err);
if (!cl) {
@@ -426,7 +430,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
@@ -436,7 +439,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return err;
}
- if (first && !ets_class_is_strict(q, cl)) {
+ if (!cl_is_active(cl) && !ets_class_is_strict(q, cl)) {
list_add_tail(&cl->alist, &q->active);
cl->deficit = cl->quantum;
}
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 2ca5332..902ff54 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -1136,7 +1136,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
sch_tree_lock(sch);
}
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = fq_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
if (!skb)
break;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6c9029f..2a0f3a5 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -441,7 +441,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
while (sch->q.qlen > sch->limit ||
q->memory_usage > q->memory_limit) {
- struct sk_buff *skb = fq_codel_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
q->cstats.drop_len += qdisc_pkt_len(skb);
rtnl_kfree_skbs(skb, skb);
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index f3b8203..df7fac9 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -366,7 +366,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
/* Drop excess packets if new limit is lower */
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
len_dropped += qdisc_pkt_len(skb);
num_dropped += 1;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index ce5045e..7986145 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -961,6 +961,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (cl != NULL) {
int old_flags;
+ int len = 0;
if (parentid) {
if (cl->cl_parent &&
@@ -991,9 +992,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (usc != NULL)
hfsc_change_usc(cl, usc, cur_time);
+ if (cl->qdisc->q.qlen != 0)
+ len = qdisc_peek_len(cl->qdisc);
+ /* Check queue length again since some qdisc implementations
+ * (e.g., netem/codel) might empty the queue during the peek
+ * operation.
+ */
if (cl->qdisc->q.qlen != 0) {
- int len = qdisc_peek_len(cl->qdisc);
-
if (cl->cl_flags & HFSC_RSC) {
if (old_flags & HFSC_RSC)
update_ed(cl, len);
@@ -1564,7 +1569,10 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
return err;
}
- if (first) {
+ sch->qstats.backlog += len;
+ sch->q.qlen++;
+
+ if (first && !cl->cl_nactive) {
if (cl->cl_flags & HFSC_RSC)
init_ed(cl, len);
if (cl->cl_flags & HFSC_FSC)
@@ -1579,9 +1587,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
}
- sch->qstats.backlog += len;
- sch->q.qlen++;
-
return NET_XMIT_SUCCESS;
}
@@ -1636,10 +1641,16 @@ hfsc_dequeue(struct Qdisc *sch)
if (cl->qdisc->q.qlen != 0) {
/* update ed */
next_len = qdisc_peek_len(cl->qdisc);
- if (realtime)
- update_ed(cl, next_len);
- else
- update_d(cl, next_len);
+ /* Check queue length again since some qdisc implementations
+ * (e.g., netem/codel) might empty the queue during the peek
+ * operation.
+ */
+ if (cl->qdisc->q.qlen != 0) {
+ if (realtime)
+ update_ed(cl, next_len);
+ else
+ update_d(cl, next_len);
+ }
} else {
/* the class becomes passive */
eltree_remove(cl);
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 44d9efe..5aa434b 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -564,7 +564,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
qlen = sch->q.qlen;
prev_backlog = sch->qstats.backlog;
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = hhf_dequeue(sch);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
rtnl_kfree_skbs(skb, skb);
}
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 4b9a639..14bf71f 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -348,7 +348,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q,
*/
static inline void htb_next_rb_node(struct rb_node **n)
{
- *n = rb_next(*n);
+ if (*n)
+ *n = rb_next(*n);
}
/**
@@ -609,8 +610,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
*/
static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
{
- WARN_ON(!cl->prio_activity);
-
+ if (!cl->prio_activity)
+ return;
htb_deactivate_prios(q, cl);
cl->prio_activity = 0;
}
@@ -1485,8 +1486,6 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg)
{
struct htb_class *cl = (struct htb_class *)arg;
- if (!cl->prio_activity)
- return;
htb_deactivate(qdisc_priv(sch), cl);
}
@@ -1740,8 +1739,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
if (cl->parent)
cl->parent->children--;
- if (cl->prio_activity)
- htb_deactivate(q, cl);
+ htb_deactivate(q, cl);
if (cl->cmode != HTB_CAN_SEND)
htb_safe_rb_erase(&cl->pq_node,
@@ -1949,8 +1947,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
/* turn parent into inner node */
qdisc_purge_queue(parent->leaf.q);
parent_qdisc = parent->leaf.q;
- if (parent->prio_activity)
- htb_deactivate(q, parent);
+ htb_deactivate(q, parent);
/* remove from evt list because of level change */
if (parent->cmode != HTB_CAN_SEND) {
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 3771d00..ff49a6c 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -195,7 +195,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
/* Drop excess packets if new limit is lower */
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
- struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+ struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 687a932..bf1282c 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -202,6 +202,11 @@ struct qfq_sched {
*/
enum update_reason {enqueue, requeue};
+static bool cl_is_active(struct qfq_class *cl)
+{
+ return !list_empty(&cl->alist);
+}
+
static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
{
struct qfq_sched *q = qdisc_priv(sch);
@@ -1215,7 +1220,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct qfq_class *cl;
struct qfq_aggregate *agg;
int err = 0;
- bool first;
cl = qfq_classify(skb, sch, &err);
if (cl == NULL) {
@@ -1237,7 +1241,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
- first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
pr_debug("qfq_enqueue: enqueue failed %d\n", err);
@@ -1253,8 +1256,8 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
++sch->q.qlen;
agg = cl->agg;
- /* if the queue was not empty, then done here */
- if (!first) {
+ /* if the class is active, then done here */
+ if (cl_is_active(cl)) {
if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) &&
list_first_entry(&agg->active, struct qfq_class, alist)
== cl && cl->deficit < len)
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 004cdb59..7ce5e28 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1536,13 +1536,9 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
* or by one second if it has already reached the current time.
* Newly added cache entries will always have ->last_refresh greater
* that ->flush_time, so they don't get flushed prematurely.
- *
- * If someone frequently calls the flush interface, we should
- * immediately clean the corresponding cache_detail instead of
- * continuously accumulating nextcheck.
*/
- if (cd->flush_time >= now && cd->flush_time < (now + 5))
+ if (cd->flush_time >= now)
now = cd->flush_time + 1;
cd->flush_time = now;
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c524421..8584893 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -817,12 +817,16 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
goto exit;
}
+ /* Get net to avoid freed tipc_crypto when delete namespace */
+ get_net(aead->crypto->net);
+
/* Now, do encrypt */
rc = crypto_aead_encrypt(req);
if (rc == -EINPROGRESS || rc == -EBUSY)
return rc;
tipc_bearer_put(b);
+ put_net(aead->crypto->net);
exit:
kfree(ctx);
@@ -860,6 +864,7 @@ static void tipc_aead_encrypt_done(void *data, int err)
kfree(tx_ctx);
tipc_bearer_put(b);
tipc_aead_put(aead);
+ put_net(net);
}
/**
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index e2f1962..b45c5b9 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -716,7 +716,8 @@ void tipc_mon_reinit_self(struct net *net)
if (!mon)
continue;
write_lock_bh(&mon->lock);
- mon->self->addr = tipc_own_addr(net);
+ if (mon->self)
+ mon->self->addr = tipc_own_addr(net);
write_unlock_bh(&mon->lock);
}
}
diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index 77e33e1..65b0da6 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -396,7 +396,6 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort)
return 0;
shinfo = skb_shinfo(strp->anchor);
- shinfo->frag_list = NULL;
/* If we don't know the length go max plus page for cipher overhead */
need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE;
@@ -412,6 +411,8 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort)
page, 0, 0);
}
+ shinfo->frag_list = NULL;
+
strp->copy_mode = 1;
strp->stm.offset = 0;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 9865f305..ddd3a97 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2681,7 +2681,7 @@ cfg80211_defrag_mle(const struct element *mle, const u8 *ie, size_t ielen,
/* Required length for first defragmentation */
buf_len = mle->datalen - 1;
for_each_element(elem, mle->data + mle->datalen,
- ielen - sizeof(*mle) + mle->datalen) {
+ ie + ielen - mle->data - mle->datalen) {
if (elem->id != WLAN_EID_FRAGMENT)
break;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5696af4..72c000c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -338,13 +338,14 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
u32 len = xdp_get_buff_len(xdp);
int err;
- spin_lock_bh(&xs->rx_lock);
err = xsk_rcv_check(xs, xdp, len);
if (!err) {
+ spin_lock_bh(&xs->pool->rx_lock);
err = __xsk_rcv(xs, xdp, len);
xsk_flush(xs);
+ spin_unlock_bh(&xs->pool->rx_lock);
}
- spin_unlock_bh(&xs->rx_lock);
+
return err;
}
@@ -1303,7 +1304,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
xs->queue_id = qid;
xp_add_xsk(xs->pool, xs);
- if (xs->zc && qid < dev->real_num_rx_queues) {
+ if (qid < dev->real_num_rx_queues) {
struct netdev_rx_queue *rxq;
rxq = __netif_get_rx_queue(dev, qid);
@@ -1734,7 +1735,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
xs = xdp_sk(sk);
xs->state = XSK_READY;
mutex_init(&xs->mutex);
- spin_lock_init(&xs->rx_lock);
INIT_LIST_HEAD(&xs->map_list);
spin_lock_init(&xs->map_list_lock);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 25a76c5..c5181a9 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -89,6 +89,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
pool->addrs = umem->addrs;
pool->tx_metadata_len = umem->tx_metadata_len;
pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
+ spin_lock_init(&pool->rx_lock);
INIT_LIST_HEAD(&pool->free_list);
INIT_LIST_HEAD(&pool->xskb_list);
INIT_LIST_HEAD(&pool->xsk_tx_list);
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index fe82e2d..fc7a603 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -171,8 +171,10 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
struct espintcp_ctx *ctx = espintcp_getctx(sk);
if (skb_queue_len(&ctx->out_queue) >=
- READ_ONCE(net_hotdata.max_backlog))
+ READ_ONCE(net_hotdata.max_backlog)) {
+ kfree_skb(skb);
return -ENOBUFS;
+ }
__skb_queue_tail(&ctx->out_queue, skb);
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 0c14205..907c3cc 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -48,7 +48,6 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
{
struct acomp_req *req = ipcomp_cb(skb)->req;
struct ipcomp_req_extra *extra;
- const int plen = skb->data_len;
struct scatterlist *dsg;
int len, dlen;
@@ -64,7 +63,7 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen)
/* Only update truesize on input. */
if (!hlen)
- skb->truesize += dlen - plen;
+ skb->truesize += dlen;
skb->data_len = dlen;
skb->len += dlen;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 143ac3a..f4bad8c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1581,6 +1581,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
struct xfrm_policy *delpol;
struct hlist_head *chain;
+ /* Sanitize mark before store */
+ policy->mark.v &= policy->mark.m;
+
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
if (chain)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 341d79e..07fe8e5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -838,9 +838,6 @@ int __xfrm_state_delete(struct xfrm_state *x)
xfrm_nat_keepalive_state_updated(x);
spin_unlock(&net->xfrm.xfrm_state_lock);
- if (x->encap_sk)
- sock_put(rcu_dereference_raw(x->encap_sk));
-
xfrm_dev_state_delete(x);
/* All xfrm_state objects are created by xfrm_state_alloc.
@@ -1721,6 +1718,9 @@ static void __xfrm_state_insert(struct xfrm_state *x)
list_add(&x->km.all, &net->xfrm.state_all);
+ /* Sanitize mark before store */
+ x->mark.v &= x->mark.m;
+
h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
x->props.reqid, x->props.family);
XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
index 014af0d..a08eb55 100644
--- a/rust/bindings/lib.rs
+++ b/rust/bindings/lib.rs
@@ -26,6 +26,7 @@
#[allow(dead_code)]
#[allow(clippy::undocumented_unsafe_blocks)]
+#[cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))]
mod bindings_raw {
// Manual definition for blocklisted types.
type __kernel_size_t = usize;
diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs
index ae9d072..87a71fd 100644
--- a/rust/kernel/alloc/kvec.rs
+++ b/rust/kernel/alloc/kvec.rs
@@ -2,6 +2,9 @@
//! Implementation of [`Vec`].
+// May not be needed in Rust 1.87.0 (pending beta backport).
+#![allow(clippy::ptr_eq)]
+
use super::{
allocator::{KVmalloc, Kmalloc, Vmalloc},
layout::ArrayLayout,
diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs
index f04b058..2494c96e 100644
--- a/rust/kernel/firmware.rs
+++ b/rust/kernel/firmware.rs
@@ -4,7 +4,7 @@
//!
//! C header: [`include/linux/firmware.h`](srctree/include/linux/firmware.h)
-use crate::{bindings, device::Device, error::Error, error::Result, str::CStr};
+use crate::{bindings, device::Device, error::Error, error::Result, ffi, str::CStr};
use core::ptr::NonNull;
/// # Invariants
@@ -12,7 +12,11 @@
/// One of the following: `bindings::request_firmware`, `bindings::firmware_request_nowarn`,
/// `bindings::firmware_request_platform`, `bindings::request_firmware_direct`.
struct FwFunc(
- unsafe extern "C" fn(*mut *const bindings::firmware, *const u8, *mut bindings::device) -> i32,
+ unsafe extern "C" fn(
+ *mut *const bindings::firmware,
+ *const ffi::c_char,
+ *mut bindings::device,
+ ) -> i32,
);
impl FwFunc {
diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs
index a335c3b..2054682 100644
--- a/rust/kernel/list.rs
+++ b/rust/kernel/list.rs
@@ -4,6 +4,9 @@
//! A linked list implementation.
+// May not be needed in Rust 1.87.0 (pending beta backport).
+#![allow(clippy::ptr_eq)]
+
use crate::sync::ArcBorrow;
use crate::types::Opaque;
use core::iter::{DoubleEndedIterator, FusedIterator};
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index 878111c..fb61ce8 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -73,7 +73,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
b'\r' => f.write_str("\\r")?,
// Printable characters.
0x20..=0x7e => f.write_char(b as char)?,
- _ => write!(f, "\\x{:02x}", b)?,
+ _ => write!(f, "\\x{b:02x}")?,
}
}
Ok(())
@@ -109,7 +109,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
b'\\' => f.write_str("\\\\")?,
// Printable characters.
0x20..=0x7e => f.write_char(b as char)?,
- _ => write!(f, "\\x{:02x}", b)?,
+ _ => write!(f, "\\x{b:02x}")?,
}
}
f.write_char('"')
@@ -447,7 +447,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
// Printable character.
f.write_char(c as char)?;
} else {
- write!(f, "\\x{:02x}", c)?;
+ write!(f, "\\x{c:02x}")?;
}
}
Ok(())
@@ -479,7 +479,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
// Printable characters.
b'\"' => f.write_str("\\\"")?,
0x20..=0x7e => f.write_char(c as char)?,
- _ => write!(f, "\\x{:02x}", c)?,
+ _ => write!(f, "\\x{c:02x}")?,
}
}
f.write_str("\"")
@@ -641,13 +641,13 @@ fn test_cstr_as_str_unchecked() {
#[test]
fn test_cstr_display() {
let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
- assert_eq!(format!("{}", hello_world), "hello, world!");
+ assert_eq!(format!("{hello_world}"), "hello, world!");
let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
- assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a");
+ assert_eq!(format!("{non_printables}"), "\\x01\\x09\\x0a");
let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
- assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+ assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");
let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
- assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+ assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");
}
#[test]
@@ -658,47 +658,47 @@ fn test_cstr_display_all_bytes() {
bytes[i as usize] = i.wrapping_add(1);
}
let cstr = CStr::from_bytes_with_nul(&bytes).unwrap();
- assert_eq!(format!("{}", cstr), ALL_ASCII_CHARS);
+ assert_eq!(format!("{cstr}"), ALL_ASCII_CHARS);
}
#[test]
fn test_cstr_debug() {
let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
- assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+ assert_eq!(format!("{hello_world:?}"), "\"hello, world!\"");
let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
- assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\"");
+ assert_eq!(format!("{non_printables:?}"), "\"\\x01\\x09\\x0a\"");
let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
- assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+ assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\"");
let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
- assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+ assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\"");
}
#[test]
fn test_bstr_display() {
let hello_world = BStr::from_bytes(b"hello, world!");
- assert_eq!(format!("{}", hello_world), "hello, world!");
+ assert_eq!(format!("{hello_world}"), "hello, world!");
let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
- assert_eq!(format!("{}", escapes), "_\\t_\\n_\\r_\\_'_\"_");
+ assert_eq!(format!("{escapes}"), "_\\t_\\n_\\r_\\_'_\"_");
let others = BStr::from_bytes(b"\x01");
- assert_eq!(format!("{}", others), "\\x01");
+ assert_eq!(format!("{others}"), "\\x01");
let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
- assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+ assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");
let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
- assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+ assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");
}
#[test]
fn test_bstr_debug() {
let hello_world = BStr::from_bytes(b"hello, world!");
- assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+ assert_eq!(format!("{hello_world:?}"), "\"hello, world!\"");
let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
- assert_eq!(format!("{:?}", escapes), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\"");
+ assert_eq!(format!("{escapes:?}"), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\"");
let others = BStr::from_bytes(b"\x01");
- assert_eq!(format!("{:?}", others), "\"\\x01\"");
+ assert_eq!(format!("{others:?}"), "\"\\x01\"");
let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
- assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+ assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\"");
let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
- assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+ assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\"");
}
}
diff --git a/rust/macros/kunit.rs b/rust/macros/kunit.rs
index 4f553ec..99ccac8 100644
--- a/rust/macros/kunit.rs
+++ b/rust/macros/kunit.rs
@@ -15,10 +15,7 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
}
if attr.len() > 255 {
- panic!(
- "The test suite name `{}` exceeds the maximum length of 255 bytes",
- attr
- )
+ panic!("The test suite name `{attr}` exceeds the maximum length of 255 bytes")
}
let mut tokens: Vec<_> = ts.into_iter().collect();
@@ -102,16 +99,14 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
let mut kunit_macros = "".to_owned();
let mut test_cases = "".to_owned();
for test in &tests {
- let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{}", test);
+ let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{test}");
let kunit_wrapper = format!(
- "unsafe extern \"C\" fn {}(_test: *mut kernel::bindings::kunit) {{ {}(); }}",
- kunit_wrapper_fn_name, test
+ "unsafe extern \"C\" fn {kunit_wrapper_fn_name}(_test: *mut kernel::bindings::kunit) {{ {test}(); }}"
);
writeln!(kunit_macros, "{kunit_wrapper}").unwrap();
writeln!(
test_cases,
- " kernel::kunit::kunit_case(kernel::c_str!(\"{}\"), {}),",
- test, kunit_wrapper_fn_name
+ " kernel::kunit::kunit_case(kernel::c_str!(\"{test}\"), {kunit_wrapper_fn_name}),"
)
.unwrap();
}
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index a9418fb..2f66107 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -48,7 +48,7 @@ fn emit_base(&mut self, field: &str, content: &str, builtin: bool) {
)
} else {
// Loadable modules' modinfo strings go as-is.
- format!("{field}={content}\0", field = field, content = content)
+ format!("{field}={content}\0")
};
write!(
@@ -126,10 +126,7 @@ fn parse(it: &mut token_stream::IntoIter) -> Self {
};
if seen_keys.contains(&key) {
- panic!(
- "Duplicated key \"{}\". Keys can only be specified once.",
- key
- );
+ panic!("Duplicated key \"{key}\". Keys can only be specified once.");
}
assert_eq!(expect_punct(it), ':');
@@ -143,10 +140,7 @@ fn parse(it: &mut token_stream::IntoIter) -> Self {
"license" => info.license = expect_string_ascii(it),
"alias" => info.alias = Some(expect_string_array(it)),
"firmware" => info.firmware = Some(expect_string_array(it)),
- _ => panic!(
- "Unknown key \"{}\". Valid keys are: {:?}.",
- key, EXPECTED_KEYS
- ),
+ _ => panic!("Unknown key \"{key}\". Valid keys are: {EXPECTED_KEYS:?}."),
}
assert_eq!(expect_punct(it), ',');
@@ -158,7 +152,7 @@ fn parse(it: &mut token_stream::IntoIter) -> Self {
for key in REQUIRED_KEYS {
if !seen_keys.iter().any(|e| e == key) {
- panic!("Missing required key \"{}\".", key);
+ panic!("Missing required key \"{key}\".");
}
}
@@ -170,10 +164,7 @@ fn parse(it: &mut token_stream::IntoIter) -> Self {
}
if seen_keys != ordered_keys {
- panic!(
- "Keys are not ordered as expected. Order them like: {:?}.",
- ordered_keys
- );
+ panic!("Keys are not ordered as expected. Order them like: {ordered_keys:?}.");
}
info
diff --git a/rust/macros/paste.rs b/rust/macros/paste.rs
index 6529a38..cce712d 100644
--- a/rust/macros/paste.rs
+++ b/rust/macros/paste.rs
@@ -50,7 +50,7 @@ fn concat_helper(tokens: &[TokenTree]) -> Vec<(String, Span)> {
let tokens = group.stream().into_iter().collect::<Vec<TokenTree>>();
segments.append(&mut concat_helper(tokens.as_slice()));
}
- token => panic!("unexpected token in paste segments: {:?}", token),
+ token => panic!("unexpected token in paste segments: {token:?}"),
};
}
diff --git a/rust/pin-init/internal/src/pinned_drop.rs b/rust/pin-init/internal/src/pinned_drop.rs
index c824dd8..c4ca7a7 100644
--- a/rust/pin-init/internal/src/pinned_drop.rs
+++ b/rust/pin-init/internal/src/pinned_drop.rs
@@ -28,8 +28,7 @@ pub(crate) fn pinned_drop(_args: TokenStream, input: TokenStream) -> TokenStream
// Found the end of the generics, this should be `PinnedDrop`.
assert!(
matches!(tt, TokenTree::Ident(i) if i.to_string() == "PinnedDrop"),
- "expected 'PinnedDrop', found: '{:?}'",
- tt
+ "expected 'PinnedDrop', found: '{tt:?}'"
);
pinned_drop_idx = Some(i);
break;
diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs
index 1349591..c98d7a8 100644
--- a/rust/uapi/lib.rs
+++ b/rust/uapi/lib.rs
@@ -24,6 +24,7 @@
unreachable_pub,
unsafe_op_in_unsafe_fn
)]
+#![cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))]
// Manual definition of blocklisted types.
type __kernel_size_t = usize;
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 5b63263..95a4fa1 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -376,7 +376,7 @@
@echo " CLANG-bpf " $@
$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
- -I$(LIBBPF_INCLUDE) \
+ -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
index dac67c3..4147616 100644
--- a/samples/ftrace/sample-trace-array.c
+++ b/samples/ftrace/sample-trace-array.c
@@ -112,7 +112,7 @@ static int __init sample_trace_array_init(void)
/*
* If context specific per-cpu buffers havent already been allocated.
*/
- trace_printk_init_buffers();
+ trace_array_init_printk(tr);
simple_tsk = kthread_run(simple_thread, NULL, "sample-instance");
if (IS_ERR(simple_tsk)) {
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index d758975..fd649c6 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -8,6 +8,7 @@
# Default set of warnings, always enabled
KBUILD_CFLAGS += -Wall
+KBUILD_CFLAGS += -Wextra
KBUILD_CFLAGS += -Wundef
KBUILD_CFLAGS += -Werror=implicit-function-declaration
KBUILD_CFLAGS += -Werror=implicit-int
@@ -15,7 +16,7 @@
KBUILD_CFLAGS += -Werror=strict-prototypes
KBUILD_CFLAGS += -Wno-format-security
KBUILD_CFLAGS += -Wno-trigraphs
-KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
+KBUILD_CFLAGS += $(call cc-disable-warning, frame-address)
KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
KBUILD_CFLAGS += -Wmissing-declarations
KBUILD_CFLAGS += -Wmissing-prototypes
@@ -36,6 +37,18 @@
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219
KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf)
KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf)
+
+# Clang may emit a warning when a const variable, such as the dummy variables
+# in typecheck(), or const member of an aggregate type are not initialized,
+# which can result in unexpected behavior. However, in many audited cases of
+# the "field" variant of the warning, this is intentional because the field is
+# never used within a particular call path, the field is within a union with
+# other non-const members, or the containing object is not const so the field
+# can be modified via memcpy() / memset(). While the variable warning also gets
+# disabled with this same switch, there should not be too much coverage lost
+# because -Wuninitialized will still flag when an uninitialized const variable
+# is used.
+KBUILD_CFLAGS += $(call cc-disable-warning, default-const-init-unsafe)
else
# gcc inanely warns about local variables called 'main'
@@ -56,6 +69,13 @@
# globally built with -Wcast-function-type.
KBUILD_CFLAGS += $(call cc-option, -Wcast-function-type)
+# Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-disable-warning, stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
+# Currently, disable -Wunterminated-string-initialization as broken
+KBUILD_CFLAGS += $(call cc-disable-warning, unterminated-string-initialization)
+
# The allocators already balk at large sizes, so silence the compiler
# warnings for bounds checks involving those possible values. While
# -Wno-alloc-size-larger-than would normally be used here, earlier versions
@@ -82,7 +102,6 @@
# Warn if there is an enum types mismatch
KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion)
-KBUILD_CFLAGS += -Wextra
KBUILD_CFLAGS += -Wunused
#
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index b0a6cd5..b64862d 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -13,7 +13,7 @@
vmlinux-final := vmlinux.unstripped
quiet_cmd_strip_relocs = RSTRIP $@
- cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $< $@
+ cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' --remove-section=!'.rel*.dyn' $< $@
vmlinux: $(vmlinux-final) FORCE
$(call if_changed,strip_relocs)
@@ -94,10 +94,10 @@
endif
ifdef CONFIG_BUILDTIME_TABLE_SORT
-vmlinux: scripts/sorttable
+$(vmlinux-final): scripts/sorttable
endif
-# module.builtin.ranges
+# modules.builtin.ranges
# ---------------------------------------------------------------------------
ifdef CONFIG_BUILTIN_MODULE_RANGES
__default: modules.builtin.ranges
diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
index 938c745..b024ffb 100644
--- a/scripts/Makefile.vmlinux_o
+++ b/scripts/Makefile.vmlinux_o
@@ -73,7 +73,7 @@
targets += vmlinux.o
-# module.builtin.modinfo
+# modules.builtin.modinfo
# ---------------------------------------------------------------------------
OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary
@@ -82,7 +82,7 @@
modules.builtin.modinfo: vmlinux.o FORCE
$(call if_changed,objcopy)
-# module.builtin
+# modules.builtin
# ---------------------------------------------------------------------------
# The second line aids cases where multiple modules share the same object.
diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
index 726f34e..98f206c 100644
--- a/scripts/package/kernel.spec
+++ b/scripts/package/kernel.spec
@@ -16,6 +16,7 @@
Source2: diff.patch
Provides: kernel-%{KERNELRELEASE}
BuildRequires: bc binutils bison dwarves
+BuildRequires: (elfutils-devel or libdw-devel)
BuildRequires: (elfutils-libelf-devel or libelf-devel) flex
BuildRequires: gcc make openssl openssl-devel perl python3 rsync
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 744ddba..d4b007b 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -210,7 +210,7 @@
Build-Depends: debhelper-compat (= 12)
Build-Depends-Arch: bc, bison, flex,
gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>,
- kmod, libelf-dev:native,
+ kmod, libdw-dev:native, libelf-dev:native,
libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>,
python3:native, rsync
Homepage: https://www.kernel.org/
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index f3e7ac5..f99ab1a 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -245,7 +245,9 @@ static int process_measurement(struct file *file, const struct cred *cred,
&allowed_algos);
violation_check = ((func == FILE_CHECK || func == MMAP_CHECK ||
func == MMAP_CHECK_REQPROT) &&
- (ima_policy_flag & IMA_MEASURE));
+ (ima_policy_flag & IMA_MEASURE) &&
+ ((action & IMA_MEASURE) ||
+ (file->f_mode & FMODE_WRITE)));
if (!action && !violation_check)
return 0;
diff --git a/security/landlock/audit.c b/security/landlock/audit.c
index 7e5e0ed..c52d079 100644
--- a/security/landlock/audit.c
+++ b/security/landlock/audit.c
@@ -175,7 +175,7 @@ static void test_get_hierarchy(struct kunit *const test)
KUNIT_EXPECT_EQ(test, 10, get_hierarchy(&dom2, 0)->id);
KUNIT_EXPECT_EQ(test, 20, get_hierarchy(&dom2, 1)->id);
KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, 2)->id);
- KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id);
+ /* KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id); */
}
#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
@@ -437,7 +437,7 @@ void landlock_log_denial(const struct landlock_cred_security *const subject,
return;
/* Checks if the current exec was restricting itself. */
- if (subject->domain_exec & (1 << youngest_layer)) {
+ if (subject->domain_exec & BIT(youngest_layer)) {
/* Ignores denials for the same execution. */
if (!youngest_denied->log_same_exec)
return;
diff --git a/security/landlock/domain.c b/security/landlock/domain.c
index bae2e99..a647b68 100644
--- a/security/landlock/domain.c
+++ b/security/landlock/domain.c
@@ -16,6 +16,7 @@
#include <linux/path.h>
#include <linux/pid.h>
#include <linux/sched.h>
+#include <linux/signal.h>
#include <linux/uidgid.h>
#include "access.h"
@@ -99,8 +100,7 @@ static struct landlock_details *get_current_details(void)
return ERR_PTR(-ENOMEM);
memcpy(details->exe_path, path_str, path_size);
- WARN_ON_ONCE(current_cred() != current_real_cred());
- details->pid = get_pid(task_pid(current));
+ details->pid = get_pid(task_tgid(current));
details->uid = from_kuid(&init_user_ns, current_uid());
get_task_comm(details->comm, current);
return details;
diff --git a/security/landlock/domain.h b/security/landlock/domain.h
index ed0d348..7fb70b2 100644
--- a/security/landlock/domain.h
+++ b/security/landlock/domain.h
@@ -130,7 +130,7 @@ int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy);
static inline void
landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy)
{
- if (WARN_ON_ONCE(!hierarchy || !hierarchy->details))
+ if (!hierarchy || !hierarchy->details)
return;
put_pid(hierarchy->details->pid);
diff --git a/security/landlock/id.c b/security/landlock/id.c
index 11fab92..56f7cc0 100644
--- a/security/landlock/id.c
+++ b/security/landlock/id.c
@@ -7,6 +7,7 @@
#include <kunit/test.h>
#include <linux/atomic.h>
+#include <linux/bitops.h>
#include <linux/random.h>
#include <linux/spinlock.h>
@@ -25,7 +26,7 @@ static void __init init_id(atomic64_t *const counter, const u32 random_32bits)
* Ensures sure 64-bit values are always used by user space (or may
* fail with -EOVERFLOW), and makes this testable.
*/
- init = 1ULL << 32;
+ init = BIT_ULL(32);
/*
* Makes a large (2^32) boot-time value to limit ID collision in logs
@@ -105,7 +106,7 @@ static u64 get_id_range(size_t number_of_ids, atomic64_t *const counter,
* to get a new ID (e.g. a full landlock_restrict_self() call), and the
* cost of draining all available IDs during the system's uptime.
*/
- random_4bits = random_4bits % (1 << 4);
+ random_4bits &= 0b1111;
step = number_of_ids + random_4bits;
/* It is safe to cast a signed atomic to an unsigned value. */
@@ -144,6 +145,19 @@ static void test_range1_rand1(struct kunit *const test)
init + 2);
}
+static void test_range1_rand15(struct kunit *const test)
+{
+ atomic64_t counter;
+ u64 init;
+
+ init = get_random_u32();
+ atomic64_set(&counter, init);
+ KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 15), init);
+ KUNIT_EXPECT_EQ(
+ test, get_id_range(get_random_u8(), &counter, get_random_u8()),
+ init + 16);
+}
+
static void test_range1_rand16(struct kunit *const test)
{
atomic64_t counter;
@@ -196,6 +210,19 @@ static void test_range2_rand2(struct kunit *const test)
init + 4);
}
+static void test_range2_rand15(struct kunit *const test)
+{
+ atomic64_t counter;
+ u64 init;
+
+ init = get_random_u32();
+ atomic64_set(&counter, init);
+ KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 15), init);
+ KUNIT_EXPECT_EQ(
+ test, get_id_range(get_random_u8(), &counter, get_random_u8()),
+ init + 17);
+}
+
static void test_range2_rand16(struct kunit *const test)
{
atomic64_t counter;
@@ -232,10 +259,12 @@ static struct kunit_case __refdata test_cases[] = {
KUNIT_CASE(test_init_once),
KUNIT_CASE(test_range1_rand0),
KUNIT_CASE(test_range1_rand1),
+ KUNIT_CASE(test_range1_rand15),
KUNIT_CASE(test_range1_rand16),
KUNIT_CASE(test_range2_rand0),
KUNIT_CASE(test_range2_rand1),
KUNIT_CASE(test_range2_rand2),
+ KUNIT_CASE(test_range2_rand15),
KUNIT_CASE(test_range2_rand16),
{}
/* clang-format on */
diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c
index 54a9f29..33eafb71 100644
--- a/security/landlock/syscalls.c
+++ b/security/landlock/syscalls.c
@@ -9,6 +9,7 @@
#include <asm/current.h>
#include <linux/anon_inodes.h>
+#include <linux/bitops.h>
#include <linux/build_bug.h>
#include <linux/capability.h>
#include <linux/cleanup.h>
@@ -169,20 +170,16 @@ const int landlock_abi_version = 7;
* the new ruleset.
* @size: Size of the pointed &struct landlock_ruleset_attr (needed for
* backward and forward compatibility).
- * @flags: Supported value:
+ * @flags: Supported values:
+ *
* - %LANDLOCK_CREATE_RULESET_VERSION
* - %LANDLOCK_CREATE_RULESET_ERRATA
*
* This system call enables to create a new Landlock ruleset, and returns the
* related file descriptor on success.
*
- * If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is
- * 0, then the returned value is the highest supported Landlock ABI version
- * (starting at 1).
- *
- * If @flags is %LANDLOCK_CREATE_RULESET_ERRATA and @attr is NULL and @size is
- * 0, then the returned value is a bitmask of fixed issues for the current
- * Landlock ABI version.
+ * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is
+ * set, then @attr must be NULL and @size must be 0.
*
* Possible returned errors are:
*
@@ -191,6 +188,9 @@ const int landlock_abi_version = 7;
* - %E2BIG: @attr or @size inconsistencies;
* - %EFAULT: @attr or @size inconsistencies;
* - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ * :identifiers: landlock_create_ruleset_flags
*/
SYSCALL_DEFINE3(landlock_create_ruleset,
const struct landlock_ruleset_attr __user *const, attr,
@@ -452,18 +452,15 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
* @ruleset_fd: File descriptor tied to the ruleset to merge with the target.
* @flags: Supported values:
*
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
*
* This system call enables to enforce a Landlock ruleset on the current
* thread. Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its
* namespace or is running with no_new_privs. This avoids scenarios where
* unprivileged tasks can affect the behavior of privileged children.
*
- * It is allowed to only pass the %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
- * flag with a @ruleset_fd value of -1.
- *
* Possible returned errors are:
*
* - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
@@ -475,6 +472,9 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
* %CAP_SYS_ADMIN in its namespace.
* - %E2BIG: The maximum number of stacked rulesets is reached for the current
* thread.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ * :identifiers: landlock_restrict_self_flags
*/
SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
flags)
@@ -564,7 +564,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
new_llcred->domain = new_dom;
#ifdef CONFIG_AUDIT
- new_llcred->domain_exec |= 1 << (new_dom->num_layers - 1);
+ new_llcred->domain_exec |= BIT(new_dom->num_layers - 1);
#endif /* CONFIG_AUDIT */
return commit_creds(new_cred);
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 4683b91..4ecb17b 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1074,8 +1074,7 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream)
runtime->oss.params = 0;
runtime->oss.prepare = 1;
runtime->oss.buffer_used = 0;
- if (runtime->dma_area)
- snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes));
+ snd_pcm_runtime_buffer_set_silence(runtime);
runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size);
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 6c2b6a6..853ac5b 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -723,6 +723,17 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime)
atomic_inc(&runtime->buffer_accessing);
}
+/* fill the PCM buffer with the current silence format; called from pcm_oss.c */
+void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime)
+{
+ snd_pcm_buffer_access_lock(runtime);
+ if (runtime->dma_area)
+ snd_pcm_format_set_silence(runtime->format, runtime->dma_area,
+ bytes_to_samples(runtime, runtime->dma_bytes));
+ snd_pcm_buffer_access_unlock(runtime);
+}
+EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence);
+
#if IS_ENABLED(CONFIG_SND_PCM_OSS)
#define is_oss_stream(substream) ((substream)->oss.oss)
#else
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 198c598..8802409 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -732,15 +732,21 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client,
*/
static int __deliver_to_subscribers(struct snd_seq_client *client,
struct snd_seq_event *event,
- struct snd_seq_client_port *src_port,
- int atomic, int hop)
+ int port, int atomic, int hop)
{
+ struct snd_seq_client_port *src_port;
struct snd_seq_subscribers *subs;
int err, result = 0, num_ev = 0;
union __snd_seq_event event_saved;
size_t saved_size;
struct snd_seq_port_subs_info *grp;
+ if (port < 0)
+ return 0;
+ src_port = snd_seq_port_use_ptr(client, port);
+ if (!src_port)
+ return 0;
+
/* save original event record */
saved_size = snd_seq_event_packet_size(event);
memcpy(&event_saved, event, saved_size);
@@ -775,6 +781,7 @@ static int __deliver_to_subscribers(struct snd_seq_client *client,
read_unlock(&grp->list_lock);
else
up_read(&grp->list_mutex);
+ snd_seq_port_unlock(src_port);
memcpy(event, &event_saved, saved_size);
return (result < 0) ? result : num_ev;
}
@@ -783,25 +790,32 @@ static int deliver_to_subscribers(struct snd_seq_client *client,
struct snd_seq_event *event,
int atomic, int hop)
{
- struct snd_seq_client_port *src_port;
- int ret = 0, ret2;
+ int ret;
+#if IS_ENABLED(CONFIG_SND_SEQ_UMP)
+ int ret2;
+#endif
- src_port = snd_seq_port_use_ptr(client, event->source.port);
- if (src_port) {
- ret = __deliver_to_subscribers(client, event, src_port, atomic, hop);
- snd_seq_port_unlock(src_port);
- }
-
- if (client->ump_endpoint_port < 0 ||
- event->source.port == client->ump_endpoint_port)
+ ret = __deliver_to_subscribers(client, event,
+ event->source.port, atomic, hop);
+#if IS_ENABLED(CONFIG_SND_SEQ_UMP)
+ if (!snd_seq_client_is_ump(client) || client->ump_endpoint_port < 0)
return ret;
-
- src_port = snd_seq_port_use_ptr(client, client->ump_endpoint_port);
- if (!src_port)
- return ret;
- ret2 = __deliver_to_subscribers(client, event, src_port, atomic, hop);
- snd_seq_port_unlock(src_port);
- return ret2 < 0 ? ret2 : ret;
+ /* If it's an event from EP port (and with a UMP group),
+ * deliver to subscribers of the corresponding UMP group port, too.
+ * Or, if it's from non-EP port, deliver to subscribers of EP port, too.
+ */
+ if (event->source.port == client->ump_endpoint_port)
+ ret2 = __deliver_to_subscribers(client, event,
+ snd_seq_ump_group_port(event),
+ atomic, hop);
+ else
+ ret2 = __deliver_to_subscribers(client, event,
+ client->ump_endpoint_port,
+ atomic, hop);
+ if (ret2 < 0)
+ return ret2;
+#endif
+ return ret;
}
/* deliver an event to the destination port(s).
diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index ff7e558b..db2f169 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -1285,3 +1285,21 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source,
else
return cvt_to_ump_midi1(dest, dest_port, event, atomic, hop);
}
+
+/* return the UMP group-port number of the event;
+ * return -1 if groupless or non-UMP event
+ */
+int snd_seq_ump_group_port(const struct snd_seq_event *event)
+{
+ const struct snd_seq_ump_event *ump_ev =
+ (const struct snd_seq_ump_event *)event;
+ unsigned char type;
+
+ if (!snd_seq_ev_is_ump(event))
+ return -1;
+ type = ump_message_type(ump_ev->ump[0]);
+ if (ump_is_groupless_msg(type))
+ return -1;
+ /* group-port number starts from 1 */
+ return ump_message_group(ump_ev->ump[0]) + 1;
+}
diff --git a/sound/core/seq/seq_ump_convert.h b/sound/core/seq/seq_ump_convert.h
index 6c146d8..4abf0a7 100644
--- a/sound/core/seq/seq_ump_convert.h
+++ b/sound/core/seq/seq_ump_convert.h
@@ -18,5 +18,6 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source,
struct snd_seq_client_port *dest_port,
struct snd_seq_event *event,
int atomic, int hop);
+int snd_seq_ump_group_port(const struct snd_seq_event *event);
#endif /* __SEQ_UMP_CONVERT_H */
diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c
index 8686ada..d351113 100644
--- a/sound/hda/intel-sdw-acpi.c
+++ b/sound/hda/intel-sdw-acpi.c
@@ -177,7 +177,7 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level,
* sdw_intel_startup() is required for creation of devices and bus
* startup
*/
-int sdw_intel_acpi_scan(acpi_handle *parent_handle,
+int sdw_intel_acpi_scan(acpi_handle parent_handle,
struct sdw_intel_acpi_info *info)
{
acpi_status status;
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index c6c018b..4e0693f 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -1561,7 +1561,7 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream)
struct snd_pcm_runtime *runtime = substream->runtime;
struct es1968 *chip = snd_pcm_substream_chip(substream);
struct esschan *es;
- int apu1, apu2;
+ int err, apu1, apu2;
apu1 = snd_es1968_alloc_apu_pair(chip, ESM_APU_PCM_CAPTURE);
if (apu1 < 0)
@@ -1605,7 +1605,9 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream)
runtime->hw = snd_es1968_capture;
runtime->hw.buffer_bytes_max = runtime->hw.period_bytes_max =
calc_available_memory_size(chip) - 1024; /* keep MIXBUF size */
- snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES);
+ err = snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES);
+ if (err < 0)
+ return err;
spin_lock_irq(&chip->substream_lock);
list_add(&es->list, &chip->substream_list);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 877137c..20ab1fb 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -441,6 +441,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
fallthrough;
case 0x10ec0215:
+ case 0x10ec0236:
+ case 0x10ec0245:
+ case 0x10ec0256:
+ case 0x10ec0257:
case 0x10ec0285:
case 0x10ec0289:
alc_update_coef_idx(codec, 0x36, 1<<13, 0);
@@ -448,12 +452,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0230:
case 0x10ec0233:
case 0x10ec0235:
- case 0x10ec0236:
- case 0x10ec0245:
case 0x10ec0255:
- case 0x10ec0256:
case 0x19e58326:
- case 0x10ec0257:
case 0x10ec0282:
case 0x10ec0283:
case 0x10ec0286:
@@ -6742,6 +6742,25 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
codec->power_save_node = 0;
}
+/* avoid DAC 0x06 for speaker switch 0x17; it has no volume control */
+static void alc274_fixup_hp_aio_bind_dacs(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */
+ /* The speaker is routed to the Node 0x06 by a mistake, thus the
+ * speaker's volume can't be adjusted since the node doesn't have
+ * Amp-out capability. Assure the speaker and lineout pin to be
+ * coupled with DAC NID 0x02.
+ */
+ static const hda_nid_t preferred_pairs[] = {
+ 0x16, 0x02, 0x17, 0x02, 0x21, 0x03, 0
+ };
+ struct alc_spec *spec = codec->spec;
+
+ snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+ spec->gen.preferred_dacs = preferred_pairs;
+}
+
/* avoid DAC 0x06 for bass speaker 0x17; it has no volume control */
static void alc289_fixup_asus_ga401(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
@@ -6811,7 +6830,10 @@ static void alc256_fixup_chromebook(struct hda_codec *codec,
switch (action) {
case HDA_FIXUP_ACT_PRE_PROBE:
- spec->gen.suppress_auto_mute = 1;
+ if (codec->core.subsystem_id == 0x10280d76)
+ spec->gen.suppress_auto_mute = 0;
+ else
+ spec->gen.suppress_auto_mute = 1;
spec->gen.suppress_auto_mic = 1;
spec->en_3kpull_low = false;
break;
@@ -6963,6 +6985,41 @@ static void alc285_fixup_hp_spectre_x360_eb1(struct hda_codec *codec,
}
}
+/* GPIO1 = amplifier on/off */
+static void alc285_fixup_hp_spectre_x360_df1(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
+{
+ struct alc_spec *spec = codec->spec;
+ static const hda_nid_t conn[] = { 0x02 };
+ static const struct hda_pintbl pincfgs[] = {
+ { 0x14, 0x90170110 }, /* front/high speakers */
+ { 0x17, 0x90170130 }, /* back/bass speakers */
+ { }
+ };
+
+ // enable mute led
+ alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ /* needed for amp of back speakers */
+ spec->gpio_mask |= 0x01;
+ spec->gpio_dir |= 0x01;
+ snd_hda_apply_pincfgs(codec, pincfgs);
+ /* share DAC to have unified volume control */
+ snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn), conn);
+ snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+ break;
+ case HDA_FIXUP_ACT_INIT:
+ /* need to toggle GPIO to enable the amp of back speakers */
+ alc_update_gpio_data(codec, 0x01, true);
+ msleep(100);
+ alc_update_gpio_data(codec, 0x01, false);
+ break;
+ }
+}
+
static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -7761,6 +7818,7 @@ enum {
ALC280_FIXUP_HP_9480M,
ALC245_FIXUP_HP_X360_AMP,
ALC285_FIXUP_HP_SPECTRE_X360_EB1,
+ ALC285_FIXUP_HP_SPECTRE_X360_DF1,
ALC285_FIXUP_HP_ENVY_X360,
ALC288_FIXUP_DELL_HEADSET_MODE,
ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -7970,6 +8028,7 @@ enum {
ALC294_FIXUP_BASS_SPEAKER_15,
ALC283_FIXUP_DELL_HP_RESUME,
ALC294_FIXUP_ASUS_CS35L41_SPI_2,
+ ALC274_FIXUP_HP_AIO_BIND_DACS,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9837,6 +9896,10 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_spectre_x360_eb1
},
+ [ALC285_FIXUP_HP_SPECTRE_X360_DF1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_hp_spectre_x360_df1
+ },
[ALC285_FIXUP_HP_ENVY_X360] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_envy_x360,
@@ -10340,6 +10403,10 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC,
},
+ [ALC274_FIXUP_HP_AIO_BIND_DACS] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc274_fixup_hp_aio_bind_dacs,
+ },
};
static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -10564,6 +10631,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+ SND_PCI_QUIRK(0x103c, 0x863e, "HP Spectre x360 15-df1xxx", ALC285_FIXUP_HP_SPECTRE_X360_DF1),
SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
@@ -10768,12 +10836,13 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8caf, "HP Elite mt645 G8 Mobile Thin Client", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
- SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
- SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
+ SND_PCI_QUIRK(0x103c, 0x8cde, "HP OmniBook Ultra Flip Laptop 14t", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALC285_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8d18, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 14 G12", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8d86, "HP Elite X360 14 G12", ALC285_FIXUP_HP_GPIO_LED),
@@ -10793,11 +10862,15 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8da1, "HP 16 Clipper OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8ded, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8dee, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8def, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8df0, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8df1, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10812,9 +10885,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8e1a, "HP ZBook Firefly 14 G12A", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A),
SND_PCI_QUIRK(0x103c, 0x8e1b, "HP EliteBook G12", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A),
SND_PCI_QUIRK(0x103c, 0x8e1c, "HP EliteBook G12", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A),
+ SND_PCI_QUIRK(0x103c, 0x8e1d, "HP ZBook X Gli 16 G12", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8e2c, "HP EliteBook 16 G12", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8e36, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8e37, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8e3a, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8e3b, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10843,10 +10919,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC294_FIXUP_ASUS_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
- SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1460, "Asus VivoBook 15", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -10900,7 +10976,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
- SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC),
@@ -11230,6 +11306,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
SND_PCI_QUIRK(0x17aa, 0x38fd, "ThinkBook plus Gen5 Hybrid", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
+ SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC),
SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TAS2781_I2C),
@@ -11494,6 +11571,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
{.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"},
{.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"},
{.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"},
+ {.id = ALC285_FIXUP_HP_SPECTRE_X360_DF1, .name = "alc285-hp-spectre-x360-df1"},
{.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"},
{.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"},
{.id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, .name = "alc287-yoga9-bass-spk-pin"},
diff --git a/sound/sh/Kconfig b/sound/sh/Kconfig
index b75fbb3..f5fa09d 100644
--- a/sound/sh/Kconfig
+++ b/sound/sh/Kconfig
@@ -14,7 +14,7 @@
config SND_AICA
tristate "Dreamcast Yamaha AICA sound"
- depends on SH_DREAMCAST
+ depends on SH_DREAMCAST && SH_DMA_API
select SND_PCM
select G2_DMA
help
diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c
index a38409d..70fa54d 100644
--- a/sound/soc/amd/acp/acp-i2s.c
+++ b/sound/soc/amd/acp/acp-i2s.c
@@ -97,7 +97,7 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas
struct acp_stream *stream;
int slot_len, no_of_slots;
- chip = dev_get_platdata(dev);
+ chip = dev_get_drvdata(dev->parent);
switch (slot_width) {
case SLOT_WIDTH_8:
slot_len = 8;
diff --git a/sound/soc/amd/acp/acp-legacy-common.c b/sound/soc/amd/acp/acp-legacy-common.c
index b4d6848..ba8db08 100644
--- a/sound/soc/amd/acp/acp-legacy-common.c
+++ b/sound/soc/amd/acp/acp-legacy-common.c
@@ -450,7 +450,7 @@ int acp_machine_select(struct acp_chip_info *chip)
struct snd_soc_acpi_mach *mach;
int size, platform;
- if (chip->flag == FLAG_AMD_LEGACY_ONLY_DMIC) {
+ if (chip->flag == FLAG_AMD_LEGACY_ONLY_DMIC && chip->is_pdm_dev) {
platform = chip->acp_rev;
chip->mach_dev = platform_device_register_data(chip->dev, "acp-pdm-mach",
PLATFORM_DEVID_NONE, &platform,
diff --git a/sound/soc/amd/acp/acp-rembrandt.c b/sound/soc/amd/acp/acp-rembrandt.c
index 746b6ed..cccdd10 100644
--- a/sound/soc/amd/acp/acp-rembrandt.c
+++ b/sound/soc/amd/acp/acp-rembrandt.c
@@ -199,7 +199,7 @@ static void rembrandt_audio_remove(struct platform_device *pdev)
static int rmb_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp-renoir.c b/sound/soc/amd/acp/acp-renoir.c
index ebf0106..04f6d70b 100644
--- a/sound/soc/amd/acp/acp-renoir.c
+++ b/sound/soc/amd/acp/acp-renoir.c
@@ -146,7 +146,7 @@ static void renoir_audio_remove(struct platform_device *pdev)
static int rn_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp63.c b/sound/soc/amd/acp/acp63.c
index 52d895e..1f15c96 100644
--- a/sound/soc/amd/acp/acp63.c
+++ b/sound/soc/amd/acp/acp63.c
@@ -250,7 +250,7 @@ static void acp63_audio_remove(struct platform_device *pdev)
static int acp63_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/acp/acp70.c b/sound/soc/amd/acp/acp70.c
index 6d5f5ad..217b717 100644
--- a/sound/soc/amd/acp/acp70.c
+++ b/sound/soc/amd/acp/acp70.c
@@ -182,7 +182,7 @@ static void acp_acp70_audio_remove(struct platform_device *pdev)
static int acp70_pcm_resume(struct device *dev)
{
- struct acp_chip_info *chip = dev_get_platdata(dev);
+ struct acp_chip_info *chip = dev_get_drvdata(dev->parent);
struct acp_stream *stream;
struct snd_pcm_substream *substream;
snd_pcm_uframes_t buf_in_frames;
diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c
index 8e57f31..7936b31 100644
--- a/sound/soc/amd/ps/pci-ps.c
+++ b/sound/soc/amd/ps/pci-ps.c
@@ -193,6 +193,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
struct amd_sdw_manager *amd_manager;
u32 ext_intr_stat, ext_intr_stat1;
u16 irq_flag = 0;
+ u16 wake_irq_flag = 0;
u16 sdw_dma_irq_flag = 0;
adata = dev_id;
@@ -231,7 +232,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
}
if (adata->acp_rev >= ACP70_PCI_REV)
- irq_flag = check_and_handle_acp70_sdw_wake_irq(adata);
+ wake_irq_flag = check_and_handle_acp70_sdw_wake_irq(adata);
if (ext_intr_stat & BIT(PDM_DMA_STAT)) {
ps_pdm_data = dev_get_drvdata(&adata->pdm_dev->dev);
@@ -245,7 +246,7 @@ static irqreturn_t acp63_irq_handler(int irq, void *dev_id)
if (sdw_dma_irq_flag)
return IRQ_WAKE_THREAD;
- if (irq_flag)
+ if (irq_flag | wake_irq_flag)
return IRQ_HANDLED;
else
return IRQ_NONE;
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 40bb7a1..20f99cb 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -776,10 +776,9 @@
tristate
config SND_SOC_CS_AMP_LIB_TEST
- tristate "KUnit test for Cirrus Logic cs-amp-lib"
- depends on KUNIT
+ tristate "KUnit test for Cirrus Logic cs-amp-lib" if !KUNIT_ALL_TESTS
+ depends on SND_SOC_CS_AMP_LIB && KUNIT
default KUNIT_ALL_TESTS
- select SND_SOC_CS_AMP_LIB
help
This builds KUnit tests for the Cirrus Logic common
amplifier library.
diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index 20e6ab6..6165ac1 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -654,6 +654,10 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
reinit_completion(&priv->type_detect);
+ regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK);
+
cs42l43_start_hs_bias(priv, true);
regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
CS42L43_HSDET_MODE_MASK, 0x3 << CS42L43_HSDET_MODE_SHIFT);
@@ -665,6 +669,9 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
CS42L43_HSDET_MODE_MASK, 0x2 << CS42L43_HSDET_MODE_SHIFT);
cs42l43_stop_hs_bias(priv);
+ regmap_update_bits(cs42l43->regmap, CS42L43_STEREO_MIC_CLAMP_CTRL,
+ CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK, 0);
+
if (!time_left)
return -ETIMEDOUT;
diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c
index 3686d46..45e000f 100644
--- a/sound/soc/fsl/imx-card.c
+++ b/sound/soc/fsl/imx-card.c
@@ -544,7 +544,7 @@ static int imx_card_parse_of(struct imx_card_data *data)
if (!card->dai_link)
return -ENOMEM;
- data->link_data = devm_kcalloc(dev, num_links, sizeof(*link), GFP_KERNEL);
+ data->link_data = devm_kcalloc(dev, num_links, sizeof(*link_data), GFP_KERNEL);
if (!data->link_data)
return -ENOMEM;
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index a1ccc30..3ae2a21 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1174,9 +1174,9 @@ void graph_util_parse_link_direction(struct device_node *np,
bool is_playback_only = of_property_read_bool(np, "playback-only");
bool is_capture_only = of_property_read_bool(np, "capture-only");
- if (is_playback_only)
+ if (playback_only)
*playback_only = is_playback_only;
- if (is_capture_only)
+ if (capture_only)
*capture_only = is_capture_only;
}
EXPORT_SYMBOL_GPL(graph_util_parse_link_direction);
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 6446cda..0f3b8f4 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -576,6 +576,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
BYT_RT5640_SSP0_AIF2 |
BYT_RT5640_MCLK_EN),
},
+ { /* Acer Aspire SW3-013 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW3-013"),
+ },
+ .driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+ BYT_RT5640_JD_SRC_JD2_IN4N |
+ BYT_RT5640_OVCD_TH_2000UA |
+ BYT_RT5640_OVCD_SF_0P75 |
+ BYT_RT5640_DIFF_MIC |
+ BYT_RT5640_SSP0_AIF1 |
+ BYT_RT5640_MCLK_EN),
+ },
{
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c
index 5993819..008a20a 100644
--- a/sound/soc/intel/catpt/dsp.c
+++ b/sound/soc/intel/catpt/dsp.c
@@ -156,7 +156,7 @@ static void catpt_dsp_set_srampge(struct catpt_dev *cdev, struct resource *sram,
{
unsigned long old;
u32 off = sram->start;
- u32 b = __ffs(mask);
+ unsigned long b = __ffs(mask);
old = catpt_readl_pci(cdev, VDRTCTL0) & mask;
dev_dbg(cdev->dev, "SRAMPGE [0x%08lx] 0x%08lx -> 0x%08lx",
diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
index 6603d8de..c599eb43 100644
--- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c
@@ -431,7 +431,8 @@ static const struct snd_soc_acpi_link_adr ptl_cs42l43_l3[] = {
.mask = BIT(3),
.num_adr = ARRAY_SIZE(cs42l43_3_adr),
.adr_d = cs42l43_3_adr,
- }
+ },
+ {}
};
static const struct snd_soc_acpi_link_adr ptl_rt722_only[] = {
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 3033e2d..90e3675 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -228,6 +228,7 @@
config SND_SOC_MT8188_MT6359
tristate "ASoC Audio driver for MT8188 with MT6359 and I2S codecs"
depends on SND_SOC_MT8188 && MTK_PMIC_WRAP
+ depends on SND_SOC_MT6359_ACCDET || !SND_SOC_MT6359_ACCDET
depends on I2C
select SND_SOC_MT6359
select SND_SOC_HDMI_CODEC
diff --git a/sound/soc/renesas/rz-ssi.c b/sound/soc/renesas/rz-ssi.c
index 3a0af4c..0f7458a 100644
--- a/sound/soc/renesas/rz-ssi.c
+++ b/sound/soc/renesas/rz-ssi.c
@@ -1244,7 +1244,7 @@ static int rz_ssi_runtime_resume(struct device *dev)
static const struct dev_pm_ops rz_ssi_pm_ops = {
RUNTIME_PM_OPS(rz_ssi_runtime_suspend, rz_ssi_runtime_resume, NULL)
- SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+ NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
};
static struct platform_driver rz_ssi_driver = {
diff --git a/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c b/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
index 246e5c2..c7e55f4 100644
--- a/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
+++ b/sound/soc/sdw_utils/soc_sdw_bridge_cs35l56.c
@@ -60,6 +60,10 @@ static int asoc_sdw_bridge_cs35l56_asp_init(struct snd_soc_pcm_runtime *rtd)
/* 4 x 16-bit sample slots and FSYNC=48000, BCLK=3.072 MHz */
for_each_rtd_codec_dais(rtd, i, codec_dai) {
+ ret = asoc_sdw_cs35l56_volume_limit(card, codec_dai->component->name_prefix);
+ if (ret)
+ return ret;
+
ret = snd_soc_dai_set_tdm_slot(codec_dai, tx_mask, rx_mask, 4, 16);
if (ret < 0)
return ret;
diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c
index 668c9d2..b415d45 100644
--- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c
+++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c
@@ -20,6 +20,8 @@
#include <sound/soc-dapm.h>
#include <sound/soc_sdw_utils.h>
+#define CS42L43_SPK_VOLUME_0DB 128 /* 0dB Max */
+
static const struct snd_soc_dapm_route cs42l43_hs_map[] = {
{ "Headphone", NULL, "cs42l43 AMP3_OUT" },
{ "Headphone", NULL, "cs42l43 AMP4_OUT" },
@@ -117,6 +119,14 @@ int asoc_sdw_cs42l43_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_so
return -ENOMEM;
}
+ ret = snd_soc_limit_volume(card, "cs42l43 Speaker Digital Volume",
+ CS42L43_SPK_VOLUME_0DB);
+ if (ret)
+ dev_err(card->dev, "cs42l43 speaker volume limit failed: %d\n", ret);
+ else
+ dev_info(card->dev, "Setting CS42L43 Speaker volume limit to %d\n",
+ CS42L43_SPK_VOLUME_0DB);
+
ret = snd_soc_dapm_add_routes(&card->dapm, cs42l43_spk_map,
ARRAY_SIZE(cs42l43_spk_map));
if (ret)
diff --git a/sound/soc/sdw_utils/soc_sdw_cs_amp.c b/sound/soc/sdw_utils/soc_sdw_cs_amp.c
index 4b6181cf..35b550b 100644
--- a/sound/soc/sdw_utils/soc_sdw_cs_amp.c
+++ b/sound/soc/sdw_utils/soc_sdw_cs_amp.c
@@ -16,6 +16,25 @@
#define CODEC_NAME_SIZE 8
#define CS_AMP_CHANNELS_PER_AMP 4
+#define CS35L56_SPK_VOLUME_0DB 400 /* 0dB Max */
+
+int asoc_sdw_cs35l56_volume_limit(struct snd_soc_card *card, const char *name_prefix)
+{
+ char *volume_ctl_name;
+ int ret;
+
+ volume_ctl_name = kasprintf(GFP_KERNEL, "%s Speaker Volume", name_prefix);
+ if (!volume_ctl_name)
+ return -ENOMEM;
+
+ ret = snd_soc_limit_volume(card, volume_ctl_name, CS35L56_SPK_VOLUME_0DB);
+ if (ret)
+ dev_err(card->dev, "%s limit set failed: %d\n", volume_ctl_name, ret);
+
+ kfree(volume_ctl_name);
+ return ret;
+}
+EXPORT_SYMBOL_NS(asoc_sdw_cs35l56_volume_limit, "SND_SOC_SDW_UTILS");
int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *dai)
{
@@ -40,6 +59,11 @@ int asoc_sdw_cs_spk_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai
snprintf(widget_name, sizeof(widget_name), "%s SPK",
codec_dai->component->name_prefix);
+
+ ret = asoc_sdw_cs35l56_volume_limit(card, codec_dai->component->name_prefix);
+ if (ret)
+ return ret;
+
ret = snd_soc_dapm_add_routes(&card->dapm, &route, 1);
if (ret)
return ret;
diff --git a/sound/soc/sdw_utils/soc_sdw_rt_dmic.c b/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
index 46d917a..97be110 100644
--- a/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
+++ b/sound/soc/sdw_utils/soc_sdw_rt_dmic.c
@@ -29,6 +29,8 @@ int asoc_sdw_rt_dmic_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_da
mic_name = devm_kasprintf(card->dev, GFP_KERNEL, "rt715-sdca");
else
mic_name = devm_kasprintf(card->dev, GFP_KERNEL, "%s", component->name_prefix);
+ if (!mic_name)
+ return -ENOMEM;
card->components = devm_kasprintf(card->dev, GFP_KERNEL,
"%s mic:%s", card->components,
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 4308a6c..4383519 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1584,10 +1584,13 @@ int dpcm_add_paths(struct snd_soc_pcm_runtime *fe, int stream,
/*
* Filter for systems with 'component_chaining' enabled.
* This helps to avoid unnecessary re-configuration of an
- * already active BE on such systems.
+ * already active BE on such systems and ensures the BE DAI
+ * widget is powered ON after hw_params() BE DAI callback.
*/
if (fe->card->component_chaining &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_NEW) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_OPEN) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_CLOSE))
continue;
diff --git a/sound/soc/sof/intel/hda-bus.c b/sound/soc/sof/intel/hda-bus.c
index b1be030..6492e1c 100644
--- a/sound/soc/sof/intel/hda-bus.c
+++ b/sound/soc/sof/intel/hda-bus.c
@@ -76,7 +76,7 @@ void sof_hda_bus_init(struct snd_sof_dev *sdev, struct device *dev)
snd_hdac_ext_bus_init(bus, dev, &bus_core_ops, sof_hda_ext_ops);
- if (chip && chip->hw_ip_version == SOF_INTEL_ACE_2_0)
+ if (chip && chip->hw_ip_version >= SOF_INTEL_ACE_2_0)
bus->use_pio_for_commands = true;
#else
snd_hdac_ext_bus_init(bus, dev, NULL, NULL);
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index b34e5fdf..6a3932d 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1049,7 +1049,21 @@ static void hda_generic_machine_select(struct snd_sof_dev *sdev,
if (!*mach && codec_num <= 2) {
bool tplg_fixup = false;
- hda_mach = snd_soc_acpi_intel_hda_machines;
+ /*
+ * make a local copy of the match array since we might
+ * be modifying it
+ */
+ hda_mach = devm_kmemdup_array(sdev->dev,
+ snd_soc_acpi_intel_hda_machines,
+ 2, /* we have one entry + sentinel in the array */
+ sizeof(snd_soc_acpi_intel_hda_machines[0]),
+ GFP_KERNEL);
+ if (!hda_mach) {
+ dev_err(bus->dev,
+ "%s: failed to duplicate the HDA match table\n",
+ __func__);
+ return;
+ }
dev_info(bus->dev, "using HDA machine driver %s now\n",
hda_mach->drv_name);
diff --git a/sound/soc/sof/ipc4-control.c b/sound/soc/sof/ipc4-control.c
index 576f407..976a479 100644
--- a/sound/soc/sof/ipc4-control.c
+++ b/sound/soc/sof/ipc4-control.c
@@ -531,6 +531,14 @@ static int sof_ipc4_bytes_ext_put(struct snd_sof_control *scontrol,
return -EINVAL;
}
+ /* Check header id */
+ if (header.numid != SOF_CTRL_CMD_BINARY) {
+ dev_err_ratelimited(scomp->dev,
+ "Incorrect numid for bytes put %d\n",
+ header.numid);
+ return -EINVAL;
+ }
+
/* Verify the ABI header first */
if (copy_from_user(&abi_hdr, tlvd->tlv, sizeof(abi_hdr)))
return -EFAULT;
@@ -613,7 +621,8 @@ static int _sof_ipc4_bytes_ext_get(struct snd_sof_control *scontrol,
if (data_size > size)
return -ENOSPC;
- header.numid = scontrol->comp_id;
+ /* Set header id and length */
+ header.numid = SOF_CTRL_CMD_BINARY;
header.length = data_size;
if (copy_to_user(tlvd, &header, sizeof(struct snd_ctl_tlv)))
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 1a28418..c09b424a 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -798,7 +798,8 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm
spcm->stream[stream].private = stream_priv;
- if (!support_info)
+ /* Delay reporting is only supported on playback */
+ if (!support_info || stream == SNDRV_PCM_STREAM_CAPTURE)
continue;
time_info = kzalloc(sizeof(*time_info), GFP_KERNEL);
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index dc9cb83..14aa8ec 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -1063,7 +1063,7 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp,
struct snd_sof_dai *dai)
{
struct snd_soc_card *card = scomp->card;
- struct snd_soc_pcm_runtime *rtd;
+ struct snd_soc_pcm_runtime *rtd, *full, *partial;
struct snd_soc_dai *cpu_dai;
int stream;
int i;
@@ -1080,12 +1080,22 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp,
else
goto end;
+ full = NULL;
+ partial = NULL;
list_for_each_entry(rtd, &card->rtd_list, list) {
/* does stream match DAI link ? */
- if (!rtd->dai_link->stream_name ||
- !strstr(rtd->dai_link->stream_name, w->sname))
- continue;
+ if (rtd->dai_link->stream_name) {
+ if (!strcmp(rtd->dai_link->stream_name, w->sname)) {
+ full = rtd;
+ break;
+ } else if (strstr(rtd->dai_link->stream_name, w->sname)) {
+ partial = rtd;
+ }
+ }
+ }
+ rtd = full ? full : partial;
+ if (rtd) {
for_each_rtd_cpu_dais(rtd, i, cpu_dai) {
/*
* Please create DAI widget in the right order
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index e8c1abf..bf5299b 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -409,11 +409,11 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
unsigned int rate)
{
struct platform_device *pdev = sai->pdev;
- unsigned int sai_ck_rate, sai_ck_max_rate, sai_curr_rate, sai_new_rate;
+ unsigned int sai_ck_rate, sai_ck_max_rate, sai_ck_min_rate, sai_curr_rate, sai_new_rate;
int div, ret;
/*
- * Set maximum expected kernel clock frequency
+ * Set minimum and maximum expected kernel clock frequency
* - mclk on or spdif:
* f_sai_ck = MCKDIV * mclk-fs * fs
* Here typical 256 ratio is assumed for mclk-fs
@@ -423,13 +423,16 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
* Set constraint MCKDIV * FRL <= 256, to ensure MCKDIV is in available range
* f_sai_ck = sai_ck_max_rate * pow_of_two(FRL) / 256
*/
+ sai_ck_min_rate = rate * 256;
if (!(rate % SAI_RATE_11K))
sai_ck_max_rate = SAI_MAX_SAMPLE_RATE_11K * 256;
else
sai_ck_max_rate = SAI_MAX_SAMPLE_RATE_8K * 256;
- if (!sai->sai_mclk && !STM_SAI_PROTOCOL_IS_SPDIF(sai))
+ if (!sai->sai_mclk && !STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+ sai_ck_min_rate = rate * sai->fs_length;
sai_ck_max_rate /= DIV_ROUND_CLOSEST(256, roundup_pow_of_two(sai->fs_length));
+ }
/*
* Request exclusivity, as the clock is shared by SAI sub-blocks and by
@@ -444,7 +447,10 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
* return immediately.
*/
sai_curr_rate = clk_get_rate(sai->sai_ck);
- if (stm32_sai_rate_accurate(sai_ck_max_rate, sai_curr_rate))
+ dev_dbg(&pdev->dev, "kernel clock rate: min [%u], max [%u], current [%u]",
+ sai_ck_min_rate, sai_ck_max_rate, sai_curr_rate);
+ if (stm32_sai_rate_accurate(sai_ck_max_rate, sai_curr_rate) &&
+ sai_curr_rate >= sai_ck_min_rate)
return 0;
/*
@@ -472,7 +478,7 @@ static int stm32_sai_set_parent_rate(struct stm32_sai_sub_data *sai,
/* Try a lower frequency */
div++;
sai_ck_rate = sai_ck_max_rate / div;
- } while (sai_ck_rate > rate);
+ } while (sai_ck_rate >= sai_ck_min_rate);
/* No accurate rate found */
dev_err(&pdev->dev, "Failed to find an accurate rate");
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index a29f28e..f36ec98 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -926,6 +926,8 @@ static int endpoint_set_interface(struct snd_usb_audio *chip,
{
int altset = set ? ep->altsetting : 0;
int err;
+ int retries = 0;
+ const int max_retries = 5;
if (ep->iface_ref->altset == altset)
return 0;
@@ -935,8 +937,13 @@ static int endpoint_set_interface(struct snd_usb_audio *chip,
usb_audio_dbg(chip, "Setting usb interface %d:%d for EP 0x%x\n",
ep->iface, altset, ep->ep_num);
+retry:
err = usb_set_interface(chip->dev, ep->iface, altset);
if (err < 0) {
+ if (err == -EPROTO && ++retries <= max_retries) {
+ msleep(5 * (1 << (retries - 1)));
+ goto retry;
+ }
usb_audio_err_ratelimited(
chip, "%d:%d: usb_set_interface failed (%d)\n",
ep->iface, altset, err);
diff --git a/sound/usb/format.c b/sound/usb/format.c
index 9d32b21..0ba4641 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -260,7 +260,8 @@ static int parse_audio_format_rates_v1(struct snd_usb_audio *chip, struct audiof
}
/* Jabra Evolve 65 headset */
- if (chip->usb_id == USB_ID(0x0b0e, 0x030b)) {
+ if (chip->usb_id == USB_ID(0x0b0e, 0x030b) ||
+ chip->usb_id == USB_ID(0x0b0e, 0x030c)) {
/* only 48kHz for playback while keeping 16kHz for capture */
if (fp->nr_rates != 1)
return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000);
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index dcdd7e9..cfed000 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1885,10 +1885,18 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
}
port_info = find_port_info(umidi, number);
- name_format = port_info ? port_info->name :
- (jack_name != default_jack_name ? "%s %s" : "%s %s %d");
- snprintf(substream->name, sizeof(substream->name),
- name_format, umidi->card->shortname, jack_name, number + 1);
+ if (port_info || jack_name == default_jack_name ||
+ strncmp(umidi->card->shortname, jack_name, strlen(umidi->card->shortname)) != 0) {
+ name_format = port_info ? port_info->name :
+ (jack_name != default_jack_name ? "%s %s" : "%s %s %d");
+ snprintf(substream->name, sizeof(substream->name),
+ name_format, umidi->card->shortname, jack_name, number + 1);
+ } else {
+ /* The manufacturer included the iProduct name in the jack
+ * name, do not use both
+ */
+ strscpy(substream->name, jack_name);
+ }
*rsubstream = substream;
}
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 9112313..dbbc9eb 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2242,6 +2242,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
QUIRK_FLAG_CTL_MSG_DELAY_1M),
DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */
QUIRK_FLAG_GET_SAMPLE_RATE),
+ DEVICE_FLG(0x0c45, 0x636b, /* Microdia JP001 USB Camera */
+ QUIRK_FLAG_GET_SAMPLE_RATE),
DEVICE_FLG(0x0d8c, 0x0014, /* USB Audio Device */
QUIRK_FLAG_CTL_MSG_DELAY_1M),
DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
@@ -2250,6 +2252,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
QUIRK_FLAG_FIXED_RATE),
DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */
QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+ DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */
+ QUIRK_FLAG_GET_SAMPLE_RATE),
DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16),
DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index caedb3e..f5dd84e 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 04ba035..b9ce3aa 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -24,6 +24,7 @@
#include <sys/poll.h>
#include <sys/utsname.h>
+#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
@@ -677,6 +678,88 @@ static void kvp_process_ipconfig_file(char *cmd,
pclose(file);
}
+static bool kvp_verify_ip_address(const void *address_string)
+{
+ char verify_buf[sizeof(struct in6_addr)];
+
+ if (inet_pton(AF_INET, address_string, verify_buf) == 1)
+ return true;
+ if (inet_pton(AF_INET6, address_string, verify_buf) == 1)
+ return true;
+ return false;
+}
+
+static void kvp_extract_routes(const char *line, void **output, size_t *remaining)
+{
+ static const char needle[] = "via ";
+ const char *match, *haystack = line;
+
+ while ((match = strstr(haystack, needle))) {
+ const char *address, *next_char;
+
+ /* Address starts after needle. */
+ address = match + strlen(needle);
+
+ /* The char following address is a space or end of line. */
+ next_char = strpbrk(address, " \t\\");
+ if (!next_char)
+ next_char = address + strlen(address) + 1;
+
+ /* Enough room for address and semicolon. */
+ if (*remaining >= (next_char - address) + 1) {
+ memcpy(*output, address, next_char - address);
+ /* Terminate string for verification. */
+ memcpy(*output + (next_char - address), "", 1);
+ if (kvp_verify_ip_address(*output)) {
+ /* Advance output buffer. */
+ *output += next_char - address;
+ *remaining -= next_char - address;
+
+ /* Each address needs a trailing semicolon. */
+ memcpy(*output, ";", 1);
+ *output += 1;
+ *remaining -= 1;
+ }
+ }
+ haystack = next_char;
+ }
+}
+
+static void kvp_get_gateway(void *buffer, size_t buffer_len)
+{
+ static const char needle[] = "default ";
+ FILE *f;
+ void *output = buffer;
+ char *line = NULL;
+ size_t alloc_size = 0, remaining = buffer_len - 1;
+ ssize_t num_chars;
+
+ /* Show route information in a single line, for each address family */
+ f = popen("ip --oneline -4 route show;ip --oneline -6 route show", "r");
+ if (!f) {
+ /* Convert buffer into C-String. */
+ memcpy(output, "", 1);
+ return;
+ }
+ while ((num_chars = getline(&line, &alloc_size, f)) > 0) {
+ /* Skip short lines. */
+ if (num_chars <= strlen(needle))
+ continue;
+ /* Skip lines without default route. */
+ if (memcmp(line, needle, strlen(needle)))
+ continue;
+ /* Remove trailing newline to simplify further parsing. */
+ if (line[num_chars - 1] == '\n')
+ line[num_chars - 1] = '\0';
+ /* Search routes after match. */
+ kvp_extract_routes(line + strlen(needle), &output, &remaining);
+ }
+ /* Convert buffer into C-String. */
+ memcpy(output, "", 1);
+ free(line);
+ pclose(f);
+}
+
static void kvp_get_ipconfig_info(char *if_name,
struct hv_kvp_ipaddr_value *buffer)
{
@@ -685,30 +768,7 @@ static void kvp_get_ipconfig_info(char *if_name,
char *p;
FILE *file;
- /*
- * Get the address of default gateway (ipv4).
- */
- sprintf(cmd, "%s %s", "ip route show dev", if_name);
- strcat(cmd, " | awk '/default/ {print $3 }'");
-
- /*
- * Execute the command to gather gateway info.
- */
- kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way,
- (MAX_GATEWAY_SIZE * 2), INET_ADDRSTRLEN, 0);
-
- /*
- * Get the address of default gateway (ipv6).
- */
- sprintf(cmd, "%s %s", "ip -f inet6 route show dev", if_name);
- strcat(cmd, " | awk '/default/ {print $3 }'");
-
- /*
- * Execute the command to gather gateway info (ipv6).
- */
- kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way,
- (MAX_GATEWAY_SIZE * 2), INET6_ADDRSTRLEN, 1);
-
+ kvp_get_gateway(buffer->gate_way, sizeof(buffer->gate_way));
/*
* Gather the DNS state.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 28705ae..fd40472 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4968,6 +4968,9 @@ union bpf_attr {
* the netns switch takes place from ingress to ingress without
* going through the CPU's backlog queue.
*
+ * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * the netns switch.
+ *
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types at the
* ingress hook and for veth and netkit target device types. The
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index ffcfd77..7fbb50b 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -42,6 +42,7 @@
TEST_ARGS := $(if $(V),-v)
INCLUDES = \
+-I$(OUTPUT)arch/$(SRCARCH)/include/generated/uapi \
-I$(srctree)/tools/lib/perf/include \
-I$(srctree)/tools/lib/ \
-I$(srctree)/tools/include \
@@ -99,7 +100,16 @@
$(call QUIET_CLEAN, libapi)
$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
-$(LIBPERF_IN): FORCE
+uapi-asm := $(OUTPUT)arch/$(SRCARCH)/include/generated/uapi/asm
+ifeq ($(SRCARCH),arm64)
+ syscall-y := $(uapi-asm)/unistd_64.h
+endif
+uapi-asm-generic:
+ $(if $(syscall-y),\
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-headers obj=$(uapi-asm) \
+ generic=include/uapi/asm-generic $(syscall-y),)
+
+$(LIBPERF_IN): uapi-asm-generic FORCE
$(Q)$(MAKE) $(build)=libperf
$(LIBPERF_A): $(LIBPERF_IN)
@@ -120,7 +130,7 @@
clean: $(LIBAPI)-clean
$(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \
*.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd tests/*.o LIBPERF-CFLAGS $(LIBPERF_PC) \
- $(TESTS_STATIC) $(TESTS_SHARED)
+ $(TESTS_STATIC) $(TESTS_SHARED) $(syscall-y)
TESTS_IN = tests-in.o
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index ce32cb3..c4da340 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -364,7 +364,7 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
"Invalid attribute (binary %s)", policy->name);
return -1;
case YNL_PT_NUL_STR:
- if ((!policy->len || len <= policy->len) && !data[len - 1])
+ if (len && (!policy->len || len <= policy->len) && !data[len - 1])
break;
yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
"Invalid attribute (string %s)", policy->name);
diff --git a/tools/net/ynl/pyynl/ethtool.py b/tools/net/ynl/pyynl/ethtool.py
index af7fddd..cab6b57 100755
--- a/tools/net/ynl/pyynl/ethtool.py
+++ b/tools/net/ynl/pyynl/ethtool.py
@@ -338,16 +338,24 @@
print('Capabilities:')
[print(f'\t{v}') for v in bits_to_dict(tsinfo['timestamping'])]
- print(f'PTP Hardware Clock: {tsinfo["phc-index"]}')
+ print(f'PTP Hardware Clock: {tsinfo.get("phc-index", "none")}')
- print('Hardware Transmit Timestamp Modes:')
- [print(f'\t{v}') for v in bits_to_dict(tsinfo['tx-types'])]
+ if 'tx-types' in tsinfo:
+ print('Hardware Transmit Timestamp Modes:')
+ [print(f'\t{v}') for v in bits_to_dict(tsinfo['tx-types'])]
+ else:
+ print('Hardware Transmit Timestamp Modes: none')
- print('Hardware Receive Filter Modes:')
- [print(f'\t{v}') for v in bits_to_dict(tsinfo['rx-filters'])]
+ if 'rx-filters' in tsinfo:
+ print('Hardware Receive Filter Modes:')
+ [print(f'\t{v}') for v in bits_to_dict(tsinfo['rx-filters'])]
+ else:
+ print('Hardware Receive Filter Modes: none')
- print('Statistics:')
- [print(f'\t{k}: {v}') for k, v in tsinfo['stats'].items()]
+ if 'stats' in tsinfo and tsinfo['stats']:
+ print('Statistics:')
+ [print(f'\t{k}: {v}') for k, v in tsinfo['stats'].items()]
+
return
print(f'Settings for {args.device}:')
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index 30c0a34..a7f08ed 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -1143,10 +1143,9 @@
self.pure_nested_structs[nested].request = True
if attr in rs_members['reply']:
self.pure_nested_structs[nested].reply = True
-
- if spec.is_multi_val():
- child = self.pure_nested_structs.get(nested)
- child.in_multi_val = True
+ if spec.is_multi_val():
+ child = self.pure_nested_structs.get(nested)
+ child.in_multi_val = True
self._sort_pure_types()
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 3ce7b54..687c5ea 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -189,6 +189,15 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
op2 = ins.opcode.bytes[1];
op3 = ins.opcode.bytes[2];
+ /*
+ * XXX hack, decoder is buggered and thinks 0xea is 7 bytes long.
+ */
+ if (op1 == 0xea) {
+ insn->len = 1;
+ insn->type = INSN_BUG;
+ return 0;
+ }
+
if (ins.rex_prefix.nbytes) {
rex = ins.rex_prefix.bytes[0];
rex_w = X86_REX_W(rex) >> 3;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 3a41106..b21b12e 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -227,6 +227,7 @@ static bool is_rust_noreturn(const struct symbol *func)
str_ends_with(func->name, "_4core9panicking19assert_failed_inner") ||
str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference") ||
str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") ||
+ str_ends_with(func->name, "_7___rustc17rust_begin_unwind") ||
strstr(func->name, "_4core9panicking13assert_failed") ||
strstr(func->name, "_4core9panicking11panic_const24panic_const_") ||
(strstr(func->name, "_4core5slice5index24slice_") &&
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index eea95c6..b7769a2 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -29,6 +29,7 @@
$(call detected_var,SRCARCH)
CFLAGS += -I$(OUTPUT)arch/$(SRCARCH)/include/generated
+CFLAGS += -I$(OUTPUT)libperf/arch/$(SRCARCH)/include/generated/uapi
# Additional ARCH settings for ppc
ifeq ($(SRCARCH),powerpc)
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
index 2c720e3..fdc7170 100644
--- a/tools/sched_ext/scx_flatcg.bpf.c
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -950,5 +950,5 @@ SCX_OPS_DEFINE(flatcg_ops,
.cgroup_move = (void *)fcg_cgroup_move,
.init = (void *)fcg_init,
.exit = (void *)fcg_exit,
- .flags = SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING,
+ .flags = SCX_OPS_ENQ_EXITING,
.name = "flatcg");
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index f2957a3..bf9caa9 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1780,7 +1780,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
if (rc)
return rc;
- rc = devm_cxl_setup_fwctl(cxlmd);
+ rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
if (rc)
dev_dbg(dev, "No CXL FWCTL setup\n");
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index cdd9782..422e186 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -20,6 +20,7 @@
CONFIG_PCI=y
CONFIG_USB4=y
+CONFIG_I2C=y
CONFIG_NET=y
CONFIG_MCTP=y
@@ -43,6 +44,8 @@
CONFIG_AUDIT=y
+CONFIG_PRIME_NUMBERS=y
+
CONFIG_SECURITY=y
CONFIG_SECURITY_APPARMOR=y
CONFIG_SECURITY_LANDLOCK=y
@@ -51,3 +54,4 @@
CONFIG_SND=y
CONFIG_SND_SOC=y
CONFIG_SND_SOC_TOPOLOGY_BUILD=y
+CONFIG_SND_SOC_CS35L56_I2C=y
diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c
index 6750308..01e836f 100644
--- a/tools/testing/memblock/tests/basic_api.c
+++ b/tools/testing/memblock/tests/basic_api.c
@@ -2434,6 +2434,107 @@ static int memblock_overlaps_region_checks(void)
return 0;
}
+#ifdef CONFIG_NUMA
+static int memblock_set_node_check(void)
+{
+ unsigned long i, max_reserved;
+ struct memblock_region *rgn;
+ void *orig_region;
+
+ PREFIX_PUSH();
+
+ reset_memblock_regions();
+ memblock_allow_resize();
+
+ dummy_physical_memory_init();
+ memblock_add(dummy_physical_memory_base(), MEM_SIZE);
+ orig_region = memblock.reserved.regions;
+
+ /* Equally Split range to node 0 and 1*/
+ memblock_set_node(memblock_start_of_DRAM(),
+ memblock_phys_mem_size() / 2, &memblock.memory, 0);
+ memblock_set_node(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2,
+ memblock_phys_mem_size() / 2, &memblock.memory, 1);
+
+ ASSERT_EQ(memblock.memory.cnt, 2);
+ rgn = &memblock.memory.regions[0];
+ ASSERT_EQ(rgn->base, memblock_start_of_DRAM());
+ ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+ ASSERT_EQ(memblock_get_region_node(rgn), 0);
+ rgn = &memblock.memory.regions[1];
+ ASSERT_EQ(rgn->base, memblock_start_of_DRAM() + memblock_phys_mem_size() / 2);
+ ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+ ASSERT_EQ(memblock_get_region_node(rgn), 1);
+
+ /* Reserve 126 regions with the last one across node boundary */
+ for (i = 0; i < 125; i++)
+ memblock_reserve(memblock_start_of_DRAM() + SZ_16 * i, SZ_8);
+
+ memblock_reserve(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2 - SZ_8,
+ SZ_16);
+
+ /*
+ * Commit 61167ad5fecd ("mm: pass nid to reserve_bootmem_region()")
+ * do following process to set nid to each memblock.reserved region.
+ * But it may miss some region if memblock_set_node() double the
+ * array.
+ *
+ * By checking 'max', we make sure all region nid is set properly.
+ */
+repeat:
+ max_reserved = memblock.reserved.max;
+ for_each_mem_region(rgn) {
+ int nid = memblock_get_region_node(rgn);
+
+ memblock_set_node(rgn->base, rgn->size, &memblock.reserved, nid);
+ }
+ if (max_reserved != memblock.reserved.max)
+ goto repeat;
+
+ /* Confirm each region has valid node set */
+ for_each_reserved_mem_region(rgn) {
+ ASSERT_TRUE(numa_valid_node(memblock_get_region_node(rgn)));
+ if (rgn == (memblock.reserved.regions + memblock.reserved.cnt - 1))
+ ASSERT_EQ(1, memblock_get_region_node(rgn));
+ else
+ ASSERT_EQ(0, memblock_get_region_node(rgn));
+ }
+
+ dummy_physical_memory_cleanup();
+
+ /*
+ * The current reserved.regions is occupying a range of memory that
+ * allocated from dummy_physical_memory_init(). After free the memory,
+ * we must not use it. So restore the origin memory region to make sure
+ * the tests can run as normal and not affected by the double array.
+ */
+ memblock.reserved.regions = orig_region;
+ memblock.reserved.cnt = INIT_MEMBLOCK_RESERVED_REGIONS;
+
+ test_pass_pop();
+
+ return 0;
+}
+
+static int memblock_set_node_checks(void)
+{
+ prefix_reset();
+ prefix_push("memblock_set_node");
+ test_print("Running memblock_set_node tests...\n");
+
+ memblock_set_node_check();
+
+ prefix_pop();
+
+ return 0;
+}
+#else
+static int memblock_set_node_checks(void)
+{
+ return 0;
+}
+#endif
+
int memblock_basic_checks(void)
{
memblock_initialization_check();
@@ -2444,6 +2545,7 @@ int memblock_basic_checks(void)
memblock_bottom_up_checks();
memblock_trim_memory_checks();
memblock_overlaps_region_checks();
+ memblock_set_node_checks();
return 0;
}
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c77c8c8..80fb84f 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -121,6 +121,7 @@
TARGETS += vDSO
TARGETS += mm
TARGETS += x86
+TARGETS += x86/bugs
TARGETS += zram
#Please keep the TARGETS list alphabetically sorted
# Run "make quicktest=1 run_tests" or
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 09f6487..5fea320 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -6,6 +6,7 @@
#include "for_each_array_map_elem.skel.h"
#include "for_each_map_elem_write_key.skel.h"
#include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
static unsigned int duration;
@@ -203,6 +204,40 @@ static void test_multi_maps(void)
for_each_multi_maps__destroy(skel);
}
+static void test_hash_modify(void)
+{
+ struct for_each_hash_modify *skel;
+ int max_entries, i, err;
+ __u64 key, val;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1
+ );
+
+ skel = for_each_hash_modify__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+ return;
+
+ max_entries = bpf_map__max_entries(skel->maps.hashmap);
+ for (i = 0; i < max_entries; i++) {
+ key = i;
+ val = i;
+ err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+ &val, sizeof(val), BPF_ANY);
+ if (!ASSERT_OK(err, "map_update"))
+ goto out;
+ }
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+ ASSERT_OK(topts.retval, "retval");
+
+out:
+ for_each_hash_modify__destroy(skel);
+}
+
void test_for_each(void)
{
if (test__start_subtest("hash_map"))
@@ -213,4 +248,6 @@ void test_for_each(void)
test_write_map_key();
if (test__start_subtest("multi_maps"))
test_multi_maps();
+ if (test__start_subtest("hash_modify"))
+ test_hash_modify();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 2d07963..0a99fd4 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -68,7 +68,6 @@ static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
goto close_cli;
err = disconnect(cli);
- ASSERT_OK(err, "disconnect");
close_cli:
close(cli);
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 13a2e22..863df7c 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -221,7 +221,7 @@
#define CAN_USE_GOTOL
#endif
-#if _clang_major__ >= 18
+#if __clang_major__ >= 18
#define CAN_USE_BPF_ST
#endif
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_modify.c b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
new file mode 100644
index 0000000..8230716
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Intel Corporation */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 128);
+ __type(key, __u64);
+ __type(value, __u64);
+} hashmap SEC(".maps");
+
+static int cb(struct bpf_map *map, __u64 *key, __u64 *val, void *arg)
+{
+ bpf_map_delete_elem(map, key);
+ bpf_map_update_elem(map, key, val, 0);
+ return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+ (void)skb;
+
+ bpf_for_each_map_elem(&hashmap, cb, NULL, 0);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
new file mode 120000
index 0000000..d16a65e
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
@@ -0,0 +1 @@
+run_net_forwarding_test.sh
\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 2bf14ac..9d48004 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -431,6 +431,22 @@ static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
return 0;
}
+static struct netdev_queue_id *create_queues(void)
+{
+ struct netdev_queue_id *queues;
+ size_t i = 0;
+
+ queues = calloc(num_queues, sizeof(*queues));
+ for (i = 0; i < num_queues; i++) {
+ queues[i]._present.type = 1;
+ queues[i]._present.id = 1;
+ queues[i].type = NETDEV_QUEUE_TYPE_RX;
+ queues[i].id = start_queue + i;
+ }
+
+ return queues;
+}
+
int do_server(struct memory_buffer *mem)
{
char ctrl_data[sizeof(int) * 20000];
@@ -448,7 +464,6 @@ int do_server(struct memory_buffer *mem)
char buffer[256];
int socket_fd;
int client_fd;
- size_t i = 0;
int ret;
ret = parse_address(server_ip, atoi(port), &server_sin);
@@ -471,16 +486,7 @@ int do_server(struct memory_buffer *mem)
sleep(1);
- queues = malloc(sizeof(*queues) * num_queues);
-
- for (i = 0; i < num_queues; i++) {
- queues[i]._present.type = 1;
- queues[i]._present.id = 1;
- queues[i].type = NETDEV_QUEUE_TYPE_RX;
- queues[i].id = start_queue + i;
- }
-
- if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
error(1, 0, "Failed to bind\n");
tmp_mem = malloc(mem->size);
@@ -545,7 +551,6 @@ int do_server(struct memory_buffer *mem)
goto cleanup;
}
- i++;
for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
if (cm->cmsg_level != SOL_SOCKET ||
(cm->cmsg_type != SCM_DEVMEM_DMABUF &&
@@ -630,10 +635,8 @@ int do_server(struct memory_buffer *mem)
void run_devmem_tests(void)
{
- struct netdev_queue_id *queues;
struct memory_buffer *mem;
struct ynl_sock *ys;
- size_t i = 0;
mem = provider->alloc(getpagesize() * NUM_PAGES);
@@ -641,38 +644,24 @@ void run_devmem_tests(void)
if (configure_rss())
error(1, 0, "rss error\n");
- queues = calloc(num_queues, sizeof(*queues));
-
if (configure_headersplit(1))
error(1, 0, "Failed to configure header split\n");
- if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (!bind_rx_queue(ifindex, mem->fd,
+ calloc(num_queues, sizeof(struct netdev_queue_id)),
+ num_queues, &ys))
error(1, 0, "Binding empty queues array should have failed\n");
- for (i = 0; i < num_queues; i++) {
- queues[i]._present.type = 1;
- queues[i]._present.id = 1;
- queues[i].type = NETDEV_QUEUE_TYPE_RX;
- queues[i].id = start_queue + i;
- }
-
if (configure_headersplit(0))
error(1, 0, "Failed to configure header split\n");
- if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (!bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
error(1, 0, "Configure dmabuf with header split off should have failed\n");
if (configure_headersplit(1))
error(1, 0, "Failed to configure header split\n");
- for (i = 0; i < num_queues; i++) {
- queues[i]._present.type = 1;
- queues[i]._present.id = 1;
- queues[i].type = NETDEV_QUEUE_TYPE_RX;
- queues[i].id = start_queue + i;
- }
-
- if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
error(1, 0, "Failed to bind\n");
/* Deactivating a bound queue should not be legal */
diff --git a/tools/testing/selftests/drivers/net/ocelot/psfp.sh b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
index bed748d..8972f42 100755
--- a/tools/testing/selftests/drivers/net/ocelot/psfp.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
@@ -266,18 +266,14 @@
"${base_time}" \
"${CYCLE_TIME_NS}" \
"${SHIFT_TIME_NS}" \
+ "${GATE_DURATION_NS}" \
"${NUM_PKTS}" \
"${STREAM_VID}" \
"${STREAM_PRIO}" \
"" \
"${isochron_dat}"
- # Count all received packets by looking at the non-zero RX timestamps
- received=$(isochron report \
- --input-file "${isochron_dat}" \
- --printf-format "%u\n" --printf-args "R" | \
- grep -w -v '0' | wc -l)
-
+ received=$(isochron_report_num_received "${isochron_dat}")
if [ "${received}" = "${expected}" ]; then
RET=0
else
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 4b68228..af8df23 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -9,11 +9,11 @@
from lib.py import bkg, cmd, wait_port_listen, rand_port
from lib.py import defer, ethtool, ip
-remote_ifname=""
no_sleep=False
def _test_v4(cfg) -> None:
- cfg.require_ipver("4")
+ if not cfg.addr_v["4"]:
+ return
cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
@@ -21,7 +21,8 @@
cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
def _test_v6(cfg) -> None:
- cfg.require_ipver("6")
+ if not cfg.addr_v["6"]:
+ return
cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"])
cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote)
@@ -57,7 +58,7 @@
def _set_xdp_generic_sb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
@@ -66,8 +67,8 @@
def _set_xdp_generic_mb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
- defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+ defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off")
@@ -76,7 +77,7 @@
def _set_xdp_native_sb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
@@ -93,8 +94,8 @@
def _set_xdp_native_mb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
- defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+ defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
try:
cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
@@ -112,18 +113,15 @@
except Exception as e:
raise KsftSkipEx('device does not support offloaded XDP')
defer(ip, f"link set dev {cfg.ifname} xdpoffload off")
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
if no_sleep != True:
time.sleep(10)
def get_interface_info(cfg) -> None:
- global remote_ifname
global no_sleep
- remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
- remote_ifname = remote_info.rstrip('\n')
- if remote_ifname == "":
+ if cfg.remote_ifname == "":
raise KsftFailEx('Can not get remote interface')
local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim":
@@ -136,15 +134,25 @@
cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True)
cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True)
cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True)
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
-def test_default(cfg, netnl) -> None:
+def test_default_v4(cfg, netnl) -> None:
+ cfg.require_ipver("4")
+
_set_offload_checksum(cfg, netnl, "off")
_test_v4(cfg)
- _test_v6(cfg)
_test_tcp(cfg)
_set_offload_checksum(cfg, netnl, "on")
_test_v4(cfg)
+ _test_tcp(cfg)
+
+def test_default_v6(cfg, netnl) -> None:
+ cfg.require_ipver("6")
+
+ _set_offload_checksum(cfg, netnl, "off")
+ _test_v6(cfg)
+ _test_tcp(cfg)
+ _set_offload_checksum(cfg, netnl, "on")
_test_v6(cfg)
_test_tcp(cfg)
@@ -202,7 +210,8 @@
with NetDrvEpEnv(__file__) as cfg:
get_interface_info(cfg)
set_interface_init(cfg)
- ksft_run([test_default,
+ ksft_run([test_default_v4,
+ test_default_v6,
test_xdp_generic_sb,
test_xdp_generic_mb,
test_xdp_native_sb,
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 4a2d5c4..59a71f2 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -48,8 +48,16 @@ static uint64_t get_mnt_id(struct __test_metadata *const _metadata,
static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
+static const int mark_cmds[] = {
+ FAN_MARK_ADD,
+ FAN_MARK_REMOVE,
+ FAN_MARK_FLUSH
+};
+
+#define NUM_FAN_FDS ARRAY_SIZE(mark_cmds)
+
FIXTURE(fanotify) {
- int fan_fd;
+ int fan_fd[NUM_FAN_FDS];
char buf[256];
unsigned int rem;
void *next;
@@ -61,7 +69,7 @@ FIXTURE(fanotify) {
FIXTURE_SETUP(fanotify)
{
- int ret;
+ int i, ret;
ASSERT_EQ(unshare(CLONE_NEWNS), 0);
@@ -89,20 +97,34 @@ FIXTURE_SETUP(fanotify)
self->root_id = get_mnt_id(_metadata, "/");
ASSERT_NE(self->root_id, 0);
- self->fan_fd = fanotify_init(FAN_REPORT_MNT, 0);
- ASSERT_GE(self->fan_fd, 0);
-
- ret = fanotify_mark(self->fan_fd, FAN_MARK_ADD | FAN_MARK_MNTNS,
- FAN_MNT_ATTACH | FAN_MNT_DETACH, self->ns_fd, NULL);
- ASSERT_EQ(ret, 0);
+ for (i = 0; i < NUM_FAN_FDS; i++) {
+ self->fan_fd[i] = fanotify_init(FAN_REPORT_MNT | FAN_NONBLOCK,
+ 0);
+ ASSERT_GE(self->fan_fd[i], 0);
+ ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ // On fd[0] we do an extra ADD that changes nothing.
+ // On fd[1]/fd[2] we REMOVE/FLUSH which removes the mark.
+ ret = fanotify_mark(self->fan_fd[i], mark_cmds[i] |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ }
self->rem = 0;
}
FIXTURE_TEARDOWN(fanotify)
{
+ int i;
+
ASSERT_EQ(self->rem, 0);
- close(self->fan_fd);
+ for (i = 0; i < NUM_FAN_FDS; i++)
+ close(self->fan_fd[i]);
ASSERT_EQ(fchdir(self->orig_root), 0);
@@ -123,8 +145,21 @@ static uint64_t expect_notify(struct __test_metadata *const _metadata,
unsigned int thislen;
if (!self->rem) {
- ssize_t len = read(self->fan_fd, self->buf, sizeof(self->buf));
- ASSERT_GT(len, 0);
+ ssize_t len;
+ int i;
+
+ for (i = NUM_FAN_FDS - 1; i >= 0; i--) {
+ len = read(self->fan_fd[i], self->buf,
+ sizeof(self->buf));
+ if (i > 0) {
+ // Groups 1,2 should get EAGAIN
+ ASSERT_EQ(len, -1);
+ ASSERT_EQ(errno, EAGAIN);
+ } else {
+ // Group 0 should get events
+ ASSERT_GT(len, 0);
+ }
+ }
self->rem = len;
self->next = (void *) self->buf;
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 322b9d3..57708de 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -129,10 +129,10 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = {
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0),
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0),
REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 1),
REG_FTR_END,
};
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
index b905408..18a6014 100644
--- a/tools/testing/selftests/landlock/audit.h
+++ b/tools/testing/selftests/landlock/audit.h
@@ -300,15 +300,22 @@ static int audit_match_record(int audit_fd, const __u16 type,
return err;
}
-static int __maybe_unused matches_log_domain_allocated(int audit_fd,
+static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid,
__u64 *domain_id)
{
- return audit_match_record(
- audit_fd, AUDIT_LANDLOCK_DOMAIN,
- REGEX_LANDLOCK_PREFIX
- " status=allocated mode=enforcing pid=[0-9]\\+ uid=[0-9]\\+"
- " exe=\"[^\"]\\+\" comm=\".*_test\"$",
- domain_id);
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " status=allocated mode=enforcing pid=%d uid=[0-9]\\+"
+ " exe=\"[^\"]\\+\" comm=\".*_test\"$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len =
+ snprintf(log_match, sizeof(log_match), log_template, pid);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+ domain_id);
}
static int __maybe_unused matches_log_domain_deallocated(
diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c
index a064307..cfc571a 100644
--- a/tools/testing/selftests/landlock/audit_test.c
+++ b/tools/testing/selftests/landlock/audit_test.c
@@ -9,6 +9,7 @@
#include <errno.h>
#include <limits.h>
#include <linux/landlock.h>
+#include <pthread.h>
#include <stdlib.h>
#include <sys/mount.h>
#include <sys/prctl.h>
@@ -40,7 +41,6 @@ FIXTURE(audit)
{
struct audit_filter audit_filter;
int audit_fd;
- __u64(*domain_stack)[16];
};
FIXTURE_SETUP(audit)
@@ -60,18 +60,10 @@ FIXTURE_SETUP(audit)
TH_LOG("Failed to initialize audit: %s", error_msg);
}
clear_cap(_metadata, CAP_AUDIT_CONTROL);
-
- self->domain_stack = mmap(NULL, sizeof(*self->domain_stack),
- PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_ANONYMOUS, -1, 0);
- ASSERT_NE(MAP_FAILED, self->domain_stack);
- memset(self->domain_stack, 0, sizeof(*self->domain_stack));
}
FIXTURE_TEARDOWN(audit)
{
- EXPECT_EQ(0, munmap(self->domain_stack, sizeof(*self->domain_stack)));
-
set_cap(_metadata, CAP_AUDIT_CONTROL);
EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
clear_cap(_metadata, CAP_AUDIT_CONTROL);
@@ -83,9 +75,15 @@ TEST_F(audit, layers)
.scoped = LANDLOCK_SCOPE_SIGNAL,
};
int status, ruleset_fd, i;
+ __u64(*domain_stack)[16];
__u64 prev_dom = 3;
pid_t child;
+ domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(MAP_FAILED, domain_stack);
+ memset(domain_stack, 0, sizeof(*domain_stack));
+
ruleset_fd =
landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
@@ -94,7 +92,7 @@ TEST_F(audit, layers)
child = fork();
ASSERT_LE(0, child);
if (child == 0) {
- for (i = 0; i < ARRAY_SIZE(*self->domain_stack); i++) {
+ for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) {
__u64 denial_dom = 1;
__u64 allocated_dom = 2;
@@ -107,7 +105,8 @@ TEST_F(audit, layers)
matches_log_signal(_metadata, self->audit_fd,
getppid(), &denial_dom));
EXPECT_EQ(0, matches_log_domain_allocated(
- self->audit_fd, &allocated_dom));
+ self->audit_fd, getpid(),
+ &allocated_dom));
EXPECT_NE(denial_dom, 1);
EXPECT_NE(denial_dom, 0);
EXPECT_EQ(denial_dom, allocated_dom);
@@ -115,7 +114,7 @@ TEST_F(audit, layers)
/* Checks that the new domain is younger than the previous one. */
EXPECT_GT(allocated_dom, prev_dom);
prev_dom = allocated_dom;
- (*self->domain_stack)[i] = allocated_dom;
+ (*domain_stack)[i] = allocated_dom;
}
/* Checks that we reached the maximum number of layers. */
@@ -142,23 +141,143 @@ TEST_F(audit, layers)
/* Purges log from deallocated domains. */
EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
- for (i = ARRAY_SIZE(*self->domain_stack) - 1; i >= 0; i--) {
+ for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) {
__u64 deallocated_dom = 2;
EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
&deallocated_dom));
- EXPECT_EQ((*self->domain_stack)[i], deallocated_dom)
+ EXPECT_EQ((*domain_stack)[i], deallocated_dom)
{
TH_LOG("Failed to match domain %llx (#%d)",
- (*self->domain_stack)[i], i);
+ (*domain_stack)[i], i);
}
}
+ EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack)));
EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
&audit_tv_default, sizeof(audit_tv_default)));
-
EXPECT_EQ(0, close(ruleset_fd));
}
+struct thread_data {
+ pid_t parent_pid;
+ int ruleset_fd, pipe_child, pipe_parent;
+};
+
+static void *thread_audit_test(void *arg)
+{
+ const struct thread_data *data = (struct thread_data *)arg;
+ uintptr_t err = 0;
+ char buffer;
+
+ /* TGID and TID are different for a second thread. */
+ if (getpid() == gettid()) {
+ err = 1;
+ goto out;
+ }
+
+ if (landlock_restrict_self(data->ruleset_fd, 0)) {
+ err = 2;
+ goto out;
+ }
+
+ if (close(data->ruleset_fd)) {
+ err = 3;
+ goto out;
+ }
+
+ /* Creates a denial to get the domain ID. */
+ if (kill(data->parent_pid, 0) != -1) {
+ err = 4;
+ goto out;
+ }
+
+ if (EPERM != errno) {
+ err = 5;
+ goto out;
+ }
+
+ /* Signals the parent to read denial logs. */
+ if (write(data->pipe_child, ".", 1) != 1) {
+ err = 6;
+ goto out;
+ }
+
+ /* Waits for the parent to update audit filters. */
+ if (read(data->pipe_parent, &buffer, 1) != 1) {
+ err = 7;
+ goto out;
+ }
+
+out:
+ close(data->pipe_child);
+ close(data->pipe_parent);
+ return (void *)err;
+}
+
+/* Checks that the PID tied to a domain is not a TID but the TGID. */
+TEST_F(audit, thread)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ __u64 denial_dom = 1;
+ __u64 allocated_dom = 2;
+ __u64 deallocated_dom = 3;
+ pthread_t thread;
+ int pipe_child[2], pipe_parent[2];
+ char buffer;
+ struct thread_data child_data;
+
+ child_data.parent_pid = getppid();
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ child_data.pipe_child = pipe_child[1];
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+ child_data.pipe_parent = pipe_parent[0];
+ child_data.ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, child_data.ruleset_fd);
+
+ /* TGID and TID are the same for the initial thread . */
+ EXPECT_EQ(getpid(), gettid());
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test,
+ &child_data));
+
+ /* Waits for the child to generate a denial. */
+ ASSERT_EQ(1, read(pipe_child[0], &buffer, 1));
+ EXPECT_EQ(0, close(pipe_child[0]));
+
+ /* Matches the signal log to get the domain ID. */
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ child_data.parent_pid, &denial_dom));
+ EXPECT_NE(denial_dom, 1);
+ EXPECT_NE(denial_dom, 0);
+
+ EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(),
+ &allocated_dom));
+ EXPECT_EQ(denial_dom, allocated_dom);
+
+ /* Updates filter rules to match the drop record. */
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+ EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ /* Signals the thread to exit, which will generate a domain deallocation. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(0, close(pipe_parent[1]));
+ ASSERT_EQ(0, pthread_join(thread, NULL));
+
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+ EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+ &deallocated_dom));
+ EXPECT_EQ(denial_dom, deallocated_dom);
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_default, sizeof(audit_tv_default)));
+}
+
FIXTURE(audit_flags)
{
struct audit_filter audit_filter;
@@ -273,7 +392,8 @@ TEST_F(audit_flags, signal)
/* Checks domain information records. */
EXPECT_EQ(0, matches_log_domain_allocated(
- self->audit_fd, &allocated_dom));
+ self->audit_fd, getpid(),
+ &allocated_dom));
EXPECT_NE(*self->domain_id, 1);
EXPECT_NE(*self->domain_id, 0);
EXPECT_EQ(*self->domain_id, allocated_dom);
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index f819011..7372938 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -5964,7 +5964,8 @@ TEST_F(audit_layout1, refer_handled)
EXPECT_EQ(EXDEV, errno);
EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
dir_s1d1));
- EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, NULL));
+ EXPECT_EQ(0,
+ matches_log_domain_allocated(self->audit_fd, getpid(), NULL));
EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
dir_s1d3));
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 2c3a0eb..9bc4591 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
int compaction_index = 0;
char nr_hugepages[20] = {0};
char init_nr_hugepages[24] = {0};
+ char target_nr_hugepages[24] = {0};
+ int slen;
snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
"%lu", initial_nr_hugepages);
@@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
goto out;
}
- /* Request a large number of huge pages. The Kernel will allocate
- as much as it can */
- if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
- ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
- strerror(errno));
+ /*
+ * Request huge pages for about half of the free memory. The Kernel
+ * will allocate as much as it can, and we expect it will get at least 1/3
+ */
+ nr_hugepages_ul = mem_free / hugepage_size / 2;
+ snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+ "%lu", nr_hugepages_ul);
+
+ slen = strlen(target_nr_hugepages);
+ if (write(fd, target_nr_hugepages, slen) != slen) {
+ ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+ nr_hugepages_ul, strerror(errno));
goto close_fd;
}
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b3d0e27..eba43ea 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions)
self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
setup_sighandler();
- if (variant->backing == ANON_BACKED)
+ switch (variant->backing) {
+ case ANON_BACKED:
return;
-
- self->fd = open_file(
- variant->backing == SHMEM_BACKED ? "/tmp/" : "",
- self->path);
+ case LOCAL_FILE_BACKED:
+ self->fd = open_file("", self->path);
+ break;
+ case SHMEM_BACKED:
+ self->fd = memfd_create(self->path, 0);
+ break;
+ }
/* We truncate file to at least 100 pages, tests can modify as needed. */
ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
@@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file)
char *ptr;
int i;
- if (variant->backing == ANON_BACKED)
+ if (variant->backing != LOCAL_FILE_BACKED)
SKIP(return, "Read-only test specific to file-backed");
/* Map shared so we can populate with pattern, populate it, unmap. */
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 1bad310..17bf2d1 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -3,6 +3,8 @@
#ifndef _PKEYS_POWERPC_H
#define _PKEYS_POWERPC_H
+#include <sys/stat.h>
+
#ifndef SYS_pkey_alloc
# define SYS_pkey_alloc 384
# define SYS_pkey_free 385
@@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
return;
}
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+ REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+ REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+ REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+ REPEAT_4096(s) REPEAT_4096(s)
+
/* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
{
diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c
index ca4ad0d..255b332 100644
--- a/tools/testing/selftests/mm/pkey_util.c
+++ b/tools/testing/selftests/mm/pkey_util.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
+#define __SANE_USERSPACE_TYPES__
#include <sys/syscall.h>
#include <unistd.h>
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 124078b..70a38f4 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,6 +31,7 @@
TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
+TEST_PROGS += gre_ipv6_lladdr.sh
TEST_PROGS += cmsg_so_mark.sh
TEST_PROGS += cmsg_so_priority.sh
TEST_PROGS += test_so_rcv.sh
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 90f8a24..e59fba3 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid 8021p drop_untagged"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
@@ -194,6 +194,100 @@
tc qdisc del dev $h2 clsact
}
+8021p_do()
+{
+ local should_fail=$1; shift
+ local mac=de:ad:be:ef:13:37
+
+ tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+ flower dst_mac $mac action drop
+
+ $MZ -q $h1 -c 1 -b $mac -a own "81:00 00:00 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+ sleep 1
+
+ tc -j -s filter show dev $h2 ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ check_err_fail $should_fail $? "802.1p-tagged reception"
+
+ tc filter del dev $h2 ingress pref 1
+}
+
+8021p()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with the default_pvid, 1, packets tagged with VID 0 are
+ # accepted.
+ 8021p_do 0
+
+ # Test that packets tagged with VID 0 are still accepted after changing
+ # the default_pvid.
+ ip link set br0 type bridge vlan_default_pvid 10
+ 8021p_do 0
+
+ log_test "Reception of 802.1p-tagged traffic"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
+send_untagged_and_8021p()
+{
+ ping_do $h1 192.0.2.2
+ check_fail $?
+
+ 8021p_do 1
+}
+
+drop_untagged()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with no PVID, untagged and 802.1p-tagged traffic is
+ # dropped.
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ # First we reconfigure the default_pvid, 1, as a non-PVID VLAN.
+ bridge vlan add dev $swp1 vid 1 untagged
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Next we try to delete VID 1 altogether
+ bridge vlan del dev $swp1 vid 1
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Set up the bridge without a default_pvid, then check that the 8021q
+ # module, when the bridge port goes down and then up again, does not
+ # accidentally re-enable untagged packet reception.
+ ip link set br0 type bridge vlan_default_pvid 0
+ ip link set $swp1 down
+ ip link set $swp1 up
+ setup_wait
+ send_untagged_and_8021p
+
+ # Remove swp1 as a bridge port and let it rejoin the bridge while it
+ # has no default_pvid.
+ ip link set $swp1 nomaster
+ ip link set $swp1 master br0
+ send_untagged_and_8021p
+
+ # Restore settings
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ log_test "Dropping of untagged and 802.1p-tagged traffic with no PVID"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/tc_taprio.sh b/tools/testing/selftests/net/forwarding/tc_taprio.sh
new file mode 100755
index 0000000..8992aea
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_taprio.sh
@@ -0,0 +1,421 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS=" \
+ test_clock_jump_backward \
+ test_taprio_after_ptp \
+ test_max_sdu \
+ test_clock_jump_backward_forward \
+"
+NUM_NETIFS=4
+source tc_common.sh
+source lib.sh
+source tsn_lib.sh
+
+require_command python3
+
+# The test assumes the usual topology from the README, where h1 is connected to
+# swp1, h2 to swp2, and swp1 and swp2 are together in a bridge.
+# Additional assumption: h1 and h2 use the same PHC, and so do swp1 and swp2.
+# By synchronizing h1 to swp1 via PTP, h2 is also implicitly synchronized to
+# swp1 (and both to CLOCK_REALTIME).
+h1=${NETIFS[p1]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p3]}
+h2=${NETIFS[p4]}
+
+UDS_ADDRESS_H1="/var/run/ptp4l_h1"
+UDS_ADDRESS_SWP1="/var/run/ptp4l_swp1"
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+# Tunables
+NUM_PKTS=100
+STREAM_VID=10
+STREAM_PRIO_1=6
+STREAM_PRIO_2=5
+STREAM_PRIO_3=4
+# PTP uses TC 0
+ALL_GATES=$((1 << 0 | 1 << STREAM_PRIO_1 | 1 << STREAM_PRIO_2))
+# Use a conservative cycle of 10 ms to allow the test to still pass when the
+# kernel has some extra overhead like lockdep etc
+CYCLE_TIME_NS=10000000
+# Create two Gate Control List entries, one OPEN and one CLOSE, of equal
+# durations
+GATE_DURATION_NS=$((CYCLE_TIME_NS / 2))
+# Give 2/3 of the cycle time to user space and 1/3 to the kernel
+FUDGE_FACTOR=$((CYCLE_TIME_NS / 3))
+# Shift the isochron base time by half the gate time, so that packets are
+# always received by swp1 close to the middle of the time slot, to minimize
+# inaccuracies due to network sync
+SHIFT_TIME_NS=$((GATE_DURATION_NS / 2))
+
+path_delay=
+
+h1_create()
+{
+ simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+switch_create()
+{
+ local h2_mac_addr=$(mac_get $h2)
+
+ ip link set $swp1 up
+ ip link set $swp2 up
+
+ ip link add br0 type bridge vlan_filtering 1
+ ip link set $swp1 master br0
+ ip link set $swp2 master br0
+ ip link set br0 up
+
+ bridge vlan add dev $swp2 vid $STREAM_VID
+ bridge vlan add dev $swp1 vid $STREAM_VID
+ bridge fdb add dev $swp2 \
+ $h2_mac_addr vlan $STREAM_VID static master
+}
+
+switch_destroy()
+{
+ ip link del br0
+}
+
+ptp_setup()
+{
+ # Set up swp1 as a master PHC for h1, synchronized to the local
+ # CLOCK_REALTIME.
+ phc2sys_start $UDS_ADDRESS_SWP1
+ ptp4l_start $h1 true $UDS_ADDRESS_H1
+ ptp4l_start $swp1 false $UDS_ADDRESS_SWP1
+}
+
+ptp_cleanup()
+{
+ ptp4l_stop $swp1
+ ptp4l_stop $h1
+ phc2sys_stop
+}
+
+txtime_setup()
+{
+ local if_name=$1
+
+ tc qdisc add dev $if_name clsact
+ # Classify PTP on TC 7 and isochron on TC 6
+ tc filter add dev $if_name egress protocol 0x88f7 \
+ flower action skbedit priority 7
+ tc filter add dev $if_name egress protocol 802.1Q \
+ flower vlan_ethtype 0xdead action skbedit priority 6
+ tc qdisc add dev $if_name handle 100: parent root mqprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ hw 1
+ # Set up TC 5, 6, 7 for SO_TXTIME. tc-mqprio queues count from 1.
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_1 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_2 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_3 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+}
+
+txtime_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name clsact
+ tc qdisc del dev $if_name root
+}
+
+taprio_replace()
+{
+ local if_name="$1"; shift
+ local extra_args="$1"; shift
+
+ # STREAM_PRIO_1 always has an open gate.
+ # STREAM_PRIO_2 has a gate open for GATE_DURATION_NS (half the cycle time)
+ # STREAM_PRIO_3 always has a closed gate.
+ tc qdisc replace dev $if_name root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ sched-entry S $(printf "%x" $ALL_GATES) $GATE_DURATION_NS \
+ sched-entry S $(printf "%x" $((ALL_GATES & ~(1 << STREAM_PRIO_2)))) $GATE_DURATION_NS \
+ base-time 0 flags 0x2 $extra_args
+ taprio_wait_for_admin $if_name
+}
+
+taprio_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name root
+}
+
+probe_path_delay()
+{
+ local isochron_dat="$(mktemp)"
+ local received
+
+ log_info "Probing path delay"
+
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" 0 \
+ "$CYCLE_TIME_NS" "" "" "$NUM_PKTS" \
+ "$STREAM_VID" "$STREAM_PRIO_1" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ if [ "$received" != "$NUM_PKTS" ]; then
+ echo "Cannot establish basic data path between $h1 and $h2"
+ exit $ksft_fail
+ fi
+
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(np.max(w)))
+ EOF
+ path_delay=$(python3 ./isochron_postprocess.py)
+
+ log_info "Path delay from $h1 to $h2 estimated at $path_delay ns"
+
+ if [ "$path_delay" -gt "$GATE_DURATION_NS" ]; then
+ echo "Path delay larger than gate duration, aborting"
+ exit $ksft_fail
+ fi
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+setup_prepare()
+{
+ vrf_prepare
+
+ h1_create
+ h2_create
+ switch_create
+
+ txtime_setup $h1
+
+ # Temporarily set up PTP just to probe the end-to-end path delay.
+ ptp_setup
+ probe_path_delay
+ ptp_cleanup
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ isochron_recv_stop
+ txtime_cleanup $h1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+run_test()
+{
+ local base_time=$1; shift
+ local stream_prio=$1; shift
+ local expected_delay=$1; shift
+ local should_fail=$1; shift
+ local test_name=$1; shift
+ local isochron_dat="$(mktemp)"
+ local received
+ local median_delay
+
+ RET=0
+
+ # Set the shift time equal to the cycle time, which effectively
+ # cancels the default advance time. Packets won't be sent early in
+ # software, which ensures that they won't prematurely enter through
+ # the open gate in __test_out_of_band(). Also, the gate is open for
+ # long enough that this won't cause a problem in __test_in_band().
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" "$base_time" \
+ "$CYCLE_TIME_NS" "$SHIFT_TIME_NS" "$GATE_DURATION_NS" \
+ "$NUM_PKTS" "$STREAM_VID" "$stream_prio" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ [ "$received" = "$NUM_PKTS" ]
+ check_err_fail $should_fail $? "Reception of $NUM_PKTS packets"
+
+ if [ $should_fail = 0 ] && [ "$received" = "$NUM_PKTS" ]; then
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(int(np.median(w))))
+ EOF
+ median_delay=$(python3 ./isochron_postprocess.py)
+
+ # If the condition below is true, packets were delayed by a closed gate
+ [ "$median_delay" -gt $((path_delay + expected_delay)) ]
+ check_fail $? "Median delay $median_delay is greater than expected delay $expected_delay plus path delay $path_delay"
+
+ # If the condition below is true, packets were sent expecting them to
+ # hit a closed gate in the switch, but were not delayed
+ [ "$expected_delay" -gt 0 ] && [ "$median_delay" -lt "$expected_delay" ]
+ check_fail $? "Median delay $median_delay is less than expected delay $expected_delay"
+ fi
+
+ log_test "$test_name"
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+__test_always_open()
+{
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Gate always open"
+}
+
+__test_always_closed()
+{
+ run_test 0.000000000 $STREAM_PRIO_3 0 1 "Gate always closed"
+}
+
+__test_in_band()
+{
+ # Send packets in-band with the OPEN gate entry
+ run_test 0.000000000 $STREAM_PRIO_2 0 0 "In band with gate"
+}
+
+__test_out_of_band()
+{
+ # Send packets in-band with the CLOSE gate entry
+ run_test 0.005000000 $STREAM_PRIO_2 \
+ $((GATE_DURATION_NS - SHIFT_TIME_NS)) 0 \
+ "Out of band with gate"
+}
+
+run_subtests()
+{
+ __test_always_open
+ __test_always_closed
+ __test_in_band
+ __test_out_of_band
+}
+
+test_taprio_after_ptp()
+{
+ log_info "Setting up taprio after PTP"
+ ptp_setup
+ taprio_replace $swp2
+ run_subtests
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+__test_under_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 100 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Under maximum SDU"
+}
+
+__test_over_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 20 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 1 "Over maximum SDU"
+}
+
+test_max_sdu()
+{
+ ptp_setup
+ __test_under_max_sdu
+ __test_over_max_sdu
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+# Perform a clock jump in the past without synchronization running, so that the
+# time base remains where it was set by phc_ctl.
+test_clock_jump_backward()
+{
+ # This is a more complex schedule specifically crafted in a way that
+ # has been problematic on NXP LS1028A. Not much to test with it other
+ # than the fact that it passes traffic.
+ tc qdisc replace dev $swp2 root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 map 0 1 2 3 4 5 6 7 \
+ base-time 0 sched-entry S 20 300000 sched-entry S 10 200000 \
+ sched-entry S 20 300000 sched-entry S 48 200000 \
+ sched-entry S 20 300000 sched-entry S 83 200000 \
+ sched-entry S 40 300000 sched-entry S 00 200000 flags 2
+
+ log_info "Forcing a backward clock jump"
+ phc_ctl $swp1 set 0
+
+ ping_test $h1 192.0.2.2
+ taprio_cleanup $swp2
+}
+
+# Test that taprio tolerates clock jumps.
+# Since ptp4l and phc2sys are running, it is expected for the time to
+# eventually recover (through yet another clock jump). Isochron waits
+# until that is the case.
+test_clock_jump_backward_forward()
+{
+ log_info "Forcing a backward and a forward clock jump"
+ taprio_replace $swp2
+ phc_ctl $swp1 set 0
+ ptp_setup
+ ping_test $h1 192.0.2.2
+ run_subtests
+ ptp_cleanup
+ taprio_cleanup $swp2
+}
+
+tc_offload_check
+if [[ $? -ne 0 ]]; then
+ log_test_skip "Could not test offloaded functionality"
+ exit $EXIT_STATUS
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tsn_lib.sh b/tools/testing/selftests/net/forwarding/tsn_lib.sh
index b91bcd8..08c044f 100644
--- a/tools/testing/selftests/net/forwarding/tsn_lib.sh
+++ b/tools/testing/selftests/net/forwarding/tsn_lib.sh
@@ -2,6 +2,8 @@
# SPDX-License-Identifier: GPL-2.0
# Copyright 2021-2022 NXP
+tc_testing_scripts_dir=$(dirname $0)/../../tc-testing/scripts
+
REQUIRE_ISOCHRON=${REQUIRE_ISOCHRON:=yes}
REQUIRE_LINUXPTP=${REQUIRE_LINUXPTP:=yes}
@@ -18,6 +20,7 @@
if [[ "$REQUIRE_LINUXPTP" = "yes" ]]; then
require_command phc2sys
require_command ptp4l
+ require_command phc_ctl
fi
phc2sys_start()
@@ -182,6 +185,7 @@
local base_time=$1; shift
local cycle_time=$1; shift
local shift_time=$1; shift
+ local window_size=$1; shift
local num_pkts=$1; shift
local vid=$1; shift
local priority=$1; shift
@@ -212,6 +216,10 @@
extra_args="${extra_args} --shift-time=${shift_time}"
fi
+ if ! [ -z "${window_size}" ]; then
+ extra_args="${extra_args} --window-size=${window_size}"
+ fi
+
if [ "${use_l2}" = "true" ]; then
extra_args="${extra_args} --l2 --etype=0xdead ${vid}"
receiver_extra_args="--l2 --etype=0xdead"
@@ -247,3 +255,21 @@
cpufreq_restore ${ISOCHRON_CPU}
}
+
+isochron_report_num_received()
+{
+ local isochron_dat=$1; shift
+
+ # Count all received packets by looking at the non-zero RX timestamps
+ isochron report \
+ --input-file "${isochron_dat}" \
+ --printf-format "%u\n" --printf-args "R" | \
+ grep -w -v '0' | wc -l
+}
+
+taprio_wait_for_admin()
+{
+ local if_name="$1"; shift
+
+ "$tc_testing_scripts_dir/taprio_wait_for_admin.sh" "$(which tc)" "$if_name"
+}
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
new file mode 100755
index 0000000..5b34f6e
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./lib.sh
+
+PAUSE_ON_FAIL="no"
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+ cleanup_all_ns
+
+ exit "${EXIT_STATUS}"
+}
+
+# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
+# underlay by future GRE devices.
+#
+setup_basenet()
+{
+ ip -netns "${NS0}" link set dev lo up
+ ip -netns "${NS0}" address add dev lo 192.0.2.10/24
+ ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
+}
+
+# Check if network device has an IPv6 link-local address assigned.
+#
+# Parameters:
+#
+# * $1: The network device to test
+# * $2: An extra regular expression that should be matched (to verify the
+# presence of extra attributes)
+# * $3: The expected return code from grep (to allow checking the absence of
+# a link-local address)
+# * $4: The user visible name for the scenario being tested
+#
+check_ipv6_ll_addr()
+{
+ local DEV="$1"
+ local EXTRA_MATCH="$2"
+ local XRET="$3"
+ local MSG="$4"
+
+ RET=0
+ set +e
+ ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
+ check_err_fail "${XRET}" $? ""
+ log_test "${MSG}"
+ set -e
+}
+
+# Create a GRE device and verify that it gets an IPv6 link-local address as
+# expected.
+#
+# Parameters:
+#
+# * $1: The device type (gre, ip6gre, gretap or ip6gretap)
+# * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $4: The IPv6 interface identifier generation mode to use for the GRE
+# device (eui64, none, stable-privacy or random).
+#
+test_gre_device()
+{
+ local GRE_TYPE="$1"
+ local LOCAL_IP="$2"
+ local REMOTE_IP="$3"
+ local MODE="$4"
+ local ADDR_GEN_MODE
+ local MATCH_REGEXP
+ local MSG
+
+ ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
+
+ case "${MODE}" in
+ "eui64")
+ ADDR_GEN_MODE=0
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ "none")
+ ADDR_GEN_MODE=1
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=1 # No link-local address should be generated
+ ;;
+ "stable-privacy")
+ ADDR_GEN_MODE=2
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ # Initialise stable_secret (required for stable-privacy mode)
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
+ ;;
+ "random")
+ ADDR_GEN_MODE=3
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ esac
+
+ # Check that IPv6 link-local address is generated when device goes up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ ip -netns "${NS0}" link set dev gretest up
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+
+ # Now disable link-local address generation
+ ip -netns "${NS0}" link set dev gretest down
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
+ ip -netns "${NS0}" link set dev gretest up
+
+ # Check that link-local address generation works when re-enabled while
+ # the device is already up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+
+ ip -netns "${NS0}" link del dev gretest
+}
+
+test_gre4()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "gre" "gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
+ done
+ done
+}
+
+test_gre6()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "ip6gre" "ip6gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
+ done
+ done
+}
+
+usage()
+{
+ echo "Usage: $0 [-p]"
+ exit 1
+}
+
+while getopts :p o
+do
+ case $o in
+ p) PAUSE_ON_FAIL="yes";;
+ *) usage;;
+ esac
+done
+
+setup_ns NS0
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_basenet
+
+test_gre4
+test_gre6
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4f55477..e7a7534 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -206,9 +206,8 @@
local token
local msg
- ss_token="$(ss -inmHMN $ns | grep 'token:' |\
- head -n 1 |\
- sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+ ss_token="$(ss -inmHMN $ns |
+ mptcp_lib_get_info_value "token" "token")"
token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
awk -F':[ \t]+' '/^token/ {print $2}')"
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
index 48ec048..277f92f 100644
--- a/tools/testing/selftests/pcie_bwctrl/Makefile
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -1,2 +1,3 @@
-TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh
+TEST_PROGS = set_pcie_cooling_state.sh
+TEST_FILES = set_pcie_speed.sh
include ../lib.mk
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index d4ea9cd..ddc97ec 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -313,5 +313,292 @@
"$TC qdisc del dev $DUMMY handle 1: root",
"$IP addr del 10.10.10.10/24 dev $DUMMY || true"
]
+ },
+ {
+ "id": "a4c3",
+ "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+ "category": [
+ "qdisc",
+ "hfsc",
+ "netem",
+ "blackhole"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+ "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+ "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+ ],
+ "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+ "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "90ec",
+ "name": "Test DRR's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "drr",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "1f1f",
+ "name": "Test ETS's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "ets"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root ets bands 2",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 ets quantum 1500",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s class show dev $DUMMY",
+ "matchJSON": [
+ {
+ "class": "ets",
+ "handle": "1:1",
+ "stats": {
+ "bytes": 196,
+ "packets": 2
+ }
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "5e6d",
+ "name": "Test QFQ's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "qfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root qfq",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 qfq weight 100 maxpkt 1500",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "qfq",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "bf1d",
+ "name": "Test HFSC's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "hfsc"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root hfsc",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc ls m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2",
+ "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true",
+ "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1",
+ "$TC class del dev $DUMMY classid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 10.10.10.2 -I$DUMMY > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "hfsc",
+ "handle": "1:",
+ "bytes": 392,
+ "packets": 4
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "7c3b",
+ "name": "Test nested DRR's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+ "$TC qdisc add dev $DUMMY handle 2:0 parent 1:1 drr",
+ "$TC class add dev $DUMMY classid 2:1 parent 2:0 drr",
+ "$TC filter add dev $DUMMY parent 2:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 2:1",
+ "$TC qdisc add dev $DUMMY parent 2:1 handle 3:0 netem duplicate 100%"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "drr",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "62c4",
+ "name": "Test HTB with FQ_CODEL - basic functionality",
+ "category": [
+ "qdisc",
+ "htb",
+ "fq_codel"
+ ],
+ "plugins": {
+ "requires": [
+ "nsPlugin",
+ "scapyPlugin"
+ ]
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 root handle 1: htb default 11",
+ "$TC class add dev $DEV1 parent 1: classid 1:1 htb rate 10kbit",
+ "$TC class add dev $DEV1 parent 1:1 classid 1:11 htb rate 10kbit prio 0 quantum 1486",
+ "$TC qdisc add dev $DEV1 parent 1:11 fq_codel quantum 300 noecn",
+ "sleep 0.5"
+ ],
+ "scapy": {
+ "iface": "$DEV0",
+ "count": 5,
+ "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/TCP(sport=12345, dport=80)"
+ },
+ "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DEV1 | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "Sent [0-9]+ bytes [0-9]+ pkt",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 handle 1: root"
+ ]
+ },
+ {
+ "id": "831d",
+ "name": "Test HFSC qlen accounting with DRR/NETEM/BLACKHOLE chain",
+ "category": ["qdisc", "hfsc", "drr", "netem", "blackhole"],
+ "plugins": { "requires": ["nsPlugin", "scapyPlugin"] },
+ "setup": [
+ "$IP link set dev $DEV1 up || true",
+ "$TC qdisc add dev $DEV1 root handle 1: drr",
+ "$TC filter add dev $DEV1 parent 1: basic classid 1:1",
+ "$TC class add dev $DEV1 parent 1: classid 1:1 drr",
+ "$TC qdisc add dev $DEV1 parent 1:1 handle 2: hfsc def 1",
+ "$TC class add dev $DEV1 parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0",
+ "$TC qdisc add dev $DEV1 parent 2:1 handle 3: netem",
+ "$TC qdisc add dev $DEV1 parent 3:1 handle 4: blackhole"
+ ],
+ "scapy": {
+ "iface": "$DEV0",
+ "count": 5,
+ "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()"
+ },
+ "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DEV1",
+ "matchPattern": "qdisc hfsc",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 root handle 1: drr"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
index e9469ee..6d515d0 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
@@ -189,5 +189,29 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "deb1",
+ "name": "CODEL test qdisc limit trimming",
+ "category": ["qdisc", "codel"],
+ "plugins": {
+ "requires": ["nsPlugin", "scapyPlugin"]
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root codel limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root codel limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1p target 5ms interval 100ms",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
index 3a537b2..24faf4e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
@@ -377,5 +377,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "9479",
+ "name": "FQ test qdisc limit trimming",
+ "category": ["qdisc", "fq"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root fq limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 1p",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
index 9774b1e..4ce62b8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
@@ -294,5 +294,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "0436",
+ "name": "FQ_CODEL test qdisc limit trimming",
+ "category": ["qdisc", "fq_codel"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root fq_codel limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_codel limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
index d012d88..229fe1b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -18,5 +18,27 @@
"matchCount": "1",
"teardown": [
]
+ },
+ {
+ "id": "83bf",
+ "name": "FQ_PIE test qdisc limit trimming",
+ "category": ["qdisc", "fq_pie"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root fq_pie limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_pie limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc fq_pie 1: root refcnt [0-9]+ limit 1p",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
index dbef547..0ca19fa 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
@@ -188,5 +188,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "385f",
+ "name": "HHF test qdisc limit trimming",
+ "category": ["qdisc", "hhf"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root hhf limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root hhf limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc hhf 1: root refcnt [0-9]+ limit 1p.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json
new file mode 100644
index 0000000..1a98b66
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json
@@ -0,0 +1,24 @@
+[
+ {
+ "id": "6158",
+ "name": "PIE test qdisc limit trimming",
+ "category": ["qdisc", "pie"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root pie limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root pie limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc pie 1: root refcnt [0-9]+ limit 1p",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
+ }
+]
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index ec4624a..f34ac0b 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -9,6 +9,7 @@
TEST_PROGS += test_generic_04.sh
TEST_PROGS += test_generic_05.sh
TEST_PROGS += test_generic_06.sh
+TEST_PROGS += test_generic_07.sh
TEST_PROGS += test_null_01.sh
TEST_PROGS += test_null_02.sh
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 759f066..842b407 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -536,12 +536,17 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
if (!(io->flags & UBLKSRV_IO_FREE))
return 0;
- /* we issue because we need either fetching or committing */
+ /*
+ * we issue because we need either fetching or committing or
+ * getting data
+ */
if (!(io->flags &
- (UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP)))
+ (UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_NEED_GET_DATA)))
return 0;
- if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
+ if (io->flags & UBLKSRV_NEED_GET_DATA)
+ cmd_op = UBLK_U_IO_NEED_GET_DATA;
+ else if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ;
else if (io->flags & UBLKSRV_NEED_FETCH_RQ)
cmd_op = UBLK_U_IO_FETCH_REQ;
@@ -658,6 +663,9 @@ static void ublk_handle_cqe(struct io_uring *r,
assert(tag < q->q_depth);
if (q->tgt_ops->queue_io)
q->tgt_ops->queue_io(q, tag);
+ } else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) {
+ io->flags |= UBLKSRV_NEED_GET_DATA | UBLKSRV_IO_FREE;
+ ublk_queue_io_cmd(q, io, tag);
} else {
/*
* COMMIT_REQ will be completed immediately since no fetching
@@ -1237,7 +1245,7 @@ static void __cmd_create_help(char *exe, bool recovery)
printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
exe, recovery ? "recover" : "add");
- printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g 0|1]\n");
+ printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g]\n");
printf("\t[-e 0|1 ] [-i 0|1]\n");
printf("\t[target options] [backfile1] [backfile2] ...\n");
printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
@@ -1313,7 +1321,7 @@ int main(int argc, char *argv[])
opterr = 0;
optind = 2;
- while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:az",
+ while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:gaz",
longopts, &option_idx)) != -1) {
switch (opt) {
case 'a':
@@ -1351,9 +1359,8 @@ int main(int argc, char *argv[])
ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
break;
case 'g':
- value = strtol(optarg, NULL, 10);
- if (value)
- ctx.flags |= UBLK_F_NEED_GET_DATA;
+ ctx.flags |= UBLK_F_NEED_GET_DATA;
+ break;
case 0:
if (!strcmp(longopts[option_idx].name, "debug_mask"))
ublk_dbg_mask = strtol(optarg, NULL, 16);
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 29571eb..44ee1e4 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -86,9 +86,6 @@ struct dev_ctx {
unsigned int fg:1;
unsigned int recovery:1;
- /* fault_inject */
- long long delay_us;
-
int _evtfd;
int _shmid;
@@ -118,6 +115,7 @@ struct ublk_io {
#define UBLKSRV_NEED_FETCH_RQ (1UL << 0)
#define UBLKSRV_NEED_COMMIT_RQ_COMP (1UL << 1)
#define UBLKSRV_IO_FREE (1UL << 2)
+#define UBLKSRV_NEED_GET_DATA (1UL << 3)
unsigned short flags;
unsigned short refs; /* used by target code only */
diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh
index 9fc111f..a81210ca 100755
--- a/tools/testing/selftests/ublk/test_common.sh
+++ b/tools/testing/selftests/ublk/test_common.sh
@@ -17,8 +17,8 @@
local minor
dev=/dev/ublkb"${dev_id}"
- major=$(stat -c '%Hr' "$dev")
- minor=$(stat -c '%Lr' "$dev")
+ major="0x"$(stat -c '%t' "$dev")
+ minor="0x"$(stat -c '%T' "$dev")
echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
}
diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh
index 714630b..3bb00a3 100755
--- a/tools/testing/selftests/ublk/test_generic_05.sh
+++ b/tools/testing/selftests/ublk/test_generic_05.sh
@@ -3,7 +3,7 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
-TID="generic_04"
+TID="generic_05"
ERR_CODE=0
ublk_run_recover_test()
diff --git a/tools/testing/selftests/ublk/test_generic_07.sh b/tools/testing/selftests/ublk/test_generic_07.sh
new file mode 100755
index 0000000..cba8645
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_07.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_07"
+ERR_CODE=0
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "generic" "test UBLK_F_NEED_GET_DATA"
+
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -q 2 -g "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
+
+# run fio over the ublk disk
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
+ERR_CODE=$?
+if [ "$ERR_CODE" -eq 0 ]; then
+ _mkfs_mount_test /dev/ublkb"${dev_id}"
+ ERR_CODE=$?
+fi
+
+_cleanup_test "generic"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
index a7071b1..88601b4 100755
--- a/tools/testing/selftests/ublk/test_stress_05.sh
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -47,15 +47,15 @@
_create_backfile 1 256M
for reissue in $(seq 0 1); do
- ublk_io_and_remove 8G -t null -q 4 -g 1 -r 1 -i "$reissue" &
- ublk_io_and_remove 256M -t loop -q 4 -g 1 -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
+ ublk_io_and_remove 8G -t null -q 4 -g -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
wait
done
if _have_feature "ZERO_COPY"; then
for reissue in $(seq 0 1); do
- ublk_io_and_remove 8G -t null -q 4 -g 1 -z -r 1 -i "$reissue" &
- ublk_io_and_remove 256M -t loop -q 4 -g 1 -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+ ublk_io_and_remove 8G -t null -q 4 -g -z -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
wait
done
fi
diff --git a/tools/testing/selftests/x86/bugs/Makefile b/tools/testing/selftests/x86/bugs/Makefile
new file mode 100644
index 0000000..8ff2d72
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/Makefile
@@ -0,0 +1,3 @@
+TEST_PROGS := its_sysfs.py its_permutations.py its_indirect_alignment.py its_ret_alignment.py
+TEST_FILES := common.py
+include ../../lib.mk
diff --git a/tools/testing/selftests/x86/bugs/common.py b/tools/testing/selftests/x86/bugs/common.py
new file mode 100755
index 0000000..2f9664a
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/common.py
@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# This contains kselftest framework adapted common functions for testing
+# mitigation for x86 bugs.
+
+import os, sys, re, shutil
+
+sys.path.insert(0, '../../kselftest')
+import ksft
+
+def read_file(path):
+ if not os.path.exists(path):
+ return None
+ with open(path, 'r') as file:
+ return file.read().strip()
+
+def cpuinfo_has(arg):
+ cpuinfo = read_file('/proc/cpuinfo')
+ if arg in cpuinfo:
+ return True
+ return False
+
+def cmdline_has(arg):
+ cmdline = read_file('/proc/cmdline')
+ if arg in cmdline:
+ return True
+ return False
+
+def cmdline_has_either(args):
+ cmdline = read_file('/proc/cmdline')
+ for arg in args:
+ if arg in cmdline:
+ return True
+ return False
+
+def cmdline_has_none(args):
+ return not cmdline_has_either(args)
+
+def cmdline_has_all(args):
+ cmdline = read_file('/proc/cmdline')
+ for arg in args:
+ if arg not in cmdline:
+ return False
+ return True
+
+def get_sysfs(bug):
+ return read_file("/sys/devices/system/cpu/vulnerabilities/" + bug)
+
+def sysfs_has(bug, mitigation):
+ status = get_sysfs(bug)
+ if mitigation in status:
+ return True
+ return False
+
+def sysfs_has_either(bugs, mitigations):
+ for bug in bugs:
+ for mitigation in mitigations:
+ if sysfs_has(bug, mitigation):
+ return True
+ return False
+
+def sysfs_has_none(bugs, mitigations):
+ return not sysfs_has_either(bugs, mitigations)
+
+def sysfs_has_all(bugs, mitigations):
+ for bug in bugs:
+ for mitigation in mitigations:
+ if not sysfs_has(bug, mitigation):
+ return False
+ return True
+
+def bug_check_pass(bug, found):
+ ksft.print_msg(f"\nFound: {found}")
+ # ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+ ksft.test_result_pass(f'{bug}: {found}')
+
+def bug_check_fail(bug, found, expected):
+ ksft.print_msg(f'\nFound:\t {found}')
+ ksft.print_msg(f'Expected:\t {expected}')
+ ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+ ksft.test_result_fail(f'{bug}: {found}')
+
+def bug_status_unknown(bug, found):
+ ksft.print_msg(f'\nUnknown status: {found}')
+ ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+ ksft.test_result_fail(f'{bug}: {found}')
+
+def basic_checks_sufficient(bug, mitigation):
+ if not mitigation:
+ bug_status_unknown(bug, "None")
+ return True
+ elif mitigation == "Not affected":
+ ksft.test_result_pass(bug)
+ return True
+ elif mitigation == "Vulnerable":
+ if cmdline_has_either([f'{bug}=off', 'mitigations=off']):
+ bug_check_pass(bug, mitigation)
+ return True
+ return False
+
+def get_section_info(vmlinux, section_name):
+ from elftools.elf.elffile import ELFFile
+ with open(vmlinux, 'rb') as f:
+ elffile = ELFFile(f)
+ section = elffile.get_section_by_name(section_name)
+ if section is None:
+ ksft.print_msg("Available sections in vmlinux:")
+ for sec in elffile.iter_sections():
+ ksft.print_msg(sec.name)
+ raise ValueError(f"Section {section_name} not found in {vmlinux}")
+ return section['sh_addr'], section['sh_offset'], section['sh_size']
+
+def get_patch_sites(vmlinux, offset, size):
+ import struct
+ output = []
+ with open(vmlinux, 'rb') as f:
+ f.seek(offset)
+ i = 0
+ while i < size:
+ data = f.read(4) # s32
+ if not data:
+ break
+ sym_offset = struct.unpack('<i', data)[0] + i
+ i += 4
+ output.append(sym_offset)
+ return output
+
+def get_instruction_from_vmlinux(elffile, section, virtual_address, target_address):
+ from capstone import Cs, CS_ARCH_X86, CS_MODE_64
+ section_start = section['sh_addr']
+ section_end = section_start + section['sh_size']
+
+ if not (section_start <= target_address < section_end):
+ return None
+
+ offset = target_address - section_start
+ code = section.data()[offset:offset + 16]
+
+ cap = init_capstone()
+ for instruction in cap.disasm(code, target_address):
+ if instruction.address == target_address:
+ return instruction
+ return None
+
+def init_capstone():
+ from capstone import Cs, CS_ARCH_X86, CS_MODE_64, CS_OPT_SYNTAX_ATT
+ cap = Cs(CS_ARCH_X86, CS_MODE_64)
+ cap.syntax = CS_OPT_SYNTAX_ATT
+ return cap
+
+def get_runtime_kernel():
+ import drgn
+ return drgn.program_from_kernel()
+
+def check_dependencies_or_skip(modules, script_name="unknown test"):
+ for mod in modules:
+ try:
+ __import__(mod)
+ except ImportError:
+ ksft.test_result_skip(f"Skipping {script_name}: missing module '{mod}'")
+ ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_indirect_alignment.py b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py
new file mode 100755
index 0000000..cdc33ae
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py
@@ -0,0 +1,150 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) mitigation.
+#
+# Test if indirect CALL/JMP are correctly patched by evaluating
+# the vmlinux .retpoline_sites in /proc/kcore.
+
+# Install dependencies
+# add-apt-repository ppa:michel-slm/kernel-utils
+# apt update
+# apt install -y python3-drgn python3-pyelftools python3-capstone
+#
+# Best to copy the vmlinux at a standard location:
+# mkdir -p /usr/lib/debug/lib/modules/$(uname -r)
+# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux
+#
+# Usage: ./its_indirect_alignment.py [vmlinux]
+
+import os, sys, argparse
+from pathlib import Path
+
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+
+mitigation = c.get_sysfs(bug)
+if not mitigation or "Aligned branch/return thunks" not in mitigation:
+ ksft.test_result_skip("Skipping its_indirect_alignment.py: Aligned branch/return thunks not enabled")
+ ksft.finished()
+
+if c.sysfs_has("spectre_v2", "Retpolines"):
+ ksft.test_result_skip("Skipping its_indirect_alignment.py: Retpolines deployed")
+ ksft.finished()
+
+c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_indirect_alignment.py")
+
+from elftools.elf.elffile import ELFFile
+from drgn.helpers.common.memory import identify_address
+
+cap = c.init_capstone()
+
+if len(os.sys.argv) > 1:
+ arg_vmlinux = os.sys.argv[1]
+ if not os.path.exists(arg_vmlinux):
+ ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at argument path: {arg_vmlinux}")
+ ksft.exit_fail()
+ os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True)
+ os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux')
+
+vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux"
+if not os.path.exists(vmlinux):
+ ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at {vmlinux}")
+ ksft.exit_fail()
+
+ksft.print_msg(f"Using vmlinux: {vmlinux}")
+
+retpolines_start_vmlinux, retpolines_sec_offset, size = c.get_section_info(vmlinux, '.retpoline_sites')
+ksft.print_msg(f"vmlinux: Section .retpoline_sites (0x{retpolines_start_vmlinux:x}) found at 0x{retpolines_sec_offset:x} with size 0x{size:x}")
+
+sites_offset = c.get_patch_sites(vmlinux, retpolines_sec_offset, size)
+total_retpoline_tests = len(sites_offset)
+ksft.print_msg(f"Found {total_retpoline_tests} retpoline sites")
+
+prog = c.get_runtime_kernel()
+retpolines_start_kcore = prog.symbol('__retpoline_sites').address
+ksft.print_msg(f'kcore: __retpoline_sites: 0x{retpolines_start_kcore:x}')
+
+x86_indirect_its_thunk_r15 = prog.symbol('__x86_indirect_its_thunk_r15').address
+ksft.print_msg(f'kcore: __x86_indirect_its_thunk_r15: 0x{x86_indirect_its_thunk_r15:x}')
+
+tests_passed = 0
+tests_failed = 0
+tests_unknown = 0
+
+with open(vmlinux, 'rb') as f:
+ elffile = ELFFile(f)
+ text_section = elffile.get_section_by_name('.text')
+
+ for i in range(0, len(sites_offset)):
+ site = retpolines_start_kcore + sites_offset[i]
+ vmlinux_site = retpolines_start_vmlinux + sites_offset[i]
+ passed = unknown = failed = False
+ try:
+ vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site)
+ kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0]
+ operand = kcore_insn.op_str
+ insn_end = site + kcore_insn.size - 1 # TODO handle Jcc.32 __x86_indirect_thunk_\reg
+ safe_site = insn_end & 0x20
+ site_status = "" if safe_site else "(unsafe)"
+
+ ksft.print_msg(f"\nSite {i}: {identify_address(prog, site)} <0x{site:x}> {site_status}")
+ ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}")
+ ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}")
+
+ if (site & 0x20) ^ (insn_end & 0x20):
+ ksft.print_msg(f"\tSite at safe/unsafe boundary: {str(kcore_insn.bytes)} {kcore_insn.mnemonic} {operand}")
+ if safe_site:
+ tests_passed += 1
+ passed = True
+ ksft.print_msg(f"\tPASSED: At safe address")
+ continue
+
+ if operand.startswith('0xffffffff'):
+ thunk = int(operand, 16)
+ if thunk > x86_indirect_its_thunk_r15:
+ insn_at_thunk = list(cap.disasm(prog.read(thunk, 16), thunk))[0]
+ operand += ' -> ' + insn_at_thunk.mnemonic + ' ' + insn_at_thunk.op_str + ' <dynamic-thunk?>'
+ if 'jmp' in insn_at_thunk.mnemonic and thunk & 0x20:
+ ksft.print_msg(f"\tPASSED: Found {operand} at safe address")
+ passed = True
+ if not passed:
+ if kcore_insn.operands[0].type == capstone.CS_OP_IMM:
+ operand += ' <' + prog.symbol(int(operand, 16)) + '>'
+ if '__x86_indirect_its_thunk_' in operand:
+ ksft.print_msg(f"\tPASSED: Found {operand}")
+ else:
+ ksft.print_msg(f"\tPASSED: Found direct branch: {kcore_insn}, ITS thunk not required.")
+ passed = True
+ else:
+ unknown = True
+ if passed:
+ tests_passed += 1
+ elif unknown:
+ ksft.print_msg(f"UNKNOWN: unexpected operand: {kcore_insn}")
+ tests_unknown += 1
+ else:
+ ksft.print_msg(f'\t************* FAILED *************')
+ ksft.print_msg(f"\tFound {kcore_insn.bytes} {kcore_insn.mnemonic} {operand}")
+ ksft.print_msg(f'\t**********************************')
+ tests_failed += 1
+ except Exception as e:
+ ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}")
+ tests_unknown += 1
+
+ksft.print_msg(f"\n\nSummary:")
+ksft.print_msg(f"PASS: \t{tests_passed} \t/ {total_retpoline_tests}")
+ksft.print_msg(f"FAIL: \t{tests_failed} \t/ {total_retpoline_tests}")
+ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_retpoline_tests}")
+
+if tests_failed == 0:
+ ksft.test_result_pass("All ITS return thunk sites passed")
+else:
+ ksft.test_result_fail(f"{tests_failed} ITS return thunk sites failed")
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_permutations.py b/tools/testing/selftests/x86/bugs/its_permutations.py
new file mode 100755
index 0000000..3204f47
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_permutations.py
@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) cmdline permutations with other bugs
+# like spectre_v2 and retbleed.
+
+import os, sys, subprocess, itertools, re, shutil
+
+test_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, test_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+mitigation = c.get_sysfs(bug)
+
+if not mitigation or "Not affected" in mitigation:
+ ksft.test_result_skip("Skipping its_permutations.py: not applicable")
+ ksft.finished()
+
+if shutil.which('vng') is None:
+ ksft.test_result_skip("Skipping its_permutations.py: virtme-ng ('vng') not found in PATH.")
+ ksft.finished()
+
+TEST = f"{test_dir}/its_sysfs.py"
+default_kparam = ['clearcpuid=hypervisor', 'panic=5', 'panic_on_warn=1', 'oops=panic', 'nmi_watchdog=1', 'hung_task_panic=1']
+
+DEBUG = " -v "
+
+# Install dependencies
+# https://github.com/arighi/virtme-ng
+# apt install virtme-ng
+BOOT_CMD = f"vng --run {test_dir}/../../../../../arch/x86/boot/bzImage "
+#BOOT_CMD += DEBUG
+
+bug = "indirect_target_selection"
+
+input_options = {
+ 'indirect_target_selection' : ['off', 'on', 'stuff', 'vmexit'],
+ 'retbleed' : ['off', 'stuff', 'auto'],
+ 'spectre_v2' : ['off', 'on', 'eibrs', 'retpoline', 'ibrs', 'eibrs,retpoline'],
+}
+
+def pretty_print(output):
+ OKBLUE = '\033[94m'
+ OKGREEN = '\033[92m'
+ WARNING = '\033[93m'
+ FAIL = '\033[91m'
+ ENDC = '\033[0m'
+ BOLD = '\033[1m'
+
+ # Define patterns and their corresponding colors
+ patterns = {
+ r"^ok \d+": OKGREEN,
+ r"^not ok \d+": FAIL,
+ r"^# Testing .*": OKBLUE,
+ r"^# Found: .*": WARNING,
+ r"^# Totals: .*": BOLD,
+ r"pass:([1-9]\d*)": OKGREEN,
+ r"fail:([1-9]\d*)": FAIL,
+ r"skip:([1-9]\d*)": WARNING,
+ }
+
+ # Apply colors based on patterns
+ for pattern, color in patterns.items():
+ output = re.sub(pattern, lambda match: f"{color}{match.group(0)}{ENDC}", output, flags=re.MULTILINE)
+
+ print(output)
+
+combinations = list(itertools.product(*input_options.values()))
+ksft.print_header()
+ksft.set_plan(len(combinations))
+
+logs = ""
+
+for combination in combinations:
+ append = ""
+ log = ""
+ for p in default_kparam:
+ append += f' --append={p}'
+ command = BOOT_CMD + append
+ test_params = ""
+ for i, key in enumerate(input_options.keys()):
+ param = f'{key}={combination[i]}'
+ test_params += f' {param}'
+ command += f" --append={param}"
+ command += f" -- {TEST}"
+ test_name = f"{bug} {test_params}"
+ pretty_print(f'# Testing {test_name}')
+ t = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+ t.wait()
+ output, _ = t.communicate()
+ if t.returncode == 0:
+ ksft.test_result_pass(test_name)
+ else:
+ ksft.test_result_fail(test_name)
+ output = output.decode()
+ log += f" {output}"
+ pretty_print(log)
+ logs += output + "\n"
+
+# Optionally use tappy to parse the output
+# apt install python3-tappy
+with open("logs.txt", "w") as f:
+ f.write(logs)
+
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_ret_alignment.py b/tools/testing/selftests/x86/bugs/its_ret_alignment.py
new file mode 100755
index 0000000..f40078d
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_ret_alignment.py
@@ -0,0 +1,139 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) mitigation.
+#
+# Tests if the RETs are correctly patched by evaluating the
+# vmlinux .return_sites in /proc/kcore.
+#
+# Install dependencies
+# add-apt-repository ppa:michel-slm/kernel-utils
+# apt update
+# apt install -y python3-drgn python3-pyelftools python3-capstone
+#
+# Run on target machine
+# mkdir -p /usr/lib/debug/lib/modules/$(uname -r)
+# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux
+#
+# Usage: ./its_ret_alignment.py
+
+import os, sys, argparse
+from pathlib import Path
+
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+mitigation = c.get_sysfs(bug)
+if not mitigation or "Aligned branch/return thunks" not in mitigation:
+ ksft.test_result_skip("Skipping its_ret_alignment.py: Aligned branch/return thunks not enabled")
+ ksft.finished()
+
+c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_ret_alignment.py")
+
+from elftools.elf.elffile import ELFFile
+from drgn.helpers.common.memory import identify_address
+
+cap = c.init_capstone()
+
+if len(os.sys.argv) > 1:
+ arg_vmlinux = os.sys.argv[1]
+ if not os.path.exists(arg_vmlinux):
+ ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at user-supplied path: {arg_vmlinux}")
+ ksft.exit_fail()
+ os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True)
+ os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux')
+
+vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux"
+if not os.path.exists(vmlinux):
+ ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at {vmlinux}")
+ ksft.exit_fail()
+
+ksft.print_msg(f"Using vmlinux: {vmlinux}")
+
+rethunks_start_vmlinux, rethunks_sec_offset, size = c.get_section_info(vmlinux, '.return_sites')
+ksft.print_msg(f"vmlinux: Section .return_sites (0x{rethunks_start_vmlinux:x}) found at 0x{rethunks_sec_offset:x} with size 0x{size:x}")
+
+sites_offset = c.get_patch_sites(vmlinux, rethunks_sec_offset, size)
+total_rethunk_tests = len(sites_offset)
+ksft.print_msg(f"Found {total_rethunk_tests} rethunk sites")
+
+prog = c.get_runtime_kernel()
+rethunks_start_kcore = prog.symbol('__return_sites').address
+ksft.print_msg(f'kcore: __rethunk_sites: 0x{rethunks_start_kcore:x}')
+
+its_return_thunk = prog.symbol('its_return_thunk').address
+ksft.print_msg(f'kcore: its_return_thunk: 0x{its_return_thunk:x}')
+
+tests_passed = 0
+tests_failed = 0
+tests_unknown = 0
+tests_skipped = 0
+
+with open(vmlinux, 'rb') as f:
+ elffile = ELFFile(f)
+ text_section = elffile.get_section_by_name('.text')
+
+ for i in range(len(sites_offset)):
+ site = rethunks_start_kcore + sites_offset[i]
+ vmlinux_site = rethunks_start_vmlinux + sites_offset[i]
+ try:
+ passed = unknown = failed = skipped = False
+
+ symbol = identify_address(prog, site)
+ vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site)
+ kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0]
+
+ insn_end = site + kcore_insn.size - 1
+
+ safe_site = insn_end & 0x20
+ site_status = "" if safe_site else "(unsafe)"
+
+ ksft.print_msg(f"\nSite {i}: {symbol} <0x{site:x}> {site_status}")
+ ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}")
+ ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}")
+
+ if safe_site:
+ tests_passed += 1
+ passed = True
+ ksft.print_msg(f"\tPASSED: At safe address")
+ continue
+
+ if "jmp" in kcore_insn.mnemonic:
+ passed = True
+ elif "ret" not in kcore_insn.mnemonic:
+ skipped = True
+
+ if passed:
+ ksft.print_msg(f"\tPASSED: Found {kcore_insn.mnemonic} {kcore_insn.op_str}")
+ tests_passed += 1
+ elif skipped:
+ ksft.print_msg(f"\tSKIPPED: Found '{kcore_insn.mnemonic}'")
+ tests_skipped += 1
+ elif unknown:
+ ksft.print_msg(f"UNKNOWN: An unknown instruction: {kcore_insn}")
+ tests_unknown += 1
+ else:
+ ksft.print_msg(f'\t************* FAILED *************')
+ ksft.print_msg(f"\tFound {kcore_insn.mnemonic} {kcore_insn.op_str}")
+ ksft.print_msg(f'\t**********************************')
+ tests_failed += 1
+ except Exception as e:
+ ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}")
+ tests_unknown += 1
+
+ksft.print_msg(f"\n\nSummary:")
+ksft.print_msg(f"PASSED: \t{tests_passed} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"FAILED: \t{tests_failed} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"SKIPPED: \t{tests_skipped} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_rethunk_tests}")
+
+if tests_failed == 0:
+ ksft.test_result_pass("All ITS return thunk sites passed.")
+else:
+ ksft.test_result_fail(f"{tests_failed} failed sites need ITS return thunks.")
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_sysfs.py b/tools/testing/selftests/x86/bugs/its_sysfs.py
new file mode 100755
index 0000000..7bca81f
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_sysfs.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for Indirect Target Selection(ITS) mitigation sysfs status.
+
+import sys, os, re
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+
+from common import *
+
+bug = "indirect_target_selection"
+mitigation = get_sysfs(bug)
+
+ITS_MITIGATION_ALIGNED_THUNKS = "Mitigation: Aligned branch/return thunks"
+ITS_MITIGATION_RETPOLINE_STUFF = "Mitigation: Retpolines, Stuffing RSB"
+ITS_MITIGATION_VMEXIT_ONLY = "Mitigation: Vulnerable, KVM: Not affected"
+ITS_MITIGATION_VULNERABLE = "Vulnerable"
+
+def check_mitigation():
+ if mitigation == ITS_MITIGATION_ALIGNED_THUNKS:
+ if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"):
+ bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_RETPOLINE_STUFF)
+ return
+ if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'):
+ bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_VMEXIT_ONLY)
+ return
+ bug_check_pass(bug, ITS_MITIGATION_ALIGNED_THUNKS)
+ return
+
+ if mitigation == ITS_MITIGATION_RETPOLINE_STUFF:
+ if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"):
+ bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF)
+ return
+ if sysfs_has('retbleed', 'Stuffing'):
+ bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF)
+ return
+ bug_check_fail(bug, ITS_MITIGATION_RETPOLINE_STUFF, ITS_MITIGATION_ALIGNED_THUNKS)
+
+ if mitigation == ITS_MITIGATION_VMEXIT_ONLY:
+ if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'):
+ bug_check_pass(bug, ITS_MITIGATION_VMEXIT_ONLY)
+ return
+ bug_check_fail(bug, ITS_MITIGATION_VMEXIT_ONLY, ITS_MITIGATION_ALIGNED_THUNKS)
+
+ if mitigation == ITS_MITIGATION_VULNERABLE:
+ if sysfs_has("spectre_v2", "Vulnerable"):
+ bug_check_pass(bug, ITS_MITIGATION_VULNERABLE)
+ else:
+ bug_check_fail(bug, "Mitigation", ITS_MITIGATION_VULNERABLE)
+
+ bug_status_unknown(bug, mitigation)
+ return
+
+ksft.print_header()
+ksft.set_plan(1)
+ksft.print_msg(f'{bug}: {mitigation} ...')
+
+if not basic_checks_sufficient(bug, mitigation):
+ check_mitigation()
+
+ksft.finished()
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index d0f6d25..6135511 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -1264,21 +1264,25 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type)
send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
control_expectln("RECEIVED");
- ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
- if (ret < 0) {
- if (errno == EOPNOTSUPP) {
- fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
- } else {
+ /* SIOCOUTQ isn't guaranteed to instantly track sent data. Even though
+ * the "RECEIVED" message means that the other side has received the
+ * data, there can be a delay in our kernel before updating the "unsent
+ * bytes" counter. Repeat SIOCOUTQ until it returns 0.
+ */
+ timeout_begin(TIMEOUT);
+ do {
+ ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+ if (ret < 0) {
+ if (errno == EOPNOTSUPP) {
+ fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+ break;
+ }
perror("ioctl");
exit(EXIT_FAILURE);
}
- } else if (ret == 0 && sock_bytes_unsent != 0) {
- fprintf(stderr,
- "Unexpected 'SIOCOUTQ' value, expected 0, got %i\n",
- sock_bytes_unsent);
- exit(EXIT_FAILURE);
- }
-
+ timeout_check("SIOCOUTQ");
+ } while (sock_bytes_unsent != 0);
+ timeout_end();
close(fd);
}
diff --git a/usr/include/Makefile b/usr/include/Makefile
index e3d6b03..f02f419 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -59,6 +59,10 @@
no-header-test += linux/bpf_perf_event.h
endif
+ifeq ($(SRCARCH),openrisc)
+no-header-test += linux/bpf_perf_event.h
+endif
+
ifeq ($(SRCARCH),powerpc)
no-header-test += linux/bpf_perf_event.h
endif
