diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
index 86ad617..5ff9cf2 100644
--- a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
@@ -43,9 +43,13 @@
         - enum:
           - allwinner,sun8i-h3-tcon-tv
           - allwinner,sun50i-a64-tcon-tv
-          - allwinner,sun50i-h6-tcon-tv
         - const: allwinner,sun8i-a83t-tcon-tv
 
+      - items:
+        - enum:
+          - allwinner,sun50i-h6-tcon-tv
+        - const: allwinner,sun8i-r40-tcon-tv
+
   reg:
     maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt b/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt
index dc194b2..cdcaa3f 100644
--- a/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt
+++ b/Documentation/devicetree/bindings/input/ilitek,ili2xxx.txt
@@ -1,9 +1,10 @@
-Ilitek ILI210x/ILI2117/ILI251x touchscreen controller
+Ilitek ILI210x/ILI2117/ILI2120/ILI251x touchscreen controller
 
 Required properties:
 - compatible:
     ilitek,ili210x for ILI210x
     ilitek,ili2117 for ILI2117
+    ilitek,ili2120 for ILI2120
     ilitek,ili251x for ILI251x
 
 - reg: The I2C address of the device
diff --git a/Documentation/driver-api/ipmb.rst b/Documentation/driver-api/ipmb.rst
index 3ec3bae..209c49e 100644
--- a/Documentation/driver-api/ipmb.rst
+++ b/Documentation/driver-api/ipmb.rst
@@ -71,9 +71,13 @@
             ipmb@10 {
                     compatible = "ipmb-dev";
                     reg = <0x10>;
+                    i2c-protocol;
             };
      };
 
+If xmit of data to be done using raw i2c block vs smbus
+then "i2c-protocol" needs to be defined as above.
+
 2) Manually from Linux::
 
      modprobe ipmb-dev-int
diff --git a/Documentation/virtual/guest-halt-polling.txt b/Documentation/virt/guest-halt-polling.rst
similarity index 90%
rename from Documentation/virtual/guest-halt-polling.txt
rename to Documentation/virt/guest-halt-polling.rst
index b3a2a29..b4e7479 100644
--- a/Documentation/virtual/guest-halt-polling.txt
+++ b/Documentation/virt/guest-halt-polling.rst
@@ -1,9 +1,11 @@
+==================
 Guest halt polling
 ==================
 
 The cpuidle_haltpoll driver, with the haltpoll governor, allows
 the guest vcpus to poll for a specified amount of time before
 halting.
+
 This provides the following benefits to host side polling:
 
 	1) The POLL flag is set while polling is performed, which allows
@@ -29,18 +31,21 @@
 The haltpoll governor has 5 tunable module parameters:
 
 1) guest_halt_poll_ns:
+
 Maximum amount of time, in nanoseconds, that polling is
 performed before halting.
 
 Default: 200000
 
 2) guest_halt_poll_shrink:
+
 Division factor used to shrink per-cpu guest_halt_poll_ns when
 wakeup event occurs after the global guest_halt_poll_ns.
 
 Default: 2
 
 3) guest_halt_poll_grow:
+
 Multiplication factor used to grow per-cpu guest_halt_poll_ns
 when event occurs after per-cpu guest_halt_poll_ns
 but before global guest_halt_poll_ns.
@@ -48,6 +53,7 @@
 Default: 2
 
 4) guest_halt_poll_grow_start:
+
 The per-cpu guest_halt_poll_ns eventually reaches zero
 in case of an idle system. This value sets the initial
 per-cpu guest_halt_poll_ns when growing. This can
@@ -66,7 +72,7 @@
 
 Default: Y
 
-The module parameters can be set from the debugfs files in:
+The module parameters can be set from the debugfs files in::
 
 	/sys/module/haltpoll/parameters/
 
@@ -74,5 +80,5 @@
 =============
 
 - Care should be taken when setting the guest_halt_poll_ns parameter as a
-large value has the potential to drive the cpu usage to 100% on a machine which
-would be almost entirely idle otherwise.
+  large value has the potential to drive the cpu usage to 100% on a machine
+  which would be almost entirely idle otherwise.
diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst
index 062ffb5..de1ab81 100644
--- a/Documentation/virt/index.rst
+++ b/Documentation/virt/index.rst
@@ -8,7 +8,9 @@
    :maxdepth: 2
 
    kvm/index
+   uml/user_mode_linux
    paravirt_ops
+   guest-halt-polling
 
 .. only:: html and subproject
 
diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.rst
similarity index 71%
rename from Documentation/virt/kvm/api.txt
rename to Documentation/virt/kvm/api.rst
index c6e1ce5..97a72a5 100644
--- a/Documentation/virt/kvm/api.txt
+++ b/Documentation/virt/kvm/api.rst
@@ -1,8 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================================================
 The Definitive KVM (Kernel-based Virtual Machine) API Documentation
 ===================================================================
 
 1. General description
-----------------------
+======================
 
 The kvm API is a set of ioctls that are issued to control various aspects
 of a virtual machine.  The ioctls belong to the following classes:
@@ -33,7 +36,7 @@
    was used to create the VM.
 
 2. File descriptors
--------------------
+===================
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
@@ -70,7 +73,7 @@
 
 
 3. Extensions
--------------
+=============
 
 As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
 incompatible change are allowed.  However, there is an extension
@@ -84,13 +87,14 @@
 
 
 4. API description
-------------------
+==================
 
 This section describes ioctls that can be used to control kvm guests.
 For each ioctl, the following information is provided along with a
 description:
 
-  Capability: which KVM extension provides this ioctl.  Can be 'basic',
+  Capability:
+      which KVM extension provides this ioctl.  Can be 'basic',
       which means that is will be provided by any kernel that supports
       API version 12 (see section 4.1), a KVM_CAP_xyz constant, which
       means availability needs to be checked with KVM_CHECK_EXTENSION
@@ -99,24 +103,29 @@
       availability: for kernels that don't support the ioctl,
       the ioctl returns -ENOTTY.
 
-  Architectures: which instruction set architectures provide this ioctl.
+  Architectures:
+      which instruction set architectures provide this ioctl.
       x86 includes both i386 and x86_64.
 
-  Type: system, vm, or vcpu.
+  Type:
+      system, vm, or vcpu.
 
-  Parameters: what parameters are accepted by the ioctl.
+  Parameters:
+      what parameters are accepted by the ioctl.
 
-  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
+  Returns:
+      the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
       are not detailed, but errors with specific meanings are.
 
 
 4.1 KVM_GET_API_VERSION
+-----------------------
 
-Capability: basic
-Architectures: all
-Type: system ioctl
-Parameters: none
-Returns: the constant KVM_API_VERSION (=12)
+:Capability: basic
+:Architectures: all
+:Type: system ioctl
+:Parameters: none
+:Returns: the constant KVM_API_VERSION (=12)
 
 This identifies the API version as the stable kvm API. It is not
 expected that this number will change.  However, Linux 2.6.20 and
@@ -127,12 +136,13 @@
 
 
 4.2 KVM_CREATE_VM
+-----------------
 
-Capability: basic
-Architectures: all
-Type: system ioctl
-Parameters: machine type identifier (KVM_VM_*)
-Returns: a VM fd that can be used to control the new virtual machine.
+:Capability: basic
+:Architectures: all
+:Type: system ioctl
+:Parameters: machine type identifier (KVM_VM_*)
+:Returns: a VM fd that can be used to control the new virtual machine.
 
 The new VM has no virtual cpus and no memory.
 You probably want to use 0 as machine type.
@@ -155,17 +165,17 @@
 address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
 machine type identifier.
 
-e.g, to configure a guest to use 48bit physical address size :
+e.g, to configure a guest to use 48bit physical address size::
 
     vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48));
 
-The requested size (IPA_Bits) must be :
-  0 - Implies default size, 40bits (for backward compatibility)
+The requested size (IPA_Bits) must be:
 
-  or
-
-  N - Implies N bits, where N is a positive integer such that,
+ ==   =========================================================
+  0   Implies default size, 40bits (for backward compatibility)
+  N   Implies N bits, where N is a positive integer such that,
       32 <= N <= Host_IPA_Limit
+ ==   =========================================================
 
 Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and
 is dependent on the CPU capability and the kernel configuration. The limit can
@@ -179,21 +189,28 @@
 
 
 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
+----------------------------------------------------------
 
-Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
-Architectures: x86
-Type: system ioctl
-Parameters: struct kvm_msr_list (in/out)
-Returns: 0 on success; -1 on error
+:Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
+:Architectures: x86
+:Type: system ioctl
+:Parameters: struct kvm_msr_list (in/out)
+:Returns: 0 on success; -1 on error
+
 Errors:
-  EFAULT:    the msr index list cannot be read from or written to
-  E2BIG:     the msr index list is to be to fit in the array specified by
-             the user.
 
-struct kvm_msr_list {
+  ======     ============================================================
+  EFAULT     the msr index list cannot be read from or written to
+  E2BIG      the msr index list is to be to fit in the array specified by
+             the user.
+  ======     ============================================================
+
+::
+
+  struct kvm_msr_list {
 	__u32 nmsrs; /* number of msrs in entries */
 	__u32 indices[0];
-};
+  };
 
 The user fills in the size of the indices array in nmsrs, and in return
 kvm adjusts nmsrs to reflect the actual number of msrs and fills in the
@@ -214,12 +231,13 @@
 
 
 4.4 KVM_CHECK_EXTENSION
+-----------------------
 
-Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
-Architectures: all
-Type: system ioctl, vm ioctl
-Parameters: extension identifier (KVM_CAP_*)
-Returns: 0 if unsupported; 1 (or some other positive integer) if supported
+:Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
+:Architectures: all
+:Type: system ioctl, vm ioctl
+:Parameters: extension identifier (KVM_CAP_*)
+:Returns: 0 if unsupported; 1 (or some other positive integer) if supported
 
 The API allows the application to query about extensions to the core
 kvm API.  Userspace passes an extension identifier (an integer) and
@@ -232,12 +250,13 @@
 with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
 
 4.5 KVM_GET_VCPU_MMAP_SIZE
+--------------------------
 
-Capability: basic
-Architectures: all
-Type: system ioctl
-Parameters: none
-Returns: size of vcpu mmap area, in bytes
+:Capability: basic
+:Architectures: all
+:Type: system ioctl
+:Parameters: none
+:Returns: size of vcpu mmap area, in bytes
 
 The KVM_RUN ioctl (cf.) communicates with userspace via a shared
 memory region.  This ioctl returns the size of that region.  See the
@@ -245,23 +264,25 @@
 
 
 4.6 KVM_SET_MEMORY_REGION
+-------------------------
 
-Capability: basic
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_memory_region (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_memory_region (in)
+:Returns: 0 on success, -1 on error
 
 This ioctl is obsolete and has been removed.
 
 
 4.7 KVM_CREATE_VCPU
+-------------------
 
-Capability: basic
-Architectures: all
-Type: vm ioctl
-Parameters: vcpu id (apic id on x86)
-Returns: vcpu fd on success, -1 on error
+:Capability: basic
+:Architectures: all
+:Type: vm ioctl
+:Parameters: vcpu id (apic id on x86)
+:Returns: vcpu fd on success, -1 on error
 
 This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
 The vcpu id is an integer in the range [0, max_vcpu_id).
@@ -302,22 +323,25 @@
 
 
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
+--------------------------------
 
-Capability: basic
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_dirty_log (in/out)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_dirty_log (in/out)
+:Returns: 0 on success, -1 on error
 
-/* for KVM_GET_DIRTY_LOG */
-struct kvm_dirty_log {
+::
+
+  /* for KVM_GET_DIRTY_LOG */
+  struct kvm_dirty_log {
 	__u32 slot;
 	__u32 padding;
 	union {
 		void __user *dirty_bitmap; /* one bit per page */
 		__u64 padding;
 	};
-};
+  };
 
 Given a memory slot, return a bitmap containing any pages dirtied
 since the last call to this ioctl.  Bit 0 is the first page in the
@@ -334,25 +358,31 @@
 see the description of the capability.
 
 4.9 KVM_SET_MEMORY_ALIAS
+------------------------
 
-Capability: basic
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_memory_alias (in)
-Returns: 0 (success), -1 (error)
+:Capability: basic
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_memory_alias (in)
+:Returns: 0 (success), -1 (error)
 
 This ioctl is obsolete and has been removed.
 
 
 4.10 KVM_RUN
+------------
 
-Capability: basic
-Architectures: all
-Type: vcpu ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: all
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0 on success, -1 on error
+
 Errors:
-  EINTR:     an unmasked signal is pending
+
+  =====      =============================
+  EINTR      an unmasked signal is pending
+  =====      =============================
 
 This ioctl is used to run a guest virtual cpu.  While there are no
 explicit parameters, there is an implicit parameter block that can be
@@ -362,42 +392,46 @@
 
 
 4.11 KVM_GET_REGS
+-----------------
 
-Capability: basic
-Architectures: all except ARM, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_regs (out)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: all except ARM, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_regs (out)
+:Returns: 0 on success, -1 on error
 
 Reads the general purpose registers from the vcpu.
 
-/* x86 */
-struct kvm_regs {
+::
+
+  /* x86 */
+  struct kvm_regs {
 	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
 	__u64 rax, rbx, rcx, rdx;
 	__u64 rsi, rdi, rsp, rbp;
 	__u64 r8,  r9,  r10, r11;
 	__u64 r12, r13, r14, r15;
 	__u64 rip, rflags;
-};
+  };
 
-/* mips */
-struct kvm_regs {
+  /* mips */
+  struct kvm_regs {
 	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
 	__u64 gpr[32];
 	__u64 hi;
 	__u64 lo;
 	__u64 pc;
-};
+  };
 
 
 4.12 KVM_SET_REGS
+-----------------
 
-Capability: basic
-Architectures: all except ARM, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_regs (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: all except ARM, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_regs (in)
+:Returns: 0 on success, -1 on error
 
 Writes the general purpose registers into the vcpu.
 
@@ -405,17 +439,20 @@
 
 
 4.13 KVM_GET_SREGS
+------------------
 
-Capability: basic
-Architectures: x86, ppc
-Type: vcpu ioctl
-Parameters: struct kvm_sregs (out)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: x86, ppc
+:Type: vcpu ioctl
+:Parameters: struct kvm_sregs (out)
+:Returns: 0 on success, -1 on error
 
 Reads special registers from the vcpu.
 
-/* x86 */
-struct kvm_sregs {
+::
+
+  /* x86 */
+  struct kvm_sregs {
 	struct kvm_segment cs, ds, es, fs, gs, ss;
 	struct kvm_segment tr, ldt;
 	struct kvm_dtable gdt, idt;
@@ -423,9 +460,9 @@
 	__u64 efer;
 	__u64 apic_base;
 	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
-};
+  };
 
-/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
+  /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
 
 interrupt_bitmap is a bitmap of pending external interrupts.  At most
 one bit may be set.  This interrupt has been acknowledged by the APIC
@@ -433,29 +470,33 @@
 
 
 4.14 KVM_SET_SREGS
+------------------
 
-Capability: basic
-Architectures: x86, ppc
-Type: vcpu ioctl
-Parameters: struct kvm_sregs (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: x86, ppc
+:Type: vcpu ioctl
+:Parameters: struct kvm_sregs (in)
+:Returns: 0 on success, -1 on error
 
 Writes special registers into the vcpu.  See KVM_GET_SREGS for the
 data structures.
 
 
 4.15 KVM_TRANSLATE
+------------------
 
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_translation (in/out)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_translation (in/out)
+:Returns: 0 on success, -1 on error
 
 Translates a virtual address according to the vcpu's current address
 translation mode.
 
-struct kvm_translation {
+::
+
+  struct kvm_translation {
 	/* in */
 	__u64 linear_address;
 
@@ -465,59 +506,68 @@
 	__u8  writeable;
 	__u8  usermode;
 	__u8  pad[5];
-};
+  };
 
 
 4.16 KVM_INTERRUPT
+------------------
 
-Capability: basic
-Architectures: x86, ppc, mips
-Type: vcpu ioctl
-Parameters: struct kvm_interrupt (in)
-Returns: 0 on success, negative on failure.
+:Capability: basic
+:Architectures: x86, ppc, mips
+:Type: vcpu ioctl
+:Parameters: struct kvm_interrupt (in)
+:Returns: 0 on success, negative on failure.
 
 Queues a hardware interrupt vector to be injected.
 
-/* for KVM_INTERRUPT */
-struct kvm_interrupt {
+::
+
+  /* for KVM_INTERRUPT */
+  struct kvm_interrupt {
 	/* in */
 	__u32 irq;
-};
+  };
 
 X86:
+^^^^
 
-Returns: 0 on success,
-	 -EEXIST if an interrupt is already enqueued
-	 -EINVAL the the irq number is invalid
-	 -ENXIO if the PIC is in the kernel
-	 -EFAULT if the pointer is invalid
+:Returns:
+
+	========= ===================================
+	  0       on success,
+	 -EEXIST  if an interrupt is already enqueued
+	 -EINVAL  the the irq number is invalid
+	 -ENXIO   if the PIC is in the kernel
+	 -EFAULT  if the pointer is invalid
+	========= ===================================
 
 Note 'irq' is an interrupt vector, not an interrupt pin or line. This
 ioctl is useful if the in-kernel PIC is not used.
 
 PPC:
+^^^^
 
 Queues an external interrupt to be injected. This ioctl is overleaded
 with 3 different irq values:
 
 a) KVM_INTERRUPT_SET
 
-  This injects an edge type external interrupt into the guest once it's ready
-  to receive interrupts. When injected, the interrupt is done.
+   This injects an edge type external interrupt into the guest once it's ready
+   to receive interrupts. When injected, the interrupt is done.
 
 b) KVM_INTERRUPT_UNSET
 
-  This unsets any pending interrupt.
+   This unsets any pending interrupt.
 
-  Only available with KVM_CAP_PPC_UNSET_IRQ.
+   Only available with KVM_CAP_PPC_UNSET_IRQ.
 
 c) KVM_INTERRUPT_SET_LEVEL
 
-  This injects a level type external interrupt into the guest context. The
-  interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
-  is triggered.
+   This injects a level type external interrupt into the guest context. The
+   interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
+   is triggered.
 
-  Only available with KVM_CAP_PPC_IRQ_LEVEL.
+   Only available with KVM_CAP_PPC_IRQ_LEVEL.
 
 Note that any value for 'irq' other than the ones stated above is invalid
 and incurs unexpected behavior.
@@ -525,6 +575,7 @@
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 MIPS:
+^^^^^
 
 Queues an external interrupt to be injected into the virtual CPU. A negative
 interrupt number dequeues the interrupt.
@@ -533,24 +584,26 @@
 
 
 4.17 KVM_DEBUG_GUEST
+--------------------
 
-Capability: basic
-Architectures: none
-Type: vcpu ioctl
-Parameters: none)
-Returns: -1 on error
+:Capability: basic
+:Architectures: none
+:Type: vcpu ioctl
+:Parameters: none)
+:Returns: -1 on error
 
 Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
 
 
 4.18 KVM_GET_MSRS
+-----------------
 
-Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
-Architectures: x86
-Type: system ioctl, vcpu ioctl
-Parameters: struct kvm_msrs (in/out)
-Returns: number of msrs successfully returned;
-        -1 on error
+:Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
+:Architectures: x86
+:Type: system ioctl, vcpu ioctl
+:Parameters: struct kvm_msrs (in/out)
+:Returns: number of msrs successfully returned;
+          -1 on error
 
 When used as a system ioctl:
 Reads the values of MSR-based features that are available for the VM.  This
@@ -562,18 +615,20 @@
 Reads model-specific registers from the vcpu.  Supported msr indices can
 be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl.
 
-struct kvm_msrs {
+::
+
+  struct kvm_msrs {
 	__u32 nmsrs; /* number of msrs in entries */
 	__u32 pad;
 
 	struct kvm_msr_entry entries[0];
-};
+  };
 
-struct kvm_msr_entry {
+  struct kvm_msr_entry {
 	__u32 index;
 	__u32 reserved;
 	__u64 data;
-};
+  };
 
 Application code should set the 'nmsrs' member (which indicates the
 size of the entries array) and the 'index' member of each array entry.
@@ -581,12 +636,13 @@
 
 
 4.19 KVM_SET_MSRS
+-----------------
 
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_msrs (in)
-Returns: number of msrs successfully set (see below), -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_msrs (in)
+:Returns: number of msrs successfully set (see below), -1 on error
 
 Writes model-specific registers to the vcpu.  See KVM_GET_MSRS for the
 data structures.
@@ -602,41 +658,44 @@
 
 
 4.20 KVM_SET_CPUID
+------------------
 
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_cpuid (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_cpuid (in)
+:Returns: 0 on success, -1 on error
 
 Defines the vcpu responses to the cpuid instruction.  Applications
 should use the KVM_SET_CPUID2 ioctl if available.
 
+::
 
-struct kvm_cpuid_entry {
+  struct kvm_cpuid_entry {
 	__u32 function;
 	__u32 eax;
 	__u32 ebx;
 	__u32 ecx;
 	__u32 edx;
 	__u32 padding;
-};
+  };
 
-/* for KVM_SET_CPUID */
-struct kvm_cpuid {
+  /* for KVM_SET_CPUID */
+  struct kvm_cpuid {
 	__u32 nent;
 	__u32 padding;
 	struct kvm_cpuid_entry entries[0];
-};
+  };
 
 
 4.21 KVM_SET_SIGNAL_MASK
+------------------------
 
-Capability: basic
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_signal_mask (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: all
+:Type: vcpu ioctl
+:Parameters: struct kvm_signal_mask (in)
+:Returns: 0 on success, -1 on error
 
 Defines which signals are blocked during execution of KVM_RUN.  This
 signal mask temporarily overrides the threads signal mask.  Any
@@ -646,25 +705,30 @@
 Note the signal will only be delivered if not blocked by the original
 signal mask.
 
-/* for KVM_SET_SIGNAL_MASK */
-struct kvm_signal_mask {
+::
+
+  /* for KVM_SET_SIGNAL_MASK */
+  struct kvm_signal_mask {
 	__u32 len;
 	__u8  sigset[0];
-};
+  };
 
 
 4.22 KVM_GET_FPU
+----------------
 
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_fpu (out)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_fpu (out)
+:Returns: 0 on success, -1 on error
 
 Reads the floating point state from the vcpu.
 
-/* for KVM_GET_FPU and KVM_SET_FPU */
-struct kvm_fpu {
+::
+
+  /* for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
 	__u16 fsw;
@@ -676,21 +740,24 @@
 	__u8  xmm[16][16];
 	__u32 mxcsr;
 	__u32 pad2;
-};
+  };
 
 
 4.23 KVM_SET_FPU
+----------------
 
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_fpu (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_fpu (in)
+:Returns: 0 on success, -1 on error
 
 Writes the floating point state to the vcpu.
 
-/* for KVM_GET_FPU and KVM_SET_FPU */
-struct kvm_fpu {
+::
+
+  /* for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
 	__u16 fsw;
@@ -702,16 +769,17 @@
 	__u8  xmm[16][16];
 	__u32 mxcsr;
 	__u32 pad2;
-};
+  };
 
 
 4.24 KVM_CREATE_IRQCHIP
+-----------------------
 
-Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
-Architectures: x86, ARM, arm64, s390
-Type: vm ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
+:Architectures: x86, ARM, arm64, s390
+:Type: vm ioctl
+:Parameters: none
+:Returns: 0 on success, -1 on error
 
 Creates an interrupt controller model in the kernel.
 On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
@@ -727,12 +795,13 @@
 
 
 4.25 KVM_IRQ_LINE
+-----------------
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86, arm, arm64
-Type: vm ioctl
-Parameters: struct kvm_irq_level
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQCHIP
+:Architectures: x86, arm, arm64
+:Type: vm ioctl
+:Parameters: struct kvm_irq_level
+:Returns: 0 on success, -1 on error
 
 Sets the level of a GSI input to the interrupt controller model in the kernel.
 On some architectures it is required that an interrupt controller model has
@@ -756,16 +825,20 @@
 ARM/arm64 can signal an interrupt either at the CPU level, or at the
 in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
 use PPIs designated for specific cpus.  The irq field is interpreted
-like this:
+like this::
 
   bits:  |  31 ... 28  | 27 ... 24 | 23  ... 16 | 15 ... 0 |
   field: | vcpu2_index | irq_type  | vcpu_index |  irq_id  |
 
 The irq_type field has the following values:
-- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
-- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
+
+- irq_type[0]:
+	       out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
+- irq_type[1]:
+	       in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
                (the vcpu_index field is ignored)
-- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
+- irq_type[2]:
+	       in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
 
 (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
 
@@ -779,27 +852,32 @@
 injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always
 be used for a userspace interrupt controller.
 
-struct kvm_irq_level {
+::
+
+  struct kvm_irq_level {
 	union {
 		__u32 irq;     /* GSI */
 		__s32 status;  /* not used for KVM_IRQ_LEVEL */
 	};
 	__u32 level;           /* 0 or 1 */
-};
+  };
 
 
 4.26 KVM_GET_IRQCHIP
+--------------------
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_irqchip (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQCHIP
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_irqchip (in/out)
+:Returns: 0 on success, -1 on error
 
 Reads the state of a kernel interrupt controller created with
 KVM_CREATE_IRQCHIP into a buffer provided by the caller.
 
-struct kvm_irqchip {
+::
+
+  struct kvm_irqchip {
 	__u32 chip_id;  /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
 	__u32 pad;
         union {
@@ -807,21 +885,24 @@
 		struct kvm_pic_state pic;
 		struct kvm_ioapic_state ioapic;
 	} chip;
-};
+  };
 
 
 4.27 KVM_SET_IRQCHIP
+--------------------
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_irqchip (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQCHIP
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_irqchip (in)
+:Returns: 0 on success, -1 on error
 
 Sets the state of a kernel interrupt controller created with
 KVM_CREATE_IRQCHIP from a buffer provided by the caller.
 
-struct kvm_irqchip {
+::
+
+  struct kvm_irqchip {
 	__u32 chip_id;  /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
 	__u32 pad;
         union {
@@ -829,16 +910,17 @@
 		struct kvm_pic_state pic;
 		struct kvm_ioapic_state ioapic;
 	} chip;
-};
+  };
 
 
 4.28 KVM_XEN_HVM_CONFIG
+-----------------------
 
-Capability: KVM_CAP_XEN_HVM
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_xen_hvm_config (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_XEN_HVM
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_xen_hvm_config (in)
+:Returns: 0 on success, -1 on error
 
 Sets the MSR that the Xen HVM guest uses to initialize its hypercall
 page, and provides the starting address and size of the hypercall
@@ -846,7 +928,9 @@
 page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
 memory.
 
-struct kvm_xen_hvm_config {
+::
+
+  struct kvm_xen_hvm_config {
 	__u32 flags;
 	__u32 msr;
 	__u64 blob_addr_32;
@@ -854,16 +938,17 @@
 	__u8 blob_size_32;
 	__u8 blob_size_64;
 	__u8 pad2[30];
-};
+  };
 
 
 4.29 KVM_GET_CLOCK
+------------------
 
-Capability: KVM_CAP_ADJUST_CLOCK
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_clock_data (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_ADJUST_CLOCK
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_clock_data (out)
+:Returns: 0 on success, -1 on error
 
 Gets the current timestamp of kvmclock as seen by the current guest. In
 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
@@ -880,47 +965,56 @@
 but the exact value read by each VCPU could differ, because the host
 TSC is not stable.
 
-struct kvm_clock_data {
+::
+
+  struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;
 	__u32 pad[9];
-};
+  };
 
 
 4.30 KVM_SET_CLOCK
+------------------
 
-Capability: KVM_CAP_ADJUST_CLOCK
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_clock_data (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_ADJUST_CLOCK
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_clock_data (in)
+:Returns: 0 on success, -1 on error
 
 Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
-struct kvm_clock_data {
+::
+
+  struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;
 	__u32 pad[9];
-};
+  };
 
 
 4.31 KVM_GET_VCPU_EVENTS
+------------------------
 
-Capability: KVM_CAP_VCPU_EVENTS
-Extended by: KVM_CAP_INTR_SHADOW
-Architectures: x86, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_vcpu_event (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_VCPU_EVENTS
+:Extended by: KVM_CAP_INTR_SHADOW
+:Architectures: x86, arm, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_vcpu_event (out)
+:Returns: 0 on success, -1 on error
 
 X86:
+^^^^
 
 Gets currently pending exceptions, interrupts, and NMIs as well as related
 states of the vcpu.
 
-struct kvm_vcpu_events {
+::
+
+  struct kvm_vcpu_events {
 	struct {
 		__u8 injected;
 		__u8 nr;
@@ -951,7 +1045,7 @@
 	__u8 reserved[27];
 	__u8 exception_has_payload;
 	__u64 exception_payload;
-};
+  };
 
 The following bits are defined in the flags field:
 
@@ -967,6 +1061,7 @@
   KVM_CAP_EXCEPTION_PAYLOAD is enabled.
 
 ARM/ARM64:
+^^^^^^^^^^
 
 If the guest accesses a device that is being emulated by the host kernel in
 such a way that a real device would generate a physical SError, KVM may make
@@ -1006,8 +1101,9 @@
 KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered
 directly to the virtual CPU).
 
+::
 
-struct kvm_vcpu_events {
+  struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
@@ -1017,18 +1113,20 @@
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
-};
+  };
 
 4.32 KVM_SET_VCPU_EVENTS
+------------------------
 
-Capability: KVM_CAP_VCPU_EVENTS
-Extended by: KVM_CAP_INTR_SHADOW
-Architectures: x86, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_vcpu_event (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_VCPU_EVENTS
+:Extended by: KVM_CAP_INTR_SHADOW
+:Architectures: x86, arm, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_vcpu_event (in)
+:Returns: 0 on success, -1 on error
 
 X86:
+^^^^
 
 Set pending exceptions, interrupts, and NMIs as well as related states of the
 vcpu.
@@ -1040,9 +1138,11 @@
 smi.pending. Keep the corresponding bits in the flags field cleared to
 suppress overwriting the current in-kernel state. The bits are:
 
-KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
-KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
-KVM_VCPUEVENT_VALID_SMM         - transfer the smi sub-struct.
+===============================  ==================================
+KVM_VCPUEVENT_VALID_NMI_PENDING  transfer nmi.pending to the kernel
+KVM_VCPUEVENT_VALID_SIPI_VECTOR  transfer sipi_vector
+KVM_VCPUEVENT_VALID_SMM          transfer the smi sub-struct.
+===============================  ==================================
 
 If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
 the flags field to signal that interrupt.shadow contains a valid state and
@@ -1056,6 +1156,7 @@
 contain a valid state and shall be written into the VCPU.
 
 ARM/ARM64:
+^^^^^^^^^^
 
 User space may need to inject several types of events to the guest.
 
@@ -1078,31 +1179,35 @@
 
 
 4.33 KVM_GET_DEBUGREGS
+----------------------
 
-Capability: KVM_CAP_DEBUGREGS
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_debugregs (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_DEBUGREGS
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_debugregs (out)
+:Returns: 0 on success, -1 on error
 
 Reads debug registers from the vcpu.
 
-struct kvm_debugregs {
+::
+
+  struct kvm_debugregs {
 	__u64 db[4];
 	__u64 dr6;
 	__u64 dr7;
 	__u64 flags;
 	__u64 reserved[9];
-};
+  };
 
 
 4.34 KVM_SET_DEBUGREGS
+----------------------
 
-Capability: KVM_CAP_DEBUGREGS
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_debugregs (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_DEBUGREGS
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_debugregs (in)
+:Returns: 0 on success, -1 on error
 
 Writes debug registers into the vcpu.
 
@@ -1111,24 +1216,27 @@
 
 
 4.35 KVM_SET_USER_MEMORY_REGION
+-------------------------------
 
-Capability: KVM_CAP_USER_MEMORY
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_userspace_memory_region (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_USER_MEMORY
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_userspace_memory_region (in)
+:Returns: 0 on success, -1 on error
 
-struct kvm_userspace_memory_region {
+::
+
+  struct kvm_userspace_memory_region {
 	__u32 slot;
 	__u32 flags;
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
 	__u64 userspace_addr; /* start of the userspace allocated memory */
-};
+  };
 
-/* for kvm_memory_region::flags */
-#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
-#define KVM_MEM_READONLY	(1UL << 1)
+  /* for kvm_memory_region::flags */
+  #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
+  #define KVM_MEM_READONLY	(1UL << 1)
 
 This ioctl allows the user to create, modify or delete a guest physical
 memory slot.  Bits 0-15 of "slot" specify the slot id and this value
@@ -1174,12 +1282,13 @@
 
 
 4.36 KVM_SET_TSS_ADDR
+---------------------
 
-Capability: KVM_CAP_SET_TSS_ADDR
-Architectures: x86
-Type: vm ioctl
-Parameters: unsigned long tss_address (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_SET_TSS_ADDR
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: unsigned long tss_address (in)
+:Returns: 0 on success, -1 on error
 
 This ioctl defines the physical address of a three-page region in the guest
 physical address space.  The region must be within the first 4GB of the
@@ -1193,21 +1302,24 @@
 
 
 4.37 KVM_ENABLE_CAP
+-------------------
 
-Capability: KVM_CAP_ENABLE_CAP
-Architectures: mips, ppc, s390
-Type: vcpu ioctl
-Parameters: struct kvm_enable_cap (in)
-Returns: 0 on success; -1 on error
+:Capability: KVM_CAP_ENABLE_CAP
+:Architectures: mips, ppc, s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_enable_cap (in)
+:Returns: 0 on success; -1 on error
 
-Capability: KVM_CAP_ENABLE_CAP_VM
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_enable_cap (in)
-Returns: 0 on success; -1 on error
+:Capability: KVM_CAP_ENABLE_CAP_VM
+:Architectures: all
+:Type: vcpu ioctl
+:Parameters: struct kvm_enable_cap (in)
+:Returns: 0 on success; -1 on error
 
-+Not all extensions are enabled by default. Using this ioctl the application
-can enable an extension, making it available to the guest.
+.. note::
+
+   Not all extensions are enabled by default. Using this ioctl the application
+   can enable an extension, making it available to the guest.
 
 On systems that do not support this ioctl, it always fails. On systems that
 do support it, it only works for extensions that are supported for enablement.
@@ -1215,76 +1327,91 @@
 To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
 be used.
 
-struct kvm_enable_cap {
+::
+
+  struct kvm_enable_cap {
        /* in */
        __u32 cap;
 
 The capability that is supposed to get enabled.
 
+::
+
        __u32 flags;
 
 A bitfield indicating future enhancements. Has to be 0 for now.
 
+::
+
        __u64 args[4];
 
 Arguments for enabling a feature. If a feature needs initial values to
 function properly, this is the place to put them.
 
+::
+
        __u8  pad[64];
-};
+  };
 
 The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
 for vm-wide capabilities.
 
 4.38 KVM_GET_MP_STATE
+---------------------
 
-Capability: KVM_CAP_MP_STATE
-Architectures: x86, s390, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_mp_state (out)
-Returns: 0 on success; -1 on error
+:Capability: KVM_CAP_MP_STATE
+:Architectures: x86, s390, arm, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_mp_state (out)
+:Returns: 0 on success; -1 on error
 
-struct kvm_mp_state {
+::
+
+  struct kvm_mp_state {
 	__u32 mp_state;
-};
+  };
 
 Returns the vcpu's current "multiprocessing state" (though also valid on
 uniprocessor guests).
 
 Possible values are:
 
- - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running [x86,arm/arm64]
- - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
+   ==========================    ===============================================
+   KVM_MP_STATE_RUNNABLE         the vcpu is currently running [x86,arm/arm64]
+   KVM_MP_STATE_UNINITIALIZED    the vcpu is an application processor (AP)
                                  which has not yet received an INIT signal [x86]
- - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
+   KVM_MP_STATE_INIT_RECEIVED    the vcpu has received an INIT signal, and is
                                  now ready for a SIPI [x86]
- - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
+   KVM_MP_STATE_HALTED           the vcpu has executed a HLT instruction and
                                  is waiting for an interrupt [x86]
- - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
+   KVM_MP_STATE_SIPI_RECEIVED    the vcpu has just received a SIPI (vector
                                  accessible via KVM_GET_VCPU_EVENTS) [x86]
- - KVM_MP_STATE_STOPPED:         the vcpu is stopped [s390,arm/arm64]
- - KVM_MP_STATE_CHECK_STOP:      the vcpu is in a special error state [s390]
- - KVM_MP_STATE_OPERATING:       the vcpu is operating (running or halted)
+   KVM_MP_STATE_STOPPED          the vcpu is stopped [s390,arm/arm64]
+   KVM_MP_STATE_CHECK_STOP       the vcpu is in a special error state [s390]
+   KVM_MP_STATE_OPERATING        the vcpu is operating (running or halted)
                                  [s390]
- - KVM_MP_STATE_LOAD:            the vcpu is in a special load/startup state
+   KVM_MP_STATE_LOAD             the vcpu is in a special load/startup state
                                  [s390]
+   ==========================    ===============================================
 
 On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
 these architectures.
 
 For arm/arm64:
+^^^^^^^^^^^^^^
 
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
 
 4.39 KVM_SET_MP_STATE
+---------------------
 
-Capability: KVM_CAP_MP_STATE
-Architectures: x86, s390, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_mp_state (in)
-Returns: 0 on success; -1 on error
+:Capability: KVM_CAP_MP_STATE
+:Architectures: x86, s390, arm, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_mp_state (in)
+:Returns: 0 on success; -1 on error
 
 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
 arguments.
@@ -1294,17 +1421,19 @@
 these architectures.
 
 For arm/arm64:
+^^^^^^^^^^^^^^
 
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
 
 4.40 KVM_SET_IDENTITY_MAP_ADDR
+------------------------------
 
-Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
-Architectures: x86
-Type: vm ioctl
-Parameters: unsigned long identity (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: unsigned long identity (in)
+:Returns: 0 on success, -1 on error
 
 This ioctl defines the physical address of a one-page region in the guest
 physical address space.  The region must be within the first 4GB of the
@@ -1322,12 +1451,13 @@
 Fails if any VCPU has already been created.
 
 4.41 KVM_SET_BOOT_CPU_ID
+------------------------
 
-Capability: KVM_CAP_SET_BOOT_CPU_ID
-Architectures: x86
-Type: vm ioctl
-Parameters: unsigned long vcpu_id
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_SET_BOOT_CPU_ID
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: unsigned long vcpu_id
+:Returns: 0 on success, -1 on error
 
 Define which vcpu is the Bootstrap Processor (BSP).  Values are the same
 as the vcpu id in KVM_CREATE_VCPU.  If this ioctl is not called, the default
@@ -1335,102 +1465,119 @@
 
 
 4.42 KVM_GET_XSAVE
+------------------
 
-Capability: KVM_CAP_XSAVE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xsave (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_XSAVE
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_xsave (out)
+:Returns: 0 on success, -1 on error
 
-struct kvm_xsave {
+
+::
+
+  struct kvm_xsave {
 	__u32 region[1024];
-};
+  };
 
 This ioctl would copy current vcpu's xsave struct to the userspace.
 
 
 4.43 KVM_SET_XSAVE
+------------------
 
-Capability: KVM_CAP_XSAVE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xsave (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_XSAVE
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_xsave (in)
+:Returns: 0 on success, -1 on error
 
-struct kvm_xsave {
+::
+
+
+  struct kvm_xsave {
 	__u32 region[1024];
-};
+  };
 
 This ioctl would copy userspace's xsave struct to the kernel.
 
 
 4.44 KVM_GET_XCRS
+-----------------
 
-Capability: KVM_CAP_XCRS
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xcrs (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_XCRS
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_xcrs (out)
+:Returns: 0 on success, -1 on error
 
-struct kvm_xcr {
+::
+
+  struct kvm_xcr {
 	__u32 xcr;
 	__u32 reserved;
 	__u64 value;
-};
+  };
 
-struct kvm_xcrs {
+  struct kvm_xcrs {
 	__u32 nr_xcrs;
 	__u32 flags;
 	struct kvm_xcr xcrs[KVM_MAX_XCRS];
 	__u64 padding[16];
-};
+  };
 
 This ioctl would copy current vcpu's xcrs to the userspace.
 
 
 4.45 KVM_SET_XCRS
+-----------------
 
-Capability: KVM_CAP_XCRS
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xcrs (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_XCRS
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_xcrs (in)
+:Returns: 0 on success, -1 on error
 
-struct kvm_xcr {
+::
+
+  struct kvm_xcr {
 	__u32 xcr;
 	__u32 reserved;
 	__u64 value;
-};
+  };
 
-struct kvm_xcrs {
+  struct kvm_xcrs {
 	__u32 nr_xcrs;
 	__u32 flags;
 	struct kvm_xcr xcrs[KVM_MAX_XCRS];
 	__u64 padding[16];
-};
+  };
 
 This ioctl would set vcpu's xcr to the value userspace specified.
 
 
 4.46 KVM_GET_SUPPORTED_CPUID
+----------------------------
 
-Capability: KVM_CAP_EXT_CPUID
-Architectures: x86
-Type: system ioctl
-Parameters: struct kvm_cpuid2 (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_EXT_CPUID
+:Architectures: x86
+:Type: system ioctl
+:Parameters: struct kvm_cpuid2 (in/out)
+:Returns: 0 on success, -1 on error
 
-struct kvm_cpuid2 {
+::
+
+  struct kvm_cpuid2 {
 	__u32 nent;
 	__u32 padding;
 	struct kvm_cpuid_entry2 entries[0];
-};
+  };
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
-#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
-#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
+  #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+  #define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+  #define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
 
-struct kvm_cpuid_entry2 {
+  struct kvm_cpuid_entry2 {
 	__u32 function;
 	__u32 index;
 	__u32 flags;
@@ -1439,7 +1586,7 @@
 	__u32 ecx;
 	__u32 edx;
 	__u32 padding[3];
-};
+  };
 
 This ioctl returns x86 cpuid features which are supported by both the
 hardware and kvm in its default configuration.  Userspace can use the
@@ -1467,10 +1614,16 @@
 x2apic), may not be present in the host cpu, but are exposed by kvm if it can
 emulate them efficiently. The fields in each entry are defined as follows:
 
-  function: the eax value used to obtain the entry
-  index: the ecx value used to obtain the entry (for entries that are
+  function:
+         the eax value used to obtain the entry
+
+  index:
+         the ecx value used to obtain the entry (for entries that are
          affected by ecx)
-  flags: an OR of zero or more of the following:
+
+  flags:
+     an OR of zero or more of the following:
+
         KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
            if the index field is valid
         KVM_CPUID_FLAG_STATEFUL_FUNC:
@@ -1480,12 +1633,14 @@
         KVM_CPUID_FLAG_STATE_READ_NEXT:
            for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
            the first entry to be read by a cpu
-   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+
+   eax, ebx, ecx, edx:
+         the values returned by the cpuid instruction for
          this function/index combination
 
 The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
 as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
-support.  Instead it is reported via
+support.  Instead it is reported via::
 
   ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
 
@@ -1494,18 +1649,21 @@
 
 
 4.47 KVM_PPC_GET_PVINFO
+-----------------------
 
-Capability: KVM_CAP_PPC_GET_PVINFO
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_ppc_pvinfo (out)
-Returns: 0 on success, !0 on error
+:Capability: KVM_CAP_PPC_GET_PVINFO
+:Architectures: ppc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_pvinfo (out)
+:Returns: 0 on success, !0 on error
 
-struct kvm_ppc_pvinfo {
+::
+
+  struct kvm_ppc_pvinfo {
 	__u32 flags;
 	__u32 hcall[4];
 	__u8  pad[108];
-};
+  };
 
 This ioctl fetches PV specific information that need to be passed to the guest
 using the device tree or other means from vm context.
@@ -1515,33 +1673,39 @@
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
-The flags bitmap is defined as:
+The flags bitmap is defined as::
 
    /* the host supports the ePAPR idle hcall
    #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
 
 4.52 KVM_SET_GSI_ROUTING
+------------------------
 
-Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 s390 arm arm64
-Type: vm ioctl
-Parameters: struct kvm_irq_routing (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQ_ROUTING
+:Architectures: x86 s390 arm arm64
+:Type: vm ioctl
+:Parameters: struct kvm_irq_routing (in)
+:Returns: 0 on success, -1 on error
 
 Sets the GSI routing table entries, overwriting any previously set entries.
 
 On arm/arm64, GSI routing has the following limitation:
+
 - GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
 
-struct kvm_irq_routing {
+::
+
+  struct kvm_irq_routing {
 	__u32 nr;
 	__u32 flags;
 	struct kvm_irq_routing_entry entries[0];
-};
+  };
 
 No flags are specified so far, the corresponding field must be set to zero.
 
-struct kvm_irq_routing_entry {
+::
+
+  struct kvm_irq_routing_entry {
 	__u32 gsi;
 	__u32 type;
 	__u32 flags;
@@ -1553,15 +1717,16 @@
 		struct kvm_irq_routing_hv_sint hv_sint;
 		__u32 pad[8];
 	} u;
-};
+  };
 
-/* gsi routing entry types */
-#define KVM_IRQ_ROUTING_IRQCHIP 1
-#define KVM_IRQ_ROUTING_MSI 2
-#define KVM_IRQ_ROUTING_S390_ADAPTER 3
-#define KVM_IRQ_ROUTING_HV_SINT 4
+  /* gsi routing entry types */
+  #define KVM_IRQ_ROUTING_IRQCHIP 1
+  #define KVM_IRQ_ROUTING_MSI 2
+  #define KVM_IRQ_ROUTING_S390_ADAPTER 3
+  #define KVM_IRQ_ROUTING_HV_SINT 4
 
 flags:
+
 - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
   type, specifies that the devid field contains a valid value.  The per-VM
   KVM_CAP_MSI_DEVID capability advertises the requirement to provide
@@ -1569,12 +1734,14 @@
   never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
 - zero otherwise
 
-struct kvm_irq_routing_irqchip {
+::
+
+  struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
 	__u32 pin;
-};
+  };
 
-struct kvm_irq_routing_msi {
+  struct kvm_irq_routing_msi {
 	__u32 address_lo;
 	__u32 address_hi;
 	__u32 data;
@@ -1582,7 +1749,7 @@
 		__u32 pad;
 		__u32 devid;
 	};
-};
+  };
 
 If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
 for the device that wrote the MSI message.  For PCI, this is usually a
@@ -1593,39 +1760,43 @@
 address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
 address_hi must be zero.
 
-struct kvm_irq_routing_s390_adapter {
+::
+
+  struct kvm_irq_routing_s390_adapter {
 	__u64 ind_addr;
 	__u64 summary_addr;
 	__u64 ind_offset;
 	__u32 summary_offset;
 	__u32 adapter_id;
-};
+  };
 
-struct kvm_irq_routing_hv_sint {
+  struct kvm_irq_routing_hv_sint {
 	__u32 vcpu;
 	__u32 sint;
-};
+  };
 
 
 4.55 KVM_SET_TSC_KHZ
+--------------------
 
-Capability: KVM_CAP_TSC_CONTROL
-Architectures: x86
-Type: vcpu ioctl
-Parameters: virtual tsc_khz
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_TSC_CONTROL
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: virtual tsc_khz
+:Returns: 0 on success, -1 on error
 
 Specifies the tsc frequency for the virtual machine. The unit of the
 frequency is KHz.
 
 
 4.56 KVM_GET_TSC_KHZ
+--------------------
 
-Capability: KVM_CAP_GET_TSC_KHZ
-Architectures: x86
-Type: vcpu ioctl
-Parameters: none
-Returns: virtual tsc-khz on success, negative value on error
+:Capability: KVM_CAP_GET_TSC_KHZ
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: virtual tsc-khz on success, negative value on error
 
 Returns the tsc frequency of the guest. The unit of the return value is
 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
@@ -1633,17 +1804,20 @@
 
 
 4.57 KVM_GET_LAPIC
+------------------
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_lapic_state (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQCHIP
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_lapic_state (out)
+:Returns: 0 on success, -1 on error
 
-#define KVM_APIC_REG_SIZE 0x400
-struct kvm_lapic_state {
+::
+
+  #define KVM_APIC_REG_SIZE 0x400
+  struct kvm_lapic_state {
 	char regs[KVM_APIC_REG_SIZE];
-};
+  };
 
 Reads the Local APIC registers and copies them into the input argument.  The
 data format and layout are the same as documented in the architecture manual.
@@ -1661,17 +1835,20 @@
 
 
 4.58 KVM_SET_LAPIC
+------------------
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_lapic_state (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQCHIP
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_lapic_state (in)
+:Returns: 0 on success, -1 on error
 
-#define KVM_APIC_REG_SIZE 0x400
-struct kvm_lapic_state {
+::
+
+  #define KVM_APIC_REG_SIZE 0x400
+  struct kvm_lapic_state {
 	char regs[KVM_APIC_REG_SIZE];
-};
+  };
 
 Copies the input argument into the Local APIC registers.  The data format
 and layout are the same as documented in the architecture manual.
@@ -1682,35 +1859,38 @@
 
 
 4.59 KVM_IOEVENTFD
+------------------
 
-Capability: KVM_CAP_IOEVENTFD
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_ioeventfd (in)
-Returns: 0 on success, !0 on error
+:Capability: KVM_CAP_IOEVENTFD
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_ioeventfd (in)
+:Returns: 0 on success, !0 on error
 
 This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
 within the guest.  A guest write in the registered address will signal the
 provided event instead of triggering an exit.
 
-struct kvm_ioeventfd {
+::
+
+  struct kvm_ioeventfd {
 	__u64 datamatch;
 	__u64 addr;        /* legal pio/mmio address */
 	__u32 len;         /* 0, 1, 2, 4, or 8 bytes    */
 	__s32 fd;
 	__u32 flags;
 	__u8  pad[36];
-};
+  };
 
 For the special case of virtio-ccw devices on s390, the ioevent is matched
 to a subchannel/virtqueue tuple instead.
 
-The following flags are defined:
+The following flags are defined::
 
-#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
-#define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
-#define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
-#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+  #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
+  #define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
+  #define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
+  #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
 	(1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
 
 If datamatch flag is set, the event will be signaled only if the written value
@@ -1725,17 +1905,20 @@
 work anyway.
 
 4.60 KVM_DIRTY_TLB
+------------------
 
-Capability: KVM_CAP_SW_TLB
-Architectures: ppc
-Type: vcpu ioctl
-Parameters: struct kvm_dirty_tlb (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_SW_TLB
+:Architectures: ppc
+:Type: vcpu ioctl
+:Parameters: struct kvm_dirty_tlb (in)
+:Returns: 0 on success, -1 on error
 
-struct kvm_dirty_tlb {
+::
+
+  struct kvm_dirty_tlb {
 	__u64 bitmap;
 	__u32 num_dirty;
-};
+  };
 
 This must be called whenever userspace has changed an entry in the shared
 TLB, prior to calling KVM_RUN on the associated vcpu.
@@ -1758,23 +1941,26 @@
 
 
 4.62 KVM_CREATE_SPAPR_TCE
+-------------------------
 
-Capability: KVM_CAP_SPAPR_TCE
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_create_spapr_tce (in)
-Returns: file descriptor for manipulating the created TCE table
+:Capability: KVM_CAP_SPAPR_TCE
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_create_spapr_tce (in)
+:Returns: file descriptor for manipulating the created TCE table
 
 This creates a virtual TCE (translation control entry) table, which
 is an IOMMU for PAPR-style virtual I/O.  It is used to translate
 logical addresses used in virtual I/O into guest physical addresses,
 and provides a scatter/gather capability for PAPR virtual I/O.
 
-/* for KVM_CAP_SPAPR_TCE */
-struct kvm_create_spapr_tce {
+::
+
+  /* for KVM_CAP_SPAPR_TCE */
+  struct kvm_create_spapr_tce {
 	__u64 liobn;
 	__u32 window_size;
-};
+  };
 
 The liobn field gives the logical IO bus number for which to create a
 TCE table.  The window_size field specifies the size of the DMA window
@@ -1794,12 +1980,13 @@
 
 
 4.63 KVM_ALLOCATE_RMA
+---------------------
 
-Capability: KVM_CAP_PPC_RMA
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_allocate_rma (out)
-Returns: file descriptor for mapping the allocated RMA
+:Capability: KVM_CAP_PPC_RMA
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_allocate_rma (out)
+:Returns: file descriptor for mapping the allocated RMA
 
 This allocates a Real Mode Area (RMA) from the pool allocated at boot
 time by the kernel.  An RMA is a physically-contiguous, aligned region
@@ -1808,10 +1995,12 @@
 POWER processors support a set of sizes for the RMA that usually
 includes 64MB, 128MB, 256MB and some larger powers of two.
 
-/* for KVM_ALLOCATE_RMA */
-struct kvm_allocate_rma {
+::
+
+  /* for KVM_ALLOCATE_RMA */
+  struct kvm_allocate_rma {
 	__u64 rma_size;
-};
+  };
 
 The return value is a file descriptor which can be passed to mmap(2)
 to map the allocated RMA into userspace.  The mapped area can then be
@@ -1827,12 +2016,13 @@
 
 
 4.64 KVM_NMI
+------------
 
-Capability: KVM_CAP_USER_NMI
-Architectures: x86
-Type: vcpu ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_USER_NMI
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0 on success, -1 on error
 
 Queues an NMI on the thread's vcpu.  Note this is well defined only
 when KVM_CREATE_IRQCHIP has not been called, since this is an interface
@@ -1853,14 +2043,16 @@
 
 
 4.65 KVM_S390_UCAS_MAP
+----------------------
 
-Capability: KVM_CAP_S390_UCONTROL
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_ucas_mapping (in)
-Returns: 0 in case of success
+:Capability: KVM_CAP_S390_UCONTROL
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_ucas_mapping (in)
+:Returns: 0 in case of success
 
-The parameter is defined like this:
+The parameter is defined like this::
+
 	struct kvm_s390_ucas_mapping {
 		__u64 user_addr;
 		__u64 vcpu_addr;
@@ -1873,14 +2065,16 @@
 
 
 4.66 KVM_S390_UCAS_UNMAP
+------------------------
 
-Capability: KVM_CAP_S390_UCONTROL
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_ucas_mapping (in)
-Returns: 0 in case of success
+:Capability: KVM_CAP_S390_UCONTROL
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_ucas_mapping (in)
+:Returns: 0 in case of success
 
-The parameter is defined like this:
+The parameter is defined like this::
+
 	struct kvm_s390_ucas_mapping {
 		__u64 user_addr;
 		__u64 vcpu_addr;
@@ -1893,12 +2087,13 @@
 
 
 4.67 KVM_S390_VCPU_FAULT
+------------------------
 
-Capability: KVM_CAP_S390_UCONTROL
-Architectures: s390
-Type: vcpu ioctl
-Parameters: vcpu absolute address (in)
-Returns: 0 in case of success
+:Capability: KVM_CAP_S390_UCONTROL
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: vcpu absolute address (in)
+:Returns: 0 in case of success
 
 This call creates a page table entry on the virtual cpu's address space
 (for user controlled virtual machines) or the virtual machine's address
@@ -1910,23 +2105,31 @@
 
 
 4.68 KVM_SET_ONE_REG
+--------------------
 
-Capability: KVM_CAP_ONE_REG
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_one_reg (in)
-Returns: 0 on success, negative value on failure
+:Capability: KVM_CAP_ONE_REG
+:Architectures: all
+:Type: vcpu ioctl
+:Parameters: struct kvm_one_reg (in)
+:Returns: 0 on success, negative value on failure
+
 Errors:
-  ENOENT:   no such register
-  EINVAL:   invalid register ID, or no such register
-  EPERM:    (arm64) register access not allowed before vcpu finalization
+
+  ======   ============================================================
+  ENOENT   no such register
+  EINVAL   invalid register ID, or no such register
+  EPERM    (arm64) register access not allowed before vcpu finalization
+  ======   ============================================================
+
 (These error codes are indicative only: do not rely on a specific error
 code being returned in a specific situation.)
 
-struct kvm_one_reg {
+::
+
+  struct kvm_one_reg {
        __u64 id;
        __u64 addr;
-};
+ };
 
 Using this ioctl, a single vcpu register can be set to a specific value
 defined by user space with the passed in struct kvm_one_reg, where id
@@ -1936,217 +2139,226 @@
 and their own constants and width. To keep track of the implemented
 registers, find a list below:
 
-  Arch  |           Register            | Width (bits)
-        |                               |
-  PPC   | KVM_REG_PPC_HIOR              | 64
-  PPC   | KVM_REG_PPC_IAC1              | 64
-  PPC   | KVM_REG_PPC_IAC2              | 64
-  PPC   | KVM_REG_PPC_IAC3              | 64
-  PPC   | KVM_REG_PPC_IAC4              | 64
-  PPC   | KVM_REG_PPC_DAC1              | 64
-  PPC   | KVM_REG_PPC_DAC2              | 64
-  PPC   | KVM_REG_PPC_DABR              | 64
-  PPC   | KVM_REG_PPC_DSCR              | 64
-  PPC   | KVM_REG_PPC_PURR              | 64
-  PPC   | KVM_REG_PPC_SPURR             | 64
-  PPC   | KVM_REG_PPC_DAR               | 64
-  PPC   | KVM_REG_PPC_DSISR             | 32
-  PPC   | KVM_REG_PPC_AMR               | 64
-  PPC   | KVM_REG_PPC_UAMOR             | 64
-  PPC   | KVM_REG_PPC_MMCR0             | 64
-  PPC   | KVM_REG_PPC_MMCR1             | 64
-  PPC   | KVM_REG_PPC_MMCRA             | 64
-  PPC   | KVM_REG_PPC_MMCR2             | 64
-  PPC   | KVM_REG_PPC_MMCRS             | 64
-  PPC   | KVM_REG_PPC_SIAR              | 64
-  PPC   | KVM_REG_PPC_SDAR              | 64
-  PPC   | KVM_REG_PPC_SIER              | 64
-  PPC   | KVM_REG_PPC_PMC1              | 32
-  PPC   | KVM_REG_PPC_PMC2              | 32
-  PPC   | KVM_REG_PPC_PMC3              | 32
-  PPC   | KVM_REG_PPC_PMC4              | 32
-  PPC   | KVM_REG_PPC_PMC5              | 32
-  PPC   | KVM_REG_PPC_PMC6              | 32
-  PPC   | KVM_REG_PPC_PMC7              | 32
-  PPC   | KVM_REG_PPC_PMC8              | 32
-  PPC   | KVM_REG_PPC_FPR0              | 64
-          ...
-  PPC   | KVM_REG_PPC_FPR31             | 64
-  PPC   | KVM_REG_PPC_VR0               | 128
-          ...
-  PPC   | KVM_REG_PPC_VR31              | 128
-  PPC   | KVM_REG_PPC_VSR0              | 128
-          ...
-  PPC   | KVM_REG_PPC_VSR31             | 128
-  PPC   | KVM_REG_PPC_FPSCR             | 64
-  PPC   | KVM_REG_PPC_VSCR              | 32
-  PPC   | KVM_REG_PPC_VPA_ADDR          | 64
-  PPC   | KVM_REG_PPC_VPA_SLB           | 128
-  PPC   | KVM_REG_PPC_VPA_DTL           | 128
-  PPC   | KVM_REG_PPC_EPCR              | 32
-  PPC   | KVM_REG_PPC_EPR               | 32
-  PPC   | KVM_REG_PPC_TCR               | 32
-  PPC   | KVM_REG_PPC_TSR               | 32
-  PPC   | KVM_REG_PPC_OR_TSR            | 32
-  PPC   | KVM_REG_PPC_CLEAR_TSR         | 32
-  PPC   | KVM_REG_PPC_MAS0              | 32
-  PPC   | KVM_REG_PPC_MAS1              | 32
-  PPC   | KVM_REG_PPC_MAS2              | 64
-  PPC   | KVM_REG_PPC_MAS7_3            | 64
-  PPC   | KVM_REG_PPC_MAS4              | 32
-  PPC   | KVM_REG_PPC_MAS6              | 32
-  PPC   | KVM_REG_PPC_MMUCFG            | 32
-  PPC   | KVM_REG_PPC_TLB0CFG           | 32
-  PPC   | KVM_REG_PPC_TLB1CFG           | 32
-  PPC   | KVM_REG_PPC_TLB2CFG           | 32
-  PPC   | KVM_REG_PPC_TLB3CFG           | 32
-  PPC   | KVM_REG_PPC_TLB0PS            | 32
-  PPC   | KVM_REG_PPC_TLB1PS            | 32
-  PPC   | KVM_REG_PPC_TLB2PS            | 32
-  PPC   | KVM_REG_PPC_TLB3PS            | 32
-  PPC   | KVM_REG_PPC_EPTCFG            | 32
-  PPC   | KVM_REG_PPC_ICP_STATE         | 64
-  PPC   | KVM_REG_PPC_VP_STATE          | 128
-  PPC   | KVM_REG_PPC_TB_OFFSET         | 64
-  PPC   | KVM_REG_PPC_SPMC1             | 32
-  PPC   | KVM_REG_PPC_SPMC2             | 32
-  PPC   | KVM_REG_PPC_IAMR              | 64
-  PPC   | KVM_REG_PPC_TFHAR             | 64
-  PPC   | KVM_REG_PPC_TFIAR             | 64
-  PPC   | KVM_REG_PPC_TEXASR            | 64
-  PPC   | KVM_REG_PPC_FSCR              | 64
-  PPC   | KVM_REG_PPC_PSPB              | 32
-  PPC   | KVM_REG_PPC_EBBHR             | 64
-  PPC   | KVM_REG_PPC_EBBRR             | 64
-  PPC   | KVM_REG_PPC_BESCR             | 64
-  PPC   | KVM_REG_PPC_TAR               | 64
-  PPC   | KVM_REG_PPC_DPDES             | 64
-  PPC   | KVM_REG_PPC_DAWR              | 64
-  PPC   | KVM_REG_PPC_DAWRX             | 64
-  PPC   | KVM_REG_PPC_CIABR             | 64
-  PPC   | KVM_REG_PPC_IC                | 64
-  PPC   | KVM_REG_PPC_VTB               | 64
-  PPC   | KVM_REG_PPC_CSIGR             | 64
-  PPC   | KVM_REG_PPC_TACR              | 64
-  PPC   | KVM_REG_PPC_TCSCR             | 64
-  PPC   | KVM_REG_PPC_PID               | 64
-  PPC   | KVM_REG_PPC_ACOP              | 64
-  PPC   | KVM_REG_PPC_VRSAVE            | 32
-  PPC   | KVM_REG_PPC_LPCR              | 32
-  PPC   | KVM_REG_PPC_LPCR_64           | 64
-  PPC   | KVM_REG_PPC_PPR               | 64
-  PPC   | KVM_REG_PPC_ARCH_COMPAT       | 32
-  PPC   | KVM_REG_PPC_DABRX             | 32
-  PPC   | KVM_REG_PPC_WORT              | 64
-  PPC	| KVM_REG_PPC_SPRG9             | 64
-  PPC	| KVM_REG_PPC_DBSR              | 32
-  PPC   | KVM_REG_PPC_TIDR              | 64
-  PPC   | KVM_REG_PPC_PSSCR             | 64
-  PPC   | KVM_REG_PPC_DEC_EXPIRY        | 64
-  PPC   | KVM_REG_PPC_PTCR              | 64
-  PPC   | KVM_REG_PPC_TM_GPR0           | 64
-          ...
-  PPC   | KVM_REG_PPC_TM_GPR31          | 64
-  PPC   | KVM_REG_PPC_TM_VSR0           | 128
-          ...
-  PPC   | KVM_REG_PPC_TM_VSR63          | 128
-  PPC   | KVM_REG_PPC_TM_CR             | 64
-  PPC   | KVM_REG_PPC_TM_LR             | 64
-  PPC   | KVM_REG_PPC_TM_CTR            | 64
-  PPC   | KVM_REG_PPC_TM_FPSCR          | 64
-  PPC   | KVM_REG_PPC_TM_AMR            | 64
-  PPC   | KVM_REG_PPC_TM_PPR            | 64
-  PPC   | KVM_REG_PPC_TM_VRSAVE         | 64
-  PPC   | KVM_REG_PPC_TM_VSCR           | 32
-  PPC   | KVM_REG_PPC_TM_DSCR           | 64
-  PPC   | KVM_REG_PPC_TM_TAR            | 64
-  PPC   | KVM_REG_PPC_TM_XER            | 64
-        |                               |
-  MIPS  | KVM_REG_MIPS_R0               | 64
-          ...
-  MIPS  | KVM_REG_MIPS_R31              | 64
-  MIPS  | KVM_REG_MIPS_HI               | 64
-  MIPS  | KVM_REG_MIPS_LO               | 64
-  MIPS  | KVM_REG_MIPS_PC               | 64
-  MIPS  | KVM_REG_MIPS_CP0_INDEX        | 32
-  MIPS  | KVM_REG_MIPS_CP0_ENTRYLO0     | 64
-  MIPS  | KVM_REG_MIPS_CP0_ENTRYLO1     | 64
-  MIPS  | KVM_REG_MIPS_CP0_CONTEXT      | 64
-  MIPS  | KVM_REG_MIPS_CP0_CONTEXTCONFIG| 32
-  MIPS  | KVM_REG_MIPS_CP0_USERLOCAL    | 64
-  MIPS  | KVM_REG_MIPS_CP0_XCONTEXTCONFIG| 64
-  MIPS  | KVM_REG_MIPS_CP0_PAGEMASK     | 32
-  MIPS  | KVM_REG_MIPS_CP0_PAGEGRAIN    | 32
-  MIPS  | KVM_REG_MIPS_CP0_SEGCTL0      | 64
-  MIPS  | KVM_REG_MIPS_CP0_SEGCTL1      | 64
-  MIPS  | KVM_REG_MIPS_CP0_SEGCTL2      | 64
-  MIPS  | KVM_REG_MIPS_CP0_PWBASE       | 64
-  MIPS  | KVM_REG_MIPS_CP0_PWFIELD      | 64
-  MIPS  | KVM_REG_MIPS_CP0_PWSIZE       | 64
-  MIPS  | KVM_REG_MIPS_CP0_WIRED        | 32
-  MIPS  | KVM_REG_MIPS_CP0_PWCTL        | 32
-  MIPS  | KVM_REG_MIPS_CP0_HWRENA       | 32
-  MIPS  | KVM_REG_MIPS_CP0_BADVADDR     | 64
-  MIPS  | KVM_REG_MIPS_CP0_BADINSTR     | 32
-  MIPS  | KVM_REG_MIPS_CP0_BADINSTRP    | 32
-  MIPS  | KVM_REG_MIPS_CP0_COUNT        | 32
-  MIPS  | KVM_REG_MIPS_CP0_ENTRYHI      | 64
-  MIPS  | KVM_REG_MIPS_CP0_COMPARE      | 32
-  MIPS  | KVM_REG_MIPS_CP0_STATUS       | 32
-  MIPS  | KVM_REG_MIPS_CP0_INTCTL       | 32
-  MIPS  | KVM_REG_MIPS_CP0_CAUSE        | 32
-  MIPS  | KVM_REG_MIPS_CP0_EPC          | 64
-  MIPS  | KVM_REG_MIPS_CP0_PRID         | 32
-  MIPS  | KVM_REG_MIPS_CP0_EBASE        | 64
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG       | 32
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG1      | 32
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG2      | 32
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG3      | 32
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG4      | 32
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG5      | 32
-  MIPS  | KVM_REG_MIPS_CP0_CONFIG7      | 32
-  MIPS  | KVM_REG_MIPS_CP0_XCONTEXT     | 64
-  MIPS  | KVM_REG_MIPS_CP0_ERROREPC     | 64
-  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH1    | 64
-  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH2    | 64
-  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH3    | 64
-  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH4    | 64
-  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH5    | 64
-  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH6    | 64
-  MIPS  | KVM_REG_MIPS_CP0_MAAR(0..63)  | 64
-  MIPS  | KVM_REG_MIPS_COUNT_CTL        | 64
-  MIPS  | KVM_REG_MIPS_COUNT_RESUME     | 64
-  MIPS  | KVM_REG_MIPS_COUNT_HZ         | 64
-  MIPS  | KVM_REG_MIPS_FPR_32(0..31)    | 32
-  MIPS  | KVM_REG_MIPS_FPR_64(0..31)    | 64
-  MIPS  | KVM_REG_MIPS_VEC_128(0..31)   | 128
-  MIPS  | KVM_REG_MIPS_FCR_IR           | 32
-  MIPS  | KVM_REG_MIPS_FCR_CSR          | 32
-  MIPS  | KVM_REG_MIPS_MSA_IR           | 32
-  MIPS  | KVM_REG_MIPS_MSA_CSR          | 32
+  ======= =============================== ============
+  Arch              Register              Width (bits)
+  ======= =============================== ============
+  PPC     KVM_REG_PPC_HIOR                64
+  PPC     KVM_REG_PPC_IAC1                64
+  PPC     KVM_REG_PPC_IAC2                64
+  PPC     KVM_REG_PPC_IAC3                64
+  PPC     KVM_REG_PPC_IAC4                64
+  PPC     KVM_REG_PPC_DAC1                64
+  PPC     KVM_REG_PPC_DAC2                64
+  PPC     KVM_REG_PPC_DABR                64
+  PPC     KVM_REG_PPC_DSCR                64
+  PPC     KVM_REG_PPC_PURR                64
+  PPC     KVM_REG_PPC_SPURR               64
+  PPC     KVM_REG_PPC_DAR                 64
+  PPC     KVM_REG_PPC_DSISR               32
+  PPC     KVM_REG_PPC_AMR                 64
+  PPC     KVM_REG_PPC_UAMOR               64
+  PPC     KVM_REG_PPC_MMCR0               64
+  PPC     KVM_REG_PPC_MMCR1               64
+  PPC     KVM_REG_PPC_MMCRA               64
+  PPC     KVM_REG_PPC_MMCR2               64
+  PPC     KVM_REG_PPC_MMCRS               64
+  PPC     KVM_REG_PPC_SIAR                64
+  PPC     KVM_REG_PPC_SDAR                64
+  PPC     KVM_REG_PPC_SIER                64
+  PPC     KVM_REG_PPC_PMC1                32
+  PPC     KVM_REG_PPC_PMC2                32
+  PPC     KVM_REG_PPC_PMC3                32
+  PPC     KVM_REG_PPC_PMC4                32
+  PPC     KVM_REG_PPC_PMC5                32
+  PPC     KVM_REG_PPC_PMC6                32
+  PPC     KVM_REG_PPC_PMC7                32
+  PPC     KVM_REG_PPC_PMC8                32
+  PPC     KVM_REG_PPC_FPR0                64
+  ...
+  PPC     KVM_REG_PPC_FPR31               64
+  PPC     KVM_REG_PPC_VR0                 128
+  ...
+  PPC     KVM_REG_PPC_VR31                128
+  PPC     KVM_REG_PPC_VSR0                128
+  ...
+  PPC     KVM_REG_PPC_VSR31               128
+  PPC     KVM_REG_PPC_FPSCR               64
+  PPC     KVM_REG_PPC_VSCR                32
+  PPC     KVM_REG_PPC_VPA_ADDR            64
+  PPC     KVM_REG_PPC_VPA_SLB             128
+  PPC     KVM_REG_PPC_VPA_DTL             128
+  PPC     KVM_REG_PPC_EPCR                32
+  PPC     KVM_REG_PPC_EPR                 32
+  PPC     KVM_REG_PPC_TCR                 32
+  PPC     KVM_REG_PPC_TSR                 32
+  PPC     KVM_REG_PPC_OR_TSR              32
+  PPC     KVM_REG_PPC_CLEAR_TSR           32
+  PPC     KVM_REG_PPC_MAS0                32
+  PPC     KVM_REG_PPC_MAS1                32
+  PPC     KVM_REG_PPC_MAS2                64
+  PPC     KVM_REG_PPC_MAS7_3              64
+  PPC     KVM_REG_PPC_MAS4                32
+  PPC     KVM_REG_PPC_MAS6                32
+  PPC     KVM_REG_PPC_MMUCFG              32
+  PPC     KVM_REG_PPC_TLB0CFG             32
+  PPC     KVM_REG_PPC_TLB1CFG             32
+  PPC     KVM_REG_PPC_TLB2CFG             32
+  PPC     KVM_REG_PPC_TLB3CFG             32
+  PPC     KVM_REG_PPC_TLB0PS              32
+  PPC     KVM_REG_PPC_TLB1PS              32
+  PPC     KVM_REG_PPC_TLB2PS              32
+  PPC     KVM_REG_PPC_TLB3PS              32
+  PPC     KVM_REG_PPC_EPTCFG              32
+  PPC     KVM_REG_PPC_ICP_STATE           64
+  PPC     KVM_REG_PPC_VP_STATE            128
+  PPC     KVM_REG_PPC_TB_OFFSET           64
+  PPC     KVM_REG_PPC_SPMC1               32
+  PPC     KVM_REG_PPC_SPMC2               32
+  PPC     KVM_REG_PPC_IAMR                64
+  PPC     KVM_REG_PPC_TFHAR               64
+  PPC     KVM_REG_PPC_TFIAR               64
+  PPC     KVM_REG_PPC_TEXASR              64
+  PPC     KVM_REG_PPC_FSCR                64
+  PPC     KVM_REG_PPC_PSPB                32
+  PPC     KVM_REG_PPC_EBBHR               64
+  PPC     KVM_REG_PPC_EBBRR               64
+  PPC     KVM_REG_PPC_BESCR               64
+  PPC     KVM_REG_PPC_TAR                 64
+  PPC     KVM_REG_PPC_DPDES               64
+  PPC     KVM_REG_PPC_DAWR                64
+  PPC     KVM_REG_PPC_DAWRX               64
+  PPC     KVM_REG_PPC_CIABR               64
+  PPC     KVM_REG_PPC_IC                  64
+  PPC     KVM_REG_PPC_VTB                 64
+  PPC     KVM_REG_PPC_CSIGR               64
+  PPC     KVM_REG_PPC_TACR                64
+  PPC     KVM_REG_PPC_TCSCR               64
+  PPC     KVM_REG_PPC_PID                 64
+  PPC     KVM_REG_PPC_ACOP                64
+  PPC     KVM_REG_PPC_VRSAVE              32
+  PPC     KVM_REG_PPC_LPCR                32
+  PPC     KVM_REG_PPC_LPCR_64             64
+  PPC     KVM_REG_PPC_PPR                 64
+  PPC     KVM_REG_PPC_ARCH_COMPAT         32
+  PPC     KVM_REG_PPC_DABRX               32
+  PPC     KVM_REG_PPC_WORT                64
+  PPC	  KVM_REG_PPC_SPRG9               64
+  PPC	  KVM_REG_PPC_DBSR                32
+  PPC     KVM_REG_PPC_TIDR                64
+  PPC     KVM_REG_PPC_PSSCR               64
+  PPC     KVM_REG_PPC_DEC_EXPIRY          64
+  PPC     KVM_REG_PPC_PTCR                64
+  PPC     KVM_REG_PPC_TM_GPR0             64
+  ...
+  PPC     KVM_REG_PPC_TM_GPR31            64
+  PPC     KVM_REG_PPC_TM_VSR0             128
+  ...
+  PPC     KVM_REG_PPC_TM_VSR63            128
+  PPC     KVM_REG_PPC_TM_CR               64
+  PPC     KVM_REG_PPC_TM_LR               64
+  PPC     KVM_REG_PPC_TM_CTR              64
+  PPC     KVM_REG_PPC_TM_FPSCR            64
+  PPC     KVM_REG_PPC_TM_AMR              64
+  PPC     KVM_REG_PPC_TM_PPR              64
+  PPC     KVM_REG_PPC_TM_VRSAVE           64
+  PPC     KVM_REG_PPC_TM_VSCR             32
+  PPC     KVM_REG_PPC_TM_DSCR             64
+  PPC     KVM_REG_PPC_TM_TAR              64
+  PPC     KVM_REG_PPC_TM_XER              64
+
+  MIPS    KVM_REG_MIPS_R0                 64
+  ...
+  MIPS    KVM_REG_MIPS_R31                64
+  MIPS    KVM_REG_MIPS_HI                 64
+  MIPS    KVM_REG_MIPS_LO                 64
+  MIPS    KVM_REG_MIPS_PC                 64
+  MIPS    KVM_REG_MIPS_CP0_INDEX          32
+  MIPS    KVM_REG_MIPS_CP0_ENTRYLO0       64
+  MIPS    KVM_REG_MIPS_CP0_ENTRYLO1       64
+  MIPS    KVM_REG_MIPS_CP0_CONTEXT        64
+  MIPS    KVM_REG_MIPS_CP0_CONTEXTCONFIG  32
+  MIPS    KVM_REG_MIPS_CP0_USERLOCAL      64
+  MIPS    KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64
+  MIPS    KVM_REG_MIPS_CP0_PAGEMASK       32
+  MIPS    KVM_REG_MIPS_CP0_PAGEGRAIN      32
+  MIPS    KVM_REG_MIPS_CP0_SEGCTL0        64
+  MIPS    KVM_REG_MIPS_CP0_SEGCTL1        64
+  MIPS    KVM_REG_MIPS_CP0_SEGCTL2        64
+  MIPS    KVM_REG_MIPS_CP0_PWBASE         64
+  MIPS    KVM_REG_MIPS_CP0_PWFIELD        64
+  MIPS    KVM_REG_MIPS_CP0_PWSIZE         64
+  MIPS    KVM_REG_MIPS_CP0_WIRED          32
+  MIPS    KVM_REG_MIPS_CP0_PWCTL          32
+  MIPS    KVM_REG_MIPS_CP0_HWRENA         32
+  MIPS    KVM_REG_MIPS_CP0_BADVADDR       64
+  MIPS    KVM_REG_MIPS_CP0_BADINSTR       32
+  MIPS    KVM_REG_MIPS_CP0_BADINSTRP      32
+  MIPS    KVM_REG_MIPS_CP0_COUNT          32
+  MIPS    KVM_REG_MIPS_CP0_ENTRYHI        64
+  MIPS    KVM_REG_MIPS_CP0_COMPARE        32
+  MIPS    KVM_REG_MIPS_CP0_STATUS         32
+  MIPS    KVM_REG_MIPS_CP0_INTCTL         32
+  MIPS    KVM_REG_MIPS_CP0_CAUSE          32
+  MIPS    KVM_REG_MIPS_CP0_EPC            64
+  MIPS    KVM_REG_MIPS_CP0_PRID           32
+  MIPS    KVM_REG_MIPS_CP0_EBASE          64
+  MIPS    KVM_REG_MIPS_CP0_CONFIG         32
+  MIPS    KVM_REG_MIPS_CP0_CONFIG1        32
+  MIPS    KVM_REG_MIPS_CP0_CONFIG2        32
+  MIPS    KVM_REG_MIPS_CP0_CONFIG3        32
+  MIPS    KVM_REG_MIPS_CP0_CONFIG4        32
+  MIPS    KVM_REG_MIPS_CP0_CONFIG5        32
+  MIPS    KVM_REG_MIPS_CP0_CONFIG7        32
+  MIPS    KVM_REG_MIPS_CP0_XCONTEXT       64
+  MIPS    KVM_REG_MIPS_CP0_ERROREPC       64
+  MIPS    KVM_REG_MIPS_CP0_KSCRATCH1      64
+  MIPS    KVM_REG_MIPS_CP0_KSCRATCH2      64
+  MIPS    KVM_REG_MIPS_CP0_KSCRATCH3      64
+  MIPS    KVM_REG_MIPS_CP0_KSCRATCH4      64
+  MIPS    KVM_REG_MIPS_CP0_KSCRATCH5      64
+  MIPS    KVM_REG_MIPS_CP0_KSCRATCH6      64
+  MIPS    KVM_REG_MIPS_CP0_MAAR(0..63)    64
+  MIPS    KVM_REG_MIPS_COUNT_CTL          64
+  MIPS    KVM_REG_MIPS_COUNT_RESUME       64
+  MIPS    KVM_REG_MIPS_COUNT_HZ           64
+  MIPS    KVM_REG_MIPS_FPR_32(0..31)      32
+  MIPS    KVM_REG_MIPS_FPR_64(0..31)      64
+  MIPS    KVM_REG_MIPS_VEC_128(0..31)     128
+  MIPS    KVM_REG_MIPS_FCR_IR             32
+  MIPS    KVM_REG_MIPS_FCR_CSR            32
+  MIPS    KVM_REG_MIPS_MSA_IR             32
+  MIPS    KVM_REG_MIPS_MSA_CSR            32
+  ======= =============================== ============
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:
 
-ARM core registers have the following id bit patterns:
+ARM core registers have the following id bit patterns::
+
   0x4020 0000 0010 <index into the kvm_regs struct:16>
 
-ARM 32-bit CP15 registers have the following id bit patterns:
+ARM 32-bit CP15 registers have the following id bit patterns::
+
   0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
 
-ARM 64-bit CP15 registers have the following id bit patterns:
+ARM 64-bit CP15 registers have the following id bit patterns::
+
   0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
 
-ARM CCSIDR registers are demultiplexed by CSSELR value:
+ARM CCSIDR registers are demultiplexed by CSSELR value::
+
   0x4020 0000 0011 00 <csselr:8>
 
-ARM 32-bit VFP control registers have the following id bit patterns:
+ARM 32-bit VFP control registers have the following id bit patterns::
+
   0x4020 0000 0012 1 <regno:12>
 
-ARM 64-bit FP registers have the following id bit patterns:
+ARM 64-bit FP registers have the following id bit patterns::
+
   0x4030 0000 0012 0 <regno:12>
 
-ARM firmware pseudo-registers have the following bit pattern:
+ARM firmware pseudo-registers have the following bit pattern::
+
   0x4030 0000 0014 <regno:16>
 
 
@@ -2156,15 +2368,18 @@
 arm64 core/FP-SIMD registers have the following id bit patterns. Note
 that the size of the access is variable, as the kvm_regs structure
 contains elements ranging from 32 to 128 bits. The index is a 32bit
-value in the kvm_regs structure seen as a 32bit array.
+value in the kvm_regs structure seen as a 32bit array::
+
   0x60x0 0000 0010 <index into the kvm_regs struct:16>
 
 Specifically:
+
+======================= ========= ===== =======================================
     Encoding            Register  Bits  kvm_regs member
-----------------------------------------------------------------
+======================= ========= ===== =======================================
   0x6030 0000 0010 0000 X0          64  regs.regs[0]
   0x6030 0000 0010 0002 X1          64  regs.regs[1]
-    ...
+  ...
   0x6030 0000 0010 003c X30         64  regs.regs[30]
   0x6030 0000 0010 003e SP          64  regs.sp
   0x6030 0000 0010 0040 PC          64  regs.pc
@@ -2176,27 +2391,31 @@
   0x6030 0000 0010 004c SPSR_UND    64  spsr[KVM_SPSR_UND]
   0x6030 0000 0010 004e SPSR_IRQ    64  spsr[KVM_SPSR_IRQ]
   0x6060 0000 0010 0050 SPSR_FIQ    64  spsr[KVM_SPSR_FIQ]
-  0x6040 0000 0010 0054 V0         128  fp_regs.vregs[0]    (*)
-  0x6040 0000 0010 0058 V1         128  fp_regs.vregs[1]    (*)
-    ...
-  0x6040 0000 0010 00d0 V31        128  fp_regs.vregs[31]   (*)
+  0x6040 0000 0010 0054 V0         128  fp_regs.vregs[0]    [1]_
+  0x6040 0000 0010 0058 V1         128  fp_regs.vregs[1]    [1]_
+  ...
+  0x6040 0000 0010 00d0 V31        128  fp_regs.vregs[31]   [1]_
   0x6020 0000 0010 00d4 FPSR        32  fp_regs.fpsr
   0x6020 0000 0010 00d5 FPCR        32  fp_regs.fpcr
+======================= ========= ===== =======================================
 
-(*) These encodings are not accepted for SVE-enabled vcpus.  See
-    KVM_ARM_VCPU_INIT.
+.. [1] These encodings are not accepted for SVE-enabled vcpus.  See
+       KVM_ARM_VCPU_INIT.
 
-    The equivalent register content can be accessed via bits [127:0] of
-    the corresponding SVE Zn registers instead for vcpus that have SVE
-    enabled (see below).
+       The equivalent register content can be accessed via bits [127:0] of
+       the corresponding SVE Zn registers instead for vcpus that have SVE
+       enabled (see below).
 
-arm64 CCSIDR registers are demultiplexed by CSSELR value:
+arm64 CCSIDR registers are demultiplexed by CSSELR value::
+
   0x6020 0000 0011 00 <csselr:8>
 
-arm64 system registers have the following id bit patterns:
+arm64 system registers have the following id bit patterns::
+
   0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
 
-WARNING:
+.. warning::
+
      Two system register IDs do not follow the specified pattern.  These
      are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to
      system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively.  These
@@ -2205,10 +2424,12 @@
      derived from the register encoding for CNTV_CVAL_EL0.  As this is
      API, it must remain this way.
 
-arm64 firmware pseudo-registers have the following bit pattern:
+arm64 firmware pseudo-registers have the following bit pattern::
+
   0x6030 0000 0014 <regno:16>
 
-arm64 SVE registers have the following bit patterns:
+arm64 SVE registers have the following bit patterns::
+
   0x6080 0000 0015 00 <n:5> <slice:5>   Zn bits[2048*slice + 2047 : 2048*slice]
   0x6050 0000 0015 04 <n:4> <slice:5>   Pn bits[256*slice + 255 : 256*slice]
   0x6050 0000 0015 060 <slice:5>        FFR bits[256*slice + 255 : 256*slice]
@@ -2216,7 +2437,7 @@
 
 Access to register IDs where 2048 * slice >= 128 * max_vq will fail with
 ENOENT.  max_vq is the vcpu's maximum supported vector length in 128-bit
-quadwords: see (**) below.
+quadwords: see [2]_ below.
 
 These registers are only accessible on vcpus for which SVE is enabled.
 See KVM_ARM_VCPU_INIT for details.
@@ -2231,21 +2452,21 @@
 userspace.  When transferred to or from user memory via KVM_GET_ONE_REG
 or KVM_SET_ONE_REG, the value of this register is of type
 __u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as
-follows:
+follows::
 
-__u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS];
+  __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS];
 
-if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX &&
-    ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
+  if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX &&
+      ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
 		((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1))
 	/* Vector length vq * 16 bytes supported */
-else
+  else
 	/* Vector length vq * 16 bytes not supported */
 
-(**) The maximum value vq for which the above condition is true is
-max_vq.  This is the maximum vector length available to the guest on
-this vcpu, and determines which register slices are visible through
-this ioctl interface.
+.. [2] The maximum value vq for which the above condition is true is
+       max_vq.  This is the maximum vector length available to the guest on
+       this vcpu, and determines which register slices are visible through
+       this ioctl interface.
 
 (See Documentation/arm64/sve.rst for an explanation of the "vq"
 nomenclature.)
@@ -2270,11 +2491,13 @@
 MIPS registers are mapped using the lower 32 bits.  The upper 16 of that is
 the register group type:
 
-MIPS core registers (see above) have the following id bit patterns:
+MIPS core registers (see above) have the following id bit patterns::
+
   0x7030 0000 0000 <reg:16>
 
 MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
-patterns depending on whether they're 32-bit or 64-bit registers:
+patterns depending on whether they're 32-bit or 64-bit registers::
+
   0x7020 0000 0001 00 <reg:5> <sel:3>   (32-bit)
   0x7030 0000 0001 00 <reg:5> <sel:3>   (64-bit)
 
@@ -2285,10 +2508,12 @@
 the PFNX field starting at bit 30.
 
 MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit
-patterns:
+patterns::
+
   0x7030 0000 0001 01 <reg:8>
 
-MIPS KVM control registers (see above) have the following id bit patterns:
+MIPS KVM control registers (see above) have the following id bit patterns::
+
   0x7030 0000 0002 <reg:16>
 
 MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following
@@ -2297,31 +2522,40 @@
 Config5.FRE), i.e. as the guest would see them, and they become unpredictable
 if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector
 registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they
-overlap the FPU registers:
+overlap the FPU registers::
+
   0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
   0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
   0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)
 
 MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the
-following id bit patterns:
+following id bit patterns::
+
   0x7020 0000 0003 01 <0:3> <reg:5>
 
 MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the
-following id bit patterns:
+following id bit patterns::
+
   0x7020 0000 0003 02 <0:3> <reg:5>
 
 
 4.69 KVM_GET_ONE_REG
+--------------------
 
-Capability: KVM_CAP_ONE_REG
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_one_reg (in and out)
-Returns: 0 on success, negative value on failure
+:Capability: KVM_CAP_ONE_REG
+:Architectures: all
+:Type: vcpu ioctl
+:Parameters: struct kvm_one_reg (in and out)
+:Returns: 0 on success, negative value on failure
+
 Errors include:
-  ENOENT:   no such register
-  EINVAL:   invalid register ID, or no such register
-  EPERM:    (arm64) register access not allowed before vcpu finalization
+
+  ======== ============================================================
+  ENOENT   no such register
+  EINVAL   invalid register ID, or no such register
+  EPERM    (arm64) register access not allowed before vcpu finalization
+  ======== ============================================================
+
 (These error codes are indicative only: do not rely on a specific error
 code being returned in a specific situation.)
 
@@ -2335,12 +2569,13 @@
 
 
 4.70 KVM_KVMCLOCK_CTRL
+----------------------
 
-Capability: KVM_CAP_KVMCLOCK_CTRL
-Architectures: Any that implement pvclocks (currently x86 only)
-Type: vcpu ioctl
-Parameters: None
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_KVMCLOCK_CTRL
+:Architectures: Any that implement pvclocks (currently x86 only)
+:Type: vcpu ioctl
+:Parameters: None
+:Returns: 0 on success, -1 on error
 
 This signals to the host kernel that the specified guest is being paused by
 userspace.  The host will set a flag in the pvclock structure that is checked
@@ -2356,26 +2591,30 @@
 
 
 4.71 KVM_SIGNAL_MSI
+-------------------
 
-Capability: KVM_CAP_SIGNAL_MSI
-Architectures: x86 arm arm64
-Type: vm ioctl
-Parameters: struct kvm_msi (in)
-Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
+:Capability: KVM_CAP_SIGNAL_MSI
+:Architectures: x86 arm arm64
+:Type: vm ioctl
+:Parameters: struct kvm_msi (in)
+:Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
 
 Directly inject a MSI message. Only valid with in-kernel irqchip that handles
 MSI messages.
 
-struct kvm_msi {
+::
+
+  struct kvm_msi {
 	__u32 address_lo;
 	__u32 address_hi;
 	__u32 data;
 	__u32 flags;
 	__u32 devid;
 	__u8  pad[12];
-};
+  };
 
-flags: KVM_MSI_VALID_DEVID: devid contains a valid value.  The per-VM
+flags:
+  KVM_MSI_VALID_DEVID: devid contains a valid value.  The per-VM
   KVM_CAP_MSI_DEVID capability advertises the requirement to provide
   the device ID.  If this capability is not available, userspace
   should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
@@ -2391,30 +2630,31 @@
 
 
 4.71 KVM_CREATE_PIT2
+--------------------
 
-Capability: KVM_CAP_PIT2
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pit_config (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PIT2
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_pit_config (in)
+:Returns: 0 on success, -1 on error
 
 Creates an in-kernel device model for the i8254 PIT. This call is only valid
 after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
-parameters have to be passed:
+parameters have to be passed::
 
-struct kvm_pit_config {
+  struct kvm_pit_config {
 	__u32 flags;
 	__u32 pad[15];
-};
+  };
 
-Valid flags are:
+Valid flags are::
 
-#define KVM_PIT_SPEAKER_DUMMY     1 /* emulate speaker port stub */
+  #define KVM_PIT_SPEAKER_DUMMY     1 /* emulate speaker port stub */
 
 PIT timer interrupts may use a per-VM kernel thread for injection. If it
-exists, this thread will have a name of the following pattern:
+exists, this thread will have a name of the following pattern::
 
-kvm-pit/<owner-process-pid>
+  kvm-pit/<owner-process-pid>
 
 When running a guest with elevated priorities, the scheduling parameters of
 this thread may have to be adjusted accordingly.
@@ -2423,37 +2663,39 @@
 
 
 4.72 KVM_GET_PIT2
+-----------------
 
-Capability: KVM_CAP_PIT_STATE2
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pit_state2 (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PIT_STATE2
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_pit_state2 (out)
+:Returns: 0 on success, -1 on error
 
 Retrieves the state of the in-kernel PIT model. Only valid after
-KVM_CREATE_PIT2. The state is returned in the following structure:
+KVM_CREATE_PIT2. The state is returned in the following structure::
 
-struct kvm_pit_state2 {
+  struct kvm_pit_state2 {
 	struct kvm_pit_channel_state channels[3];
 	__u32 flags;
 	__u32 reserved[9];
-};
+  };
 
-Valid flags are:
+Valid flags are::
 
-/* disable PIT in HPET legacy mode */
-#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+  /* disable PIT in HPET legacy mode */
+  #define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
 
 This IOCTL replaces the obsolete KVM_GET_PIT.
 
 
 4.73 KVM_SET_PIT2
+-----------------
 
-Capability: KVM_CAP_PIT_STATE2
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pit_state2 (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PIT_STATE2
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_pit_state2 (in)
+:Returns: 0 on success, -1 on error
 
 Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
 See KVM_GET_PIT2 for details on struct kvm_pit_state2.
@@ -2462,12 +2704,13 @@
 
 
 4.74 KVM_PPC_GET_SMMU_INFO
+--------------------------
 
-Capability: KVM_CAP_PPC_GET_SMMU_INFO
-Architectures: powerpc
-Type: vm ioctl
-Parameters: None
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PPC_GET_SMMU_INFO
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: None
+:Returns: 0 on success, -1 on error
 
 This populates and returns a structure describing the features of
 the "Server" class MMU emulation supported by KVM.
@@ -2475,7 +2718,7 @@
 device-tree properties for the guest operating system.
 
 The structure contains some global information, followed by an
-array of supported segment page sizes:
+array of supported segment page sizes::
 
       struct kvm_ppc_smmu_info {
 	     __u64 flags;
@@ -2503,7 +2746,7 @@
 
 The "sps" array contains 8 entries indicating the supported base
 page sizes for a segment in increasing order. Each entry is defined
-as follow:
+as follow::
 
    struct kvm_ppc_one_seg_page_size {
 	__u32 page_shift;	/* Base page shift of segment (or 0) */
@@ -2524,7 +2767,7 @@
 only larger or equal to the base page size), along with the
 corresponding encoding in the hash PTE. Similarly, the array is
 8 entries sorted by increasing sizes and an entry with a "0" shift
-is an empty entry and a terminator:
+is an empty entry and a terminator::
 
    struct kvm_ppc_one_page_size {
 	__u32 page_shift;	/* Page shift (or 0) */
@@ -2536,12 +2779,13 @@
 into the hash PTE second double word).
 
 4.75 KVM_IRQFD
+--------------
 
-Capability: KVM_CAP_IRQFD
-Architectures: x86 s390 arm arm64
-Type: vm ioctl
-Parameters: struct kvm_irqfd (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_IRQFD
+:Architectures: x86 s390 arm arm64
+:Type: vm ioctl
+:Parameters: struct kvm_irqfd (in)
+:Returns: 0 on success, -1 on error
 
 Allows setting an eventfd to directly trigger a guest interrupt.
 kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
@@ -2565,6 +2809,7 @@
 and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
 
 On arm/arm64, gsi routing being supported, the following can happen:
+
 - in case no routing entry is associated to this gsi, injection fails
 - in case the gsi is associated to an irqchip routing entry,
   irqchip.pin + 32 corresponds to the injected SPI ID.
@@ -2573,12 +2818,13 @@
   to GICv3 ITS in-kernel emulation).
 
 4.76 KVM_PPC_ALLOCATE_HTAB
+--------------------------
 
-Capability: KVM_CAP_PPC_ALLOC_HTAB
-Architectures: powerpc
-Type: vm ioctl
-Parameters: Pointer to u32 containing hash table order (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PPC_ALLOC_HTAB
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: Pointer to u32 containing hash table order (in/out)
+:Returns: 0 on success, -1 on error
 
 This requests the host kernel to allocate an MMU hash table for a
 guest using the PAPR paravirtualization interface.  This only does
@@ -2609,75 +2855,88 @@
 HPTEs on the next KVM_RUN of any vcpu.
 
 4.77 KVM_S390_INTERRUPT
+-----------------------
 
-Capability: basic
-Architectures: s390
-Type: vm ioctl, vcpu ioctl
-Parameters: struct kvm_s390_interrupt (in)
-Returns: 0 on success, -1 on error
+:Capability: basic
+:Architectures: s390
+:Type: vm ioctl, vcpu ioctl
+:Parameters: struct kvm_s390_interrupt (in)
+:Returns: 0 on success, -1 on error
 
 Allows to inject an interrupt to the guest. Interrupts can be floating
 (vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
 
-Interrupt parameters are passed via kvm_s390_interrupt:
+Interrupt parameters are passed via kvm_s390_interrupt::
 
-struct kvm_s390_interrupt {
+  struct kvm_s390_interrupt {
 	__u32 type;
 	__u32 parm;
 	__u64 parm64;
-};
+  };
 
 type can be one of the following:
 
-KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm
-KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
-KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
-KVM_S390_RESTART (vcpu) - restart
-KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
-KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
-KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
-			   parameters in parm and parm64
-KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
-KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
-KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
-KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
-    I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
-    I/O interruption parameters in parm (subchannel) and parm64 (intparm,
-    interruption subclass)
-KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
-                           machine check interrupt code in parm64 (note that
-                           machine checks needing further payload are not
-                           supported by this ioctl)
+KVM_S390_SIGP_STOP (vcpu)
+    - sigp stop; optional flags in parm
+KVM_S390_PROGRAM_INT (vcpu)
+    - program check; code in parm
+KVM_S390_SIGP_SET_PREFIX (vcpu)
+    - sigp set prefix; prefix address in parm
+KVM_S390_RESTART (vcpu)
+    - restart
+KVM_S390_INT_CLOCK_COMP (vcpu)
+    - clock comparator interrupt
+KVM_S390_INT_CPU_TIMER (vcpu)
+    - CPU timer interrupt
+KVM_S390_INT_VIRTIO (vm)
+    - virtio external interrupt; external interrupt
+      parameters in parm and parm64
+KVM_S390_INT_SERVICE (vm)
+    - sclp external interrupt; sclp parameter in parm
+KVM_S390_INT_EMERGENCY (vcpu)
+    - sigp emergency; source cpu in parm
+KVM_S390_INT_EXTERNAL_CALL (vcpu)
+    - sigp external call; source cpu in parm
+KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm)
+    - compound value to indicate an
+      I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
+      I/O interruption parameters in parm (subchannel) and parm64 (intparm,
+      interruption subclass)
+KVM_S390_MCHK (vm, vcpu)
+    - machine check interrupt; cr 14 bits in parm, machine check interrupt
+      code in parm64 (note that machine checks needing further payload are not
+      supported by this ioctl)
 
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 4.78 KVM_PPC_GET_HTAB_FD
+------------------------
 
-Capability: KVM_CAP_PPC_HTAB_FD
-Architectures: powerpc
-Type: vm ioctl
-Parameters: Pointer to struct kvm_get_htab_fd (in)
-Returns: file descriptor number (>= 0) on success, -1 on error
+:Capability: KVM_CAP_PPC_HTAB_FD
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: Pointer to struct kvm_get_htab_fd (in)
+:Returns: file descriptor number (>= 0) on success, -1 on error
 
 This returns a file descriptor that can be used either to read out the
 entries in the guest's hashed page table (HPT), or to write entries to
 initialize the HPT.  The returned fd can only be written to if the
 KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
 can only be read if that bit is clear.  The argument struct looks like
-this:
+this::
 
-/* For KVM_PPC_GET_HTAB_FD */
-struct kvm_get_htab_fd {
+  /* For KVM_PPC_GET_HTAB_FD */
+  struct kvm_get_htab_fd {
 	__u64	flags;
 	__u64	start_index;
 	__u64	reserved[2];
-};
+  };
 
-/* Values for kvm_get_htab_fd.flags */
-#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
-#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+  /* Values for kvm_get_htab_fd.flags */
+  #define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+  #define KVM_GET_HTAB_WRITE		((__u64)0x2)
 
-The `start_index' field gives the index in the HPT of the entry at
+The 'start_index' field gives the index in the HPT of the entry at
 which to start reading.  It is ignored when writing.
 
 Reads on the fd will initially supply information about all
@@ -2692,29 +2951,34 @@
 series of valid HPT entries (16 bytes) each.  The header indicates how
 many valid HPT entries there are and how many invalid entries follow
 the valid entries.  The invalid entries are not represented explicitly
-in the stream.  The header format is:
+in the stream.  The header format is::
 
-struct kvm_get_htab_header {
+  struct kvm_get_htab_header {
 	__u32	index;
 	__u16	n_valid;
 	__u16	n_invalid;
-};
+  };
 
 Writes to the fd create HPT entries starting at the index given in the
-header; first `n_valid' valid entries with contents from the data
-written, then `n_invalid' invalid entries, invalidating any previously
+header; first 'n_valid' valid entries with contents from the data
+written, then 'n_invalid' invalid entries, invalidating any previously
 valid entries found.
 
 4.79 KVM_CREATE_DEVICE
+----------------------
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: vm ioctl
-Parameters: struct kvm_create_device (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_DEVICE_CTRL
+:Type: vm ioctl
+:Parameters: struct kvm_create_device (in/out)
+:Returns: 0 on success, -1 on error
+
 Errors:
-  ENODEV: The device type is unknown or unsupported
-  EEXIST: Device already created, and this type of device may not
+
+  ======  =======================================================
+  ENODEV  The device type is unknown or unsupported
+  EEXIST  Device already created, and this type of device may not
           be instantiated multiple times
+  ======  =======================================================
 
   Other error conditions may be defined by individual device types or
   have their standard meanings.
@@ -2730,25 +2994,32 @@
 for specifying any behavior that is not implied by the device type
 number.
 
-struct kvm_create_device {
+::
+
+  struct kvm_create_device {
 	__u32	type;	/* in: KVM_DEV_TYPE_xxx */
 	__u32	fd;	/* out: device handle */
 	__u32	flags;	/* in: KVM_CREATE_DEVICE_xxx */
-};
+  };
 
 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
+--------------------------------------------
 
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
-  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
-Type: device ioctl, vm ioctl, vcpu ioctl
-Parameters: struct kvm_device_attr
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+             KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+:Type: device ioctl, vm ioctl, vcpu ioctl
+:Parameters: struct kvm_device_attr
+:Returns: 0 on success, -1 on error
+
 Errors:
-  ENXIO:  The group or attribute is unknown/unsupported for this device
+
+  =====   =============================================================
+  ENXIO   The group or attribute is unknown/unsupported for this device
           or hardware support is missing.
-  EPERM:  The attribute cannot (currently) be accessed this way
+  EPERM   The attribute cannot (currently) be accessed this way
           (e.g. read-only attribute, or attribute that only makes
           sense when the device is in a different state)
+  =====   =============================================================
 
   Other error conditions may be defined by individual device types.
 
@@ -2757,23 +3028,30 @@
 the "devices" directory.  As with ONE_REG, the size of the data
 transferred is defined by the particular attribute.
 
-struct kvm_device_attr {
+::
+
+  struct kvm_device_attr {
 	__u32	flags;		/* no flags currently defined */
 	__u32	group;		/* device-defined */
 	__u64	attr;		/* group-defined */
 	__u64	addr;		/* userspace address of attr data */
-};
+  };
 
 4.81 KVM_HAS_DEVICE_ATTR
+------------------------
 
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
-  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
-Type: device ioctl, vm ioctl, vcpu ioctl
-Parameters: struct kvm_device_attr
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+	     KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+:Type: device ioctl, vm ioctl, vcpu ioctl
+:Parameters: struct kvm_device_attr
+:Returns: 0 on success, -1 on error
+
 Errors:
-  ENXIO:  The group or attribute is unknown/unsupported for this device
+
+  =====   =============================================================
+  ENXIO   The group or attribute is unknown/unsupported for this device
           or hardware support is missing.
+  =====   =============================================================
 
 Tests whether a device supports a particular attribute.  A successful
 return indicates the attribute is implemented.  It does not necessarily
@@ -2781,15 +3059,20 @@
 current state.  "addr" is ignored.
 
 4.82 KVM_ARM_VCPU_INIT
+----------------------
 
-Capability: basic
-Architectures: arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_vcpu_init (in)
-Returns: 0 on success; -1 on error
+:Capability: basic
+:Architectures: arm, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_vcpu_init (in)
+:Returns: 0 on success; -1 on error
+
 Errors:
-  EINVAL:    the target is unknown, or the combination of features is invalid.
-  ENOENT:    a features bit specified is unknown.
+
+  ======     =================================================================
+  EINVAL     the target is unknown, or the combination of features is invalid.
+  ENOENT     a features bit specified is unknown.
+  ======     =================================================================
 
 This tells KVM what type of CPU to present to the guest, and what
 optional features it should have.  This will cause a reset of the cpu
@@ -2805,6 +3088,7 @@
 target and same set of feature flags, otherwise EINVAL will be returned.
 
 Possible features:
+
 	- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
 	  Depends on KVM_CAP_ARM_PSCI.  If not set, the CPU will be powered on
 	  and execute guest code when KVM_RUN is called.
@@ -2861,14 +3145,19 @@
 	        no longer be written using KVM_SET_ONE_REG.
 
 4.83 KVM_ARM_PREFERRED_TARGET
+-----------------------------
 
-Capability: basic
-Architectures: arm, arm64
-Type: vm ioctl
-Parameters: struct struct kvm_vcpu_init (out)
-Returns: 0 on success; -1 on error
+:Capability: basic
+:Architectures: arm, arm64
+:Type: vm ioctl
+:Parameters: struct struct kvm_vcpu_init (out)
+:Returns: 0 on success; -1 on error
+
 Errors:
-  ENODEV:    no preferred target available for the host
+
+  ======     ==========================================
+  ENODEV     no preferred target available for the host
+  ======     ==========================================
 
 This queries KVM for preferred CPU target type which can be emulated
 by KVM on underlying host.
@@ -2885,43 +3174,57 @@
 
 
 4.84 KVM_GET_REG_LIST
+---------------------
 
-Capability: basic
-Architectures: arm, arm64, mips
-Type: vcpu ioctl
-Parameters: struct kvm_reg_list (in/out)
-Returns: 0 on success; -1 on error
+:Capability: basic
+:Architectures: arm, arm64, mips
+:Type: vcpu ioctl
+:Parameters: struct kvm_reg_list (in/out)
+:Returns: 0 on success; -1 on error
+
 Errors:
-  E2BIG:     the reg index list is too big to fit in the array specified by
-             the user (the number required will be written into n).
 
-struct kvm_reg_list {
+  =====      ==============================================================
+  E2BIG      the reg index list is too big to fit in the array specified by
+             the user (the number required will be written into n).
+  =====      ==============================================================
+
+::
+
+  struct kvm_reg_list {
 	__u64 n; /* number of registers in reg[] */
 	__u64 reg[0];
-};
+  };
 
 This ioctl returns the guest registers that are supported for the
 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
 
 
 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
+-----------------------------------------
 
-Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
-Architectures: arm, arm64
-Type: vm ioctl
-Parameters: struct kvm_arm_device_address (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
+:Architectures: arm, arm64
+:Type: vm ioctl
+:Parameters: struct kvm_arm_device_address (in)
+:Returns: 0 on success, -1 on error
+
 Errors:
-  ENODEV: The device id is unknown
-  ENXIO:  Device not supported on current system
-  EEXIST: Address already set
-  E2BIG:  Address outside guest physical address space
-  EBUSY:  Address overlaps with other device range
 
-struct kvm_arm_device_addr {
+  ======  ============================================
+  ENODEV  The device id is unknown
+  ENXIO   Device not supported on current system
+  EEXIST  Address already set
+  E2BIG   Address outside guest physical address space
+  EBUSY   Address overlaps with other device range
+  ======  ============================================
+
+::
+
+  struct kvm_arm_device_addr {
 	__u64 id;
 	__u64 addr;
-};
+  };
 
 Specify a device address in the guest's physical address space where guests
 can access emulated or directly exposed devices, which the host kernel needs
@@ -2929,7 +3232,7 @@
 specific device.
 
 ARM/arm64 divides the id field into two parts, a device id and an
-address type id specific to the individual device.
+address type id specific to the individual device::
 
   bits:  | 63        ...       32 | 31    ...    16 | 15    ...    0 |
   field: |        0x00000000      |     device id   |  addr type id  |
@@ -2947,12 +3250,13 @@
 
 
 4.86 KVM_PPC_RTAS_DEFINE_TOKEN
+------------------------------
 
-Capability: KVM_CAP_PPC_RTAS
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_rtas_token_args
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PPC_RTAS
+:Architectures: ppc
+:Type: vm ioctl
+:Parameters: struct kvm_rtas_token_args
+:Returns: 0 on success, -1 on error
 
 Defines a token value for a RTAS (Run Time Abstraction Services)
 service in order to allow it to be handled in the kernel.  The
@@ -2966,18 +3270,21 @@
 handled.
 
 4.87 KVM_SET_GUEST_DEBUG
+------------------------
 
-Capability: KVM_CAP_SET_GUEST_DEBUG
-Architectures: x86, s390, ppc, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_guest_debug (in)
-Returns: 0 on success; -1 on error
+:Capability: KVM_CAP_SET_GUEST_DEBUG
+:Architectures: x86, s390, ppc, arm64
+:Type: vcpu ioctl
+:Parameters: struct kvm_guest_debug (in)
+:Returns: 0 on success; -1 on error
 
-struct kvm_guest_debug {
+::
+
+  struct kvm_guest_debug {
        __u32 control;
        __u32 pad;
        struct kvm_guest_debug_arch arch;
-};
+  };
 
 Set up the processor specific debug registers and configure vcpu for
 handling guest debug events. There are two parts to the structure, the
@@ -3019,26 +3326,31 @@
 structure containing architecture specific debug information.
 
 4.88 KVM_GET_EMULATED_CPUID
+---------------------------
 
-Capability: KVM_CAP_EXT_EMUL_CPUID
-Architectures: x86
-Type: system ioctl
-Parameters: struct kvm_cpuid2 (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_EXT_EMUL_CPUID
+:Architectures: x86
+:Type: system ioctl
+:Parameters: struct kvm_cpuid2 (in/out)
+:Returns: 0 on success, -1 on error
 
-struct kvm_cpuid2 {
+::
+
+  struct kvm_cpuid2 {
 	__u32 nent;
 	__u32 flags;
 	struct kvm_cpuid_entry2 entries[0];
-};
+  };
 
 The member 'flags' is used for passing flags from userspace.
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
-#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
-#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
+::
 
-struct kvm_cpuid_entry2 {
+  #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+  #define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+  #define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
+
+  struct kvm_cpuid_entry2 {
 	__u32 function;
 	__u32 index;
 	__u32 flags;
@@ -3047,7 +3359,7 @@
 	__u32 ecx;
 	__u32 edx;
 	__u32 padding[3];
-};
+  };
 
 This ioctl returns x86 cpuid features which are emulated by
 kvm.Userspace can use the information returned by this ioctl to query
@@ -3072,10 +3384,14 @@
 
 The fields in each entry are defined as follows:
 
-  function: the eax value used to obtain the entry
-  index: the ecx value used to obtain the entry (for entries that are
+  function:
+	 the eax value used to obtain the entry
+  index:
+	 the ecx value used to obtain the entry (for entries that are
          affected by ecx)
-  flags: an OR of zero or more of the following:
+  flags:
+    an OR of zero or more of the following:
+
         KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
            if the index field is valid
         KVM_CPUID_FLAG_STATEFUL_FUNC:
@@ -3085,24 +3401,28 @@
         KVM_CPUID_FLAG_STATE_READ_NEXT:
            for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
            the first entry to be read by a cpu
-   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+
+   eax, ebx, ecx, edx:
+
+         the values returned by the cpuid instruction for
          this function/index combination
 
 4.89 KVM_S390_MEM_OP
+--------------------
 
-Capability: KVM_CAP_S390_MEM_OP
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_mem_op (in)
-Returns: = 0 on success,
-         < 0 on generic error (e.g. -EFAULT or -ENOMEM),
-         > 0 if an exception occurred while walking the page tables
+:Capability: KVM_CAP_S390_MEM_OP
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_mem_op (in)
+:Returns: = 0 on success,
+          < 0 on generic error (e.g. -EFAULT or -ENOMEM),
+          > 0 if an exception occurred while walking the page tables
 
 Read or write data from/to the logical (virtual) memory of a VCPU.
 
-Parameters are specified via the following structure:
+Parameters are specified via the following structure::
 
-struct kvm_s390_mem_op {
+  struct kvm_s390_mem_op {
 	__u64 gaddr;		/* the guest address */
 	__u64 flags;		/* flags */
 	__u32 size;		/* amount of bytes */
@@ -3110,7 +3430,7 @@
 	__u64 buf;		/* buffer in userspace */
 	__u8 ar;		/* the access register number */
 	__u8 reserved[31];	/* should be set to 0 */
-};
+  };
 
 The type of operation is specified in the "op" field. It is either
 KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
@@ -3137,24 +3457,25 @@
 KVM with the currently defined set of flags.
 
 4.90 KVM_S390_GET_SKEYS
+-----------------------
 
-Capability: KVM_CAP_S390_SKEYS
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_skeys
-Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
-         keys, negative value on error
+:Capability: KVM_CAP_S390_SKEYS
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_s390_skeys
+:Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
+          keys, negative value on error
 
 This ioctl is used to get guest storage key values on the s390
-architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
+architecture. The ioctl takes parameters via the kvm_s390_skeys struct::
 
-struct kvm_s390_skeys {
+  struct kvm_s390_skeys {
 	__u64 start_gfn;
 	__u64 count;
 	__u64 skeydata_addr;
 	__u32 flags;
 	__u32 reserved[9];
-};
+  };
 
 The start_gfn field is the number of the first guest frame whose storage keys
 you want to get.
@@ -3168,12 +3489,13 @@
 bytes. This buffer will be filled with storage key data by the ioctl.
 
 4.91 KVM_S390_SET_SKEYS
+-----------------------
 
-Capability: KVM_CAP_S390_SKEYS
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_skeys
-Returns: 0 on success, negative value on error
+:Capability: KVM_CAP_S390_SKEYS
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_s390_skeys
+:Returns: 0 on success, negative value on error
 
 This ioctl is used to set guest storage key values on the s390
 architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
@@ -3195,21 +3517,27 @@
 the ioctl will return -EINVAL.
 
 4.92 KVM_S390_IRQ
+-----------------
 
-Capability: KVM_CAP_S390_INJECT_IRQ
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_irq (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_S390_INJECT_IRQ
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_irq (in)
+:Returns: 0 on success, -1 on error
+
 Errors:
-  EINVAL: interrupt type is invalid
-          type is KVM_S390_SIGP_STOP and flag parameter is invalid value
+
+
+  ======  =================================================================
+  EINVAL  interrupt type is invalid
+          type is KVM_S390_SIGP_STOP and flag parameter is invalid value,
           type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
-            than the maximum of VCPUs
-  EBUSY:  type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped
-          type is KVM_S390_SIGP_STOP and a stop irq is already pending
+          than the maximum of VCPUs
+  EBUSY   type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped,
+          type is KVM_S390_SIGP_STOP and a stop irq is already pending,
           type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
-            is already pending
+          is already pending
+  ======  =================================================================
 
 Allows to inject an interrupt to the guest.
 
@@ -3217,9 +3545,9 @@
 to inject additional payload which is not
 possible via KVM_S390_INTERRUPT.
 
-Interrupt parameters are passed via kvm_s390_irq:
+Interrupt parameters are passed via kvm_s390_irq::
 
-struct kvm_s390_irq {
+  struct kvm_s390_irq {
 	__u64 type;
 	union {
 		struct kvm_s390_io_info io;
@@ -3232,44 +3560,45 @@
 		struct kvm_s390_mchk_info mchk;
 		char reserved[64];
 	} u;
-};
+  };
 
 type can be one of the following:
 
-KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
-KVM_S390_PROGRAM_INT - program check; parameters in .pgm
-KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
-KVM_S390_RESTART - restart; no parameters
-KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
-KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
-KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
-KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
-KVM_S390_MCHK - machine check interrupt; parameters in .mchk
+- KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
+- KVM_S390_PROGRAM_INT - program check; parameters in .pgm
+- KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
+- KVM_S390_RESTART - restart; no parameters
+- KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
+- KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
+- KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
+- KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
+- KVM_S390_MCHK - machine check interrupt; parameters in .mchk
 
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 4.94 KVM_S390_GET_IRQ_STATE
+---------------------------
 
-Capability: KVM_CAP_S390_IRQ_STATE
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_irq_state (out)
-Returns: >= number of bytes copied into buffer,
-         -EINVAL if buffer size is 0,
-         -ENOBUFS if buffer size is too small to fit all pending interrupts,
-         -EFAULT if the buffer address was invalid
+:Capability: KVM_CAP_S390_IRQ_STATE
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_irq_state (out)
+:Returns: >= number of bytes copied into buffer,
+          -EINVAL if buffer size is 0,
+          -ENOBUFS if buffer size is too small to fit all pending interrupts,
+          -EFAULT if the buffer address was invalid
 
 This ioctl allows userspace to retrieve the complete state of all currently
 pending interrupts in a single buffer. Use cases include migration
 and introspection. The parameter structure contains the address of a
-userspace buffer and its length:
+userspace buffer and its length::
 
-struct kvm_s390_irq_state {
+  struct kvm_s390_irq_state {
 	__u64 buf;
 	__u32 flags;        /* will stay unused for compatibility reasons */
 	__u32 len;
 	__u32 reserved[4];  /* will stay unused for compatibility reasons */
-};
+  };
 
 Userspace passes in the above struct and for each pending interrupt a
 struct kvm_s390_irq is copied to the provided buffer.
@@ -3283,29 +3612,30 @@
 may retry with a bigger buffer.
 
 4.95 KVM_S390_SET_IRQ_STATE
+---------------------------
 
-Capability: KVM_CAP_S390_IRQ_STATE
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_irq_state (in)
-Returns: 0 on success,
-         -EFAULT if the buffer address was invalid,
-         -EINVAL for an invalid buffer length (see below),
-         -EBUSY if there were already interrupts pending,
-         errors occurring when actually injecting the
+:Capability: KVM_CAP_S390_IRQ_STATE
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: struct kvm_s390_irq_state (in)
+:Returns: 0 on success,
+          -EFAULT if the buffer address was invalid,
+          -EINVAL for an invalid buffer length (see below),
+          -EBUSY if there were already interrupts pending,
+          errors occurring when actually injecting the
           interrupt. See KVM_S390_IRQ.
 
 This ioctl allows userspace to set the complete state of all cpu-local
 interrupts currently pending for the vcpu. It is intended for restoring
 interrupt state after a migration. The input parameter is a userspace buffer
-containing a struct kvm_s390_irq_state:
+containing a struct kvm_s390_irq_state::
 
-struct kvm_s390_irq_state {
+  struct kvm_s390_irq_state {
 	__u64 buf;
 	__u32 flags;        /* will stay unused for compatibility reasons */
 	__u32 len;
 	__u32 reserved[4];  /* will stay unused for compatibility reasons */
-};
+  };
 
 The restrictions for flags and reserved apply as well.
 (see KVM_S390_GET_IRQ_STATE)
@@ -3320,20 +3650,22 @@
 which is the maximum number of possibly pending cpu-local interrupts.
 
 4.96 KVM_SMI
+------------
 
-Capability: KVM_CAP_X86_SMM
-Architectures: x86
-Type: vcpu ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_X86_SMM
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0 on success, -1 on error
 
 Queues an SMI on the thread's vcpu.
 
 4.97 KVM_CAP_PPC_MULTITCE
+-------------------------
 
-Capability: KVM_CAP_PPC_MULTITCE
-Architectures: ppc
-Type: vm
+:Capability: KVM_CAP_PPC_MULTITCE
+:Architectures: ppc
+:Type: vm
 
 This capability means the kernel is capable of handling hypercalls
 H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
@@ -3355,26 +3687,27 @@
 This capability is always enabled.
 
 4.98 KVM_CREATE_SPAPR_TCE_64
+----------------------------
 
-Capability: KVM_CAP_SPAPR_TCE_64
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_create_spapr_tce_64 (in)
-Returns: file descriptor for manipulating the created TCE table
+:Capability: KVM_CAP_SPAPR_TCE_64
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_create_spapr_tce_64 (in)
+:Returns: file descriptor for manipulating the created TCE table
 
 This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
 windows, described in 4.62 KVM_CREATE_SPAPR_TCE
 
-This capability uses extended struct in ioctl interface:
+This capability uses extended struct in ioctl interface::
 
-/* for KVM_CAP_SPAPR_TCE_64 */
-struct kvm_create_spapr_tce_64 {
+  /* for KVM_CAP_SPAPR_TCE_64 */
+  struct kvm_create_spapr_tce_64 {
 	__u64 liobn;
 	__u32 page_shift;
 	__u32 flags;
 	__u64 offset;	/* in pages */
 	__u64 size; 	/* in pages */
-};
+  };
 
 The aim of extension is to support an additional bigger DMA window with
 a variable page size.
@@ -3387,12 +3720,13 @@
 The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.
 
 4.99 KVM_REINJECT_CONTROL
+-------------------------
 
-Capability: KVM_CAP_REINJECT_CONTROL
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_reinject_control (in)
-Returns: 0 on success,
+:Capability: KVM_CAP_REINJECT_CONTROL
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_reinject_control (in)
+:Returns: 0 on success,
          -EFAULT if struct kvm_reinject_control cannot be read,
          -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
 
@@ -3402,21 +3736,24 @@
 interrupt whenever there isn't a pending interrupt from i8254.
 !reinject mode injects an interrupt as soon as a tick arrives.
 
-struct kvm_reinject_control {
+::
+
+  struct kvm_reinject_control {
 	__u8 pit_reinject;
 	__u8 reserved[31];
-};
+  };
 
 pit_reinject = 0 (!reinject mode) is recommended, unless running an old
 operating system that uses the PIT for timing (e.g. Linux 2.4.x).
 
 4.100 KVM_PPC_CONFIGURE_V3_MMU
+------------------------------
 
-Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_ppc_mmuv3_cfg (in)
-Returns: 0 on success,
+:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
+:Architectures: ppc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_mmuv3_cfg (in)
+:Returns: 0 on success,
          -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read,
          -EINVAL if the configuration is invalid
 
@@ -3424,10 +3761,12 @@
 page table) translation, and sets the pointer to the process table for
 the guest.
 
-struct kvm_ppc_mmuv3_cfg {
+::
+
+  struct kvm_ppc_mmuv3_cfg {
 	__u64	flags;
 	__u64	process_table;
-};
+  };
 
 There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and
 KVM_PPC_MMUV3_GTSE.  KVM_PPC_MMUV3_RADIX, if set, configures the guest
@@ -3442,12 +3781,13 @@
 the Power ISA V3.00, Book III section 5.7.6.1.
 
 4.101 KVM_PPC_GET_RMMU_INFO
+---------------------------
 
-Capability: KVM_CAP_PPC_RADIX_MMU
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_ppc_rmmu_info (out)
-Returns: 0 on success,
+:Capability: KVM_CAP_PPC_RADIX_MMU
+:Architectures: ppc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_rmmu_info (out)
+:Returns: 0 on success,
 	 -EFAULT if struct kvm_ppc_rmmu_info cannot be written,
 	 -EINVAL if no useful information can be returned
 
@@ -3456,14 +3796,16 @@
 page sizes to put in the "AP" (actual page size) field for the tlbie
 (TLB invalidate entry) instruction.
 
-struct kvm_ppc_rmmu_info {
+::
+
+  struct kvm_ppc_rmmu_info {
 	struct kvm_ppc_radix_geom {
 		__u8	page_shift;
 		__u8	level_bits[4];
 		__u8	pad[3];
 	}	geometries[8];
 	__u32	ap_encodings[8];
-};
+  };
 
 The geometries[] field gives up to 8 supported geometries for the
 radix page table, in terms of the log base 2 of the smallest page
@@ -3476,19 +3818,54 @@
 base 2 of the page size in the bottom 6 bits.
 
 4.102 KVM_PPC_RESIZE_HPT_PREPARE
+--------------------------------
 
-Capability: KVM_CAP_SPAPR_RESIZE_HPT
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_ppc_resize_hpt (in)
-Returns: 0 on successful completion,
+:Capability: KVM_CAP_SPAPR_RESIZE_HPT
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_resize_hpt (in)
+:Returns: 0 on successful completion,
 	 >0 if a new HPT is being prepared, the value is an estimated
-             number of milliseconds until preparation is complete
+         number of milliseconds until preparation is complete,
          -EFAULT if struct kvm_reinject_control cannot be read,
-	 -EINVAL if the supplied shift or flags are invalid
-	 -ENOMEM if unable to allocate the new HPT
-	 -ENOSPC if there was a hash collision when moving existing
-                  HPT entries to the new HPT
+	 -EINVAL if the supplied shift or flags are invalid,
+	 -ENOMEM if unable to allocate the new HPT,
+	 -ENOSPC if there was a hash collision
+
+::
+
+  struct kvm_ppc_rmmu_info {
+	struct kvm_ppc_radix_geom {
+		__u8	page_shift;
+		__u8	level_bits[4];
+		__u8	pad[3];
+	}	geometries[8];
+	__u32	ap_encodings[8];
+  };
+
+The geometries[] field gives up to 8 supported geometries for the
+radix page table, in terms of the log base 2 of the smallest page
+size, and the number of bits indexed at each level of the tree, from
+the PTE level up to the PGD level in that order.  Any unused entries
+will have 0 in the page_shift field.
+
+The ap_encodings gives the supported page sizes and their AP field
+encodings, encoded with the AP value in the top 3 bits and the log
+base 2 of the page size in the bottom 6 bits.
+
+4.102 KVM_PPC_RESIZE_HPT_PREPARE
+--------------------------------
+
+:Capability: KVM_CAP_SPAPR_RESIZE_HPT
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_resize_hpt (in)
+:Returns: 0 on successful completion,
+	 >0 if a new HPT is being prepared, the value is an estimated
+         number of milliseconds until preparation is complete,
+         -EFAULT if struct kvm_reinject_control cannot be read,
+	 -EINVAL if the supplied shift or flags are invalid,when moving existing
+         HPT entries to the new HPT,
 	 -EIO on other error conditions
 
 Used to implement the PAPR extension for runtime resizing of a guest's
@@ -3506,6 +3883,7 @@
 creates a new one as above.
 
 If called when there is a pending HPT of the size requested, will:
+
   * If preparation of the pending HPT is already complete, return 0
   * If preparation of the pending HPT has failed, return an error
     code, then discard the pending HPT.
@@ -3522,26 +3900,29 @@
 it returns <= 0.  The first call will initiate preparation, subsequent
 ones will monitor preparation until it completes or fails.
 
-struct kvm_ppc_resize_hpt {
+::
+
+  struct kvm_ppc_resize_hpt {
 	__u64 flags;
 	__u32 shift;
 	__u32 pad;
-};
+  };
 
 4.103 KVM_PPC_RESIZE_HPT_COMMIT
+-------------------------------
 
-Capability: KVM_CAP_SPAPR_RESIZE_HPT
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_ppc_resize_hpt (in)
-Returns: 0 on successful completion,
+:Capability: KVM_CAP_SPAPR_RESIZE_HPT
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_resize_hpt (in)
+:Returns: 0 on successful completion,
          -EFAULT if struct kvm_reinject_control cannot be read,
-	 -EINVAL if the supplied shift or flags are invalid
+	 -EINVAL if the supplied shift or flags are invalid,
 	 -ENXIO is there is no pending HPT, or the pending HPT doesn't
-                 have the requested size
-	 -EBUSY if the pending HPT is not fully prepared
+         have the requested size,
+	 -EBUSY if the pending HPT is not fully prepared,
 	 -ENOSPC if there was a hash collision when moving existing
-                  HPT entries to the new HPT
+         HPT entries to the new HPT,
 	 -EIO on other error conditions
 
 Used to implement the PAPR extension for runtime resizing of a guest's
@@ -3564,31 +3945,35 @@
 
 On failure, the guest will still be operating on its previous HPT.
 
-struct kvm_ppc_resize_hpt {
+::
+
+  struct kvm_ppc_resize_hpt {
 	__u64 flags;
 	__u32 shift;
 	__u32 pad;
-};
+  };
 
 4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
+-----------------------------------
 
-Capability: KVM_CAP_MCE
-Architectures: x86
-Type: system ioctl
-Parameters: u64 mce_cap (out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_MCE
+:Architectures: x86
+:Type: system ioctl
+:Parameters: u64 mce_cap (out)
+:Returns: 0 on success, -1 on error
 
 Returns supported MCE capabilities. The u64 mce_cap parameter
 has the same format as the MSR_IA32_MCG_CAP register. Supported
 capabilities will have the corresponding bits set.
 
 4.105 KVM_X86_SETUP_MCE
+-----------------------
 
-Capability: KVM_CAP_MCE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: u64 mcg_cap (in)
-Returns: 0 on success,
+:Capability: KVM_CAP_MCE
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: u64 mcg_cap (in)
+:Returns: 0 on success,
          -EFAULT if u64 mcg_cap cannot be read,
          -EINVAL if the requested number of banks is invalid,
          -EINVAL if requested MCE capability is not supported.
@@ -3601,20 +3986,21 @@
 retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
 
 4.106 KVM_X86_SET_MCE
+---------------------
 
-Capability: KVM_CAP_MCE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_x86_mce (in)
-Returns: 0 on success,
+:Capability: KVM_CAP_MCE
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_x86_mce (in)
+:Returns: 0 on success,
          -EFAULT if struct kvm_x86_mce cannot be read,
          -EINVAL if the bank number is invalid,
          -EINVAL if VAL bit is not set in status field.
 
 Inject a machine check error (MCE) into the guest. The input
-parameter is:
+parameter is::
 
-struct kvm_x86_mce {
+  struct kvm_x86_mce {
 	__u64 status;
 	__u64 addr;
 	__u64 misc;
@@ -3622,7 +4008,7 @@
 	__u8 bank;
 	__u8 pad1[7];
 	__u64 pad2[3];
-};
+  };
 
 If the MCE being reported is an uncorrected error, KVM will
 inject it as an MCE exception into the guest. If the guest
@@ -3634,15 +4020,17 @@
 not holding a previously reported uncorrected error).
 
 4.107 KVM_S390_GET_CMMA_BITS
+----------------------------
 
-Capability: KVM_CAP_S390_CMMA_MIGRATION
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_cmma_log (in, out)
-Returns: 0 on success, a negative value on error
+:Capability: KVM_CAP_S390_CMMA_MIGRATION
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_s390_cmma_log (in, out)
+:Returns: 0 on success, a negative value on error
 
 This ioctl is used to get the values of the CMMA bits on the s390
 architecture. It is meant to be used in two scenarios:
+
 - During live migration to save the CMMA values. Live migration needs
   to be enabled via the KVM_REQ_START_MIGRATION VM property.
 - To non-destructively peek at the CMMA values, with the flag
@@ -3652,9 +4040,12 @@
 values are written to a buffer whose location is indicated via the "values"
 member in the kvm_s390_cmma_log struct.  The values in the input struct are
 also updated as needed.
+
 Each CMMA value takes up one byte.
 
-struct kvm_s390_cmma_log {
+::
+
+  struct kvm_s390_cmma_log {
 	__u64 start_gfn;
 	__u32 count;
 	__u32 flags;
@@ -3663,7 +4054,7 @@
 		__u64 mask;
 	};
 	__u64 values;
-};
+  };
 
 start_gfn is the number of the first guest frame whose CMMA values are
 to be retrieved,
@@ -3724,12 +4115,13 @@
 present for the addresses (e.g. when using hugepages).
 
 4.108 KVM_S390_SET_CMMA_BITS
+----------------------------
 
-Capability: KVM_CAP_S390_CMMA_MIGRATION
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_cmma_log (in)
-Returns: 0 on success, a negative value on error
+:Capability: KVM_CAP_S390_CMMA_MIGRATION
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_s390_cmma_log (in)
+:Returns: 0 on success, a negative value on error
 
 This ioctl is used to set the values of the CMMA bits on the s390
 architecture. It is meant to be used during live migration to restore
@@ -3737,16 +4129,18 @@
 The ioctl takes parameters via the kvm_s390_cmma_values struct.
 Each CMMA value takes up one byte.
 
-struct kvm_s390_cmma_log {
+::
+
+  struct kvm_s390_cmma_log {
 	__u64 start_gfn;
 	__u32 count;
 	__u32 flags;
 	union {
 		__u64 remaining;
 		__u64 mask;
-	};
+ 	};
 	__u64 values;
-};
+  };
 
 start_gfn indicates the starting guest frame number,
 
@@ -3769,26 +4163,27 @@
 hugepages).
 
 4.109 KVM_PPC_GET_CPU_CHAR
+--------------------------
 
-Capability: KVM_CAP_PPC_GET_CPU_CHAR
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_ppc_cpu_char (out)
-Returns: 0 on successful completion
+:Capability: KVM_CAP_PPC_GET_CPU_CHAR
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: struct kvm_ppc_cpu_char (out)
+:Returns: 0 on successful completion,
 	 -EFAULT if struct kvm_ppc_cpu_char cannot be written
 
 This ioctl gives userspace information about certain characteristics
 of the CPU relating to speculative execution of instructions and
 possible information leakage resulting from speculative execution (see
 CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754).  The information is
-returned in struct kvm_ppc_cpu_char, which looks like this:
+returned in struct kvm_ppc_cpu_char, which looks like this::
 
-struct kvm_ppc_cpu_char {
+  struct kvm_ppc_cpu_char {
 	__u64	character;		/* characteristics of the CPU */
 	__u64	behaviour;		/* recommended software behaviour */
 	__u64	character_mask;		/* valid bits in character */
 	__u64	behaviour_mask;		/* valid bits in behaviour */
-};
+  };
 
 For extensibility, the character_mask and behaviour_mask fields
 indicate which bits of character and behaviour have been filled in by
@@ -3815,12 +4210,13 @@
 H_GET_CPU_CHARACTERISTICS hypercall.
 
 4.110 KVM_MEMORY_ENCRYPT_OP
+---------------------------
 
-Capability: basic
-Architectures: x86
-Type: system
-Parameters: an opaque platform specific structure (in/out)
-Returns: 0 on success; -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: system
+:Parameters: an opaque platform specific structure (in/out)
+:Returns: 0 on success; -1 on error
 
 If the platform supports creating encrypted VMs then this ioctl can be used
 for issuing platform-specific memory encryption commands to manage those
@@ -3831,12 +4227,13 @@
 Documentation/virt/kvm/amd-memory-encryption.rst.
 
 4.111 KVM_MEMORY_ENCRYPT_REG_REGION
+-----------------------------------
 
-Capability: basic
-Architectures: x86
-Type: system
-Parameters: struct kvm_enc_region (in)
-Returns: 0 on success; -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: system
+:Parameters: struct kvm_enc_region (in)
+:Returns: 0 on success; -1 on error
 
 This ioctl can be used to register a guest memory region which may
 contain encrypted data (e.g. guest RAM, SMRAM etc).
@@ -3854,60 +4251,71 @@
 memory region registered with the ioctl.
 
 4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION
+-------------------------------------
 
-Capability: basic
-Architectures: x86
-Type: system
-Parameters: struct kvm_enc_region (in)
-Returns: 0 on success; -1 on error
+:Capability: basic
+:Architectures: x86
+:Type: system
+:Parameters: struct kvm_enc_region (in)
+:Returns: 0 on success; -1 on error
 
 This ioctl can be used to unregister the guest memory region registered
 with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
 
 4.113 KVM_HYPERV_EVENTFD
+------------------------
 
-Capability: KVM_CAP_HYPERV_EVENTFD
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_hyperv_eventfd (in)
+:Capability: KVM_CAP_HYPERV_EVENTFD
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_hyperv_eventfd (in)
 
 This ioctl (un)registers an eventfd to receive notifications from the guest on
 the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
 causing a user exit.  SIGNAL_EVENT hypercall with non-zero event flag number
 (bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
 
-struct kvm_hyperv_eventfd {
+::
+
+  struct kvm_hyperv_eventfd {
 	__u32 conn_id;
 	__s32 fd;
 	__u32 flags;
 	__u32 padding[3];
-};
+  };
 
-The conn_id field should fit within 24 bits:
+The conn_id field should fit within 24 bits::
 
-#define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
+  #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 
-The acceptable values for the flags field are:
+The acceptable values for the flags field are::
 
-#define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
+  #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
-Returns: 0 on success,
-	-EINVAL if conn_id or flags is outside the allowed range
-	-ENOENT on deassign if the conn_id isn't registered
-	-EEXIST on assign if the conn_id is already registered
+:Returns: 0 on success,
+ 	  -EINVAL if conn_id or flags is outside the allowed range,
+	  -ENOENT on deassign if the conn_id isn't registered,
+	  -EEXIST on assign if the conn_id is already registered
 
 4.114 KVM_GET_NESTED_STATE
+--------------------------
 
-Capability: KVM_CAP_NESTED_STATE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_nested_state (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_NESTED_STATE
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_nested_state (in/out)
+:Returns: 0 on success, -1 on error
+
 Errors:
-  E2BIG:     the total state size exceeds the value of 'size' specified by
-             the user; the size required will be written into size.
 
-struct kvm_nested_state {
+  =====      =============================================================
+  E2BIG      the total state size exceeds the value of 'size' specified by
+             the user; the size required will be written into size.
+  =====      =============================================================
+
+::
+
+  struct kvm_nested_state {
 	__u16 flags;
 	__u16 format;
 	__u32 size;
@@ -3924,33 +4332,33 @@
 		struct kvm_vmx_nested_state_data vmx[0];
 		struct kvm_svm_nested_state_data svm[0];
 	} data;
-};
+  };
 
-#define KVM_STATE_NESTED_GUEST_MODE	0x00000001
-#define KVM_STATE_NESTED_RUN_PENDING	0x00000002
-#define KVM_STATE_NESTED_EVMCS		0x00000004
+  #define KVM_STATE_NESTED_GUEST_MODE		0x00000001
+  #define KVM_STATE_NESTED_RUN_PENDING		0x00000002
+  #define KVM_STATE_NESTED_EVMCS		0x00000004
 
-#define KVM_STATE_NESTED_FORMAT_VMX		0
-#define KVM_STATE_NESTED_FORMAT_SVM		1
+  #define KVM_STATE_NESTED_FORMAT_VMX		0
+  #define KVM_STATE_NESTED_FORMAT_SVM		1
 
-#define KVM_STATE_NESTED_VMX_VMCS_SIZE		0x1000
+  #define KVM_STATE_NESTED_VMX_VMCS_SIZE	0x1000
 
-#define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE	0x00000001
-#define KVM_STATE_NESTED_VMX_SMM_VMXON		0x00000002
+  #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE	0x00000001
+  #define KVM_STATE_NESTED_VMX_SMM_VMXON	0x00000002
 
-struct kvm_vmx_nested_state_hdr {
+  struct kvm_vmx_nested_state_hdr {
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
 
 	struct {
 		__u16 flags;
 	} smm;
-};
+  };
 
-struct kvm_vmx_nested_state_data {
+  struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
 	__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
-};
+  };
 
 This ioctl copies the vcpu's nested virtualization state from the kernel to
 userspace.
@@ -3959,24 +4367,26 @@
 to the KVM_CHECK_EXTENSION ioctl().
 
 4.115 KVM_SET_NESTED_STATE
+--------------------------
 
-Capability: KVM_CAP_NESTED_STATE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_nested_state (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_NESTED_STATE
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_nested_state (in)
+:Returns: 0 on success, -1 on error
 
 This copies the vcpu's kvm_nested_state struct from userspace to the kernel.
 For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
 
 4.116 KVM_(UN)REGISTER_COALESCED_MMIO
+-------------------------------------
 
-Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
-	    KVM_CAP_COALESCED_PIO (for coalesced pio)
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_coalesced_mmio_zone
-Returns: 0 on success, < 0 on error
+:Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
+	     KVM_CAP_COALESCED_PIO (for coalesced pio)
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_coalesced_mmio_zone
+:Returns: 0 on success, < 0 on error
 
 Coalesced I/O is a performance optimization that defers hardware
 register write emulation so that userspace exits are avoided.  It is
@@ -3998,15 +4408,18 @@
 to I/O ports.
 
 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
+------------------------------------
 
-Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
-Architectures: x86, arm, arm64, mips
-Type: vm ioctl
-Parameters: struct kvm_dirty_log (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
+:Architectures: x86, arm, arm64, mips
+:Type: vm ioctl
+:Parameters: struct kvm_dirty_log (in)
+:Returns: 0 on success, -1 on error
 
-/* for KVM_CLEAR_DIRTY_LOG */
-struct kvm_clear_dirty_log {
+::
+
+  /* for KVM_CLEAR_DIRTY_LOG */
+  struct kvm_clear_dirty_log {
 	__u32 slot;
 	__u32 num_pages;
 	__u64 first_page;
@@ -4014,7 +4427,7 @@
 		void __user *dirty_bitmap; /* one bit per page */
 		__u64 padding;
 	};
-};
+  };
 
 The ioctl clears the dirty status of pages in a memory slot, according to
 the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
@@ -4038,20 +4451,23 @@
 that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present.
 
 4.118 KVM_GET_SUPPORTED_HV_CPUID
+--------------------------------
 
-Capability: KVM_CAP_HYPERV_CPUID
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_cpuid2 (in/out)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_HYPERV_CPUID
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_cpuid2 (in/out)
+:Returns: 0 on success, -1 on error
 
-struct kvm_cpuid2 {
+::
+
+  struct kvm_cpuid2 {
 	__u32 nent;
 	__u32 padding;
 	struct kvm_cpuid_entry2 entries[0];
-};
+  };
 
-struct kvm_cpuid_entry2 {
+  struct kvm_cpuid_entry2 {
 	__u32 function;
 	__u32 index;
 	__u32 flags;
@@ -4060,7 +4476,7 @@
 	__u32 ecx;
 	__u32 edx;
 	__u32 padding[3];
-};
+  };
 
 This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in
 KVM.  Userspace can use the information returned by this ioctl to construct
@@ -4073,13 +4489,13 @@
 leaves (0x40000000, 0x40000001).
 
 Currently, the following list of CPUID leaves are returned:
- HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
- HYPERV_CPUID_INTERFACE
- HYPERV_CPUID_VERSION
- HYPERV_CPUID_FEATURES
- HYPERV_CPUID_ENLIGHTMENT_INFO
- HYPERV_CPUID_IMPLEMENT_LIMITS
- HYPERV_CPUID_NESTED_FEATURES
+ - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
+ - HYPERV_CPUID_INTERFACE
+ - HYPERV_CPUID_VERSION
+ - HYPERV_CPUID_FEATURES
+ - HYPERV_CPUID_ENLIGHTMENT_INFO
+ - HYPERV_CPUID_IMPLEMENT_LIMITS
+ - HYPERV_CPUID_NESTED_FEATURES
 
 HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
 enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
@@ -4095,17 +4511,25 @@
 userspace should not expect to get any particular value there.
 
 4.119 KVM_ARM_VCPU_FINALIZE
+---------------------------
 
-Architectures: arm, arm64
-Type: vcpu ioctl
-Parameters: int feature (in)
-Returns: 0 on success, -1 on error
+:Architectures: arm, arm64
+:Type: vcpu ioctl
+:Parameters: int feature (in)
+:Returns: 0 on success, -1 on error
+
 Errors:
-  EPERM:     feature not enabled, needs configuration, or already finalized
-  EINVAL:    feature unknown or not present
+
+  ======     ==============================================================
+  EPERM      feature not enabled, needs configuration, or already finalized
+  EINVAL     feature unknown or not present
+  ======     ==============================================================
 
 Recognised values for feature:
+
+  =====      ===========================================
   arm64      KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE)
+  =====      ===========================================
 
 Finalizes the configuration of the specified vcpu feature.
 
@@ -4129,21 +4553,24 @@
 using this ioctl.
 
 4.120 KVM_SET_PMU_EVENT_FILTER
+------------------------------
 
-Capability: KVM_CAP_PMU_EVENT_FILTER
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pmu_event_filter (in)
-Returns: 0 on success, -1 on error
+:Capability: KVM_CAP_PMU_EVENT_FILTER
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_pmu_event_filter (in)
+:Returns: 0 on success, -1 on error
 
-struct kvm_pmu_event_filter {
+::
+
+  struct kvm_pmu_event_filter {
 	__u32 action;
 	__u32 nevents;
 	__u32 fixed_counter_bitmap;
 	__u32 flags;
 	__u32 pad[4];
 	__u64 events[0];
-};
+  };
 
 This ioctl restricts the set of PMU events that the guest can program.
 The argument holds a list of events which will be allowed or denied.
@@ -4154,20 +4581,26 @@
 
 No flags are defined yet, the field must be zero.
 
-Valid values for 'action':
-#define KVM_PMU_EVENT_ALLOW 0
-#define KVM_PMU_EVENT_DENY 1
+Valid values for 'action'::
+
+  #define KVM_PMU_EVENT_ALLOW 0
+  #define KVM_PMU_EVENT_DENY 1
 
 4.121 KVM_PPC_SVM_OFF
+---------------------
 
-Capability: basic
-Architectures: powerpc
-Type: vm ioctl
-Parameters: none
-Returns: 0 on successful completion,
+:Capability: basic
+:Architectures: powerpc
+:Type: vm ioctl
+:Parameters: none
+:Returns: 0 on successful completion,
+
 Errors:
-  EINVAL:    if ultravisor failed to terminate the secure guest
-  ENOMEM:    if hypervisor failed to allocate new radix page tables for guest
+
+  ======     ================================================================
+  EINVAL     if ultravisor failed to terminate the secure guest
+  ENOMEM     if hypervisor failed to allocate new radix page tables for guest
+  ======     ================================================================
 
 This ioctl is used to turn off the secure mode of the guest or transition
 the guest from secure mode to normal mode. This is invoked when the guest
@@ -4214,7 +4647,7 @@
 
 
 5. The kvm_run structure
-------------------------
+========================
 
 Application code obtains a pointer to the kvm_run structure by
 mmap()ing a vcpu fd.  From that point, application code can control
@@ -4222,13 +4655,17 @@
 ioctl, and obtain information about the reason KVM_RUN returned by
 looking up structure members.
 
-struct kvm_run {
+::
+
+  struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
 
 Request that KVM_RUN return when it becomes possible to inject external
 interrupts into the guest.  Useful in conjunction with KVM_INTERRUPT.
 
+::
+
 	__u8 immediate_exit;
 
 This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
@@ -4240,6 +4677,8 @@
 
 This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available.
 
+::
+
 	__u8 padding1[6];
 
 	/* out */
@@ -4249,16 +4688,22 @@
 application code why KVM_RUN has returned.  Allowable values for this
 field are detailed below.
 
+::
+
 	__u8 ready_for_interrupt_injection;
 
 If request_interrupt_window has been specified, this field indicates
 an interrupt can be injected now with KVM_INTERRUPT.
 
+::
+
 	__u8 if_flag;
 
 The value of the current interrupt flag.  Only valid if in-kernel
 local APIC is not used.
 
+::
+
 	__u16 flags;
 
 More architecture-specific flags detailing state of the VCPU that may
@@ -4266,17 +4711,23 @@
 KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
 VCPU is in system management mode.
 
+::
+
 	/* in (pre_kvm_run), out (post_kvm_run) */
 	__u64 cr8;
 
 The value of the cr8 register.  Only valid if in-kernel local APIC is
 not used.  Both input and output.
 
+::
+
 	__u64 apic_base;
 
 The value of the APIC BASE msr.  Only valid if in-kernel local
 APIC is not used.  Both input and output.
 
+::
+
 	union {
 		/* KVM_EXIT_UNKNOWN */
 		struct {
@@ -4287,6 +4738,8 @@
 reasons.  Further architecture-specific information is available in
 hardware_exit_reason.
 
+::
+
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
@@ -4296,6 +4749,8 @@
 to unknown reasons.  Further architecture-specific information is
 available in hardware_entry_failure_reason.
 
+::
+
 		/* KVM_EXIT_EXCEPTION */
 		struct {
 			__u32 exception;
@@ -4304,10 +4759,12 @@
 
 Unused.
 
+::
+
 		/* KVM_EXIT_IO */
 		struct {
-#define KVM_EXIT_IO_IN  0
-#define KVM_EXIT_IO_OUT 1
+  #define KVM_EXIT_IO_IN  0
+  #define KVM_EXIT_IO_OUT 1
 			__u8 direction;
 			__u8 size; /* bytes */
 			__u16 port;
@@ -4321,6 +4778,8 @@
 where kvm expects application code to place the data for the next
 KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
+::
+
 		/* KVM_EXIT_DEBUG */
 		struct {
 			struct kvm_debug_exit_arch arch;
@@ -4329,6 +4788,8 @@
 If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
 for which architecture specific information is returned.
 
+::
+
 		/* KVM_EXIT_MMIO */
 		struct {
 			__u64 phys_addr;
@@ -4346,14 +4807,19 @@
 appear if the VCPU performed a load or store of the appropriate width directly
 to the byte array.
 
-NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
+.. note::
+
+      For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
       KVM_EXIT_EPR the corresponding
+
 operations are complete (and guest state is consistent) only after userspace
 has re-entered the kernel with KVM_RUN.  The kernel side will first finish
 incomplete operations and then check for pending signals.  Userspace
 can re-enter the guest with an unmasked signal pending to complete
 pending operations.
 
+::
+
 		/* KVM_EXIT_HYPERCALL */
 		struct {
 			__u64 nr;
@@ -4365,7 +4831,10 @@
 
 Unused.  This was once used for 'hypercall to userspace'.  To implement
 such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
-Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
+
+.. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
+
+::
 
 		/* KVM_EXIT_TPR_ACCESS */
 		struct {
@@ -4376,6 +4845,8 @@
 
 To be documented (KVM_TPR_ACCESS_REPORTING).
 
+::
+
 		/* KVM_EXIT_S390_SIEIC */
 		struct {
 			__u8 icptcode;
@@ -4387,16 +4858,20 @@
 
 s390 specific.
 
+::
+
 		/* KVM_EXIT_S390_RESET */
-#define KVM_S390_RESET_POR       1
-#define KVM_S390_RESET_CLEAR     2
-#define KVM_S390_RESET_SUBSYSTEM 4
-#define KVM_S390_RESET_CPU_INIT  8
-#define KVM_S390_RESET_IPL       16
+  #define KVM_S390_RESET_POR       1
+  #define KVM_S390_RESET_CLEAR     2
+  #define KVM_S390_RESET_SUBSYSTEM 4
+  #define KVM_S390_RESET_CPU_INIT  8
+  #define KVM_S390_RESET_IPL       16
 		__u64 s390_reset_flags;
 
 s390 specific.
 
+::
+
 		/* KVM_EXIT_S390_UCONTROL */
 		struct {
 			__u64 trans_exc_code;
@@ -4411,6 +4886,8 @@
 Principles of Operation Book in the Chapter for Dynamic Address Translation
 (DAT)
 
+::
+
 		/* KVM_EXIT_DCR */
 		struct {
 			__u32 dcrn;
@@ -4420,6 +4897,8 @@
 
 Deprecated - was used for 440 KVM.
 
+::
+
 		/* KVM_EXIT_OSI */
 		struct {
 			__u64 gprs[32];
@@ -4433,6 +4912,8 @@
 necessary. Upon guest entry all guest GPRs will then be replaced by the values
 in this struct.
 
+::
+
 		/* KVM_EXIT_PAPR_HCALL */
 		struct {
 			__u64 nr;
@@ -4450,6 +4931,8 @@
 Requirements (PAPR) document available from www.power.org (free
 developer registration required to access it).
 
+::
+
 		/* KVM_EXIT_S390_TSCH */
 		struct {
 			__u16 subchannel_id;
@@ -4466,6 +4949,8 @@
 subchannel_nr, io_int_parm and io_int_word contain the parameters for that
 interrupt. ipb is needed for instruction parameter decoding.
 
+::
+
 		/* KVM_EXIT_EPR */
 		struct {
 			__u32 epr;
@@ -4485,11 +4970,13 @@
 external interrupt has just been delivered into the guest. User space
 should put the acknowledged interrupt vector into the 'epr' field.
 
+::
+
 		/* KVM_EXIT_SYSTEM_EVENT */
 		struct {
-#define KVM_SYSTEM_EVENT_SHUTDOWN       1
-#define KVM_SYSTEM_EVENT_RESET          2
-#define KVM_SYSTEM_EVENT_CRASH          3
+  #define KVM_SYSTEM_EVENT_SHUTDOWN       1
+  #define KVM_SYSTEM_EVENT_RESET          2
+  #define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
 			__u64 flags;
 		} system_event;
@@ -4502,18 +4989,21 @@
 specific flags for the system-level event.
 
 Valid values for 'type' are:
-  KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
+
+ - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
    VM. Userspace is not obliged to honour this, and if it does honour
    this does not need to destroy the VM synchronously (ie it may call
    KVM_RUN again before shutdown finally occurs).
-  KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
+ - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
    As with SHUTDOWN, userspace can choose to ignore the request, or
    to schedule the reset to occur in the future and may call KVM_RUN again.
-  KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
+ - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
    has requested a crash condition maintenance. Userspace can choose
    to ignore the request, or to gather VM memory core dump and/or
    reset/shutdown of the VM.
 
+::
+
 		/* KVM_EXIT_IOAPIC_EOI */
 		struct {
 			__u8 vector;
@@ -4526,9 +5016,11 @@
 it is still asserted.  Vector is the LAPIC interrupt vector for which the
 EOI was received.
 
+::
+
 		struct kvm_hyperv_exit {
-#define KVM_EXIT_HYPERV_SYNIC          1
-#define KVM_EXIT_HYPERV_HCALL          2
+  #define KVM_EXIT_HYPERV_SYNIC          1
+  #define KVM_EXIT_HYPERV_HCALL          2
 			__u32 type;
 			union {
 				struct {
@@ -4546,14 +5038,20 @@
 		};
 		/* KVM_EXIT_HYPERV */
                 struct kvm_hyperv_exit hyperv;
+
 Indicates that the VCPU exits into userspace to process some tasks
 related to Hyper-V emulation.
+
 Valid values for 'type' are:
-	KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
+
+	- KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
+
 Hyper-V SynIC state change. Notification is used to remap SynIC
 event/message pages and to enable/disable SynIC messages/events processing
 in userspace.
 
+::
+
 		/* KVM_EXIT_ARM_NISV */
 		struct {
 			__u64 esr_iss;
@@ -4587,6 +5085,8 @@
 KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state
 if it decides to decode and emulate the instruction.
 
+::
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -4611,18 +5111,20 @@
 Userspace can query the validity of the structure by checking
 kvm_valid_regs for specific bits. These bits are architecture specific
 and usually define the validity of a groups of registers. (e.g. one bit
- for general purpose registers)
+for general purpose registers)
 
 Please note that the kernel is allowed to use the kvm_run structure as the
 primary storage for certain register types. Therefore, the kernel may use the
 values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
 
-};
+::
+
+  };
 
 
 
 6. Capabilities that can be enabled on vCPUs
---------------------------------------------
+============================================
 
 There are certain capabilities that change the behavior of the virtual CPU or
 the virtual machine when enabled. To enable them, please see section 4.37.
@@ -4631,23 +5133,28 @@
 
 The following information is provided along with the description:
 
-  Architectures: which instruction set architectures provide this ioctl.
+  Architectures:
+      which instruction set architectures provide this ioctl.
       x86 includes both i386 and x86_64.
 
-  Target: whether this is a per-vcpu or per-vm capability.
+  Target:
+      whether this is a per-vcpu or per-vm capability.
 
-  Parameters: what parameters are accepted by the capability.
+  Parameters:
+      what parameters are accepted by the capability.
 
-  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
+  Returns:
+      the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
       are not detailed, but errors with specific meanings are.
 
 
 6.1 KVM_CAP_PPC_OSI
+-------------------
 
-Architectures: ppc
-Target: vcpu
-Parameters: none
-Returns: 0 on success; -1 on error
+:Architectures: ppc
+:Target: vcpu
+:Parameters: none
+:Returns: 0 on success; -1 on error
 
 This capability enables interception of OSI hypercalls that otherwise would
 be treated as normal system calls to be injected into the guest. OSI hypercalls
@@ -4658,11 +5165,12 @@
 
 
 6.2 KVM_CAP_PPC_PAPR
+--------------------
 
-Architectures: ppc
-Target: vcpu
-Parameters: none
-Returns: 0 on success; -1 on error
+:Architectures: ppc
+:Target: vcpu
+:Parameters: none
+:Returns: 0 on success; -1 on error
 
 This capability enables interception of PAPR hypercalls. PAPR hypercalls are
 done using the hypercall instruction "sc 1".
@@ -4678,18 +5186,21 @@
 
 
 6.3 KVM_CAP_SW_TLB
+------------------
 
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] is the address of a struct kvm_config_tlb
-Returns: 0 on success; -1 on error
+:Architectures: ppc
+:Target: vcpu
+:Parameters: args[0] is the address of a struct kvm_config_tlb
+:Returns: 0 on success; -1 on error
 
-struct kvm_config_tlb {
+::
+
+  struct kvm_config_tlb {
 	__u64 params;
 	__u64 array;
 	__u32 mmu_type;
 	__u32 array_len;
-};
+  };
 
 Configures the virtual CPU's TLB array, establishing a shared memory area
 between userspace and KVM.  The "params" and "array" fields are userspace
@@ -4708,6 +5219,7 @@
 on this vcpu.
 
 For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+
  - The "params" field is of type "struct kvm_book3e_206_tlb_params".
  - The "array" field points to an array of type "struct
    kvm_book3e_206_tlb_entry".
@@ -4721,11 +5233,12 @@
    hardware ignores this value for TLB0.
 
 6.4 KVM_CAP_S390_CSS_SUPPORT
+----------------------------
 
-Architectures: s390
-Target: vcpu
-Parameters: none
-Returns: 0 on success; -1 on error
+:Architectures: s390
+:Target: vcpu
+:Parameters: none
+:Returns: 0 on success; -1 on error
 
 This capability enables support for handling of channel I/O instructions.
 
@@ -4739,11 +5252,12 @@
 virtual machine is affected.
 
 6.5 KVM_CAP_PPC_EPR
+-------------------
 
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] defines whether the proxy facility is active
-Returns: 0 on success; -1 on error
+:Architectures: ppc
+:Target: vcpu
+:Parameters: args[0] defines whether the proxy facility is active
+:Returns: 0 on success; -1 on error
 
 This capability enables or disables the delivery of interrupts through the
 external proxy facility.
@@ -4757,62 +5271,70 @@
 When this capability is enabled, KVM_EXIT_EPR can occur.
 
 6.6 KVM_CAP_IRQ_MPIC
+--------------------
 
-Architectures: ppc
-Parameters: args[0] is the MPIC device fd
-            args[1] is the MPIC CPU number for this vcpu
+:Architectures: ppc
+:Parameters: args[0] is the MPIC device fd;
+             args[1] is the MPIC CPU number for this vcpu
 
 This capability connects the vcpu to an in-kernel MPIC device.
 
 6.7 KVM_CAP_IRQ_XICS
+--------------------
 
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] is the XICS device fd
-            args[1] is the XICS CPU number (server ID) for this vcpu
+:Architectures: ppc
+:Target: vcpu
+:Parameters: args[0] is the XICS device fd;
+             args[1] is the XICS CPU number (server ID) for this vcpu
 
 This capability connects the vcpu to an in-kernel XICS device.
 
 6.8 KVM_CAP_S390_IRQCHIP
+------------------------
 
-Architectures: s390
-Target: vm
-Parameters: none
+:Architectures: s390
+:Target: vm
+:Parameters: none
 
 This capability enables the in-kernel irqchip for s390. Please refer to
 "4.24 KVM_CREATE_IRQCHIP" for details.
 
 6.9 KVM_CAP_MIPS_FPU
+--------------------
 
-Architectures: mips
-Target: vcpu
-Parameters: args[0] is reserved for future use (should be 0).
+:Architectures: mips
+:Target: vcpu
+:Parameters: args[0] is reserved for future use (should be 0).
 
 This capability allows the use of the host Floating Point Unit by the guest. It
 allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is
-done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed
-(depending on the current guest FPU register mode), and the Status.FR,
+done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG_MIPS_FCR_*`` registers can be
+accessed (depending on the current guest FPU register mode), and the Status.FR,
 Config5.FRE bits are accessible via the KVM API and also from the guest,
 depending on them being supported by the FPU.
 
 6.10 KVM_CAP_MIPS_MSA
+---------------------
 
-Architectures: mips
-Target: vcpu
-Parameters: args[0] is reserved for future use (should be 0).
+:Architectures: mips
+:Target: vcpu
+:Parameters: args[0] is reserved for future use (should be 0).
 
 This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
 It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest.
-Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
-accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
-the guest.
+Once this is done the ``KVM_REG_MIPS_VEC_*`` and ``KVM_REG_MIPS_MSA_*``
+registers can be accessed, and the Config5.MSAEn bit is accessible via the
+KVM API and also from the guest.
 
 6.74 KVM_CAP_SYNC_REGS
-Architectures: s390, x86
-Target: s390: always enabled, x86: vcpu
-Parameters: none
-Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
-sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
+----------------------
+
+:Architectures: s390, x86
+:Target: s390: always enabled, x86: vcpu
+:Parameters: none
+:Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
+          sets are supported
+          (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
 
 As described above in the kvm_sync_regs struct info in section 5 (kvm_run):
 KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers
@@ -4825,6 +5347,7 @@
 For s390 specifics, please refer to the source code.
 
 For x86:
+
 - the register sets to be copied out to kvm_run are selectable
   by userspace (rather that all sets being copied out for every exit).
 - vcpu_events are available in addition to regs and sregs.
@@ -4841,23 +5364,26 @@
 
 Unused bitfields in the bitarrays must be set to zero.
 
-struct kvm_sync_regs {
+::
+
+  struct kvm_sync_regs {
         struct kvm_regs regs;
         struct kvm_sregs sregs;
         struct kvm_vcpu_events events;
-};
+  };
 
 6.75 KVM_CAP_PPC_IRQ_XIVE
+-------------------------
 
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] is the XIVE device fd
-            args[1] is the XIVE CPU number (server ID) for this vcpu
+:Architectures: ppc
+:Target: vcpu
+:Parameters: args[0] is the XIVE device fd;
+             args[1] is the XIVE CPU number (server ID) for this vcpu
 
 This capability connects the vcpu to an in-kernel XIVE device.
 
 7. Capabilities that can be enabled on VMs
-------------------------------------------
+==========================================
 
 There are certain capabilities that change the behavior of the virtual
 machine when enabled. To enable them, please see section 4.37. Below
@@ -4866,20 +5392,24 @@
 
 The following information is provided along with the description:
 
-  Architectures: which instruction set architectures provide this ioctl.
+  Architectures:
+      which instruction set architectures provide this ioctl.
       x86 includes both i386 and x86_64.
 
-  Parameters: what parameters are accepted by the capability.
+  Parameters:
+      what parameters are accepted by the capability.
 
-  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
+  Returns:
+      the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
       are not detailed, but errors with specific meanings are.
 
 
 7.1 KVM_CAP_PPC_ENABLE_HCALL
+----------------------------
 
-Architectures: ppc
-Parameters: args[0] is the sPAPR hcall number
-	    args[1] is 0 to disable, 1 to enable in-kernel handling
+:Architectures: ppc
+:Parameters: args[0] is the sPAPR hcall number;
+	     args[1] is 0 to disable, 1 to enable in-kernel handling
 
 This capability controls whether individual sPAPR hypercalls (hcalls)
 get handled by the kernel or not.  Enabling or disabling in-kernel
@@ -4897,13 +5427,15 @@
 error.
 
 7.2 KVM_CAP_S390_USER_SIGP
+--------------------------
 
-Architectures: s390
-Parameters: none
+:Architectures: s390
+:Parameters: none
 
 This capability controls which SIGP orders will be handled completely in user
 space. With this capability enabled, all fast orders will be handled completely
 in the kernel:
+
 - SENSE
 - SENSE RUNNING
 - EXTERNAL CALL
@@ -4917,48 +5449,52 @@
 old way of handling SIGP orders is used (partially in kernel and user space).
 
 7.3 KVM_CAP_S390_VECTOR_REGISTERS
+---------------------------------
 
-Architectures: s390
-Parameters: none
-Returns: 0 on success, negative value on error
+:Architectures: s390
+:Parameters: none
+:Returns: 0 on success, negative value on error
 
 Allows use of the vector registers introduced with z13 processor, and
 provides for the synchronization between host and user space.  Will
 return -EINVAL if the machine does not support vectors.
 
 7.4 KVM_CAP_S390_USER_STSI
+--------------------------
 
-Architectures: s390
-Parameters: none
+:Architectures: s390
+:Parameters: none
 
 This capability allows post-handlers for the STSI instruction. After
 initial handling in the kernel, KVM exits to user space with
 KVM_EXIT_S390_STSI to allow user space to insert further data.
 
 Before exiting to userspace, kvm handlers should fill in s390_stsi field of
-vcpu->run:
-struct {
+vcpu->run::
+
+  struct {
 	__u64 addr;
 	__u8 ar;
 	__u8 reserved;
 	__u8 fc;
 	__u8 sel1;
 	__u16 sel2;
-} s390_stsi;
+  } s390_stsi;
 
-@addr - guest address of STSI SYSIB
-@fc   - function code
-@sel1 - selector 1
-@sel2 - selector 2
-@ar   - access register number
+  @addr - guest address of STSI SYSIB
+  @fc   - function code
+  @sel1 - selector 1
+  @sel2 - selector 2
+  @ar   - access register number
 
 KVM handlers should exit to userspace with rc = -EREMOTE.
 
 7.5 KVM_CAP_SPLIT_IRQCHIP
+-------------------------
 
-Architectures: x86
-Parameters: args[0] - number of routes reserved for userspace IOAPICs
-Returns: 0 on success, -1 on error
+:Architectures: x86
+:Parameters: args[0] - number of routes reserved for userspace IOAPICs
+:Returns: 0 on success, -1 on error
 
 Create a local apic for each processor in the kernel. This can be used
 instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
@@ -4975,24 +5511,26 @@
 kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
 
 7.6 KVM_CAP_S390_RI
+-------------------
 
-Architectures: s390
-Parameters: none
+:Architectures: s390
+:Parameters: none
 
 Allows use of runtime-instrumentation introduced with zEC12 processor.
 Will return -EINVAL if the machine does not support runtime-instrumentation.
 Will return -EBUSY if a VCPU has already been created.
 
 7.7 KVM_CAP_X2APIC_API
+----------------------
 
-Architectures: x86
-Parameters: args[0] - features that should be enabled
-Returns: 0 on success, -EINVAL when args[0] contains invalid features
+:Architectures: x86
+:Parameters: args[0] - features that should be enabled
+:Returns: 0 on success, -EINVAL when args[0] contains invalid features
 
-Valid feature flags in args[0] are
+Valid feature flags in args[0] are::
 
-#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+  #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+  #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
 Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
 KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
@@ -5006,9 +5544,10 @@
 where 0xff represents CPUs 0-7 in cluster 0.
 
 7.8 KVM_CAP_S390_USER_INSTR0
+----------------------------
 
-Architectures: s390
-Parameters: none
+:Architectures: s390
+:Parameters: none
 
 With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
 be intercepted and forwarded to user space. User space can use this
@@ -5020,26 +5559,29 @@
 created and are running.
 
 7.9 KVM_CAP_S390_GS
+-------------------
 
-Architectures: s390
-Parameters: none
-Returns: 0 on success; -EINVAL if the machine does not support
-	 guarded storage; -EBUSY if a VCPU has already been created.
+:Architectures: s390
+:Parameters: none
+:Returns: 0 on success; -EINVAL if the machine does not support
+          guarded storage; -EBUSY if a VCPU has already been created.
 
 Allows use of guarded storage for the KVM guest.
 
 7.10 KVM_CAP_S390_AIS
+---------------------
 
-Architectures: s390
-Parameters: none
+:Architectures: s390
+:Parameters: none
 
 Allow use of adapter-interruption suppression.
-Returns: 0 on success; -EBUSY if a VCPU has already been created.
+:Returns: 0 on success; -EBUSY if a VCPU has already been created.
 
 7.11 KVM_CAP_PPC_SMT
+--------------------
 
-Architectures: ppc
-Parameters: vsmt_mode, flags
+:Architectures: ppc
+:Parameters: vsmt_mode, flags
 
 Enabling this capability on a VM provides userspace with a way to set
 the desired virtual SMT mode (i.e. the number of virtual CPUs per
@@ -5054,9 +5596,10 @@
 modes are available.
 
 7.12 KVM_CAP_PPC_FWNMI
+----------------------
 
-Architectures: ppc
-Parameters: none
+:Architectures: ppc
+:Parameters: none
 
 With this capability a machine check exception in the guest address
 space will cause KVM to exit the guest with NMI exit reason. This
@@ -5065,17 +5608,18 @@
 branch to guests' 0x200 interrupt vector.
 
 7.13 KVM_CAP_X86_DISABLE_EXITS
+------------------------------
 
-Architectures: x86
-Parameters: args[0] defines which exits are disabled
-Returns: 0 on success, -EINVAL when args[0] contains invalid exits
+:Architectures: x86
+:Parameters: args[0] defines which exits are disabled
+:Returns: 0 on success, -EINVAL when args[0] contains invalid exits
 
-Valid bits in args[0] are
+Valid bits in args[0] are::
 
-#define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE            (1 << 2)
-#define KVM_X86_DISABLE_EXITS_CSTATE           (1 << 3)
+  #define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
+  #define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
+  #define KVM_X86_DISABLE_EXITS_PAUSE            (1 << 2)
+  #define KVM_X86_DISABLE_EXITS_CSTATE           (1 << 3)
 
 Enabling this capability on a VM provides userspace with a way to no
 longer intercept some instructions for improved latency in some
@@ -5087,12 +5631,13 @@
 Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 
 7.14 KVM_CAP_S390_HPAGE_1M
+--------------------------
 
-Architectures: s390
-Parameters: none
-Returns: 0 on success, -EINVAL if hpage module parameter was not set
-	 or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL
-	 flag set
+:Architectures: s390
+:Parameters: none
+:Returns: 0 on success, -EINVAL if hpage module parameter was not set
+	  or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL
+	  flag set
 
 With this capability the KVM support for memory backing with 1m pages
 through hugetlbfs can be enabled for a VM. After the capability is
@@ -5104,20 +5649,22 @@
 this capability, the VM will not be able to run.
 
 7.15 KVM_CAP_MSR_PLATFORM_INFO
+------------------------------
 
-Architectures: x86
-Parameters: args[0] whether feature should be enabled or not
+:Architectures: x86
+:Parameters: args[0] whether feature should be enabled or not
 
 With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
 a #GP would be raised when the guest tries to access. Currently, this
 capability does not enable write permissions of this MSR for the guest.
 
 7.16 KVM_CAP_PPC_NESTED_HV
+--------------------------
 
-Architectures: ppc
-Parameters: none
-Returns: 0 on success, -EINVAL when the implementation doesn't support
-	 nested-HV virtualization.
+:Architectures: ppc
+:Parameters: none
+:Returns: 0 on success, -EINVAL when the implementation doesn't support
+	  nested-HV virtualization.
 
 HV-KVM on POWER9 and later systems allows for "nested-HV"
 virtualization, which provides a way for a guest VM to run guests that
@@ -5127,9 +5674,10 @@
 kvm-hv module parameter.
 
 7.17 KVM_CAP_EXCEPTION_PAYLOAD
+------------------------------
 
-Architectures: x86
-Parameters: args[0] whether feature should be enabled or not
+:Architectures: x86
+:Parameters: args[0] whether feature should be enabled or not
 
 With this capability enabled, CR2 will not be modified prior to the
 emulated VM-exit when L1 intercepts a #PF exception that occurs in
@@ -5140,21 +5688,21 @@
 faulting address (or the new DR6 bits*) will be reported in the
 exception_payload field. Similarly, when userspace injects a #PF (or
 #DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set
-exception.has_payload and to put the faulting address (or the new DR6
-bits*) in the exception_payload field.
+exception.has_payload and to put the faulting address - or the new DR6
+bits\ [#]_ - in the exception_payload field.
 
 This capability also enables exception.pending in struct
 kvm_vcpu_events, which allows userspace to distinguish between pending
 and injected exceptions.
 
 
-* For the new DR6 bits, note that bit 16 is set iff the #DB exception
-  will clear DR6.RTM.
+.. [#] For the new DR6 bits, note that bit 16 is set iff the #DB exception
+       will clear DR6.RTM.
 
 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
 
-Architectures: x86, arm, arm64, mips
-Parameters: args[0] whether feature should be enabled or not
+:Architectures: x86, arm, arm64, mips
+:Parameters: args[0] whether feature should be enabled or not
 
 With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
 clear and write-protect all pages that are returned as dirty.
@@ -5181,14 +5729,15 @@
 Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT.
 
 8. Other capabilities.
-----------------------
+======================
 
 This section lists capabilities that give information about other
 features of the KVM implementation.
 
 8.1 KVM_CAP_PPC_HWRNG
+---------------------
 
-Architectures: ppc
+:Architectures: ppc
 
 This capability, if KVM_CHECK_EXTENSION indicates that it is
 available, means that that the kernel has an implementation of the
@@ -5197,8 +5746,10 @@
 with the KVM_CAP_PPC_ENABLE_HCALL capability.
 
 8.2 KVM_CAP_HYPERV_SYNIC
+------------------------
 
-Architectures: x86
+:Architectures: x86
+
 This capability, if KVM_CHECK_EXTENSION indicates that it is
 available, means that that the kernel has an implementation of the
 Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
@@ -5210,8 +5761,9 @@
 by the CPU, as it's incompatible with SynIC auto-EOI behavior.
 
 8.3 KVM_CAP_PPC_RADIX_MMU
+-------------------------
 
-Architectures: ppc
+:Architectures: ppc
 
 This capability, if KVM_CHECK_EXTENSION indicates that it is
 available, means that that the kernel can support guests using the
@@ -5219,8 +5771,9 @@
 processor).
 
 8.4 KVM_CAP_PPC_HASH_MMU_V3
+---------------------------
 
-Architectures: ppc
+:Architectures: ppc
 
 This capability, if KVM_CHECK_EXTENSION indicates that it is
 available, means that that the kernel can support guests using the
@@ -5228,8 +5781,9 @@
 the POWER9 processor), including in-memory segment tables.
 
 8.5 KVM_CAP_MIPS_VZ
+-------------------
 
-Architectures: mips
+:Architectures: mips
 
 This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
 it is available, means that full hardware assisted virtualization capabilities
@@ -5247,16 +5801,19 @@
 possibility of other hardware assisted virtualization implementations which
 may be incompatible with the MIPS VZ ASE.
 
- 0: The trap & emulate implementation is in use to run guest code in user
+==  ==========================================================================
+ 0  The trap & emulate implementation is in use to run guest code in user
     mode. Guest virtual memory segments are rearranged to fit the guest in the
     user mode address space.
 
- 1: The MIPS VZ ASE is in use, providing full hardware assisted
+ 1  The MIPS VZ ASE is in use, providing full hardware assisted
     virtualization, including standard guest virtual memory segments.
+==  ==========================================================================
 
 8.6 KVM_CAP_MIPS_TE
+-------------------
 
-Architectures: mips
+:Architectures: mips
 
 This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
 it is available, means that the trap & emulate implementation is available to
@@ -5268,8 +5825,9 @@
 available, it means that the VM is using trap & emulate.
 
 8.7 KVM_CAP_MIPS_64BIT
+----------------------
 
-Architectures: mips
+:Architectures: mips
 
 This capability indicates the supported architecture type of the guest, i.e. the
 supported register and address width.
@@ -5279,22 +5837,26 @@
 be checked specifically against known values (see below). All other values are
 reserved.
 
- 0: MIPS32 or microMIPS32.
+==  ========================================================================
+ 0  MIPS32 or microMIPS32.
     Both registers and addresses are 32-bits wide.
     It will only be possible to run 32-bit guest code.
 
- 1: MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
+ 1  MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
     Registers are 64-bits wide, but addresses are 32-bits wide.
     64-bit guest code may run but cannot access MIPS64 memory segments.
     It will also be possible to run 32-bit guest code.
 
- 2: MIPS64 or microMIPS64 with access to all address segments.
+ 2  MIPS64 or microMIPS64 with access to all address segments.
     Both registers and addresses are 64-bits wide.
     It will be possible to run 64-bit or 32-bit guest code.
+==  ========================================================================
 
 8.9 KVM_CAP_ARM_USER_IRQ
+------------------------
 
-Architectures: arm, arm64
+:Architectures: arm, arm64
+
 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
 that if userspace creates a VM without an in-kernel interrupt controller, it
 will be notified of changes to the output level of in-kernel emulated devices,
@@ -5321,7 +5883,7 @@
 number larger than 0 indicating the version of this capability is implemented
 and thereby which bits in in run->s.regs.device_irq_level can signal values.
 
-Currently the following bits are defined for the device_irq_level bitmap:
+Currently the following bits are defined for the device_irq_level bitmap::
 
   KVM_CAP_ARM_USER_IRQ >= 1:
 
@@ -5334,8 +5896,9 @@
 listed above.
 
 8.10 KVM_CAP_PPC_SMT_POSSIBLE
+-----------------------------
 
-Architectures: ppc
+:Architectures: ppc
 
 Querying this capability returns a bitmap indicating the possible
 virtual SMT modes that can be set using KVM_CAP_PPC_SMT.  If bit N
@@ -5343,8 +5906,9 @@
 available.
 
 8.11 KVM_CAP_HYPERV_SYNIC2
+--------------------------
 
-Architectures: x86
+:Architectures: x86
 
 This capability enables a newer version of Hyper-V Synthetic interrupt
 controller (SynIC).  The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
@@ -5352,8 +5916,9 @@
 writing to the respective MSRs.
 
 8.12 KVM_CAP_HYPERV_VP_INDEX
+----------------------------
 
-Architectures: x86
+:Architectures: x86
 
 This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr.  Its
 value is used to denote the target vcpu for a SynIC interrupt.  For
@@ -5361,47 +5926,53 @@
 capability is absent, userspace can still query this msr's value.
 
 8.13 KVM_CAP_S390_AIS_MIGRATION
+-------------------------------
 
-Architectures: s390
-Parameters: none
+:Architectures: s390
+:Parameters: none
 
 This capability indicates if the flic device will be able to get/set the
 AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
 to discover this without having to create a flic device.
 
 8.14 KVM_CAP_S390_PSW
+---------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the PSW is exposed via the kvm_run structure.
 
 8.15 KVM_CAP_S390_GMAP
+----------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the user space memory used as guest mapping can
 be anywhere in the user memory address space, as long as the memory slots are
 aligned and sized to a segment (1MB) boundary.
 
 8.16 KVM_CAP_S390_COW
+---------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the user space memory used as guest mapping can
 use copy-on-write semantics as well as dirty pages tracking via read-only page
 tables.
 
 8.17 KVM_CAP_S390_BPB
+---------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that kvm will implement the interfaces to handle
 reset, migration and nested KVM for branch prediction blocking. The stfle
 facility 82 should not be provided to the guest without this capability.
 
 8.18 KVM_CAP_HYPERV_TLBFLUSH
+----------------------------
 
-Architectures: x86
+:Architectures: x86
 
 This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
 hypercalls:
@@ -5409,8 +5980,9 @@
 HvFlushVirtualAddressList, HvFlushVirtualAddressListEx.
 
 8.19 KVM_CAP_ARM_INJECT_SERROR_ESR
+----------------------------------
 
-Architectures: arm, arm64
+:Architectures: arm, arm64
 
 This capability indicates that userspace can specify (via the
 KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it
@@ -5421,16 +5993,20 @@
 AArch64, this value will be reported in the ISS field of ESR_ELx.
 
 See KVM_CAP_VCPU_EVENTS for more details.
-8.20 KVM_CAP_HYPERV_SEND_IPI
 
-Architectures: x86
+8.20 KVM_CAP_HYPERV_SEND_IPI
+----------------------------
+
+:Architectures: x86
 
 This capability indicates that KVM supports paravirtualized Hyper-V IPI send
 hypercalls:
 HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
-8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
 
-Architecture: x86
+8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
+-----------------------------------
+
+:Architecture: x86
 
 This capability indicates that KVM running on top of Hyper-V hypervisor
 enables Direct TLB flush for its guests meaning that TLB flush
diff --git a/Documentation/virt/kvm/arm/hyp-abi.txt b/Documentation/virt/kvm/arm/hyp-abi.rst
similarity index 78%
rename from Documentation/virt/kvm/arm/hyp-abi.txt
rename to Documentation/virt/kvm/arm/hyp-abi.rst
index a20a0be..d1fc27d 100644
--- a/Documentation/virt/kvm/arm/hyp-abi.txt
+++ b/Documentation/virt/kvm/arm/hyp-abi.rst
@@ -1,4 +1,8 @@
-* Internal ABI between the kernel and HYP
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+Internal ABI between the kernel and HYP
+=======================================
 
 This file documents the interaction between the Linux kernel and the
 hypervisor layer when running Linux as a hypervisor (for example
@@ -19,25 +23,31 @@
 Unless specified otherwise, any built-in hypervisor must implement
 these functions (see arch/arm{,64}/include/asm/virt.h):
 
-* r0/x0 = HVC_SET_VECTORS
-  r1/x1 = vectors
+* ::
+
+    r0/x0 = HVC_SET_VECTORS
+    r1/x1 = vectors
 
   Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors'
   must be a physical address, and respect the alignment requirements
   of the architecture. Only implemented by the initial stubs, not by
   Linux hypervisors.
 
-* r0/x0 = HVC_RESET_VECTORS
+* ::
+
+    r0/x0 = HVC_RESET_VECTORS
 
   Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials
   stubs' exception vector value. This effectively disables an existing
   hypervisor.
 
-* r0/x0 = HVC_SOFT_RESTART
-  r1/x1 = restart address
-  x2 = x0's value when entering the next payload (arm64)
-  x3 = x1's value when entering the next payload (arm64)
-  x4 = x2's value when entering the next payload (arm64)
+* ::
+
+    r0/x0 = HVC_SOFT_RESTART
+    r1/x1 = restart address
+    x2 = x0's value when entering the next payload (arm64)
+    x3 = x1's value when entering the next payload (arm64)
+    x4 = x2's value when entering the next payload (arm64)
 
   Mask all exceptions, disable the MMU, move the arguments into place
   (arm64 only), and jump to the restart address while at HYP/EL2. This
diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst
new file mode 100644
index 0000000..3e2b2ab
--- /dev/null
+++ b/Documentation/virt/kvm/arm/index.rst
@@ -0,0 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===
+ARM
+===
+
+.. toctree::
+   :maxdepth: 2
+
+   hyp-abi
+   psci
+   pvtime
diff --git a/Documentation/virt/kvm/arm/psci.txt b/Documentation/virt/kvm/arm/psci.rst
similarity index 60%
rename from Documentation/virt/kvm/arm/psci.txt
rename to Documentation/virt/kvm/arm/psci.rst
index 559586f..d52c2e8 100644
--- a/Documentation/virt/kvm/arm/psci.txt
+++ b/Documentation/virt/kvm/arm/psci.rst
@@ -1,3 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+Power State Coordination Interface (PSCI)
+=========================================
+
 KVM implements the PSCI (Power State Coordination Interface)
 specification in order to provide services such as CPU on/off, reset
 and power-off to the guest.
@@ -30,32 +36,42 @@
   - Affects the whole VM (even if the register view is per-vcpu)
 
 * KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-  Holds the state of the firmware support to mitigate CVE-2017-5715, as
-  offered by KVM to the guest via a HVC call. The workaround is described
-  under SMCCC_ARCH_WORKAROUND_1 in [1].
+    Holds the state of the firmware support to mitigate CVE-2017-5715, as
+    offered by KVM to the guest via a HVC call. The workaround is described
+    under SMCCC_ARCH_WORKAROUND_1 in [1].
+
   Accepted values are:
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: KVM does not offer
+
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL:
+      KVM does not offer
       firmware support for the workaround. The mitigation status for the
       guest is unknown.
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: The workaround HVC call is
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL:
+      The workaround HVC call is
       available to the guest and required for the mitigation.
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: The workaround HVC call
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED:
+      The workaround HVC call
       is available to the guest, but it is not needed on this VCPU.
 
 * KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-  Holds the state of the firmware support to mitigate CVE-2018-3639, as
-  offered by KVM to the guest via a HVC call. The workaround is described
-  under SMCCC_ARCH_WORKAROUND_2 in [1].
+    Holds the state of the firmware support to mitigate CVE-2018-3639, as
+    offered by KVM to the guest via a HVC call. The workaround is described
+    under SMCCC_ARCH_WORKAROUND_2 in [1]_.
+
   Accepted values are:
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: A workaround is not
+
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL:
+      A workaround is not
       available. KVM does not offer firmware support for the workaround.
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: The workaround state is
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN:
+      The workaround state is
       unknown. KVM does not offer firmware support for the workaround.
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: The workaround is available,
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
+      The workaround is available,
       and can be disabled by a vCPU. If
       KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for
       this vCPU.
-    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: The workaround is
-      always active on this vCPU or it is not needed.
+    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
+      The workaround is always active on this vCPU or it is not needed.
 
-[1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf
+.. [1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf
diff --git a/Documentation/virt/kvm/devices/arm-vgic-its.txt b/Documentation/virt/kvm/devices/arm-vgic-its.rst
similarity index 71%
rename from Documentation/virt/kvm/devices/arm-vgic-its.txt
rename to Documentation/virt/kvm/devices/arm-vgic-its.rst
index eeaa95b..6c304fd 100644
--- a/Documentation/virt/kvm/devices/arm-vgic-its.txt
+++ b/Documentation/virt/kvm/devices/arm-vgic-its.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================================
 ARM Virtual Interrupt Translation Service (ITS)
 ===============================================
 
@@ -12,22 +15,32 @@
 a separate, non-overlapping MMIO region.
 
 
-Groups:
-  KVM_DEV_ARM_VGIC_GRP_ADDR
+Groups
+======
+
+KVM_DEV_ARM_VGIC_GRP_ADDR
+-------------------------
+
   Attributes:
     KVM_VGIC_ITS_ADDR_TYPE (rw, 64-bit)
       Base address in the guest physical address space of the GICv3 ITS
       control register frame.
       This address needs to be 64K aligned and the region covers 128K.
+
   Errors:
-    -E2BIG:  Address outside of addressable IPA range
-    -EINVAL: Incorrectly aligned address
-    -EEXIST: Address already configured
-    -EFAULT: Invalid user pointer for attr->addr.
-    -ENODEV: Incorrect attribute or the ITS is not supported.
+
+    =======  =================================================
+    -E2BIG   Address outside of addressable IPA range
+    -EINVAL  Incorrectly aligned address
+    -EEXIST  Address already configured
+    -EFAULT  Invalid user pointer for attr->addr.
+    -ENODEV  Incorrect attribute or the ITS is not supported.
+    =======  =================================================
 
 
-  KVM_DEV_ARM_VGIC_GRP_CTRL
+KVM_DEV_ARM_VGIC_GRP_CTRL
+-------------------------
+
   Attributes:
     KVM_DEV_ARM_VGIC_CTRL_INIT
       request the initialization of the ITS, no additional parameter in
@@ -58,16 +71,21 @@
       "ITS Restore Sequence".
 
   Errors:
-    -ENXIO:  ITS not properly configured as required prior to setting
-             this attribute
-    -ENOMEM: Memory shortage when allocating ITS internal data
-    -EINVAL: Inconsistent restored data
-    -EFAULT: Invalid guest ram access
-    -EBUSY:  One or more VCPUS are running
-    -EACCES: The virtual ITS is backed by a physical GICv4 ITS, and the
-	     state is not available
 
-  KVM_DEV_ARM_VGIC_GRP_ITS_REGS
+    =======  ==========================================================
+     -ENXIO  ITS not properly configured as required prior to setting
+             this attribute
+    -ENOMEM  Memory shortage when allocating ITS internal data
+    -EINVAL  Inconsistent restored data
+    -EFAULT  Invalid guest ram access
+    -EBUSY   One or more VCPUS are running
+    -EACCES  The virtual ITS is backed by a physical GICv4 ITS, and the
+	     state is not available
+    =======  ==========================================================
+
+KVM_DEV_ARM_VGIC_GRP_ITS_REGS
+-----------------------------
+
   Attributes:
       The attr field of kvm_device_attr encodes the offset of the
       ITS register, relative to the ITS control frame base address
@@ -78,6 +96,7 @@
       be accessed with full length.
 
       Writes to read-only registers are ignored by the kernel except for:
+
       - GITS_CREADR. It must be restored otherwise commands in the queue
         will be re-executed after restoring CWRITER. GITS_CREADR must be
         restored before restoring the GITS_CTLR which is likely to enable the
@@ -91,30 +110,36 @@
 
       For other registers, getting or setting a register has the same
       effect as reading/writing the register on real hardware.
-  Errors:
-    -ENXIO: Offset does not correspond to any supported register
-    -EFAULT: Invalid user pointer for attr->addr
-    -EINVAL: Offset is not 64-bit aligned
-    -EBUSY: one or more VCPUS are running
 
- ITS Restore Sequence:
- -------------------------
+  Errors:
+
+    =======  ====================================================
+    -ENXIO   Offset does not correspond to any supported register
+    -EFAULT  Invalid user pointer for attr->addr
+    -EINVAL  Offset is not 64-bit aligned
+    -EBUSY   one or more VCPUS are running
+    =======  ====================================================
+
+ITS Restore Sequence:
+---------------------
 
 The following ordering must be followed when restoring the GIC and the ITS:
+
 a) restore all guest memory and create vcpus
 b) restore all redistributors
 c) provide the ITS base address
    (KVM_DEV_ARM_VGIC_GRP_ADDR)
 d) restore the ITS in the following order:
-   1. Restore GITS_CBASER
-   2. Restore all other GITS_ registers, except GITS_CTLR!
-   3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES)
-   4. Restore GITS_CTLR
+
+     1. Restore GITS_CBASER
+     2. Restore all other ``GITS_`` registers, except GITS_CTLR!
+     3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES)
+     4. Restore GITS_CTLR
 
 Then vcpus can be started.
 
- ITS Table ABI REV0:
- -------------------
+ITS Table ABI REV0:
+-------------------
 
  Revision 0 of the ABI only supports the features of a virtual GICv3, and does
  not support a virtual GICv4 with support for direct injection of virtual
@@ -125,12 +150,13 @@
  entries in the collection are listed in no particular order.
  All entries are 8 bytes.
 
- Device Table Entry (DTE):
+ Device Table Entry (DTE)::
 
- bits:     | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 |
- values:   | V |   next    | ITT_addr |  Size   |
+   bits:     | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 |
+   values:   | V |   next    | ITT_addr |  Size   |
 
- where;
+ where:
+
  - V indicates whether the entry is valid. If not, other fields
    are not meaningful.
  - next: equals to 0 if this entry is the last one; otherwise it
@@ -140,32 +166,34 @@
  - Size specifies the supported number of bits for the EventID,
    minus one
 
- Collection Table Entry (CTE):
+ Collection Table Entry (CTE)::
 
- bits:     | 63| 62 ..  52  | 51 ... 16 | 15  ...   0 |
- values:   | V |    RES0    |  RDBase   |    ICID     |
+   bits:     | 63| 62 ..  52  | 51 ... 16 | 15  ...   0 |
+   values:   | V |    RES0    |  RDBase   |    ICID     |
 
  where:
+
  - V indicates whether the entry is valid. If not, other fields are
    not meaningful.
  - RES0: reserved field with Should-Be-Zero-or-Preserved behavior.
  - RDBase is the PE number (GICR_TYPER.Processor_Number semantic),
  - ICID is the collection ID
 
- Interrupt Translation Entry (ITE):
+ Interrupt Translation Entry (ITE)::
 
- bits:     | 63 ... 48 | 47 ... 16 | 15 ... 0 |
- values:   |    next   |   pINTID  |  ICID    |
+   bits:     | 63 ... 48 | 47 ... 16 | 15 ... 0 |
+   values:   |    next   |   pINTID  |  ICID    |
 
  where:
+
  - next: equals to 0 if this entry is the last one; otherwise it corresponds
    to the EventID offset to the next ITE capped by 2^16 -1.
  - pINTID is the physical LPI ID; if zero, it means the entry is not valid
    and other fields are not meaningful.
  - ICID is the collection ID
 
- ITS Reset State:
- ----------------
+ITS Reset State:
+----------------
 
 RESET returns the ITS to the same state that it was when first created and
 initialized. When the RESET command returns, the following things are
diff --git a/Documentation/virt/kvm/devices/arm-vgic-v3.txt b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
similarity index 76%
rename from Documentation/virt/kvm/devices/arm-vgic-v3.txt
rename to Documentation/virt/kvm/devices/arm-vgic-v3.rst
index ff290b4..5dd3bff 100644
--- a/Documentation/virt/kvm/devices/arm-vgic-v3.txt
+++ b/Documentation/virt/kvm/devices/arm-vgic-v3.rst
@@ -1,9 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================================
 ARM Virtual Generic Interrupt Controller v3 and later (VGICv3)
 ==============================================================
 
 
 Device types supported:
-  KVM_DEV_TYPE_ARM_VGIC_V3     ARM Generic Interrupt Controller v3.0
+  - KVM_DEV_TYPE_ARM_VGIC_V3     ARM Generic Interrupt Controller v3.0
 
 Only one VGIC instance may be instantiated through this API.  The created VGIC
 will act as the VM interrupt controller, requiring emulated user-space devices
@@ -15,7 +18,8 @@
 
 Groups:
   KVM_DEV_ARM_VGIC_GRP_ADDR
-  Attributes:
+   Attributes:
+
     KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit)
       Base address in the guest physical address space of the GICv3 distributor
       register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
@@ -29,21 +33,25 @@
       This address needs to be 64K aligned.
 
     KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION (rw, 64-bit)
-      The attribute data pointed to by kvm_device_attr.addr is a __u64 value:
-      bits:     | 63   ....  52  |  51   ....   16 | 15 - 12  |11 - 0
-      values:   |     count      |       base      |  flags   | index
+      The attribute data pointed to by kvm_device_attr.addr is a __u64 value::
+
+        bits:     | 63   ....  52  |  51   ....   16 | 15 - 12  |11 - 0
+        values:   |     count      |       base      |  flags   | index
+
       - index encodes the unique redistributor region index
       - flags: reserved for future use, currently 0
       - base field encodes bits [51:16] of the guest physical base address
         of the first redistributor in the region.
       - count encodes the number of redistributors in the region. Must be
         greater than 0.
+
       There are two 64K pages for each redistributor in the region and
       redistributors are laid out contiguously within the region. Regions
       are filled with redistributors in the index order. The sum of all
       region count fields must be greater than or equal to the number of
       VCPUs. Redistributor regions must be registered in the incremental
       index order, starting from index 0.
+
       The characteristics of a specific redistributor region can be read
       by presetting the index field in the attr data.
       Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
@@ -52,23 +60,27 @@
   KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes.
 
   Errors:
-    -E2BIG:  Address outside of addressable IPA range
-    -EINVAL: Incorrectly aligned address, bad redistributor region
+
+    =======  =============================================================
+    -E2BIG   Address outside of addressable IPA range
+    -EINVAL  Incorrectly aligned address, bad redistributor region
              count/index, mixed redistributor region attribute usage
-    -EEXIST: Address already configured
-    -ENOENT: Attempt to read the characteristics of a non existing
+    -EEXIST  Address already configured
+    -ENOENT  Attempt to read the characteristics of a non existing
              redistributor region
-    -ENXIO:  The group or attribute is unknown/unsupported for this device
+    -ENXIO   The group or attribute is unknown/unsupported for this device
              or hardware support is missing.
-    -EFAULT: Invalid user pointer for attr->addr.
+    -EFAULT  Invalid user pointer for attr->addr.
+    =======  =============================================================
 
 
-  KVM_DEV_ARM_VGIC_GRP_DIST_REGS
-  KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
-  Attributes:
-    The attr field of kvm_device_attr encodes two values:
-    bits:     | 63   ....  32  |  31   ....    0 |
-    values:   |      mpidr     |      offset     |
+  KVM_DEV_ARM_VGIC_GRP_DIST_REGS, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
+   Attributes:
+
+    The attr field of kvm_device_attr encodes two values::
+
+      bits:     | 63   ....  32  |  31   ....    0 |
+      values:   |      mpidr     |      offset     |
 
     All distributor regs are (rw, 32-bit) and kvm_device_attr.addr points to a
     __u32 value.  64-bit registers must be accessed by separately accessing the
@@ -93,7 +105,8 @@
     redistributor is accessed.  The mpidr is ignored for the distributor.
 
     The mpidr encoding is based on the affinity information in the
-    architecture defined MPIDR, and the field is encoded as follows:
+    architecture defined MPIDR, and the field is encoded as follows::
+
       | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
       |    Aff3    |    Aff2    |    Aff1    |    Aff0    |
 
@@ -148,24 +161,30 @@
     ignored.
 
   Errors:
-    -ENXIO: Getting or setting this register is not yet supported
-    -EBUSY: One or more VCPUs are running
+
+    ======  =====================================================
+    -ENXIO  Getting or setting this register is not yet supported
+    -EBUSY  One or more VCPUs are running
+    ======  =====================================================
 
 
   KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS
-  Attributes:
-    The attr field of kvm_device_attr encodes two values:
-    bits:     | 63      ....       32 | 31  ....  16 | 15  ....  0 |
-    values:   |         mpidr         |      RES     |    instr    |
+   Attributes:
+
+    The attr field of kvm_device_attr encodes two values::
+
+      bits:     | 63      ....       32 | 31  ....  16 | 15  ....  0 |
+      values:   |         mpidr         |      RES     |    instr    |
 
     The mpidr field encodes the CPU ID based on the affinity information in the
-    architecture defined MPIDR, and the field is encoded as follows:
+    architecture defined MPIDR, and the field is encoded as follows::
+
       | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
       |    Aff3    |    Aff2    |    Aff1    |    Aff0    |
 
     The instr field encodes the system register to access based on the fields
     defined in the A64 instruction set encoding for system register access
-    (RES means the bits are reserved for future use and should be zero):
+    (RES means the bits are reserved for future use and should be zero)::
 
       | 15 ... 14 | 13 ... 11 | 10 ... 7 | 6 ... 3 | 2 ... 0 |
       |   Op 0    |    Op1    |    CRn   |   CRm   |   Op2   |
@@ -178,26 +197,35 @@
 
     CPU interface registers access is not implemented for AArch32 mode.
     Error -ENXIO is returned when accessed in AArch32 mode.
+
   Errors:
-    -ENXIO: Getting or setting this register is not yet supported
-    -EBUSY: VCPU is running
-    -EINVAL: Invalid mpidr or register value supplied
+
+    =======  =====================================================
+    -ENXIO   Getting or setting this register is not yet supported
+    -EBUSY   VCPU is running
+    -EINVAL  Invalid mpidr or register value supplied
+    =======  =====================================================
 
 
   KVM_DEV_ARM_VGIC_GRP_NR_IRQS
-  Attributes:
+   Attributes:
+
     A value describing the number of interrupts (SGI, PPI and SPI) for
     this GIC instance, ranging from 64 to 1024, in increments of 32.
 
     kvm_device_attr.addr points to a __u32 value.
 
   Errors:
-    -EINVAL: Value set is out of the expected range
-    -EBUSY: Value has already be set.
+
+    =======  ======================================
+    -EINVAL  Value set is out of the expected range
+    -EBUSY   Value has already be set.
+    =======  ======================================
 
 
   KVM_DEV_ARM_VGIC_GRP_CTRL
-  Attributes:
+   Attributes:
+
     KVM_DEV_ARM_VGIC_CTRL_INIT
       request the initialization of the VGIC, no additional parameter in
       kvm_device_attr.addr.
@@ -205,20 +233,26 @@
       save all LPI pending bits into guest RAM pending tables.
 
       The first kB of the pending table is not altered by this operation.
+
   Errors:
-    -ENXIO: VGIC not properly configured as required prior to calling
-     this attribute
-    -ENODEV: no online VCPU
-    -ENOMEM: memory shortage when allocating vgic internal data
-    -EFAULT: Invalid guest ram access
-    -EBUSY:  One or more VCPUS are running
+
+    =======  ========================================================
+    -ENXIO   VGIC not properly configured as required prior to calling
+             this attribute
+    -ENODEV  no online VCPU
+    -ENOMEM  memory shortage when allocating vgic internal data
+    -EFAULT  Invalid guest ram access
+    -EBUSY   One or more VCPUS are running
+    =======  ========================================================
 
 
   KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO
-  Attributes:
-    The attr field of kvm_device_attr encodes the following values:
-    bits:     | 63      ....       32 | 31   ....    10 | 9  ....  0 |
-    values:   |         mpidr         |      info       |   vINTID   |
+   Attributes:
+
+    The attr field of kvm_device_attr encodes the following values::
+
+      bits:     | 63      ....       32 | 31   ....    10 | 9  ....  0 |
+      values:   |         mpidr         |      info       |   vINTID   |
 
     The vINTID specifies which set of IRQs is reported on.
 
@@ -228,6 +262,7 @@
       VGIC_LEVEL_INFO_LINE_LEVEL:
 	Get/Set the input level of the IRQ line for a set of 32 contiguously
 	numbered interrupts.
+
 	vINTID must be a multiple of 32.
 
 	kvm_device_attr.addr points to a __u32 value which will contain a
@@ -243,9 +278,14 @@
     reported with the same value regardless of the mpidr specified.
 
     The mpidr field encodes the CPU ID based on the affinity information in the
-    architecture defined MPIDR, and the field is encoded as follows:
+    architecture defined MPIDR, and the field is encoded as follows::
+
       | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
       |    Aff3    |    Aff2    |    Aff1    |    Aff0    |
+
   Errors:
-    -EINVAL: vINTID is not multiple of 32 or
-     info field is not VGIC_LEVEL_INFO_LINE_LEVEL
+
+    =======  =============================================
+    -EINVAL  vINTID is not multiple of 32 or info field is
+	     not VGIC_LEVEL_INFO_LINE_LEVEL
+    =======  =============================================
diff --git a/Documentation/virt/kvm/devices/arm-vgic.txt b/Documentation/virt/kvm/devices/arm-vgic.rst
similarity index 66%
rename from Documentation/virt/kvm/devices/arm-vgic.txt
rename to Documentation/virt/kvm/devices/arm-vgic.rst
index 97b6518..40bdeea 100644
--- a/Documentation/virt/kvm/devices/arm-vgic.txt
+++ b/Documentation/virt/kvm/devices/arm-vgic.rst
@@ -1,8 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================================
 ARM Virtual Generic Interrupt Controller v2 (VGIC)
 ==================================================
 
 Device types supported:
-  KVM_DEV_TYPE_ARM_VGIC_V2     ARM Generic Interrupt Controller v2.0
+
+  - KVM_DEV_TYPE_ARM_VGIC_V2     ARM Generic Interrupt Controller v2.0
 
 Only one VGIC instance may be instantiated through either this API or the
 legacy KVM_CREATE_IRQCHIP API.  The created VGIC will act as the VM interrupt
@@ -17,7 +21,8 @@
 
 Groups:
   KVM_DEV_ARM_VGIC_GRP_ADDR
-  Attributes:
+   Attributes:
+
     KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit)
       Base address in the guest physical address space of the GIC distributor
       register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
@@ -27,19 +32,25 @@
       Base address in the guest physical address space of the GIC virtual cpu
       interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
       This address needs to be 4K aligned and the region covers 4 KByte.
+
   Errors:
-    -E2BIG:  Address outside of addressable IPA range
-    -EINVAL: Incorrectly aligned address
-    -EEXIST: Address already configured
-    -ENXIO:  The group or attribute is unknown/unsupported for this device
+
+    =======  =============================================================
+    -E2BIG   Address outside of addressable IPA range
+    -EINVAL  Incorrectly aligned address
+    -EEXIST  Address already configured
+    -ENXIO   The group or attribute is unknown/unsupported for this device
              or hardware support is missing.
-    -EFAULT: Invalid user pointer for attr->addr.
+    -EFAULT  Invalid user pointer for attr->addr.
+    =======  =============================================================
 
   KVM_DEV_ARM_VGIC_GRP_DIST_REGS
-  Attributes:
-    The attr field of kvm_device_attr encodes two values:
-    bits:     | 63   ....  40 | 39 ..  32  |  31   ....    0 |
-    values:   |    reserved   | vcpu_index |      offset     |
+   Attributes:
+
+    The attr field of kvm_device_attr encodes two values::
+
+      bits:     | 63   ....  40 | 39 ..  32  |  31   ....    0 |
+      values:   |    reserved   | vcpu_index |      offset     |
 
     All distributor regs are (rw, 32-bit)
 
@@ -58,16 +69,22 @@
     KVM_DEV_ARM_VGIC_GRP_DIST_REGS and KVM_DEV_ARM_VGIC_GRP_CPU_REGS) to ensure
     the expected behavior. Unless GICD_IIDR has been set from userspace, writes
     to the interrupt group registers (GICD_IGROUPR) are ignored.
+
   Errors:
-    -ENXIO: Getting or setting this register is not yet supported
-    -EBUSY: One or more VCPUs are running
-    -EINVAL: Invalid vcpu_index supplied
+
+    =======  =====================================================
+    -ENXIO   Getting or setting this register is not yet supported
+    -EBUSY   One or more VCPUs are running
+    -EINVAL  Invalid vcpu_index supplied
+    =======  =====================================================
 
   KVM_DEV_ARM_VGIC_GRP_CPU_REGS
-  Attributes:
-    The attr field of kvm_device_attr encodes two values:
-    bits:     | 63   ....  40 | 39 ..  32  |  31   ....    0 |
-    values:   |    reserved   | vcpu_index |      offset     |
+   Attributes:
+
+    The attr field of kvm_device_attr encodes two values::
+
+      bits:     | 63   ....  40 | 39 ..  32  |  31   ....    0 |
+      values:   |    reserved   | vcpu_index |      offset     |
 
     All CPU interface regs are (rw, 32-bit)
 
@@ -101,27 +118,39 @@
     value left by 3 places to obtain the actual priority mask level.
 
   Errors:
-    -ENXIO: Getting or setting this register is not yet supported
-    -EBUSY: One or more VCPUs are running
-    -EINVAL: Invalid vcpu_index supplied
+
+    =======  =====================================================
+    -ENXIO   Getting or setting this register is not yet supported
+    -EBUSY   One or more VCPUs are running
+    -EINVAL  Invalid vcpu_index supplied
+    =======  =====================================================
 
   KVM_DEV_ARM_VGIC_GRP_NR_IRQS
-  Attributes:
+   Attributes:
+
     A value describing the number of interrupts (SGI, PPI and SPI) for
     this GIC instance, ranging from 64 to 1024, in increments of 32.
 
   Errors:
-    -EINVAL: Value set is out of the expected range
-    -EBUSY: Value has already be set, or GIC has already been initialized
-            with default values.
+
+    =======  =============================================================
+    -EINVAL  Value set is out of the expected range
+    -EBUSY   Value has already be set, or GIC has already been initialized
+             with default values.
+    =======  =============================================================
 
   KVM_DEV_ARM_VGIC_GRP_CTRL
-  Attributes:
+   Attributes:
+
     KVM_DEV_ARM_VGIC_CTRL_INIT
       request the initialization of the VGIC or ITS, no additional parameter
       in kvm_device_attr.addr.
+
   Errors:
-    -ENXIO: VGIC not properly configured as required prior to calling
-     this attribute
-    -ENODEV: no online VCPU
-    -ENOMEM: memory shortage when allocating vgic internal data
+
+    =======  =========================================================
+    -ENXIO   VGIC not properly configured as required prior to calling
+             this attribute
+    -ENODEV  no online VCPU
+    -ENOMEM  memory shortage when allocating vgic internal data
+    =======  =========================================================
diff --git a/Documentation/virt/kvm/devices/index.rst b/Documentation/virt/kvm/devices/index.rst
new file mode 100644
index 0000000..192cda7
--- /dev/null
+++ b/Documentation/virt/kvm/devices/index.rst
@@ -0,0 +1,19 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======
+Devices
+=======
+
+.. toctree::
+   :maxdepth: 2
+
+   arm-vgic-its
+   arm-vgic
+   arm-vgic-v3
+   mpic
+   s390_flic
+   vcpu
+   vfio
+   vm
+   xics
+   xive
diff --git a/Documentation/virt/kvm/devices/mpic.txt b/Documentation/virt/kvm/devices/mpic.rst
similarity index 90%
rename from Documentation/virt/kvm/devices/mpic.txt
rename to Documentation/virt/kvm/devices/mpic.rst
index 8257397..55cefe0 100644
--- a/Documentation/virt/kvm/devices/mpic.txt
+++ b/Documentation/virt/kvm/devices/mpic.rst
@@ -1,9 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
 MPIC interrupt controller
 =========================
 
 Device types supported:
-  KVM_DEV_TYPE_FSL_MPIC_20     Freescale MPIC v2.0
-  KVM_DEV_TYPE_FSL_MPIC_42     Freescale MPIC v4.2
+
+  - KVM_DEV_TYPE_FSL_MPIC_20     Freescale MPIC v2.0
+  - KVM_DEV_TYPE_FSL_MPIC_42     Freescale MPIC v4.2
 
 Only one MPIC instance, of any type, may be instantiated.  The created
 MPIC will act as the system interrupt controller, connecting to each
@@ -11,7 +15,8 @@
 
 Groups:
   KVM_DEV_MPIC_GRP_MISC
-  Attributes:
+   Attributes:
+
     KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit)
       Base address of the 256 KiB MPIC register space.  Must be
       naturally aligned.  A value of zero disables the mapping.
diff --git a/Documentation/virt/kvm/devices/s390_flic.txt b/Documentation/virt/kvm/devices/s390_flic.rst
similarity index 87%
rename from Documentation/virt/kvm/devices/s390_flic.txt
rename to Documentation/virt/kvm/devices/s390_flic.rst
index a4e20a0..954190d 100644
--- a/Documentation/virt/kvm/devices/s390_flic.txt
+++ b/Documentation/virt/kvm/devices/s390_flic.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================
 FLIC (floating interrupt controller)
 ====================================
 
@@ -31,8 +34,10 @@
     Copies all floating interrupts into a buffer provided by userspace.
     When the buffer is too small it returns -ENOMEM, which is the indication
     for userspace to try again with a bigger buffer.
+
     -ENOBUFS is returned when the allocation of a kernelspace buffer has
     failed.
+
     -EFAULT is returned when copying data to userspace failed.
     All interrupts remain pending, i.e. are not deleted from the list of
     currently pending interrupts.
@@ -60,38 +65,41 @@
 
   KVM_DEV_FLIC_ADAPTER_REGISTER
     Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter
-    describing the adapter to register:
+    describing the adapter to register::
 
-struct kvm_s390_io_adapter {
-	__u32 id;
-	__u8 isc;
-	__u8 maskable;
-	__u8 swap;
-	__u8 flags;
-};
+	struct kvm_s390_io_adapter {
+		__u32 id;
+		__u8 isc;
+		__u8 maskable;
+		__u8 swap;
+		__u8 flags;
+	};
 
    id contains the unique id for the adapter, isc the I/O interruption subclass
    to use, maskable whether this adapter may be masked (interrupts turned off),
    swap whether the indicators need to be byte swapped, and flags contains
    further characteristics of the adapter.
+
    Currently defined values for 'flags' are:
+
    - KVM_S390_ADAPTER_SUPPRESSIBLE: adapter is subject to AIS
      (adapter-interrupt-suppression) facility. This flag only has an effect if
      the AIS capability is enabled.
+
    Unknown flag values are ignored.
 
 
   KVM_DEV_FLIC_ADAPTER_MODIFY
     Modifies attributes of an existing I/O adapter interrupt source. Takes
-    a kvm_s390_io_adapter_req specifying the adapter and the operation:
+    a kvm_s390_io_adapter_req specifying the adapter and the operation::
 
-struct kvm_s390_io_adapter_req {
-	__u32 id;
-	__u8 type;
-	__u8 mask;
-	__u16 pad0;
-	__u64 addr;
-};
+	struct kvm_s390_io_adapter_req {
+		__u32 id;
+		__u8 type;
+		__u8 mask;
+		__u16 pad0;
+		__u64 addr;
+	};
 
     id specifies the adapter and type the operation. The supported operations
     are:
@@ -103,8 +111,9 @@
       perform a gmap translation for the guest address provided in addr,
       pin a userspace page for the translated address and add it to the
       list of mappings
-      Note: A new mapping will be created unconditionally; therefore,
-            the calling code should avoid making duplicate mappings.
+
+      .. note:: A new mapping will be created unconditionally; therefore,
+	        the calling code should avoid making duplicate mappings.
 
     KVM_S390_IO_ADAPTER_UNMAP
       release a userspace page for the translated address specified in addr
@@ -112,16 +121,17 @@
 
   KVM_DEV_FLIC_AISM
     modify the adapter-interruption-suppression mode for a given isc if the
-    AIS capability is enabled. Takes a kvm_s390_ais_req describing:
+    AIS capability is enabled. Takes a kvm_s390_ais_req describing::
 
-struct kvm_s390_ais_req {
-	__u8 isc;
-	__u16 mode;
-};
+	struct kvm_s390_ais_req {
+		__u8 isc;
+		__u16 mode;
+	};
 
     isc contains the target I/O interruption subclass, mode the target
     adapter-interruption-suppression mode. The following modes are
     currently supported:
+
     - KVM_S390_AIS_MODE_ALL: ALL-Interruptions Mode, i.e. airq injection
       is always allowed;
     - KVM_S390_AIS_MODE_SINGLE: SINGLE-Interruption Mode, i.e. airq
@@ -139,12 +149,12 @@
 
   KVM_DEV_FLIC_AISM_ALL
     Gets or sets the adapter-interruption-suppression mode for all ISCs. Takes
-    a kvm_s390_ais_all describing:
+    a kvm_s390_ais_all describing::
 
-struct kvm_s390_ais_all {
-       __u8 simm; /* Single-Interruption-Mode mask */
-       __u8 nimm; /* No-Interruption-Mode mask *
-};
+	struct kvm_s390_ais_all {
+	       __u8 simm; /* Single-Interruption-Mode mask */
+	       __u8 nimm; /* No-Interruption-Mode mask *
+	};
 
     simm contains Single-Interruption-Mode mask for all ISCs, nimm contains
     No-Interruption-Mode mask for all ISCs. Each bit in simm and nimm corresponds
@@ -159,5 +169,5 @@
 that a FLIC operation is unavailable based on the error code resulting from a
 usage attempt.
 
-Note: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a zero
-schid is specified.
+.. note:: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a
+	  zero schid is specified.
diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst
new file mode 100644
index 0000000..9963e68
--- /dev/null
+++ b/Documentation/virt/kvm/devices/vcpu.rst
@@ -0,0 +1,114 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+Generic vcpu interface
+======================
+
+The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct
+kvm_device_attr as other devices, but targets VCPU-wide settings and controls.
+
+The groups and attributes per virtual cpu, if any, are architecture specific.
+
+1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL
+==================================
+
+:Architectures: ARM64
+
+1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ
+---------------------------------------
+
+:Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
+	     pointer to an int
+
+Returns:
+
+	 =======  ========================================================
+	 -EBUSY   The PMU overflow interrupt is already set
+	 -ENXIO   The overflow interrupt not set when attempting to get it
+	 -ENODEV  PMUv3 not supported
+	 -EINVAL  Invalid PMU overflow interrupt number supplied or
+		  trying to set the IRQ number without using an in-kernel
+		  irqchip.
+	 =======  ========================================================
+
+A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
+number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
+type must be same for each vcpu. As a PPI, the interrupt number is the same for
+all vcpus, while as an SPI it must be a separate number per vcpu.
+
+1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
+---------------------------------------
+
+:Parameters: no additional parameter in kvm_device_attr.addr
+
+Returns:
+
+	 =======  ======================================================
+	 -ENODEV  PMUv3 not supported or GIC not initialized
+	 -ENXIO   PMUv3 not properly configured or in-kernel irqchip not
+		  configured as required prior to calling this attribute
+	 -EBUSY   PMUv3 already initialized
+	 =======  ======================================================
+
+Request the initialization of the PMUv3.  If using the PMUv3 with an in-kernel
+virtual GIC implementation, this must be done after initializing the in-kernel
+irqchip.
+
+
+2. GROUP: KVM_ARM_VCPU_TIMER_CTRL
+=================================
+
+:Architectures: ARM, ARM64
+
+2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_VTIMER, KVM_ARM_VCPU_TIMER_IRQ_PTIMER
+-----------------------------------------------------------------------------
+
+:Parameters: in kvm_device_attr.addr the address for the timer interrupt is a
+	     pointer to an int
+
+Returns:
+
+	 =======  =================================
+	 -EINVAL  Invalid timer interrupt number
+	 -EBUSY   One or more VCPUs has already run
+	 =======  =================================
+
+A value describing the architected timer interrupt number when connected to an
+in-kernel virtual GIC.  These must be a PPI (16 <= intid < 32).  Setting the
+attribute overrides the default values (see below).
+
+=============================  ==========================================
+KVM_ARM_VCPU_TIMER_IRQ_VTIMER  The EL1 virtual timer intid (default: 27)
+KVM_ARM_VCPU_TIMER_IRQ_PTIMER  The EL1 physical timer intid (default: 30)
+=============================  ==========================================
+
+Setting the same PPI for different timers will prevent the VCPUs from running.
+Setting the interrupt number on a VCPU configures all VCPUs created at that
+time to use the number provided for a given timer, overwriting any previously
+configured values on other VCPUs.  Userspace should configure the interrupt
+numbers on at least one VCPU after creating all VCPUs and before running any
+VCPUs.
+
+3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL
+==================================
+
+:Architectures: ARM64
+
+3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA
+--------------------------------------
+
+:Parameters: 64-bit base address
+
+Returns:
+
+	 =======  ======================================
+	 -ENXIO   Stolen time not implemented
+	 -EEXIST  Base address already set for this VCPU
+	 -EINVAL  Base address not 64 byte aligned
+	 =======  ======================================
+
+Specifies the base address of the stolen time structure for this VCPU. The
+base address must be 64 byte aligned and exist within a valid guest memory
+region. See Documentation/virt/kvm/arm/pvtime.txt for more information
+including the layout of the stolen time structure.
diff --git a/Documentation/virt/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt
deleted file mode 100644
index 6f3bd64..0000000
--- a/Documentation/virt/kvm/devices/vcpu.txt
+++ /dev/null
@@ -1,76 +0,0 @@
-Generic vcpu interface
-====================================
-
-The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
-KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct
-kvm_device_attr as other devices, but targets VCPU-wide settings and controls.
-
-The groups and attributes per virtual cpu, if any, are architecture specific.
-
-1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL
-Architectures: ARM64
-
-1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ
-Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
-            pointer to an int
-Returns: -EBUSY: The PMU overflow interrupt is already set
-         -ENXIO: The overflow interrupt not set when attempting to get it
-         -ENODEV: PMUv3 not supported
-         -EINVAL: Invalid PMU overflow interrupt number supplied or
-                  trying to set the IRQ number without using an in-kernel
-                  irqchip.
-
-A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
-number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
-type must be same for each vcpu. As a PPI, the interrupt number is the same for
-all vcpus, while as an SPI it must be a separate number per vcpu.
-
-1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
-Parameters: no additional parameter in kvm_device_attr.addr
-Returns: -ENODEV: PMUv3 not supported or GIC not initialized
-         -ENXIO: PMUv3 not properly configured or in-kernel irqchip not
-                 configured as required prior to calling this attribute
-         -EBUSY: PMUv3 already initialized
-
-Request the initialization of the PMUv3.  If using the PMUv3 with an in-kernel
-virtual GIC implementation, this must be done after initializing the in-kernel
-irqchip.
-
-
-2. GROUP: KVM_ARM_VCPU_TIMER_CTRL
-Architectures: ARM,ARM64
-
-2.1. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_VTIMER
-2.2. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_PTIMER
-Parameters: in kvm_device_attr.addr the address for the timer interrupt is a
-            pointer to an int
-Returns: -EINVAL: Invalid timer interrupt number
-         -EBUSY:  One or more VCPUs has already run
-
-A value describing the architected timer interrupt number when connected to an
-in-kernel virtual GIC.  These must be a PPI (16 <= intid < 32).  Setting the
-attribute overrides the default values (see below).
-
-KVM_ARM_VCPU_TIMER_IRQ_VTIMER: The EL1 virtual timer intid (default: 27)
-KVM_ARM_VCPU_TIMER_IRQ_PTIMER: The EL1 physical timer intid (default: 30)
-
-Setting the same PPI for different timers will prevent the VCPUs from running.
-Setting the interrupt number on a VCPU configures all VCPUs created at that
-time to use the number provided for a given timer, overwriting any previously
-configured values on other VCPUs.  Userspace should configure the interrupt
-numbers on at least one VCPU after creating all VCPUs and before running any
-VCPUs.
-
-3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL
-Architectures: ARM64
-
-3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA
-Parameters: 64-bit base address
-Returns: -ENXIO:  Stolen time not implemented
-         -EEXIST: Base address already set for this VCPU
-         -EINVAL: Base address not 64 byte aligned
-
-Specifies the base address of the stolen time structure for this VCPU. The
-base address must be 64 byte aligned and exist within a valid guest memory
-region. See Documentation/virt/kvm/arm/pvtime.txt for more information
-including the layout of the stolen time structure.
diff --git a/Documentation/virt/kvm/devices/vfio.txt b/Documentation/virt/kvm/devices/vfio.rst
similarity index 72%
rename from Documentation/virt/kvm/devices/vfio.txt
rename to Documentation/virt/kvm/devices/vfio.rst
index 528c77c..2d20dc5 100644
--- a/Documentation/virt/kvm/devices/vfio.txt
+++ b/Documentation/virt/kvm/devices/vfio.rst
@@ -1,8 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================
 VFIO virtual device
 ===================
 
 Device types supported:
-  KVM_DEV_TYPE_VFIO
+
+  - KVM_DEV_TYPE_VFIO
 
 Only one VFIO instance may be created per VM.  The created device
 tracks VFIO groups in use by the VM and features of those groups
@@ -23,14 +27,15 @@
 	for the VFIO group.
   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
 	allocated by sPAPR KVM.
-	kvm_device_attr.addr points to a struct:
+	kvm_device_attr.addr points to a struct::
 
-	struct kvm_vfio_spapr_tce {
-		__s32	groupfd;
-		__s32	tablefd;
-	};
+		struct kvm_vfio_spapr_tce {
+			__s32	groupfd;
+			__s32	tablefd;
+		};
 
-	where
-	@groupfd is a file descriptor for a VFIO group;
-	@tablefd is a file descriptor for a TCE table allocated via
-		KVM_CREATE_SPAPR_TCE.
+	where:
+
+	- @groupfd is a file descriptor for a VFIO group;
+	- @tablefd is a file descriptor for a TCE table allocated via
+	  KVM_CREATE_SPAPR_TCE.
diff --git a/Documentation/virt/kvm/devices/vm.txt b/Documentation/virt/kvm/devices/vm.rst
similarity index 61%
rename from Documentation/virt/kvm/devices/vm.txt
rename to Documentation/virt/kvm/devices/vm.rst
index 4ffb82b..0aa5b1c 100644
--- a/Documentation/virt/kvm/devices/vm.txt
+++ b/Documentation/virt/kvm/devices/vm.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
 Generic vm interface
-====================================
+====================
 
 The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
 KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same
@@ -10,30 +13,38 @@
 specific.
 
 1. GROUP: KVM_S390_VM_MEM_CTRL
-Architectures: s390
+==============================
+
+:Architectures: s390
 
 1.1. ATTRIBUTE: KVM_S390_VM_MEM_ENABLE_CMMA
-Parameters: none
-Returns: -EBUSY if a vcpu is already defined, otherwise 0
+-------------------------------------------
+
+:Parameters: none
+:Returns: -EBUSY if a vcpu is already defined, otherwise 0
 
 Enables Collaborative Memory Management Assist (CMMA) for the virtual machine.
 
 1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA
-Parameters: none
-Returns: -EINVAL if CMMA was not enabled
-         0 otherwise
+----------------------------------------
+
+:Parameters: none
+:Returns: -EINVAL if CMMA was not enabled;
+	  0 otherwise
 
 Clear the CMMA status for all guest pages, so any pages the guest marked
 as unused are again used any may not be reclaimed by the host.
 
 1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE
-Parameters: in attr->addr the address for the new limit of guest memory
-Returns: -EFAULT if the given address is not accessible
-         -EINVAL if the virtual machine is of type UCONTROL
-         -E2BIG if the given guest memory is to big for that machine
-         -EBUSY if a vcpu is already defined
-         -ENOMEM if not enough memory is available for a new shadow guest mapping
-          0 otherwise
+-----------------------------------------
+
+:Parameters: in attr->addr the address for the new limit of guest memory
+:Returns: -EFAULT if the given address is not accessible;
+	  -EINVAL if the virtual machine is of type UCONTROL;
+	  -E2BIG if the given guest memory is to big for that machine;
+	  -EBUSY if a vcpu is already defined;
+	  -ENOMEM if not enough memory is available for a new shadow guest mapping;
+	  0 otherwise.
 
 Allows userspace to query the actual limit and set a new limit for
 the maximum guest memory size. The limit will be rounded up to
@@ -42,78 +53,92 @@
 the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX).
 
 2. GROUP: KVM_S390_VM_CPU_MODEL
-Architectures: s390
+===============================
+
+:Architectures: s390
 
 2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o)
+---------------------------------------------
 
-Allows user space to retrieve machine and kvm specific cpu related information:
+Allows user space to retrieve machine and kvm specific cpu related information::
 
-struct kvm_s390_vm_cpu_machine {
+  struct kvm_s390_vm_cpu_machine {
        __u64 cpuid;           # CPUID of host
        __u32 ibc;             # IBC level range offered by host
        __u8  pad[4];
        __u64 fac_mask[256];   # set of cpu facilities enabled by KVM
        __u64 fac_list[256];   # set of cpu facilities offered by host
-}
+  }
 
-Parameters: address of buffer to store the machine related cpu data
-            of type struct kvm_s390_vm_cpu_machine*
-Returns:    -EFAULT if the given address is not accessible from kernel space
-	    -ENOMEM if not enough memory is available to process the ioctl
-	    0 in case of success
+:Parameters: address of buffer to store the machine related cpu data
+	     of type struct kvm_s390_vm_cpu_machine*
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
+	    -ENOMEM if not enough memory is available to process the ioctl;
+	    0 in case of success.
 
 2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w)
+===============================================
 
-Allows user space to retrieve or request to change cpu related information for a vcpu:
+Allows user space to retrieve or request to change cpu related information for a vcpu::
 
-struct kvm_s390_vm_cpu_processor {
+  struct kvm_s390_vm_cpu_processor {
        __u64 cpuid;           # CPUID currently (to be) used by this vcpu
        __u16 ibc;             # IBC level currently (to be) used by this vcpu
        __u8  pad[6];
        __u64 fac_list[256];   # set of cpu facilities currently (to be) used
-                              # by this vcpu
-}
+			      # by this vcpu
+  }
 
 KVM does not enforce or limit the cpu model data in any form. Take the information
 retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration
 setups. Instruction interceptions triggered by additionally set facility bits that
 are not handled by KVM need to by imlemented in the VM driver code.
 
-Parameters: address of buffer to store/set the processor related cpu
-	    data of type struct kvm_s390_vm_cpu_processor*.
-Returns:    -EBUSY in case 1 or more vcpus are already activated (only in write case)
-	    -EFAULT if the given address is not accessible from kernel space
-	    -ENOMEM if not enough memory is available to process the ioctl
-	    0 in case of success
+:Parameters: address of buffer to store/set the processor related cpu
+	     data of type struct kvm_s390_vm_cpu_processor*.
+:Returns:  -EBUSY in case 1 or more vcpus are already activated (only in write case);
+	   -EFAULT if the given address is not accessible from kernel space;
+	   -ENOMEM if not enough memory is available to process the ioctl;
+	   0 in case of success.
+
+.. _KVM_S390_VM_CPU_MACHINE_FEAT:
 
 2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o)
+--------------------------------------------------
 
 Allows user space to retrieve available cpu features. A feature is available if
 provided by the hardware and supported by kvm. In theory, cpu features could
 even be completely emulated by kvm.
 
-struct kvm_s390_vm_cpu_feat {
-        __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering
-};
+::
 
-Parameters: address of a buffer to load the feature list from.
-Returns:    -EFAULT if the given address is not accessible from kernel space.
-	    0 in case of success.
+  struct kvm_s390_vm_cpu_feat {
+	__u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering
+  };
+
+:Parameters: address of a buffer to load the feature list from.
+:Returns:  -EFAULT if the given address is not accessible from kernel space;
+	   0 in case of success.
 
 2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w)
+----------------------------------------------------
 
 Allows user space to retrieve or change enabled cpu features for all VCPUs of a
 VM. Features that are not available cannot be enabled.
 
-See 2.3. for a description of the parameter struct.
+See :ref:`KVM_S390_VM_CPU_MACHINE_FEAT` for
+a description of the parameter struct.
 
-Parameters: address of a buffer to store/load the feature list from.
-Returns:    -EFAULT if the given address is not accessible from kernel space.
-	    -EINVAL if a cpu feature that is not available is to be enabled.
-	    -EBUSY if at least one VCPU has already been defined.
+:Parameters: address of a buffer to store/load the feature list from.
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
+	    -EINVAL if a cpu feature that is not available is to be enabled;
+	    -EBUSY if at least one VCPU has already been defined;
 	    0 in case of success.
 
+.. _KVM_S390_VM_CPU_MACHINE_SUBFUNC:
+
 2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o)
+-----------------------------------------------------
 
 Allows user space to retrieve available cpu subfunctions without any filtering
 done by a set IBC. These subfunctions are indicated to the guest VCPU via
@@ -126,7 +151,9 @@
 indicates subfunctions via a "test bit" mechanism, the subfunction codes are
 contained in the returned struct in MSB 0 bit numbering.
 
-struct kvm_s390_vm_cpu_subfunc {
+::
+
+  struct kvm_s390_vm_cpu_subfunc {
        u8 plo[32];           # always valid (ESA/390 feature)
        u8 ptff[16];          # valid with TOD-clock steering
        u8 kmac[16];          # valid with Message-Security-Assist
@@ -143,13 +170,14 @@
        u8 kma[16];           # valid with Message-Security-Assist-Extension 8
        u8 kdsa[16];          # valid with Message-Security-Assist-Extension 9
        u8 reserved[1792];    # reserved for future instructions
-};
+  };
 
-Parameters: address of a buffer to load the subfunction blocks from.
-Returns:    -EFAULT if the given address is not accessible from kernel space.
+:Parameters: address of a buffer to load the subfunction blocks from.
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
 	    0 in case of success.
 
 2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w)
+-------------------------------------------------------
 
 Allows user space to retrieve or change cpu subfunctions to be indicated for
 all VCPUs of a VM. This attribute will only be available if kernel and
@@ -164,107 +192,125 @@
 to determine available subfunctions in this case, this will guarantee backward
 compatibility.
 
-See 2.5. for a description of the parameter struct.
+See :ref:`KVM_S390_VM_CPU_MACHINE_SUBFUNC` for a
+description of the parameter struct.
 
-Parameters: address of a buffer to store/load the subfunction blocks from.
-Returns:    -EFAULT if the given address is not accessible from kernel space.
-	    -EINVAL when reading, if there was no write yet.
-	    -EBUSY if at least one VCPU has already been defined.
+:Parameters: address of a buffer to store/load the subfunction blocks from.
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
+	    -EINVAL when reading, if there was no write yet;
+	    -EBUSY if at least one VCPU has already been defined;
 	    0 in case of success.
 
 3. GROUP: KVM_S390_VM_TOD
-Architectures: s390
+=========================
+
+:Architectures: s390
 
 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
+------------------------------------
 
 Allows user space to set/get the TOD clock extension (u8) (superseded by
 KVM_S390_VM_TOD_EXT).
 
-Parameters: address of a buffer in user space to store the data (u8) to
-Returns:    -EFAULT if the given address is not accessible from kernel space
+:Parameters: address of a buffer in user space to store the data (u8) to
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
 	    -EINVAL if setting the TOD clock extension to != 0 is not supported
 
 3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
+-----------------------------------
 
 Allows user space to set/get bits 0-63 of the TOD clock register as defined in
 the POP (u64).
 
-Parameters: address of a buffer in user space to store the data (u64) to
-Returns:    -EFAULT if the given address is not accessible from kernel space
+:Parameters: address of a buffer in user space to store the data (u64) to
+:Returns:    -EFAULT if the given address is not accessible from kernel space
 
 3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
+-----------------------------------
+
 Allows user space to set/get bits 0-63 of the TOD clock register as defined in
 the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
 also allows user space to get/set it. If the guest CPU model does not support
 it, it is stored as 0 and not allowed to be set to a value != 0.
 
-Parameters: address of a buffer in user space to store the data
-            (kvm_s390_vm_tod_clock) to
-Returns:    -EFAULT if the given address is not accessible from kernel space
+:Parameters: address of a buffer in user space to store the data
+	     (kvm_s390_vm_tod_clock) to
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
 	    -EINVAL if setting the TOD clock extension to != 0 is not supported
 
 4. GROUP: KVM_S390_VM_CRYPTO
-Architectures: s390
+============================
+
+:Architectures: s390
 
 4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o)
+------------------------------------------------------
 
 Allows user space to enable aes key wrapping, including generating a new
 wrapping key.
 
-Parameters: none
-Returns:    0
+:Parameters: none
+:Returns:    0
 
 4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o)
+------------------------------------------------------
 
 Allows user space to enable dea key wrapping, including generating a new
 wrapping key.
 
-Parameters: none
-Returns:    0
+:Parameters: none
+:Returns:    0
 
 4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o)
+-------------------------------------------------------
 
 Allows user space to disable aes key wrapping, clearing the wrapping key.
 
-Parameters: none
-Returns:    0
+:Parameters: none
+:Returns:    0
 
 4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o)
+-------------------------------------------------------
 
 Allows user space to disable dea key wrapping, clearing the wrapping key.
 
-Parameters: none
-Returns:    0
+:Parameters: none
+:Returns:    0
 
 5. GROUP: KVM_S390_VM_MIGRATION
-Architectures: s390
+===============================
+
+:Architectures: s390
 
 5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o)
+------------------------------------------------
 
 Allows userspace to stop migration mode, needed for PGSTE migration.
 Setting this attribute when migration mode is not active will have no
 effects.
 
-Parameters: none
-Returns:    0
+:Parameters: none
+:Returns:    0
 
 5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o)
+-------------------------------------------------
 
 Allows userspace to start migration mode, needed for PGSTE migration.
 Setting this attribute when migration mode is already active will have
 no effects.
 
-Parameters: none
-Returns:    -ENOMEM if there is not enough free memory to start migration mode
-	    -EINVAL if the state of the VM is invalid (e.g. no memory defined)
+:Parameters: none
+:Returns:   -ENOMEM if there is not enough free memory to start migration mode;
+	    -EINVAL if the state of the VM is invalid (e.g. no memory defined);
 	    0 in case of success.
 
 5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o)
+--------------------------------------------------
 
 Allows userspace to query the status of migration mode.
 
-Parameters: address of a buffer in user space to store the data (u64) to;
-	    the data itself is either 0 if migration mode is disabled or 1
-	    if it is enabled
-Returns:    -EFAULT if the given address is not accessible from kernel space
+:Parameters: address of a buffer in user space to store the data (u64) to;
+	     the data itself is either 0 if migration mode is disabled or 1
+	     if it is enabled
+:Returns:   -EFAULT if the given address is not accessible from kernel space;
 	    0 in case of success.
diff --git a/Documentation/virt/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.rst
similarity index 83%
rename from Documentation/virt/kvm/devices/xics.txt
rename to Documentation/virt/kvm/devices/xics.rst
index 423332d..2d6927e 100644
--- a/Documentation/virt/kvm/devices/xics.txt
+++ b/Documentation/virt/kvm/devices/xics.rst
@@ -1,20 +1,31 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
 XICS interrupt controller
+=========================
 
 Device type supported: KVM_DEV_TYPE_XICS
 
 Groups:
   1. KVM_DEV_XICS_GRP_SOURCES
-  Attributes: One per interrupt source, indexed by the source number.
+       Attributes:
 
+         One per interrupt source, indexed by the source number.
   2. KVM_DEV_XICS_GRP_CTRL
-  Attributes:
-    2.1 KVM_DEV_XICS_NR_SERVERS (write only)
+       Attributes:
+
+         2.1 KVM_DEV_XICS_NR_SERVERS (write only)
+
   The kvm_device_attr.addr points to a __u32 value which is the number of
   interrupt server numbers (ie, highest possible vcpu id plus one).
+
   Errors:
-    -EINVAL: Value greater than KVM_MAX_VCPU_ID.
-    -EFAULT: Invalid user pointer for attr->addr.
-    -EBUSY:  A vcpu is already connected to the device.
+
+    =======  ==========================================
+    -EINVAL  Value greater than KVM_MAX_VCPU_ID.
+    -EFAULT  Invalid user pointer for attr->addr.
+    -EBUSY   A vcpu is already connected to the device.
+    =======  ==========================================
 
 This device emulates the XICS (eXternal Interrupt Controller
 Specification) defined in PAPR.  The XICS has a set of interrupt
@@ -53,24 +64,29 @@
 bitfields, starting from the least-significant end of the word:
 
 * Destination (server number), 32 bits
+
   This specifies where the interrupt should be sent, and is the
   interrupt server number specified for the destination vcpu.
 
 * Priority, 8 bits
+
   This is the priority specified for this interrupt source, where 0 is
   the highest priority and 255 is the lowest.  An interrupt with a
   priority of 255 will never be delivered.
 
 * Level sensitive flag, 1 bit
+
   This bit is 1 for a level-sensitive interrupt source, or 0 for
   edge-sensitive (or MSI).
 
 * Masked flag, 1 bit
+
   This bit is set to 1 if the interrupt is masked (cannot be delivered
   regardless of its priority), for example by the ibm,int-off RTAS
   call, or 0 if it is not masked.
 
 * Pending flag, 1 bit
+
   This bit is 1 if the source has a pending interrupt, otherwise 0.
 
 Only one XICS instance may be created per VM.
diff --git a/Documentation/virt/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.rst
similarity index 62%
rename from Documentation/virt/kvm/devices/xive.txt
rename to Documentation/virt/kvm/devices/xive.rst
index f5d1d6b..8bdf3dc 100644
--- a/Documentation/virt/kvm/devices/xive.txt
+++ b/Documentation/virt/kvm/devices/xive.rst
@@ -1,8 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================================================
 POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1)
-==========================================================
+===========================================================
 
 Device types supported:
-  KVM_DEV_TYPE_XIVE     POWER9 XIVE Interrupt Controller generation 1
+  - KVM_DEV_TYPE_XIVE     POWER9 XIVE Interrupt Controller generation 1
 
 This device acts as a VM interrupt controller. It provides the KVM
 interface to configure the interrupt sources of a VM in the underlying
@@ -64,72 +67,100 @@
 
 * Groups:
 
-  1. KVM_DEV_XIVE_GRP_CTRL
-  Provides global controls on the device
+1. KVM_DEV_XIVE_GRP_CTRL
+     Provides global controls on the device
+
   Attributes:
     1.1 KVM_DEV_XIVE_RESET (write only)
     Resets the interrupt controller configuration for sources and event
     queues. To be used by kexec and kdump.
+
     Errors: none
 
     1.2 KVM_DEV_XIVE_EQ_SYNC (write only)
     Sync all the sources and queues and mark the EQ pages dirty. This
     to make sure that a consistent memory state is captured when
     migrating the VM.
+
     Errors: none
 
     1.3 KVM_DEV_XIVE_NR_SERVERS (write only)
     The kvm_device_attr.addr points to a __u32 value which is the number of
     interrupt server numbers (ie, highest possible vcpu id plus one).
-    Errors:
-      -EINVAL: Value greater than KVM_MAX_VCPU_ID.
-      -EFAULT: Invalid user pointer for attr->addr.
-      -EBUSY:  A vCPU is already connected to the device.
 
-  2. KVM_DEV_XIVE_GRP_SOURCE (write only)
-  Initializes a new source in the XIVE device and mask it.
+    Errors:
+
+      =======  ==========================================
+      -EINVAL  Value greater than KVM_MAX_VCPU_ID.
+      -EFAULT  Invalid user pointer for attr->addr.
+      -EBUSY   A vCPU is already connected to the device.
+      =======  ==========================================
+
+2. KVM_DEV_XIVE_GRP_SOURCE (write only)
+     Initializes a new source in the XIVE device and mask it.
+
   Attributes:
     Interrupt source number  (64-bit)
-  The kvm_device_attr.addr points to a __u64 value:
-  bits:     | 63   ....  2 |   1   |   0
-  values:   |    unused    | level | type
+
+  The kvm_device_attr.addr points to a __u64 value::
+
+    bits:     | 63   ....  2 |   1   |   0
+    values:   |    unused    | level | type
+
   - type:  0:MSI 1:LSI
   - level: assertion level in case of an LSI.
-  Errors:
-    -E2BIG:  Interrupt source number is out of range
-    -ENOMEM: Could not create a new source block
-    -EFAULT: Invalid user pointer for attr->addr.
-    -ENXIO:  Could not allocate underlying HW interrupt
 
-  3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only)
-  Configures source targeting
+  Errors:
+
+    =======  ==========================================
+    -E2BIG   Interrupt source number is out of range
+    -ENOMEM  Could not create a new source block
+    -EFAULT  Invalid user pointer for attr->addr.
+    -ENXIO   Could not allocate underlying HW interrupt
+    =======  ==========================================
+
+3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only)
+     Configures source targeting
+
   Attributes:
     Interrupt source number  (64-bit)
-  The kvm_device_attr.addr points to a __u64 value:
-  bits:     | 63   ....  33 |  32  | 31 .. 3 |  2 .. 0
-  values:   |    eisn       | mask |  server | priority
+
+  The kvm_device_attr.addr points to a __u64 value::
+
+    bits:     | 63   ....  33 |  32  | 31 .. 3 |  2 .. 0
+    values:   |    eisn       | mask |  server | priority
+
   - priority: 0-7 interrupt priority level
   - server: CPU number chosen to handle the interrupt
   - mask: mask flag (unused)
   - eisn: Effective Interrupt Source Number
-  Errors:
-    -ENOENT: Unknown source number
-    -EINVAL: Not initialized source number
-    -EINVAL: Invalid priority
-    -EINVAL: Invalid CPU number.
-    -EFAULT: Invalid user pointer for attr->addr.
-    -ENXIO:  CPU event queues not configured or configuration of the
-             underlying HW interrupt failed
-    -EBUSY:  No CPU available to serve interrupt
 
-  4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
-  Configures an event queue of a CPU
+  Errors:
+
+    =======  =======================================================
+    -ENOENT  Unknown source number
+    -EINVAL  Not initialized source number
+    -EINVAL  Invalid priority
+    -EINVAL  Invalid CPU number.
+    -EFAULT  Invalid user pointer for attr->addr.
+    -ENXIO   CPU event queues not configured or configuration of the
+	     underlying HW interrupt failed
+    -EBUSY   No CPU available to serve interrupt
+    =======  =======================================================
+
+4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
+     Configures an event queue of a CPU
+
   Attributes:
     EQ descriptor identifier (64-bit)
-  The EQ descriptor identifier is a tuple (server, priority) :
-  bits:     | 63   ....  32 | 31 .. 3 |  2 .. 0
-  values:   |    unused     |  server | priority
-  The kvm_device_attr.addr points to :
+
+  The EQ descriptor identifier is a tuple (server, priority)::
+
+    bits:     | 63   ....  32 | 31 .. 3 |  2 .. 0
+    values:   |    unused     |  server | priority
+
+  The kvm_device_attr.addr points to::
+
     struct kvm_ppc_xive_eq {
 	__u32 flags;
 	__u32 qshift;
@@ -138,8 +169,9 @@
 	__u32 qindex;
 	__u8  pad[40];
     };
+
   - flags: queue flags
-    KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
+      KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
 	forces notification without using the coalescing mechanism
 	provided by the XIVE END ESBs.
   - qshift: queue size (power of 2)
@@ -147,22 +179,31 @@
   - qtoggle: current queue toggle bit
   - qindex: current queue index
   - pad: reserved for future use
-  Errors:
-    -ENOENT: Invalid CPU number
-    -EINVAL: Invalid priority
-    -EINVAL: Invalid flags
-    -EINVAL: Invalid queue size
-    -EINVAL: Invalid queue address
-    -EFAULT: Invalid user pointer for attr->addr.
-    -EIO:    Configuration of the underlying HW failed
 
-  5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only)
-  Synchronize the source to flush event notifications
+  Errors:
+
+    =======  =========================================
+    -ENOENT  Invalid CPU number
+    -EINVAL  Invalid priority
+    -EINVAL  Invalid flags
+    -EINVAL  Invalid queue size
+    -EINVAL  Invalid queue address
+    -EFAULT  Invalid user pointer for attr->addr.
+    -EIO     Configuration of the underlying HW failed
+    =======  =========================================
+
+5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only)
+     Synchronize the source to flush event notifications
+
   Attributes:
     Interrupt source number  (64-bit)
+
   Errors:
-    -ENOENT: Unknown source number
-    -EINVAL: Not initialized source number
+
+    =======  =============================
+    -ENOENT  Unknown source number
+    -EINVAL  Not initialized source number
+    =======  =============================
 
 * VCPU state
 
@@ -175,11 +216,12 @@
   as it synthesizes the priorities of the pending interrupts. We
   capture a bit more to report debug information.
 
-  KVM_REG_PPC_VP_STATE (2 * 64bits)
-  bits:     |  63  ....  32  |  31  ....  0  |
-  values:   |   TIMA word0   |   TIMA word1  |
-  bits:     | 127       ..........       64  |
-  values:   |            unused              |
+  KVM_REG_PPC_VP_STATE (2 * 64bits)::
+
+    bits:     |  63  ....  32  |  31  ....  0  |
+    values:   |   TIMA word0   |   TIMA word1  |
+    bits:     | 127       ..........       64  |
+    values:   |            unused              |
 
 * Migration:
 
@@ -196,7 +238,7 @@
   3. Capture the state of the source targeting, the EQs configuration
   and the state of thread interrupt context registers.
 
-  Restore is similar :
+  Restore is similar:
 
   1. Restore the EQ configuration. As targeting depends on it.
   2. Restore targeting
diff --git a/Documentation/virt/kvm/halt-polling.txt b/Documentation/virt/kvm/halt-polling.rst
similarity index 64%
rename from Documentation/virt/kvm/halt-polling.txt
rename to Documentation/virt/kvm/halt-polling.rst
index 4f791b1..4922e4a 100644
--- a/Documentation/virt/kvm/halt-polling.txt
+++ b/Documentation/virt/kvm/halt-polling.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
 The KVM halt polling system
 ===========================
 
@@ -68,7 +71,8 @@
 which come at an approximately constant rate, otherwise there will be constant
 adjustment of the polling interval.
 
-[0] total block time: the time between when the halt polling function is
+[0] total block time:
+		      the time between when the halt polling function is
 		      invoked and a wakeup source received (irrespective of
 		      whether the scheduler is invoked within that function).
 
@@ -81,31 +85,32 @@
 parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
 powerpc kvm-hv case.
 
-Module Parameter	|   Description		    |	     Default Value
---------------------------------------------------------------------------------
-halt_poll_ns		| The global max polling    | KVM_HALT_POLL_NS_DEFAULT
-			| interval which defines    |
-			| the ceiling value of the  |
-			| polling interval for      | (per arch value)
-			| each vcpu.		    |
---------------------------------------------------------------------------------
-halt_poll_ns_grow	| The value by which the    | 2
-			| halt polling interval is  |
-			| multiplied in the	    |
-			| grow_halt_poll_ns()	    |
-			| function.		    |
---------------------------------------------------------------------------------
-halt_poll_ns_grow_start | The initial value to grow | 10000
-			| to from zero in the	    |
-			| grow_halt_poll_ns()	    |
-			| function.		    |
---------------------------------------------------------------------------------
-halt_poll_ns_shrink	| The value by which the    | 0
-			| halt polling interval is  |
-			| divided in the	    |
-			| shrink_halt_poll_ns()	    |
-			| function.		    |
---------------------------------------------------------------------------------
++-----------------------+---------------------------+-------------------------+
+|Module Parameter	|   Description		    |	     Default Value    |
++-----------------------+---------------------------+-------------------------+
+|halt_poll_ns		| The global max polling    | KVM_HALT_POLL_NS_DEFAULT|
+|			| interval which defines    |			      |
+|			| the ceiling value of the  |			      |
+|			| polling interval for      | (per arch value)	      |
+|			| each vcpu.		    |			      |
++-----------------------+---------------------------+-------------------------+
+|halt_poll_ns_grow	| The value by which the    | 2			      |
+|			| halt polling interval is  |			      |
+|			| multiplied in the	    |			      |
+|			| grow_halt_poll_ns()	    |			      |
+|			| function.		    |			      |
++-----------------------+---------------------------+-------------------------+
+|halt_poll_ns_grow_start| The initial value to grow | 10000		      |
+|			| to from zero in the	    |			      |
+|			| grow_halt_poll_ns()	    |			      |
+|			| function.		    |			      |
++-----------------------+---------------------------+-------------------------+
+|halt_poll_ns_shrink	| The value by which the    | 0			      |
+|			| halt polling interval is  |			      |
+|			| divided in the	    |			      |
+|			| shrink_halt_poll_ns()	    |			      |
+|			| function.		    |			      |
++-----------------------+---------------------------+-------------------------+
 
 These module parameters can be set from the debugfs files in:
 
@@ -117,20 +122,19 @@
 Further Notes
 =============
 
-- Care should be taken when setting the halt_poll_ns module parameter as a
-large value has the potential to drive the cpu usage to 100% on a machine which
-would be almost entirely idle otherwise. This is because even if a guest has
-wakeups during which very little work is done and which are quite far apart, if
-the period is shorter than the global max polling interval (halt_poll_ns) then
-the host will always poll for the entire block time and thus cpu utilisation
-will go to 100%.
+- Care should be taken when setting the halt_poll_ns module parameter as a large value
+  has the potential to drive the cpu usage to 100% on a machine which would be almost
+  entirely idle otherwise. This is because even if a guest has wakeups during which very
+  little work is done and which are quite far apart, if the period is shorter than the
+  global max polling interval (halt_poll_ns) then the host will always poll for the
+  entire block time and thus cpu utilisation will go to 100%.
 
-- Halt polling essentially presents a trade off between power usage and latency
-and the module parameters should be used to tune the affinity for this. Idle
-cpu time is essentially converted to host kernel time with the aim of decreasing
-latency when entering the guest.
+- Halt polling essentially presents a trade off between power usage and latency and
+  the module parameters should be used to tune the affinity for this. Idle cpu time is
+  essentially converted to host kernel time with the aim of decreasing latency when
+  entering the guest.
 
-- Halt polling will only be conducted by the host when no other tasks are
-runnable on that cpu, otherwise the polling will cease immediately and
-schedule will be invoked to allow that other task to run. Thus this doesn't
-allow a guest to denial of service the cpu.
+- Halt polling will only be conducted by the host when no other tasks are runnable on
+  that cpu, otherwise the polling will cease immediately and schedule will be invoked to
+  allow that other task to run. Thus this doesn't allow a guest to denial of service the
+  cpu.
diff --git a/Documentation/virt/kvm/hypercalls.rst b/Documentation/virt/kvm/hypercalls.rst
new file mode 100644
index 0000000..dbaf207
--- /dev/null
+++ b/Documentation/virt/kvm/hypercalls.rst
@@ -0,0 +1,171 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================
+Linux KVM Hypercall
+===================
+
+X86:
+ KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall
+ instruction. The hypervisor can replace it with instructions that are
+ guaranteed to be supported.
+
+ Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
+ The hypercall number should be placed in rax and the return value will be
+ placed in rax.  No other registers will be clobbered unless explicitly stated
+ by the particular hypercall.
+
+S390:
+  R2-R7 are used for parameters 1-6. In addition, R1 is used for hypercall
+  number. The return value is written to R2.
+
+  S390 uses diagnose instruction as hypercall (0x500) along with hypercall
+  number in R1.
+
+  For further information on the S390 diagnose call as supported by KVM,
+  refer to Documentation/virt/kvm/s390-diag.txt.
+
+PowerPC:
+  It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
+  Return value is placed in R3.
+
+  KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
+  property inside the device tree's /hypervisor node.
+  For more information refer to Documentation/virt/kvm/ppc-pv.txt
+
+MIPS:
+  KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall
+  number in $2 (v0). Up to four arguments may be placed in $4-$7 (a0-a3) and
+  the return value is placed in $2 (v0).
+
+KVM Hypercalls Documentation
+============================
+
+The template for each hypercall is:
+1. Hypercall name.
+2. Architecture(s)
+3. Status (deprecated, obsolete, active)
+4. Purpose
+
+1. KVM_HC_VAPIC_POLL_IRQ
+------------------------
+
+:Architecture: x86
+:Status: active
+:Purpose: Trigger guest exit so that the host can check for pending
+          interrupts on reentry.
+
+2. KVM_HC_MMU_OP
+----------------
+
+:Architecture: x86
+:Status: deprecated.
+:Purpose: Support MMU operations such as writing to PTE,
+          flushing TLB, release PT.
+
+3. KVM_HC_FEATURES
+------------------
+
+:Architecture: PPC
+:Status: active
+:Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid
+          used to enumerate which hypercalls are available. On PPC, either
+	  device tree based lookup ( which is also what EPAPR dictates)
+	  OR KVM specific enumeration mechanism (which is this hypercall)
+	  can be used.
+
+4. KVM_HC_PPC_MAP_MAGIC_PAGE
+----------------------------
+
+:Architecture: PPC
+:Status: active
+:Purpose: To enable communication between the hypervisor and guest there is a
+	  shared page that contains parts of supervisor visible register state.
+	  The guest can map this shared page to access its supervisor register
+	  through memory using this hypercall.
+
+5. KVM_HC_KICK_CPU
+------------------
+
+:Architecture: x86
+:Status: active
+:Purpose: Hypercall used to wakeup a vcpu from HLT state
+:Usage example:
+  A vcpu of a paravirtualized guest that is busywaiting in guest
+  kernel mode for an event to occur (ex: a spinlock to become available) can
+  execute HLT instruction once it has busy-waited for more than a threshold
+  time-interval. Execution of HLT instruction would cause the hypervisor to put
+  the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the
+  same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall,
+  specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0)
+  is used in the hypercall for future use.
+
+
+6. KVM_HC_CLOCK_PAIRING
+-----------------------
+:Architecture: x86
+:Status: active
+:Purpose: Hypercall used to synchronize host and guest clocks.
+
+Usage:
+
+a0: guest physical address where host copies
+"struct kvm_clock_offset" structure.
+
+a1: clock_type, ATM only KVM_CLOCK_PAIRING_WALLCLOCK (0)
+is supported (corresponding to the host's CLOCK_REALTIME clock).
+
+       ::
+
+		struct kvm_clock_pairing {
+			__s64 sec;
+			__s64 nsec;
+			__u64 tsc;
+			__u32 flags;
+			__u32 pad[9];
+		};
+
+       Where:
+               * sec: seconds from clock_type clock.
+               * nsec: nanoseconds from clock_type clock.
+               * tsc: guest TSC value used to calculate sec/nsec pair
+               * flags: flags, unused (0) at the moment.
+
+The hypercall lets a guest compute a precise timestamp across
+host and guest.  The guest can use the returned TSC value to
+compute the CLOCK_REALTIME for its clock, at the same instant.
+
+Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,
+or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.
+
+6. KVM_HC_SEND_IPI
+------------------
+
+:Architecture: x86
+:Status: active
+:Purpose: Send IPIs to multiple vCPUs.
+
+- a0: lower part of the bitmap of destination APIC IDs
+- a1: higher part of the bitmap of destination APIC IDs
+- a2: the lowest APIC ID in bitmap
+- a3: APIC ICR
+
+The hypercall lets a guest send multicast IPIs, with at most 128
+128 destinations per hypercall in 64-bit mode and 64 vCPUs per
+hypercall in 32-bit mode.  The destinations are represented by a
+bitmap contained in the first two arguments (a0 and a1). Bit 0 of
+a0 corresponds to the APIC ID in the third argument (a2), bit 1
+corresponds to the APIC ID a2+1, and so on.
+
+Returns the number of CPUs to which the IPIs were delivered successfully.
+
+7. KVM_HC_SCHED_YIELD
+---------------------
+
+:Architecture: x86
+:Status: active
+:Purpose: Hypercall used to yield if the IPI target vCPU is preempted
+
+a0: destination APIC ID
+
+:Usage example: When sending a call-function IPI-many to vCPUs, yield if
+	        any of the IPI target vCPUs was preempted.
diff --git a/Documentation/virt/kvm/hypercalls.txt b/Documentation/virt/kvm/hypercalls.txt
deleted file mode 100644
index 5f6d291..0000000
--- a/Documentation/virt/kvm/hypercalls.txt
+++ /dev/null
@@ -1,154 +0,0 @@
-Linux KVM Hypercall:
-===================
-X86:
- KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall
- instruction. The hypervisor can replace it with instructions that are
- guaranteed to be supported.
-
- Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
- The hypercall number should be placed in rax and the return value will be
- placed in rax.  No other registers will be clobbered unless explicitly stated
- by the particular hypercall.
-
-S390:
-  R2-R7 are used for parameters 1-6. In addition, R1 is used for hypercall
-  number. The return value is written to R2.
-
-  S390 uses diagnose instruction as hypercall (0x500) along with hypercall
-  number in R1.
-
-  For further information on the S390 diagnose call as supported by KVM,
-  refer to Documentation/virt/kvm/s390-diag.txt.
-
- PowerPC:
-  It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
-  Return value is placed in R3.
-
-  KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
-  property inside the device tree's /hypervisor node.
-  For more information refer to Documentation/virt/kvm/ppc-pv.txt
-
-MIPS:
-  KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall
-  number in $2 (v0). Up to four arguments may be placed in $4-$7 (a0-a3) and
-  the return value is placed in $2 (v0).
-
-KVM Hypercalls Documentation
-===========================
-The template for each hypercall is:
-1. Hypercall name.
-2. Architecture(s)
-3. Status (deprecated, obsolete, active)
-4. Purpose
-
-1. KVM_HC_VAPIC_POLL_IRQ
-------------------------
-Architecture: x86
-Status: active
-Purpose: Trigger guest exit so that the host can check for pending
-interrupts on reentry.
-
-2. KVM_HC_MMU_OP
-------------------------
-Architecture: x86
-Status: deprecated.
-Purpose: Support MMU operations such as writing to PTE,
-flushing TLB, release PT.
-
-3. KVM_HC_FEATURES
-------------------------
-Architecture: PPC
-Status: active
-Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid
-used to enumerate which hypercalls are available. On PPC, either device tree
-based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration
-mechanism (which is this hypercall) can be used.
-
-4. KVM_HC_PPC_MAP_MAGIC_PAGE
-------------------------
-Architecture: PPC
-Status: active
-Purpose: To enable communication between the hypervisor and guest there is a
-shared page that contains parts of supervisor visible register state.
-The guest can map this shared page to access its supervisor register through
-memory using this hypercall.
-
-5. KVM_HC_KICK_CPU
-------------------------
-Architecture: x86
-Status: active
-Purpose: Hypercall used to wakeup a vcpu from HLT state
-Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest
-kernel mode for an event to occur (ex: a spinlock to become available) can
-execute HLT instruction once it has busy-waited for more than a threshold
-time-interval. Execution of HLT instruction would cause the hypervisor to put
-the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the
-same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall,
-specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0)
-is used in the hypercall for future use.
-
-
-6. KVM_HC_CLOCK_PAIRING
-------------------------
-Architecture: x86
-Status: active
-Purpose: Hypercall used to synchronize host and guest clocks.
-Usage:
-
-a0: guest physical address where host copies
-"struct kvm_clock_offset" structure.
-
-a1: clock_type, ATM only KVM_CLOCK_PAIRING_WALLCLOCK (0)
-is supported (corresponding to the host's CLOCK_REALTIME clock).
-
-		struct kvm_clock_pairing {
-			__s64 sec;
-			__s64 nsec;
-			__u64 tsc;
-			__u32 flags;
-			__u32 pad[9];
-		};
-
-       Where:
-               * sec: seconds from clock_type clock.
-               * nsec: nanoseconds from clock_type clock.
-               * tsc: guest TSC value used to calculate sec/nsec pair
-               * flags: flags, unused (0) at the moment.
-
-The hypercall lets a guest compute a precise timestamp across
-host and guest.  The guest can use the returned TSC value to
-compute the CLOCK_REALTIME for its clock, at the same instant.
-
-Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,
-or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.
-
-6. KVM_HC_SEND_IPI
-------------------------
-Architecture: x86
-Status: active
-Purpose: Send IPIs to multiple vCPUs.
-
-a0: lower part of the bitmap of destination APIC IDs
-a1: higher part of the bitmap of destination APIC IDs
-a2: the lowest APIC ID in bitmap
-a3: APIC ICR
-
-The hypercall lets a guest send multicast IPIs, with at most 128
-128 destinations per hypercall in 64-bit mode and 64 vCPUs per
-hypercall in 32-bit mode.  The destinations are represented by a
-bitmap contained in the first two arguments (a0 and a1). Bit 0 of
-a0 corresponds to the APIC ID in the third argument (a2), bit 1
-corresponds to the APIC ID a2+1, and so on.
-
-Returns the number of CPUs to which the IPIs were delivered successfully.
-
-7. KVM_HC_SCHED_YIELD
-------------------------
-Architecture: x86
-Status: active
-Purpose: Hypercall used to yield if the IPI target vCPU is preempted
-
-a0: destination APIC ID
-
-Usage example: When sending a call-function IPI-many to vCPUs, yield if
-any of the IPI target vCPUs was preempted.
diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst
index ada224a..774deae 100644
--- a/Documentation/virt/kvm/index.rst
+++ b/Documentation/virt/kvm/index.rst
@@ -7,6 +7,22 @@
 .. toctree::
    :maxdepth: 2
 
+   api
    amd-memory-encryption
    cpuid
+   halt-polling
+   hypercalls
+   locking
+   mmu
+   msr
+   nested-vmx
+   ppc-pv
+   s390-diag
+   timekeeping
    vcpu-requests
+
+   review-checklist
+
+   arm/index
+
+   devices/index
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
new file mode 100644
index 0000000..c02291b
--- /dev/null
+++ b/Documentation/virt/kvm/locking.rst
@@ -0,0 +1,243 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================
+KVM Lock Overview
+=================
+
+1. Acquisition Orders
+---------------------
+
+The acquisition orders for mutexes are as follows:
+
+- kvm->lock is taken outside vcpu->mutex
+
+- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
+
+- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
+  them together is quite rare.
+
+On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
+
+Everything else is a leaf: no other lock is taken inside the critical
+sections.
+
+2. Exception
+------------
+
+Fast page fault:
+
+Fast page fault is the fast path which fixes the guest page fault out of
+the mmu-lock on x86. Currently, the page fault can be fast in one of the
+following two cases:
+
+1. Access Tracking: The SPTE is not present, but it is marked for access
+   tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to
+   restore the saved R/X bits. This is described in more detail later below.
+
+2. Write-Protection: The SPTE is present and the fault is
+   caused by write-protect. That means we just need to change the W bit of
+   the spte.
+
+What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and
+SPTE_MMU_WRITEABLE bit on the spte:
+
+- SPTE_HOST_WRITEABLE means the gfn is writable on host.
+- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when
+  the gfn is writable on guest mmu and it is not write-protected by shadow
+  page write-protection.
+
+On fast page fault path, we will use cmpxchg to atomically set the spte W
+bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or
+restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This
+is safe because whenever changing these bits can be detected by cmpxchg.
+
+But we need carefully check these cases:
+
+1) The mapping from gfn to pfn
+
+The mapping from gfn to pfn may be changed since we can only ensure the pfn
+is not changed during cmpxchg. This is a ABA problem, for example, below case
+will happen:
+
++------------------------------------------------------------------------+
+| At the beginning::                                                     |
+|                                                                        |
+|	gpte = gfn1                                                      |
+|	gfn1 is mapped to pfn1 on host                                   |
+|	spte is the shadow page table entry corresponding with gpte and  |
+|	spte = pfn1                                                      |
++------------------------------------------------------------------------+
+| On fast page fault path:                                               |
++------------------------------------+-----------------------------------+
+| CPU 0:                             | CPU 1:                            |
++------------------------------------+-----------------------------------+
+| ::                                 |                                   |
+|                                    |                                   |
+|   old_spte = *spte;                |                                   |
++------------------------------------+-----------------------------------+
+|                                    | pfn1 is swapped out::             |
+|                                    |                                   |
+|                                    |    spte = 0;                      |
+|                                    |                                   |
+|                                    | pfn1 is re-alloced for gfn2.      |
+|                                    |                                   |
+|                                    | gpte is changed to point to       |
+|                                    | gfn2 by the guest::               |
+|                                    |                                   |
+|                                    |    spte = pfn1;                   |
++------------------------------------+-----------------------------------+
+| ::                                                                     |
+|                                                                        |
+|   if (cmpxchg(spte, old_spte, old_spte+W)                              |
+|	mark_page_dirty(vcpu->kvm, gfn1)                                 |
+|            OOPS!!!                                                     |
++------------------------------------------------------------------------+
+
+We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap.
+
+For direct sp, we can easily avoid it since the spte of direct sp is fixed
+to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic()
+to pin gfn to pfn, because after gfn_to_pfn_atomic():
+
+- We have held the refcount of pfn that means the pfn can not be freed and
+  be reused for another gfn.
+- The pfn is writable that means it can not be shared between different gfns
+  by KSM.
+
+Then, we can ensure the dirty bitmaps is correctly set for a gfn.
+
+Currently, to simplify the whole things, we disable fast page fault for
+indirect shadow page.
+
+2) Dirty bit tracking
+
+In the origin code, the spte can be fast updated (non-atomically) if the
+spte is read-only and the Accessed bit has already been set since the
+Accessed bit and Dirty bit can not be lost.
+
+But it is not true after fast page fault since the spte can be marked
+writable between reading spte and updating spte. Like below case:
+
++------------------------------------------------------------------------+
+| At the beginning::                                                     |
+|                                                                        |
+|	spte.W = 0                                                       |
+|	spte.Accessed = 1                                                |
++------------------------------------+-----------------------------------+
+| CPU 0:                             | CPU 1:                            |
++------------------------------------+-----------------------------------+
+| In mmu_spte_clear_track_bits()::   |                                   |
+|                                    |                                   |
+|  old_spte = *spte;                 |                                   |
+|                                    |                                   |
+|                                    |                                   |
+|  /* 'if' condition is satisfied. */|                                   |
+|  if (old_spte.Accessed == 1 &&     |                                   |
+|       old_spte.W == 0)             |                                   |
+|     spte = 0ull;                   |                                   |
++------------------------------------+-----------------------------------+
+|                                    | on fast page fault path::         |
+|                                    |                                   |
+|                                    |    spte.W = 1                     |
+|                                    |                                   |
+|                                    | memory write on the spte::        |
+|                                    |                                   |
+|                                    |    spte.Dirty = 1                 |
++------------------------------------+-----------------------------------+
+|  ::                                |                                   |
+|                                    |                                   |
+|   else                             |                                   |
+|     old_spte = xchg(spte, 0ull)    |                                   |
+|   if (old_spte.Accessed == 1)      |                                   |
+|     kvm_set_pfn_accessed(spte.pfn);|                                   |
+|   if (old_spte.Dirty == 1)         |                                   |
+|     kvm_set_pfn_dirty(spte.pfn);   |                                   |
+|     OOPS!!!                        |                                   |
++------------------------------------+-----------------------------------+
+
+The Dirty bit is lost in this case.
+
+In order to avoid this kind of issue, we always treat the spte as "volatile"
+if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means,
+the spte is always atomically updated in this case.
+
+3) flush tlbs due to spte updated
+
+If the spte is updated from writable to readonly, we should flush all TLBs,
+otherwise rmap_write_protect will find a read-only spte, even though the
+writable spte might be cached on a CPU's TLB.
+
+As mentioned before, the spte can be updated to writable out of mmu-lock on
+fast page fault path, in order to easily audit the path, we see if TLBs need
+be flushed caused by this reason in mmu_spte_update() since this is a common
+function to update spte (present -> present).
+
+Since the spte is "volatile" if it can be updated out of mmu-lock, we always
+atomically update the spte, the race caused by fast page fault can be avoided,
+See the comments in spte_has_volatile_bits() and mmu_spte_update().
+
+Lockless Access Tracking:
+
+This is used for Intel CPUs that are using EPT but do not support the EPT A/D
+bits. In this case, when the KVM MMU notifier is called to track accesses to a
+page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present
+by clearing the RWX bits in the PTE and storing the original R & X bits in
+some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the
+PTE (using the ignored bit 62). When the VM tries to access the page later on,
+a fault is generated and the fast page fault mechanism described above is used
+to atomically restore the PTE to a Present state. The W bit is not saved when
+the PTE is marked for access tracking and during restoration to the Present
+state, the W bit is set depending on whether or not it was a write access. If
+it wasn't, then the W bit will remain clear until a write access happens, at
+which time it will be set using the Dirty tracking mechanism described above.
+
+3. Reference
+------------
+
+:Name:		kvm_lock
+:Type:		mutex
+:Arch:		any
+:Protects:	- vm_list
+
+:Name:		kvm_count_lock
+:Type:		raw_spinlock_t
+:Arch:		any
+:Protects:	- hardware virtualization enable/disable
+:Comment:	'raw' because hardware enabling/disabling must be atomic /wrt
+		migration.
+
+:Name:		kvm_arch::tsc_write_lock
+:Type:		raw_spinlock
+:Arch:		x86
+:Protects:	- kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset}
+		- tsc offset in vmcb
+:Comment:	'raw' because updating the tsc offsets must not be preempted.
+
+:Name:		kvm->mmu_lock
+:Type:		spinlock_t
+:Arch:		any
+:Protects:	-shadow page/shadow tlb entry
+:Comment:	it is a spinlock since it is used in mmu notifier.
+
+:Name:		kvm->srcu
+:Type:		srcu lock
+:Arch:		any
+:Protects:	- kvm->memslots
+		- kvm->buses
+:Comment:	The srcu read lock must be held while accessing memslots (e.g.
+		when using gfn_to_* functions) and while accessing in-kernel
+		MMIO/PIO address->device structure mapping (kvm->buses).
+		The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu
+		if it is needed by multiple functions.
+
+:Name:		blocked_vcpu_on_cpu_lock
+:Type:		spinlock_t
+:Arch:		x86
+:Protects:	blocked_vcpu_on_cpu
+:Comment:	This is a per-CPU lock and it is used for VT-d posted-interrupts.
+		When VT-d posted-interrupts is supported and the VM has assigned
+		devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu
+		protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues
+		wakeup notification event since external interrupts from the
+		assigned devices happens, we will find the vCPU on the list to
+		wakeup.
diff --git a/Documentation/virt/kvm/locking.txt b/Documentation/virt/kvm/locking.txt
deleted file mode 100644
index 635cd6e..0000000
--- a/Documentation/virt/kvm/locking.txt
+++ /dev/null
@@ -1,215 +0,0 @@
-KVM Lock Overview
-=================
-
-1. Acquisition Orders
----------------------
-
-The acquisition orders for mutexes are as follows:
-
-- kvm->lock is taken outside vcpu->mutex
-
-- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
-
-- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
-  them together is quite rare.
-
-On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
-
-Everything else is a leaf: no other lock is taken inside the critical
-sections.
-
-2: Exception
-------------
-
-Fast page fault:
-
-Fast page fault is the fast path which fixes the guest page fault out of
-the mmu-lock on x86. Currently, the page fault can be fast in one of the
-following two cases:
-
-1. Access Tracking: The SPTE is not present, but it is marked for access
-tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to
-restore the saved R/X bits. This is described in more detail later below.
-
-2. Write-Protection: The SPTE is present and the fault is
-caused by write-protect. That means we just need to change the W bit of the 
-spte.
-
-What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and
-SPTE_MMU_WRITEABLE bit on the spte:
-- SPTE_HOST_WRITEABLE means the gfn is writable on host.
-- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when
-  the gfn is writable on guest mmu and it is not write-protected by shadow
-  page write-protection.
-
-On fast page fault path, we will use cmpxchg to atomically set the spte W
-bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or 
-restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This
-is safe because whenever changing these bits can be detected by cmpxchg.
-
-But we need carefully check these cases:
-1): The mapping from gfn to pfn
-The mapping from gfn to pfn may be changed since we can only ensure the pfn
-is not changed during cmpxchg. This is a ABA problem, for example, below case
-will happen:
-
-At the beginning:
-gpte = gfn1
-gfn1 is mapped to pfn1 on host
-spte is the shadow page table entry corresponding with gpte and
-spte = pfn1
-
-   VCPU 0                           VCPU0
-on fast page fault path:
-
-   old_spte = *spte;
-                                 pfn1 is swapped out:
-                                    spte = 0;
-
-                                 pfn1 is re-alloced for gfn2.
-
-                                 gpte is changed to point to
-                                 gfn2 by the guest:
-                                    spte = pfn1;
-
-   if (cmpxchg(spte, old_spte, old_spte+W)
-	mark_page_dirty(vcpu->kvm, gfn1)
-             OOPS!!!
-
-We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap.
-
-For direct sp, we can easily avoid it since the spte of direct sp is fixed
-to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic()
-to pin gfn to pfn, because after gfn_to_pfn_atomic():
-- We have held the refcount of pfn that means the pfn can not be freed and
-  be reused for another gfn.
-- The pfn is writable that means it can not be shared between different gfns
-  by KSM.
-
-Then, we can ensure the dirty bitmaps is correctly set for a gfn.
-
-Currently, to simplify the whole things, we disable fast page fault for
-indirect shadow page.
-
-2): Dirty bit tracking
-In the origin code, the spte can be fast updated (non-atomically) if the
-spte is read-only and the Accessed bit has already been set since the
-Accessed bit and Dirty bit can not be lost.
-
-But it is not true after fast page fault since the spte can be marked
-writable between reading spte and updating spte. Like below case:
-
-At the beginning:
-spte.W = 0
-spte.Accessed = 1
-
-   VCPU 0                                       VCPU0
-In mmu_spte_clear_track_bits():
-
-   old_spte = *spte;
-
-   /* 'if' condition is satisfied. */
-   if (old_spte.Accessed == 1 &&
-        old_spte.W == 0)
-      spte = 0ull;
-                                         on fast page fault path:
-                                             spte.W = 1
-                                         memory write on the spte:
-                                             spte.Dirty = 1
-
-
-   else
-      old_spte = xchg(spte, 0ull)
-
-
-   if (old_spte.Accessed == 1)
-      kvm_set_pfn_accessed(spte.pfn);
-   if (old_spte.Dirty == 1)
-      kvm_set_pfn_dirty(spte.pfn);
-      OOPS!!!
-
-The Dirty bit is lost in this case.
-
-In order to avoid this kind of issue, we always treat the spte as "volatile"
-if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means,
-the spte is always atomically updated in this case.
-
-3): flush tlbs due to spte updated
-If the spte is updated from writable to readonly, we should flush all TLBs,
-otherwise rmap_write_protect will find a read-only spte, even though the
-writable spte might be cached on a CPU's TLB.
-
-As mentioned before, the spte can be updated to writable out of mmu-lock on
-fast page fault path, in order to easily audit the path, we see if TLBs need
-be flushed caused by this reason in mmu_spte_update() since this is a common
-function to update spte (present -> present).
-
-Since the spte is "volatile" if it can be updated out of mmu-lock, we always
-atomically update the spte, the race caused by fast page fault can be avoided,
-See the comments in spte_has_volatile_bits() and mmu_spte_update().
-
-Lockless Access Tracking:
-
-This is used for Intel CPUs that are using EPT but do not support the EPT A/D
-bits. In this case, when the KVM MMU notifier is called to track accesses to a
-page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present
-by clearing the RWX bits in the PTE and storing the original R & X bits in
-some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the
-PTE (using the ignored bit 62). When the VM tries to access the page later on,
-a fault is generated and the fast page fault mechanism described above is used
-to atomically restore the PTE to a Present state. The W bit is not saved when
-the PTE is marked for access tracking and during restoration to the Present
-state, the W bit is set depending on whether or not it was a write access. If
-it wasn't, then the W bit will remain clear until a write access happens, at 
-which time it will be set using the Dirty tracking mechanism described above.
-
-3. Reference
-------------
-
-Name:		kvm_lock
-Type:		mutex
-Arch:		any
-Protects:	- vm_list
-
-Name:		kvm_count_lock
-Type:		raw_spinlock_t
-Arch:		any
-Protects:	- hardware virtualization enable/disable
-Comment:	'raw' because hardware enabling/disabling must be atomic /wrt
-		migration.
-
-Name:		kvm_arch::tsc_write_lock
-Type:		raw_spinlock
-Arch:		x86
-Protects:	- kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset}
-		- tsc offset in vmcb
-Comment:	'raw' because updating the tsc offsets must not be preempted.
-
-Name:		kvm->mmu_lock
-Type:		spinlock_t
-Arch:		any
-Protects:	-shadow page/shadow tlb entry
-Comment:	it is a spinlock since it is used in mmu notifier.
-
-Name:		kvm->srcu
-Type:		srcu lock
-Arch:		any
-Protects:	- kvm->memslots
-		- kvm->buses
-Comment:	The srcu read lock must be held while accessing memslots (e.g.
-		when using gfn_to_* functions) and while accessing in-kernel
-		MMIO/PIO address->device structure mapping (kvm->buses).
-		The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu
-		if it is needed by multiple functions.
-
-Name:		blocked_vcpu_on_cpu_lock
-Type:		spinlock_t
-Arch:		x86
-Protects:	blocked_vcpu_on_cpu
-Comment:	This is a per-CPU lock and it is used for VT-d posted-interrupts.
-		When VT-d posted-interrupts is supported and the VM has assigned
-		devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu
-		protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues
-		wakeup notification event since external interrupts from the
-		assigned devices happens, we will find the vCPU on the list to
-		wakeup.
diff --git a/Documentation/virt/kvm/mmu.txt b/Documentation/virt/kvm/mmu.rst
similarity index 94%
rename from Documentation/virt/kvm/mmu.txt
rename to Documentation/virt/kvm/mmu.rst
index dadb29e..6098188 100644
--- a/Documentation/virt/kvm/mmu.txt
+++ b/Documentation/virt/kvm/mmu.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
 The x86 kvm shadow mmu
 ======================
 
@@ -7,27 +10,37 @@
 
 The mmu code attempts to satisfy the following requirements:
 
-- correctness: the guest should not be able to determine that it is running
+- correctness:
+	       the guest should not be able to determine that it is running
                on an emulated mmu except for timing (we attempt to comply
                with the specification, not emulate the characteristics of
                a particular implementation such as tlb size)
-- security:    the guest must not be able to touch host memory not assigned
+- security:
+	       the guest must not be able to touch host memory not assigned
                to it
-- performance: minimize the performance penalty imposed by the mmu
-- scaling:     need to scale to large memory and large vcpu guests
-- hardware:    support the full range of x86 virtualization hardware
-- integration: Linux memory management code must be in control of guest memory
+- performance:
+               minimize the performance penalty imposed by the mmu
+- scaling:
+               need to scale to large memory and large vcpu guests
+- hardware:
+               support the full range of x86 virtualization hardware
+- integration:
+               Linux memory management code must be in control of guest memory
                so that swapping, page migration, page merging, transparent
                hugepages, and similar features work without change
-- dirty tracking: report writes to guest memory to enable live migration
+- dirty tracking:
+               report writes to guest memory to enable live migration
                and framebuffer-based displays
-- footprint:   keep the amount of pinned kernel memory low (most memory
+- footprint:
+               keep the amount of pinned kernel memory low (most memory
                should be shrinkable)
-- reliability:  avoid multipage or GFP_ATOMIC allocations
+- reliability:
+               avoid multipage or GFP_ATOMIC allocations
 
 Acronyms
 ========
 
+====  ====================================================================
 pfn   host page frame number
 hpa   host physical address
 hva   host virtual address
@@ -41,6 +54,7 @@
 gpte  guest pte (referring to gfns)
 spte  shadow pte (referring to pfns)
 tdp   two dimensional paging (vendor neutral term for NPT and EPT)
+====  ====================================================================
 
 Virtual and real hardware supported
 ===================================
@@ -90,11 +104,13 @@
 The mmu is driven by events, some from the guest, some from the host.
 
 Guest generated events:
+
 - writes to control registers (especially cr3)
 - invlpg/invlpga instruction execution
 - access to missing or protected translations
 
 Host generated events:
+
 - changes in the gpa->hpa translation (either through gpa->hva changes or
   through hva->hpa changes)
 - memory pressure (the shrinker)
@@ -117,16 +133,19 @@
 The following table shows translations encoded by leaf ptes, with higher-level
 translations in parentheses:
 
- Non-nested guests:
+ Non-nested guests::
+
   nonpaging:     gpa->hpa
   paging:        gva->gpa->hpa
   paging, tdp:   (gva->)gpa->hpa
- Nested guests:
+
+ Nested guests::
+
   non-tdp:       ngva->gpa->hpa  (*)
   tdp:           (ngva->)ngpa->gpa->hpa
 
-(*) the guest hypervisor will encode the ngva->gpa translation into its page
-    tables if npt is not present
+  (*) the guest hypervisor will encode the ngva->gpa translation into its page
+      tables if npt is not present
 
 Shadow pages contain the following information:
   role.level:
@@ -291,28 +310,41 @@
 
  - if the RSV bit of the error code is set, the page fault is caused by guest
    accessing MMIO and cached MMIO information is available.
+
    - walk shadow page table
    - check for valid generation number in the spte (see "Fast invalidation of
      MMIO sptes" below)
    - cache the information to vcpu->arch.mmio_gva, vcpu->arch.mmio_access and
      vcpu->arch.mmio_gfn, and call the emulator
+
  - If both P bit and R/W bit of error code are set, this could possibly
    be handled as a "fast page fault" (fixed without taking the MMU lock).  See
    the description in Documentation/virt/kvm/locking.txt.
+
  - if needed, walk the guest page tables to determine the guest translation
    (gva->gpa or ngpa->gpa)
+
    - if permissions are insufficient, reflect the fault back to the guest
+
  - determine the host page
+
    - if this is an mmio request, there is no host page; cache the info to
      vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn
+
  - walk the shadow page table to find the spte for the translation,
    instantiating missing intermediate page tables as necessary
+
    - If this is an mmio request, cache the mmio info to the spte and set some
      reserved bit on the spte (see callers of kvm_mmu_set_mmio_spte_mask)
+
  - try to unsynchronize the page
+
    - if successful, we can let the guest continue and modify the gpte
+
  - emulate the instruction
+
    - if failed, unshadow the page and let the guest continue
+
  - update any translations that were modified by the instruction
 
 invlpg handling:
@@ -324,10 +356,12 @@
 Guest control register updates:
 
 - mov to cr3
+
   - look up new shadow roots
   - synchronize newly reachable shadow pages
 
 - mov to cr0/cr4/efer
+
   - set up mmu context for new paging mode
   - look up new shadow roots
   - synchronize newly reachable shadow pages
@@ -358,6 +392,7 @@
 (user write faults generate a #PF)
 
 In the first case there are two additional complications:
+
 - if CR4.SMEP is enabled: since we've turned the page into a kernel page,
   the kernel may now execute it.  We handle this by also setting spte.nx.
   If we get a user fetch or read fault, we'll change spte.u=1 and
@@ -446,4 +481,3 @@
 
 - NPT presentation from KVM Forum 2008
   http://www.linux-kvm.org/images/c/c8/KvmForum2008%24kdf2008_21.pdf
-
diff --git a/Documentation/virt/kvm/msr.txt b/Documentation/virt/kvm/msr.rst
similarity index 74%
rename from Documentation/virt/kvm/msr.txt
rename to Documentation/virt/kvm/msr.rst
index df1f433..3389203 100644
--- a/Documentation/virt/kvm/msr.txt
+++ b/Documentation/virt/kvm/msr.rst
@@ -1,6 +1,10 @@
-KVM-specific MSRs.
-Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
-=====================================================
+.. SPDX-License-Identifier: GPL-2.0
+
+=================
+KVM-specific MSRs
+=================
+
+:Author: Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
 
 KVM makes use of some custom MSRs to service some requests.
 
@@ -9,34 +13,39 @@
 but they are deprecated and their use is discouraged.
 
 Custom MSR list
---------
+---------------
 
 The current supported Custom MSR list is:
 
-MSR_KVM_WALL_CLOCK_NEW:   0x4b564d00
+MSR_KVM_WALL_CLOCK_NEW:
+	0x4b564d00
 
-	data: 4-byte alignment physical address of a memory area which must be
+data:
+	4-byte alignment physical address of a memory area which must be
 	in guest RAM. This memory is expected to hold a copy of the following
-	structure:
+	structure::
 
-	struct pvclock_wall_clock {
+	 struct pvclock_wall_clock {
 		u32   version;
 		u32   sec;
 		u32   nsec;
-	} __attribute__((__packed__));
+	  } __attribute__((__packed__));
 
 	whose data will be filled in by the hypervisor. The hypervisor is only
 	guaranteed to update this data at the moment of MSR write.
 	Users that want to reliably query this information more than once have
 	to write more than once to this MSR. Fields have the following meanings:
 
-		version: guest has to check version before and after grabbing
+	version:
+		guest has to check version before and after grabbing
 		time information and check that they are both equal and even.
 		An odd version indicates an in-progress update.
 
-		sec: number of seconds for wallclock at time of boot.
+	sec:
+		 number of seconds for wallclock at time of boot.
 
-		nsec: number of nanoseconds for wallclock at time of boot.
+	nsec:
+		 number of nanoseconds for wallclock at time of boot.
 
 	In order to get the current wallclock time, the system_time from
 	MSR_KVM_SYSTEM_TIME_NEW needs to be added.
@@ -47,13 +56,15 @@
 	Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
 	leaf prior to usage.
 
-MSR_KVM_SYSTEM_TIME_NEW:  0x4b564d01
+MSR_KVM_SYSTEM_TIME_NEW:
+	0x4b564d01
 
-	data: 4-byte aligned physical address of a memory area which must be in
+data:
+	4-byte aligned physical address of a memory area which must be in
 	guest RAM, plus an enable bit in bit 0. This memory is expected to hold
-	a copy of the following structure:
+	a copy of the following structure::
 
-	struct pvclock_vcpu_time_info {
+	  struct pvclock_vcpu_time_info {
 		u32   version;
 		u32   pad0;
 		u64   tsc_timestamp;
@@ -62,7 +73,7 @@
 		s8    tsc_shift;
 		u8    flags;
 		u8    pad[2];
-	} __attribute__((__packed__)); /* 32 bytes */
+	  } __attribute__((__packed__)); /* 32 bytes */
 
 	whose data will be filled in by the hypervisor periodically. Only one
 	write, or registration, is needed for each VCPU. The interval between
@@ -72,23 +83,28 @@
 
 	Fields have the following meanings:
 
-		version: guest has to check version before and after grabbing
+	version:
+		guest has to check version before and after grabbing
 		time information and check that they are both equal and even.
 		An odd version indicates an in-progress update.
 
-		tsc_timestamp: the tsc value at the current VCPU at the time
+	tsc_timestamp:
+		the tsc value at the current VCPU at the time
 		of the update of this structure. Guests can subtract this value
 		from current tsc to derive a notion of elapsed time since the
 		structure update.
 
-		system_time: a host notion of monotonic time, including sleep
+	system_time:
+		a host notion of monotonic time, including sleep
 		time at the time this structure was last updated. Unit is
 		nanoseconds.
 
-		tsc_to_system_mul: multiplier to be used when converting
+	tsc_to_system_mul:
+		multiplier to be used when converting
 		tsc-related quantity to nanoseconds
 
-		tsc_shift: shift to be used when converting tsc-related
+	tsc_shift:
+		shift to be used when converting tsc-related
 		quantity to nanoseconds. This shift will ensure that
 		multiplication with tsc_to_system_mul does not overflow.
 		A positive value denotes a left shift, a negative value
@@ -96,7 +112,7 @@
 
 		The conversion from tsc to nanoseconds involves an additional
 		right shift by 32 bits. With this information, guests can
-		derive per-CPU time by doing:
+		derive per-CPU time by doing::
 
 			time = (current_tsc - tsc_timestamp)
 			if (tsc_shift >= 0)
@@ -106,29 +122,34 @@
 			time = (time * tsc_to_system_mul) >> 32
 			time = time + system_time
 
-		flags: bits in this field indicate extended capabilities
+	flags:
+		bits in this field indicate extended capabilities
 		coordinated between the guest and the hypervisor. Availability
 		of specific flags has to be checked in 0x40000001 cpuid leaf.
 		Current flags are:
 
-		 flag bit   | cpuid bit    | meaning
-		-------------------------------------------------------------
-			    |	           | time measures taken across
-		     0      |	   24      | multiple cpus are guaranteed to
-			    |		   | be monotonic
-		-------------------------------------------------------------
-			    |		   | guest vcpu has been paused by
-		     1	    |	  N/A	   | the host
-			    |		   | See 4.70 in api.txt
-		-------------------------------------------------------------
+
+		+-----------+--------------+----------------------------------+
+		| flag bit  | cpuid bit    | meaning			      |
+		+-----------+--------------+----------------------------------+
+		|	    |		   | time measures taken across       |
+		|    0      |	   24      | multiple cpus are guaranteed to  |
+		|	    |		   | be monotonic		      |
+		+-----------+--------------+----------------------------------+
+		|	    |		   | guest vcpu has been paused by    |
+		|    1	    |	  N/A	   | the host			      |
+		|	    |		   | See 4.70 in api.txt	      |
+		+-----------+--------------+----------------------------------+
 
 	Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
 	leaf prior to usage.
 
 
-MSR_KVM_WALL_CLOCK:  0x11
+MSR_KVM_WALL_CLOCK:
+	0x11
 
-	data and functioning: same as MSR_KVM_WALL_CLOCK_NEW. Use that instead.
+data and functioning:
+	same as MSR_KVM_WALL_CLOCK_NEW. Use that instead.
 
 	This MSR falls outside the reserved KVM range and may be removed in the
 	future. Its usage is deprecated.
@@ -136,9 +157,11 @@
 	Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid
 	leaf prior to usage.
 
-MSR_KVM_SYSTEM_TIME: 0x12
+MSR_KVM_SYSTEM_TIME:
+	0x12
 
-	data and functioning: same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead.
+data and functioning:
+	same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead.
 
 	This MSR falls outside the reserved KVM range and may be removed in the
 	future. Its usage is deprecated.
@@ -146,7 +169,7 @@
 	Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid
 	leaf prior to usage.
 
-	The suggested algorithm for detecting kvmclock presence is then:
+	The suggested algorithm for detecting kvmclock presence is then::
 
 		if (!kvm_para_available())    /* refer to cpuid.txt */
 			return NON_PRESENT;
@@ -163,8 +186,11 @@
 		} else
 			return NON_PRESENT;
 
-MSR_KVM_ASYNC_PF_EN: 0x4b564d02
-	data: Bits 63-6 hold 64-byte aligned physical address of a
+MSR_KVM_ASYNC_PF_EN:
+	0x4b564d02
+
+data:
+	Bits 63-6 hold 64-byte aligned physical address of a
 	64 byte memory area which must be in guest RAM and must be
 	zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
 	when asynchronous page faults are enabled on the vcpu 0 when
@@ -200,20 +226,22 @@
 	Currently type 2 APF will be always delivered on the same vcpu as
 	type 1 was, but guest should not rely on that.
 
-MSR_KVM_STEAL_TIME: 0x4b564d03
+MSR_KVM_STEAL_TIME:
+	0x4b564d03
 
-	data: 64-byte alignment physical address of a memory area which must be
+data:
+	64-byte alignment physical address of a memory area which must be
 	in guest RAM, plus an enable bit in bit 0. This memory is expected to
-	hold a copy of the following structure:
+	hold a copy of the following structure::
 
-	struct kvm_steal_time {
+	  struct kvm_steal_time {
 		__u64 steal;
 		__u32 version;
 		__u32 flags;
 		__u8  preempted;
 		__u8  u8_pad[3];
 		__u32 pad[11];
-	}
+	  }
 
 	whose data will be filled in by the hypervisor periodically. Only one
 	write, or registration, is needed for each VCPU. The interval between
@@ -224,25 +252,32 @@
 
 	Fields have the following meanings:
 
-		version: a sequence counter. In other words, guest has to check
+	version:
+		a sequence counter. In other words, guest has to check
 		this field before and after grabbing time information and make
 		sure they are both equal and even. An odd version indicates an
 		in-progress update.
 
-		flags: At this point, always zero. May be used to indicate
+	flags:
+		At this point, always zero. May be used to indicate
 		changes in this structure in the future.
 
-		steal: the amount of time in which this vCPU did not run, in
+	steal:
+		the amount of time in which this vCPU did not run, in
 		nanoseconds. Time during which the vcpu is idle, will not be
 		reported as steal time.
 
-		preempted: indicate the vCPU who owns this struct is running or
+	preempted:
+		indicate the vCPU who owns this struct is running or
 		not. Non-zero values mean the vCPU has been preempted. Zero
 		means the vCPU is not preempted. NOTE, it is always zero if the
 		the hypervisor doesn't support this field.
 
-MSR_KVM_EOI_EN: 0x4b564d04
-	data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0
+MSR_KVM_EOI_EN:
+	0x4b564d04
+
+data:
+	Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0
 	when disabled.  Bit 1 is reserved and must be zero.  When PV end of
 	interrupt is enabled (bit 0 set), bits 63-2 hold a 4-byte aligned
 	physical address of a 4 byte memory area which must be in guest RAM and
@@ -274,11 +309,13 @@
 	clear it using a single CPU instruction, such as test and clear, or
 	compare and exchange.
 
-MSR_KVM_POLL_CONTROL: 0x4b564d05
+MSR_KVM_POLL_CONTROL:
+	0x4b564d05
+
 	Control host-side polling.
 
-	data: Bit 0 enables (1) or disables (0) host-side HLT polling logic.
+data:
+	Bit 0 enables (1) or disables (0) host-side HLT polling logic.
 
 	KVM guests can request the host not to poll on HLT, for example if
 	they are performing polling themselves.
-
diff --git a/Documentation/virt/kvm/nested-vmx.txt b/Documentation/virt/kvm/nested-vmx.rst
similarity index 89%
rename from Documentation/virt/kvm/nested-vmx.txt
rename to Documentation/virt/kvm/nested-vmx.rst
index 97eb135..592b0ab 100644
--- a/Documentation/virt/kvm/nested-vmx.txt
+++ b/Documentation/virt/kvm/nested-vmx.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========
 Nested VMX
 ==========
 
@@ -41,9 +44,9 @@
 emulated CPU type (qemu64) does not list the "VMX" CPU feature, so it must be
 explicitly enabled, by giving qemu one of the following options:
 
-     -cpu host              (emulated CPU has all features of the real CPU)
+     - cpu host              (emulated CPU has all features of the real CPU)
 
-     -cpu qemu64,+vmx       (add just the vmx feature to a named CPU type)
+     - cpu qemu64,+vmx       (add just the vmx feature to a named CPU type)
 
 
 ABIs
@@ -75,6 +78,8 @@
 VMCS12_REVISION (from vmx.c) should be changed if struct vmcs12 or its inner
 struct shadow_vmcs is ever changed.
 
+::
+
 	typedef u64 natural_width;
 	struct __packed vmcs12 {
 		/* According to the Intel spec, a VMCS region must start with
@@ -220,21 +225,21 @@
 -------
 
 These patches were written by:
-     Abel Gordon, abelg <at> il.ibm.com
-     Nadav Har'El, nyh <at> il.ibm.com
-     Orit Wasserman, oritw <at> il.ibm.com
-     Ben-Ami Yassor, benami <at> il.ibm.com
-     Muli Ben-Yehuda, muli <at> il.ibm.com
+    - Abel Gordon, abelg <at> il.ibm.com
+    - Nadav Har'El, nyh <at> il.ibm.com
+    - Orit Wasserman, oritw <at> il.ibm.com
+    - Ben-Ami Yassor, benami <at> il.ibm.com
+    - Muli Ben-Yehuda, muli <at> il.ibm.com
 
 With contributions by:
-     Anthony Liguori, aliguori <at> us.ibm.com
-     Mike Day, mdday <at> us.ibm.com
-     Michael Factor, factor <at> il.ibm.com
-     Zvi Dubitzky, dubi <at> il.ibm.com
+    - Anthony Liguori, aliguori <at> us.ibm.com
+    - Mike Day, mdday <at> us.ibm.com
+    - Michael Factor, factor <at> il.ibm.com
+    - Zvi Dubitzky, dubi <at> il.ibm.com
 
 And valuable reviews by:
-     Avi Kivity, avi <at> redhat.com
-     Gleb Natapov, gleb <at> redhat.com
-     Marcelo Tosatti, mtosatti <at> redhat.com
-     Kevin Tian, kevin.tian <at> intel.com
-     and others.
+    - Avi Kivity, avi <at> redhat.com
+    - Gleb Natapov, gleb <at> redhat.com
+    - Marcelo Tosatti, mtosatti <at> redhat.com
+    - Kevin Tian, kevin.tian <at> intel.com
+    - and others.
diff --git a/Documentation/virt/kvm/ppc-pv.txt b/Documentation/virt/kvm/ppc-pv.rst
similarity index 90%
rename from Documentation/virt/kvm/ppc-pv.txt
rename to Documentation/virt/kvm/ppc-pv.rst
index e26115c..5fdb907 100644
--- a/Documentation/virt/kvm/ppc-pv.txt
+++ b/Documentation/virt/kvm/ppc-pv.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================
 The PPC KVM paravirtual interface
 =================================
 
@@ -34,8 +37,9 @@
 
 The parameters are as follows:
 
+        ========	================	================
 	Register	IN			OUT
-
+        ========	================	================
 	r0		-			volatile
 	r3		1st parameter		Return code
 	r4		2nd parameter		1st output value
@@ -47,6 +51,7 @@
 	r10		8th parameter		7th output value
 	r11		hypercall number	8th output value
 	r12		-			volatile
+        ========	================	================
 
 Hypercall definitions are shared in generic code, so the same hypercall numbers
 apply for x86 and powerpc alike with the exception that each KVM hypercall
@@ -54,11 +59,13 @@
 
 Return codes can be as follows:
 
+	====		=========================
 	Code		Meaning
-
+	====		=========================
 	0		Success
 	12		Hypercall not implemented
 	<0		Error
+	====		=========================
 
 The magic page
 ==============
@@ -72,7 +79,7 @@
 MMU is enabled. The second parameter indicates the address in real mode, if
 applicable to the target. For now, we always map the page to -4096. This way we
 can access it using absolute load and store functions. The following
-instruction reads the first field of the magic page:
+instruction reads the first field of the magic page::
 
 	ld	rX, -4096(0)
 
@@ -93,8 +100,10 @@
 
 The following enhancements to the magic page are currently available:
 
+  ============================  =======================================
   KVM_MAGIC_FEAT_SR		Maps SR registers r/w in the magic page
   KVM_MAGIC_FEAT_MAS0_TO_SPRG7	Maps MASn, ESR, PIR and high SPRGs
+  ============================  =======================================
 
 For enhanced features in the magic page, please check for the existence of the
 feature before using them!
@@ -121,8 +130,8 @@
 
 The following bits are safe to be set inside the guest:
 
-  MSR_EE
-  MSR_RI
+  - MSR_EE
+  - MSR_RI
 
 If any other bit changes in the MSR, please still use mtmsr(d).
 
@@ -138,9 +147,9 @@
 also act on the shared page. So calling privileged instructions still works as
 before.
 
+======================= ================================
 From			To
-====			==
-
+======================= ================================
 mfmsr	rX		ld	rX, magic_page->msr
 mfsprg	rX, 0		ld	rX, magic_page->sprg0
 mfsprg	rX, 1		ld	rX, magic_page->sprg1
@@ -173,7 +182,7 @@
 
 [BookE only]
 wrteei	[0|1]		b	<special wrteei section>
-
+======================= ================================
 
 Some instructions require more logic to determine what's going on than a load
 or store instruction can deliver. To enable patching of those, we keep some
@@ -191,6 +200,7 @@
 
 Hypercall ABIs in KVM on PowerPC
 =================================
+
 1) KVM hypercalls (ePAPR)
 
 These are ePAPR compliant hypercall implementation (mentioned above). Even
diff --git a/Documentation/virt/kvm/review-checklist.txt b/Documentation/virt/kvm/review-checklist.rst
similarity index 95%
rename from Documentation/virt/kvm/review-checklist.txt
rename to Documentation/virt/kvm/review-checklist.rst
index 499af49..1f86a9d3 100644
--- a/Documentation/virt/kvm/review-checklist.txt
+++ b/Documentation/virt/kvm/review-checklist.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
 Review checklist for kvm patches
 ================================
 
diff --git a/Documentation/virt/kvm/s390-diag.txt b/Documentation/virt/kvm/s390-diag.rst
similarity index 89%
rename from Documentation/virt/kvm/s390-diag.txt
rename to Documentation/virt/kvm/s390-diag.rst
index 7c52e5f..eaac486 100644
--- a/Documentation/virt/kvm/s390-diag.txt
+++ b/Documentation/virt/kvm/s390-diag.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============================
 The s390 DIAGNOSE call on KVM
 =============================
 
@@ -16,12 +19,12 @@
 all supported DIAGNOSE calls need to be handled by either KVM or its
 userspace.
 
-All DIAGNOSE calls supported by KVM use the RS-a format:
+All DIAGNOSE calls supported by KVM use the RS-a format::
 
---------------------------------------
-|  '83'  | R1 | R3 | B2 |     D2     |
---------------------------------------
-0        8    12   16   20           31
+  --------------------------------------
+  |  '83'  | R1 | R3 | B2 |     D2     |
+  --------------------------------------
+  0        8    12   16   20           31
 
 The second-operand address (obtained by the base/displacement calculation)
 is not used to address data. Instead, bits 48-63 of this address specify
diff --git a/Documentation/virt/kvm/timekeeping.txt b/Documentation/virt/kvm/timekeeping.rst
similarity index 85%
rename from Documentation/virt/kvm/timekeeping.txt
rename to Documentation/virt/kvm/timekeeping.rst
index 76808a1..21ae7ef 100644
--- a/Documentation/virt/kvm/timekeeping.txt
+++ b/Documentation/virt/kvm/timekeeping.rst
@@ -1,17 +1,21 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-	Timekeeping Virtualization for X86-Based Architectures
+======================================================
+Timekeeping Virtualization for X86-Based Architectures
+======================================================
 
-	Zachary Amsden <zamsden@redhat.com>
-	Copyright (c) 2010, Red Hat.  All rights reserved.
+:Author: Zachary Amsden <zamsden@redhat.com>
+:Copyright: (c) 2010, Red Hat.  All rights reserved.
 
-1) Overview
-2) Timing Devices
-3) TSC Hardware
-4) Virtualization Problems
+.. Contents
 
-=========================================================================
+   1) Overview
+   2) Timing Devices
+   3) TSC Hardware
+   4) Virtualization Problems
 
-1) Overview
+1. Overview
+===========
 
 One of the most complicated parts of the X86 platform, and specifically,
 the virtualization of this platform is the plethora of timing devices available
@@ -27,15 +31,15 @@
 timekeeping which may be difficult to find elsewhere, specifically,
 information relevant to KVM and hardware-based virtualization.
 
-=========================================================================
-
-2) Timing Devices
+2. Timing Devices
+=================
 
 First we discuss the basic hardware devices available.  TSC and the related
 KVM clock are special enough to warrant a full exposition and are described in
 the following section.
 
-2.1) i8254 - PIT
+2.1. i8254 - PIT
+----------------
 
 One of the first timer devices available is the programmable interrupt timer,
 or PIT.  The PIT has a fixed frequency 1.193182 MHz base clock and three
@@ -50,13 +54,13 @@
 using single or multiple byte access to the I/O ports.  There are 6 modes
 available, but not all modes are available to all timers, as only timer 2
 has a connected gate input, required for modes 1 and 5.  The gate line is
-controlled by port 61h, bit 0, as illustrated in the following diagram.
+controlled by port 61h, bit 0, as illustrated in the following diagram::
 
- --------------             ----------------
-|              |           |                |
-|  1.1932 MHz  |---------->| CLOCK      OUT | ---------> IRQ 0
-|    Clock     |   |       |                |
- --------------    |    +->| GATE  TIMER 0  |
+  --------------             ----------------
+  |            |           |                |
+  |  1.1932 MHz|---------->| CLOCK      OUT | ---------> IRQ 0
+  |    Clock   |   |       |                |
+  --------------   |    +->| GATE  TIMER 0  |
                    |        ----------------
                    |
                    |        ----------------
@@ -70,29 +74,33 @@
                    |       |                |
                    |------>| CLOCK      OUT | ---------> Port 61h, bit 5
                            |                |      |
-Port 61h, bit 0 ---------->| GATE  TIMER 2  |       \_.----   ____
+  Port 61h, bit 0 -------->| GATE  TIMER 2  |       \_.----   ____
                             ----------------         _|    )--|LPF|---Speaker
                                                     / *----   \___/
-Port 61h, bit 1 -----------------------------------/
+  Port 61h, bit 1 ---------------------------------/
 
 The timer modes are now described.
 
-Mode 0: Single Timeout.   This is a one-shot software timeout that counts down
+Mode 0: Single Timeout.
+ This is a one-shot software timeout that counts down
  when the gate is high (always true for timers 0 and 1).  When the count
  reaches zero, the output goes high.
 
-Mode 1: Triggered One-shot.  The output is initially set high.  When the gate
+Mode 1: Triggered One-shot.
+ The output is initially set high.  When the gate
  line is set high, a countdown is initiated (which does not stop if the gate is
  lowered), during which the output is set low.  When the count reaches zero,
  the output goes high.
 
-Mode 2: Rate Generator.  The output is initially set high.  When the countdown
+Mode 2: Rate Generator.
+ The output is initially set high.  When the countdown
  reaches 1, the output goes low for one count and then returns high.  The value
  is reloaded and the countdown automatically resumes.  If the gate line goes
  low, the count is halted.  If the output is low when the gate is lowered, the
  output automatically goes high (this only affects timer 2).
 
-Mode 3: Square Wave.   This generates a high / low square wave.  The count
+Mode 3: Square Wave.
+ This generates a high / low square wave.  The count
  determines the length of the pulse, which alternates between high and low
  when zero is reached.  The count only proceeds when gate is high and is
  automatically reloaded on reaching zero.  The count is decremented twice at
@@ -103,12 +111,14 @@
  values are not observed when reading.  This is the intended mode for timer 2,
  which generates sine-like tones by low-pass filtering the square wave output.
 
-Mode 4: Software Strobe.  After programming this mode and loading the counter,
+Mode 4: Software Strobe.
+ After programming this mode and loading the counter,
  the output remains high until the counter reaches zero.  Then the output
  goes low for 1 clock cycle and returns high.  The counter is not reloaded.
  Counting only occurs when gate is high.
 
-Mode 5: Hardware Strobe.  After programming and loading the counter, the
+Mode 5: Hardware Strobe.
+ After programming and loading the counter, the
  output remains high.  When the gate is raised, a countdown is initiated
  (which does not stop if the gate is lowered).  When the counter reaches zero,
  the output goes low for 1 clock cycle and then returns high.  The counter is
@@ -118,49 +128,49 @@
 command port, 0x43 is used to set the counter and mode for each of the three
 timers.
 
-PIT commands, issued to port 0x43, using the following bit encoding:
+PIT commands, issued to port 0x43, using the following bit encoding::
 
-Bit 7-4: Command (See table below)
-Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined)
-Bit 0  : Binary (0) / BCD (1)
+  Bit 7-4: Command (See table below)
+  Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined)
+  Bit 0  : Binary (0) / BCD (1)
 
-Command table:
+Command table::
 
-0000 - Latch Timer 0 count for port 0x40
+  0000 - Latch Timer 0 count for port 0x40
 	sample and hold the count to be read in port 0x40;
 	additional commands ignored until counter is read;
 	mode bits ignored.
 
-0001 - Set Timer 0 LSB mode for port 0x40
+  0001 - Set Timer 0 LSB mode for port 0x40
 	set timer to read LSB only and force MSB to zero;
 	mode bits set timer mode
 
-0010 - Set Timer 0 MSB mode for port 0x40
+  0010 - Set Timer 0 MSB mode for port 0x40
 	set timer to read MSB only and force LSB to zero;
 	mode bits set timer mode
 
-0011 - Set Timer 0 16-bit mode for port 0x40
+  0011 - Set Timer 0 16-bit mode for port 0x40
 	set timer to read / write LSB first, then MSB;
 	mode bits set timer mode
 
-0100 - Latch Timer 1 count for port 0x41 - as described above
-0101 - Set Timer 1 LSB mode for port 0x41 - as described above
-0110 - Set Timer 1 MSB mode for port 0x41 - as described above
-0111 - Set Timer 1 16-bit mode for port 0x41 - as described above
+  0100 - Latch Timer 1 count for port 0x41 - as described above
+  0101 - Set Timer 1 LSB mode for port 0x41 - as described above
+  0110 - Set Timer 1 MSB mode for port 0x41 - as described above
+  0111 - Set Timer 1 16-bit mode for port 0x41 - as described above
 
-1000 - Latch Timer 2 count for port 0x42 - as described above
-1001 - Set Timer 2 LSB mode for port 0x42 - as described above
-1010 - Set Timer 2 MSB mode for port 0x42 - as described above
-1011 - Set Timer 2 16-bit mode for port 0x42 as described above
+  1000 - Latch Timer 2 count for port 0x42 - as described above
+  1001 - Set Timer 2 LSB mode for port 0x42 - as described above
+  1010 - Set Timer 2 MSB mode for port 0x42 - as described above
+  1011 - Set Timer 2 16-bit mode for port 0x42 as described above
 
-1101 - General counter latch
+  1101 - General counter latch
 	Latch combination of counters into corresponding ports
 	Bit 3 = Counter 2
 	Bit 2 = Counter 1
 	Bit 1 = Counter 0
 	Bit 0 = Unused
 
-1110 - Latch timer status
+  1110 - Latch timer status
 	Latch combination of counter mode into corresponding ports
 	Bit 3 = Counter 2
 	Bit 2 = Counter 1
@@ -177,7 +187,8 @@
 	Bit 3-1 = Mode
 	Bit 0 = Binary (0) / BCD mode (1)
 
-2.2) RTC
+2.2. RTC
+--------
 
 The second device which was available in the original PC was the MC146818 real
 time clock.  The original device is now obsolete, and usually emulated by the
@@ -201,21 +212,21 @@
 The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be
 programmed to a 32kHz divider if the RTC is to count seconds.
 
-This is the RAM map originally used for the RTC/CMOS:
+This is the RAM map originally used for the RTC/CMOS::
 
-Location    Size    Description
-------------------------------------------
-00h         byte    Current second (BCD)
-01h         byte    Seconds alarm (BCD)
-02h         byte    Current minute (BCD)
-03h         byte    Minutes alarm (BCD)
-04h         byte    Current hour (BCD)
-05h         byte    Hours alarm (BCD)
-06h         byte    Current day of week (BCD)
-07h         byte    Current day of month (BCD)
-08h         byte    Current month (BCD)
-09h         byte    Current year (BCD)
-0Ah         byte    Register A
+  Location    Size    Description
+  ------------------------------------------
+  00h         byte    Current second (BCD)
+  01h         byte    Seconds alarm (BCD)
+  02h         byte    Current minute (BCD)
+  03h         byte    Minutes alarm (BCD)
+  04h         byte    Current hour (BCD)
+  05h         byte    Hours alarm (BCD)
+  06h         byte    Current day of week (BCD)
+  07h         byte    Current day of month (BCD)
+  08h         byte    Current month (BCD)
+  09h         byte    Current year (BCD)
+  0Ah         byte    Register A
                        bit 7   = Update in progress
                        bit 6-4 = Divider for clock
                                   000 = 4.194 MHz
@@ -234,7 +245,7 @@
                                  1101 = 125 mS
                                  1110 = 250 mS
                                  1111 = 500 mS
-0Bh         byte    Register B
+  0Bh         byte    Register B
                        bit 7   = Run (0) / Halt (1)
                        bit 6   = Periodic interrupt enable
                        bit 5   = Alarm interrupt enable
@@ -243,19 +254,20 @@
                        bit 2   = BCD calendar (0) / Binary (1)
                        bit 1   = 12-hour mode (0) / 24-hour mode (1)
                        bit 0   = 0 (DST off) / 1 (DST enabled)
-OCh         byte    Register C (read only)
+  OCh         byte    Register C (read only)
                        bit 7   = interrupt request flag (IRQF)
                        bit 6   = periodic interrupt flag (PF)
                        bit 5   = alarm interrupt flag (AF)
                        bit 4   = update interrupt flag (UF)
                        bit 3-0 = reserved
-ODh         byte    Register D (read only)
+  ODh         byte    Register D (read only)
                        bit 7   = RTC has power
                        bit 6-0 = reserved
-32h         byte    Current century BCD (*)
+  32h         byte    Current century BCD (*)
   (*) location vendor specific and now determined from ACPI global tables
 
-2.3) APIC
+2.3. APIC
+---------
 
 On Pentium and later processors, an on-board timer is available to each CPU
 as part of the Advanced Programmable Interrupt Controller.  The APIC is
@@ -276,7 +288,8 @@
 of one-shot or periodic operation, and is based on the bus clock divided down
 by the programmable divider register.
 
-2.4) HPET
+2.4. HPET
+---------
 
 HPET is quite complex, and was originally intended to replace the PIT / RTC
 support of the X86 PC.  It remains to be seen whether that will be the case, as
@@ -297,7 +310,8 @@
 Detailed specification of the HPET is beyond the current scope of this
 document, as it is also very well documented elsewhere.
 
-2.5) Offboard Timers
+2.5. Offboard Timers
+--------------------
 
 Several cards, both proprietary (watchdog boards) and commonplace (e1000) have
 timing chips built into the cards which may have registers which are accessible
@@ -307,9 +321,8 @@
 timer device would require additional support to be virtualized properly and is
 not considered important at this time as no known operating system does this.
 
-=========================================================================
-
-3) TSC Hardware
+3. TSC Hardware
+===============
 
 The TSC or time stamp counter is relatively simple in theory; it counts
 instruction cycles issued by the processor, which can be used as a measure of
@@ -340,7 +353,8 @@
 promise to allow the TSC to additionally be scaled, but this hardware is not
 yet widely available.
 
-3.1) TSC synchronization
+3.1. TSC synchronization
+------------------------
 
 The TSC is a CPU-local clock in most implementations.  This means, on SMP
 platforms, the TSCs of different CPUs may start at different times depending
@@ -357,7 +371,8 @@
 values are read from the same clock, which generally only is possible on single
 socket systems or those with special hardware support.
 
-3.2) TSC and CPU hotplug
+3.2. TSC and CPU hotplug
+------------------------
 
 As touched on already, CPUs which arrive later than the boot time of the system
 may not have a TSC value that is synchronized with the rest of the system.
@@ -367,7 +382,8 @@
 TSC is synchronized back to a state where TSC synchronization flaws, however
 small, may be exposed to the OS and any virtualization environment.
 
-3.3) TSC and multi-socket / NUMA
+3.3. TSC and multi-socket / NUMA
+--------------------------------
 
 Multi-socket systems, especially large multi-socket systems are likely to have
 individual clocksources rather than a single, universally distributed clock.
@@ -385,7 +401,8 @@
 It is recommended not to trust the TSCs to remain synchronized on NUMA or
 multiple socket systems for these reasons.
 
-3.4) TSC and C-states
+3.4. TSC and C-states
+---------------------
 
 C-states, or idling states of the processor, especially C1E and deeper sleep
 states may be problematic for TSC as well.  The TSC may stop advancing in such
@@ -396,7 +413,8 @@
 The TSC in such a case may be corrected by catching it up to a known external
 clocksource.
 
-3.5) TSC frequency change / P-states
+3.5. TSC frequency change / P-states
+------------------------------------
 
 To make things slightly more interesting, some CPUs may change frequency.  They
 may or may not run the TSC at the same rate, and because the frequency change
@@ -416,14 +434,16 @@
 than that of non-halted processors.  AMD Turion processors are known to have
 this problem.
 
-3.6) TSC and STPCLK / T-states
+3.6. TSC and STPCLK / T-states
+------------------------------
 
 External signals given to the processor may also have the effect of stopping
 the TSC.  This is typically done for thermal emergency power control to prevent
 an overheating condition, and typically, there is no way to detect that this
 condition has happened.
 
-3.7) TSC virtualization - VMX
+3.7. TSC virtualization - VMX
+-----------------------------
 
 VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
 instructions, which is enough for full virtualization of TSC in any manner.  In
@@ -431,14 +451,16 @@
 field specified in the VMCS.  Special instructions must be used to read and
 write the VMCS field.
 
-3.8) TSC virtualization - SVM
+3.8. TSC virtualization - SVM
+-----------------------------
 
 SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
 instructions, which is enough for full virtualization of TSC in any manner.  In
 addition, SVM allows passing through the host TSC plus an additional offset
 field specified in the SVM control block.
 
-3.9) TSC feature bits in Linux
+3.9. TSC feature bits in Linux
+------------------------------
 
 In summary, there is no way to guarantee the TSC remains in perfect
 synchronization unless it is explicitly guaranteed by the architecture.  Even
@@ -448,13 +470,16 @@
 The following feature bits are used by Linux to signal various TSC attributes,
 but they can only be taken to be meaningful for UP or single node systems.
 
-X86_FEATURE_TSC 		: The TSC is available in hardware
-X86_FEATURE_RDTSCP		: The RDTSCP instruction is available
-X86_FEATURE_CONSTANT_TSC 	: The TSC rate is unchanged with P-states
-X86_FEATURE_NONSTOP_TSC		: The TSC does not stop in C-states
-X86_FEATURE_TSC_RELIABLE	: TSC sync checks are skipped (VMware)
+=========================	=======================================
+X86_FEATURE_TSC			The TSC is available in hardware
+X86_FEATURE_RDTSCP		The RDTSCP instruction is available
+X86_FEATURE_CONSTANT_TSC	The TSC rate is unchanged with P-states
+X86_FEATURE_NONSTOP_TSC		The TSC does not stop in C-states
+X86_FEATURE_TSC_RELIABLE	TSC sync checks are skipped (VMware)
+=========================	=======================================
 
-4) Virtualization Problems
+4. Virtualization Problems
+==========================
 
 Timekeeping is especially problematic for virtualization because a number of
 challenges arise.  The most obvious problem is that time is now shared between
@@ -473,7 +498,8 @@
 cause similar problems to virtualization makes it a good justification for
 solving many of these problems on bare metal.
 
-4.1) Interrupt clocking
+4.1. Interrupt clocking
+-----------------------
 
 One of the most immediate problems that occurs with legacy operating systems
 is that the system timekeeping routines are often designed to keep track of
@@ -502,7 +528,8 @@
 rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in
 practice.
 
-4.2) TSC sampling and serialization
+4.2. TSC sampling and serialization
+-----------------------------------
 
 As the highest precision time source available, the cycle counter of the CPU
 has aroused much interest from developers.  As explained above, this timer has
@@ -524,7 +551,8 @@
 the TSC as seen from other CPUs, even in an otherwise perfectly synchronized
 system.
 
-4.3) Timespec aliasing
+4.3. Timespec aliasing
+----------------------
 
 Additionally, this lack of serialization from the TSC poses another challenge
 when using results of the TSC when measured against another time source.  As
@@ -548,7 +576,8 @@
 and any other values derived from TSC computation (such as TSC virtualization
 itself).
 
-4.4) Migration
+4.4. Migration
+--------------
 
 Migration of a virtual machine raises problems for timekeeping in two ways.
 First, the migration itself may take time, during which interrupts cannot be
@@ -566,7 +595,8 @@
 simply storing multipliers and offsets against the TSC for the guest to convert
 back into nanosecond resolution values.
 
-4.5) Scheduling
+4.5. Scheduling
+---------------
 
 Since scheduling may be based on precise timing and firing of interrupts, the
 scheduling algorithms of an operating system may be adversely affected by
@@ -579,7 +609,8 @@
 paravirtualized scheduler clock, which reveals the true amount of CPU time for
 which a virtual machine has been running.
 
-4.6) Watchdogs
+4.6. Watchdogs
+--------------
 
 Watchdog timers, such as the lock detector in Linux may fire accidentally when
 running under hardware virtualization due to timer interrupts being delayed or
@@ -587,7 +618,8 @@
 spurious and can be ignored, but in some circumstances it may be necessary to
 disable such detection.
 
-4.7) Delays and precision timing
+4.7. Delays and precision timing
+--------------------------------
 
 Precise timing and delays may not be possible in a virtualized system.  This
 can happen if the system is controlling physical hardware, or issues delays to
@@ -600,7 +632,8 @@
 significant issue.  In many cases these delays may be eliminated through
 configuration or paravirtualization.
 
-4.8) Covert channels and leaks
+4.8. Covert channels and leaks
+------------------------------
 
 In addition to the above problems, time information will inevitably leak to the
 guest about the host in anything but a perfect implementation of virtualized
diff --git a/Documentation/virt/uml/UserModeLinux-HOWTO.txt b/Documentation/virt/uml/user_mode_linux.rst
similarity index 74%
rename from Documentation/virt/uml/UserModeLinux-HOWTO.txt
rename to Documentation/virt/uml/user_mode_linux.rst
index 87b80f5..de0f0b2 100644
--- a/Documentation/virt/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virt/uml/user_mode_linux.rst
@@ -1,12 +1,17 @@
-  User Mode Linux HOWTO
-  User Mode Linux Core Team
-  Mon Nov 18 14:16:16 EST 2002
+.. SPDX-License-Identifier: GPL-2.0
 
-  This document describes the use and abuse of Jeff Dike's User Mode
-  Linux: a port of the Linux kernel as a normal Intel Linux process.
-  ______________________________________________________________________
+=====================
+User Mode Linux HOWTO
+=====================
 
-  Table of Contents
+:Author:  User Mode Linux Core Team
+:Last-updated: Sat Jan 25 16:07:55 CET 2020
+
+This document describes the use and abuse of Jeff Dike's User Mode
+Linux: a port of the Linux kernel as a normal Intel Linux process.
+
+
+.. Table of Contents
 
   1. Introduction
 
@@ -132,19 +137,19 @@
      15.5 Other contributions
 
 
-  ______________________________________________________________________
-
-  1.  Introduction
+1.  Introduction
+================
 
   Welcome to User Mode Linux.  It's going to be fun.
 
 
 
-  1.1.  How is User Mode Linux Different?
+1.1.  How is User Mode Linux Different?
+---------------------------------------
 
   Normally, the Linux Kernel talks straight to your hardware (video
   card, keyboard, hard drives, etc), and any programs which run ask the
-  kernel to operate the hardware, like so:
+  kernel to operate the hardware, like so::
 
 
 
@@ -160,10 +165,10 @@
 
 
   The User Mode Linux Kernel is different; instead of talking to the
-  hardware, it talks to a `real' Linux kernel (called the `host kernel'
+  hardware, it talks to a `real` Linux kernel (called the `host kernel`
   from now on), like any other program.  Programs can then run inside
   User-Mode Linux as if they were running under a normal kernel, like
-  so:
+  so::
 
 
 
@@ -181,7 +186,8 @@
 
 
 
-  1.2.  Why Would I Want User Mode Linux?
+1.2.  Why Would I Want User Mode Linux?
+---------------------------------------
 
 
   1. If User Mode Linux crashes, your host kernel is still fine.
@@ -204,83 +210,41 @@
 
 
 
+.. _Compiling_the_kernel_and_modules:
 
-
-  2.  Compiling the kernel and modules
+2.  Compiling the kernel and modules
+====================================
 
 
 
 
-  2.1.  Compiling the kernel
+2.1.  Compiling the kernel
+--------------------------
 
 
   Compiling the user mode kernel is just like compiling any other
-  kernel.  Let's go through the steps, using 2.4.0-prerelease (current
-  as of this writing) as an example:
+  kernel.
 
 
-  1. Download the latest UML patch from
-
-     the download page <http://user-mode-linux.sourceforge.net/
-
-     In this example, the file is uml-patch-2.4.0-prerelease.bz2.
-
-
-  2. Download the matching kernel from your favourite kernel mirror,
+  1. Download the latest kernel from your favourite kernel mirror,
      such as:
 
-     ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2
-     <ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2>
-     .
+     https://mirrors.edge.kernel.org/pub/linux/kernel/v5.x/linux-5.4.14.tar.xz
 
-
-  3. Make a directory and unpack the kernel into it.
-
-
+  2. Make a directory and unpack the kernel into it::
 
        host%
        mkdir ~/uml
 
-
-
-
-
-
        host%
        cd ~/uml
 
-
-
-
-
-
        host%
-       tar -xzvf linux-2.4.0-prerelease.tar.bz2
+       tar xvf linux-5.4.14.tar.xz
 
 
-
-
-
-
-  4. Apply the patch using
-
-
-
-       host%
-       cd ~/uml/linux
-
-
-
-       host%
-       bzcat uml-patch-2.4.0-prerelease.bz2 | patch -p1
-
-
-
-
-
-
-  5. Run your favorite config; `make xconfig ARCH=um' is the most
-     convenient.  `make config ARCH=um' and 'make menuconfig ARCH=um'
+  3. Run your favorite config; ``make xconfig ARCH=um`` is the most
+     convenient.  ``make config ARCH=um`` and ``make menuconfig ARCH=um``
      will work as well.  The defaults will give you a useful kernel.  If
      you want to change something, go ahead, it probably won't hurt
      anything.
@@ -288,44 +252,20 @@
 
      Note:  If the host is configured with a 2G/2G address space split
      rather than the usual 3G/1G split, then the packaged UML binaries
-     will not run.  They will immediately segfault.  See ``UML on 2G/2G
-     hosts''  for the scoop on running UML on your system.
+     will not run.  They will immediately segfault.  See
+     :ref:`UML_on_2G/2G_hosts`  for the scoop on running UML on your system.
 
 
 
-  6. Finish with `make linux ARCH=um': the result is a file called
-     `linux' in the top directory of your source tree.
-
-  Make sure that you don't build this kernel in /usr/src/linux.  On some
-  distributions, /usr/include/asm is a link into this pool.  The user-
-  mode build changes the other end of that link, and things that include
-  <asm/anything.h> stop compiling.
-
-  The sources are also available from cvs at the project's cvs page,
-  which has directions on getting the sources. You can also browse the
-  CVS pool from there.
-
-  If you get the CVS sources, you will have to check them out into an
-  empty directory. You will then have to copy each file into the
-  corresponding directory in the appropriate kernel pool.
-
-  If you don't have the latest kernel pool, you can get the
-  corresponding user-mode sources with
+  4. Finish with ``make linux ARCH=um``: the result is a file called
+     ``linux`` in the top directory of your source tree.
 
 
-       host% cvs co -r v_2_3_x linux
-
-
-
-
-  where 'x' is the version in your pool. Note that you will not get the
-  bug fixes and enhancements that have gone into subsequent releases.
-
-
-  2.2.  Compiling and installing kernel modules
+2.2.  Compiling and installing kernel modules
+---------------------------------------------
 
   UML modules are built in the same way as the native kernel (with the
-  exception of the 'ARCH=um' that you always need for UML):
+  exception of the 'ARCH=um' that you always need for UML)::
 
 
        host% make modules ARCH=um
@@ -337,12 +277,12 @@
   the user-mode pool.  Modules from the native kernel won't work.
 
   You can install them by using ftp or something to copy them into the
-  virtual machine and dropping them into /lib/modules/`uname -r`.
+  virtual machine and dropping them into ``/lib/modules/$(uname -r)``.
 
   You can also get the kernel build process to install them as follows:
 
   1. with the kernel not booted, mount the root filesystem in the top
-     level of the kernel pool:
+     level of the kernel pool::
 
 
        host% mount root_fs mnt -o loop
@@ -352,7 +292,7 @@
 
 
 
-  2. run
+  2. run::
 
 
        host%
@@ -363,7 +303,7 @@
 
 
 
-  3. unmount the filesystem
+  3. unmount the filesystem::
 
 
        host% umount mnt
@@ -381,27 +321,28 @@
   as modules, especially filesystems and network protocols and filters,
   so most symbols which need to be exported probably already are.
   However, if you do find symbols that need exporting, let  us
-  <http://user-mode-linux.sourceforge.net/>  know, and
+  know at http://user-mode-linux.sourceforge.net/, and
   they'll be "taken care of".
 
 
 
-  2.3.  Compiling and installing uml_utilities
+2.3.  Compiling and installing uml_utilities
+--------------------------------------------
 
   Many features of the UML kernel require a user-space helper program,
   so a uml_utilities package is distributed separately from the kernel
   patch which provides these helpers. Included within this is:
 
-  o  port-helper - Used by consoles which connect to xterms or ports
+  -  port-helper - Used by consoles which connect to xterms or ports
 
-  o  tunctl - Configuration tool to create and delete tap devices
+  -  tunctl - Configuration tool to create and delete tap devices
 
-  o  uml_net - Setuid binary for automatic tap device configuration
+  -  uml_net - Setuid binary for automatic tap device configuration
 
-  o  uml_switch - User-space virtual switch required for daemon
+  -  uml_switch - User-space virtual switch required for daemon
      transport
 
-     The uml_utilities tree is compiled with:
+     The uml_utilities tree is compiled with::
 
 
        host#
@@ -423,38 +364,42 @@
 
 
 
-  3.  Running UML and logging in
+3.  Running UML and logging in
+==============================
 
 
 
-  3.1.  Running UML
+3.1.  Running UML
+-----------------
 
-  It runs on 2.2.15 or later, and all 2.4 kernels.
+  It runs on 2.2.15 or later, and all kernel versions since 2.4.
 
 
   Booting UML is straightforward.  Simply run 'linux': it will try to
-  mount the file `root_fs' in the current directory.  You do not need to
-  run it as root.  If your root filesystem is not named `root_fs', then
-  you need to put a `ubd0=root_fs_whatever' switch on the linux command
+  mount the file ``root_fs`` in the current directory.  You do not need to
+  run it as root.  If your root filesystem is not named ``root_fs``, then
+  you need to put a ``ubd0=root_fs_whatever`` switch on the linux command
   line.
 
 
   You will need a filesystem to boot UML from.  There are a number
-  available for download from  here  <http://user-mode-
-  linux.sourceforge.net/> .  There are also  several tools
-  <http://user-mode-linux.sourceforge.net/>  which can be
+  available for download from http://user-mode-linux.sourceforge.net.
+  There are also  several tools at
+  http://user-mode-linux.sourceforge.net/  which can be
   used to generate UML-compatible filesystem images from media.
   The kernel will boot up and present you with a login prompt.
 
 
-  Note:  If the host is configured with a 2G/2G address space split
+Note:
+  If the host is configured with a 2G/2G address space split
   rather than the usual 3G/1G split, then the packaged UML binaries will
-  not run.  They will immediately segfault.  See ``UML on 2G/2G hosts''
+  not run.  They will immediately segfault.  See :ref:`UML_on_2G/2G_hosts`
   for the scoop on running UML on your system.
 
 
 
-  3.2.  Logging in
+3.2.  Logging in
+----------------
 
 
 
@@ -468,22 +413,22 @@
 
   There are a couple of other ways to log in:
 
-  o  On a virtual console
+  -  On a virtual console
 
 
 
      Each virtual console that is configured (i.e. the device exists in
      /dev and /etc/inittab runs a getty on it) will come up in its own
-     xterm.  If you get tired of the xterms, read ``Setting up serial
-     lines and consoles''  to see how to attach the consoles to
-     something else, like host ptys.
+     xterm.  If you get tired of the xterms, read
+     :ref:`setting_up_serial_lines_and_consoles` to see how to attach
+     the consoles to something else, like host ptys.
 
 
 
-  o  Over the serial line
+  -  Over the serial line
 
 
-     In the boot output, find a line that looks like:
+     In the boot output, find a line that looks like::
 
 
 
@@ -493,7 +438,7 @@
 
 
   Attach your favorite terminal program to the corresponding tty.  I.e.
-  for minicom, the command would be
+  for minicom, the command would be::
 
 
        host% minicom -o -p /dev/ttyp1
@@ -503,37 +448,40 @@
 
 
 
-  o  Over the net
+  -  Over the net
 
 
      If the network is running, then you can telnet to the virtual
-     machine and log in to it.  See ``Setting up the network''  to learn
+     machine and log in to it.  See :ref:`Setting_up_the_network`  to learn
      about setting up a virtual network.
 
   When you're done using it, run halt, and the kernel will bring itself
   down and the process will exit.
 
 
-  3.3.  Examples
+3.3.  Examples
+--------------
 
   Here are some examples of UML in action:
 
-  o  A login session <http://user-mode-linux.sourceforge.net/login.html>
+  -  A login session http://user-mode-linux.sourceforge.net/old/login.html
 
-  o  A virtual network <http://user-mode-linux.sourceforge.net/net.html>
+  -  A virtual network http://user-mode-linux.sourceforge.net/old/net.html
 
 
 
 
 
+.. _UML_on_2G/2G_hosts:
 
-
-  4.  UML on 2G/2G hosts
+4.  UML on 2G/2G hosts
+======================
 
 
 
 
-  4.1.  Introduction
+4.1.  Introduction
+------------------
 
 
   Most Linux machines are configured so that the kernel occupies the
@@ -546,7 +494,8 @@
 
 
 
-  4.2.  The problem
+4.2.  The problem
+-----------------
 
 
   The prebuilt UML binaries on this site will not run on 2G/2G hosts
@@ -558,13 +507,14 @@
 
 
 
-  4.3.  The solution
+4.3.  The solution
+------------------
 
 
   The fix for this is to rebuild UML from source after enabling
   CONFIG_HOST_2G_2G (under 'General Setup').  This will cause UML to
   load itself in the top .5G of that smaller process address space,
-  where it will run fine.  See ``Compiling the kernel and modules''  if
+  where it will run fine.  See :ref:`Compiling_the_kernel_and_modules`  if
   you need help building UML from source.
 
 
@@ -573,10 +523,11 @@
 
 
 
+.. _setting_up_serial_lines_and_consoles:
 
 
-
-  5.  Setting up serial lines and consoles
+5.  Setting up serial lines and consoles
+========================================
 
 
   It is possible to attach UML serial lines and consoles to many types
@@ -584,22 +535,23 @@
 
 
   You can attach them to host ptys, ttys, file descriptors, and ports.
-  This allows you to do things like
+  This allows you to do things like:
 
-  o  have a UML console appear on an unused host console,
+  -  have a UML console appear on an unused host console,
 
-  o  hook two virtual machines together by having one attach to a pty
+  -  hook two virtual machines together by having one attach to a pty
      and having the other attach to the corresponding tty
 
-  o  make a virtual machine accessible from the net by attaching a
+  -  make a virtual machine accessible from the net by attaching a
      console to a port on the host.
 
 
-  The general format of the command line option is device=channel.
+  The general format of the command line option is ``device=channel``.
 
 
 
-  5.1.  Specifying the device
+5.1.  Specifying the device
+---------------------------
 
   Devices are specified with "con" or "ssl" (console or serial line,
   respectively), optionally with a device number if you are talking
@@ -613,7 +565,7 @@
 
   A specific device name will override a less general "con=" or "ssl=".
   So, for example, you can assign a pty to each of the serial lines
-  except for the first two like this:
+  except for the first two like this::
 
 
         ssl=pty ssl0=tty:/dev/tty0 ssl1=tty:/dev/tty1
@@ -626,13 +578,14 @@
 
 
 
-  5.2.  Specifying the channel
+5.2.  Specifying the channel
+----------------------------
 
   There are a number of different types of channels to attach a UML
   device to, each with a different way of specifying exactly what to
   attach to.
 
-  o  pseudo-terminals - device=pty pts terminals - device=pts
+  -  pseudo-terminals - device=pty pts terminals - device=pts
 
 
      This will cause UML to allocate a free host pseudo-terminal for the
@@ -640,23 +593,23 @@
      log.  You access it by attaching a terminal program to the
      corresponding tty:
 
-  o  screen /dev/pts/n
+  -  screen /dev/pts/n
 
-  o  screen /dev/ttyxx
+  -  screen /dev/ttyxx
 
-  o  minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
+  -  minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
      devices
 
-  o  kermit - start it up, 'open' the device, then 'connect'
+  -  kermit - start it up, 'open' the device, then 'connect'
 
 
 
 
 
-  o  terminals - device=tty:tty device file
+  -  terminals - device=tty:tty device file
 
 
-     This will make UML attach the device to the specified tty (i.e
+     This will make UML attach the device to the specified tty (i.e::
 
 
         con1=tty:/dev/tty3
@@ -672,7 +625,7 @@
 
 
 
-  o  xterms - device=xterm
+  -  xterms - device=xterm
 
 
      UML will run an xterm and the device will be attached to it.
@@ -681,12 +634,12 @@
 
 
 
-  o  Port - device=port:port number
+  -  Port - device=port:port number
 
 
      This will attach the UML devices to the specified host port.
      Attaching console 1 to the host's port 9000 would be done like
-     this:
+     this::
 
 
         con1=port:9000
@@ -694,7 +647,7 @@
 
 
 
-  Attaching all the serial lines to that port would be done similarly:
+  Attaching all the serial lines to that port would be done similarly::
 
 
         ssl=port:9000
@@ -702,8 +655,8 @@
 
 
 
-  You access these devices by telnetting to that port.  Each active tel-
-  net session gets a different device.  If there are more telnets to a
+  You access these devices by telnetting to that port.  Each active
+  telnet session gets a different device.  If there are more telnets to a
   port than UML devices attached to it, then the extra telnet sessions
   will block until an existing telnet detaches, or until another device
   becomes active (i.e. by being activated in /etc/inittab).
@@ -725,13 +678,13 @@
 
 
 
-  o  already-existing file descriptors - device=file descriptor
+  -  already-existing file descriptors - device=file descriptor
 
 
      If you set up a file descriptor on the UML command line, you can
      attach a UML device to it.  This is most commonly used to put the
      main console back on stdin and stdout after assigning all the other
-     consoles to something else:
+     consoles to something else::
 
 
         con0=fd:0,fd:1 con=pts
@@ -743,7 +696,7 @@
 
 
 
-  o  Nothing - device=null
+  -  Nothing - device=null
 
 
      This allows the device to be opened, in contrast to 'none', but
@@ -754,7 +707,7 @@
 
 
 
-  o  None - device=none
+  -  None - device=none
 
 
      This causes the device to disappear.
@@ -762,7 +715,7 @@
 
 
   You can also specify different input and output channels for a device
-  by putting a comma between them:
+  by putting a comma between them::
 
 
         ssl3=tty:/dev/tty2,xterm
@@ -785,14 +738,15 @@
 
 
 
-  5.3.  Examples
+5.3.  Examples
+--------------
 
   There are a number of interesting things you can do with this
   capability.
 
 
   First, this is how you get rid of those bleeding console xterms by
-  attaching them to host ptys:
+  attaching them to host ptys::
 
 
         con=pty con0=fd:0,fd:1
@@ -802,7 +756,7 @@
 
   This will make a UML console take over an unused host virtual console,
   so that when you switch to it, you will see the UML login prompt
-  rather than the host login prompt:
+  rather than the host login prompt::
 
 
         con1=tty:/dev/tty6
@@ -813,7 +767,7 @@
   You can attach two virtual machines together with what amounts to a
   serial line as follows:
 
-  Run one UML with a serial line attached to a pty -
+  Run one UML with a serial line attached to a pty::
 
 
         ssl1=pty
@@ -825,7 +779,7 @@
   that it got /dev/ptyp1).
 
   Boot the other UML with a serial line attached to the corresponding
-  tty -
+  tty::
 
 
         ssl1=tty:/dev/ttyp1
@@ -838,7 +792,10 @@
   prompt of the other virtual machine.
 
 
-  6.  Setting up the network
+.. _setting_up_the_network:
+
+6.  Setting up the network
+==========================
 
 
 
@@ -858,19 +815,19 @@
   There are currently five transport types available for a UML virtual
   machine to exchange packets with other hosts:
 
-  o  ethertap
+  -  ethertap
 
-  o  TUN/TAP
+  -  TUN/TAP
 
-  o  Multicast
+  -  Multicast
 
-  o  a switch daemon
+  -  a switch daemon
 
-  o  slip
+  -  slip
 
-  o  slirp
+  -  slirp
 
-  o  pcap
+  -  pcap
 
      The TUN/TAP, ethertap, slip, and slirp transports allow a UML
      instance to exchange packets with the host.  They may be directed
@@ -893,28 +850,28 @@
   With so many host transports, which one should you use?  Here's when
   you should use each one:
 
-  o  ethertap - if you want access to the host networking and it is
+  -  ethertap - if you want access to the host networking and it is
      running 2.2
 
-  o  TUN/TAP - if you want access to the host networking and it is
+  -  TUN/TAP - if you want access to the host networking and it is
      running 2.4.  Also, the TUN/TAP transport is able to use a
      preconfigured device, allowing it to avoid using the setuid uml_net
      helper, which is a security advantage.
 
-  o  Multicast - if you want a purely virtual network and you don't want
+  -  Multicast - if you want a purely virtual network and you don't want
      to set up anything but the UML
 
-  o  a switch daemon - if you want a purely virtual network and you
+  -  a switch daemon - if you want a purely virtual network and you
      don't mind running the daemon in order to get somewhat better
      performance
 
-  o  slip - there is no particular reason to run the slip backend unless
+  -  slip - there is no particular reason to run the slip backend unless
      ethertap and TUN/TAP are just not available for some reason
 
-  o  slirp - if you don't have root access on the host to setup
+  -  slirp - if you don't have root access on the host to setup
      networking, or if you don't want to allocate an IP to your UML
 
-  o  pcap - not much use for actual network connectivity, but great for
+  -  pcap - not much use for actual network connectivity, but great for
      monitoring traffic on the host
 
      Ethertap is available on 2.4 and works fine.  TUN/TAP is preferred
@@ -926,7 +883,8 @@
      exploit the helper's root privileges.
 
 
-  6.1.  General setup
+6.1.  General setup
+-------------------
 
   First, you must have the virtual network enabled in your UML.  If are
   running a prebuilt kernel from this site, everything is already
@@ -938,7 +896,7 @@
   The next step is to provide a network device to the virtual machine.
   This is done by describing it on the kernel command line.
 
-  The general format is
+  The general format is::
 
 
        eth <n> = <transport> , <transport args>
@@ -947,7 +905,7 @@
 
 
   For example, a virtual ethernet device may be attached to a host
-  ethertap device as follows:
+  ethertap device as follows::
 
 
        eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254
@@ -978,7 +936,7 @@
 
 
   You can also add devices to a UML and remove them at runtime.  See the
-  ``The Management Console''  page for details.
+  :ref:`The_Management_Console`  page for details.
 
 
   The sections below describe this in more detail.
@@ -995,7 +953,8 @@
 
 
 
-  6.2.  Userspace daemons
+6.2.  Userspace daemons
+-----------------------
 
   You will likely need the setuid helper, or the switch daemon, or both.
   They are both installed with the RPM and deb, so if you've installed
@@ -1011,7 +970,8 @@
 
 
 
-  6.3.  Specifying ethernet addresses
+6.3.  Specifying ethernet addresses
+-----------------------------------
 
   Below, you will see that the TUN/TAP, ethertap, and daemon interfaces
   allow you to specify hardware addresses for the virtual ethernet
@@ -1023,21 +983,21 @@
   sufficient to guarantee a unique hardware address for the device.  A
   couple of exceptions are:
 
-  o  Another set of virtual ethernet devices are on the same network and
+  -  Another set of virtual ethernet devices are on the same network and
      they are assigned hardware addresses using a different scheme which
      may conflict with the UML IP address-based scheme
 
-  o  You aren't going to use the device for IP networking, so you don't
+  -  You aren't going to use the device for IP networking, so you don't
      assign the device an IP address
 
      If you let the driver provide the hardware address, you should make
      sure that the device IP address is known before the interface is
-     brought up.  So, inside UML, this will guarantee that:
+     brought up.  So, inside UML, this will guarantee that::
 
 
 
-  UML#
-  ifconfig eth0 192.168.0.250 up
+	  UML#
+	  ifconfig eth0 192.168.0.250 up
 
 
 
@@ -1049,13 +1009,14 @@
 
 
 
-  6.4.  UML interface setup
+6.4.  UML interface setup
+-------------------------
 
   Once the network devices have been described on the command line, you
   should boot UML and log in.
 
 
-  The first thing to do is bring the interface up:
+  The first thing to do is bring the interface up::
 
 
        UML# ifconfig ethn ip-address up
@@ -1067,7 +1028,7 @@
 
 
   To reach the rest of the world, you should set a default route to the
-  host:
+  host::
 
 
        UML# route add default gw host ip
@@ -1075,7 +1036,7 @@
 
 
 
-  Again, with host ip of 192.168.0.4:
+  Again, with host ip of 192.168.0.4::
 
 
        UML# route add default gw 192.168.0.4
@@ -1097,29 +1058,25 @@
   Note: If you can't communicate with other hosts on your physical
   ethernet, it's probably because of a network route that's
   automatically set up.  If you run 'route -n' and see a route that
-  looks like this:
+  looks like this::
 
 
 
 
-  Destination     Gateway         Genmask         Flags Metric Ref    Use Iface
-  192.168.0.0     0.0.0.0         255.255.255.0   U     0      0      0   eth0
+    Destination     Gateway         Genmask         Flags Metric Ref    Use Iface
+    192.168.0.0     0.0.0.0         255.255.255.0   U     0      0      0   eth0
 
 
 
 
   with a mask that's not 255.255.255.255, then replace it with a route
-  to your host:
+  to your host::
 
 
        UML#
        route del -net 192.168.0.0 dev eth0 netmask 255.255.255.0
 
 
-
-
-
-
        UML#
        route add -host 192.168.0.4 dev eth0
 
@@ -1131,7 +1088,8 @@
 
 
 
-  6.5.  Multicast
+6.5.  Multicast
+---------------
 
   The simplest way to set up a virtual network between multiple UMLs is
   to use the mcast transport.  This was written by Harald Welte and is
@@ -1142,7 +1100,7 @@
   messages when you bring the device up inside UML.
 
 
-  To use it, run two UMLs with
+  To use it, run two UMLs with::
 
 
         eth0=mcast
@@ -1151,16 +1109,12 @@
 
 
   on their command lines.  Log in, configure the ethernet device in each
-  machine with different IP addresses:
+  machine with different IP addresses::
 
 
        UML1# ifconfig eth0 192.168.0.254
 
 
-
-
-
-
        UML2# ifconfig eth0 192.168.0.253
 
 
@@ -1168,7 +1122,7 @@
 
   and they should be able to talk to each other.
 
-  The full set of command line options for this transport are
+  The full set of command line options for this transport are::
 
 
 
@@ -1177,16 +1131,11 @@
 
 
 
-
-  Harald's original README is here <http://user-mode-linux.source-
-  forge.net/>  and explains these in detail, as well as
-  some other issues.
-
   There is also a related point-to-point only "ucast" transport.
   This is useful when your network does not support multicast, and
   all network connections are simple point to point links.
 
-  The full set of command line options for this transport are
+  The full set of command line options for this transport are::
 
 
        ethn=ucast,ethernet address,remote address,listen port,remote port
@@ -1194,7 +1143,8 @@
 
 
 
-  6.6.  TUN/TAP with the uml_net helper
+6.6.  TUN/TAP with the uml_net helper
+-------------------------------------
 
   TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the
   host.  The TUN/TAP backend has been in UML since 2.4.9-3um.
@@ -1216,7 +1166,7 @@
   kernel or as the tun.o module.
 
   The format of the command line switch to attach a device to a TUN/TAP
-  device is
+  device is::
 
 
        eth <n> =tuntap,,, <IP address>
@@ -1226,7 +1176,7 @@
 
   For example, this argument will attach the UML's eth0 to the next
   available tap device and assign an ethernet address to it based on its
-  IP address
+  IP address::
 
 
        eth0=tuntap,,,192.168.0.254
@@ -1247,10 +1197,10 @@
   There are a couple potential problems with running the TUN/TAP
   transport on a 2.4 host kernel
 
-  o  TUN/TAP seems not to work on 2.4.3 and earlier.  Upgrade the host
+  -  TUN/TAP seems not to work on 2.4.3 and earlier.  Upgrade the host
      kernel or use the ethertap transport.
 
-  o  With an upgraded kernel, TUN/TAP may fail with
+  -  With an upgraded kernel, TUN/TAP may fail with::
 
 
        File descriptor in bad state
@@ -1263,13 +1213,12 @@
   make sure that /usr/src/linux points to the headers for the running
   kernel.
 
-  These were pointed out by Tim Robinson <timro at trkr dot net> in
-  <http://www.geocrawler.com/> name="this uml-
-  user post"> .
+  These were pointed out by Tim Robinson <timro at trkr dot net> in the past.
 
 
 
-  6.7.  TUN/TAP with a preconfigured tap device
+6.7.  TUN/TAP with a preconfigured tap device
+---------------------------------------------
 
   If you prefer not to have UML use uml_net (which is somewhat
   insecure), with UML 2.4.17-11, you can set up a TUN/TAP device
@@ -1277,8 +1226,8 @@
   there is no need for root assistance.  Setting up the device is done
   as follows:
 
-  o  Create the device with tunctl (available from the UML utilities
-     tarball)
+  -  Create the device with tunctl (available from the UML utilities
+     tarball)::
 
 
 
@@ -1291,8 +1240,8 @@
   where uid is the user id or username that UML will be run as.  This
   will tell you what device was created.
 
-  o  Configure the device IP (change IP addresses and device name to
-     suit)
+  -  Configure the device IP (change IP addresses and device name to
+     suit)::
 
 
 
@@ -1303,8 +1252,8 @@
 
 
 
-  o  Set up routing and arping if desired - this is my recipe, there are
-     other ways of doing the same thing
+  -  Set up routing and arping if desired - this is my recipe, there are
+     other ways of doing the same thing::
 
 
        host#
@@ -1313,19 +1262,9 @@
        host#
        route add -host 192.168.0.253 dev tap0
 
-
-
-
-
-
        host#
        bash -c 'echo 1 > /proc/sys/net/ipv4/conf/tap0/proxy_arp'
 
-
-
-
-
-
        host#
        arp -Ds 192.168.0.253 eth0 pub
 
@@ -1338,76 +1277,43 @@
   utility which reads the information from a config file and sets up
   devices at boot time.
 
-  o  Rather than using up two IPs and ARPing for one of them, you can
+  -  Rather than using up two IPs and ARPing for one of them, you can
      also provide direct access to your LAN by the UML by using a
-     bridge.
+     bridge::
 
 
        host#
        brctl addbr br0
 
 
-
-
-
-
        host#
        ifconfig eth0 0.0.0.0 promisc up
 
 
-
-
-
-
        host#
        ifconfig tap0 0.0.0.0 promisc up
 
 
-
-
-
-
        host#
        ifconfig br0 192.168.0.1 netmask 255.255.255.0 up
 
 
-
-
-
-
-
-  host#
-  brctl stp br0 off
-
-
-
-
+       host#
+       brctl stp br0 off
 
 
        host#
        brctl setfd br0 1
 
 
-
-
-
-
        host#
        brctl sethello br0 1
 
 
-
-
-
-
        host#
        brctl addif br0 eth0
 
 
-
-
-
-
        host#
        brctl addif br0 tap0
 
@@ -1417,12 +1323,12 @@
   Note that 'br0' should be setup using ifconfig with the existing IP
   address of eth0, as eth0 no longer has its own IP.
 
-  o
+  -
 
 
      Also, the /dev/net/tun device must be writable by the user running
      UML in order for the UML to use the device that's been configured
-     for it.  The simplest thing to do is
+     for it.  The simplest thing to do is::
 
 
        host#  chmod 666 /dev/net/tun
@@ -1438,14 +1344,14 @@
   devices and chgrp /dev/net/tun to that group with mode 664 or 660.
 
 
-  o  Once the device is set up, run UML with 'eth0=tuntap,device name'
+  -  Once the device is set up, run UML with 'eth0=tuntap,device name'
      (i.e. 'eth0=tuntap,tap0') on the command line (or do it with the
      mconsole config command).
 
-  o  Bring the eth device up in UML and you're in business.
+  -  Bring the eth device up in UML and you're in business.
 
      If you don't want that tap device any more, you can make it non-
-     persistent with
+     persistent with::
 
 
        host#  tunctl -d tap device
@@ -1455,7 +1361,7 @@
 
   Finally, tunctl has a -b (for brief mode) switch which causes it to
   output only the name of the tap device it created.  This makes it
-  suitable for capture by a script:
+  suitable for capture by a script::
 
 
        host#  TAP=`tunctl -u 1000 -b`
@@ -1465,7 +1371,8 @@
 
 
 
-  6.8.  Ethertap
+6.8.  Ethertap
+--------------
 
   Ethertap is the general mechanism on 2.2 for userspace processes to
   exchange packets with the kernel.
@@ -1473,7 +1380,7 @@
 
 
   To use this transport, you need to describe the virtual network device
-  on the UML command line.  The general format for this is
+  on the UML command line.  The general format for this is::
 
 
        eth <n> =ethertap, <device> , <ethernet address> , <tap IP address>
@@ -1481,7 +1388,7 @@
 
 
 
-  So, the previous example
+  So, the previous example::
 
 
        eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254
@@ -1521,7 +1428,7 @@
 
   If you want to set things up yourself, you need to make sure that the
   appropriate /dev entry exists.  If it doesn't, become root and create
-  it as follows:
+  it as follows::
 
 
        mknod /dev/tap <minor>  c 36  <minor>  + 16
@@ -1529,7 +1436,7 @@
 
 
 
-  For example, this is how to create /dev/tap0:
+  For example, this is how to create /dev/tap0::
 
 
        mknod /dev/tap0 c 36 0 + 16
@@ -1539,7 +1446,7 @@
 
   You also need to make sure that the host kernel has ethertap support.
   If ethertap is enabled as a module, you apparently need to insmod
-  ethertap once for each ethertap device you want to enable.  So,
+  ethertap once for each ethertap device you want to enable.  So,::
 
 
        host#
@@ -1549,7 +1456,7 @@
 
 
   will give you the tap0 interface.  To get the tap1 interface, you need
-  to run
+  to run::
 
 
        host#
@@ -1561,7 +1468,8 @@
 
 
 
-  6.9.  The switch daemon
+6.9.  The switch daemon
+-----------------------
 
   Note: This is the daemon formerly known as uml_router, but which was
   renamed so the network weenies of the world would stop growling at me.
@@ -1577,7 +1485,7 @@
   sockets.
 
 
-  If you want it to listen on a different pair of sockets, use
+  If you want it to listen on a different pair of sockets, use::
 
 
         -unix control socket data socket
@@ -1586,7 +1494,7 @@
 
 
 
-  If you want it to act as a hub rather than a switch, use
+  If you want it to act as a hub rather than a switch, use::
 
 
         -hub
@@ -1596,7 +1504,7 @@
 
 
   If you want the switch to be connected to host networking (allowing
-  the umls to get access to the outside world through the host), use
+  the umls to get access to the outside world through the host), use::
 
 
         -tap tap0
@@ -1610,7 +1518,7 @@
   device than tap0, specify that instead of tap0.
 
 
-  uml_switch can be backgrounded as follows
+  uml_switch can be backgrounded as follows::
 
 
        host%
@@ -1623,7 +1531,7 @@
   stdin for EOF.  When it sees that, it exits.
 
 
-  The general format of the kernel command line switch is
+  The general format of the kernel command line switch is::
 
 
 
@@ -1639,7 +1547,8 @@
   how to communicate with the daemon.  You should only specify them if
   you told the daemon to use different sockets than the default.  So, if
   you ran the daemon with no arguments, running the UML on the same
-  machine with
+  machine with::
+
        eth0=daemon
 
 
@@ -1649,7 +1558,8 @@
 
 
 
-  6.10.  Slip
+6.10.  Slip
+-----------
 
   Slip is another, less general, mechanism for a process to communicate
   with the host networking.  In contrast to the ethertap interface,
@@ -1658,7 +1568,7 @@
   IP.
 
 
-  The general format of the command line switch is
+  The general format of the command line switch is::
 
 
 
@@ -1681,7 +1591,8 @@
 
 
 
-  6.11.  Slirp
+6.11.  Slirp
+------------
 
   slirp uses an external program, usually /usr/bin/slirp, to provide IP
   only networking connectivity through the host. This is similar to IP
@@ -1691,7 +1602,7 @@
   root access or setuid binaries on the host.
 
 
-  The general format of the command line switch for slirp is:
+  The general format of the command line switch for slirp is::
 
 
 
@@ -1716,7 +1627,7 @@
   The eth0 interface on UML should be set up with the IP 10.2.0.15,
   although you can use anything as long as it is not used by a network
   you will be connecting to. The default route on UML should be set to
-  use
+  use::
 
 
        UML#
@@ -1737,10 +1648,11 @@
 
 
 
-  6.12.  pcap
+6.12.  pcap
+-----------
 
   The pcap transport is attached to a UML ethernet device on the command
-  line or with uml_mconsole with the following syntax:
+  line or with uml_mconsole with the following syntax::
 
 
 
@@ -1762,7 +1674,7 @@
   expression optimizer is used.
 
 
-  Example:
+  Example::
 
 
 
@@ -1777,7 +1689,8 @@
 
 
 
-  6.13.  Setting up the host yourself
+6.13.  Setting up the host yourself
+-----------------------------------
 
   If you don't specify an address for the host side of the ethertap or
   slip device, UML won't do any setup on the host.  So this is what is
@@ -1785,19 +1698,15 @@
   192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your
   own network):
 
-  o  The device needs to be configured with its IP address.  Tap devices
+  -  The device needs to be configured with its IP address.  Tap devices
      are also configured with an mtu of 1484.  Slip devices are
      configured with a point-to-point address pointing at the UML ip
-     address.
+     address::
 
 
        host#  ifconfig tap0 arp mtu 1484 192.168.0.251 up
 
 
-
-
-
-
        host#
        ifconfig sl0 192.168.0.251 pointopoint 192.168.0.250 up
 
@@ -1805,7 +1714,7 @@
 
 
 
-  o  If a tap device is being set up, a route is set to the UML IP.
+  -  If a tap device is being set up, a route is set to the UML IP::
 
 
        UML# route add -host 192.168.0.250 gw 192.168.0.251
@@ -1814,8 +1723,8 @@
 
 
 
-  o  To allow other hosts on your network to see the virtual machine,
-     proxy arp is set up for it.
+  -  To allow other hosts on your network to see the virtual machine,
+     proxy arp is set up for it::
 
 
        host#  arp -Ds 192.168.0.250 eth0 pub
@@ -1824,7 +1733,7 @@
 
 
 
-  o  Finally, the host is set up to route packets.
+  -  Finally, the host is set up to route packets::
 
 
        host#  echo 1 > /proc/sys/net/ipv4/ip_forward
@@ -1838,12 +1747,14 @@
 
 
 
-  7.  Sharing Filesystems between Virtual Machines
+7.  Sharing Filesystems between Virtual Machines
+================================================
 
 
 
 
-  7.1.  A warning
+7.1.  A warning
+---------------
 
   Don't attempt to share filesystems simply by booting two UMLs from the
   same file.  That's the same thing as booting two physical machines
@@ -1851,7 +1762,8 @@
 
 
 
-  7.2.  Using layered block devices
+7.2.  Using layered block devices
+---------------------------------
 
   The way to share a filesystem between two virtual machines is to use
   the copy-on-write (COW) layering capability of the ubd block driver.
@@ -1872,7 +1784,7 @@
 
 
   To add a copy-on-write layer to an existing block device file, simply
-  add the name of the COW file to the appropriate ubd switch:
+  add the name of the COW file to the appropriate ubd switch::
 
 
         ubd0=root_fs_cow,root_fs_debian_22
@@ -1883,7 +1795,7 @@
   where 'root_fs_cow' is the private COW file and 'root_fs_debian_22' is
   the existing shared filesystem.  The COW file need not exist.  If it
   doesn't, the driver will create and initialize it.  Once the COW file
-  has been initialized, it can be used on its own on the command line:
+  has been initialized, it can be used on its own on the command line::
 
 
         ubd0=root_fs_cow
@@ -1896,14 +1808,16 @@
 
 
 
-  7.3.  Note!
+7.3.  Note!
+-----------
 
   When checking the size of the COW file in order to see the gobs of
   space that you're saving, make sure you use 'ls -ls' to see the actual
   disk consumption rather than the length of the file.  The COW file is
   sparse, so the length will be very different from the disk usage.
   Here is a 'ls -l' of a COW file and backing file from one boot and
-  shutdown:
+  shutdown::
+
        host% ls -l cow.debian debian2.2
        -rw-r--r--    1 jdike    jdike    492504064 Aug  6 21:16 cow.debian
        -rwxrw-rw-    1 jdike    jdike    537919488 Aug  6 20:42 debian2.2
@@ -1911,7 +1825,7 @@
 
 
 
-  Doesn't look like much saved space, does it?  Well, here's 'ls -ls':
+  Doesn't look like much saved space, does it?  Well, here's 'ls -ls'::
 
 
        host% ls -ls cow.debian debian2.2
@@ -1926,7 +1840,8 @@
 
 
 
-  7.4.  Another warning
+7.4.  Another warning
+---------------------
 
   Once a filesystem is being used as a readonly backing file for a COW
   file, do not boot directly from it or modify it in any way.  Doing so
@@ -1952,7 +1867,8 @@
 
 
 
-  7.5.  uml_moo : Merging a COW file with its backing file
+7.5.  uml_moo : Merging a COW file with its backing file
+--------------------------------------------------------
 
   Depending on how you use UML and COW devices, it may be advisable to
   merge the changes in the COW file into the backing file every once in
@@ -1961,7 +1877,7 @@
 
 
 
-  The utility that does this is uml_moo.  Its usage is
+  The utility that does this is uml_moo.  Its usage is::
 
 
        host% uml_moo COW file new backing file
@@ -1991,8 +1907,8 @@
 
   uml_moo is installed with the UML deb and RPM.  If you didn't install
   UML from one of those packages, you can also get it from the UML
-  utilities <http://user-mode-linux.sourceforge.net/
-  utilities>  tar file in tools/moo.
+  utilities http://user-mode-linux.sourceforge.net/utilities tar file
+  in tools/moo.
 
 
 
@@ -2001,7 +1917,8 @@
 
 
 
-  8.  Creating filesystems
+8.  Creating filesystems
+========================
 
 
   You may want to create and mount new UML filesystems, either because
@@ -2015,13 +1932,14 @@
   should be easy to translate to the filesystem of your choice.
 
 
-  8.1.  Create the filesystem file
+8.1.  Create the filesystem file
+================================
 
   dd is your friend.  All you need to do is tell dd to create an empty
   file of the appropriate size.  I usually make it sparse to save time
   and to avoid allocating disk space until it's actually used.  For
   example, the following command will create a sparse 100 meg file full
-  of zeroes.
+  of zeroes::
 
 
        host%
@@ -2034,9 +1952,9 @@
 
   8.2.  Assign the file to a UML device
 
-  Add an argument like the following to the UML command line:
+  Add an argument like the following to the UML command line::
 
-  ubd4=new_filesystem
+	ubd4=new_filesystem
 
 
 
@@ -2053,7 +1971,7 @@
   etc), then get them into UML by way of the net or hostfs.
 
 
-  Make the new filesystem on the device assigned to the new file:
+  Make the new filesystem on the device assigned to the new file::
 
 
        host#  mkreiserfs /dev/ubd/4
@@ -2077,7 +1995,7 @@
 
 
 
-  Now, mount it:
+  Now, mount it::
 
 
        UML#
@@ -2096,7 +2014,8 @@
 
 
 
-  9.  Host file access
+9.  Host file access
+====================
 
 
   If you want to access files on the host machine from inside UML, you
@@ -2112,10 +2031,11 @@
   files contained in it just as you would on the host.
 
 
-  9.1.  Using hostfs
+9.1.  Using hostfs
+------------------
 
   To begin with, make sure that hostfs is available inside the virtual
-  machine with
+  machine with::
 
 
        UML# cat /proc/filesystems
@@ -2127,7 +2047,7 @@
   module and available inside the virtual machine, and insmod it.
 
 
-  Now all you need to do is run mount:
+  Now all you need to do is run mount::
 
 
        UML# mount none /mnt/host -t hostfs
@@ -2139,7 +2059,7 @@
 
 
   If you don't want to mount the host root directory, then you can
-  specify a subdirectory to mount with the -o switch to mount:
+  specify a subdirectory to mount with the -o switch to mount::
 
 
        UML# mount none /mnt/home -t hostfs -o /home
@@ -2151,13 +2071,14 @@
 
 
 
-  9.2.  hostfs as the root filesystem
+9.2.  hostfs as the root filesystem
+-----------------------------------
 
   It's possible to boot from a directory hierarchy on the host using
   hostfs rather than using the standard filesystem in a file.
 
   To start, you need that hierarchy.  The easiest way is to loop mount
-  an existing root_fs file:
+  an existing root_fs file::
 
 
        host#  mount root_fs uml_root_dir -o loop
@@ -2166,15 +2087,15 @@
 
 
   You need to change the filesystem type of / in etc/fstab to be
-  'hostfs', so that line looks like this:
+  'hostfs', so that line looks like this::
 
-  /dev/ubd/0       /        hostfs      defaults          1   1
+    /dev/ubd/0       /        hostfs      defaults          1   1
 
 
 
 
   Then you need to chown to yourself all the files in that directory
-  that are owned by root.  This worked for me:
+  that are owned by root.  This worked for me::
 
 
        host#  find . -uid 0 -exec chown jdike {} \;
@@ -2183,7 +2104,7 @@
 
 
   Next, make sure that your UML kernel has hostfs compiled in, not as a
-  module.  Then run UML with the boot device pointing at that directory:
+  module.  Then run UML with the boot device pointing at that directory::
 
 
         ubd0=/path/to/uml/root/directory
@@ -2194,41 +2115,35 @@
   UML should then boot as it does normally.
 
 
-  9.3.  Building hostfs
+9.3.  Building hostfs
+---------------------
 
   If you need to build hostfs because it's not in your kernel, you have
   two choices:
 
 
 
-  o  Compiling hostfs into the kernel:
+  -  Compiling hostfs into the kernel:
 
 
      Reconfigure the kernel and set the 'Host filesystem' option under
 
 
-  o  Compiling hostfs as a module:
+  -  Compiling hostfs as a module:
 
 
      Reconfigure the kernel and set the 'Host filesystem' option under
      be in arch/um/fs/hostfs/hostfs.o.  Install that in
-     /lib/modules/`uname -r`/fs in the virtual machine, boot it up, and
+     ``/lib/modules/$(uname -r)/fs`` in the virtual machine, boot it up, and::
 
 
        UML# insmod hostfs
 
 
+.. _The_Management_Console:
 
-
-
-
-
-
-
-
-
-
-  10.  The Management Console
+10.  The Management Console
+===========================
 
 
 
@@ -2240,15 +2155,15 @@
 
   There are a number of things you can do with the mconsole interface:
 
-  o  get the kernel version
+  -  get the kernel version
 
-  o  add and remove devices
+  -  add and remove devices
 
-  o  halt or reboot the machine
+  -  halt or reboot the machine
 
-  o  Send SysRq commands
+  -  Send SysRq commands
 
-  o  Pause and resume the UML
+  -  Pause and resume the UML
 
 
   You need the mconsole client (uml_mconsole) which is present in CVS
@@ -2257,7 +2172,7 @@
 
 
   You also need CONFIG_MCONSOLE (under 'General Setup') enabled in UML.
-  When you boot UML, you'll see a line like:
+  When you boot UML, you'll see a line like::
 
 
        mconsole initialized on /home/jdike/.uml/umlNJ32yL/mconsole
@@ -2265,7 +2180,7 @@
 
 
 
-  If you specify a unique machine id one the UML command line, i.e.
+  If you specify a unique machine id one the UML command line, i.e.::
 
 
         umid=debian
@@ -2273,7 +2188,7 @@
 
 
 
-  you'll see this
+  you'll see this::
 
 
        mconsole initialized on /home/jdike/.uml/debian/mconsole
@@ -2282,7 +2197,7 @@
 
 
   That file is the socket that uml_mconsole will use to communicate with
-  UML.  Run it with either the umid or the full path as its argument:
+  UML.  Run it with either the umid or the full path as its argument::
 
 
        host% uml_mconsole debian
@@ -2290,7 +2205,7 @@
 
 
 
-  or
+  or::
 
 
        host% uml_mconsole /home/jdike/.uml/debian/mconsole
@@ -2300,30 +2215,31 @@
 
   You'll get a prompt, at which you can run one of these commands:
 
-  o  version
+  -  version
 
-  o  halt
+  -  halt
 
-  o  reboot
+  -  reboot
 
-  o  config
+  -  config
 
-  o  remove
+  -  remove
 
-  o  sysrq
+  -  sysrq
 
-  o  help
+  -  help
 
-  o  cad
+  -  cad
 
-  o  stop
+  -  stop
 
-  o  go
+  -  go
 
 
-  10.1.  version
+10.1.  version
+--------------
 
-  This takes no arguments.  It prints the UML version.
+  This takes no arguments.  It prints the UML version::
 
 
        (mconsole)  version
@@ -2342,11 +2258,12 @@
 
 
 
-  10.2.  halt and reboot
+10.2.  halt and reboot
+----------------------
 
   These take no arguments.  They shut the machine down immediately, with
   no syncing of disks and no clean shutdown of userspace.  So, they are
-  pretty close to crashing the machine.
+  pretty close to crashing the machine::
 
 
        (mconsole)  halt
@@ -2357,34 +2274,36 @@
 
 
 
-  10.3.  config
+10.3.  config
+-------------
 
   "config" adds a new device to the virtual machine.  Currently the ubd
   and network drivers support this.  It takes one argument, which is the
-  device to add, with the same syntax as the kernel command line.
+  device to add, with the same syntax as the kernel command line::
 
 
 
 
-  (mconsole)
-  config ubd3=/home/jdike/incoming/roots/root_fs_debian22
+	(mconsole)
+	config ubd3=/home/jdike/incoming/roots/root_fs_debian22
 
-  OK
-  (mconsole)  config eth1=mcast
-  OK
+	OK
+	(mconsole)  config eth1=mcast
+	OK
 
 
 
 
 
 
-  10.4.  remove
+10.4.  remove
+-------------
 
   "remove" deletes a device from the system.  Its argument is just the
   name of the device to be removed. The device must be idle in whatever
   sense the driver considers necessary.  In the case of the ubd driver,
   the removed block device must not be mounted, swapped on, or otherwise
-  open, and in the case of the network driver, the device must be down.
+  open, and in the case of the network driver, the device must be down::
 
 
        (mconsole)  remove ubd3
@@ -2397,7 +2316,8 @@
 
 
 
-  10.5.  sysrq
+10.5.  sysrq
+------------
 
   This takes one argument, which is a single letter.  It calls the
   generic kernel's SysRq driver, which does whatever is called for by
@@ -2407,19 +2327,21 @@
 
 
 
-  10.6.  help
+10.6.  help
+-----------
 
   "help" returns a string listing the valid commands and what each one
   does.
 
 
 
-  10.7.  cad
+10.7.  cad
+----------
 
   This invokes the Ctl-Alt-Del action on init.  What exactly this ends
   up doing is up to /etc/inittab.  Normally, it reboots the machine.
   With UML, this is usually not desired, so if a halt would be better,
-  then find the section of inittab that looks like this
+  then find the section of inittab that looks like this::
 
 
        # What to do when CTRL-ALT-DEL is pressed.
@@ -2432,7 +2354,8 @@
 
 
 
-  10.8.  stop
+10.8.  stop
+-----------
 
   This puts the UML in a loop reading mconsole requests until a 'go'
   mconsole command is received. This is very useful for making backups
@@ -2448,7 +2371,8 @@
 
 
 
-  10.9.  go
+10.9.  go
+---------
 
   This resumes a UML after being paused by a 'stop' command. Note that
   when the UML has resumed, TCP connections may have timed out and if
@@ -2460,9 +2384,10 @@
 
 
 
+.. _Kernel_debugging:
 
-
-  11.  Kernel debugging
+11.  Kernel debugging
+=====================
 
 
   Note: The interface that makes debugging, as described here, possible
@@ -2477,15 +2402,16 @@
 
 
   In order to debug the kernel, you need build it from source.  See
-  ``Compiling the kernel and modules''  for information on doing that.
+  :ref:`Compiling_the_kernel_and_modules`  for information on doing that.
   Make sure that you enable CONFIG_DEBUGSYM and CONFIG_PT_PROXY during
-  the config.  These will compile the kernel with -g, and enable the
+  the config.  These will compile the kernel with ``-g``, and enable the
   ptrace proxy so that gdb works with UML, respectively.
 
 
 
 
-  11.1.  Starting the kernel under gdb
+11.1.  Starting the kernel under gdb
+------------------------------------
 
   You can have the kernel running under the control of gdb from the
   beginning by putting 'debug' on the command line.  You will get an
@@ -2498,7 +2424,11 @@
   There is a transcript of a debugging session  here <debug-
   session.html> , with breakpoints being set in the scheduler and in an
   interrupt handler.
-  11.2.  Examining sleeping processes
+
+
+11.2.  Examining sleeping processes
+-----------------------------------
+
 
   Not every bug is evident in the currently running process.  Sometimes,
   processes hang in the kernel when they shouldn't because they've
@@ -2516,7 +2446,7 @@
 
   Now what you do is this:
 
-  o  detach from the current thread
+  -  detach from the current thread::
 
 
        (UML gdb)  det
@@ -2525,7 +2455,7 @@
 
 
 
-  o  attach to the thread you are interested in
+  -  attach to the thread you are interested in::
 
 
        (UML gdb)  att <host pid>
@@ -2534,7 +2464,7 @@
 
 
 
-  o  look at its stack and anything else of interest
+  -  look at its stack and anything else of interest::
 
 
        (UML gdb)  bt
@@ -2545,18 +2475,14 @@
   Note that you can't do anything at this point that requires that a
   process execute, e.g. calling a function
 
-  o  when you're done looking at that process, reattach to the current
-     thread and continue it
+  -  when you're done looking at that process, reattach to the current
+     thread and continue it::
 
 
        (UML gdb)
        att 1
 
 
-
-
-
-
        (UML gdb)
        c
 
@@ -2569,12 +2495,13 @@
 
 
 
-  11.3.  Running ddd on UML
+11.3.  Running ddd on UML
+-------------------------
 
   ddd works on UML, but requires a special kludge.  The process goes
   like this:
 
-  o  Start ddd
+  -  Start ddd::
 
 
        host% ddd linux
@@ -2583,14 +2510,14 @@
 
 
 
-  o  With ps, get the pid of the gdb that ddd started.  You can ask the
+  -  With ps, get the pid of the gdb that ddd started.  You can ask the
      gdb to tell you, but for some reason that confuses things and
      causes a hang.
 
-  o  run UML with 'debug=parent gdb-pid=<pid>' added to the command line
+  -  run UML with 'debug=parent gdb-pid=<pid>' added to the command line
      - it will just sit there after you hit return
 
-  o  type 'att 1' to the ddd gdb and you will see something like
+  -  type 'att 1' to the ddd gdb and you will see something like::
 
 
        0xa013dc51 in __kill ()
@@ -2602,12 +2529,14 @@
 
 
 
-  o  At this point, type 'c', UML will boot up, and you can use ddd just
+  -  At this point, type 'c', UML will boot up, and you can use ddd just
      as you do on any other process.
 
 
 
-  11.4.  Debugging modules
+11.4.  Debugging modules
+------------------------
+
 
   gdb has support for debugging code which is dynamically loaded into
   the process.  This support is what is needed to debug kernel modules
@@ -2629,7 +2558,8 @@
 
 
   First, you must tell it where your modules are.  There is a list in
-  the script that looks like this:
+  the script that looks like this::
+
        set MODULE_PATHS {
        "fat" "/usr/src/uml/linux-2.4.18/fs/fat/fat.o"
        "isofs" "/usr/src/uml/linux-2.4.18/fs/isofs/isofs.o"
@@ -2641,9 +2571,7 @@
 
   You change that to list the names and paths of the modules that you
   are going to debug.  Then you run it from the toplevel directory of
-  your UML pool and it basically tells you what to do:
-
-
+  your UML pool and it basically tells you what to do::
 
 
                    ******** GDB pid is 21903 ********
@@ -2666,7 +2594,7 @@
 
 
   After you run UML and it sits there doing nothing, you hit return at
-  the 'att 1' and continue it:
+  the 'att 1' and continue it::
 
 
        Attaching to program: /home/jdike/linux/2.4/um/./linux, process 1
@@ -2678,63 +2606,48 @@
 
 
   At this point, you debug normally.  When you insmod something, the
-  expect magic will kick in and you'll see something like:
+  expect magic will kick in and you'll see something like::
 
 
+     *** Module hostfs loaded ***
+    Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs",
+        mod_user=0x8070e00) at module.c:349
+    349             char *name, *n_name, *name_tmp = NULL;
+    (UML gdb)  finish
+    Run till exit from #0  sys_init_module (name_user=0x805abb0 "hostfs",
+        mod_user=0x8070e00) at module.c:349
+    0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411
+    411             else res = EXECUTE_SYSCALL(syscall, regs);
+    Value returned is $1 = 0
+    (UML gdb)
+    p/x (int)module_list + module_list->size_of_struct
 
+    $2 = 0xa9021054
+    (UML gdb)  symbol-file ./linux
+    Load new symbol table from "./linux"? (y or n) y
+    Reading symbols from ./linux...
+    done.
+    (UML gdb)
+    add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054
 
+    add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at
+            .text_addr = 0xa9021054
+     (y or n) y
 
-
-
-
-
-
-
-
-
-
-
-
-
-   *** Module hostfs loaded ***
-  Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs",
-      mod_user=0x8070e00) at module.c:349
-  349             char *name, *n_name, *name_tmp = NULL;
-  (UML gdb)  finish
-  Run till exit from #0  sys_init_module (name_user=0x805abb0 "hostfs",
-      mod_user=0x8070e00) at module.c:349
-  0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411
-  411             else res = EXECUTE_SYSCALL(syscall, regs);
-  Value returned is $1 = 0
-  (UML gdb)
-  p/x (int)module_list + module_list->size_of_struct
-
-  $2 = 0xa9021054
-  (UML gdb)  symbol-file ./linux
-  Load new symbol table from "./linux"? (y or n) y
-  Reading symbols from ./linux...
-  done.
-  (UML gdb)
-  add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054
-
-  add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at
-          .text_addr = 0xa9021054
-   (y or n) y
-
-  Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o...
-  done.
-  (UML gdb)  p *module_list
-  $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs",
-    size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1,
-    nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0,
-    init = 0xa90221f0 <init_hostfs>, cleanup = 0xa902222c <exit_hostfs>,
-    ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0,
-    persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0,
-    kallsyms_end = 0x0,
-    archdata_start = 0x1b855 <Address 0x1b855 out of bounds>,
-    archdata_end = 0xe5890000 <Address 0xe5890000 out of bounds>,
-    kernel_data = 0xf689c35d <Address 0xf689c35d out of bounds>}
-  >> Finished loading symbols for hostfs ...
+    Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o...
+    done.
+    (UML gdb)  p *module_list
+    $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs",
+      size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1,
+      nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0,
+      init = 0xa90221f0 <init_hostfs>, cleanup = 0xa902222c <exit_hostfs>,
+      ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0,
+      persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0,
+      kallsyms_end = 0x0,
+      archdata_start = 0x1b855 <Address 0x1b855 out of bounds>,
+      archdata_end = 0xe5890000 <Address 0xe5890000 out of bounds>,
+      kernel_data = 0xf689c35d <Address 0xf689c35d out of bounds>}
+    >> Finished loading symbols for hostfs ...
 
 
 
@@ -2744,7 +2657,7 @@
 
 
   Boot the kernel under the debugger and load the module with insmod or
-  modprobe.  With gdb, do:
+  modprobe.  With gdb, do::
 
 
        (UML gdb)  p module_list
@@ -2758,12 +2671,12 @@
   the name fields until find the module you want to debug.  Take the
   address of that structure, and add module.size_of_struct (which in
   2.4.10 kernels is 96 (0x60)) to it.  Gdb can make this hard addition
-  for you :-):
+  for you :-)::
 
 
 
-  (UML gdb)
-  printf "%#x\n", (int)module_list module_list->size_of_struct
+	(UML gdb)
+	printf "%#x\n", (int)module_list module_list->size_of_struct
 
 
 
@@ -2771,7 +2684,7 @@
   The offset from the module start occasionally changes (before 2.4.0,
   it was module.size_of_struct + 4), so it's a good idea to check the
   init and cleanup addresses once in a while, as describe below.  Now
-  do:
+  do::
 
 
        (UML gdb)
@@ -2786,7 +2699,7 @@
   If there's any doubt that you got the offset right, like breakpoints
   appear not to work, or they're appearing in the wrong place, you can
   check it by looking at the module structure.  The init and cleanup
-  fields should look like:
+  fields should look like::
 
 
        init = 0x588066b0 <init_hostfs>, cleanup = 0x588066c0 <exit_hostfs>
@@ -2801,7 +2714,7 @@
 
   When you want to load in a new version of the module, you need to get
   gdb to forget about the old one.  The only way I've found to do that
-  is to tell gdb to forget about all symbols that it knows about:
+  is to tell gdb to forget about all symbols that it knows about::
 
 
        (UML gdb)  symbol-file
@@ -2809,7 +2722,7 @@
 
 
 
-  Then reload the symbols from the kernel binary:
+  Then reload the symbols from the kernel binary::
 
 
        (UML gdb)  symbol-file /path/to/kernel
@@ -2823,17 +2736,19 @@
 
 
 
-  11.5.  Attaching gdb to the kernel
+11.5.  Attaching gdb to the kernel
+----------------------------------
 
   If you don't have the kernel running under gdb, you can attach gdb to
   it later by sending the tracing thread a SIGUSR1.  The first line of
-  the console output identifies its pid:
+  the console output identifies its pid::
+
        tracing thread pid = 20093
 
 
 
 
-  When you send it the signal:
+  When you send it the signal::
 
 
        host% kill -USR1 20093
@@ -2845,7 +2760,7 @@
 
 
   If you have the mconsole compiled into UML, then the mconsole client
-  can be used to start gdb:
+  can be used to start gdb::
 
 
        (mconsole)  (mconsole) config gdb=xterm
@@ -2857,7 +2772,8 @@
 
 
 
-  11.6.  Using alternate debuggers
+11.6.  Using alternate debuggers
+--------------------------------
 
   UML has support for attaching to an already running debugger rather
   than starting gdb itself.  This is present in CVS as of 17 Apr 2001.
@@ -2886,7 +2802,7 @@
   An example of an alternate debugger is strace.  You can strace the
   actual kernel as follows:
 
-  o  Run the following in a shell
+  -  Run the following in a shell::
 
 
        host%
@@ -2894,13 +2810,13 @@
 
 
 
-  o  Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
+  -  Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
      by the previous command
 
-  o  Hit return in the shell, and UML will start running, and strace
+  -  Hit return in the shell, and UML will start running, and strace
      output will start accumulating in the output file.
 
-     Note that this is different from running
+     Note that this is different from running::
 
 
        host% strace ./linux
@@ -2917,95 +2833,57 @@
 
 
 
-  12.  Kernel debugging examples
+12.  Kernel debugging examples
+==============================
 
-  12.1.  The case of the hung fsck
+12.1.  The case of the hung fsck
+--------------------------------
 
   When booting up the kernel, fsck failed, and dropped me into a shell
-  to fix things up.  I ran fsck -y, which hung:
+  to fix things up.  I ran fsck -y, which hung::
 
 
+    Setting hostname uml                    [ OK ]
+    Checking root filesystem
+    /dev/fhd0 was not cleanly unmounted, check forced.
+    Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
 
+    /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
+	    (i.e., without -a or -p options)
+    [ FAILED ]
 
+    *** An error occurred during the file system check.
+    *** Dropping you to a shell; the system will reboot
+    *** when you leave the shell.
+    Give root password for maintenance
+    (or type Control-D for normal startup):
 
+    [root@uml /root]# fsck -y /dev/fhd0
+    fsck -y /dev/fhd0
+    Parallelizing fsck version 1.14 (9-Jan-1999)
+    e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
+    /dev/fhd0 contains a file system with errors, check forced.
+    Pass 1: Checking inodes, blocks, and sizes
+    Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.  Ignore error? yes
 
+    Inode 19780, i_blocks is 1548, should be 540.  Fix? yes
 
+    Pass 2: Checking directory structure
+    Error reading block 49405 (Attempt to read block from filesystem resulted in short read).  Ignore error? yes
 
+    Directory inode 11858, block 0, offset 0: directory corrupted
+    Salvage? yes
 
+    Missing '.' in directory inode 11858.
+    Fix? yes
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-  Setting hostname uml                    [ OK ]
-  Checking root filesystem
-  /dev/fhd0 was not cleanly unmounted, check forced.
-  Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
-
-  /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
-          (i.e., without -a or -p options)
-  [ FAILED ]
-
-  *** An error occurred during the file system check.
-  *** Dropping you to a shell; the system will reboot
-  *** when you leave the shell.
-  Give root password for maintenance
-  (or type Control-D for normal startup):
-
-  [root@uml /root]# fsck -y /dev/fhd0
-  fsck -y /dev/fhd0
-  Parallelizing fsck version 1.14 (9-Jan-1999)
-  e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
-  /dev/fhd0 contains a file system with errors, check forced.
-  Pass 1: Checking inodes, blocks, and sizes
-  Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.  Ignore error? yes
-
-  Inode 19780, i_blocks is 1548, should be 540.  Fix? yes
-
-  Pass 2: Checking directory structure
-  Error reading block 49405 (Attempt to read block from filesystem resulted in short read).  Ignore error? yes
-
-  Directory inode 11858, block 0, offset 0: directory corrupted
-  Salvage? yes
-
-  Missing '.' in directory inode 11858.
-  Fix? yes
-
-  Missing '..' in directory inode 11858.
-  Fix? yes
-
-
-
+    Missing '..' in directory inode 11858.
+    Fix? yes
 
 
   The standard drill in this sort of situation is to fire up gdb on the
   signal thread, which, in this case, was pid 1935.  In another window,
-  I run gdb and attach pid 1935.
-
-
+  I run gdb and attach pid 1935::
 
 
        ~/linux/2.3.26/um 1016: gdb linux
@@ -3022,11 +2900,7 @@
        0x100756d9 in __wait4 ()
 
 
-
-
-
-
-  Let's see what's currently running:
+  Let's see what's currently running::
 
 
 
@@ -3041,7 +2915,7 @@
   reason and never woke up.
 
 
-  Let's guess that the last process in the process list is fsck:
+  Let's guess that the last process in the process list is fsck::
 
 
 
@@ -3052,7 +2926,7 @@
 
 
 
-  It is, so let's see what it thinks it's up to:
+  It is, so let's see what it thinks it's up to::
 
 
 
@@ -3068,8 +2942,6 @@
 
 
 
-
-
   The interesting things here are the fact that its .thread.syscall.id
   is __NR_write (see the big switch in arch/um/kernel/syscall_kern.c or
   the defines in include/asm-um/arch/unistd.h), and that it never
@@ -3081,30 +2953,20 @@
   The fact that it never returned from write means that its stack should
   be fairly interesting.  Its pid is 1980 (.thread.extern_pid).  That
   process is being ptraced by the signal thread, so it must be detached
-  before gdb can attach it:
+  before gdb can attach it::
 
 
 
+    (gdb) call detach(1980)
 
-
-
-
-
-
-
-  (gdb) call detach(1980)
-
-  Program received signal SIGSEGV, Segmentation fault.
-  <function called from gdb>
-  The program being debugged stopped while in a function called from GDB.
-  When the function (detach) is done executing, GDB will silently
-  stop (instead of continuing to evaluate the expression containing
-  the function call).
-  (gdb) call detach(1980)
-  $15 = 0
-
-
-
+    Program received signal SIGSEGV, Segmentation fault.
+    <function called from gdb>
+    The program being debugged stopped while in a function called from GDB.
+    When the function (detach) is done executing, GDB will silently
+    stop (instead of continuing to evaluate the expression containing
+    the function call).
+    (gdb) call detach(1980)
+    $15 = 0
 
 
   The first detach segfaults for some reason, and the second one
@@ -3112,7 +2974,7 @@
 
 
   Now I detach from the signal thread, attach to the fsck thread, and
-  look at its stack:
+  look at its stack::
 
 
        (gdb) det
@@ -3152,14 +3014,14 @@
 
 
 
-  The interesting things here are :
+  The interesting things here are:
 
-  o  There are two segfaults on this stack (frames 9 and 14)
+  -  There are two segfaults on this stack (frames 9 and 14)
 
-  o  The first faulting address (frame 11) is 0x50000800
+  -  The first faulting address (frame 11) is 0x50000800::
 
-  (gdb) p (void *)1342179328
-  $16 = (void *) 0x50000800
+	(gdb) p (void *)1342179328
+	$16 = (void *) 0x50000800
 
 
 
@@ -3175,7 +3037,7 @@
 
   However, the more immediate problem is that second segfault and I'm
   going to concentrate on that.  First, I want to see where the fault
-  happened, so I have to go look at the sigcontent struct in frame 8:
+  happened, so I have to go look at the sigcontent struct in frame 8::
 
 
 
@@ -3211,7 +3073,7 @@
 
 
 
-  That's not very useful, so I'll try a more manual method:
+  That's not very useful, so I'll try a more manual method::
 
 
        (gdb) p *((struct sigcontext *) (&sig + 1))
@@ -3224,7 +3086,7 @@
 
 
 
-  The ip is in handle_mm_fault:
+  The ip is in handle_mm_fault::
 
 
        (gdb) p (void *)268480945
@@ -3236,7 +3098,7 @@
 
 
 
-  Specifically, it's in pte_alloc:
+  Specifically, it's in pte_alloc::
 
 
        (gdb) i line *$20
@@ -3249,7 +3111,7 @@
 
 
   To find where in handle_mm_fault this is, I'll jump forward in the
-  code until I see an address in that procedure:
+  code until I see an address in that procedure::
 
 
 
@@ -3286,21 +3148,21 @@
 
 
   Something is apparently wrong with the page tables or vma_structs, so
-  lets go back to frame 11 and have a look at them:
+  lets go back to frame 11 and have a look at them::
 
 
 
-  #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50
-  50        handle_mm_fault(current, vma, address, is_write);
-  (gdb) call pgd_offset_proc(vma->vm_mm, address)
-  $22 = (pgd_t *) 0x80a548c
+    #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50
+    50        handle_mm_fault(current, vma, address, is_write);
+    (gdb) call pgd_offset_proc(vma->vm_mm, address)
+    $22 = (pgd_t *) 0x80a548c
 
 
 
 
 
   That's pretty bogus.  Page tables aren't supposed to be in process
-  text or data areas.  Let's see what's in the vma:
+  text or data areas.  Let's see what's in the vma::
 
 
        (gdb) p *vma
@@ -3325,12 +3187,9 @@
 
 
 
-
-
   This also pretty bogus.  With all of the 0x80xxxxx and 0xaffffxxx
   addresses, this is looking like a stack was plonked down on top of
-  these structures.  Maybe it's a stack overflow from the next page:
-
+  these structures.  Maybe it's a stack overflow from the next page::
 
 
        (gdb) p vma
@@ -3338,52 +3197,36 @@
 
 
 
-
-
   That's towards the lower quarter of the page, so that would have to
-  have been pretty heavy stack overflow:
+  have been pretty heavy stack overflow::
 
 
-
-
-
-
-
-
-
-
-
-
-
-
-  (gdb) x/100x $25
-  0x507d2434:     0x507d2434      0x00000000      0x08048000      0x080a4f8c
-  0x507d2444:     0x00000000      0x080a79e0      0x080a8c94      0x080d1000
-  0x507d2454:     0xaffffdb0      0xaffffe63      0xaffffe7a      0xaffffe7a
-  0x507d2464:     0xafffffec      0x00000062      0x0000008a      0x00000000
-  0x507d2474:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2484:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2494:     0x00000000      0x00000000      0x507d2fe0      0x00000000
-  0x507d24a4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d24b4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d24c4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d24d4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d24e4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d24f4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2504:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2514:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2524:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2534:     0x00000000      0x00000000      0x507d25dc      0x00000000
-  0x507d2544:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2554:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2564:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2574:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2584:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d2594:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d25a4:     0x00000000      0x00000000      0x00000000      0x00000000
-  0x507d25b4:     0x00000000      0x00000000      0x00000000      0x00000000
-
-
+    (gdb) x/100x $25
+    0x507d2434:     0x507d2434      0x00000000      0x08048000      0x080a4f8c
+    0x507d2444:     0x00000000      0x080a79e0      0x080a8c94      0x080d1000
+    0x507d2454:     0xaffffdb0      0xaffffe63      0xaffffe7a      0xaffffe7a
+    0x507d2464:     0xafffffec      0x00000062      0x0000008a      0x00000000
+    0x507d2474:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2484:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2494:     0x00000000      0x00000000      0x507d2fe0      0x00000000
+    0x507d24a4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d24b4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d24c4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d24d4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d24e4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d24f4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2504:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2514:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2524:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2534:     0x00000000      0x00000000      0x507d25dc      0x00000000
+    0x507d2544:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2554:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2564:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2574:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2584:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d2594:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d25a4:     0x00000000      0x00000000      0x00000000      0x00000000
+    0x507d25b4:     0x00000000      0x00000000      0x00000000      0x00000000
 
 
 
@@ -3399,65 +3242,53 @@
   on will be somewhat clearer.
 
 
-  12.2.  Episode 2: The case of the hung fsck
+12.2.  Episode 2: The case of the hung fsck
+-------------------------------------------
 
   After setting a trap in the SEGV handler for accesses to the signal
   thread's stack, I reran the kernel.
 
 
-  fsck hung again, this time by hitting the trap:
+  fsck hung again, this time by hitting the trap::
 
 
 
+    Setting hostname uml                            [ OK ]
+    Checking root filesystem
+    /dev/fhd0 contains a file system with errors, check forced.
+    Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
 
+    /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
+	    (i.e., without -a or -p options)
+    [ FAILED ]
 
+    *** An error occurred during the file system check.
+    *** Dropping you to a shell; the system will reboot
+    *** when you leave the shell.
+    Give root password for maintenance
+    (or type Control-D for normal startup):
 
+    [root@uml /root]# fsck -y /dev/fhd0
+    fsck -y /dev/fhd0
+    Parallelizing fsck version 1.14 (9-Jan-1999)
+    e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
+    /dev/fhd0 contains a file system with errors, check forced.
+    Pass 1: Checking inodes, blocks, and sizes
+    Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.  Ignore error? yes
 
+    Pass 2: Checking directory structure
+    Error reading block 49405 (Attempt to read block from filesystem resulted in short read).  Ignore error? yes
 
+    Directory inode 11858, block 0, offset 0: directory corrupted
+    Salvage? yes
 
+    Missing '.' in directory inode 11858.
+    Fix? yes
 
+    Missing '..' in directory inode 11858.
+    Fix? yes
 
-
-
-
-
-
-  Setting hostname uml                            [ OK ]
-  Checking root filesystem
-  /dev/fhd0 contains a file system with errors, check forced.
-  Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
-
-  /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
-          (i.e., without -a or -p options)
-  [ FAILED ]
-
-  *** An error occurred during the file system check.
-  *** Dropping you to a shell; the system will reboot
-  *** when you leave the shell.
-  Give root password for maintenance
-  (or type Control-D for normal startup):
-
-  [root@uml /root]# fsck -y /dev/fhd0
-  fsck -y /dev/fhd0
-  Parallelizing fsck version 1.14 (9-Jan-1999)
-  e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
-  /dev/fhd0 contains a file system with errors, check forced.
-  Pass 1: Checking inodes, blocks, and sizes
-  Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.  Ignore error? yes
-
-  Pass 2: Checking directory structure
-  Error reading block 49405 (Attempt to read block from filesystem resulted in short read).  Ignore error? yes
-
-  Directory inode 11858, block 0, offset 0: directory corrupted
-  Salvage? yes
-
-  Missing '.' in directory inode 11858.
-  Fix? yes
-
-  Missing '..' in directory inode 11858.
-  Fix? yes
-
-  Untested (4127) [100fe44c]: trap_kern.c line 31
+    Untested (4127) [100fe44c]: trap_kern.c line 31
 
 
 
@@ -3465,7 +3296,7 @@
 
   I need to get the signal thread to detach from pid 4127 so that I can
   attach to it with gdb.  This is done by sending it a SIGUSR1, which is
-  caught by the signal thread, which detaches the process:
+  caught by the signal thread, which detaches the process::
 
 
        kill -USR1 4127
@@ -3474,31 +3305,20 @@
 
 
 
-  Now I can run gdb on it:
+  Now I can run gdb on it::
 
 
-
-
-
-
-
-
-
-
-
-
-
-  ~/linux/2.3.26/um 1034: gdb linux
-  GNU gdb 4.17.0.11 with Linux support
-  Copyright 1998 Free Software Foundation, Inc.
-  GDB is free software, covered by the GNU General Public License, and you are
-  welcome to change it and/or distribute copies of it under certain conditions.
-  Type "show copying" to see the conditions.
-  There is absolutely no warranty for GDB.  Type "show warranty" for details.
-  This GDB was configured as "i386-redhat-linux"...
-  (gdb) att 4127
-  Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127
-  0x10075891 in __libc_nanosleep ()
+    ~/linux/2.3.26/um 1034: gdb linux
+    GNU gdb 4.17.0.11 with Linux support
+    Copyright 1998 Free Software Foundation, Inc.
+    GDB is free software, covered by the GNU General Public License, and you are
+    welcome to change it and/or distribute copies of it under certain conditions.
+    Type "show copying" to see the conditions.
+    There is absolutely no warranty for GDB.  Type "show warranty" for details.
+    This GDB was configured as "i386-redhat-linux"...
+    (gdb) att 4127
+    Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127
+    0x10075891 in __libc_nanosleep ()
 
 
 
@@ -3506,7 +3326,7 @@
 
   The backtrace shows that it was in a write and that the fault address
   (address in frame 3) is 0x50000800, which is right in the middle of
-  the signal thread's stack page:
+  the signal thread's stack page::
 
 
        (gdb) bt
@@ -3540,58 +3360,48 @@
 
 
 
-
-
   Going up the stack to the segv_handler frame and looking at where in
   the code the access happened shows that it happened near line 110 of
-  block_dev.c:
+  block_dev.c::
 
 
 
-
-
-
-
-
-
-  (gdb) up
-  #1  0x1007584d in __sleep (seconds=1000000)
-      at ../sysdeps/unix/sysv/linux/sleep.c:78
-  ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory.
-  (gdb)
-  #2  0x1006ce9a in stop () at user_util.c:191
-  191       while(1) sleep(1000000);
-  (gdb)
-  #3  0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31
-  31          KERN_UNTESTED();
-  (gdb)
-  #4  0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
-  174       segv(sc->cr2, sc->err & 2);
-  (gdb) p *sc
-  $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43,
-    __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484,
-    esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14,
-    err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070,
-    esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0,
-    cr2 = 1342179328}
-  (gdb) p (void *)268550834
-  $2 = (void *) 0x1001c2b2
-  (gdb) i sym $2
-  block_write + 1090 in section .text
-  (gdb) i line *$2
-  Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h"
-     starts at address 0x1001c2a1 <block_write+1073>
-     and ends at 0x1001c2bf <block_write+1103>.
-  (gdb) i line *0x1001c2c0
-  Line 110 of "block_dev.c" starts at address 0x1001c2bf <block_write+1103>
-     and ends at 0x1001c2e3 <block_write+1139>.
-
-
+    (gdb) up
+    #1  0x1007584d in __sleep (seconds=1000000)
+	at ../sysdeps/unix/sysv/linux/sleep.c:78
+    ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory.
+    (gdb)
+    #2  0x1006ce9a in stop () at user_util.c:191
+    191       while(1) sleep(1000000);
+    (gdb)
+    #3  0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31
+    31          KERN_UNTESTED();
+    (gdb)
+    #4  0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
+    174       segv(sc->cr2, sc->err & 2);
+    (gdb) p *sc
+    $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43,
+	__dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484,
+	esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14,
+	err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070,
+	esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0,
+	cr2 = 1342179328}
+    (gdb) p (void *)268550834
+    $2 = (void *) 0x1001c2b2
+    (gdb) i sym $2
+    block_write + 1090 in section .text
+    (gdb) i line *$2
+    Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h"
+	starts at address 0x1001c2a1 <block_write+1073>
+	and ends at 0x1001c2bf <block_write+1103>.
+    (gdb) i line *0x1001c2c0
+    Line 110 of "block_dev.c" starts at address 0x1001c2bf <block_write+1103>
+	and ends at 0x1001c2e3 <block_write+1139>.
 
 
 
   Looking at the source shows that the fault happened during a call to
-  copy_from_user to copy the data into the kernel:
+  copy_from_user to copy the data into the kernel::
 
 
        107             count -= chars;
@@ -3601,10 +3411,8 @@
 
 
 
-
-
   p is the pointer which must contain 0x50000800, since buf contains
-  0x80b8800 (frame 8 above).  It is defined as:
+  0x80b8800 (frame 8 above).  It is defined as::
 
 
                        p = offset + bh->b_data;
@@ -3615,24 +3423,22 @@
 
   I need to figure out what bh is, and it just so happens that bh is
   passed as an argument to mark_buffer_uptodate and mark_buffer_dirty a
-  few lines later, so I do a little disassembly:
+  few lines later, so I do a little disassembly::
 
 
-
-
-  (gdb) disas 0x1001c2bf 0x1001c2e0
-  Dump of assembler code from 0x1001c2bf to 0x1001c2d0:
-  0x1001c2bf <block_write+1103>:  addl   %eax,0xc(%ebp)
-  0x1001c2c2 <block_write+1106>:  movl   0xfffffdd4(%ebp),%edx
-  0x1001c2c8 <block_write+1112>:  btsl   $0x0,0x18(%edx)
-  0x1001c2cd <block_write+1117>:  btsl   $0x1,0x18(%edx)
-  0x1001c2d2 <block_write+1122>:  sbbl   %ecx,%ecx
-  0x1001c2d4 <block_write+1124>:  testl  %ecx,%ecx
-  0x1001c2d6 <block_write+1126>:  jne    0x1001c2e3 <block_write+1139>
-  0x1001c2d8 <block_write+1128>:  pushl  $0x0
-  0x1001c2da <block_write+1130>:  pushl  %edx
-  0x1001c2db <block_write+1131>:  call   0x1001819c <__mark_buffer_dirty>
-  End of assembler dump.
+    (gdb) disas 0x1001c2bf 0x1001c2e0
+    Dump of assembler code from 0x1001c2bf to 0x1001c2d0:
+    0x1001c2bf <block_write+1103>:  addl   %eax,0xc(%ebp)
+    0x1001c2c2 <block_write+1106>:  movl   0xfffffdd4(%ebp),%edx
+    0x1001c2c8 <block_write+1112>:  btsl   $0x0,0x18(%edx)
+    0x1001c2cd <block_write+1117>:  btsl   $0x1,0x18(%edx)
+    0x1001c2d2 <block_write+1122>:  sbbl   %ecx,%ecx
+    0x1001c2d4 <block_write+1124>:  testl  %ecx,%ecx
+    0x1001c2d6 <block_write+1126>:  jne    0x1001c2e3 <block_write+1139>
+    0x1001c2d8 <block_write+1128>:  pushl  $0x0
+    0x1001c2da <block_write+1130>:  pushl  %edx
+    0x1001c2db <block_write+1131>:  call   0x1001819c <__mark_buffer_dirty>
+    End of assembler dump.
 
 
 
@@ -3640,7 +3446,7 @@
 
   At that point, bh is in %edx (address 0x1001c2da), which is calculated
   at 0x1001c2c2 as %ebp + 0xfffffdd4, so I figure exactly what that is,
-  taking %ebp from the sigcontext_struct above:
+  taking %ebp from the sigcontext_struct above::
 
 
        (gdb) p (void *)1342631484
@@ -3657,7 +3463,7 @@
 
 
   Now, I look at the structure to see what's in it, and particularly,
-  what its b_data field contains:
+  what its b_data field contains::
 
 
        (gdb) p *((struct buffer_head *)0x50100200)
@@ -3682,18 +3488,18 @@
 
   The b_page field is a pointer to the page_struct representing the
   0x50000000 page.  Looking at it shows the kernel's idea of the state
-  of that page:
+  of that page::
 
 
 
-  (gdb) p *$13.b_page
-  $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0,
-    index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = {
-      next = 0x50008460, prev = 0x50019350}, wait = {
-      lock = <optimized out or zero length>, task_list = {next = 0x50004024,
-        prev = 0x50004024}, __magic = 1342193708, __creator = 0},
-    pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280,
-    zone = 0x100c5160}
+    (gdb) p *$13.b_page
+    $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0,
+	index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = {
+	next = 0x50008460, prev = 0x50019350}, wait = {
+	lock = <optimized out or zero length>, task_list = {next = 0x50004024,
+	    prev = 0x50004024}, __magic = 1342193708, __creator = 0},
+	pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280,
+	zone = 0x100c5160}
 
 
 
@@ -3702,7 +3508,7 @@
   Some sanity-checking: the virtual field shows the "virtual" address of
   this page, which in this kernel is the same as its "physical" address,
   and the page_struct itself should be mem_map[0], since it represents
-  the first page of memory:
+  the first page of memory::
 
 
 
@@ -3719,7 +3525,7 @@
 
 
   Now to check out the page_struct itself.  In particular, the flags
-  field shows whether the page is considered free or not:
+  field shows whether the page is considered free or not::
 
 
        (gdb) p (void *)132
@@ -3739,7 +3545,7 @@
 
 
   In my setup_arch procedure, I have the following code which looks just
-  fine:
+  fine::
 
 
 
@@ -3762,7 +3568,7 @@
 
 
   Stepping into init_bootmem, and looking at bootmem_map before looking
-  at what it contains shows the following:
+  at what it contains shows the following::
 
 
 
@@ -3788,18 +3594,20 @@
 
 
 
-  13.  What to do when UML doesn't work
+13.  What to do when UML doesn't work
+=====================================
 
 
 
 
-  13.1.  Strange compilation errors when you build from source
+13.1.  Strange compilation errors when you build from source
+------------------------------------------------------------
 
   As of test11, it is necessary to have "ARCH=um" in the environment or
   on the make command line for all steps in building UML, including
   clean, distclean, or mrproper, config, menuconfig, or xconfig, dep,
   and linux.  If you forget for any of them, the i386 build seems to
-  contaminate the UML build.  If this happens, start from scratch with
+  contaminate the UML build.  If this happens, start from scratch with::
 
 
        host%
@@ -3811,7 +3619,7 @@
   and repeat the build process with ARCH=um on all the steps.
 
 
-  See ``Compiling the kernel and modules''  for more details.
+  See :ref:`Compiling_the_kernel_and_modules`  for more details.
 
 
   Another cause of strange compilation errors is building UML in
@@ -3824,11 +3632,11 @@
 
 
 
-  13.3.  A variety of panics and hangs with /tmp on a reiserfs  filesys-
-  tem
+13.3.  A variety of panics and hangs with /tmp on a reiserfs filesystem
+-----------------------------------------------------------------------
 
   I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27.
-  Panics preceded by
+  Panics preceded by::
 
 
        Detaching pid nnnn
@@ -3854,17 +3662,19 @@
 
 
 
-  13.5.  UML doesn't work when /tmp is an NFS filesystem
+13.5.  UML doesn't work when /tmp is an NFS filesystem
+------------------------------------------------------
 
   This seems to be a similar situation with the ReiserFS problem above.
   Some versions of NFS seems not to handle mmap correctly, which UML
   depends on.  The workaround is have /tmp be a non-NFS directory.
 
 
-  13.6.  UML hangs on boot when compiled with gprof support
+13.6.  UML hangs on boot when compiled with gprof support
+---------------------------------------------------------
 
   If you build UML with gprof support and, early in the boot, it does
-  this
+  this::
 
 
        kernel BUG at page_alloc.c:100!
@@ -3878,10 +3688,11 @@
 
 
 
-  13.7.  syslogd dies with a SIGTERM on startup
+13.7.  syslogd dies with a SIGTERM on startup
+---------------------------------------------
 
   The exact boot error depends on the distribution that you're booting,
-  but Debian produces this:
+  but Debian produces this::
 
 
        /etc/rc2.d/S10sysklogd: line 49:    93 Terminated
@@ -3891,23 +3702,21 @@
 
 
   This is a syslogd bug.  There's a race between a parent process
-  installing a signal handler and its child sending the signal.  See
-  this uml-devel post <http://www.geocrawler.com/lists/3/Source-
-  Forge/709/0/6612801>  for the details.
+  installing a signal handler and its child sending the signal.
 
 
 
-  13.8.  TUN/TAP networking doesn't work on a 2.4 host
+13.8.  TUN/TAP networking doesn't work on a 2.4 host
+----------------------------------------------------
 
-  There are a couple of problems which were
-  <http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed
-  out">  by Tim Robinson <timro at trkr dot net>
+  There are a couple of problems which were reported by
+  Tim Robinson <timro at trkr dot net>
 
-  o  It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
+  -  It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
      The fix is to upgrade to something more recent and then read the
      next item.
 
-  o  If you see
+  -  If you see::
 
 
        File descriptor in bad state
@@ -3921,8 +3730,8 @@
 
 
 
-  13.9.  You can network to the host but not to other machines on the
-  net
+13.9.  You can network to the host but not to other machines on the net
+=======================================================================
 
   If you can connect to the host, and the host can connect to UML, but
   you cannot connect to any other machines, then you may need to enable
@@ -3930,7 +3739,7 @@
   using private IP addresses (192.168.x.x or 10.x.x.x) for host/UML
   networking, rather than the public address space that your host is
   connected to.  UML does not enable IP Masquerading, so you will need
-  to create a static rule to enable it:
+  to create a static rule to enable it::
 
 
        host%
@@ -3944,11 +3753,11 @@
 
 
   Documentation on IP Masquerading, and SNAT, can be found at
-  www.netfilter.org  <http://www.netfilter.org> .
+  http://www.netfilter.org.
 
 
   If you can reach the local net, but not the outside Internet, then
-  that is usually a routing problem.  The UML needs a default route:
+  that is usually a routing problem.  The UML needs a default route::
 
 
        UML#
@@ -3972,7 +3781,8 @@
 
 
 
-  13.10.  I have no root and I want to scream
+13.10.  I have no root and I want to scream
+===========================================
 
   Thanks to Birgit Wahlich for telling me about this strange one.  It
   turns out that there's a limit of six environment variables on the
@@ -3987,14 +3797,16 @@
 
 
 
-  13.11.  UML build conflict between ptrace.h and ucontext.h
+13.11.  UML build conflict between ptrace.h and ucontext.h
+==========================================================
 
   On some older systems, /usr/include/asm/ptrace.h and
   /usr/include/sys/ucontext.h define the same names.  So, when they're
   included together, the defines from one completely mess up the parsing
-  of the other, producing errors like:
+  of the other, producing errors like::
+
        /usr/include/sys/ucontext.h:47: parse error before
-       `10'
+       `10`
 
 
 
@@ -4007,7 +3819,8 @@
 
 
 
-  13.12.  The UML BogoMips is exactly half the host's BogoMips
+13.12.  The UML BogoMips is exactly half the host's BogoMips
+------------------------------------------------------------
 
   On i386 kernels, there are two ways of running the loop that is used
   to calculate the BogoMips rating, using the TSC if it's there or using
@@ -4019,15 +3832,17 @@
 
 
 
-  13.13.  When you run UML, it immediately segfaults
+13.13.  When you run UML, it immediately segfaults
+--------------------------------------------------
 
   If the host is configured with the 2G/2G address space split, that's
-  why.  See ``UML on 2G/2G hosts''  for the details on getting UML to
+  why.  See ref:`UML_on_2G/2G_hosts`  for the details on getting UML to
   run on your host.
 
 
 
-  13.14.  xterms appear, then immediately disappear
+13.14.  xterms appear, then immediately disappear
+-------------------------------------------------
 
   If you're running an up to date kernel with an old release of
   uml_utilities, the port-helper program will not work properly, so
@@ -4039,7 +3854,8 @@
 
 
 
-  13.15.  Any other panic, hang, or strange behavior
+13.15.  Any other panic, hang, or strange behavior
+--------------------------------------------------
 
   If you're seeing truly strange behavior, such as hangs or panics that
   happen in random places, or you try running the debugger to see what's
@@ -4057,9 +3873,13 @@
   it and that a fix is imminent.
 
 
-  If you want to be super-helpful, read ``Diagnosing Problems'' and
+  If you want to be super-helpful, read :ref:`Diagnosing_Problems` and
   follow the instructions contained therein.
-  14.  Diagnosing Problems
+
+.. _Diagnosing_Problems:
+
+14.  Diagnosing Problems
+========================
 
 
   If you get UML to crash, hang, or otherwise misbehave, you should
@@ -4074,21 +3894,22 @@
 
   For any diagnosis, you're going to need to build a debugging kernel.
   The binaries from this site aren't debuggable.  If you haven't done
-  this before, read about ``Compiling the kernel and modules''  and
-  ``Kernel debugging''  UML first.
+  this before, read about :ref:`Compiling_the_kernel_and_modules`  and
+  :ref:`Kernel_debugging` UML first.
 
 
-  14.1.  Case 1 : Normal kernel panics
+14.1.  Case 1 : Normal kernel panics
+------------------------------------
 
   The most common case is for a normal thread to panic.  To debug this,
   you will need to run it under the debugger (add 'debug' to the command
   line).  An xterm will start up with gdb running inside it.  Continue
-  it when it stops in start_kernel and make it crash.  Now ^C gdb and
+  it when it stops in start_kernel and make it crash.  Now ``^C gdb`` and
 
 
   If the panic was a "Kernel mode fault", then there will be a segv
   frame on the stack and I'm going to want some more information.  The
-  stack might look something like this:
+  stack might look something like this::
 
 
        (UML gdb)  backtrace
@@ -4107,7 +3928,7 @@
 
 
   I'm going to want to see the symbol and line information for the value
-  of ip in the segv frame.  In this case, you would do the following:
+  of ip in the segv frame.  In this case, you would do the following::
 
 
        (UML gdb)  i sym 268849158
@@ -4115,7 +3936,7 @@
 
 
 
-  and
+  and::
 
 
        (UML gdb)  i line *268849158
@@ -4128,7 +3949,8 @@
   to get that information from the faulting ip.
 
 
-  14.2.  Case 2 : Tracing thread panics
+14.2.  Case 2 : Tracing thread panics
+-------------------------------------
 
   The less common and more painful case is when the tracing thread
   panics.  In this case, the kernel debugger will be useless because it
@@ -4136,7 +3958,7 @@
   do is get a backtrace from the tracing thread.  This is done by
   figuring out what its pid is, firing up gdb, and attaching it to that
   pid.  You can figure out the tracing thread pid by looking at the
-  first line of the console output, which will look like this:
+  first line of the console output, which will look like this::
 
 
        tracing thread pid = 15851
@@ -4145,7 +3967,7 @@
 
 
   or by running ps on the host and finding the line that looks like
-  this:
+  this::
 
 
        jdike 15851 4.5 0.4 132568 1104 pts/0 S 21:34 0:05 ./linux [(tracing thread)]
@@ -4164,7 +3986,7 @@
   14.3.  Case 3 : Tracing thread panics caused by other threads
 
   However, there are cases where the misbehavior of another thread
-  caused the problem.  The most common panic of this type is:
+  caused the problem.  The most common panic of this type is::
 
 
        wait_for_stop failed to wait for  <pid>  to stop with  <signal number>
@@ -4177,7 +3999,7 @@
   debugger is defunct and without some fancy footwork, another gdb can't
   attach to it.  So, this is how the fancy footwork goes:
 
-  In a shell:
+  In a shell::
 
 
        host% kill -STOP pid
@@ -4185,7 +4007,7 @@
 
 
 
-  Run gdb on the tracing thread as described in case 2 and do:
+  Run gdb on the tracing thread as described in case 2 and do::
 
 
        (host gdb)  call detach(pid)
@@ -4193,7 +4015,7 @@
 
   If you get a segfault, do it again.  It always works the second time.
 
-  Detach from the tracing thread and attach to that other thread:
+  Detach from the tracing thread and attach to that other thread::
 
 
        (host gdb)  detach
@@ -4209,7 +4031,7 @@
 
 
   If gdb hangs when attaching to that process, go back to a shell and
-  do:
+  do::
 
 
        host%
@@ -4218,7 +4040,7 @@
 
 
 
-  And then get the backtrace:
+  And then get the backtrace::
 
 
        (host gdb)  backtrace
@@ -4227,13 +4049,14 @@
 
 
 
-  14.4.  Case 4 : Hangs
+14.4.  Case 4 : Hangs
+---------------------
 
   Hangs seem to be fairly rare, but they sometimes happen.  When a hang
   happens, we need a backtrace from the offending process.  Run the
   kernel debugger as described in case 1 and get a backtrace.  If the
   current process is not the idle thread, then send in the backtrace.
-  You can tell that it's the idle thread if the stack looks like this:
+  You can tell that it's the idle thread if the stack looks like this::
 
 
        #0  0x100b1401 in __libc_nanosleep ()
@@ -4257,7 +4080,8 @@
 
 
 
-  15.  Thanks
+15.  Thanks
+===========
 
 
   A number of people have helped this project in various ways, and this
@@ -4274,20 +4098,21 @@
   bookkeeping lapses and I forget about contributions.
 
 
-  15.1.  Code and Documentation
+15.1.  Code and Documentation
+-----------------------------
 
   Rusty Russell <rusty at linuxcare.com.au>  -
 
-  o  wrote the  HOWTO <http://user-mode-
-     linux.sourceforge.net/UserModeLinux-HOWTO.html>
+  -  wrote the  HOWTO
+     http://user-mode-linux.sourceforge.net/old/UserModeLinux-HOWTO.html
 
-  o  prodded me into making this project official and putting it on
+  -  prodded me into making this project official and putting it on
      SourceForge
 
-  o  came up with the way cool UML logo <http://user-mode-
-     linux.sourceforge.net/uml-small.png>
+  -  came up with the way cool UML logo
+     http://user-mode-linux.sourceforge.net/uml-small.png
 
-  o  redid the config process
+  -  redid the config process
 
 
   Peter Moulder <reiter at netspace.net.au>  - Fixed my config and build
@@ -4296,34 +4121,32 @@
 
   Bill Stearns <wstearns at pobox.com>  -
 
-  o  HOWTO updates
+  -  HOWTO updates
 
-  o  lots of bug reports
+  -  lots of bug reports
 
-  o  lots of testing
+  -  lots of testing
 
-  o  dedicated a box (uml.ists.dartmouth.edu) to support UML development
+  -  dedicated a box (uml.ists.dartmouth.edu) to support UML development
 
-  o  wrote the mkrootfs script, which allows bootable filesystems of
+  -  wrote the mkrootfs script, which allows bootable filesystems of
      RPM-based distributions to be cranked out
 
-  o  cranked out a large number of filesystems with said script
+  -  cranked out a large number of filesystems with said script
 
 
   Jim Leu <jleu at mindspring.com>  - Wrote the virtual ethernet driver
   and associated usermode tools
 
-  Lars Brinkhoff <http://lars.nocrew.org/>  - Contributed the ptrace
-  proxy from his own  project <http://a386.nocrew.org/> to allow easier
-  kernel debugging
+  Lars Brinkhoff http://lars.nocrew.org/  - Contributed the ptrace
+  proxy from his own  project to allow easier kernel debugging
 
 
   Andrea Arcangeli <andrea at suse.de>  - Redid some of the early boot
   code so that it would work on machines with Large File Support
 
 
-  Chris Emerson <http://www.chiark.greenend.org.uk/~cemerson/>  - Did
-  the first UML port to Linux/ppc
+  Chris Emerson - Did the first UML port to Linux/ppc
 
 
   Harald Welte <laforge at gnumonks.org>  - Wrote the multicast
@@ -4338,7 +4161,7 @@
   wrote the iomem emulation support
 
 
-  Henrik Nordstrom <http://hem.passagen.se/hno/>  - Provided a variety
+  Henrik Nordstrom http://hem.passagen.se/hno/  - Provided a variety
   of patches, fixes, and clues
 
 
@@ -4373,190 +4196,193 @@
   submitted patches for the slip transport and lots of other things.
 
 
-  David Coulson <http://davidcoulson.net>  -
+  David Coulson http://davidcoulson.net  -
 
-  o  Set up the usermodelinux.org <http://usermodelinux.org>  site,
+  -  Set up the http://usermodelinux.org  site,
      which is a great way of keeping the UML user community on top of
      UML goings-on.
 
-  o  Site documentation and updates
+  -  Site documentation and updates
 
-  o  Nifty little UML management daemon  UMLd
-     <http://uml.openconsultancy.com/umld/>
+  -  Nifty little UML management daemon  UMLd
 
-  o  Lots of testing and bug reports
+  -  Lots of testing and bug reports
 
 
 
 
-  15.2.  Flushing out bugs
+15.2.  Flushing out bugs
+------------------------
 
 
 
-  o  Yuri Pudgorodsky
+  -  Yuri Pudgorodsky
 
-  o  Gerald Britton
+  -  Gerald Britton
 
-  o  Ian Wehrman
+  -  Ian Wehrman
 
-  o  Gord Lamb
+  -  Gord Lamb
 
-  o  Eugene Koontz
+  -  Eugene Koontz
 
-  o  John H. Hartman
+  -  John H. Hartman
 
-  o  Anders Karlsson
+  -  Anders Karlsson
 
-  o  Daniel Phillips
+  -  Daniel Phillips
 
-  o  John Fremlin
+  -  John Fremlin
 
-  o  Rainer Burgstaller
+  -  Rainer Burgstaller
 
-  o  James Stevenson
+  -  James Stevenson
 
-  o  Matt Clay
+  -  Matt Clay
 
-  o  Cliff Jefferies
+  -  Cliff Jefferies
 
-  o  Geoff Hoff
+  -  Geoff Hoff
 
-  o  Lennert Buytenhek
+  -  Lennert Buytenhek
 
-  o  Al Viro
+  -  Al Viro
 
-  o  Frank Klingenhoefer
+  -  Frank Klingenhoefer
 
-  o  Livio Baldini Soares
+  -  Livio Baldini Soares
 
-  o  Jon Burgess
+  -  Jon Burgess
 
-  o  Petru Paler
+  -  Petru Paler
 
-  o  Paul
+  -  Paul
 
-  o  Chris Reahard
+  -  Chris Reahard
 
-  o  Sverker Nilsson
+  -  Sverker Nilsson
 
-  o  Gong Su
+  -  Gong Su
 
-  o  johan verrept
+  -  johan verrept
 
-  o  Bjorn Eriksson
+  -  Bjorn Eriksson
 
-  o  Lorenzo Allegrucci
+  -  Lorenzo Allegrucci
 
-  o  Muli Ben-Yehuda
+  -  Muli Ben-Yehuda
 
-  o  David Mansfield
+  -  David Mansfield
 
-  o  Howard Goff
+  -  Howard Goff
 
-  o  Mike Anderson
+  -  Mike Anderson
 
-  o  John Byrne
+  -  John Byrne
 
-  o  Sapan J. Batia
+  -  Sapan J. Batia
 
-  o  Iris Huang
+  -  Iris Huang
 
-  o  Jan Hudec
+  -  Jan Hudec
 
-  o  Voluspa
+  -  Voluspa
 
 
 
 
-  15.3.  Buglets and clean-ups
+15.3.  Buglets and clean-ups
+----------------------------
 
 
 
-  o  Dave Zarzycki
+  -  Dave Zarzycki
 
-  o  Adam Lazur
+  -  Adam Lazur
 
-  o  Boria Feigin
+  -  Boria Feigin
 
-  o  Brian J. Murrell
+  -  Brian J. Murrell
 
-  o  JS
+  -  JS
 
-  o  Roman Zippel
+  -  Roman Zippel
 
-  o  Wil Cooley
+  -  Wil Cooley
 
-  o  Ayelet Shemesh
+  -  Ayelet Shemesh
 
-  o  Will Dyson
+  -  Will Dyson
 
-  o  Sverker Nilsson
+  -  Sverker Nilsson
 
-  o  dvorak
+  -  dvorak
 
-  o  v.naga srinivas
+  -  v.naga srinivas
 
-  o  Shlomi Fish
+  -  Shlomi Fish
 
-  o  Roger Binns
+  -  Roger Binns
 
-  o  johan verrept
+  -  johan verrept
 
-  o  MrChuoi
+  -  MrChuoi
 
-  o  Peter Cleve
+  -  Peter Cleve
 
-  o  Vincent Guffens
+  -  Vincent Guffens
 
-  o  Nathan Scott
+  -  Nathan Scott
 
-  o  Patrick Caulfield
+  -  Patrick Caulfield
 
-  o  jbearce
+  -  jbearce
 
-  o  Catalin Marinas
+  -  Catalin Marinas
 
-  o  Shane Spencer
+  -  Shane Spencer
 
-  o  Zou Min
+  -  Zou Min
 
 
-  o  Ryan Boder
+  -  Ryan Boder
 
-  o  Lorenzo Colitti
+  -  Lorenzo Colitti
 
-  o  Gwendal Grignou
+  -  Gwendal Grignou
 
-  o  Andre' Breiler
+  -  Andre' Breiler
 
-  o  Tsutomu Yasuda
+  -  Tsutomu Yasuda
 
 
 
-  15.4.  Case Studies
+15.4.  Case Studies
+-------------------
 
 
-  o  Jon Wright
+  -  Jon Wright
 
-  o  William McEwan
+  -  William McEwan
 
-  o  Michael Richardson
+  -  Michael Richardson
 
 
 
-  15.5.  Other contributions
+15.5.  Other contributions
+--------------------------
 
 
   Bill Carr <Bill.Carr at compaq.com>  made the Red Hat mkrootfs script
   work with RH 6.2.
 
   Michael Jennings <mikejen at hevanet.com>  sent in some material which
-  is now gracing the top of the  index  page <http://user-mode-
-  linux.sourceforge.net/>  of this site.
+  is now gracing the top of the  index  page
+  http://user-mode-linux.sourceforge.net/  of this site.
 
-  SGI <http://www.sgi.com>  (and more specifically Ralf Baechle <ralf at
-  uni-koblenz.de> ) gave me an account on oss.sgi.com
-  <http://www.oss.sgi.com> .  The bandwidth there made it possible to
+  SGI (and more specifically Ralf Baechle <ralf at
+  uni-koblenz.de> ) gave me an account on oss.sgi.com.
+  The bandwidth there made it possible to
   produce most of the filesystems available on the project download
   page.
 
@@ -4573,17 +4399,5 @@
 
   Chris Reahard built a specialized root filesystem for running a DNS
   server jailed inside UML.  It's available from the download
-  <http://user-mode-linux.sourceforge.net/dl-sf.html>  page in the Jail
+  http://user-mode-linux.sourceforge.net/old/dl-sf.html  page in the Jail
   Filesystems section.
-
-
-
-
-
-
-
-
-
-
-
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 38fe2f3..be029c7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2796,11 +2796,11 @@
 
 ATHEROS 71XX/9XXX GPIO DRIVER
 M:	Alban Bedel <albeu@free.fr>
+S:	Maintained
 W:	https://github.com/AlbanBedel/linux
 T:	git git://github.com/AlbanBedel/linux
-S:	Maintained
-F:	drivers/gpio/gpio-ath79.c
 F:	Documentation/devicetree/bindings/gpio/gpio-ath79.txt
+F:	drivers/gpio/gpio-ath79.c
 
 ATHEROS 71XX/9XXX USB PHY DRIVER
 M:	Alban Bedel <albeu@free.fr>
@@ -3422,8 +3422,8 @@
 M:	Gregory Fong <gregory.0xf0@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 S:	Supported
-F:	drivers/gpio/gpio-brcmstb.c
 F:	Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
+F:	drivers/gpio/gpio-brcmstb.c
 
 BROADCOM BRCMSTB I2C DRIVER
 M:	Kamal Dasu <kdasu.kdev@gmail.com>
@@ -3481,8 +3481,8 @@
 M:	Ray Jui <rjui@broadcom.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 S:	Supported
-F:	drivers/gpio/gpio-bcm-kona.c
 F:	Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt
+F:	drivers/gpio/gpio-bcm-kona.c
 
 BROADCOM NETXTREME-E ROCE DRIVER
 M:	Selvin Xavier <selvin.xavier@broadcom.com>
@@ -3597,8 +3597,8 @@
 
 BT8XXGPIO DRIVER
 M:	Michael Buesch <m@bues.ch>
-W:	http://bu3sch.de/btgpio.php
 S:	Maintained
+W:	http://bu3sch.de/btgpio.php
 F:	drivers/gpio/gpio-bt8xx.c
 
 BTRFS FILE SYSTEM
@@ -5932,12 +5932,12 @@
 F:	drivers/media/dvb-frontends/ec100*
 
 ECRYPT FILE SYSTEM
-M:	Tyler Hicks <tyhicks@canonical.com>
+M:	Tyler Hicks <code@tyhicks.com>
 L:	ecryptfs@vger.kernel.org
 W:	http://ecryptfs.org
 W:	https://launchpad.net/ecryptfs
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs.git
-S:	Supported
+S:	Odd Fixes
 F:	Documentation/filesystems/ecryptfs.txt
 F:	fs/ecryptfs/
 
@@ -7143,18 +7143,18 @@
 M:	Linus Walleij <linus.walleij@linaro.org>
 M:	Bartosz Golaszewski <bgolaszewski@baylibre.com>
 L:	linux-gpio@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
+F:	Documentation/ABI/obsolete/sysfs-gpio
+F:	Documentation/ABI/testing/gpio-cdev
+F:	Documentation/admin-guide/gpio/
 F:	Documentation/devicetree/bindings/gpio/
 F:	Documentation/driver-api/gpio/
-F:	Documentation/admin-guide/gpio/
-F:	Documentation/ABI/testing/gpio-cdev
-F:	Documentation/ABI/obsolete/sysfs-gpio
 F:	drivers/gpio/
+F:	include/asm-generic/gpio.h
 F:	include/linux/gpio/
 F:	include/linux/gpio.h
 F:	include/linux/of_gpio.h
-F:	include/asm-generic/gpio.h
 F:	include/uapi/linux/gpio.h
 F:	tools/gpio/
 
@@ -8055,8 +8055,8 @@
 ICH LPC AND GPIO DRIVER
 M:	Peter Tyser <ptyser@xes-inc.com>
 S:	Maintained
-F:	drivers/mfd/lpc_ich.c
 F:	drivers/gpio/gpio-ich.c
+F:	drivers/mfd/lpc_ich.c
 
 ICY I2C DRIVER
 M:	Max Staudt <max@enpas.org>
@@ -8392,7 +8392,7 @@
 M:	Rodrigo Vivi <rodrigo.vivi@intel.com>
 L:	intel-gfx@lists.freedesktop.org
 W:	https://01.org/linuxgraphics/
-B:	https://01.org/linuxgraphics/documentation/how-report-bugs
+B:	https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 C:	irc://chat.freenode.net/intel-gfx
 Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 T:	git git://anongit.freedesktop.org/drm-intel
@@ -14582,10 +14582,10 @@
 F:	include/media/drv-intf/saa7146*
 
 SAFESETID SECURITY MODULE
-M:     Micah Morton <mortonm@chromium.org>
-S:     Supported
-F:     security/safesetid/
-F:     Documentation/admin-guide/LSM/SafeSetID.rst
+M:	Micah Morton <mortonm@chromium.org>
+S:	Supported
+F:	security/safesetid/
+F:	Documentation/admin-guide/LSM/SafeSetID.rst
 
 SAMSUNG AUDIO (ASoC) DRIVERS
 M:	Krzysztof Kozlowski <krzk@kernel.org>
@@ -16075,8 +16075,8 @@
 SYNOPSYS CREG GPIO DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
 S:	Maintained
-F:	drivers/gpio/gpio-creg-snps.c
 F:	Documentation/devicetree/bindings/gpio/snps,creg-gpio.txt
+F:	drivers/gpio/gpio-creg-snps.c
 
 SYNOPSYS DESIGNWARE 8250 UART DRIVER
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
@@ -16087,8 +16087,8 @@
 M:	Hoan Tran <hoan@os.amperecomputing.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
-F:	drivers/gpio/gpio-dwapb.c
 F:	Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
+F:	drivers/gpio/gpio-dwapb.c
 
 SYNOPSYS DESIGNWARE AXI DMAC DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
@@ -16552,8 +16552,8 @@
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Yehezkel Bernat <YehezkelShB@gmail.com>
 L:	linux-usb@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
 F:	Documentation/admin-guide/thunderbolt.rst
 F:	drivers/thunderbolt/
 F:	include/linux/thunderbolt.h
@@ -17392,11 +17392,14 @@
 F:	include/linux/usb.h
 F:	include/linux/usb/
 
-USB TYPEC PI3USB30532 MUX DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+USB TYPEC BUS FOR ALTERNATE MODES
+M:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
-F:	drivers/usb/typec/mux/pi3usb30532.c
+F:	Documentation/ABI/testing/sysfs-bus-typec
+F:	Documentation/driver-api/usb/typec_bus.rst
+F:	drivers/usb/typec/altmodes/
+F:	include/linux/usb/typec_altmode.h
 
 USB TYPEC CLASS
 M:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
@@ -17407,14 +17410,11 @@
 F:	drivers/usb/typec/
 F:	include/linux/usb/typec.h
 
-USB TYPEC BUS FOR ALTERNATE MODES
-M:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
+USB TYPEC PI3USB30532 MUX DRIVER
+M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
-F:	Documentation/ABI/testing/sysfs-bus-typec
-F:	Documentation/driver-api/usb/typec_bus.rst
-F:	drivers/usb/typec/altmodes/
-F:	include/linux/usb/typec_altmode.h
+F:	drivers/usb/typec/mux/pi3usb30532.c
 
 USB TYPEC PORT CONTROLLER DRIVERS
 M:	Guenter Roeck <linux@roeck-us.net>
@@ -18414,8 +18414,8 @@
 M:	Semi Malinen <semi.malinen@ge.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
-F:	drivers/gpio/gpio-xra1403.c
 F:	Documentation/devicetree/bindings/gpio/gpio-xra1403.txt
+F:	drivers/gpio/gpio-xra1403.c
 
 XTENSA XTFPGA PLATFORM SUPPORT
 M:	Max Filippov <jcmvbkbc@gmail.com>
diff --git a/Makefile b/Makefile
index 84b7184..aab38cb 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
diff --git a/arch/arm/boot/dts/stih410-b2260.dts b/arch/arm/boot/dts/stih410-b2260.dts
index 4fbd8e9..e2bb597 100644
--- a/arch/arm/boot/dts/stih410-b2260.dts
+++ b/arch/arm/boot/dts/stih410-b2260.dts
@@ -178,9 +178,6 @@
 			phy-mode = "rgmii";
 			pinctrl-0 = <&pinctrl_rgmii1 &pinctrl_rgmii1_mdio_1>;
 
-			snps,phy-bus-name = "stmmac";
-			snps,phy-bus-id = <0>;
-			snps,phy-addr = <0>;
 			snps,reset-gpio = <&pio0 7 0>;
 			snps,reset-active-low;
 			snps,reset-delays-us = <0 10000 1000000>;
diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi
index 60e1104..d051f08 100644
--- a/arch/arm/boot/dts/stihxxx-b2120.dtsi
+++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi
@@ -46,7 +46,7 @@
 			/* DAC */
 			format = "i2s";
 			mclk-fs = <256>;
-			frame-inversion = <1>;
+			frame-inversion;
 			cpu {
 				sound-dai = <&sti_uni_player2>;
 			};
diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig
index 622436f..f56ac39 100644
--- a/arch/arm/configs/am200epdkit_defconfig
+++ b/arch/arm/configs/am200epdkit_defconfig
@@ -11,8 +11,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_ARCH_GUMSTIX=y
 CONFIG_PCCARD=y
diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig
index f53634a..6ea7daf 100644
--- a/arch/arm/configs/axm55xx_defconfig
+++ b/arch/arm/configs/axm55xx_defconfig
@@ -25,7 +25,6 @@
 CONFIG_PROFILING=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
-# CONFIG_IOSCHED_DEADLINE is not set
 CONFIG_ARCH_AXXIA=y
 CONFIG_GPIO_PCA953X=y
 CONFIG_ARM_LPAE=y
diff --git a/arch/arm/configs/clps711x_defconfig b/arch/arm/configs/clps711x_defconfig
index c255dab..63a153f 100644
--- a/arch/arm/configs/clps711x_defconfig
+++ b/arch/arm/configs/clps711x_defconfig
@@ -7,7 +7,6 @@
 CONFIG_SLOB=y
 CONFIG_JUMP_LABEL=y
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_CLPS711X=y
 CONFIG_ARCH_AUTCPU12=y
 CONFIG_ARCH_CDB89712=y
diff --git a/arch/arm/configs/cns3420vb_defconfig b/arch/arm/configs/cns3420vb_defconfig
index 89df0a5..66a80b4 100644
--- a/arch/arm/configs/cns3420vb_defconfig
+++ b/arch/arm/configs/cns3420vb_defconfig
@@ -17,7 +17,7 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
-CONFIG_IOSCHED_CFQ=m
+CONFIG_IOSCHED_BFQ=m
 CONFIG_ARCH_MULTI_V6=y
 #CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_CNS3XXX=y
diff --git a/arch/arm/configs/colibri_pxa300_defconfig b/arch/arm/configs/colibri_pxa300_defconfig
index 446134c..0dae3b1 100644
--- a/arch/arm/configs/colibri_pxa300_defconfig
+++ b/arch/arm/configs/colibri_pxa300_defconfig
@@ -43,7 +43,6 @@
 CONFIG_USB_MON=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
-# CONFIG_MMC_BLOCK_BOUNCE is not set
 CONFIG_MMC_PXA=y
 CONFIG_EXT3_FS=y
 CONFIG_NFS_FS=y
diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig
index e6df11e..36384fd 100644
--- a/arch/arm/configs/collie_defconfig
+++ b/arch/arm/configs/collie_defconfig
@@ -7,8 +7,6 @@
 # CONFIG_BASE_FULL is not set
 # CONFIG_EPOLL is not set
 CONFIG_SLOB=y
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_SA1100=y
 CONFIG_SA1100_COLLIE=y
 CONFIG_PCCARD=y
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 231f897..b5ba8d7 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -15,8 +15,6 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_MULTIPLATFORM=y
 CONFIG_ARCH_MULTI_V7=n
 CONFIG_ARCH_MULTI_V5=y
diff --git a/arch/arm/configs/efm32_defconfig b/arch/arm/configs/efm32_defconfig
index 10ea925..46213f0 100644
--- a/arch/arm/configs/efm32_defconfig
+++ b/arch/arm/configs/efm32_defconfig
@@ -12,8 +12,6 @@
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_MMU is not set
 CONFIG_ARM_SINGLE_ARMV7M=y
 CONFIG_ARCH_EFM32=y
diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig
index ef2d2a8..cd16fb6 100644
--- a/arch/arm/configs/ep93xx_defconfig
+++ b/arch/arm/configs/ep93xx_defconfig
@@ -11,7 +11,6 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_EP93XX=y
 CONFIG_CRUNCH=y
 CONFIG_MACH_ADSSPHERE=y
diff --git a/arch/arm/configs/eseries_pxa_defconfig b/arch/arm/configs/eseries_pxa_defconfig
index 56452fa..046f4dc 100644
--- a/arch/arm/configs/eseries_pxa_defconfig
+++ b/arch/arm/configs/eseries_pxa_defconfig
@@ -9,8 +9,6 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_ARCH_PXA_ESERIES=y
 # CONFIG_ARM_THUMB is not set
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index 4e28771..bd7b7f9 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -14,7 +14,6 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_PXA_EZX=y
 CONFIG_NO_HZ=y
diff --git a/arch/arm/configs/h3600_defconfig b/arch/arm/configs/h3600_defconfig
index 4d91e41..c02b3e4 100644
--- a/arch/arm/configs/h3600_defconfig
+++ b/arch/arm/configs/h3600_defconfig
@@ -5,8 +5,6 @@
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_SA1100=y
 CONFIG_SA1100_H3600=y
 CONFIG_PCCARD=y
diff --git a/arch/arm/configs/h5000_defconfig b/arch/arm/configs/h5000_defconfig
index 3946c60..f5a338f 100644
--- a/arch/arm/configs/h5000_defconfig
+++ b/arch/arm/configs/h5000_defconfig
@@ -10,7 +10,6 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_MACH_H5000=y
 CONFIG_AEABI=y
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 770469f..05c5515 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -13,7 +13,6 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_MACH_INTELMOTE2=y
 CONFIG_NO_HZ=y
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index 2b2d617..3df90fc 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -32,8 +32,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig
index e518168..be882ea 100644
--- a/arch/arm/configs/lpc18xx_defconfig
+++ b/arch/arm/configs/lpc18xx_defconfig
@@ -1,4 +1,3 @@
-CONFIG_CROSS_COMPILE="arm-linux-gnueabihf-"
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
 CONFIG_BLK_DEV_INITRD=y
@@ -28,10 +27,7 @@
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
-# CONFIG_LBDAF is not set
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_BINFMT_FLAT=y
 CONFIG_BINFMT_ZFLAT=y
 CONFIG_BINFMT_SHARED_FLAT=y
diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig
index e6486c9..d2e684f 100644
--- a/arch/arm/configs/magician_defconfig
+++ b/arch/arm/configs/magician_defconfig
@@ -9,8 +9,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_MACH_H4700=y
 CONFIG_MACH_MAGICIAN=y
diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig
index 45d2719..6834e97 100644
--- a/arch/arm/configs/moxart_defconfig
+++ b/arch/arm/configs/moxart_defconfig
@@ -15,7 +15,6 @@
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
 CONFIG_ARCH_MULTI_V4=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_MOXART=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index 2773899..a9c6f32 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -25,8 +25,6 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_BLK_DEV_INTEGRITY=y
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 0c43c58..3b6e745 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -18,8 +18,6 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_OMAP=y
 CONFIG_ARCH_OMAP1=y
 CONFIG_OMAP_RESET_CLOCKS=y
diff --git a/arch/arm/configs/palmz72_defconfig b/arch/arm/configs/palmz72_defconfig
index 4a3fd82..b47c8ab 100644
--- a/arch/arm/configs/palmz72_defconfig
+++ b/arch/arm/configs/palmz72_defconfig
@@ -7,8 +7,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_ARCH_PXA_PALM=y
 # CONFIG_MACH_PALMTX is not set
diff --git a/arch/arm/configs/pcm027_defconfig b/arch/arm/configs/pcm027_defconfig
index a8c5322..e97a158 100644
--- a/arch/arm/configs/pcm027_defconfig
+++ b/arch/arm/configs/pcm027_defconfig
@@ -13,8 +13,6 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_MACH_PCM027=y
 CONFIG_MACH_PCM990_BASEBOARD=y
diff --git a/arch/arm/configs/pleb_defconfig b/arch/arm/configs/pleb_defconfig
index f0541b0..2170148 100644
--- a/arch/arm/configs/pleb_defconfig
+++ b/arch/arm/configs/pleb_defconfig
@@ -6,8 +6,6 @@
 # CONFIG_HOTPLUG is not set
 # CONFIG_SHMEM is not set
 CONFIG_MODULES=y
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_SA1100=y
 CONFIG_SA1100_PLEB=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig
index 8a056cc..70e2c74 100644
--- a/arch/arm/configs/realview_defconfig
+++ b/arch/arm/configs/realview_defconfig
@@ -8,7 +8,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_MULTI_V6=y
 CONFIG_ARCH_REALVIEW=y
 CONFIG_MACH_REALVIEW_EB=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index 27f6135..bab7861 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -14,8 +14,6 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_AT91=y
 CONFIG_SOC_SAMA5D2=y
 CONFIG_SOC_SAMA5D3=y
@@ -182,7 +180,6 @@
 CONFIG_USB_ATMEL_USBA=y
 CONFIG_USB_G_SERIAL=y
 CONFIG_MMC=y
-# CONFIG_MMC_BLOCK_BOUNCE is not set
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_OF_AT91=y
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index 152321d..551db328 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -14,8 +14,6 @@
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_MMU is not set
 CONFIG_ARCH_STM32=y
 CONFIG_CPU_V7M_NUM_IRQ=240
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 3f5d727..e9fb573 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -85,6 +85,7 @@
 CONFIG_AXP20X_POWER=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
+CONFIG_SUN8I_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
 CONFIG_MFD_AC100=y
diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig
index 8223397..543f073 100644
--- a/arch/arm/configs/u300_defconfig
+++ b/arch/arm/configs/u300_defconfig
@@ -11,7 +11,6 @@
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_U300=y
 CONFIG_MACH_U300_SPIDUMMY=y
@@ -46,7 +45,6 @@
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
-# CONFIG_MMC_BLOCK_BOUNCE is not set
 CONFIG_MMC_ARMMMCI=y
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig
index 2575355..c01baf7 100644
--- a/arch/arm/configs/vexpress_defconfig
+++ b/arch/arm/configs/vexpress_defconfig
@@ -15,8 +15,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_VEXPRESS_DCSCB=y
 CONFIG_ARCH_VEXPRESS_TC2_PM=y
diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig
index 2ff1616..989599c 100644
--- a/arch/arm/configs/viper_defconfig
+++ b/arch/arm/configs/viper_defconfig
@@ -9,7 +9,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_ARCH_VIPER=y
 CONFIG_IWMMXT=y
diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig
index aa3023c..d3b98c4 100644
--- a/arch/arm/configs/zeus_defconfig
+++ b/arch/arm/configs/zeus_defconfig
@@ -4,7 +4,6 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_PXA=y
 CONFIG_MACH_ARCOM_ZEUS=y
 CONFIG_PCCARD=m
@@ -137,7 +136,6 @@
 CONFIG_USB_G_SERIAL=m
 CONFIG_USB_G_PRINTER=m
 CONFIG_MMC=y
-# CONFIG_MMC_BLOCK_BOUNCE is not set
 CONFIG_MMC_PXA=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=m
diff --git a/arch/arm/configs/zx_defconfig b/arch/arm/configs/zx_defconfig
index 4d2ef78..a046a49 100644
--- a/arch/arm/configs/zx_defconfig
+++ b/arch/arm/configs/zx_defconfig
@@ -16,7 +16,6 @@
 CONFIG_PERF_EVENTS=y
 CONFIG_SLAB=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_ZX=y
 CONFIG_SOC_ZX296702=y
 # CONFIG_SWP_EMULATE is not set
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 2a5ff69..10499d4 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -78,13 +78,10 @@
 {
 	unsigned long replaced;
 
-	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
 		old = __opcode_to_mem_thumb32(old);
-		new = __opcode_to_mem_thumb32(new);
-	} else {
+	else
 		old = __opcode_to_mem_arm(old);
-		new = __opcode_to_mem_arm(new);
-	}
 
 	if (validate) {
 		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index d0a05a3..e9e828b 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,10 +16,10 @@
 	unsigned int insn;
 };
 
+#ifdef CONFIG_MMU
 static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
-	__acquires(&patch_lock)
 {
 	unsigned int uintaddr = (uintptr_t) addr;
 	bool module = !core_kernel_text(uintaddr);
@@ -34,8 +34,6 @@
 
 	if (flags)
 		raw_spin_lock_irqsave(&patch_lock, *flags);
-	else
-		__acquire(&patch_lock);
 
 	set_fixmap(fixmap, page_to_phys(page));
 
@@ -43,15 +41,19 @@
 }
 
 static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
-	__releases(&patch_lock)
 {
 	clear_fixmap(fixmap);
 
 	if (flags)
 		raw_spin_unlock_irqrestore(&patch_lock, *flags);
-	else
-		__release(&patch_lock);
 }
+#else
+static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
+{
+	return addr;
+}
+static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { }
+#endif
 
 void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 {
@@ -64,8 +66,6 @@
 
 	if (remap)
 		waddr = patch_map(addr, FIX_TEXT_POKE0, &flags);
-	else
-		__acquire(&patch_lock);
 
 	if (thumb2 && __opcode_is_thumb16(insn)) {
 		*(u16 *)waddr = __opcode_to_mem_thumb16(insn);
@@ -102,8 +102,7 @@
 	if (waddr != addr) {
 		flush_kernel_vmap_range(waddr, twopage ? size / 2 : size);
 		patch_unmap(FIX_TEXT_POKE0, &flags);
-	} else
-		__release(&patch_lock);
+	}
 
 	flush_icache_range((uintptr_t)(addr),
 			   (uintptr_t)(addr) + size);
diff --git a/arch/arm/mach-npcm/Kconfig b/arch/arm/mach-npcm/Kconfig
index 880bc2a..7f7002d 100644
--- a/arch/arm/mach-npcm/Kconfig
+++ b/arch/arm/mach-npcm/Kconfig
@@ -11,7 +11,7 @@
 	depends on ARCH_MULTI_V7
 	select PINCTRL_NPCM7XX
 	select NPCM7XX_TIMER
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select CACHE_L2X0
 	select ARM_GIC
 	select HAVE_ARM_TWD if SMP
diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
index 62ab0d5..335fff7 100644
--- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts
+++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
@@ -161,10 +161,10 @@
 		bus-range = <0x0 0x1>;
 		reg = <0x0 0x40000000 0x0 0x10000000>;
 		ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>;
-		interrupt-map = <0 0 0 1 &gic GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 2 &gic GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 3 &gic GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 4 &gic GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &gic 0 0 GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &gic 0 0 GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &gic 0 0 GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
 		msi-map = <0x0 &its 0x0 0x10000>;
 		iommu-map = <0x0 &smmu 0x0 0x10000>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 0f21288..905109f 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -452,6 +452,7 @@
 CONFIG_CPU_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
 CONFIG_QORIQ_THERMAL=m
+CONFIG_SUN8I_THERMAL=y
 CONFIG_ROCKCHIP_THERMAL=m
 CONFIG_RCAR_THERMAL=y
 CONFIG_RCAR_GEN3_THERMAL=y
@@ -547,6 +548,7 @@
 CONFIG_ROCKCHIP_INNO_HDMI=y
 CONFIG_DRM_RCAR_DU=m
 CONFIG_DRM_SUN4I=m
+CONFIG_DRM_SUN6I_DSI=m
 CONFIG_DRM_SUN8I_DW_HDMI=m
 CONFIG_DRM_SUN8I_MIXER=m
 CONFIG_DRM_MSM=m
@@ -681,7 +683,7 @@
 CONFIG_RTC_DRV_IMX_SC=m
 CONFIG_RTC_DRV_XGENE=y
 CONFIG_DMADEVICES=y
-CONFIG_DMA_BCM2835=m
+CONFIG_DMA_BCM2835=y
 CONFIG_DMA_SUN6I=m
 CONFIG_FSL_EDMA=y
 CONFIG_IMX_SDMA=y
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index b87c6e2..7a6e81ca 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -33,7 +33,6 @@
 
 asmlinkage void enter_from_user_mode(void);
 void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
-void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
@@ -47,7 +46,4 @@
 void do_cp15instr(unsigned int esr, struct pt_regs *regs);
 void do_el0_svc(struct pt_regs *regs);
 void do_el0_svc_compat(struct pt_regs *regs);
-void do_el0_ia_bp_hardening(unsigned long addr,  unsigned int esr,
-			    struct pt_regs *regs);
-
 #endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 102404d..9083d69 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -18,6 +18,10 @@
  * See:
  * https://lore.kernel.org/lkml/20200110100612.GC2827@hirez.programming.kicks-ass.net
  */
-#define vcpu_is_preempted(cpu)	false
+#define vcpu_is_preempted vcpu_is_preempted
+static inline bool vcpu_is_preempted(int cpu)
+{
+	return false;
+}
 
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 53b8a4e..91a8310 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
+#include <asm/archrandom.h>
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/kernel-pgtable.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index bbb0f0c..0062605 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -466,6 +466,13 @@
 	if (unlikely(next->flags & PF_KTHREAD))
 		return;
 
+	/*
+	 * If all CPUs implement the SSBS extension, then we just need to
+	 * context-switch the PSTATE field.
+	 */
+	if (cpu_have_feature(cpu_feature(SSBS)))
+		return;
+
 	/* If the mitigation is enabled, then we leave SSBS clear. */
 	if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
 	    test_tsk_thread_flag(next, TIF_SSBD))
@@ -608,8 +615,6 @@
  * only prevents the tagged address ABI enabling via prctl() and does not
  * disable it for tasks that already opted in to the relaxed ABI.
  */
-static int zero;
-static int one = 1;
 
 static struct ctl_table tagged_addr_sysctl_table[] = {
 	{
@@ -618,8 +623,8 @@
 		.data		= &tagged_addr_disabled,
 		.maxlen		= sizeof(int),
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{ }
 };
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 73f06d4..eebbc8d 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -23,7 +23,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/clocksource.h>
-#include <linux/clk-provider.h>
+#include <linux/of_clk.h>
 #include <linux/acpi.h>
 
 #include <clocksource/arm_arch_timer.h>
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index ed007f4..3f50115 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -15,7 +15,8 @@
 	if (!test_facility(158))
 		return;
 
-	if (uv_call(0, (uint64_t)&uvcb))
+	/* rc==0x100 means that there is additional data we do not process */
+	if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100)
 		return;
 
 	if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 670f14a..6bf3a45 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -155,7 +155,7 @@
 
 static inline unsigned long long get_tod_clock(void)
 {
-	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	char clk[STORE_CLOCK_EXT_SIZE];
 
 	get_tod_clock_ext(clk);
 	return *((unsigned long long *)&clk[1]);
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1f22b6b..39eb276 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,6 +250,7 @@
 	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3be51aa..dff6623 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4765,6 +4765,7 @@
 		break;
 
 	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e1daf41..4814c964 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,17 +40,18 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT,GLM,CNL
+ *			 Available model: SLM,AMT,GLM,CNL,TNT
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
- *						CNL,KBL,CML
+ *						CNL,KBL,CML,TNT
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -60,17 +61,18 @@
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL,TGL
+ *						KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL,KBL,CML,ICL,TGL
+ *						GLM,CNL,KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -87,7 +89,8 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *
  */
@@ -640,8 +643,9 @@
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT,   glm_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
-
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4b94ae4..dc43cc1 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1714,6 +1714,8 @@
 	old = ((s64)(prev_raw_count << shift) >> shift);
 	local64_add(new - old + count * period, &event->count);
 
+	local64_set(&hwc->period_left, -new);
+
 	perf_event_update_userpage(event);
 
 	return 0;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 6f86650..a949f6f 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -75,8 +75,9 @@
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:
-
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4dffbc1..40a0c0f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -781,9 +781,19 @@
 	u64 msr_kvm_poll_control;
 
 	/*
-	 * Indicate whether the access faults on its page table in guest
-	 * which is set when fix page fault and used to detect unhandeable
-	 * instruction.
+	 * Indicates the guest is trying to write a gfn that contains one or
+	 * more of the PTEs used to translate the write itself, i.e. the access
+	 * is changing its own translation in the guest page tables.  KVM exits
+	 * to userspace if emulation of the faulting instruction fails and this
+	 * flag is set, as KVM cannot make forward progress.
+	 *
+	 * If emulation fails for a write to guest page tables, KVM unprotects
+	 * (zaps) the shadow page for the target gfn and resumes the guest to
+	 * retry the non-emulatable instruction (on hardware).  Unprotecting the
+	 * gfn doesn't allow forward progress for a self-changing access because
+	 * doing so also zaps the translation for the gfn, i.e. retrying the
+	 * instruction will hit a !PRESENT fault, which results in a new shadow
+	 * page and sends KVM back to square one.
 	 */
 	bool write_fault_to_shadow_pgtable;
 
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index 4d4f5d9..2305490 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -10,8 +10,6 @@
 
 static enum efi_secureboot_mode get_sb_mode(void)
 {
-	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-	efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
 	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	efi_status_t status;
 	unsigned long size;
@@ -25,7 +23,7 @@
 	}
 
 	/* Get variable contents into buffer */
-	status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
 				  NULL, &size, &secboot);
 	if (status == EFI_NOT_FOUND) {
 		pr_info("ima: secureboot mode disabled\n");
@@ -38,7 +36,7 @@
 	}
 
 	size = sizeof(setupmode);
-	status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
 				  NULL, &size, &setupmode);
 
 	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index eafc631..afcd30d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1080,9 +1080,6 @@
 			result = 1;
 			/* assumes that there are only KVM_APIC_INIT/SIPI */
 			apic->pending_events = (1UL << KVM_APIC_INIT);
-			/* make sure pending_events is visible before sending
-			 * the request */
-			smp_wmb();
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index d55674f..a647601 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -102,6 +102,19 @@
 					      kvm_get_active_pcid(vcpu));
 }
 
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+		       bool prefault);
+
+static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+					u32 err, bool prefault)
+{
+#ifdef CONFIG_RETPOLINE
+	if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault))
+		return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault);
+#endif
+	return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault);
+}
+
 /*
  * Currently, we have two sorts of write-protection, a) the first one
  * write-protects guest page to sync the guest modification, b) another one is
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7011a4e..87e9ba2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4219,8 +4219,8 @@
 }
 EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
-			  bool prefault)
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+		       bool prefault)
 {
 	int max_level;
 
@@ -4925,7 +4925,7 @@
 		return;
 
 	context->mmu_role.as_u64 = new_role.as_u64;
-	context->page_fault = tdp_page_fault;
+	context->page_fault = kvm_tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
 	context->update_pte = nonpaging_update_pte;
@@ -5436,9 +5436,8 @@
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
-					       lower_32_bits(error_code),
-					       false);
+		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
+					  lower_32_bits(error_code), false);
 		WARN_ON(r == RET_PF_INVALID);
 	}
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4e1ef04..e4c8a4c 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -33,7 +33,7 @@
 	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
 	#ifdef CONFIG_X86_64
-	#define PT_MAX_FULL_LEVELS 4
+	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 	#define CMPXCHG cmpxchg
 	#else
 	#define CMPXCHG cmpxchg64
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a3e32d6..bef0ba3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2175,7 +2175,6 @@
 	u32 dummy;
 	u32 eax = 1;
 
-	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
 	svm->virt_spec_ctrl = 0;
 
@@ -2266,6 +2265,7 @@
 	init_vmcb(svm);
 
 	svm_init_osvw(vcpu);
+	vcpu->arch.microcode_version = 0x01000065;
 
 	return 0;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 657c2ed..3589cd3 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -544,7 +544,8 @@
 	}
 }
 
-static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
+{
 	int msr;
 
 	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
@@ -1981,7 +1982,7 @@
 	}
 
 	/*
-	 * Clean fields data can't de used on VMLAUNCH and when we switch
+	 * Clean fields data can't be used on VMLAUNCH and when we switch
 	 * between different L2 guests as KVM keeps a single VMCS12 per L1.
 	 */
 	if (from_launch || evmcs_gpa_changed)
@@ -3575,6 +3576,33 @@
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
 }
 
+/*
+ * Returns true if a debug trap is pending delivery.
+ *
+ * In KVM, debug traps bear an exception payload. As such, the class of a #DB
+ * exception may be inferred from the presence of an exception payload.
+ */
+static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.exception.pending &&
+			vcpu->arch.exception.nr == DB_VECTOR &&
+			vcpu->arch.exception.payload;
+}
+
+/*
+ * Certain VM-exits set the 'pending debug exceptions' field to indicate a
+ * recognized #DB (data or single-step) that has yet to be delivered. Since KVM
+ * represents these debug traps with a payload that is said to be compatible
+ * with the 'pending debug exceptions' field, write the payload to the VMCS
+ * field if a VM-exit is delivered before the debug trap.
+ */
+static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
+{
+	if (vmx_pending_dbg_trap(vcpu))
+		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+			    vcpu->arch.exception.payload);
+}
+
 static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3587,6 +3615,7 @@
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		nested_vmx_update_pending_dbg(vcpu);
 		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
 		return 0;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9a66648..3be25ec 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2947,6 +2947,9 @@
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
+	/* Nested EPT currently only supports 4-level walks. */
+	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
+		return 4;
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;
@@ -4238,7 +4241,6 @@
 
 	vmx->msr_ia32_umwait_control = 0;
 
-	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	vmx->hv_deadline_tsc = -1;
 	kvm_set_cr8(vcpu, 0);
@@ -6763,6 +6765,7 @@
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
 
+	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fbabb2f..fb5d64e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -438,6 +438,14 @@
 		 * for #DB exceptions under VMX.
 		 */
 		vcpu->arch.dr6 ^= payload & DR6_RTM;
+
+		/*
+		 * The #DB payload is defined as compatible with the 'pending
+		 * debug exceptions' field under VMX, not DR6. While bit 12 is
+		 * defined in the 'pending debug exceptions' field (enabled
+		 * breakpoint), it is reserved and must be zero in DR6.
+		 */
+		vcpu->arch.dr6 &= ~BIT(12);
 		break;
 	case PF_VECTOR:
 		vcpu->arch.cr2 = payload;
@@ -490,19 +498,7 @@
 		vcpu->arch.exception.error_code = error_code;
 		vcpu->arch.exception.has_payload = has_payload;
 		vcpu->arch.exception.payload = payload;
-		/*
-		 * In guest mode, payload delivery should be deferred,
-		 * so that the L1 hypervisor can intercept #PF before
-		 * CR2 is modified (or intercept #DB before DR6 is
-		 * modified under nVMX).  However, for ABI
-		 * compatibility with KVM_GET_VCPU_EVENTS and
-		 * KVM_SET_VCPU_EVENTS, we can't delay payload
-		 * delivery unless userspace has enabled this
-		 * functionality via the per-VM capability,
-		 * KVM_CAP_EXCEPTION_PAYLOAD.
-		 */
-		if (!vcpu->kvm->arch.exception_payload_enabled ||
-		    !is_guest_mode(vcpu))
+		if (!is_guest_mode(vcpu))
 			kvm_deliver_exception_payload(vcpu);
 		return;
 	}
@@ -2448,7 +2444,7 @@
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
-	WARN_ON(vcpu->hv_clock.system_time < 0);
+	WARN_ON((s64)vcpu->hv_clock.system_time < 0);
 
 	/* If the host uses TSC clocksource, then it is stable */
 	pvclock_flags = 0;
@@ -3796,6 +3792,21 @@
 	process_nmi(vcpu);
 
 	/*
+	 * In guest mode, payload delivery should be deferred,
+	 * so that the L1 hypervisor can intercept #PF before
+	 * CR2 is modified (or intercept #DB before DR6 is
+	 * modified under nVMX). Unless the per-VM capability,
+	 * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of
+	 * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we
+	 * opportunistically defer the exception payload, deliver it if the
+	 * capability hasn't been requested before processing a
+	 * KVM_GET_VCPU_EVENTS.
+	 */
+	if (!vcpu->kvm->arch.exception_payload_enabled &&
+	    vcpu->arch.exception.pending && vcpu->arch.exception.has_payload)
+		kvm_deliver_exception_payload(vcpu);
+
+	/*
 	 * The API doesn't provide the instruction length for software
 	 * exceptions, so don't report them. As long as the guest RIP
 	 * isn't advanced, we should expect to encounter the exception
@@ -8942,7 +8953,6 @@
 
 	kvm_rip_write(vcpu, ctxt->eip);
 	kvm_set_rflags(vcpu, ctxt->eflags);
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
@@ -10182,7 +10192,7 @@
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
+	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
diff --git a/crypto/Kconfig b/crypto/Kconfig
index cdb51d4..c24a474 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -136,8 +136,6 @@
 	  Userspace configuration for cryptographic instantiations such as
 	  cbc(aes).
 
-if CRYPTO_MANAGER2
-
 config CRYPTO_MANAGER_DISABLE_TESTS
 	bool "Disable run-time self tests"
 	default y
@@ -155,8 +153,6 @@
 	  This is intended for developer use only, as these tests take much
 	  longer to run than the normal self tests.
 
-endif	# if CRYPTO_MANAGER2
-
 config CRYPTO_GF128MUL
 	tristate
 
diff --git a/crypto/hash_info.c b/crypto/hash_info.c
index c754cb7..a49ff96 100644
--- a/crypto/hash_info.c
+++ b/crypto/hash_info.c
@@ -26,7 +26,7 @@
 	[HASH_ALGO_TGR_128]	= "tgr128",
 	[HASH_ALGO_TGR_160]	= "tgr160",
 	[HASH_ALGO_TGR_192]	= "tgr192",
-	[HASH_ALGO_SM3_256]	= "sm3-256",
+	[HASH_ALGO_SM3_256]	= "sm3",
 	[HASH_ALGO_STREEBOG_256] = "streebog256",
 	[HASH_ALGO_STREEBOG_512] = "streebog512",
 };
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 88f33c0..ccb3d60 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4436,6 +4436,15 @@
 			.cipher = __VECS(tf_cbc_tv_template)
 		},
 	}, {
+#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390)
+		.alg = "cbc-paes-s390",
+		.fips_allowed = 1,
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aes_cbc_tv_template)
+		}
+	}, {
+#endif
 		.alg = "cbcmac(aes)",
 		.fips_allowed = 1,
 		.test = alg_test_hash,
@@ -4587,6 +4596,15 @@
 			.cipher = __VECS(tf_ctr_tv_template)
 		}
 	}, {
+#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390)
+		.alg = "ctr-paes-s390",
+		.fips_allowed = 1,
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aes_ctr_tv_template)
+		}
+	}, {
+#endif
 		.alg = "cts(cbc(aes))",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
@@ -4879,6 +4897,15 @@
 			.cipher = __VECS(xtea_tv_template)
 		}
 	}, {
+#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390)
+		.alg = "ecb-paes-s390",
+		.fips_allowed = 1,
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aes_tv_template)
+		}
+	}, {
+#endif
 		.alg = "ecdh",
 		.test = alg_test_kpp,
 		.fips_allowed = 1,
@@ -5465,6 +5492,15 @@
 			.cipher = __VECS(tf_xts_tv_template)
 		}
 	}, {
+#if IS_ENABLED(CONFIG_CRYPTO_PAES_S390)
+		.alg = "xts-paes-s390",
+		.fips_allowed = 1,
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = __VECS(aes_xts_tv_template)
+		}
+	}, {
+#endif
 		.alg = "xts4096(paes)",
 		.test = alg_test_null,
 		.fips_allowed = 1,
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index 67f282e..6ad0517 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -101,6 +101,8 @@
 
 acpi_status acpi_hw_enable_all_wakeup_gpes(void);
 
+u8 acpi_hw_check_all_gpes(void);
+
 acpi_status
 acpi_hw_enable_runtime_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 				 struct acpi_gpe_block_info *gpe_block,
diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c
index 8c83d8c..789d5e9 100644
--- a/drivers/acpi/acpica/evevent.c
+++ b/drivers/acpi/acpica/evevent.c
@@ -265,4 +265,49 @@
 		 handler) (acpi_gbl_fixed_event_handlers[event].context));
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_any_fixed_event_status_set
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      TRUE or FALSE
+ *
+ * DESCRIPTION: Checks the PM status register for active fixed events
+ *
+ ******************************************************************************/
+
+u32 acpi_any_fixed_event_status_set(void)
+{
+	acpi_status status;
+	u32 in_status;
+	u32 in_enable;
+	u32 i;
+
+	status = acpi_hw_register_read(ACPI_REGISTER_PM1_ENABLE, &in_enable);
+	if (ACPI_FAILURE(status)) {
+		return (FALSE);
+	}
+
+	status = acpi_hw_register_read(ACPI_REGISTER_PM1_STATUS, &in_status);
+	if (ACPI_FAILURE(status)) {
+		return (FALSE);
+	}
+
+	/*
+	 * Check for all possible Fixed Events and dispatch those that are active
+	 */
+	for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) {
+
+		/* Both the status and enable bits must be on for this event */
+
+		if ((in_status & acpi_gbl_fixed_event_info[i].status_bit_mask) &&
+		    (in_enable & acpi_gbl_fixed_event_info[i].enable_bit_mask)) {
+			return (TRUE);
+		}
+	}
+
+	return (FALSE);
+}
+
 #endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 2c39ff2..f2de66b 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -795,6 +795,38 @@
 
 ACPI_EXPORT_SYMBOL(acpi_enable_all_wakeup_gpes)
 
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_any_gpe_status_set
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Whether or not the status bit is set for any GPE
+ *
+ * DESCRIPTION: Check the status bits of all enabled GPEs and return TRUE if any
+ *              of them is set or FALSE otherwise.
+ *
+ ******************************************************************************/
+u32 acpi_any_gpe_status_set(void)
+{
+	acpi_status status;
+	u8 ret;
+
+	ACPI_FUNCTION_TRACE(acpi_any_gpe_status_set);
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return (FALSE);
+	}
+
+	ret = acpi_hw_check_all_gpes();
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+
+	return (ret);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_any_gpe_status_set)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_install_gpe_block
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 1b4252b..f4c285c 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -446,6 +446,53 @@
 
 /******************************************************************************
  *
+ * FUNCTION:    acpi_hw_get_gpe_block_status
+ *
+ * PARAMETERS:  gpe_xrupt_info      - GPE Interrupt info
+ *              gpe_block           - Gpe Block info
+ *
+ * RETURN:      Success
+ *
+ * DESCRIPTION: Produce a combined GPE status bits mask for the given block.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_hw_get_gpe_block_status(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
+			     struct acpi_gpe_block_info *gpe_block,
+			     void *ret_ptr)
+{
+	struct acpi_gpe_register_info *gpe_register_info;
+	u64 in_enable, in_status;
+	acpi_status status;
+	u8 *ret = ret_ptr;
+	u32 i;
+
+	/* Examine each GPE Register within the block */
+
+	for (i = 0; i < gpe_block->register_count; i++) {
+		gpe_register_info = &gpe_block->register_info[i];
+
+		status = acpi_hw_read(&in_enable,
+				      &gpe_register_info->enable_address);
+		if (ACPI_FAILURE(status)) {
+			continue;
+		}
+
+		status = acpi_hw_read(&in_status,
+				      &gpe_register_info->status_address);
+		if (ACPI_FAILURE(status)) {
+			continue;
+		}
+
+		*ret |= in_enable & in_status;
+	}
+
+	return (AE_OK);
+}
+
+/******************************************************************************
+ *
  * FUNCTION:    acpi_hw_disable_all_gpes
  *
  * PARAMETERS:  None
@@ -510,4 +557,28 @@
 	return_ACPI_STATUS(status);
 }
 
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_check_all_gpes
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Combined status of all GPEs
+ *
+ * DESCRIPTION: Check all enabled GPEs in all GPE blocks and return TRUE if the
+ *              status bit is set for at least one of them of FALSE otherwise.
+ *
+ ******************************************************************************/
+
+u8 acpi_hw_check_all_gpes(void)
+{
+	u8 ret = 0;
+
+	ACPI_FUNCTION_TRACE(acpi_hw_check_all_gpes);
+
+	(void)acpi_ev_walk_gpe_list(acpi_hw_get_gpe_block_status, &ret);
+
+	return (ret != 0);
+}
+
 #endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 08bc975..d1f1cf5 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -179,6 +179,7 @@
 
 static struct acpi_ec *boot_ec;
 static bool boot_ec_is_ecdt = false;
+static struct workqueue_struct *ec_wq;
 static struct workqueue_struct *ec_query_wq;
 
 static int EC_FLAGS_QUERY_HANDSHAKE; /* Needs QR_EC issued when SCI_EVT set */
@@ -469,7 +470,7 @@
 		ec_dbg_evt("Command(%s) submitted/blocked",
 			   acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY));
 		ec->nr_pending_queries++;
-		schedule_work(&ec->work);
+		queue_work(ec_wq, &ec->work);
 	}
 }
 
@@ -535,7 +536,7 @@
 #ifdef CONFIG_PM_SLEEP
 static void __acpi_ec_flush_work(void)
 {
-	flush_scheduled_work(); /* flush ec->work */
+	drain_workqueue(ec_wq); /* flush ec->work */
 	flush_workqueue(ec_query_wq); /* flush queries */
 }
 
@@ -556,8 +557,8 @@
 
 void acpi_ec_flush_work(void)
 {
-	/* Without ec_query_wq there is nothing to flush. */
-	if (!ec_query_wq)
+	/* Without ec_wq there is nothing to flush. */
+	if (!ec_wq)
 		return;
 
 	__acpi_ec_flush_work();
@@ -2107,25 +2108,33 @@
 	.drv.pm = &acpi_ec_pm,
 };
 
-static inline int acpi_ec_query_init(void)
+static void acpi_ec_destroy_workqueues(void)
 {
-	if (!ec_query_wq) {
-		ec_query_wq = alloc_workqueue("kec_query", 0,
-					      ec_max_queries);
-		if (!ec_query_wq)
-			return -ENODEV;
+	if (ec_wq) {
+		destroy_workqueue(ec_wq);
+		ec_wq = NULL;
 	}
-	return 0;
-}
-
-static inline void acpi_ec_query_exit(void)
-{
 	if (ec_query_wq) {
 		destroy_workqueue(ec_query_wq);
 		ec_query_wq = NULL;
 	}
 }
 
+static int acpi_ec_init_workqueues(void)
+{
+	if (!ec_wq)
+		ec_wq = alloc_ordered_workqueue("kec", 0);
+
+	if (!ec_query_wq)
+		ec_query_wq = alloc_workqueue("kec_query", 0, ec_max_queries);
+
+	if (!ec_wq || !ec_query_wq) {
+		acpi_ec_destroy_workqueues();
+		return -ENODEV;
+	}
+	return 0;
+}
+
 static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 	{
 		.ident = "Thinkpad X1 Carbon 6th",
@@ -2156,8 +2165,7 @@
 	int result;
 	int ecdt_fail, dsdt_fail;
 
-	/* register workqueue for _Qxx evaluations */
-	result = acpi_ec_query_init();
+	result = acpi_ec_init_workqueues();
 	if (result)
 		return result;
 
@@ -2188,6 +2196,6 @@
 {
 
 	acpi_bus_unregister_driver(&acpi_ec_driver);
-	acpi_ec_query_exit();
+	acpi_ec_destroy_workqueues();
 }
 #endif	/* 0 */
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 43988062..e5f9592 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -990,21 +990,41 @@
 	acpi_os_wait_events_complete(); /* synchronize Notify handling */
 }
 
-static void acpi_s2idle_wake(void)
+static bool acpi_s2idle_wake(void)
 {
-	/*
-	 * If IRQD_WAKEUP_ARMED is set for the SCI at this point, the SCI has
-	 * not triggered while suspended, so bail out.
-	 */
-	if (!acpi_sci_irq_valid() ||
-	    irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
-		return;
+	if (!acpi_sci_irq_valid())
+		return pm_wakeup_pending();
 
-	/*
-	 * If there are EC events to process, the wakeup may be a spurious one
-	 * coming from the EC.
-	 */
-	if (acpi_ec_dispatch_gpe()) {
+	while (pm_wakeup_pending()) {
+		/*
+		 * If IRQD_WAKEUP_ARMED is set for the SCI at this point, the
+		 * SCI has not triggered while suspended, so bail out (the
+		 * wakeup is pending anyway and the SCI is not the source of
+		 * it).
+		 */
+		if (irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
+			return true;
+
+		/*
+		 * If the status bit of any enabled fixed event is set, the
+		 * wakeup is regarded as valid.
+		 */
+		if (acpi_any_fixed_event_status_set())
+			return true;
+
+		/*
+		 * If there are no EC events to process and at least one of the
+		 * other enabled GPEs is active, the wakeup is regarded as a
+		 * genuine one.
+		 *
+		 * Note that the checks below must be carried out in this order
+		 * to avoid returning prematurely due to a change of the EC GPE
+		 * status bit from unset to set between the checks with the
+		 * status bits of all the other GPEs unset.
+		 */
+		if (acpi_any_gpe_status_set() && !acpi_ec_dispatch_gpe())
+			return true;
+
 		/*
 		 * Cancel the wakeup and process all pending events in case
 		 * there are any wakeup ones in there.
@@ -1017,8 +1037,19 @@
 
 		acpi_s2idle_sync();
 
+		/*
+		 * The SCI is in the "suspended" state now and it cannot produce
+		 * new wakeup events till the rearming below, so if any of them
+		 * are pending here, they must be resulting from the processing
+		 * of EC events above or coming from somewhere else.
+		 */
+		if (pm_wakeup_pending())
+			return true;
+
 		rearm_wake_irq(acpi_sci_irq);
 	}
+
+	return false;
 }
 
 static void acpi_s2idle_restore_early(void)
diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index 15fa293..b20fdcb 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -465,7 +465,7 @@
 {
 	struct moxtet *moxtet = file->private_data;
 	u8 bin[TURRIS_MOX_MAX_MODULES];
-	u8 hex[sizeof(buf) * 2 + 1];
+	u8 hex[sizeof(bin) * 2 + 1];
 	int ret, n;
 
 	ret = moxtet_spi_read(moxtet, bin);
diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c
index 1ff4fb1..382b28f 100644
--- a/drivers/char/ipmi/ipmb_dev_int.c
+++ b/drivers/char/ipmi/ipmb_dev_int.c
@@ -19,7 +19,7 @@
 #include <linux/spinlock.h>
 #include <linux/wait.h>
 
-#define MAX_MSG_LEN		128
+#define MAX_MSG_LEN		240
 #define IPMB_REQUEST_LEN_MIN	7
 #define NETFN_RSP_BIT_MASK	0x4
 #define REQUEST_QUEUE_MAX_LEN	256
@@ -63,6 +63,7 @@
 	spinlock_t lock;
 	wait_queue_head_t wait_queue;
 	struct mutex file_mutex;
+	bool is_i2c_protocol;
 };
 
 static inline struct ipmb_dev *to_ipmb_dev(struct file *file)
@@ -112,6 +113,25 @@
 	return ret < 0 ? ret : count;
 }
 
+static int ipmb_i2c_write(struct i2c_client *client, u8 *msg, u8 addr)
+{
+	struct i2c_msg i2c_msg;
+
+	/*
+	 * subtract 1 byte (rq_sa) from the length of the msg passed to
+	 * raw i2c_transfer
+	 */
+	i2c_msg.len = msg[IPMB_MSG_LEN_IDX] - 1;
+
+	/* Assign message to buffer except first 2 bytes (length and address) */
+	i2c_msg.buf = msg + 2;
+
+	i2c_msg.addr = addr;
+	i2c_msg.flags = client->flags & I2C_CLIENT_PEC;
+
+	return i2c_transfer(client->adapter, &i2c_msg, 1);
+}
+
 static ssize_t ipmb_write(struct file *file, const char __user *buf,
 			size_t count, loff_t *ppos)
 {
@@ -133,6 +153,12 @@
 	rq_sa = GET_7BIT_ADDR(msg[RQ_SA_8BIT_IDX]);
 	netf_rq_lun = msg[NETFN_LUN_IDX];
 
+	/* Check i2c block transfer vs smbus */
+	if (ipmb_dev->is_i2c_protocol) {
+		ret = ipmb_i2c_write(ipmb_dev->client, msg, rq_sa);
+		return (ret == 1) ? count : ret;
+	}
+
 	/*
 	 * subtract rq_sa and netf_rq_lun from the length of the msg passed to
 	 * i2c_smbus_xfer
@@ -253,7 +279,7 @@
 		break;
 
 	case I2C_SLAVE_WRITE_RECEIVED:
-		if (ipmb_dev->msg_idx >= sizeof(struct ipmb_msg))
+		if (ipmb_dev->msg_idx >= sizeof(struct ipmb_msg) - 1)
 			break;
 
 		buf[++ipmb_dev->msg_idx] = *val;
@@ -302,6 +328,9 @@
 	if (ret)
 		return ret;
 
+	ipmb_dev->is_i2c_protocol
+		= device_property_read_bool(&client->dev, "i2c-protocol");
+
 	ipmb_dev->client = client;
 	i2c_set_clientdata(client, ipmb_dev);
 	ret = i2c_slave_register(client, ipmb_slave_cb);
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 22c6a2e..8ac390c 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -775,10 +775,14 @@
 	flags = ipmi_ssif_lock_cond(ssif_info, &oflags);
 	msg = ssif_info->curr_msg;
 	if (msg) {
+		if (data) {
+			if (len > IPMI_MAX_MSG_LENGTH)
+				len = IPMI_MAX_MSG_LENGTH;
+			memcpy(msg->rsp, data, len);
+		} else {
+			len = 0;
+		}
 		msg->rsp_size = len;
-		if (msg->rsp_size > IPMI_MAX_MSG_LENGTH)
-			msg->rsp_size = IPMI_MAX_MSG_LENGTH;
-		memcpy(msg->rsp, data, msg->rsp_size);
 		ssif_info->curr_msg = NULL;
 	}
 
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index 5a0d99d..9567e51 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -21,9 +21,11 @@
 tpm-$(CONFIG_OF) += eventlog/of.o
 obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o
 obj-$(CONFIG_TCG_TIS) += tpm_tis.o
-obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o
-tpm_tis_spi_mod-y := tpm_tis_spi.o
-tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
+
+obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o
+tpm_tis_spi-y := tpm_tis_spi_main.o
+tpm_tis_spi-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
+
 obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o
 obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o
 obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 13696de..7603295 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -525,6 +525,8 @@
 		return 0;
 	}
 
+	bank->crypto_id = HASH_ALGO__LAST;
+
 	return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size);
 }
 
diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi_main.c
similarity index 100%
rename from drivers/char/tpm/tpm_tis_spi.c
rename to drivers/char/tpm/tpm_tis_spi_main.c
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 4adac3a..cbe6c94 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -105,6 +105,8 @@
 }
 EXPORT_SYMBOL_GPL(have_governor_per_policy);
 
+static struct kobject *cpufreq_global_kobject;
+
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
 {
 	if (have_governor_per_policy())
@@ -2745,9 +2747,6 @@
 }
 EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);
 
-struct kobject *cpufreq_global_kobject;
-EXPORT_SYMBOL(cpufreq_global_kobject);
-
 static int __init cpufreq_core_init(void)
 {
 	if (cpufreq_disabled())
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 26a654d..0aa4b6b 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -61,7 +61,7 @@
 {
 	if (!blk_queue_dax(bdev->bd_queue))
 		return NULL;
-	return fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	return dax_get_by_host(bdev->bd_disk->disk_name);
 }
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 #endif
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 7243b88..69e0d90 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -505,16 +505,10 @@
 {
 	edac_dbg(1, "\n");
 
-	/* If we're not yet registered with sysfs free only what was allocated
-	 * in edac_mc_alloc().
-	 */
-	if (!device_is_registered(&mci->dev)) {
-		_edac_mc_free(mci);
-		return;
-	}
+	if (device_is_registered(&mci->dev))
+		edac_unregister_sysfs(mci);
 
-	/* the mci instance is freed here, when the sysfs object is dropped */
-	edac_unregister_sysfs(mci);
+	_edac_mc_free(mci);
 }
 EXPORT_SYMBOL_GPL(edac_mc_free);
 
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 0367554..c70ec0a 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -276,10 +276,7 @@
 
 static void csrow_attr_release(struct device *dev)
 {
-	struct csrow_info *csrow = container_of(dev, struct csrow_info, dev);
-
-	edac_dbg(1, "device %s released\n", dev_name(dev));
-	kfree(csrow);
+	/* release device with _edac_mc_free() */
 }
 
 static const struct device_type csrow_attr_type = {
@@ -447,8 +444,7 @@
 		csrow = mci->csrows[i];
 		if (!nr_pages_per_csrow(csrow))
 			continue;
-
-		device_del(&mci->csrows[i]->dev);
+		device_unregister(&mci->csrows[i]->dev);
 	}
 
 	return err;
@@ -608,10 +604,7 @@
 
 static void dimm_attr_release(struct device *dev)
 {
-	struct dimm_info *dimm = container_of(dev, struct dimm_info, dev);
-
-	edac_dbg(1, "device %s released\n", dev_name(dev));
-	kfree(dimm);
+	/* release device with _edac_mc_free() */
 }
 
 static const struct device_type dimm_attr_type = {
@@ -893,10 +886,7 @@
 
 static void mci_attr_release(struct device *dev)
 {
-	struct mem_ctl_info *mci = container_of(dev, struct mem_ctl_info, dev);
-
-	edac_dbg(1, "device %s released\n", dev_name(dev));
-	kfree(mci);
+	/* release device with _edac_mc_free() */
 }
 
 static const struct device_type mci_attr_type = {
diff --git a/drivers/gpio/gpio-bd71828.c b/drivers/gpio/gpio-bd71828.c
index 04aade9..3dbbc63 100644
--- a/drivers/gpio/gpio-bd71828.c
+++ b/drivers/gpio/gpio-bd71828.c
@@ -10,16 +10,6 @@
 #define GPIO_OUT_REG(off) (BD71828_REG_GPIO_CTRL1 + (off))
 #define HALL_GPIO_OFFSET 3
 
-/*
- * These defines can be removed when
- * "gpio: Add definition for GPIO direction"
- * (9208b1e77d6e8e9776f34f46ef4079ecac9c3c25 in GPIO tree) gets merged,
- */
-#ifndef GPIO_LINE_DIRECTION_IN
-	#define GPIO_LINE_DIRECTION_IN 1
-	#define GPIO_LINE_DIRECTION_OUT 0
-#endif
-
 struct bd71828_gpio {
 	struct rohm_regmap_dev chip;
 	struct gpio_chip gpio;
diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c
index 147a1bd..c54dd08 100644
--- a/drivers/gpio/gpio-sifive.c
+++ b/drivers/gpio/gpio-sifive.c
@@ -35,7 +35,7 @@
 	void __iomem		*base;
 	struct gpio_chip	gc;
 	struct regmap		*regs;
-	u32			irq_state;
+	unsigned long		irq_state;
 	unsigned int		trigger[SIFIVE_GPIO_MAX];
 	unsigned int		irq_parent[SIFIVE_GPIO_MAX];
 };
@@ -94,7 +94,7 @@
 	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	/* Enable interrupts */
-	assign_bit(offset, (unsigned long *)&chip->irq_state, 1);
+	assign_bit(offset, &chip->irq_state, 1);
 	sifive_gpio_set_ie(chip, offset);
 }
 
@@ -104,7 +104,7 @@
 	struct sifive_gpio *chip = gpiochip_get_data(gc);
 	int offset = irqd_to_hwirq(d) % SIFIVE_GPIO_MAX;
 
-	assign_bit(offset, (unsigned long *)&chip->irq_state, 0);
+	assign_bit(offset, &chip->irq_state, 0);
 	sifive_gpio_set_ie(chip, offset);
 	irq_chip_disable_parent(d);
 }
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index a9748b5..67f9f82 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -147,9 +147,10 @@
 	for (i = 0; i < gc->ngpio; i++) {
 		if (*mask == 0)
 			break;
+		/* Once finished with an index write it out to the register */
 		if (index !=  xgpio_index(chip, i)) {
 			xgpio_writereg(chip->regs + XGPIO_DATA_OFFSET +
-				       xgpio_regoffset(chip, i),
+				       index * XGPIO_CHANNEL_OFFSET,
 				       chip->gpio_state[index]);
 			spin_unlock_irqrestore(&chip->gpio_lock[index], flags);
 			index =  xgpio_index(chip, i);
@@ -165,7 +166,7 @@
 	}
 
 	xgpio_writereg(chip->regs + XGPIO_DATA_OFFSET +
-		       xgpio_regoffset(chip, i), chip->gpio_state[index]);
+		       index * XGPIO_CHANNEL_OFFSET, chip->gpio_state[index]);
 
 	spin_unlock_irqrestore(&chip->gpio_lock[index], flags);
 }
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 7532834..4d0106c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3035,13 +3035,33 @@
  * rely on gpio_request() having been called beforehand.
  */
 
-static int gpio_set_config(struct gpio_chip *gc, unsigned int offset,
-			   enum pin_config_param mode)
+static int gpio_do_set_config(struct gpio_chip *gc, unsigned int offset,
+			      unsigned long config)
 {
 	if (!gc->set_config)
 		return -ENOTSUPP;
 
-	return gc->set_config(gc, offset, mode);
+	return gc->set_config(gc, offset, config);
+}
+
+static int gpio_set_config(struct gpio_chip *gc, unsigned int offset,
+			   enum pin_config_param mode)
+{
+	unsigned long config;
+	unsigned arg;
+
+	switch (mode) {
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+	case PIN_CONFIG_BIAS_PULL_UP:
+		arg = 1;
+		break;
+
+	default:
+		arg = 0;
+	}
+
+	config = PIN_CONF_PACKED(mode, arg);
+	return gpio_do_set_config(gc, offset, config);
 }
 
 static int gpio_set_bias(struct gpio_chip *chip, struct gpio_desc *desc)
@@ -3277,7 +3297,7 @@
 	chip = desc->gdev->chip;
 
 	config = pinconf_to_config_packed(PIN_CONFIG_INPUT_DEBOUNCE, debounce);
-	return gpio_set_config(chip, gpio_chip_hwgpio(desc), config);
+	return gpio_do_set_config(chip, gpio_chip_hwgpio(desc), config);
 }
 EXPORT_SYMBOL_GPL(gpiod_set_debounce);
 
@@ -3311,7 +3331,7 @@
 	packed = pinconf_to_config_packed(PIN_CONFIG_PERSIST_STATE,
 					  !transitory);
 	gpio = gpio_chip_hwgpio(desc);
-	rc = gpio_set_config(chip, gpio, packed);
+	rc = gpio_do_set_config(chip, gpio, packed);
 	if (rc == -ENOTSUPP) {
 		dev_dbg(&desc->gdev->dev, "Persistence not supported for GPIO %d\n",
 				gpio);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
index 07914e34..1311d6ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
@@ -52,7 +52,7 @@
 		return -ENOENT;
 
 	/* update the hw_perf_event struct with config data */
-	hwc->conf = event->attr.config;
+	hwc->config = event->attr.config;
 
 	return 0;
 }
@@ -74,9 +74,9 @@
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
 		if (!(flags & PERF_EF_RELOAD))
-			pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
+			pe->adev->df.funcs->pmc_start(pe->adev, hwc->config, 1);
 
-		pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 0);
+		pe->adev->df.funcs->pmc_start(pe->adev, hwc->config, 0);
 		break;
 	default:
 		break;
@@ -101,7 +101,7 @@
 
 		switch (pe->pmu_perf_type) {
 		case PERF_TYPE_AMDGPU_DF:
-			pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->conf,
+			pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->config,
 							  &count);
 			break;
 		default:
@@ -126,7 +126,7 @@
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 0);
+		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->config, 0);
 		break;
 	default:
 		break;
@@ -156,7 +156,8 @@
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		retval = pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
+		retval = pe->adev->df.funcs->pmc_start(pe->adev,
+						       hwc->config, 1);
 		break;
 	default:
 		return 0;
@@ -184,7 +185,7 @@
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 1);
+		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->config, 1);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 3a1570d..146f966 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1013,6 +1013,30 @@
 	return 0;
 }
 
+static int psp_dtm_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	/*
+	 * TODO: bypass the unloading in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
 int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
 	/*
@@ -1037,7 +1061,7 @@
 	if (!psp->dtm_context.dtm_initialized)
 		return 0;
 
-	ret = psp_hdcp_unload(psp);
+	ret = psp_dtm_unload(psp);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index d6deb0e..6fe0573 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -179,6 +179,7 @@
 	struct amdgpu_irq_src	irq;
 	struct amdgpu_vcn_reg	external;
 	struct amdgpu_bo	*dpg_sram_bo;
+	struct dpg_pause_state	pause_state;
 	void			*dpg_sram_cpu_addr;
 	uint64_t		dpg_sram_gpu_addr;
 	uint32_t		*dpg_sram_curr_addr;
@@ -190,8 +191,6 @@
 	const struct firmware	*fw;	/* VCN firmware */
 	unsigned		num_enc_rings;
 	enum amd_powergating_state cur_state;
-	struct dpg_pause_state pause_state;
-
 	bool			indirect_sram;
 
 	uint8_t	num_vcn_inst;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 1785fda..22bbb36 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3923,11 +3923,13 @@
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
 	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
 		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 90f64b8..3afdbbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1193,6 +1193,14 @@
 	return false;
 }
 
+static bool is_raven_kicker(struct amdgpu_device *adev)
+{
+	if (adev->pm.fw_version >= 0x41e2b)
+		return true;
+	else
+		return false;
+}
+
 static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 {
 	if (gfx_v9_0_should_disable_gfxoff(adev->pdev))
@@ -1205,9 +1213,8 @@
 		break;
 	case CHIP_RAVEN:
 		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) &&
-		    ((adev->gfx.rlc_fw_version != 106 &&
+		    ((!is_raven_kicker(adev) &&
 		      adev->gfx.rlc_fw_version < 531) ||
-		     (adev->gfx.rlc_fw_version == 53815) ||
 		     (adev->gfx.rlc_feature_version < 1) ||
 		     !adev->gfx.rlc.is_rlc_v2_1))
 			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
@@ -3959,6 +3966,7 @@
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
 		uint32_t tmp, lsb, msb, i = 0;
@@ -3977,6 +3985,7 @@
 			((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	}
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
@@ -4374,9 +4383,17 @@
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
-	r = gfx_v9_0_do_edc_gds_workarounds(adev);
-	if (r)
-		return r;
+	/*
+	 * Temp workaround to fix the issue that CP firmware fails to
+	 * update read pointer when CPDMA is writing clearing operation
+	 * to GDS in suspend/resume sequence on several cards. So just
+	 * limit this operation in cold boot sequence.
+	 */
+	if (!adev->in_suspend) {
+		r = gfx_v9_0_do_edc_gds_workarounds(adev);
+		if (r)
+			return r;
+	}
 
 	/* requires IBs so do in late init after IB pool is initialized */
 	r = gfx_v9_0_do_edc_gpr_workarounds(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15f3424..2b488df 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -272,7 +272,12 @@
 
 static u32 soc15_get_xclk(struct amdgpu_device *adev)
 {
-	return adev->clock.spll.reference_freq;
+	u32 reference_clock = adev->clock.spll.reference_freq;
+
+	if (adev->asic_type == CHIP_RAVEN)
+		return reference_clock / 4;
+
+	return reference_clock;
 }
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 1a24fad..71f61af 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1207,9 +1207,10 @@
 	struct amdgpu_ring *ring;
 
 	/* pause/unpause if state is changed */
-	if (adev->vcn.pause_state.fw_based != new_state->fw_based) {
+	if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) {
 		DRM_DEBUG("dpg pause state changed %d:%d -> %d:%d",
-			adev->vcn.pause_state.fw_based, adev->vcn.pause_state.jpeg,
+			adev->vcn.inst[inst_idx].pause_state.fw_based,
+			adev->vcn.inst[inst_idx].pause_state.jpeg,
 			new_state->fw_based, new_state->jpeg);
 
 		reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) &
@@ -1258,13 +1259,14 @@
 			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
 			WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
 		}
-		adev->vcn.pause_state.fw_based = new_state->fw_based;
+		adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based;
 	}
 
 	/* pause/unpause if state is changed */
-	if (adev->vcn.pause_state.jpeg != new_state->jpeg) {
+	if (adev->vcn.inst[inst_idx].pause_state.jpeg != new_state->jpeg) {
 		DRM_DEBUG("dpg pause state changed %d:%d -> %d:%d",
-			adev->vcn.pause_state.fw_based, adev->vcn.pause_state.jpeg,
+			adev->vcn.inst[inst_idx].pause_state.fw_based,
+			adev->vcn.inst[inst_idx].pause_state.jpeg,
 			new_state->fw_based, new_state->jpeg);
 
 		reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) &
@@ -1318,7 +1320,7 @@
 			reg_data &= ~UVD_DPG_PAUSE__JPEG_PAUSE_DPG_REQ_MASK;
 			WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
 		}
-		adev->vcn.pause_state.jpeg = new_state->jpeg;
+		adev->vcn.inst[inst_idx].pause_state.jpeg = new_state->jpeg;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 4f72167..c387c81 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -1137,9 +1137,9 @@
 	int ret_code;
 
 	/* pause/unpause if state is changed */
-	if (adev->vcn.pause_state.fw_based != new_state->fw_based) {
+	if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) {
 		DRM_DEBUG("dpg pause state changed %d -> %d",
-			adev->vcn.pause_state.fw_based,	new_state->fw_based);
+			adev->vcn.inst[inst_idx].pause_state.fw_based,	new_state->fw_based);
 		reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) &
 			(~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
 
@@ -1185,7 +1185,7 @@
 			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
 			WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
 		}
-		adev->vcn.pause_state.fw_based = new_state->fw_based;
+		adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 70fae79..2d64ba1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -1367,9 +1367,9 @@
 	int ret_code;
 
 	/* pause/unpause if state is changed */
-	if (adev->vcn.pause_state.fw_based != new_state->fw_based) {
+	if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) {
 		DRM_DEBUG("dpg pause state changed %d -> %d",
-			adev->vcn.pause_state.fw_based,	new_state->fw_based);
+			adev->vcn.inst[inst_idx].pause_state.fw_based,	new_state->fw_based);
 		reg_data = RREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE) &
 			(~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
 
@@ -1407,14 +1407,14 @@
 					   RREG32_SOC15(UVD, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF);
 
 				SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS,
-					   0x0, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+					   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
 			}
 		} else {
 			/* unpause dpg, no need to wait */
 			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
 			WREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE, reg_data);
 		}
-		adev->vcn.pause_state.fw_based = new_state->fw_based;
+		adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based;
 	}
 
 	return 0;
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 2795415..e8f66fb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1911,7 +1911,7 @@
 	mutex_lock(&aconnector->hpd_lock);
 
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-	if (adev->asic_type >= CHIP_RAVEN)
+	if (adev->dm.hdcp_workqueue)
 		hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index);
 #endif
 	if (aconnector->fake_enable)
@@ -2088,8 +2088,10 @@
 		}
 	}
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-	if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ)
-		hdcp_handle_cpirq(adev->dm.hdcp_workqueue,  aconnector->base.index);
+	    if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ) {
+		    if (adev->dm.hdcp_workqueue)
+			    hdcp_handle_cpirq(adev->dm.hdcp_workqueue,  aconnector->base.index);
+	    }
 #endif
 	if ((dc_link->cur_link_settings.lane_count != LANE_COUNT_UNKNOWN) ||
 	    (dc_link->type == dc_connection_mst_branch))
@@ -5702,7 +5704,7 @@
 		drm_connector_attach_vrr_capable_property(
 			&aconnector->base);
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-		if (adev->asic_type >= CHIP_RAVEN)
+		if (adev->dm.hdcp_workqueue)
 			drm_connector_attach_content_protection_property(&aconnector->base, true);
 #endif
 	}
@@ -8408,7 +8410,6 @@
 	/* Calculate number of static frames before generating interrupt to
 	 * enter PSR.
 	 */
-	unsigned int frame_time_microsec = 1000000 / vsync_rate_hz;
 	// Init fail safe of 2 frames static
 	unsigned int num_frames_static = 2;
 
@@ -8423,8 +8424,10 @@
 	 * Calculate number of frames such that at least 30 ms of time has
 	 * passed.
 	 */
-	if (vsync_rate_hz != 0)
+	if (vsync_rate_hz != 0) {
+		unsigned int frame_time_microsec = 1000000 / vsync_rate_hz;
 		num_frames_static = (30000 / frame_time_microsec) + 1;
+	}
 
 	params.triggers.cursor_update = true;
 	params.triggers.overlay_update = true;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index 629a07a..c4ba6e8 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -711,10 +711,6 @@
 	power_gating.header.sub_type = DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING;
 	power_gating.power_gating.pwr = *pwr;
 
-	/* ATOM_ENABLE is old API in DMUB */
-	if (power_gating.power_gating.pwr.enable == ATOM_ENABLE)
-		power_gating.power_gating.pwr.enable = ATOM_INIT;
-
 	dc_dmub_srv_cmd_queue(dmcub, &power_gating.header);
 	dc_dmub_srv_cmd_execute(dmcub);
 	dc_dmub_srv_wait_idle(dmcub);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index 3cd28319..c0f6a8c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -87,6 +87,12 @@
 ###############################################################################
 CLK_MGR_DCN21 = rn_clk_mgr.o rn_clk_mgr_vbios_smu.o
 
+# prevent build errors regarding soft-float vs hard-float FP ABI tags
+# this code is currently unused on ppc64, as it applies to Renoir APUs only
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
+endif
+
 AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 495f01e..49ce46b 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -117,7 +117,7 @@
 
 		prev_dppclk_khz = clk_mgr->base.ctx->dc->current_state->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
 
-		if (safe_to_lower || prev_dppclk_khz < dppclk_khz) {
+		if ((prev_dppclk_khz > dppclk_khz && safe_to_lower) || prev_dppclk_khz < dppclk_khz) {
 			clk_mgr->dccg->funcs->update_dpp_dto(
 							clk_mgr->dccg, dpp_inst, dppclk_khz);
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 7ae4c06..9ef3f7b 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -151,6 +151,12 @@
 		rn_vbios_smu_set_min_deep_sleep_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz);
 	}
 
+	// workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow.
+	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
+		if (new_clocks->dppclk_khz < 100000)
+			new_clocks->dppclk_khz = 100000;
+	}
+
 	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
 		if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz)
 			dpp_clock_lowered = true;
@@ -412,19 +418,19 @@
 
 		ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst;
 		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;
-		/* We will not select WM based on dcfclk, so leave it as unconstrained */
-		ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-		ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-		/* fclk wil be used to select WM*/
+		/* We will not select WM based on fclk, so leave it as unconstrained */
+		ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+		ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+		/* dcfclk wil be used to select WM*/
 
 		if (ranges->reader_wm_sets[num_valid_sets].wm_type == WM_TYPE_PSTATE_CHG) {
 			if (i == 0)
-				ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = 0;
+				ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = 0;
 			else {
 				/* add 1 to make it non-overlapping with next lvl */
-				ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = bw_params->clk_table.entries[i - 1].fclk_mhz + 1;
+				ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = bw_params->clk_table.entries[i - 1].dcfclk_mhz + 1;
 			}
-			ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = bw_params->clk_table.entries[i].fclk_mhz;
+			ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz;
 
 		} else {
 			/* unconstrained for memory retraining */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index f1a5d2c..68c4049 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -400,7 +400,7 @@
 {
 	enum gpio_result result;
 
-	if (!is_engine_available(engine))
+	if ((engine == NULL) || !is_engine_available(engine))
 		return false;
 
 	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index cfbbaff..a444fed 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -572,7 +572,6 @@
 	dpp->funcs->dpp_dppclk_control(dpp, false, false);
 
 	hubp->power_gated = true;
-	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
 	hws->funcs.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 0d506d3..33d0a17 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -60,6 +60,7 @@
 #include "dcn20/dcn20_dccg.h"
 #include "dcn21_hubbub.h"
 #include "dcn10/dcn10_resource.h"
+#include "dce110/dce110_resource.h"
 
 #include "dcn20/dcn20_dwb.h"
 #include "dcn20/dcn20_mmhubbub.h"
@@ -856,6 +857,7 @@
 enum dcn20_clk_src_array_id {
 	DCN20_CLK_SRC_PLL0,
 	DCN20_CLK_SRC_PLL1,
+	DCN20_CLK_SRC_PLL2,
 	DCN20_CLK_SRC_TOTAL_DCN21
 };
 
@@ -1718,6 +1720,10 @@
 			dcn21_clock_source_create(ctx, ctx->dc_bios,
 				CLOCK_SOURCE_COMBO_PHY_PLL1,
 				&clk_src_regs[1], false);
+	pool->base.clock_sources[DCN20_CLK_SRC_PLL2] =
+			dcn21_clock_source_create(ctx, ctx->dc_bios,
+				CLOCK_SOURCE_COMBO_PHY_PLL2,
+				&clk_src_regs[2], false);
 
 	pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21;
 
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
index f730b94..5524671 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
@@ -46,8 +46,8 @@
 	enum mod_hdcp_status status;
 
 	if (is_dp_hdcp(hdcp))
-		status = (hdcp->auth.msg.hdcp2.rxcaps_dp[2] & HDCP_2_2_RX_CAPS_VERSION_VAL) &&
-				HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[0]) ?
+		status = (hdcp->auth.msg.hdcp2.rxcaps_dp[0] == HDCP_2_2_RX_CAPS_VERSION_VAL) &&
+				HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[2]) ?
 				MOD_HDCP_STATUS_SUCCESS :
 				MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE;
 	else
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
index b2f96a1..7a63cf8 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
@@ -39,21 +39,39 @@
 #define SMU_11_0_PP_OVERDRIVE_VERSION                   0x0800
 #define SMU_11_0_PP_POWERSAVINGCLOCK_VERSION            0x0100
 
+enum SMU_11_0_ODFEATURE_CAP {
+    SMU_11_0_ODCAP_GFXCLK_LIMITS = 0,
+    SMU_11_0_ODCAP_GFXCLK_CURVE,
+    SMU_11_0_ODCAP_UCLK_MAX,
+    SMU_11_0_ODCAP_POWER_LIMIT,
+    SMU_11_0_ODCAP_FAN_ACOUSTIC_LIMIT,
+    SMU_11_0_ODCAP_FAN_SPEED_MIN,
+    SMU_11_0_ODCAP_TEMPERATURE_FAN,
+    SMU_11_0_ODCAP_TEMPERATURE_SYSTEM,
+    SMU_11_0_ODCAP_MEMORY_TIMING_TUNE,
+    SMU_11_0_ODCAP_FAN_ZERO_RPM_CONTROL,
+    SMU_11_0_ODCAP_AUTO_UV_ENGINE,
+    SMU_11_0_ODCAP_AUTO_OC_ENGINE,
+    SMU_11_0_ODCAP_AUTO_OC_MEMORY,
+    SMU_11_0_ODCAP_FAN_CURVE,
+    SMU_11_0_ODCAP_COUNT,
+};
+
 enum SMU_11_0_ODFEATURE_ID {
-    SMU_11_0_ODFEATURE_GFXCLK_LIMITS        = 1 << 0,         //GFXCLK Limit feature
-    SMU_11_0_ODFEATURE_GFXCLK_CURVE         = 1 << 1,         //GFXCLK Curve feature
-    SMU_11_0_ODFEATURE_UCLK_MAX             = 1 << 2,         //UCLK Limit feature
-    SMU_11_0_ODFEATURE_POWER_LIMIT          = 1 << 3,         //Power Limit feature
-    SMU_11_0_ODFEATURE_FAN_ACOUSTIC_LIMIT   = 1 << 4,         //Fan Acoustic RPM feature
-    SMU_11_0_ODFEATURE_FAN_SPEED_MIN        = 1 << 5,         //Minimum Fan Speed feature
-    SMU_11_0_ODFEATURE_TEMPERATURE_FAN      = 1 << 6,         //Fan Target Temperature Limit feature
-    SMU_11_0_ODFEATURE_TEMPERATURE_SYSTEM   = 1 << 7,         //Operating Temperature Limit feature
-    SMU_11_0_ODFEATURE_MEMORY_TIMING_TUNE   = 1 << 8,         //AC Timing Tuning feature
-    SMU_11_0_ODFEATURE_FAN_ZERO_RPM_CONTROL = 1 << 9,         //Zero RPM feature
-    SMU_11_0_ODFEATURE_AUTO_UV_ENGINE       = 1 << 10,        //Auto Under Volt GFXCLK feature
-    SMU_11_0_ODFEATURE_AUTO_OC_ENGINE       = 1 << 11,        //Auto Over Clock GFXCLK feature
-    SMU_11_0_ODFEATURE_AUTO_OC_MEMORY       = 1 << 12,        //Auto Over Clock MCLK feature
-    SMU_11_0_ODFEATURE_FAN_CURVE            = 1 << 13,        //VICTOR TODO
+    SMU_11_0_ODFEATURE_GFXCLK_LIMITS        = 1 << SMU_11_0_ODCAP_GFXCLK_LIMITS,            //GFXCLK Limit feature
+    SMU_11_0_ODFEATURE_GFXCLK_CURVE         = 1 << SMU_11_0_ODCAP_GFXCLK_CURVE,             //GFXCLK Curve feature
+    SMU_11_0_ODFEATURE_UCLK_MAX             = 1 << SMU_11_0_ODCAP_UCLK_MAX,                 //UCLK Limit feature
+    SMU_11_0_ODFEATURE_POWER_LIMIT          = 1 << SMU_11_0_ODCAP_POWER_LIMIT,              //Power Limit feature
+    SMU_11_0_ODFEATURE_FAN_ACOUSTIC_LIMIT   = 1 << SMU_11_0_ODCAP_FAN_ACOUSTIC_LIMIT,       //Fan Acoustic RPM feature
+    SMU_11_0_ODFEATURE_FAN_SPEED_MIN        = 1 << SMU_11_0_ODCAP_FAN_SPEED_MIN,            //Minimum Fan Speed feature
+    SMU_11_0_ODFEATURE_TEMPERATURE_FAN      = 1 << SMU_11_0_ODCAP_TEMPERATURE_FAN,          //Fan Target Temperature Limit feature
+    SMU_11_0_ODFEATURE_TEMPERATURE_SYSTEM   = 1 << SMU_11_0_ODCAP_TEMPERATURE_SYSTEM,       //Operating Temperature Limit feature
+    SMU_11_0_ODFEATURE_MEMORY_TIMING_TUNE   = 1 << SMU_11_0_ODCAP_MEMORY_TIMING_TUNE,       //AC Timing Tuning feature
+    SMU_11_0_ODFEATURE_FAN_ZERO_RPM_CONTROL = 1 << SMU_11_0_ODCAP_FAN_ZERO_RPM_CONTROL,     //Zero RPM feature
+    SMU_11_0_ODFEATURE_AUTO_UV_ENGINE       = 1 << SMU_11_0_ODCAP_AUTO_UV_ENGINE,           //Auto Under Volt GFXCLK feature
+    SMU_11_0_ODFEATURE_AUTO_OC_ENGINE       = 1 << SMU_11_0_ODCAP_AUTO_OC_ENGINE,           //Auto Over Clock GFXCLK feature
+    SMU_11_0_ODFEATURE_AUTO_OC_MEMORY       = 1 << SMU_11_0_ODCAP_AUTO_OC_MEMORY,           //Auto Over Clock MCLK feature
+    SMU_11_0_ODFEATURE_FAN_CURVE            = 1 << SMU_11_0_ODCAP_FAN_CURVE,                //Fan Curve feature
     SMU_11_0_ODFEATURE_COUNT                = 14,
 };
 #define SMU_11_0_MAX_ODFEATURE    32          //Maximum Number of OD Features
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 19a9846..0d73a49 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -736,9 +736,9 @@
 	return dpm_desc->SnapToDiscrete == 0 ? true : false;
 }
 
-static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_ID feature)
+static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_CAP cap)
 {
-	return od_table->cap[feature];
+	return od_table->cap[cap];
 }
 
 static void navi10_od_setting_get_range(struct smu_11_0_overdrive_table *od_table,
@@ -846,7 +846,7 @@
 	case SMU_OD_SCLK:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
-		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS))
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS))
 			break;
 		size += sprintf(buf + size, "OD_SCLK:\n");
 		size += sprintf(buf + size, "0: %uMhz\n1: %uMhz\n", od_table->GfxclkFmin, od_table->GfxclkFmax);
@@ -854,7 +854,7 @@
 	case SMU_OD_MCLK:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
-		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX))
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX))
 			break;
 		size += sprintf(buf + size, "OD_MCLK:\n");
 		size += sprintf(buf + size, "1: %uMHz\n", od_table->UclkFmax);
@@ -862,7 +862,7 @@
 	case SMU_OD_VDDC_CURVE:
 		if (!smu->od_enabled || !od_table || !od_settings)
 			break;
-		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE))
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE))
 			break;
 		size += sprintf(buf + size, "OD_VDDC_CURVE:\n");
 		for (i = 0; i < 3; i++) {
@@ -887,7 +887,7 @@
 			break;
 		size = sprintf(buf, "%s:\n", "OD_RANGE");
 
-		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS)) {
+		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMIN,
 						    &min_value, NULL);
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMAX,
@@ -896,14 +896,14 @@
 					min_value, max_value);
 		}
 
-		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX)) {
+		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_UCLKFMAX,
 						    &min_value, &max_value);
 			size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n",
 					min_value, max_value);
 		}
 
-		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE)) {
+		if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE)) {
 			navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P1,
 						    &min_value, &max_value);
 			size += sprintf(buf + size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
@@ -2056,7 +2056,7 @@
 
 	switch (type) {
 	case PP_OD_EDIT_SCLK_VDDC_TABLE:
-		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS)) {
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) {
 			pr_warn("GFXCLK_LIMITS not supported!\n");
 			return -ENOTSUPP;
 		}
@@ -2102,7 +2102,7 @@
 		}
 		break;
 	case PP_OD_EDIT_MCLK_VDDC_TABLE:
-		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX)) {
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_UCLK_MAX)) {
 			pr_warn("UCLK_MAX not supported!\n");
 			return -ENOTSUPP;
 		}
@@ -2143,7 +2143,7 @@
 		}
 		break;
 	case PP_OD_EDIT_VDDC_CURVE:
-		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE)) {
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_CURVE)) {
 			pr_warn("GFXCLK_CURVE not supported!\n");
 			return -ENOTSUPP;
 		}
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index 0dc4947..b06c057 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -898,6 +898,9 @@
 	if (ret)
 		return ret;
 
+	bitmap_zero(feature->enabled, feature->feature_num);
+	bitmap_zero(feature->supported, feature->feature_num);
+
 	if (en) {
 		ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
 		if (ret)
@@ -907,9 +910,6 @@
 			    feature->feature_num);
 		bitmap_copy(feature->supported, (unsigned long *)&feature_mask,
 			    feature->feature_num);
-	} else {
-		bitmap_zero(feature->enabled, feature->feature_num);
-		bitmap_zero(feature->supported, feature->feature_num);
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 3709e5a..fbdb42d 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -297,7 +297,7 @@
 
 static int tc_aux_wait_busy(struct tc_data *tc)
 {
-	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000);
+	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000);
 }
 
 static int tc_aux_write_data(struct tc_data *tc, const void *data,
@@ -640,7 +640,7 @@
 	if (ret)
 		goto err;
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000);
 	if (ret == -ETIMEDOUT) {
 		dev_err(tc->dev, "Timeout waiting for PHY to become ready");
 		return ret;
@@ -876,7 +876,7 @@
 	int ret;
 
 	ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE,
-			      LT_LOOPDONE, 1, 1000);
+			      LT_LOOPDONE, 500, 100000);
 	if (ret) {
 		dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n");
 		return ret;
@@ -949,7 +949,7 @@
 	dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST);
 	ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl);
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000);
 	if (ret) {
 		dev_err(dev, "timeout waiting for phy become ready");
 		return ret;
diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c
index 6f6d6d1..f195a47 100644
--- a/drivers/gpu/drm/bridge/ti-tfp410.c
+++ b/drivers/gpu/drm/bridge/ti-tfp410.c
@@ -140,7 +140,8 @@
 					  dvi->connector_type,
 					  dvi->ddc);
 	if (ret) {
-		dev_err(dvi->dev, "drm_connector_init() failed: %d\n", ret);
+		dev_err(dvi->dev, "drm_connector_init_with_ddc() failed: %d\n",
+			ret);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 6d4a29e..3035584 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -951,7 +951,8 @@
 	 * depending on the hardware this may require the framebuffer
 	 * to be in a specific tiling format.
 	 */
-	if ((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180 ||
+	if (((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_0 &&
+	     (*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180) ||
 	    !plane->rotation_property)
 		return false;
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 20cdaf3..cce0b1b 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3838,7 +3838,8 @@
 		else if (msg->req_type == DP_RESOURCE_STATUS_NOTIFY)
 			guid = msg->u.resource_stat.guid;
 
-		mstb = drm_dp_get_mst_branch_device_by_guid(mgr, guid);
+		if (guid)
+			mstb = drm_dp_get_mst_branch_device_by_guid(mgr, guid);
 	} else {
 		mstb = drm_dp_get_mst_branch_device(mgr, hdr->lct, hdr->rad);
 	}
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 99769d6..805fb00 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -3211,7 +3211,7 @@
 	return cea;
 }
 
-static const struct drm_display_mode *cea_mode_for_vic(u8 vic)
+static __always_inline const struct drm_display_mode *cea_mode_for_vic(u8 vic)
 {
 	BUILD_BUG_ON(1 + ARRAY_SIZE(edid_cea_modes_1) - 1 != 127);
 	BUILD_BUG_ON(193 + ARRAY_SIZE(edid_cea_modes_193) - 1 != 219);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 10336b1..d4d6451 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1698,6 +1698,13 @@
 	if (rotation && freestanding)
 		return -EINVAL;
 
+	if (!(rotation & DRM_MODE_ROTATE_MASK))
+		rotation |= DRM_MODE_ROTATE_0;
+
+	/* Make sure there is exactly one rotation defined */
+	if (!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK))
+		return -EINVAL;
+
 	mode->rotation_reflection = rotation;
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index ba95959..907c447 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -75,9 +75,8 @@
 	help
 	  This option enables capturing the GPU state when a hang is detected.
 	  This information is vital for triaging hangs and assists in debugging.
-	  Please report any hang to
-	    https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
-	  for triaging.
+	  Please report any hang for triaging according to:
+	    https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 
 	  If in doubt, say "Y".
 
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 8beac06..ef4017a 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -357,14 +357,16 @@
 		panel_fixed_mode->hdisplay + dtd->hfront_porch;
 	panel_fixed_mode->hsync_end =
 		panel_fixed_mode->hsync_start + dtd->hsync;
-	panel_fixed_mode->htotal = panel_fixed_mode->hsync_end;
+	panel_fixed_mode->htotal =
+		panel_fixed_mode->hdisplay + dtd->hblank;
 
 	panel_fixed_mode->vdisplay = dtd->vactive;
 	panel_fixed_mode->vsync_start =
 		panel_fixed_mode->vdisplay + dtd->vfront_porch;
 	panel_fixed_mode->vsync_end =
 		panel_fixed_mode->vsync_start + dtd->vsync;
-	panel_fixed_mode->vtotal = panel_fixed_mode->vsync_end;
+	panel_fixed_mode->vtotal =
+		panel_fixed_mode->vdisplay + dtd->vblank;
 
 	panel_fixed_mode->clock = dtd->pixel_clock;
 	panel_fixed_mode->width_mm = dtd->width_mm;
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 33f1dc3..d9a61f3 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -4251,7 +4251,9 @@
 void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 					 struct intel_crtc_state *crtc_state)
 {
-	if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
+	if (IS_ELKHARTLAKE(dev_priv) && crtc_state->port_clock > 594000)
+		crtc_state->min_voltage_level = 3;
+	else if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 1;
 	else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 2;
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 19ea842..aa45395 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11087,7 +11087,7 @@
 	u32 base;
 
 	if (INTEL_INFO(dev_priv)->display.cursor_needs_physical)
-		base = obj->phys_handle->busaddr;
+		base = sg_dma_address(obj->mm.pages->sgl);
 	else
 		base = intel_plane_ggtt_offset(plane_state);
 
@@ -12366,6 +12366,7 @@
 		/* Copy parameters to slave plane */
 		linked_state->ctl = plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE;
 		linked_state->color_ctl = plane_state->color_ctl;
+		linked_state->view = plane_state->view;
 		memcpy(linked_state->color_plane, plane_state->color_plane,
 		       sizeof(linked_state->color_plane));
 
@@ -14476,37 +14477,23 @@
 	return 0;
 }
 
-static bool intel_cpu_transcoder_needs_modeset(struct intel_atomic_state *state,
-					       enum transcoder transcoder)
+static bool intel_cpu_transcoders_need_modeset(struct intel_atomic_state *state,
+					       u8 transcoders)
 {
-	struct intel_crtc_state *new_crtc_state;
+	const struct intel_crtc_state *new_crtc_state;
 	struct intel_crtc *crtc;
 	int i;
 
-	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
-		if (new_crtc_state->cpu_transcoder == transcoder)
-			return needs_modeset(new_crtc_state);
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (new_crtc_state->hw.enable &&
+		    transcoders & BIT(new_crtc_state->cpu_transcoder) &&
+		    needs_modeset(new_crtc_state))
+			return true;
+	}
 
 	return false;
 }
 
-static void
-intel_modeset_synced_crtcs(struct intel_atomic_state *state,
-			   u8 transcoders)
-{
-	struct intel_crtc_state *new_crtc_state;
-	struct intel_crtc *crtc;
-	int i;
-
-	for_each_new_intel_crtc_in_state(state, crtc,
-					 new_crtc_state, i) {
-		if (transcoders & BIT(new_crtc_state->cpu_transcoder)) {
-			new_crtc_state->uapi.mode_changed = true;
-			new_crtc_state->update_pipe = false;
-		}
-	}
-}
-
 static int
 intel_modeset_all_tiles(struct intel_atomic_state *state, int tile_grp_id)
 {
@@ -14662,15 +14649,20 @@
 		if (intel_dp_mst_is_slave_trans(new_crtc_state)) {
 			enum transcoder master = new_crtc_state->mst_master_transcoder;
 
-			if (intel_cpu_transcoder_needs_modeset(state, master)) {
+			if (intel_cpu_transcoders_need_modeset(state, BIT(master))) {
 				new_crtc_state->uapi.mode_changed = true;
 				new_crtc_state->update_pipe = false;
 			}
-		} else if (is_trans_port_sync_mode(new_crtc_state)) {
+		}
+
+		if (is_trans_port_sync_mode(new_crtc_state)) {
 			u8 trans = new_crtc_state->sync_mode_slaves_mask |
 				   BIT(new_crtc_state->master_transcoder);
 
-			intel_modeset_synced_crtcs(state, trans);
+			if (intel_cpu_transcoders_need_modeset(state, trans)) {
+				new_crtc_state->uapi.mode_changed = true;
+				new_crtc_state->update_pipe = false;
+			}
 		}
 	}
 
@@ -17441,6 +17433,24 @@
 			 * have readout for pipe gamma enable.
 			 */
 			crtc_state->uapi.color_mgmt_changed = true;
+
+			/*
+			 * FIXME hack to force full modeset when DSC is being
+			 * used.
+			 *
+			 * As long as we do not have full state readout and
+			 * config comparison of crtc_state->dsc, we have no way
+			 * to ensure reliable fastset. Remove once we have
+			 * readout for DSC.
+			 */
+			if (crtc_state->dsc.compression_enable) {
+				ret = drm_atomic_add_affected_connectors(state,
+									 &crtc->base);
+				if (ret)
+					goto out;
+				crtc_state->uapi.mode_changed = true;
+				drm_dbg_kms(dev, "Force full modeset for DSC\n");
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index 89fb0d9..04f953b 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -384,6 +384,7 @@
 	return data;
 }
 
+#ifdef CONFIG_ACPI
 static int i2c_adapter_lookup(struct acpi_resource *ares, void *data)
 {
 	struct i2c_adapter_lookup *lookup = data;
@@ -393,8 +394,7 @@
 	acpi_handle adapter_handle;
 	acpi_status status;
 
-	if (intel_dsi->i2c_bus_num >= 0 ||
-	    !i2c_acpi_get_i2c_resource(ares, &sb))
+	if (!i2c_acpi_get_i2c_resource(ares, &sb))
 		return 1;
 
 	if (lookup->slave_addr != sb->slave_address)
@@ -413,14 +413,41 @@
 	return 1;
 }
 
+static void i2c_acpi_find_adapter(struct intel_dsi *intel_dsi,
+				  const u16 slave_addr)
+{
+	struct drm_device *drm_dev = intel_dsi->base.base.dev;
+	struct device *dev = &drm_dev->pdev->dev;
+	struct acpi_device *acpi_dev;
+	struct list_head resource_list;
+	struct i2c_adapter_lookup lookup;
+
+	acpi_dev = ACPI_COMPANION(dev);
+	if (acpi_dev) {
+		memset(&lookup, 0, sizeof(lookup));
+		lookup.slave_addr = slave_addr;
+		lookup.intel_dsi = intel_dsi;
+		lookup.dev_handle = acpi_device_handle(acpi_dev);
+
+		INIT_LIST_HEAD(&resource_list);
+		acpi_dev_get_resources(acpi_dev, &resource_list,
+				       i2c_adapter_lookup,
+				       &lookup);
+		acpi_dev_free_resource_list(&resource_list);
+	}
+}
+#else
+static inline void i2c_acpi_find_adapter(struct intel_dsi *intel_dsi,
+					 const u16 slave_addr)
+{
+}
+#endif
+
 static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data)
 {
 	struct drm_device *drm_dev = intel_dsi->base.base.dev;
 	struct device *dev = &drm_dev->pdev->dev;
 	struct i2c_adapter *adapter;
-	struct acpi_device *acpi_dev;
-	struct list_head resource_list;
-	struct i2c_adapter_lookup lookup;
 	struct i2c_msg msg;
 	int ret;
 	u8 vbt_i2c_bus_num = *(data + 2);
@@ -431,20 +458,7 @@
 
 	if (intel_dsi->i2c_bus_num < 0) {
 		intel_dsi->i2c_bus_num = vbt_i2c_bus_num;
-
-		acpi_dev = ACPI_COMPANION(dev);
-		if (acpi_dev) {
-			memset(&lookup, 0, sizeof(lookup));
-			lookup.slave_addr = slave_addr;
-			lookup.intel_dsi = intel_dsi;
-			lookup.dev_handle = acpi_device_handle(acpi_dev);
-
-			INIT_LIST_HEAD(&resource_list);
-			acpi_dev_get_resources(acpi_dev, &resource_list,
-					       i2c_adapter_lookup,
-					       &lookup);
-			acpi_dev_free_resource_list(&resource_list);
-		}
+		i2c_acpi_find_adapter(intel_dsi, slave_addr);
 	}
 
 	adapter = i2c_get_adapter(intel_dsi->i2c_bus_num);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index a2e57e62..151a1e8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -565,6 +565,22 @@
 		if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
 			return -ENODEV;
 
+		/*
+		 * If the cancel fails, we then need to reset, cleanly!
+		 *
+		 * If the per-engine reset fails, all hope is lost! We resort
+		 * to a full GPU reset in that unlikely case, but realistically
+		 * if the engine could not reset, the full reset does not fare
+		 * much better. The damage has been done.
+		 *
+		 * However, if we cannot reset an engine by itself, we cannot
+		 * cleanup a hanging persistent context without causing
+		 * colateral damage, and we should not pretend we can by
+		 * exposing the interface.
+		 */
+		if (!intel_has_reset_engine(&ctx->i915->gt))
+			return -ENODEV;
+
 		i915_gem_context_clear_persistence(ctx);
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d5a0f5a..60c984e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1981,9 +1981,20 @@
 				       pw->trampoline);
 }
 
+static void __eb_parse_release(struct dma_fence_work *work)
+{
+	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
+
+	if (pw->trampoline)
+		i915_active_release(&pw->trampoline->active);
+	i915_active_release(&pw->shadow->active);
+	i915_active_release(&pw->batch->active);
+}
+
 static const struct dma_fence_work_ops eb_parse_ops = {
 	.name = "eb_parse",
 	.work = __eb_parse,
+	.release = __eb_parse_release,
 };
 
 static int eb_parse_pipeline(struct i915_execbuffer *eb,
@@ -1997,6 +2008,20 @@
 	if (!pw)
 		return -ENOMEM;
 
+	err = i915_active_acquire(&eb->batch->active);
+	if (err)
+		goto err_free;
+
+	err = i915_active_acquire(&shadow->active);
+	if (err)
+		goto err_batch;
+
+	if (trampoline) {
+		err = i915_active_acquire(&trampoline->active);
+		if (err)
+			goto err_shadow;
+	}
+
 	dma_fence_work_init(&pw->base, &eb_parse_ops);
 
 	pw->engine = eb->engine;
@@ -2006,7 +2031,9 @@
 	pw->shadow = shadow;
 	pw->trampoline = trampoline;
 
-	dma_resv_lock(pw->batch->resv, NULL);
+	err = dma_resv_lock_interruptible(pw->batch->resv, NULL);
+	if (err)
+		goto err_trampoline;
 
 	err = dma_resv_reserve_shared(pw->batch->resv, 1);
 	if (err)
@@ -2034,6 +2061,14 @@
 
 err_batch_unlock:
 	dma_resv_unlock(pw->batch->resv);
+err_trampoline:
+	if (trampoline)
+		i915_active_release(&trampoline->active);
+err_shadow:
+	i915_active_release(&shadow->active);
+err_batch:
+	i915_active_release(&eb->batch->active);
+err_free:
 	kfree(pw);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index b9fdac2..0b6a442 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -455,10 +455,11 @@
 
 void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
 {
-	struct i915_mmap_offset *mmo;
+	struct i915_mmap_offset *mmo, *mn;
 
 	spin_lock(&obj->mmo.lock);
-	list_for_each_entry(mmo, &obj->mmo.offsets, offset) {
+	rbtree_postorder_for_each_entry_safe(mmo, mn,
+					     &obj->mmo.offsets, offset) {
 		/*
 		 * vma_node_unmap for GTT mmaps handled already in
 		 * __i915_gem_object_release_mmap_gtt
@@ -488,6 +489,67 @@
 }
 
 static struct i915_mmap_offset *
+lookup_mmo(struct drm_i915_gem_object *obj,
+	   enum i915_mmap_type mmap_type)
+{
+	struct rb_node *rb;
+
+	spin_lock(&obj->mmo.lock);
+	rb = obj->mmo.offsets.rb_node;
+	while (rb) {
+		struct i915_mmap_offset *mmo =
+			rb_entry(rb, typeof(*mmo), offset);
+
+		if (mmo->mmap_type == mmap_type) {
+			spin_unlock(&obj->mmo.lock);
+			return mmo;
+		}
+
+		if (mmo->mmap_type < mmap_type)
+			rb = rb->rb_right;
+		else
+			rb = rb->rb_left;
+	}
+	spin_unlock(&obj->mmo.lock);
+
+	return NULL;
+}
+
+static struct i915_mmap_offset *
+insert_mmo(struct drm_i915_gem_object *obj, struct i915_mmap_offset *mmo)
+{
+	struct rb_node *rb, **p;
+
+	spin_lock(&obj->mmo.lock);
+	rb = NULL;
+	p = &obj->mmo.offsets.rb_node;
+	while (*p) {
+		struct i915_mmap_offset *pos;
+
+		rb = *p;
+		pos = rb_entry(rb, typeof(*pos), offset);
+
+		if (pos->mmap_type == mmo->mmap_type) {
+			spin_unlock(&obj->mmo.lock);
+			drm_vma_offset_remove(obj->base.dev->vma_offset_manager,
+					      &mmo->vma_node);
+			kfree(mmo);
+			return pos;
+		}
+
+		if (pos->mmap_type < mmo->mmap_type)
+			p = &rb->rb_right;
+		else
+			p = &rb->rb_left;
+	}
+	rb_link_node(&mmo->offset, rb, p);
+	rb_insert_color(&mmo->offset, &obj->mmo.offsets);
+	spin_unlock(&obj->mmo.lock);
+
+	return mmo;
+}
+
+static struct i915_mmap_offset *
 mmap_offset_attach(struct drm_i915_gem_object *obj,
 		   enum i915_mmap_type mmap_type,
 		   struct drm_file *file)
@@ -496,20 +558,22 @@
 	struct i915_mmap_offset *mmo;
 	int err;
 
+	mmo = lookup_mmo(obj, mmap_type);
+	if (mmo)
+		goto out;
+
 	mmo = kmalloc(sizeof(*mmo), GFP_KERNEL);
 	if (!mmo)
 		return ERR_PTR(-ENOMEM);
 
 	mmo->obj = obj;
-	mmo->dev = obj->base.dev;
-	mmo->file = file;
 	mmo->mmap_type = mmap_type;
 	drm_vma_node_reset(&mmo->vma_node);
 
-	err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node,
-				 obj->base.size / PAGE_SIZE);
+	err = drm_vma_offset_add(obj->base.dev->vma_offset_manager,
+				 &mmo->vma_node, obj->base.size / PAGE_SIZE);
 	if (likely(!err))
-		goto out;
+		goto insert;
 
 	/* Attempt to reap some mmap space from dead objects */
 	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT);
@@ -517,19 +581,17 @@
 		goto err;
 
 	i915_gem_drain_freed_objects(i915);
-	err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node,
-				 obj->base.size / PAGE_SIZE);
+	err = drm_vma_offset_add(obj->base.dev->vma_offset_manager,
+				 &mmo->vma_node, obj->base.size / PAGE_SIZE);
 	if (err)
 		goto err;
 
+insert:
+	mmo = insert_mmo(obj, mmo);
+	GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo);
 out:
 	if (file)
 		drm_vma_node_allow(&mmo->vma_node, file);
-
-	spin_lock(&obj->mmo.lock);
-	list_add(&mmo->offset, &obj->mmo.offsets);
-	spin_unlock(&obj->mmo.lock);
-
 	return mmo;
 
 err:
@@ -745,60 +807,43 @@
 	struct drm_vma_offset_node *node;
 	struct drm_file *priv = filp->private_data;
 	struct drm_device *dev = priv->minor->dev;
+	struct drm_i915_gem_object *obj = NULL;
 	struct i915_mmap_offset *mmo = NULL;
-	struct drm_gem_object *obj = NULL;
 	struct file *anon;
 
 	if (drm_dev_is_unplugged(dev))
 		return -ENODEV;
 
+	rcu_read_lock();
 	drm_vma_offset_lock_lookup(dev->vma_offset_manager);
 	node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager,
 						  vma->vm_pgoff,
 						  vma_pages(vma));
-	if (likely(node)) {
-		mmo = container_of(node, struct i915_mmap_offset,
-				   vma_node);
-		/*
-		 * In our dependency chain, the drm_vma_offset_node
-		 * depends on the validity of the mmo, which depends on
-		 * the gem object. However the only reference we have
-		 * at this point is the mmo (as the parent of the node).
-		 * Try to check if the gem object was at least cleared.
-		 */
-		if (!mmo || !mmo->obj) {
-			drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
-			return -EINVAL;
-		}
+	if (node && drm_vma_node_is_allowed(node, priv)) {
 		/*
 		 * Skip 0-refcnted objects as it is in the process of being
 		 * destroyed and will be invalid when the vma manager lock
 		 * is released.
 		 */
-		obj = &mmo->obj->base;
-		if (!kref_get_unless_zero(&obj->refcount))
-			obj = NULL;
+		mmo = container_of(node, struct i915_mmap_offset, vma_node);
+		obj = i915_gem_object_get_rcu(mmo->obj);
 	}
 	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
+	rcu_read_unlock();
 	if (!obj)
-		return -EINVAL;
+		return node ? -EACCES : -EINVAL;
 
-	if (!drm_vma_node_is_allowed(node, priv)) {
-		drm_gem_object_put_unlocked(obj);
-		return -EACCES;
-	}
-
-	if (i915_gem_object_is_readonly(to_intel_bo(obj))) {
+	if (i915_gem_object_is_readonly(obj)) {
 		if (vma->vm_flags & VM_WRITE) {
-			drm_gem_object_put_unlocked(obj);
+			i915_gem_object_put(obj);
 			return -EINVAL;
 		}
 		vma->vm_flags &= ~VM_MAYWRITE;
 	}
 
-	anon = mmap_singleton(to_i915(obj->dev));
+	anon = mmap_singleton(to_i915(dev));
 	if (IS_ERR(anon)) {
-		drm_gem_object_put_unlocked(obj);
+		i915_gem_object_put(obj);
 		return PTR_ERR(anon);
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 46bacc8..3598521 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -63,7 +63,7 @@
 	INIT_LIST_HEAD(&obj->lut_list);
 
 	spin_lock_init(&obj->mmo.lock);
-	INIT_LIST_HEAD(&obj->mmo.offsets);
+	obj->mmo.offsets = RB_ROOT;
 
 	init_rcu_head(&obj->rcu);
 
@@ -100,8 +100,8 @@
 {
 	struct drm_i915_gem_object *obj = to_intel_bo(gem);
 	struct drm_i915_file_private *fpriv = file->driver_priv;
+	struct i915_mmap_offset *mmo, *mn;
 	struct i915_lut_handle *lut, *ln;
-	struct i915_mmap_offset *mmo;
 	LIST_HEAD(close);
 
 	i915_gem_object_lock(obj);
@@ -117,14 +117,8 @@
 	i915_gem_object_unlock(obj);
 
 	spin_lock(&obj->mmo.lock);
-	list_for_each_entry(mmo, &obj->mmo.offsets, offset) {
-		if (mmo->file != file)
-			continue;
-
-		spin_unlock(&obj->mmo.lock);
+	rbtree_postorder_for_each_entry_safe(mmo, mn, &obj->mmo.offsets, offset)
 		drm_vma_node_revoke(&mmo->vma_node, file);
-		spin_lock(&obj->mmo.lock);
-	}
 	spin_unlock(&obj->mmo.lock);
 
 	list_for_each_entry_safe(lut, ln, &close, obj_link) {
@@ -203,12 +197,14 @@
 
 		i915_gem_object_release_mmap(obj);
 
-		list_for_each_entry_safe(mmo, mn, &obj->mmo.offsets, offset) {
+		rbtree_postorder_for_each_entry_safe(mmo, mn,
+						     &obj->mmo.offsets,
+						     offset) {
 			drm_vma_offset_remove(obj->base.dev->vma_offset_manager,
 					      &mmo->vma_node);
 			kfree(mmo);
 		}
-		INIT_LIST_HEAD(&obj->mmo.offsets);
+		obj->mmo.offsets = RB_ROOT;
 
 		GEM_BUG_ON(atomic_read(&obj->bind_count));
 		GEM_BUG_ON(obj->userfault_count);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index db70a33..9c86f2d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -70,14 +70,22 @@
 }
 
 static inline struct drm_i915_gem_object *
+i915_gem_object_get_rcu(struct drm_i915_gem_object *obj)
+{
+	if (obj && !kref_get_unless_zero(&obj->base.refcount))
+		obj = NULL;
+
+	return obj;
+}
+
+static inline struct drm_i915_gem_object *
 i915_gem_object_lookup(struct drm_file *file, u32 handle)
 {
 	struct drm_i915_gem_object *obj;
 
 	rcu_read_lock();
 	obj = i915_gem_object_lookup_rcu(file, handle);
-	if (obj && !kref_get_unless_zero(&obj->base.refcount))
-		obj = NULL;
+	obj = i915_gem_object_get_rcu(obj);
 	rcu_read_unlock();
 
 	return obj;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 88e2686..c2174da 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -71,13 +71,11 @@
 };
 
 struct i915_mmap_offset {
-	struct drm_device *dev;
 	struct drm_vma_offset_node vma_node;
 	struct drm_i915_gem_object *obj;
-	struct drm_file *file;
 	enum i915_mmap_type mmap_type;
 
-	struct list_head offset;
+	struct rb_node offset;
 };
 
 struct drm_i915_gem_object {
@@ -137,7 +135,7 @@
 
 	struct {
 		spinlock_t lock; /* Protects access to mmo offsets */
-		struct list_head offsets;
+		struct rb_root offsets;
 	} mmo;
 
 	I915_SELFTEST_DECLARE(struct list_head st_link);
@@ -287,9 +285,6 @@
 
 		void *gvt_info;
 	};
-
-	/** for phys allocated objects */
-	struct drm_dma_handle *phys_handle;
 };
 
 static inline struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index b1b7c1b3..b07bb40 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -22,88 +22,87 @@
 static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 {
 	struct address_space *mapping = obj->base.filp->f_mapping;
-	struct drm_dma_handle *phys;
-	struct sg_table *st;
 	struct scatterlist *sg;
-	char *vaddr;
+	struct sg_table *st;
+	dma_addr_t dma;
+	void *vaddr;
+	void *dst;
 	int i;
-	int err;
 
 	if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj)))
 		return -EINVAL;
 
-	/* Always aligning to the object size, allows a single allocation
+	/*
+	 * Always aligning to the object size, allows a single allocation
 	 * to handle all possible callers, and given typical object sizes,
 	 * the alignment of the buddy allocation will naturally match.
 	 */
-	phys = drm_pci_alloc(obj->base.dev,
-			     roundup_pow_of_two(obj->base.size),
-			     roundup_pow_of_two(obj->base.size));
-	if (!phys)
+	vaddr = dma_alloc_coherent(&obj->base.dev->pdev->dev,
+				   roundup_pow_of_two(obj->base.size),
+				   &dma, GFP_KERNEL);
+	if (!vaddr)
 		return -ENOMEM;
 
-	vaddr = phys->vaddr;
-	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
-		struct page *page;
-		char *src;
-
-		page = shmem_read_mapping_page(mapping, i);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			goto err_phys;
-		}
-
-		src = kmap_atomic(page);
-		memcpy(vaddr, src, PAGE_SIZE);
-		drm_clflush_virt_range(vaddr, PAGE_SIZE);
-		kunmap_atomic(src);
-
-		put_page(page);
-		vaddr += PAGE_SIZE;
-	}
-
-	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
-
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st) {
-		err = -ENOMEM;
-		goto err_phys;
-	}
+	if (!st)
+		goto err_pci;
 
-	if (sg_alloc_table(st, 1, GFP_KERNEL)) {
-		kfree(st);
-		err = -ENOMEM;
-		goto err_phys;
-	}
+	if (sg_alloc_table(st, 1, GFP_KERNEL))
+		goto err_st;
 
 	sg = st->sgl;
 	sg->offset = 0;
 	sg->length = obj->base.size;
 
-	sg_dma_address(sg) = phys->busaddr;
+	sg_assign_page(sg, (struct page *)vaddr);
+	sg_dma_address(sg) = dma;
 	sg_dma_len(sg) = obj->base.size;
 
-	obj->phys_handle = phys;
+	dst = vaddr;
+	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
+		struct page *page;
+		void *src;
+
+		page = shmem_read_mapping_page(mapping, i);
+		if (IS_ERR(page))
+			goto err_st;
+
+		src = kmap_atomic(page);
+		memcpy(dst, src, PAGE_SIZE);
+		drm_clflush_virt_range(dst, PAGE_SIZE);
+		kunmap_atomic(src);
+
+		put_page(page);
+		dst += PAGE_SIZE;
+	}
+
+	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
 
 	__i915_gem_object_set_pages(obj, st, sg->length);
 
 	return 0;
 
-err_phys:
-	drm_pci_free(obj->base.dev, phys);
-
-	return err;
+err_st:
+	kfree(st);
+err_pci:
+	dma_free_coherent(&obj->base.dev->pdev->dev,
+			  roundup_pow_of_two(obj->base.size),
+			  vaddr, dma);
+	return -ENOMEM;
 }
 
 static void
 i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
+	dma_addr_t dma = sg_dma_address(pages->sgl);
+	void *vaddr = sg_page(pages->sgl);
+
 	__i915_gem_object_release_shmem(obj, pages, false);
 
 	if (obj->mm.dirty) {
 		struct address_space *mapping = obj->base.filp->f_mapping;
-		char *vaddr = obj->phys_handle->vaddr;
+		void *src = vaddr;
 		int i;
 
 		for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
@@ -115,15 +114,16 @@
 				continue;
 
 			dst = kmap_atomic(page);
-			drm_clflush_virt_range(vaddr, PAGE_SIZE);
-			memcpy(dst, vaddr, PAGE_SIZE);
+			drm_clflush_virt_range(src, PAGE_SIZE);
+			memcpy(dst, src, PAGE_SIZE);
 			kunmap_atomic(dst);
 
 			set_page_dirty(page);
 			if (obj->mm.madv == I915_MADV_WILLNEED)
 				mark_page_accessed(page);
 			put_page(page);
-			vaddr += PAGE_SIZE;
+
+			src += PAGE_SIZE;
 		}
 		obj->mm.dirty = false;
 	}
@@ -131,7 +131,9 @@
 	sg_free_table(pages);
 	kfree(pages);
 
-	drm_pci_free(obj->base.dev, obj->phys_handle);
+	dma_free_coherent(&obj->base.dev->pdev->dev,
+			  roundup_pow_of_two(obj->base.size),
+			  vaddr, dma);
 }
 
 static void phys_release(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 0ba524a..cbad7fe 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -136,6 +136,9 @@
 	struct intel_engine_cs *engine =
 		container_of(b, struct intel_engine_cs, breadcrumbs);
 
+	if (unlikely(intel_engine_is_virtual(engine)))
+		engine = intel_virtual_engine_get_sibling(engine, 0);
+
 	intel_engine_add_retire(engine, tl);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 23137b2..57e8a05 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -67,21 +67,18 @@
 {
 	int err;
 
-	err = i915_active_acquire(&ce->active);
-	if (err)
-		return err;
+	__i915_active_acquire(&ce->active);
+
+	if (intel_context_is_barrier(ce))
+		return 0;
 
 	/* Preallocate tracking nodes */
-	if (!intel_context_is_barrier(ce)) {
-		err = i915_active_acquire_preallocate_barrier(&ce->active,
-							      ce->engine);
-		if (err) {
-			i915_active_release(&ce->active);
-			return err;
-		}
-	}
+	err = i915_active_acquire_preallocate_barrier(&ce->active,
+						      ce->engine);
+	if (err)
+		i915_active_release(&ce->active);
 
-	return 0;
+	return err;
 }
 
 static void intel_context_active_release(struct intel_context *ce)
@@ -101,13 +98,19 @@
 			return err;
 	}
 
-	if (mutex_lock_interruptible(&ce->pin_mutex))
-		return -EINTR;
+	err = i915_active_acquire(&ce->active);
+	if (err)
+		return err;
 
-	if (likely(!atomic_read(&ce->pin_count))) {
+	if (mutex_lock_interruptible(&ce->pin_mutex)) {
+		err = -EINTR;
+		goto out_release;
+	}
+
+	if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) {
 		err = intel_context_active_acquire(ce);
 		if (unlikely(err))
-			goto err;
+			goto out_unlock;
 
 		err = ce->ops->pin(ce);
 		if (unlikely(err))
@@ -117,18 +120,19 @@
 			 ce->ring->head, ce->ring->tail);
 
 		smp_mb__before_atomic(); /* flush pin before it is visible */
+		atomic_inc(&ce->pin_count);
 	}
 
-	atomic_inc(&ce->pin_count);
 	GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */
-
-	mutex_unlock(&ce->pin_mutex);
-	return 0;
+	GEM_BUG_ON(i915_active_is_idle(&ce->active));
+	goto out_unlock;
 
 err_active:
 	intel_context_active_release(ce);
-err:
+out_unlock:
 	mutex_unlock(&ce->pin_mutex);
+out_release:
+	i915_active_release(&ce->active);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index f451ef3..06ff769 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -671,6 +671,7 @@
 intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass)
 {
 	INIT_LIST_HEAD(&engine->active.requests);
+	INIT_LIST_HEAD(&engine->active.hold);
 
 	spin_lock_init(&engine->active.lock);
 	lockdep_set_subclass(&engine->active.lock, subclass);
@@ -1422,6 +1423,17 @@
 	}
 }
 
+static unsigned long list_count(struct list_head *list)
+{
+	struct list_head *pos;
+	unsigned long count = 0;
+
+	list_for_each(pos, list)
+		count++;
+
+	return count;
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1491,6 +1503,7 @@
 			hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
 		}
 	}
+	drm_printf(m, "\tOn hold?: %lu\n", list_count(&engine->active.hold));
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 
 	drm_printf(m, "\tMMIO base:  0x%08x\n", engine->mmio_base);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 350da59..92be41a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -295,6 +295,7 @@
 	struct {
 		spinlock_t lock;
 		struct list_head requests;
+		struct list_head hold; /* ready requests, but on hold */
 	} active;
 
 	struct llist_head barrier_tasks;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 7ef1d37..8a5054f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -99,6 +99,9 @@
 void intel_engine_add_retire(struct intel_engine_cs *engine,
 			     struct intel_timeline *tl)
 {
+	/* We don't deal well with the engine disappearing beneath us */
+	GEM_BUG_ON(intel_engine_is_virtual(engine));
+
 	if (add_retire(engine, tl))
 		schedule_work(&engine->retire_work);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 0cf0f6f..fe8a59a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -237,7 +237,8 @@
 				     bool close);
 static void
 __execlists_update_reg_state(const struct intel_context *ce,
-			     const struct intel_engine_cs *engine);
+			     const struct intel_engine_cs *engine,
+			     u32 head);
 
 static void mark_eio(struct i915_request *rq)
 {
@@ -985,6 +986,8 @@
 			GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 
 			list_move(&rq->sched.link, pl);
+			set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+
 			active = rq;
 		} else {
 			struct intel_engine_cs *owner = rq->context->engine;
@@ -1184,12 +1187,11 @@
 		head = rq->tail;
 	else
 		head = active_request(ce->timeline, rq)->head;
-	ce->ring->head = intel_ring_wrap(ce->ring, head);
-	intel_ring_update_space(ce->ring);
+	head = intel_ring_wrap(ce->ring, head);
 
 	/* Scrub the context image to prevent replaying the previous batch */
 	restore_default_state(ce, engine);
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, head);
 
 	/* We've switched away, so this should be a no-op, but intent matters */
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
@@ -1319,7 +1321,7 @@
 {
 	struct intel_context *ce = rq->context;
 	u64 desc = ce->lrc_desc;
-	u32 tail;
+	u32 tail, prev;
 
 	/*
 	 * WaIdleLiteRestore:bdw,skl
@@ -1332,9 +1334,15 @@
 	 * subsequent resubmissions (for lite restore). Should that fail us,
 	 * and we try and submit the same tail again, force the context
 	 * reload.
+	 *
+	 * If we need to return to a preempted context, we need to skip the
+	 * lite-restore and force it to reload the RING_TAIL. Otherwise, the
+	 * HW has a tendency to ignore us rewinding the TAIL to the end of
+	 * an earlier request.
 	 */
 	tail = intel_ring_set_tail(rq->ring, rq->tail);
-	if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+	prev = ce->lrc_reg_state[CTX_RING_TAIL];
+	if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
 		desc |= CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state[CTX_RING_TAIL] = tail;
 	rq->tail = rq->wa_tail;
@@ -1535,7 +1543,8 @@
 		return true;
 
 	if (unlikely((prev->fence.flags ^ next->fence.flags) &
-		     (I915_FENCE_FLAG_NOPREEMPT | I915_FENCE_FLAG_SENTINEL)))
+		     (BIT(I915_FENCE_FLAG_NOPREEMPT) |
+		      BIT(I915_FENCE_FLAG_SENTINEL))))
 		return false;
 
 	if (!can_merge_ctx(prev->context, next->context))
@@ -1602,6 +1611,11 @@
 	return *last;
 }
 
+#define for_each_waiter(p__, rq__) \
+	list_for_each_entry_lockless(p__, \
+				     &(rq__)->sched.waiters_list, \
+				     wait_link)
+
 static void defer_request(struct i915_request *rq, struct list_head * const pl)
 {
 	LIST_HEAD(list);
@@ -1619,7 +1633,7 @@
 		GEM_BUG_ON(i915_request_is_active(rq));
 		list_move_tail(&rq->sched.link, pl);
 
-		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+		for_each_waiter(p, rq) {
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
@@ -1632,8 +1646,8 @@
 				   !i915_request_completed(rq));
 
 			GEM_BUG_ON(i915_request_is_active(w));
-			if (list_empty(&w->sched.link))
-				continue; /* Not yet submitted; unready */
+			if (!i915_request_is_ready(w))
+				continue;
 
 			if (rq_prio(w) < rq_prio(rq))
 				continue;
@@ -1831,14 +1845,6 @@
 			 */
 			__unwind_incomplete_requests(engine);
 
-			/*
-			 * If we need to return to the preempted context, we
-			 * need to skip the lite-restore and force it to
-			 * reload the RING_TAIL. Otherwise, the HW has a
-			 * tendency to ignore us rewinding the TAIL to the
-			 * end of an earlier request.
-			 */
-			last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timer_expired(&engine->execlists.timer)) {
@@ -2351,6 +2357,310 @@
 	}
 }
 
+static void __execlists_hold(struct i915_request *rq)
+{
+	LIST_HEAD(list);
+
+	do {
+		struct i915_dependency *p;
+
+		if (i915_request_is_active(rq))
+			__i915_request_unsubmit(rq);
+
+		RQ_TRACE(rq, "on hold\n");
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		list_move_tail(&rq->sched.link, &rq->engine->active.hold);
+		i915_request_set_hold(rq);
+
+		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+			struct i915_request *w =
+				container_of(p->waiter, typeof(*w), sched);
+
+			/* Leave semaphores spinning on the other engines */
+			if (w->engine != rq->engine)
+				continue;
+
+			if (!i915_request_is_ready(w))
+				continue;
+
+			if (i915_request_completed(w))
+				continue;
+
+			if (i915_request_on_hold(rq))
+				continue;
+
+			list_move_tail(&w->sched.link, &list);
+		}
+
+		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
+	} while (rq);
+}
+
+static bool execlists_hold(struct intel_engine_cs *engine,
+			   struct i915_request *rq)
+{
+	spin_lock_irq(&engine->active.lock);
+
+	if (i915_request_completed(rq)) { /* too late! */
+		rq = NULL;
+		goto unlock;
+	}
+
+	if (rq->engine != engine) { /* preempted virtual engine */
+		struct virtual_engine *ve = to_virtual_engine(rq->engine);
+
+		/*
+		 * intel_context_inflight() is only protected by virtue
+		 * of process_csb() being called only by the tasklet (or
+		 * directly from inside reset while the tasklet is suspended).
+		 * Assert that neither of those are allowed to run while we
+		 * poke at the request queues.
+		 */
+		GEM_BUG_ON(!reset_in_progress(&engine->execlists));
+
+		/*
+		 * An unsubmitted request along a virtual engine will
+		 * remain on the active (this) engine until we are able
+		 * to process the context switch away (and so mark the
+		 * context as no longer in flight). That cannot have happened
+		 * yet, otherwise we would not be hanging!
+		 */
+		spin_lock(&ve->base.active.lock);
+		GEM_BUG_ON(intel_context_inflight(rq->context) != engine);
+		GEM_BUG_ON(ve->request != rq);
+		ve->request = NULL;
+		spin_unlock(&ve->base.active.lock);
+		i915_request_put(rq);
+
+		rq->engine = engine;
+	}
+
+	/*
+	 * Transfer this request onto the hold queue to prevent it
+	 * being resumbitted to HW (and potentially completed) before we have
+	 * released it. Since we may have already submitted following
+	 * requests, we need to remove those as well.
+	 */
+	GEM_BUG_ON(i915_request_on_hold(rq));
+	GEM_BUG_ON(rq->engine != engine);
+	__execlists_hold(rq);
+
+unlock:
+	spin_unlock_irq(&engine->active.lock);
+	return rq;
+}
+
+static bool hold_request(const struct i915_request *rq)
+{
+	struct i915_dependency *p;
+
+	/*
+	 * If one of our ancestors is on hold, we must also be on hold,
+	 * otherwise we will bypass it and execute before it.
+	 */
+	list_for_each_entry(p, &rq->sched.signalers_list, signal_link) {
+		const struct i915_request *s =
+			container_of(p->signaler, typeof(*s), sched);
+
+		if (s->engine != rq->engine)
+			continue;
+
+		if (i915_request_on_hold(s))
+			return true;
+	}
+
+	return false;
+}
+
+static void __execlists_unhold(struct i915_request *rq)
+{
+	LIST_HEAD(list);
+
+	do {
+		struct i915_dependency *p;
+
+		GEM_BUG_ON(!i915_request_on_hold(rq));
+		GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
+
+		i915_request_clear_hold(rq);
+		list_move_tail(&rq->sched.link,
+			       i915_sched_lookup_priolist(rq->engine,
+							  rq_prio(rq)));
+		set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+		RQ_TRACE(rq, "hold release\n");
+
+		/* Also release any children on this engine that are ready */
+		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+			struct i915_request *w =
+				container_of(p->waiter, typeof(*w), sched);
+
+			if (w->engine != rq->engine)
+				continue;
+
+			if (!i915_request_on_hold(rq))
+				continue;
+
+			/* Check that no other parents are also on hold */
+			if (hold_request(rq))
+				continue;
+
+			list_move_tail(&w->sched.link, &list);
+		}
+
+		rq = list_first_entry_or_null(&list, typeof(*rq), sched.link);
+	} while (rq);
+}
+
+static void execlists_unhold(struct intel_engine_cs *engine,
+			     struct i915_request *rq)
+{
+	spin_lock_irq(&engine->active.lock);
+
+	/*
+	 * Move this request back to the priority queue, and all of its
+	 * children and grandchildren that were suspended along with it.
+	 */
+	__execlists_unhold(rq);
+
+	if (rq_prio(rq) > engine->execlists.queue_priority_hint) {
+		engine->execlists.queue_priority_hint = rq_prio(rq);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+	}
+
+	spin_unlock_irq(&engine->active.lock);
+}
+
+struct execlists_capture {
+	struct work_struct work;
+	struct i915_request *rq;
+	struct i915_gpu_coredump *error;
+};
+
+static void execlists_capture_work(struct work_struct *work)
+{
+	struct execlists_capture *cap = container_of(work, typeof(*cap), work);
+	const gfp_t gfp = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
+	struct intel_engine_cs *engine = cap->rq->engine;
+	struct intel_gt_coredump *gt = cap->error->gt;
+	struct intel_engine_capture_vma *vma;
+
+	/* Compress all the objects attached to the request, slow! */
+	vma = intel_engine_coredump_add_request(gt->engine, cap->rq, gfp);
+	if (vma) {
+		struct i915_vma_compress *compress =
+			i915_vma_capture_prepare(gt);
+
+		intel_engine_coredump_add_vma(gt->engine, vma, compress);
+		i915_vma_capture_finish(gt, compress);
+	}
+
+	gt->simulated = gt->engine->simulated;
+	cap->error->simulated = gt->simulated;
+
+	/* Publish the error state, and announce it to the world */
+	i915_error_state_store(cap->error);
+	i915_gpu_coredump_put(cap->error);
+
+	/* Return this request and all that depend upon it for signaling */
+	execlists_unhold(engine, cap->rq);
+	i915_request_put(cap->rq);
+
+	kfree(cap);
+}
+
+static struct execlists_capture *capture_regs(struct intel_engine_cs *engine)
+{
+	const gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+	struct execlists_capture *cap;
+
+	cap = kmalloc(sizeof(*cap), gfp);
+	if (!cap)
+		return NULL;
+
+	cap->error = i915_gpu_coredump_alloc(engine->i915, gfp);
+	if (!cap->error)
+		goto err_cap;
+
+	cap->error->gt = intel_gt_coredump_alloc(engine->gt, gfp);
+	if (!cap->error->gt)
+		goto err_gpu;
+
+	cap->error->gt->engine = intel_engine_coredump_alloc(engine, gfp);
+	if (!cap->error->gt->engine)
+		goto err_gt;
+
+	return cap;
+
+err_gt:
+	kfree(cap->error->gt);
+err_gpu:
+	kfree(cap->error);
+err_cap:
+	kfree(cap);
+	return NULL;
+}
+
+static bool execlists_capture(struct intel_engine_cs *engine)
+{
+	struct execlists_capture *cap;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR))
+		return true;
+
+	/*
+	 * We need to _quickly_ capture the engine state before we reset.
+	 * We are inside an atomic section (softirq) here and we are delaying
+	 * the forced preemption event.
+	 */
+	cap = capture_regs(engine);
+	if (!cap)
+		return true;
+
+	cap->rq = execlists_active(&engine->execlists);
+	GEM_BUG_ON(!cap->rq);
+
+	rcu_read_lock();
+	cap->rq = active_request(cap->rq->context->timeline, cap->rq);
+	cap->rq = i915_request_get_rcu(cap->rq);
+	rcu_read_unlock();
+	if (!cap->rq)
+		goto err_free;
+
+	/*
+	 * Remove the request from the execlists queue, and take ownership
+	 * of the request. We pass it to our worker who will _slowly_ compress
+	 * all the pages the _user_ requested for debugging their batch, after
+	 * which we return it to the queue for signaling.
+	 *
+	 * By removing them from the execlists queue, we also remove the
+	 * requests from being processed by __unwind_incomplete_requests()
+	 * during the intel_engine_reset(), and so they will *not* be replayed
+	 * afterwards.
+	 *
+	 * Note that because we have not yet reset the engine at this point,
+	 * it is possible for the request that we have identified as being
+	 * guilty, did in fact complete and we will then hit an arbitration
+	 * point allowing the outstanding preemption to succeed. The likelihood
+	 * of that is very low (as capturing of the engine registers should be
+	 * fast enough to run inside an irq-off atomic section!), so we will
+	 * simply hold that request accountable for being non-preemptible
+	 * long enough to force the reset.
+	 */
+	if (!execlists_hold(engine, cap->rq))
+		goto err_rq;
+
+	INIT_WORK(&cap->work, execlists_capture_work);
+	schedule_work(&cap->work);
+	return true;
+
+err_rq:
+	i915_request_put(cap->rq);
+err_free:
+	i915_gpu_coredump_put(cap->error);
+	kfree(cap);
+	return false;
+}
+
 static noinline void preempt_reset(struct intel_engine_cs *engine)
 {
 	const unsigned int bit = I915_RESET_ENGINE + engine->id;
@@ -2368,7 +2678,12 @@
 	ENGINE_TRACE(engine, "preempt timeout %lu+%ums\n",
 		     READ_ONCE(engine->props.preempt_timeout_ms),
 		     jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
-	intel_engine_reset(engine, "preemption time out");
+
+	ring_set_paused(engine, 1); /* Freeze the current request in place */
+	if (execlists_capture(engine))
+		intel_engine_reset(engine, "preemption time out");
+	else
+		ring_set_paused(engine, 0);
 
 	tasklet_enable(&engine->execlists.tasklet);
 	clear_and_wake_up_bit(bit, lock);
@@ -2430,11 +2745,12 @@
 }
 
 static void queue_request(struct intel_engine_cs *engine,
-			  struct i915_sched_node *node,
-			  int prio)
+			  struct i915_request *rq)
 {
-	GEM_BUG_ON(!list_empty(&node->link));
-	list_add_tail(&node->link, i915_sched_lookup_priolist(engine, prio));
+	GEM_BUG_ON(!list_empty(&rq->sched.link));
+	list_add_tail(&rq->sched.link,
+		      i915_sched_lookup_priolist(engine, rq_prio(rq)));
+	set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
 static void __submit_queue_imm(struct intel_engine_cs *engine)
@@ -2462,6 +2778,13 @@
 	__submit_queue_imm(engine);
 }
 
+static bool ancestor_on_hold(const struct intel_engine_cs *engine,
+			     const struct i915_request *rq)
+{
+	GEM_BUG_ON(i915_request_on_hold(rq));
+	return !list_empty(&engine->active.hold) && hold_request(rq);
+}
+
 static void execlists_submit_request(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
@@ -2470,12 +2793,17 @@
 	/* Will be called from irq-context when using foreign fences. */
 	spin_lock_irqsave(&engine->active.lock, flags);
 
-	queue_request(engine, &request->sched, rq_prio(request));
+	if (unlikely(ancestor_on_hold(engine, request))) {
+		list_add_tail(&request->sched.link, &engine->active.hold);
+		i915_request_set_hold(request);
+	} else {
+		queue_request(engine, request);
 
-	GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
-	GEM_BUG_ON(list_empty(&request->sched.link));
+		GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+		GEM_BUG_ON(list_empty(&request->sched.link));
 
-	submit_queue(engine, request);
+		submit_queue(engine, request);
+	}
 
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
@@ -2531,21 +2859,21 @@
 		      ce->engine);
 
 	i915_gem_object_unpin_map(ce->state->obj);
-	intel_ring_reset(ce->ring, ce->ring->tail);
 }
 
 static void
 __execlists_update_reg_state(const struct intel_context *ce,
-			     const struct intel_engine_cs *engine)
+			     const struct intel_engine_cs *engine,
+			     u32 head)
 {
 	struct intel_ring *ring = ce->ring;
 	u32 *regs = ce->lrc_reg_state;
 
-	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, head));
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
 
 	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
-	regs[CTX_RING_HEAD] = ring->head;
+	regs[CTX_RING_HEAD] = head;
 	regs[CTX_RING_TAIL] = ring->tail;
 
 	/* RPCS */
@@ -2574,7 +2902,7 @@
 
 	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, ce->ring->tail);
 
 	return 0;
 }
@@ -2615,7 +2943,7 @@
 	/* Scrub away the garbage */
 	execlists_init_reg_state(ce->lrc_reg_state,
 				 ce, ce->engine, ce->ring, true);
-	__execlists_update_reg_state(ce, ce->engine);
+	__execlists_update_reg_state(ce, ce->engine, ce->ring->tail);
 
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 }
@@ -3170,6 +3498,7 @@
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct intel_context *ce;
 	struct i915_request *rq;
+	u32 head;
 
 	mb(); /* paranoia: read the CSB pointers from after the reset */
 	clflush(execlists->csb_write);
@@ -3197,15 +3526,15 @@
 
 	if (i915_request_completed(rq)) {
 		/* Idle context; tidy up the ring so we can restart afresh */
-		ce->ring->head = intel_ring_wrap(ce->ring, rq->tail);
+		head = intel_ring_wrap(ce->ring, rq->tail);
 		goto out_replay;
 	}
 
 	/* Context has requests still in-flight; it should not be idle! */
 	GEM_BUG_ON(i915_active_is_idle(&ce->active));
 	rq = active_request(ce->timeline, rq);
-	ce->ring->head = intel_ring_wrap(ce->ring, rq->head);
-	GEM_BUG_ON(ce->ring->head == ce->ring->tail);
+	head = intel_ring_wrap(ce->ring, rq->head);
+	GEM_BUG_ON(head == ce->ring->tail);
 
 	/*
 	 * If this request hasn't started yet, e.g. it is waiting on a
@@ -3250,10 +3579,9 @@
 
 out_replay:
 	ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
-		     ce->ring->head, ce->ring->tail);
-	intel_ring_update_space(ce->ring);
+		     head, ce->ring->tail);
 	__execlists_reset_reg_state(ce, engine);
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, head);
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
 
 unwind:
@@ -3325,6 +3653,10 @@
 		i915_priolist_free(p);
 	}
 
+	/* On-hold requests will be flushed to timeline upon their release */
+	list_for_each_entry(rq, &engine->active.hold, sched.link)
+		mark_eio(rq);
+
 	/* Cancel all attached virtual engines */
 	while ((rb = rb_first_cached(&execlists->virtual))) {
 		struct virtual_engine *ve =
@@ -4892,10 +5224,7 @@
 		restore_default_state(ce, engine);
 
 	/* Rerun the request; its payload has been neutered (if guilty). */
-	ce->ring->head = head;
-	intel_ring_update_space(ce->ring);
-
-	__execlists_update_reg_state(ce, engine);
+	__execlists_update_reg_state(ce, engine, head);
 }
 
 bool
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 374b28f..6ff803f 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -145,6 +145,7 @@
 
 	kref_init(&ring->ref);
 	ring->size = size;
+	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
 
 	/*
 	 * Workaround an erratum on the i830 which causes a hang if
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index ea2839d..5bdce24 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -56,6 +56,14 @@
 	return pos & (ring->size - 1);
 }
 
+static inline int intel_ring_direction(const struct intel_ring *ring,
+				       u32 next, u32 prev)
+{
+	typecheck(typeof(ring->size), next);
+	typecheck(typeof(ring->size), prev);
+	return (next - prev) << ring->wrap;
+}
+
 static inline bool
 intel_ring_offset_valid(const struct intel_ring *ring,
 			unsigned int pos)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h
index d9f17f3..1a189ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h
@@ -39,12 +39,13 @@
 	 */
 	atomic_t pin_count;
 
-	u32 head;
-	u32 tail;
-	u32 emit;
+	u32 head; /* updated during retire, loosely tracks RING_HEAD */
+	u32 tail; /* updated on submission, used for RING_TAIL */
+	u32 emit; /* updated during request construction */
 
 	u32 space;
 	u32 size;
+	u32 wrap;
 	u32 effective_size;
 };
 
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index a560b7e..f2806381 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -59,11 +59,26 @@
 	ring->vaddr = (void *)(ring + 1);
 	atomic_set(&ring->pin_count, 1);
 
+	ring->vma = i915_vma_alloc();
+	if (!ring->vma) {
+		kfree(ring);
+		return NULL;
+	}
+	i915_active_init(&ring->vma->active, NULL, NULL);
+
 	intel_ring_update_space(ring);
 
 	return ring;
 }
 
+static void mock_ring_free(struct intel_ring *ring)
+{
+	i915_active_fini(&ring->vma->active);
+	i915_vma_free(ring->vma);
+
+	kfree(ring);
+}
+
 static struct i915_request *first_request(struct mock_engine *engine)
 {
 	return list_first_entry_or_null(&engine->hw_queue,
@@ -121,7 +136,7 @@
 	GEM_BUG_ON(intel_context_is_pinned(ce));
 
 	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
-		kfree(ce->ring);
+		mock_ring_free(ce->ring);
 		mock_timeline_unpin(ce->timeline);
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 15cda02..b292f8c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -186,7 +186,7 @@
 		}
 		GEM_BUG_ON(!ce[1]->ring->size);
 		intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2);
-		__execlists_update_reg_state(ce[1], engine);
+		__execlists_update_reg_state(ce[1], engine, ce[1]->ring->head);
 
 		rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK);
 		if (IS_ERR(rq[0])) {
@@ -285,6 +285,107 @@
 	return live_unlite_restore(arg, I915_USER_PRIORITY(I915_PRIORITY_MAX));
 }
 
+static int live_hold_reset(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	/*
+	 * In order to support offline error capture for fast preempt reset,
+	 * we need to decouple the guilty request and ensure that it and its
+	 * descendents are not executed while the capture is in progress.
+	 */
+
+	if (!intel_has_reset_engine(gt))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+		unsigned long heartbeat;
+		struct i915_request *rq;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		engine_heartbeat_disable(engine, &heartbeat);
+
+		rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out;
+		}
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(&spin, rq)) {
+			intel_gt_set_wedged(gt);
+			err = -ETIME;
+			goto out;
+		}
+
+		/* We have our request executing, now remove it and reset */
+
+		if (test_and_set_bit(I915_RESET_ENGINE + id,
+				     &gt->reset.flags)) {
+			intel_gt_set_wedged(gt);
+			err = -EBUSY;
+			goto out;
+		}
+		tasklet_disable(&engine->execlists.tasklet);
+
+		engine->execlists.tasklet.func(engine->execlists.tasklet.data);
+		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
+
+		i915_request_get(rq);
+		execlists_hold(engine, rq);
+		GEM_BUG_ON(!i915_request_on_hold(rq));
+
+		intel_engine_reset(engine, NULL);
+		GEM_BUG_ON(rq->fence.error != -EIO);
+
+		tasklet_enable(&engine->execlists.tasklet);
+		clear_and_wake_up_bit(I915_RESET_ENGINE + id,
+				      &gt->reset.flags);
+
+		/* Check that we do not resubmit the held request */
+		if (!i915_request_wait(rq, 0, HZ / 5)) {
+			pr_err("%s: on hold request completed!\n",
+			       engine->name);
+			i915_request_put(rq);
+			err = -EIO;
+			goto out;
+		}
+		GEM_BUG_ON(!i915_request_on_hold(rq));
+
+		/* But is resubmitted on release */
+		execlists_unhold(engine, rq);
+		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+			pr_err("%s: held request did not complete!\n",
+			       engine->name);
+			intel_gt_set_wedged(gt);
+			err = -ETIME;
+		}
+		i915_request_put(rq);
+
+out:
+		engine_heartbeat_enable(engine, heartbeat);
+		intel_context_put(ce);
+		if (err)
+			break;
+	}
+
+	igt_spinner_fini(&spin);
+	return err;
+}
+
 static int
 emit_semaphore_chain(struct i915_request *rq, struct i915_vma *vma, int idx)
 {
@@ -3309,12 +3410,168 @@
 	return 0;
 }
 
+static int reset_virtual_engine(struct intel_gt *gt,
+				struct intel_engine_cs **siblings,
+				unsigned int nsibling)
+{
+	struct intel_engine_cs *engine;
+	struct intel_context *ve;
+	unsigned long *heartbeat;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	unsigned int n;
+	int err = 0;
+
+	/*
+	 * In order to support offline error capture for fast preempt reset,
+	 * we need to decouple the guilty request and ensure that it and its
+	 * descendents are not executed while the capture is in progress.
+	 */
+
+	heartbeat = kmalloc_array(nsibling, sizeof(*heartbeat), GFP_KERNEL);
+	if (!heartbeat)
+		return -ENOMEM;
+
+	if (igt_spinner_init(&spin, gt)) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	ve = intel_execlists_create_virtual(siblings, nsibling);
+	if (IS_ERR(ve)) {
+		err = PTR_ERR(ve);
+		goto out_spin;
+	}
+
+	for (n = 0; n < nsibling; n++)
+		engine_heartbeat_disable(siblings[n], &heartbeat[n]);
+
+	rq = igt_spinner_create_request(&spin, ve, MI_ARB_CHECK);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_heartbeat;
+	}
+	i915_request_add(rq);
+
+	if (!igt_wait_for_spinner(&spin, rq)) {
+		intel_gt_set_wedged(gt);
+		err = -ETIME;
+		goto out_heartbeat;
+	}
+
+	engine = rq->engine;
+	GEM_BUG_ON(engine == ve->engine);
+
+	/* Take ownership of the reset and tasklet */
+	if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
+			     &gt->reset.flags)) {
+		intel_gt_set_wedged(gt);
+		err = -EBUSY;
+		goto out_heartbeat;
+	}
+	tasklet_disable(&engine->execlists.tasklet);
+
+	engine->execlists.tasklet.func(engine->execlists.tasklet.data);
+	GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
+
+	/* Fake a preemption event; failed of course */
+	spin_lock_irq(&engine->active.lock);
+	__unwind_incomplete_requests(engine);
+	spin_unlock_irq(&engine->active.lock);
+	GEM_BUG_ON(rq->engine != ve->engine);
+
+	/* Reset the engine while keeping our active request on hold */
+	execlists_hold(engine, rq);
+	GEM_BUG_ON(!i915_request_on_hold(rq));
+
+	intel_engine_reset(engine, NULL);
+	GEM_BUG_ON(rq->fence.error != -EIO);
+
+	/* Release our grasp on the engine, letting CS flow again */
+	tasklet_enable(&engine->execlists.tasklet);
+	clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags);
+
+	/* Check that we do not resubmit the held request */
+	i915_request_get(rq);
+	if (!i915_request_wait(rq, 0, HZ / 5)) {
+		pr_err("%s: on hold request completed!\n",
+		       engine->name);
+		intel_gt_set_wedged(gt);
+		err = -EIO;
+		goto out_rq;
+	}
+	GEM_BUG_ON(!i915_request_on_hold(rq));
+
+	/* But is resubmitted on release */
+	execlists_unhold(engine, rq);
+	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		pr_err("%s: held request did not complete!\n",
+		       engine->name);
+		intel_gt_set_wedged(gt);
+		err = -ETIME;
+	}
+
+out_rq:
+	i915_request_put(rq);
+out_heartbeat:
+	for (n = 0; n < nsibling; n++)
+		engine_heartbeat_enable(siblings[n], heartbeat[n]);
+
+	intel_context_put(ve);
+out_spin:
+	igt_spinner_fini(&spin);
+out_free:
+	kfree(heartbeat);
+	return err;
+}
+
+static int live_virtual_reset(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
+	unsigned int class, inst;
+
+	/*
+	 * Check that we handle a reset event within a virtual engine.
+	 * Only the physical engine is reset, but we have to check the flow
+	 * of the virtual requests around the reset, and make sure it is not
+	 * forgotten.
+	 */
+
+	if (USES_GUC_SUBMISSION(gt->i915))
+		return 0;
+
+	if (!intel_has_reset_engine(gt))
+		return 0;
+
+	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
+		int nsibling, err;
+
+		nsibling = 0;
+		for (inst = 0; inst <= MAX_ENGINE_INSTANCE; inst++) {
+			if (!gt->engine_class[class][inst])
+				continue;
+
+			siblings[nsibling++] = gt->engine_class[class][inst];
+		}
+		if (nsibling < 2)
+			continue;
+
+		err = reset_virtual_engine(gt, siblings, nsibling);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 int intel_execlists_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_sanitycheck),
 		SUBTEST(live_unlite_switch),
 		SUBTEST(live_unlite_preempt),
+		SUBTEST(live_hold_reset),
 		SUBTEST(live_timeslice_preempt),
 		SUBTEST(live_timeslice_queue),
 		SUBTEST(live_busywait_preempt),
@@ -3333,6 +3590,7 @@
 		SUBTEST(live_virtual_mask),
 		SUBTEST(live_virtual_preserved),
 		SUBTEST(live_virtual_bond),
+		SUBTEST(live_virtual_reset),
 	};
 
 	if (!HAS_EXECLISTS(i915))
diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c
index 049775e..b0c1fda 100644
--- a/drivers/gpu/drm/i915/gvt/firmware.c
+++ b/drivers/gpu/drm/i915/gvt/firmware.c
@@ -146,7 +146,7 @@
 		clean_firmware_sysfs(gvt);
 
 	kfree(gvt->firmware.cfg_space);
-	kfree(gvt->firmware.mmio);
+	vfree(gvt->firmware.mmio);
 }
 
 static int verify_firmware(struct intel_gvt *gvt,
@@ -229,7 +229,7 @@
 
 	firmware->cfg_space = mem;
 
-	mem = kmalloc(info->mmio_size, GFP_KERNEL);
+	mem = vmalloc(info->mmio_size);
 	if (!mem) {
 		kfree(path);
 		kfree(firmware->cfg_space);
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 34cb404..4a48280 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1956,7 +1956,11 @@
 
 	if (mm->type == INTEL_GVT_MM_PPGTT) {
 		list_del(&mm->ppgtt_mm.list);
+
+		mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
 		list_del(&mm->ppgtt_mm.lru_list);
+		mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
+
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index f3da5c0..b0a4997 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -416,13 +416,15 @@
 	if (err)
 		return err;
 
-	if (!atomic_read(&ref->count) && ref->active)
-		err = ref->active(ref);
-	if (!err) {
-		spin_lock_irq(&ref->tree_lock); /* vs __active_retire() */
-		debug_active_activate(ref);
-		atomic_inc(&ref->count);
-		spin_unlock_irq(&ref->tree_lock);
+	if (likely(!i915_active_acquire_if_busy(ref))) {
+		if (ref->active)
+			err = ref->active(ref);
+		if (!err) {
+			spin_lock_irq(&ref->tree_lock); /* __active_retire() */
+			debug_active_activate(ref);
+			atomic_inc(&ref->count);
+			spin_unlock_irq(&ref->tree_lock);
+		}
 	}
 
 	mutex_unlock(&ref->mutex);
@@ -605,7 +607,7 @@
 					    struct intel_engine_cs *engine)
 {
 	intel_engine_mask_t tmp, mask = engine->mask;
-	struct llist_node *pos = NULL, *next;
+	struct llist_node *first = NULL, *last = NULL;
 	struct intel_gt *gt = engine->gt;
 	int err;
 
@@ -623,6 +625,7 @@
 	 */
 	for_each_engine_masked(engine, gt, mask, tmp) {
 		u64 idx = engine->kernel_context->timeline->fence_context;
+		struct llist_node *prev = first;
 		struct active_node *node;
 
 		node = reuse_idle_barrier(ref, idx);
@@ -656,23 +659,23 @@
 		GEM_BUG_ON(rcu_access_pointer(node->base.fence) != ERR_PTR(-EAGAIN));
 
 		GEM_BUG_ON(barrier_to_engine(node) != engine);
-		next = barrier_to_ll(node);
-		next->next = pos;
-		if (!pos)
-			pos = next;
+		first = barrier_to_ll(node);
+		first->next = prev;
+		if (!last)
+			last = first;
 		intel_engine_pm_get(engine);
 	}
 
 	GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers));
-	llist_add_batch(next, pos, &ref->preallocated_barriers);
+	llist_add_batch(first, last, &ref->preallocated_barriers);
 
 	return 0;
 
 unwind:
-	while (pos) {
-		struct active_node *node = barrier_from_ll(pos);
+	while (first) {
+		struct active_node *node = barrier_from_ll(first);
 
-		pos = pos->next;
+		first = first->next;
 
 		atomic_dec(&ref->count);
 		intel_engine_pm_put(barrier_to_engine(node));
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index b571f67..51e1e854 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -188,6 +188,12 @@
 bool i915_active_acquire_if_busy(struct i915_active *ref);
 void i915_active_release(struct i915_active *ref);
 
+static inline void __i915_active_acquire(struct i915_active *ref)
+{
+	GEM_BUG_ON(!atomic_read(&ref->count));
+	atomic_inc(&ref->count);
+}
+
 static inline bool
 i915_active_is_idle(const struct i915_active *ref)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 94f993e..5f6e639 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -180,7 +180,7 @@
 		     struct drm_i915_gem_pwrite *args,
 		     struct drm_file *file)
 {
-	void *vaddr = obj->phys_handle->vaddr + args->offset;
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
 
 	/*
@@ -265,7 +265,10 @@
 						    DRM_FORMAT_MOD_LINEAR))
 		args->pitch = ALIGN(args->pitch, 4096);
 
-	args->size = args->pitch * args->height;
+	if (args->pitch < args->width)
+		return -EINVAL;
+
+	args->size = mul_u32_u32(args->pitch, args->height);
 
 	mem_type = INTEL_MEMORY_SYSTEM;
 	if (HAS_LMEM(to_i915(dev)))
@@ -841,10 +844,10 @@
 		ret = i915_gem_gtt_pwrite_fast(obj, args);
 
 	if (ret == -EFAULT || ret == -ENOSPC) {
-		if (obj->phys_handle)
-			ret = i915_gem_phys_pwrite(obj, args, file);
-		else
+		if (i915_gem_object_has_struct_page(obj))
 			ret = i915_gem_shmem_pwrite(obj, args);
+		else
+			ret = i915_gem_phys_pwrite(obj, args, file);
 	}
 
 	i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 4c1836f..9e401a5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1681,7 +1681,7 @@
 			"GPU HANG: ecode %d:%x:%08x",
 			INTEL_GEN(error->i915), engines,
 			generate_ecode(first));
-	if (first) {
+	if (first && first->context.pid) {
 		/* Just show the first executing process, more is confusing */
 		len += scnprintf(error->error_msg + len,
 				 sizeof(error->error_msg) - len,
@@ -1852,7 +1852,8 @@
 	if (!xchg(&warned, true) &&
 	    ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
 		pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
-		pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+		pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n");
+		pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n");
 		pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
 		pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n");
 		pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n",
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 9109004..e4a6afe 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -314,8 +314,11 @@
 }
 
 static inline void
-i915_error_state_store(struct drm_i915_private *i915,
-		       struct i915_gpu_coredump *error)
+i915_error_state_store(struct i915_gpu_coredump *error)
+{
+}
+
+static inline void i915_gpu_coredump_put(struct i915_gpu_coredump *gpu)
 {
 }
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 28a82c8..ec02994 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -637,8 +637,10 @@
 		container_of(event->pmu, typeof(*i915), pmu.base);
 	unsigned int bit = event_enabled_bit(event);
 	struct i915_pmu *pmu = &i915->pmu;
+	intel_wakeref_t wakeref;
 	unsigned long flags;
 
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	spin_lock_irqsave(&pmu->lock, flags);
 
 	/*
@@ -648,6 +650,14 @@
 	BUILD_BUG_ON(ARRAY_SIZE(pmu->enable_count) != I915_PMU_MASK_BITS);
 	GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count));
 	GEM_BUG_ON(pmu->enable_count[bit] == ~0);
+
+	if (pmu->enable_count[bit] == 0 &&
+	    config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) {
+		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = 0;
+		pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt);
+		pmu->sleep_last = ktime_get();
+	}
+
 	pmu->enable |= BIT_ULL(bit);
 	pmu->enable_count[bit]++;
 
@@ -688,6 +698,8 @@
 	 * an existing non-zero value.
 	 */
 	local64_set(&event->hw.prev_count, __i915_pmu_event_read(event));
+
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
 static void i915_pmu_disable(struct perf_event *event)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index be185886..f56b046 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -221,6 +221,8 @@
 		locked = engine;
 	}
 	list_del_init(&rq->sched.link);
+	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
 	spin_unlock_irq(&locked->active.lock);
 }
 
@@ -408,8 +410,10 @@
 xfer:	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) {
 		list_move_tail(&request->sched.link, &engine->active.requests);
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
+	}
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -591,6 +595,8 @@
 	i915_sw_fence_init(&rq->submit, submit_notify);
 	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
 
+	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
+
 	rq->file_priv = NULL;
 	rq->capture_list = NULL;
 
@@ -649,25 +655,30 @@
 		}
 	}
 
-	ret = intel_timeline_get_seqno(tl, rq, &seqno);
-	if (ret)
-		goto err_free;
-
 	rq->i915 = ce->engine->i915;
 	rq->context = ce;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
+	kref_init(&rq->fence.refcount);
+	rq->fence.flags = 0;
+	rq->fence.error = 0;
+	INIT_LIST_HEAD(&rq->fence.cb_list);
+
+	ret = intel_timeline_get_seqno(tl, rq, &seqno);
+	if (ret)
+		goto err_free;
+
+	rq->fence.context = tl->fence_context;
+	rq->fence.seqno = seqno;
+
 	RCU_INIT_POINTER(rq->timeline, tl);
 	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
-	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
-		       tl->fence_context, seqno);
-
 	/* We bump the ref for the fence chain */
 	i915_sw_fence_reinit(&i915_request_get(rq)->submit);
 	i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 0314336..f57eadc 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -71,6 +71,18 @@
 	I915_FENCE_FLAG_ACTIVE = DMA_FENCE_FLAG_USER_BITS,
 
 	/*
+	 * I915_FENCE_FLAG_PQUEUE - this request is ready for execution
+	 *
+	 * Using the scheduler, when a request is ready for execution it is put
+	 * into the priority queue, and removed from that queue when transferred
+	 * to the HW runlists. We want to track its membership within the
+	 * priority queue so that we can easily check before rescheduling.
+	 *
+	 * See i915_request_in_priority_queue()
+	 */
+	I915_FENCE_FLAG_PQUEUE,
+
+	/*
 	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
 	 *
 	 * Internal bookkeeping used by the breadcrumb code to track when
@@ -79,6 +91,13 @@
 	I915_FENCE_FLAG_SIGNAL,
 
 	/*
+	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
+	 *
+	 * This request has been suspended, pending an ongoing investigation.
+	 */
+	I915_FENCE_FLAG_HOLD,
+
+	/*
 	 * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted
 	 *
 	 * The execution of some requests should not be interrupted. This is
@@ -361,6 +380,11 @@
 	return test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
 }
 
+static inline bool i915_request_in_priority_queue(const struct i915_request *rq)
+{
+	return test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+}
+
 /**
  * Returns true if seq1 is later than seq2.
  */
@@ -454,6 +478,27 @@
 	return __i915_request_has_started(rq);
 }
 
+/**
+ * i915_request_is_running - check if the request is ready for execution
+ * @rq: the request
+ *
+ * Upon construction, the request is instructed to wait upon various
+ * signals before it is ready to be executed by the HW. That is, we do
+ * not want to start execution and read data before it is written. In practice,
+ * this is controlled with a mixture of interrupts and semaphores. Once
+ * the submit fence is completed, the backend scheduler will place the
+ * request into its queue and from there submit it for execution. So we
+ * can detect when a request is eligible for execution (and is under control
+ * of the scheduler) by querying where it is in any of the scheduler's lists.
+ *
+ * Returns true if the request is ready for execution (it may be inflight),
+ * false otherwise.
+ */
+static inline bool i915_request_is_ready(const struct i915_request *rq)
+{
+	return !list_empty(&rq->sched.link);
+}
+
 static inline bool i915_request_completed(const struct i915_request *rq)
 {
 	if (i915_request_signaled(rq))
@@ -483,6 +528,21 @@
 	return unlikely(test_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags));
 }
 
+static inline bool i915_request_on_hold(const struct i915_request *rq)
+{
+	return unlikely(test_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags));
+}
+
+static inline void i915_request_set_hold(struct i915_request *rq)
+{
+	set_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
+}
+
+static inline void i915_request_clear_hold(struct i915_request *rq)
+{
+	clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
+}
+
 static inline struct intel_timeline *
 i915_request_timeline(struct i915_request *rq)
 {
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index bf87c70b..34b654b 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -326,20 +326,18 @@
 
 		node->attr.priority = prio;
 
-		if (list_empty(&node->link)) {
-			/*
-			 * If the request is not in the priolist queue because
-			 * it is not yet runnable, then it doesn't contribute
-			 * to our preemption decisions. On the other hand,
-			 * if the request is on the HW, it too is not in the
-			 * queue; but in that case we may still need to reorder
-			 * the inflight requests.
-			 */
+		/*
+		 * Once the request is ready, it will be placed into the
+		 * priority lists and then onto the HW runlist. Before the
+		 * request is ready, it does not contribute to our preemption
+		 * decisions and we can safely ignore it, as it will, and
+		 * any preemption required, be dealt with upon submission.
+		 * See engine->submit_request()
+		 */
+		if (list_empty(&node->link))
 			continue;
-		}
 
-		if (!intel_engine_is_virtual(engine) &&
-		    !i915_request_is_active(node_to_request(node))) {
+		if (i915_request_in_priority_queue(node_to_request(node))) {
 			if (!cache.priolist)
 				cache.priolist =
 					i915_sched_lookup_priolist(engine,
@@ -425,8 +423,6 @@
 
 	if (!node_signaled(signal)) {
 		INIT_LIST_HEAD(&dep->dfs_link);
-		list_add(&dep->wait_link, &signal->waiters_list);
-		list_add(&dep->signal_link, &node->signalers_list);
 		dep->signaler = signal;
 		dep->waiter = node;
 		dep->flags = flags;
@@ -436,6 +432,10 @@
 		    !node_started(signal))
 			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 
+		/* All set, now publish. Beware the lockless walkers. */
+		list_add(&dep->signal_link, &node->signalers_list);
+		list_add_rcu(&dep->wait_link, &signal->waiters_list);
+
 		/*
 		 * As we do not allow WAIT to preempt inflight requests,
 		 * once we have executed a request, along with triggering
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index c47261a..632d695 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -8,9 +8,8 @@
 #include "i915_drv.h"
 #include "i915_utils.h"
 
-#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
-#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
-		    "providing the dmesg log by booting with drm.debug=0xf"
+#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs"
+#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details."
 
 void
 __i915_printk(struct drm_i915_private *dev_priv, const char *level,
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 17d7c52..4ff3807 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1202,16 +1202,26 @@
 	if (ret)
 		return ret;
 
-	GEM_BUG_ON(i915_vma_is_active(vma));
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
 		return -EAGAIN;
 	}
 
-	GEM_BUG_ON(i915_vma_is_active(vma));
+	/*
+	 * After confirming that no one else is pinning this vma, wait for
+	 * any laggards who may have crept in during the wait (through
+	 * a residual pin skipping the vm->mutex) to complete.
+	 */
+	ret = i915_vma_sync(vma);
+	if (ret)
+		return ret;
+
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
 
+	GEM_BUG_ON(i915_vma_is_pinned(vma));
+	GEM_BUG_ON(i915_vma_is_active(vma));
+
 	if (i915_vma_is_map_and_fenceable(vma)) {
 		/*
 		 * Check that we have flushed all writes through the GGTT
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 983afea..748cd37 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -796,12 +796,41 @@
 	return true;
 }
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if (!a6xx_has_gbif(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/* The GBIF halt needs to be explicitly cleared */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 /* Gracefully try to shut down the GMU and by extension the GPU */
 static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 {
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
-	struct msm_gpu *gpu = &adreno_gpu->base;
 	u32 val;
 
 	/*
@@ -819,11 +848,7 @@
 			return;
 		}
 
-		/* Clear the VBIF pipe before shutting down */
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf)
-			== 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+		a6xx_bus_clear_pending_transactions(adreno_gpu);
 
 		/* tell the GMU we want to slumber */
 		a6xx_gmu_notify_slumber(gmu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index daf0780..68af241 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -378,18 +378,6 @@
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
-	/*
-	 * During a previous slumber, GBIF halt is asserted to ensure
-	 * no further transaction can go through GPU before GPU
-	 * headswitch is turned off.
-	 *
-	 * This halt is deasserted once headswitch goes off but
-	 * incase headswitch doesn't goes off clear GBIF halt
-	 * here to ensure GPU wake-up doesn't fail because of
-	 * halted GPU transactions.
-	 */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
@@ -470,10 +458,12 @@
 	/* Select CP0 to always count cycles */
 	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
 
-	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+	if (adreno_is_a630(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+	}
 
 	/* Enable fault detection */
 	gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL,
@@ -748,39 +738,6 @@
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
-#define GBIF_CLIENT_HALT_MASK             BIT(0)
-#define GBIF_ARB_HALT_MASK                BIT(1)
-
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
-{
-	struct msm_gpu *gpu = &adreno_gpu->base;
-
-	if(!a6xx_has_gbif(adreno_gpu)){
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
-								0xf) == 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
-
-		return;
-	}
-
-	/* Halt new client requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
-	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
-
-	/* Halt all AXI requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
-	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
-
-	/*
-	 * GMU needs DDR access in slumber path. Deassert GBIF halt now
-	 * to allow for GMU to access system memory.
-	 */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-}
-
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -805,16 +762,6 @@
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
-	/*
-	 * Make sure the GMU is idle before continuing (because some transitions
-	 * may use VBIF
-	 */
-	a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
-
-	/* Clear the VBIF pipe before shutting down */
-	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
-	a6xx_bus_clear_pending_transactions(adreno_gpu);
-
 	return a6xx_gmu_stop(a6xx_gpu);
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index eda11ab..e450e0b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -7,6 +7,7 @@
 
 #include "a6xx_gmu.h"
 #include "a6xx_gmu.xml.h"
+#include "a6xx_gpu.h"
 
 #define HFI_MSG_ID(val) [val] = #val
 
@@ -216,48 +217,82 @@
 		NULL, 0);
 }
 
-static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
-	struct a6xx_hfi_msg_bw_table msg = { 0 };
+	/* Send a single "off" entry since the 618 GMU doesn't do bus scaling */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x01;
+
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5003c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
 
 	/*
-	 * The sdm845 GMU doesn't do bus frequency scaling on its own but it
-	 * does need at least one entry in the list because it might be accessed
-	 * when the GMU is shutting down. Send a single "off" entry.
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
 	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
 
-	msg.bw_level_num = 1;
+	msg->cnoc_cmds_addrs[0] = 0x5007c;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 
-	msg.ddr_cmds_num = 3;
-	msg.ddr_wait_bitmask = 0x07;
+static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
+	msg->bw_level_num = 1;
 
-	msg.ddr_cmds_addrs[0] = 0x50000;
-	msg.ddr_cmds_addrs[1] = 0x5005c;
-	msg.ddr_cmds_addrs[2] = 0x5000c;
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x07;
 
-	msg.ddr_cmds_data[0][0] =  0x40000000;
-	msg.ddr_cmds_data[0][1] =  0x40000000;
-	msg.ddr_cmds_data[0][2] =  0x40000000;
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5005c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
 
 	/*
 	 * These are the CX (CNOC) votes.  This is used but the values for the
 	 * sdm845 GMU are known and fixed so we can hard code them.
 	 */
 
-	msg.cnoc_cmds_num = 3;
-	msg.cnoc_wait_bitmask = 0x05;
+	msg->cnoc_cmds_num = 3;
+	msg->cnoc_wait_bitmask = 0x05;
 
-	msg.cnoc_cmds_addrs[0] = 0x50034;
-	msg.cnoc_cmds_addrs[1] = 0x5007c;
-	msg.cnoc_cmds_addrs[2] = 0x5004c;
+	msg->cnoc_cmds_addrs[0] = 0x50034;
+	msg->cnoc_cmds_addrs[1] = 0x5007c;
+	msg->cnoc_cmds_addrs[2] = 0x5004c;
 
-	msg.cnoc_cmds_data[0][0] =  0x40000000;
-	msg.cnoc_cmds_data[0][1] =  0x00000000;
-	msg.cnoc_cmds_data[0][2] =  0x40000000;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[0][1] =  0x00000000;
+	msg->cnoc_cmds_data[0][2] =  0x40000000;
 
-	msg.cnoc_cmds_data[1][0] =  0x60000001;
-	msg.cnoc_cmds_data[1][1] =  0x20000001;
-	msg.cnoc_cmds_data[1][2] =  0x60000001;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+	msg->cnoc_cmds_data[1][1] =  0x20000001;
+	msg->cnoc_cmds_data[1][2] =  0x60000001;
+}
+
+
+static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+{
+	struct a6xx_hfi_msg_bw_table msg = { 0 };
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+
+	if (adreno_is_a618(adreno_gpu))
+		a618_build_bw_table(&msg);
+	else
+		a6xx_build_bw_table(&msg);
 
 	return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg),
 		NULL, 0);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 5286326..a05282d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -255,13 +255,13 @@
 
 	INTERLEAVED_RGB_FMT(RGB565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
 	INTERLEAVED_RGB_FMT(BGR565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
index 29705e7..80d3cfc 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -12,6 +12,7 @@
 
 #define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
 
+#define HW_REV				0x0
 #define HW_INTR_STATUS			0x0010
 
 /* Max BW defined in KBps */
@@ -22,6 +23,17 @@
 	struct irq_domain *domain;
 };
 
+struct dpu_hw_cfg {
+	u32 val;
+	u32 offset;
+};
+
+struct dpu_mdss_hw_init_handler {
+	u32 hw_rev;
+	u32 hw_reg_count;
+	struct dpu_hw_cfg* hw_cfg;
+};
+
 struct dpu_mdss {
 	struct msm_mdss base;
 	void __iomem *mmio;
@@ -32,6 +44,44 @@
 	u32 num_paths;
 };
 
+static struct dpu_hw_cfg hw_cfg[] = {
+    {
+	/* UBWC global settings */
+	.val = 0x1E,
+	.offset = 0x144,
+    }
+};
+
+static struct dpu_mdss_hw_init_handler cfg_handler[] = {
+    { .hw_rev = DPU_HW_VER_620,
+      .hw_reg_count = ARRAY_SIZE(hw_cfg),
+      .hw_cfg = hw_cfg
+    },
+};
+
+static void dpu_mdss_hw_init(struct dpu_mdss *dpu_mdss, u32 hw_rev)
+{
+	int i;
+	u32 count = 0;
+	struct dpu_hw_cfg *hw_cfg = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev) {
+			hw_cfg = cfg_handler[i].hw_cfg;
+			count = cfg_handler[i].hw_reg_count;
+			break;
+	    }
+	}
+
+	for (i = 0; i < count; i++ ) {
+		writel_relaxed(hw_cfg->val,
+			dpu_mdss->mmio + hw_cfg->offset);
+		hw_cfg++;
+	}
+
+    return;
+}
+
 static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev,
 						struct dpu_mdss *dpu_mdss)
 {
@@ -174,12 +224,18 @@
 	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
 	struct dss_module_power *mp = &dpu_mdss->mp;
 	int ret;
+	u32 mdss_rev;
 
 	dpu_mdss_icc_request_bw(mdss);
 
 	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
-	if (ret)
+	if (ret) {
 		DPU_ERROR("clock enable failed, ret:%d\n", ret);
+		return ret;
+	}
+
+	mdss_rev = readl_relaxed(dpu_mdss->mmio + HW_REV);
+	dpu_mdss_hw_init(dpu_mdss, mdss_rev);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 05cc04f..e1cc541 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1109,8 +1109,8 @@
 	ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion,
 						msecs_to_jiffies(50));
 	if (ret == 0)
-		dev_warn(dev->dev, "pp done time out, lm=%d\n",
-			 mdp5_cstate->pipeline.mixer->lm);
+		dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n",
+				     mdp5_cstate->pipeline.mixer->lm);
 }
 
 static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 104115d..4864b95 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -336,7 +336,7 @@
 	return num;
 }
 
-static int dsi_mgr_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	int id = dsi_mgr_connector_get_id(connector);
@@ -506,6 +506,7 @@
 	struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
+	struct msm_dsi_pll *src_pll;
 	bool is_dual_dsi = IS_DUAL_DSI();
 	int ret;
 
@@ -539,6 +540,10 @@
 								id, ret);
 	}
 
+	/* Save PLL status if it is a clock source */
+	src_pll = msm_dsi_phy_get_pll(msm_dsi->phy);
+	msm_dsi_pll_save_state(src_pll);
+
 	ret = msm_dsi_host_power_off(host);
 	if (ret)
 		pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index b0cfa67..f509ebd 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -724,10 +724,6 @@
 	if (!phy || !phy->cfg->ops.disable)
 		return;
 
-	/* Save PLL status if it is a clock source */
-	if (phy->usecase != MSM_DSI_PHY_SLAVE)
-		msm_dsi_pll_save_state(phy->pll);
-
 	phy->cfg->ops.disable(phy);
 
 	dsi_phy_regulator_disable(phy);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index 1c89454..6ac04fc 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -411,6 +411,12 @@
 	if (pll_10nm->slave)
 		dsi_pll_enable_pll_bias(pll_10nm->slave);
 
+	rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
+	if (rc) {
+		pr_err("vco_set_rate failed, rc=%d\n", rc);
+		return rc;
+	}
+
 	/* Start PLL */
 	pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL,
 		  0x01);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index c26219c..e4b750b 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -441,6 +441,14 @@
 	if (ret)
 		goto err_msm_uninit;
 
+	if (!dev->dma_parms) {
+		dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms),
+					      GFP_KERNEL);
+		if (!dev->dma_parms)
+			return -ENOMEM;
+	}
+	dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
+
 	msm_gem_shrinker_init(ddev);
 
 	switch (get_mdp_ver(pdev)) {
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 8903152..bb737f9 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -458,6 +458,8 @@
 		asyw->clr.ntfy = armw->ntfy.handle != 0;
 		asyw->clr.sema = armw->sema.handle != 0;
 		asyw->clr.xlut = armw->xlut.handle != 0;
+		if (asyw->clr.xlut && asyw->visible)
+			asyw->set.xlut = asyw->xlut.handle != 0;
 		asyw->clr.csc  = armw->csc.valid;
 		if (wndw->func->image_clr)
 			asyw->clr.image = armw->image.handle[0] != 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index c7d700916..8ebbe16 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2579,6 +2579,7 @@
 static const struct nvkm_device_chip
 nv167_chipset = {
 	.name = "TU117",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2607,6 +2608,7 @@
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
+	.gr = tu102_gr_new,
 	.nvdec[0] = gm107_nvdec_new,
 	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
@@ -2615,6 +2617,7 @@
 static const struct nvkm_device_chip
 nv168_chipset = {
 	.name = "TU116",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2643,6 +2646,7 @@
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
+	.gr = tu102_gr_new,
 	.nvdec[0] = gm107_nvdec_new,
 	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
index 454668b..a9efa4d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
@@ -164,6 +164,32 @@
 MODULE_FIRMWARE("nvidia/tu106/gr/sw_bundle_init.bin");
 MODULE_FIRMWARE("nvidia/tu106/gr/sw_method_init.bin");
 
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_method_init.bin");
+
 static const struct gf100_gr_fwif
 tu102_gr_fwif[] = {
 	{ 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
index 7f4b89d..d28d8f3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
@@ -107,6 +107,12 @@
 MODULE_FIRMWARE("nvidia/tu106/acr/unload_bl.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/ucode_unload.bin");
 
+MODULE_FIRMWARE("nvidia/tu116/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/tu117/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_unload.bin");
+
 static const struct nvkm_acr_hsf_fwif
 tu102_acr_unload_fwif[] = {
 	{  0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 },
@@ -130,6 +136,8 @@
 MODULE_FIRMWARE("nvidia/tu102/acr/ucode_asb.bin");
 MODULE_FIRMWARE("nvidia/tu104/acr/ucode_asb.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_asb.bin");
 
 static const struct nvkm_acr_hsf_fwif
 tu102_acr_asb_fwif[] = {
@@ -154,6 +162,12 @@
 MODULE_FIRMWARE("nvidia/tu106/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/ucode_ahesasc.bin");
 
+MODULE_FIRMWARE("nvidia/tu116/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_ahesasc.bin");
+
+MODULE_FIRMWARE("nvidia/tu117/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_ahesasc.bin");
+
 static const struct nvkm_acr_hsf_fwif
 tu102_acr_ahesasc_fwif[] = {
 	{  0, nvkm_acr_hsfw_load, &tu102_acr_ahesasc_0 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
index 389bad3..10ff5d05 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -51,3 +51,5 @@
 MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin");
 MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin");
 MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin");
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 6da59f4..b7a618d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -166,6 +166,7 @@
 			break;
 		}
 
+		atomic_inc(&bo->gpu_usecount);
 		job->mappings[i] = mapping;
 	}
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index ca1bc90..b3517ff 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -30,6 +30,12 @@
 		struct mutex lock;
 	} mappings;
 
+	/*
+	 * Count the number of jobs referencing this BO so we don't let the
+	 * shrinker reclaim this object prematurely.
+	 */
+	atomic_t gpu_usecount;
+
 	bool noexec		:1;
 	bool is_heap		:1;
 };
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index f5dd7b2..288e46c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -41,6 +41,9 @@
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 
+	if (atomic_read(&bo->gpu_usecount))
+		return false;
+
 	if (!mutex_trylock(&shmem->pages_lock))
 		return false;
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 7c36ec6..9a1a72a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -269,18 +269,19 @@
 	dma_fence_put(job->render_done_fence);
 
 	if (job->mappings) {
-		for (i = 0; i < job->bo_count; i++)
+		for (i = 0; i < job->bo_count; i++) {
+			if (!job->mappings[i])
+				break;
+
+			atomic_dec(&job->mappings[i]->obj->gpu_usecount);
 			panfrost_gem_mapping_put(job->mappings[i]);
+		}
 		kvfree(job->mappings);
 	}
 
 	if (job->bos) {
-		struct panfrost_gem_object *bo;
-
-		for (i = 0; i < job->bo_count; i++) {
-			bo = to_panfrost_bo(job->bos[i]);
+		for (i = 0; i < job->bo_count; i++)
 			drm_gem_object_put_unlocked(job->bos[i]);
-		}
 
 		kvfree(job->bos);
 	}
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 763cfca..3107b07 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -151,7 +151,12 @@
 	as = mmu->as;
 	if (as >= 0) {
 		int en = atomic_inc_return(&mmu->as_count);
-		WARN_ON(en >= NUM_JOB_SLOTS);
+
+		/*
+		 * AS can be retained by active jobs or a perfcnt context,
+		 * hence the '+ 1' here.
+		 */
+		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
 
 		list_move(&mmu->list, &pfdev->as_lru_list);
 		goto out;
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 6848204..6913578 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -73,7 +73,7 @@
 	struct panfrost_file_priv *user = file_priv->driver_priv;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 	struct drm_gem_shmem_object *bo;
-	u32 cfg;
+	u32 cfg, as;
 	int ret;
 
 	if (user == perfcnt->user)
@@ -126,12 +126,8 @@
 
 	perfcnt->user = user;
 
-	/*
-	 * Always use address space 0 for now.
-	 * FIXME: this needs to be updated when we start using different
-	 * address space.
-	 */
-	cfg = GPU_PERFCNT_CFG_AS(0) |
+	as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu);
+	cfg = GPU_PERFCNT_CFG_AS(as) |
 	      GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL);
 
 	/*
@@ -195,6 +191,7 @@
 	drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf);
 	perfcnt->buf = NULL;
 	panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
+	panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
 	panfrost_gem_mapping_put(perfcnt->mapping);
 	perfcnt->mapping = NULL;
 	pm_runtime_mark_last_busy(pfdev->dev);
diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
index ceac7af..29e367d 100644
--- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
@@ -53,6 +53,7 @@
 cmdline_test(drm_cmdline_test_rotate_90)
 cmdline_test(drm_cmdline_test_rotate_180)
 cmdline_test(drm_cmdline_test_rotate_270)
+cmdline_test(drm_cmdline_test_rotate_multiple)
 cmdline_test(drm_cmdline_test_rotate_invalid_val)
 cmdline_test(drm_cmdline_test_rotate_truncated)
 cmdline_test(drm_cmdline_test_hmirror)
diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
index 520f3e6..d96cd89 100644
--- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
+++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
@@ -856,6 +856,17 @@
 	return 0;
 }
 
+static int drm_cmdline_test_rotate_multiple(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(drm_mode_parse_command_line_for_connector("720x480,rotate=0,rotate=90",
+							  &no_connector,
+							  &mode));
+
+	return 0;
+}
+
 static int drm_cmdline_test_rotate_invalid_val(void *ignored)
 {
 	struct drm_cmdline_mode mode = { };
@@ -888,7 +899,7 @@
 	FAIL_ON(!mode.specified);
 	FAIL_ON(mode.xres != 720);
 	FAIL_ON(mode.yres != 480);
-	FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_X);
+	FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X));
 
 	FAIL_ON(mode.refresh_specified);
 
@@ -913,7 +924,7 @@
 	FAIL_ON(!mode.specified);
 	FAIL_ON(mode.xres != 720);
 	FAIL_ON(mode.yres != 480);
-	FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_Y);
+	FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y));
 
 	FAIL_ON(mode.refresh_specified);
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 5ae67d5..328272f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -85,7 +85,6 @@
 	}
 
 	drm_mode_config_init(drm);
-	drm->mode_config.allow_fb_modifiers = true;
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret) {
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 5bd60ded..909eba4 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -196,9 +196,10 @@
 		return ERR_CAST(obj);
 
 	ret = drm_gem_handle_create(file, &obj->base, handle);
-	drm_gem_object_put_unlocked(&obj->base);
-	if (ret)
+	if (ret) {
+		drm_gem_object_put_unlocked(&obj->base);
 		return ERR_PTR(ret);
+	}
 
 	return &obj->base;
 }
@@ -221,7 +222,9 @@
 	args->size = gem_object->size;
 	args->pitch = pitch;
 
-	DRM_DEBUG("Created object of size %lld\n", size);
+	drm_gem_object_put_unlocked(gem_object);
+
+	DRM_DEBUG("Created object of size %llu\n", args->size);
 
 	return 0;
 }
diff --git a/drivers/hwmon/pmbus/ltc2978.c b/drivers/hwmon/pmbus/ltc2978.c
index f01f488..a91ed01 100644
--- a/drivers/hwmon/pmbus/ltc2978.c
+++ b/drivers/hwmon/pmbus/ltc2978.c
@@ -82,8 +82,8 @@
 
 #define LTC_POLL_TIMEOUT		100	/* in milli-seconds */
 
-#define LTC_NOT_BUSY			BIT(5)
-#define LTC_NOT_PENDING			BIT(4)
+#define LTC_NOT_BUSY			BIT(6)
+#define LTC_NOT_PENDING			BIT(5)
 
 /*
  * LTC2978 clears peak data whenever the CLEAR_FAULTS command is executed, which
diff --git a/drivers/hwmon/pmbus/xdpe12284.c b/drivers/hwmon/pmbus/xdpe12284.c
index 3d47806..ecd9b65 100644
--- a/drivers/hwmon/pmbus/xdpe12284.c
+++ b/drivers/hwmon/pmbus/xdpe12284.c
@@ -94,8 +94,8 @@
 MODULE_DEVICE_TABLE(i2c, xdpe122_id);
 
 static const struct of_device_id __maybe_unused xdpe122_of_match[] = {
-	{.compatible = "infineon, xdpe12254"},
-	{.compatible = "infineon, xdpe12284"},
+	{.compatible = "infineon,xdpe12254"},
+	{.compatible = "infineon,xdpe12284"},
 	{}
 };
 MODULE_DEVICE_TABLE(of, xdpe122_of_match);
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index 6eb6d27..2b4d803 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -339,22 +339,16 @@
 	if (!new_pps)
 		return NULL;
 
-	if (qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) {
-		if (!qp_pps) {
-			new_pps->main.port_num = qp_attr->port_num;
-			new_pps->main.pkey_index = qp_attr->pkey_index;
-		} else {
-			new_pps->main.port_num = (qp_attr_mask & IB_QP_PORT) ?
-						  qp_attr->port_num :
-						  qp_pps->main.port_num;
-
-			new_pps->main.pkey_index =
-					(qp_attr_mask & IB_QP_PKEY_INDEX) ?
-					 qp_attr->pkey_index :
-					 qp_pps->main.pkey_index;
-		}
+	if (qp_attr_mask & IB_QP_PORT)
+		new_pps->main.port_num =
+			(qp_pps) ? qp_pps->main.port_num : qp_attr->port_num;
+	if (qp_attr_mask & IB_QP_PKEY_INDEX)
+		new_pps->main.pkey_index = (qp_pps) ? qp_pps->main.pkey_index :
+						      qp_attr->pkey_index;
+	if ((qp_attr_mask & IB_QP_PKEY_INDEX) && (qp_attr_mask & IB_QP_PORT))
 		new_pps->main.state = IB_PORT_PKEY_VALID;
-	} else if (qp_pps) {
+
+	if (!(qp_attr_mask & (IB_QP_PKEY_INDEX || IB_QP_PORT)) && qp_pps) {
 		new_pps->main.port_num = qp_pps->main.port_num;
 		new_pps->main.pkey_index = qp_pps->main.pkey_index;
 		if (qp_pps->main.state != IB_PORT_PKEY_NOT_VALID)
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index d1407fa..1235ffb 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -1312,6 +1312,9 @@
 	struct ib_umad_file *file;
 	int id;
 
+	cdev_device_del(&port->sm_cdev, &port->sm_dev);
+	cdev_device_del(&port->cdev, &port->dev);
+
 	mutex_lock(&port->file_mutex);
 
 	/* Mark ib_dev NULL and block ioctl or other file ops to progress
@@ -1331,8 +1334,6 @@
 
 	mutex_unlock(&port->file_mutex);
 
-	cdev_device_del(&port->sm_cdev, &port->sm_dev);
-	cdev_device_del(&port->cdev, &port->dev);
 	ida_free(&umad_ida, port->dev_num);
 
 	/* balances device_initialize() */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index c8693f5..0259337 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2745,12 +2745,6 @@
 	return 0;
 }
 
-static size_t kern_spec_filter_sz(const struct ib_uverbs_flow_spec_hdr *spec)
-{
-	/* Returns user space filter size, includes padding */
-	return (spec->size - sizeof(struct ib_uverbs_flow_spec_hdr)) / 2;
-}
-
 static ssize_t spec_filter_size(const void *kern_spec_filter, u16 kern_filter_size,
 				u16 ib_real_filter_sz)
 {
@@ -2894,11 +2888,16 @@
 static int kern_spec_to_ib_spec_filter(struct ib_uverbs_flow_spec *kern_spec,
 				       union ib_flow_spec *ib_spec)
 {
-	ssize_t kern_filter_sz;
+	size_t kern_filter_sz;
 	void *kern_spec_mask;
 	void *kern_spec_val;
 
-	kern_filter_sz = kern_spec_filter_sz(&kern_spec->hdr);
+	if (check_sub_overflow((size_t)kern_spec->hdr.size,
+			       sizeof(struct ib_uverbs_flow_spec_hdr),
+			       &kern_filter_sz))
+		return -EINVAL;
+
+	kern_filter_sz /= 2;
 
 	kern_spec_val = (void *)kern_spec +
 		sizeof(struct ib_uverbs_flow_spec_hdr);
diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index 994d874..3abfc63 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -220,6 +220,7 @@
 	list_for_each_entry_safe(entry, tmp, &event_queue->event_list, list) {
 		if (entry->counter)
 			list_del(&entry->obj_list);
+		list_del(&entry->list);
 		kfree(entry);
 	}
 	spin_unlock_irq(&event_queue->lock);
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index ee1182f..d69dece3 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3036,6 +3036,10 @@
 				       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
 		}
 
+		/* As per draft-hilland-iwarp-verbs-v1.0, sec 6.2.3,
+		 * when entering the TERM state the RNIC MUST initiate a CLOSE.
+		 */
+		c4iw_ep_disconnect(ep, 1, GFP_KERNEL);
 		c4iw_put_ep(&ep->com);
 	} else
 		pr_warn("TERM received tid %u no ep/qp\n", tid);
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index bbcac53..89ac2f9 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1948,10 +1948,10 @@
 			qhp->attr.layer_etype = attrs->layer_etype;
 			qhp->attr.ecode = attrs->ecode;
 			ep = qhp->ep;
-			c4iw_get_ep(&ep->com);
-			disconnect = 1;
 			if (!internal) {
+				c4iw_get_ep(&ep->com);
 				terminate = 1;
+				disconnect = 1;
 			} else {
 				terminate = qhp->attr.send_term;
 				ret = rdma_fini(rhp, qhp, ep);
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index c142b23..1aeea5d 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -479,6 +479,8 @@
 			  rvt_get_ibdev_name(&(dd)->verbs_dev.rdi), i, cpu);
 	}
 
+	free_cpumask_var(available_cpus);
+	free_cpumask_var(non_intr_cpus);
 	return 0;
 
 fail:
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index bef6946..2591158 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -200,23 +200,24 @@
 
 	fd = kzalloc(sizeof(*fd), GFP_KERNEL);
 
-	if (fd) {
-		fd->rec_cpu_num = -1; /* no cpu affinity by default */
-		fd->mm = current->mm;
-		mmgrab(fd->mm);
-		fd->dd = dd;
-		kobject_get(&fd->dd->kobj);
-		fp->private_data = fd;
-	} else {
-		fp->private_data = NULL;
-
-		if (atomic_dec_and_test(&dd->user_refcount))
-			complete(&dd->user_comp);
-
-		return -ENOMEM;
-	}
-
+	if (!fd || init_srcu_struct(&fd->pq_srcu))
+		goto nomem;
+	spin_lock_init(&fd->pq_rcu_lock);
+	spin_lock_init(&fd->tid_lock);
+	spin_lock_init(&fd->invalid_lock);
+	fd->rec_cpu_num = -1; /* no cpu affinity by default */
+	fd->mm = current->mm;
+	mmgrab(fd->mm);
+	fd->dd = dd;
+	kobject_get(&fd->dd->kobj);
+	fp->private_data = fd;
 	return 0;
+nomem:
+	kfree(fd);
+	fp->private_data = NULL;
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+	return -ENOMEM;
 }
 
 static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
@@ -301,21 +302,30 @@
 static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 {
 	struct hfi1_filedata *fd = kiocb->ki_filp->private_data;
-	struct hfi1_user_sdma_pkt_q *pq = fd->pq;
+	struct hfi1_user_sdma_pkt_q *pq;
 	struct hfi1_user_sdma_comp_q *cq = fd->cq;
 	int done = 0, reqs = 0;
 	unsigned long dim = from->nr_segs;
+	int idx;
 
-	if (!cq || !pq)
+	idx = srcu_read_lock(&fd->pq_srcu);
+	pq = srcu_dereference(fd->pq, &fd->pq_srcu);
+	if (!cq || !pq) {
+		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -EIO;
+	}
 
-	if (!iter_is_iovec(from) || !dim)
+	if (!iter_is_iovec(from) || !dim) {
+		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -EINVAL;
+	}
 
 	trace_hfi1_sdma_request(fd->dd, fd->uctxt->ctxt, fd->subctxt, dim);
 
-	if (atomic_read(&pq->n_reqs) == pq->n_max_reqs)
+	if (atomic_read(&pq->n_reqs) == pq->n_max_reqs) {
+		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -ENOSPC;
+	}
 
 	while (dim) {
 		int ret;
@@ -333,6 +343,7 @@
 		reqs++;
 	}
 
+	srcu_read_unlock(&fd->pq_srcu, idx);
 	return reqs;
 }
 
@@ -707,6 +718,7 @@
 	if (atomic_dec_and_test(&dd->user_refcount))
 		complete(&dd->user_comp);
 
+	cleanup_srcu_struct(&fdata->pq_srcu);
 	kfree(fdata);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 6365e8f..cae12f4 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1444,10 +1444,13 @@
 
 /* Private data for file operations */
 struct hfi1_filedata {
+	struct srcu_struct pq_srcu;
 	struct hfi1_devdata *dd;
 	struct hfi1_ctxtdata *uctxt;
 	struct hfi1_user_sdma_comp_q *cq;
-	struct hfi1_user_sdma_pkt_q *pq;
+	/* update side lock for SRCU */
+	spinlock_t pq_rcu_lock;
+	struct hfi1_user_sdma_pkt_q __rcu *pq;
 	u16 subctxt;
 	/* for cpu affinity; -1 if none */
 	int rec_cpu_num;
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index f05742a..4da03f8 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -87,9 +87,6 @@
 {
 	int ret = 0;
 
-	spin_lock_init(&fd->tid_lock);
-	spin_lock_init(&fd->invalid_lock);
-
 	fd->entry_to_rb = kcalloc(uctxt->expected_count,
 				  sizeof(struct rb_node *),
 				  GFP_KERNEL);
@@ -142,10 +139,12 @@
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 
+	mutex_lock(&uctxt->exp_mutex);
 	if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
 		unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
 	if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
 		unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
+	mutex_unlock(&uctxt->exp_mutex);
 
 	kfree(fd->invalid_tids);
 	fd->invalid_tids = NULL;
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index fd754a1..c2f0d9b 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -179,7 +179,6 @@
 	pq = kzalloc(sizeof(*pq), GFP_KERNEL);
 	if (!pq)
 		return -ENOMEM;
-
 	pq->dd = dd;
 	pq->ctxt = uctxt->ctxt;
 	pq->subctxt = fd->subctxt;
@@ -236,7 +235,7 @@
 		goto pq_mmu_fail;
 	}
 
-	fd->pq = pq;
+	rcu_assign_pointer(fd->pq, pq);
 	fd->cq = cq;
 
 	return 0;
@@ -264,8 +263,14 @@
 
 	trace_hfi1_sdma_user_free_queues(uctxt->dd, uctxt->ctxt, fd->subctxt);
 
-	pq = fd->pq;
+	spin_lock(&fd->pq_rcu_lock);
+	pq = srcu_dereference_check(fd->pq, &fd->pq_srcu,
+				    lockdep_is_held(&fd->pq_rcu_lock));
 	if (pq) {
+		rcu_assign_pointer(fd->pq, NULL);
+		spin_unlock(&fd->pq_rcu_lock);
+		synchronize_srcu(&fd->pq_srcu);
+		/* at this point there can be no more new requests */
 		if (pq->handler)
 			hfi1_mmu_rb_unregister(pq->handler);
 		iowait_sdma_drain(&pq->busy);
@@ -277,7 +282,8 @@
 		kfree(pq->req_in_use);
 		kmem_cache_destroy(pq->txreq_cache);
 		kfree(pq);
-		fd->pq = NULL;
+	} else {
+		spin_unlock(&fd->pq_rcu_lock);
 	}
 	if (fd->cq) {
 		vfree(fd->cq->comps);
@@ -321,7 +327,8 @@
 {
 	int ret = 0, i;
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
-	struct hfi1_user_sdma_pkt_q *pq = fd->pq;
+	struct hfi1_user_sdma_pkt_q *pq =
+		srcu_dereference(fd->pq, &fd->pq_srcu);
 	struct hfi1_user_sdma_comp_q *cq = fd->cq;
 	struct hfi1_devdata *dd = pq->dd;
 	unsigned long idx = 0;
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index d7efc9f..46e1ab7 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2319,14 +2319,12 @@
 
 	if (ev_file->omit_data) {
 		spin_lock_irqsave(&ev_file->lock, flags);
-		if (!list_empty(&event_sub->event_list)) {
+		if (!list_empty(&event_sub->event_list) ||
+		    ev_file->is_destroyed) {
 			spin_unlock_irqrestore(&ev_file->lock, flags);
 			return 0;
 		}
 
-		/* is_destroyed is ignored here because we don't have any memory
-		 * allocation to clean up for the omit_data case
-		 */
 		list_add_tail(&event_sub->event_list, &ev_file->event_list);
 		spin_unlock_irqrestore(&ev_file->lock, flags);
 		wake_up_interruptible(&ev_file->poll_wait);
@@ -2473,11 +2471,11 @@
 			return -ERESTARTSYS;
 		}
 
-		if (list_empty(&ev_queue->event_list) &&
-		    ev_queue->is_destroyed)
-			return -EIO;
-
 		spin_lock_irq(&ev_queue->lock);
+		if (ev_queue->is_destroyed) {
+			spin_unlock_irq(&ev_queue->lock);
+			return -EIO;
+		}
 	}
 
 	event = list_entry(ev_queue->event_list.next,
@@ -2551,10 +2549,6 @@
 		return -EOVERFLOW;
 	}
 
-	if (ev_file->is_destroyed) {
-		spin_unlock_irq(&ev_file->lock);
-		return -EIO;
-	}
 
 	while (list_empty(&ev_file->event_list)) {
 		spin_unlock_irq(&ev_file->lock);
@@ -2667,8 +2661,10 @@
 
 	spin_lock_irq(&comp_ev_file->ev_queue.lock);
 	list_for_each_entry_safe(entry, tmp,
-				 &comp_ev_file->ev_queue.event_list, list)
+				 &comp_ev_file->ev_queue.event_list, list) {
+		list_del(&entry->list);
 		kvfree(entry);
+	}
 	spin_unlock_irq(&comp_ev_file->ev_queue.lock);
 	return 0;
 };
@@ -2680,11 +2676,29 @@
 		container_of(uobj, struct devx_async_event_file,
 			     uobj);
 	struct devx_event_subscription *event_sub, *event_sub_tmp;
-	struct devx_async_event_data *entry, *tmp;
 	struct mlx5_ib_dev *dev = ev_file->dev;
 
 	spin_lock_irq(&ev_file->lock);
 	ev_file->is_destroyed = 1;
+
+	/* free the pending events allocation */
+	if (ev_file->omit_data) {
+		struct devx_event_subscription *event_sub, *tmp;
+
+		list_for_each_entry_safe(event_sub, tmp, &ev_file->event_list,
+					 event_list)
+			list_del_init(&event_sub->event_list);
+
+	} else {
+		struct devx_async_event_data *entry, *tmp;
+
+		list_for_each_entry_safe(entry, tmp, &ev_file->event_list,
+					 list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+
 	spin_unlock_irq(&ev_file->lock);
 	wake_up_interruptible(&ev_file->poll_wait);
 
@@ -2699,15 +2713,6 @@
 	}
 	mutex_unlock(&dev->devx_event_table.event_xa_lock);
 
-	/* free the pending events allocation */
-	if (!ev_file->omit_data) {
-		spin_lock_irq(&ev_file->lock);
-		list_for_each_entry_safe(entry, tmp,
-					 &ev_file->event_list, list)
-			kfree(entry); /* read can't come any more */
-		spin_unlock_irq(&ev_file->lock);
-	}
-
 	put_device(&dev->ib_dev.dev);
 	return 0;
 };
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e874d68..e4bcfa8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2283,8 +2283,8 @@
 
 static u64 mlx5_entry_to_mmap_offset(struct mlx5_user_mmap_entry *entry)
 {
-	u16 cmd = entry->rdma_entry.start_pgoff >> 16;
-	u16 index = entry->rdma_entry.start_pgoff & 0xFFFF;
+	u64 cmd = (entry->rdma_entry.start_pgoff >> 16) & 0xFFFF;
+	u64 index = entry->rdma_entry.start_pgoff & 0xFFFF;
 
 	return (((index >> 8) << 16) | (cmd << MLX5_IB_MMAP_CMD_SHIFT) |
 		(index & 0xFF)) << PAGE_SHIFT;
@@ -6545,7 +6545,7 @@
 					doorbell_bar_offset);
 	bar_size = (1ULL << log_doorbell_bar_size) * 4096;
 	var_table->stride_size = 1ULL << log_doorbell_stride;
-	var_table->num_var_hw_entries = bar_size / var_table->stride_size;
+	var_table->num_var_hw_entries = div64_u64(bar_size, var_table->stride_size);
 	mutex_init(&var_table->bitmap_lock);
 	var_table->bitmap = bitmap_zalloc(var_table->num_var_hw_entries,
 					  GFP_KERNEL);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index a4f8e70..957f3a5 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3441,9 +3441,6 @@
 	struct mlx5_ib_qp_base *base;
 	u32 set_id;
 
-	if (!MLX5_CAP_GEN(dev->mdev, rts2rts_qp_counters_set_id))
-		return 0;
-
 	if (counter)
 		set_id = counter->id;
 	else
@@ -6576,6 +6573,7 @@
  */
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter)
 {
+	struct mlx5_ib_dev *dev = to_mdev(qp->device);
 	struct mlx5_ib_qp *mqp = to_mqp(qp);
 	int err = 0;
 
@@ -6585,6 +6583,11 @@
 		goto out;
 	}
 
+	if (!MLX5_CAP_GEN(dev->mdev, rts2rts_qp_counters_set_id)) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
 	if (mqp->state == IB_QPS_RTS) {
 		err = __mlx5_ib_qp_set_counter(qp, counter);
 		if (!err)
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 3cdf75d..7858d49 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -61,6 +61,8 @@
 #define RVT_RWQ_COUNT_THRESHOLD 16
 
 static void rvt_rc_timeout(struct timer_list *t);
+static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			 enum ib_qp_type type);
 
 /*
  * Convert the AETH RNR timeout code into the number of microseconds.
@@ -452,40 +454,41 @@
 }
 
 /**
- * free_all_qps - check for QPs still in use
+ * rvt_free_qp_cb - callback function to reset a qp
+ * @qp: the qp to reset
+ * @v: a 64-bit value
+ *
+ * This function resets the qp and removes it from the
+ * qp hash table.
+ */
+static void rvt_free_qp_cb(struct rvt_qp *qp, u64 v)
+{
+	unsigned int *qp_inuse = (unsigned int *)v;
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+
+	/* Reset the qp and remove it from the qp hash list */
+	rvt_reset_qp(rdi, qp, qp->ibqp.qp_type);
+
+	/* Increment the qp_inuse count */
+	(*qp_inuse)++;
+}
+
+/**
+ * rvt_free_all_qps - check for QPs still in use
  * @rdi: rvt device info structure
  *
  * There should not be any QPs still in use.
  * Free memory for table.
+ * Return the number of QPs still in use.
  */
 static unsigned rvt_free_all_qps(struct rvt_dev_info *rdi)
 {
-	unsigned long flags;
-	struct rvt_qp *qp;
-	unsigned n, qp_inuse = 0;
-	spinlock_t *ql; /* work around too long line below */
-
-	if (rdi->driver_f.free_all_qps)
-		qp_inuse = rdi->driver_f.free_all_qps(rdi);
+	unsigned int qp_inuse = 0;
 
 	qp_inuse += rvt_mcast_tree_empty(rdi);
 
-	if (!rdi->qp_dev)
-		return qp_inuse;
+	rvt_qp_iter(rdi, (u64)&qp_inuse, rvt_free_qp_cb);
 
-	ql = &rdi->qp_dev->qpt_lock;
-	spin_lock_irqsave(ql, flags);
-	for (n = 0; n < rdi->qp_dev->qp_table_size; n++) {
-		qp = rcu_dereference_protected(rdi->qp_dev->qp_table[n],
-					       lockdep_is_held(ql));
-		RCU_INIT_POINTER(rdi->qp_dev->qp_table[n], NULL);
-
-		for (; qp; qp = rcu_dereference_protected(qp->next,
-							  lockdep_is_held(ql)))
-			qp_inuse++;
-	}
-	spin_unlock_irqrestore(ql, flags);
-	synchronize_rcu();
 	return qp_inuse;
 }
 
@@ -902,14 +905,14 @@
 }
 
 /**
- * rvt_reset_qp - initialize the QP state to the reset state
+ * _rvt_reset_qp - initialize the QP state to the reset state
  * @qp: the QP to reset
  * @type: the QP type
  *
  * r_lock, s_hlock, and s_lock are required to be held by the caller
  */
-static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-			 enum ib_qp_type type)
+static void _rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			  enum ib_qp_type type)
 	__must_hold(&qp->s_lock)
 	__must_hold(&qp->s_hlock)
 	__must_hold(&qp->r_lock)
@@ -955,6 +958,27 @@
 	lockdep_assert_held(&qp->s_lock);
 }
 
+/**
+ * rvt_reset_qp - initialize the QP state to the reset state
+ * @rdi: the device info
+ * @qp: the QP to reset
+ * @type: the QP type
+ *
+ * This is the wrapper function to acquire the r_lock, s_hlock, and s_lock
+ * before calling _rvt_reset_qp().
+ */
+static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			 enum ib_qp_type type)
+{
+	spin_lock_irq(&qp->r_lock);
+	spin_lock(&qp->s_hlock);
+	spin_lock(&qp->s_lock);
+	_rvt_reset_qp(rdi, qp, type);
+	spin_unlock(&qp->s_lock);
+	spin_unlock(&qp->s_hlock);
+	spin_unlock_irq(&qp->r_lock);
+}
+
 /** rvt_free_qpn - Free a qpn from the bit map
  * @qpt: QP table
  * @qpn: queue pair number to free
@@ -1546,7 +1570,7 @@
 	switch (new_state) {
 	case IB_QPS_RESET:
 		if (qp->state != IB_QPS_RESET)
-			rvt_reset_qp(rdi, qp, ibqp->qp_type);
+			_rvt_reset_qp(rdi, qp, ibqp->qp_type);
 		break;
 
 	case IB_QPS_RTR:
@@ -1695,13 +1719,7 @@
 	struct rvt_qp *qp = ibqp_to_rvtqp(ibqp);
 	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
 
-	spin_lock_irq(&qp->r_lock);
-	spin_lock(&qp->s_hlock);
-	spin_lock(&qp->s_lock);
 	rvt_reset_qp(rdi, qp, ibqp->qp_type);
-	spin_unlock(&qp->s_lock);
-	spin_unlock(&qp->s_hlock);
-	spin_unlock_irq(&qp->r_lock);
 
 	wait_event(qp->wait, !atomic_read(&qp->refcount));
 	/* qpn is now available for use again */
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 116cafc..4bc8870 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -329,7 +329,7 @@
 					qp->comp.psn = pkt->psn;
 					if (qp->req.wait_psn) {
 						qp->req.wait_psn = 0;
-						rxe_run_task(&qp->req.task, 1);
+						rxe_run_task(&qp->req.task, 0);
 					}
 				}
 				return COMPST_ERROR_RETRY;
@@ -463,7 +463,7 @@
 	 */
 	if (qp->req.wait_fence) {
 		qp->req.wait_fence = 0;
-		rxe_run_task(&qp->req.task, 1);
+		rxe_run_task(&qp->req.task, 0);
 	}
 }
 
@@ -479,7 +479,7 @@
 		if (qp->req.need_rd_atomic) {
 			qp->comp.timeout_retry = 0;
 			qp->req.need_rd_atomic = 0;
-			rxe_run_task(&qp->req.task, 1);
+			rxe_run_task(&qp->req.task, 0);
 		}
 	}
 
@@ -725,7 +725,7 @@
 							RXE_CNT_COMP_RETRY);
 					qp->req.need_retry = 1;
 					qp->comp.started_retry = 1;
-					rxe_run_task(&qp->req.task, 1);
+					rxe_run_task(&qp->req.task, 0);
 				}
 
 				if (pkt) {
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index 0c3f058..c5651a9 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -1225,10 +1225,9 @@
 	read_lock(&sk->sk_callback_lock);
 
 	cep = sk_to_cep(sk);
-	if (!cep) {
-		WARN_ON(1);
+	if (!cep)
 		goto out;
-	}
+
 	siw_dbg_cep(cep, "state: %d\n", cep->state);
 
 	switch (cep->state) {
diff --git a/drivers/input/keyboard/goldfish_events.c b/drivers/input/keyboard/goldfish_events.c
index bc8c85a..57d435f 100644
--- a/drivers/input/keyboard/goldfish_events.c
+++ b/drivers/input/keyboard/goldfish_events.c
@@ -30,7 +30,7 @@
 	struct input_dev *input;
 	int irq;
 	void __iomem *addr;
-	char name[0];
+	char name[];
 };
 
 static irqreturn_t events_interrupt(int irq, void *dev_id)
diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 1f56d53..53c9ff3 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -55,7 +55,7 @@
 	struct input_dev *input;
 	struct mutex disable_lock;
 	unsigned short *keymap;
-	struct gpio_button_data data[0];
+	struct gpio_button_data data[];
 };
 
 /*
diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index 6eb0a2f..c3937d2 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -38,7 +38,7 @@
 	const struct gpio_keys_platform_data *pdata;
 	unsigned long rel_axis_seen[BITS_TO_LONGS(REL_CNT)];
 	unsigned long abs_axis_seen[BITS_TO_LONGS(ABS_CNT)];
-	struct gpio_keys_button_data data[0];
+	struct gpio_keys_button_data data[];
 };
 
 static void gpio_keys_button_event(struct input_dev *input,
diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 2a14769..2175876 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -33,7 +33,7 @@
 
 struct tca6416_drv_data {
 	struct input_dev *input;
-	struct tca6416_button data[0];
+	struct tca6416_button data[];
 };
 
 struct tca6416_keypad_chip {
@@ -48,7 +48,7 @@
 	int irqnum;
 	u16 pinmask;
 	bool use_polling;
-	struct tca6416_button buttons[0];
+	struct tca6416_button buttons[];
 };
 
 static int tca6416_write_reg(struct tca6416_keypad_chip *chip, int reg, u16 val)
diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c
index 14239fb..7f012bf 100644
--- a/drivers/input/mouse/cyapa_gen5.c
+++ b/drivers/input/mouse/cyapa_gen5.c
@@ -250,7 +250,7 @@
 
 struct cyapa_tsg_bin_image {
 	struct cyapa_tsg_bin_image_head image_head;
-	struct cyapa_tsg_bin_image_data_record records[0];
+	struct cyapa_tsg_bin_image_data_record records[];
 } __packed;
 
 struct pip_bl_packet_start {
@@ -271,7 +271,7 @@
 	u8 report_id;  /* Bootloader output report id, must be 40h */
 	u8 rsvd;  /* Reserved, must be 0 */
 	struct pip_bl_packet_start packet_start;
-	u8 data[0];  /* Command data variable based on commands */
+	u8 data[];  /* Command data variable based on commands */
 } __packed;
 
 /* Initiate bootload command data structure. */
@@ -300,7 +300,7 @@
 struct tsg_bl_flash_row_head {
 	u8 flash_array_id;
 	__le16 flash_row_id;
-	u8 flash_data[0];
+	u8 flash_data[];
 } __packed;
 
 struct pip_app_cmd_head {
@@ -314,7 +314,7 @@
 	 * Bit 6-0: command code.
 	 */
 	u8 cmd_code;
-	u8 parameter_data[0];  /* Parameter data variable based on cmd_code */
+	u8 parameter_data[];  /* Parameter data variable based on cmd_code */
 } __packed;
 
 /* Application get/set parameter command data structure */
diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c
index 027efdd..a472489 100644
--- a/drivers/input/mouse/psmouse-smbus.c
+++ b/drivers/input/mouse/psmouse-smbus.c
@@ -190,6 +190,7 @@
 	struct psmouse_smbus_dev *smbdev = data;
 	unsigned short addr_list[] = { smbdev->board.addr, I2C_CLIENT_END };
 	struct i2c_adapter *adapter;
+	struct i2c_client *client;
 
 	adapter = i2c_verify_adapter(dev);
 	if (!adapter)
@@ -198,12 +199,13 @@
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_HOST_NOTIFY))
 		return 0;
 
-	smbdev->client = i2c_new_probed_device(adapter, &smbdev->board,
-					       addr_list, NULL);
-	if (!smbdev->client)
+	client = i2c_new_scanned_device(adapter, &smbdev->board,
+					addr_list, NULL);
+	if (IS_ERR(client))
 		return 0;
 
 	/* We have our(?) device, stop iterating i2c bus. */
+	smbdev->client = client;
 	return 1;
 }
 
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 1ae6f8b..2c666fb 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -146,7 +146,6 @@
 	"LEN0042", /* Yoga */
 	"LEN0045",
 	"LEN0047",
-	"LEN0049",
 	"LEN2000", /* S540 */
 	"LEN2001", /* Edge E431 */
 	"LEN2002", /* Edge E531 */
@@ -166,9 +165,11 @@
 	/* all of the topbuttonpad_pnp_ids are valid, we just add some extras */
 	"LEN0048", /* X1 Carbon 3 */
 	"LEN0046", /* X250 */
+	"LEN0049", /* Yoga 11e */
 	"LEN004a", /* W541 */
 	"LEN005b", /* P50 */
 	"LEN005e", /* T560 */
+	"LEN006c", /* T470s */
 	"LEN0071", /* T480 */
 	"LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
 	"LEN0073", /* X1 Carbon G5 (Elantech) */
@@ -179,6 +180,7 @@
 	"LEN0097", /* X280 -> ALPS trackpoint */
 	"LEN009b", /* T580 */
 	"LEN200f", /* T450s */
+	"LEN2044", /* L470  */
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
 	"SYN3052", /* HP EliteBook 840 G4 */
diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c
index 4a17096..199cf3d 100644
--- a/drivers/input/touchscreen/ili210x.c
+++ b/drivers/input/touchscreen/ili210x.c
@@ -167,6 +167,36 @@
 	.resolution		= 2048,
 };
 
+static bool ili212x_touchdata_to_coords(const u8 *touchdata,
+					unsigned int finger,
+					unsigned int *x, unsigned int *y)
+{
+	u16 val;
+
+	val = get_unaligned_be16(touchdata + 3 + (finger * 5) + 0);
+	if (!(val & BIT(15)))	/* Touch indication */
+		return false;
+
+	*x = val & 0x3fff;
+	*y = get_unaligned_be16(touchdata + 3 + (finger * 5) + 2);
+
+	return true;
+}
+
+static bool ili212x_check_continue_polling(const u8 *data, bool touch)
+{
+	return touch;
+}
+
+static const struct ili2xxx_chip ili212x_chip = {
+	.read_reg		= ili210x_read_reg,
+	.get_touch_data		= ili210x_read_touch_data,
+	.parse_touch_data	= ili212x_touchdata_to_coords,
+	.continue_polling	= ili212x_check_continue_polling,
+	.max_touches		= 10,
+	.has_calibrate_reg	= true,
+};
+
 static int ili251x_read_reg(struct i2c_client *client,
 			    u8 reg, void *buf, size_t len)
 {
@@ -321,7 +351,7 @@
 	struct i2c_client *client = to_i2c_client(dev);
 	struct ili210x *priv = i2c_get_clientdata(client);
 
-	return priv->chip->has_calibrate_reg;
+	return priv->chip->has_calibrate_reg ? attr->mode : 0;
 }
 
 static const struct attribute_group ili210x_attr_group = {
@@ -447,6 +477,7 @@
 static const struct i2c_device_id ili210x_i2c_id[] = {
 	{ "ili210x", (long)&ili210x_chip },
 	{ "ili2117", (long)&ili211x_chip },
+	{ "ili2120", (long)&ili212x_chip },
 	{ "ili251x", (long)&ili251x_chip },
 	{ }
 };
@@ -455,6 +486,7 @@
 static const struct of_device_id ili210x_dt_ids[] = {
 	{ .compatible = "ilitek,ili210x", .data = &ili210x_chip },
 	{ .compatible = "ilitek,ili2117", .data = &ili211x_chip },
+	{ .compatible = "ilitek,ili2120", .data = &ili212x_chip },
 	{ .compatible = "ilitek,ili251x", .data = &ili251x_chip },
 	{ }
 };
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 2104fb8..9f33fdb 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -14,8 +14,8 @@
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu-mod.o
-arm-smmu-mod-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 2759a8d..6be3853 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2523,6 +2523,7 @@
 	struct acpi_table_header *ivrs_base;
 	acpi_status status;
 	int i, remap_cache_sz, ret = 0;
+	u32 pci_id;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -2610,6 +2611,16 @@
 	if (ret)
 		goto out;
 
+	/* Disable IOMMU if there's Stoney Ridge graphics */
+	for (i = 0; i < 32; i++) {
+		pci_id = read_pci_config(0, i, 0, 0);
+		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+			pr_info("Disable IOMMU on Stoney Ridge\n");
+			amd_iommu_disabled = true;
+			break;
+		}
+	}
+
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();
@@ -2718,7 +2729,7 @@
 		ret = early_amd_iommu_init();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
 		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
-			pr_info("AMD IOMMU disabled on kernel command-line\n");
+			pr_info("AMD IOMMU disabled\n");
 			init_state = IOMMU_CMDLINE_DISABLED;
 			ret = -EINVAL;
 		}
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 9dc3767..6fa6de2 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -762,6 +762,11 @@
 	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
 }
 
+static bool attach_deferred(struct device *dev)
+{
+	return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+}
+
 /**
  * is_downstream_to_pci_bridge - test if a device belongs to the PCI
  *				 sub-hierarchy of a candidate PCI-PCI bridge
@@ -2510,8 +2515,7 @@
 {
 	struct device_domain_info *info;
 
-	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO ||
-		     dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
+	if (unlikely(attach_deferred(dev) || iommu_dummy(dev)))
 		return NULL;
 
 	if (dev_is_pci(dev))
@@ -2525,18 +2529,14 @@
 	return NULL;
 }
 
-static struct dmar_domain *deferred_attach_domain(struct device *dev)
+static void do_deferred_attach(struct device *dev)
 {
-	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
-		struct iommu_domain *domain;
+	struct iommu_domain *domain;
 
-		dev->archdata.iommu = NULL;
-		domain = iommu_get_domain_for_dev(dev);
-		if (domain)
-			intel_iommu_attach_device(domain, dev);
-	}
-
-	return find_domain(dev);
+	dev->archdata.iommu = NULL;
+	domain = iommu_get_domain_for_dev(dev);
+	if (domain)
+		intel_iommu_attach_device(domain, dev);
 }
 
 static inline struct device_domain_info *
@@ -2916,7 +2916,7 @@
 	struct device_domain_info *info;
 
 	info = dev->archdata.iommu;
-	if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO)
+	if (info)
 		return (info->domain == si_domain);
 
 	return 0;
@@ -3587,6 +3587,9 @@
 	if (iommu_dummy(dev))
 		return false;
 
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
+
 	ret = identity_mapping(dev);
 	if (ret) {
 		u64 dma_mask = *dev->dma_mask;
@@ -3635,7 +3638,7 @@
 
 	BUG_ON(dir == DMA_NONE);
 
-	domain = deferred_attach_domain(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return DMA_MAPPING_ERROR;
 
@@ -3855,7 +3858,7 @@
 	if (!iommu_need_mapping(dev))
 		return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
 
-	domain = deferred_attach_domain(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return 0;
 
@@ -3950,7 +3953,11 @@
 	int prot = 0;
 	int ret;
 
-	domain = deferred_attach_domain(dev);
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
+
+	domain = find_domain(dev);
+
 	if (WARN_ON(dir == DMA_NONE || !domain))
 		return DMA_MAPPING_ERROR;
 
@@ -6133,7 +6140,7 @@
 static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
 					   struct device *dev)
 {
-	return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+	return attach_deferred(dev);
 }
 
 static int
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 39759db..4328da0 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -344,21 +344,19 @@
 {
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 
-	if (WARN_ON(qcom_domain->iommu))    /* forgot to detach? */
-		return;
-
 	iommu_put_dma_cookie(domain);
 
-	/* NOTE: unmap can be called after client device is powered off,
-	 * for example, with GPUs or anything involving dma-buf.  So we
-	 * cannot rely on the device_link.  Make sure the IOMMU is on to
-	 * avoid unclocked accesses in the TLB inv path:
-	 */
-	pm_runtime_get_sync(qcom_domain->iommu->dev);
-
-	free_io_pgtable_ops(qcom_domain->pgtbl_ops);
-
-	pm_runtime_put_sync(qcom_domain->iommu->dev);
+	if (qcom_domain->iommu) {
+		/*
+		 * NOTE: unmap can be called after client device is powered
+		 * off, for example, with GPUs or anything involving dma-buf.
+		 * So we cannot rely on the device_link.  Make sure the IOMMU
+		 * is on to avoid unclocked accesses in the TLB inv path:
+		 */
+		pm_runtime_get_sync(qcom_domain->iommu->dev);
+		free_io_pgtable_ops(qcom_domain->pgtbl_ops);
+		pm_runtime_put_sync(qcom_domain->iommu->dev);
+	}
 
 	kfree(qcom_domain);
 }
@@ -404,7 +402,7 @@
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	unsigned i;
 
-	if (!qcom_domain->iommu)
+	if (WARN_ON(!qcom_domain->iommu))
 		return;
 
 	pm_runtime_get_sync(qcom_iommu->dev);
@@ -417,8 +415,6 @@
 		ctx->domain = NULL;
 	}
 	pm_runtime_put_sync(qcom_iommu->dev);
-
-	qcom_domain->iommu = NULL;
 }
 
 static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index a1df0d9..8bc1faf 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -67,6 +67,7 @@
 #include <linux/blkdev.h>
 #include <linux/kthread.h>
 #include <linux/random.h>
+#include <linux/sched/signal.h>
 #include <trace/events/bcache.h>
 
 #define MAX_OPEN_BUCKETS 128
@@ -733,8 +734,21 @@
 
 int bch_cache_allocator_start(struct cache *ca)
 {
-	struct task_struct *k = kthread_run(bch_allocator_thread,
-					    ca, "bcache_allocator");
+	struct task_struct *k;
+
+	/*
+	 * In case previous btree check operation occupies too many
+	 * system memory for bcache btree node cache, and the
+	 * registering process is selected by OOM killer. Here just
+	 * ignore the SIGKILL sent by OOM killer if there is, to
+	 * avoid kthread_run() being failed by pending signals. The
+	 * bcache registering process will exit after the registration
+	 * done.
+	 */
+	if (signal_pending(current))
+		flush_signals(current);
+
+	k = kthread_run(bch_allocator_thread, ca, "bcache_allocator");
 	if (IS_ERR(k))
 		return PTR_ERR(k);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index fa872df..b12186c 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -34,6 +34,7 @@
 #include <linux/random.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/signal.h>
 #include <linux/rculist.h>
 #include <linux/delay.h>
 #include <trace/events/bcache.h>
@@ -1913,6 +1914,18 @@
 
 int bch_gc_thread_start(struct cache_set *c)
 {
+	/*
+	 * In case previous btree check operation occupies too many
+	 * system memory for bcache btree node cache, and the
+	 * registering process is selected by OOM killer. Here just
+	 * ignore the SIGKILL sent by OOM killer if there is, to
+	 * avoid kthread_run() being failed by pending signals. The
+	 * bcache registering process will exit after the registration
+	 * done.
+	 */
+	if (signal_pending(current))
+		flush_signals(current);
+
 	c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc");
 	return PTR_ERR_OR_ZERO(c->gc_thread);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 6730820..0e3ff97 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -417,8 +417,6 @@
 
 /* Journalling */
 
-#define nr_to_fifo_front(p, front_p, mask)	(((p) - (front_p)) & (mask))
-
 static void btree_flush_write(struct cache_set *c)
 {
 	struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR];
@@ -510,9 +508,8 @@
 		 *   journal entry can be reclaimed). These selected nodes
 		 *   will be ignored and skipped in the folowing for-loop.
 		 */
-		if (nr_to_fifo_front(btree_current_write(b)->journal,
-				     fifo_front_p,
-				     mask) != 0) {
+		if (((btree_current_write(b)->journal - fifo_front_p) &
+		     mask) != 0) {
 			mutex_unlock(&b->write_lock);
 			continue;
 		}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2749daf..0c3c541 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1917,23 +1917,6 @@
 		if (bch_btree_check(c))
 			goto err;
 
-		/*
-		 * bch_btree_check() may occupy too much system memory which
-		 * has negative effects to user space application (e.g. data
-		 * base) performance. Shrink the mca cache memory proactively
-		 * here to avoid competing memory with user space workloads..
-		 */
-		if (!c->shrinker_disabled) {
-			struct shrink_control sc;
-
-			sc.gfp_mask = GFP_KERNEL;
-			sc.nr_to_scan = c->btree_cache_used * c->btree_pages;
-			/* first run to clear b->accessed tag */
-			c->shrink.scan_objects(&c->shrink, &sc);
-			/* second run to reap non-accessed nodes */
-			c->shrink.scan_objects(&c->shrink, &sc);
-		}
-
 		bch_journal_mark(c, &journal);
 		bch_initial_gc_finish(c);
 		pr_debug("btree_check() done");
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 48d5ec7..d10805e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3526,6 +3526,47 @@
 	}
 }
 
+#ifdef CONFIG_LOCKDEP
+static int bond_get_lowest_level_rcu(struct net_device *dev)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int cur = 0, max = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			if (max <= cur)
+				max = cur;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return max;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return max;
+}
+#endif
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3533,11 +3574,17 @@
 	struct rtnl_link_stats64 temp;
 	struct list_head *iter;
 	struct slave *slave;
+	int nest_level = 0;
 
-	spin_lock(&bond->stats_lock);
-	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
+#ifdef CONFIG_LOCKDEP
+	nest_level = bond_get_lowest_level_rcu(bond_dev);
+#endif
+
+	spin_lock_nested(&bond->stats_lock, nest_level);
+	memcpy(stats, &bond->bond_stats, sizeof(*stats));
+
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
@@ -3547,10 +3594,10 @@
 		/* save off the slave stats for the next run */
 		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
-	rcu_read_unlock();
 
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
 	spin_unlock(&bond->stats_lock);
+	rcu_read_unlock();
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
@@ -3640,6 +3687,8 @@
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
 		res = bond_release(bond_dev, slave_dev);
+		if (!res)
+			netdev_update_lockdep_key(slave_dev);
 		break;
 	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index ddb3916..215c109 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1398,6 +1398,8 @@
 	case '-':
 		slave_dbg(bond->dev, dev, "Releasing interface\n");
 		ret = bond_release(bond->dev, dev);
+		if (!ret)
+			netdev_update_lockdep_key(dev);
 		break;
 
 	default:
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 449a221..1a69286 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1366,6 +1366,9 @@
 
 		b53_get_vlan_entry(dev, vid, vl);
 
+		if (vid == 0 && vid == b53_default_pvid(dev))
+			untagged = true;
+
 		vl->members |= BIT(port);
 		if (untagged && !dsa_is_cpu_port(ds, port))
 			vl->untag |= BIT(port);
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index f332cb4..79cad5e 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -236,7 +236,7 @@
 	bool mirror_ingress;
 	bool mirror_egress;
 	unsigned int serdes_irq;
-	char serdes_irq_name[32];
+	char serdes_irq_name[64];
 };
 
 struct mv88e6xxx_chip {
@@ -293,16 +293,16 @@
 	struct mv88e6xxx_irq g1_irq;
 	struct mv88e6xxx_irq g2_irq;
 	int irq;
-	char irq_name[32];
+	char irq_name[64];
 	int device_irq;
-	char device_irq_name[32];
+	char device_irq_name[64];
 	int watchdog_irq;
-	char watchdog_irq_name[32];
+	char watchdog_irq_name[64];
 
 	int atu_prob_irq;
-	char atu_prob_irq_name[32];
+	char atu_prob_irq_name[64];
 	int vtu_prob_irq;
-	char vtu_prob_irq_name[32];
+	char vtu_prob_irq_name[64];
 	struct kthread_worker *kworker;
 	struct kthread_delayed_work irq_poll_work;
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index ea62604..1fb58f9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -200,6 +200,11 @@
 static struct ena_comp_ctx *get_comp_ctxt(struct ena_com_admin_queue *queue,
 					  u16 command_id, bool capture)
 {
+	if (unlikely(!queue->comp_ctx)) {
+		pr_err("Completion context is NULL\n");
+		return NULL;
+	}
+
 	if (unlikely(command_id >= queue->q_depth)) {
 		pr_err("command id is larger than the queue size. cmd_id: %u queue size %d\n",
 		       command_id, queue->q_depth);
@@ -1041,9 +1046,41 @@
 				      feature_ver);
 }
 
+int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev)
+{
+	return ena_dev->rss.hash_func;
+}
+
+static void ena_com_hash_key_fill_default_key(struct ena_com_dev *ena_dev)
+{
+	struct ena_admin_feature_rss_flow_hash_control *hash_key =
+		(ena_dev->rss).hash_key;
+
+	netdev_rss_key_fill(&hash_key->key, sizeof(hash_key->key));
+	/* The key is stored in the device in u32 array
+	 * as well as the API requires the key to be passed in this
+	 * format. Thus the size of our array should be divided by 4
+	 */
+	hash_key->keys_num = sizeof(hash_key->key) / sizeof(u32);
+}
+
 static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev)
 {
 	struct ena_rss *rss = &ena_dev->rss;
+	struct ena_admin_feature_rss_flow_hash_control *hash_key;
+	struct ena_admin_get_feat_resp get_resp;
+	int rc;
+
+	hash_key = (ena_dev->rss).hash_key;
+
+	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
+				    ENA_ADMIN_RSS_HASH_FUNCTION,
+				    ena_dev->rss.hash_key_dma_addr,
+				    sizeof(ena_dev->rss.hash_key), 0);
+	if (unlikely(rc)) {
+		hash_key = NULL;
+		return -EOPNOTSUPP;
+	}
 
 	rss->hash_key =
 		dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key),
@@ -1254,30 +1291,6 @@
 	return 0;
 }
 
-static int ena_com_ind_tbl_convert_from_device(struct ena_com_dev *ena_dev)
-{
-	u16 dev_idx_to_host_tbl[ENA_TOTAL_NUM_QUEUES] = { (u16)-1 };
-	struct ena_rss *rss = &ena_dev->rss;
-	u8 idx;
-	u16 i;
-
-	for (i = 0; i < ENA_TOTAL_NUM_QUEUES; i++)
-		dev_idx_to_host_tbl[ena_dev->io_sq_queues[i].idx] = i;
-
-	for (i = 0; i < 1 << rss->tbl_log_size; i++) {
-		if (rss->rss_ind_tbl[i].cq_idx > ENA_TOTAL_NUM_QUEUES)
-			return -EINVAL;
-		idx = (u8)rss->rss_ind_tbl[i].cq_idx;
-
-		if (dev_idx_to_host_tbl[idx] > ENA_TOTAL_NUM_QUEUES)
-			return -EINVAL;
-
-		rss->host_rss_ind_tbl[i] = dev_idx_to_host_tbl[idx];
-	}
-
-	return 0;
-}
-
 static void ena_com_update_intr_delay_resolution(struct ena_com_dev *ena_dev,
 						 u16 intr_delay_resolution)
 {
@@ -2297,15 +2310,16 @@
 
 	switch (func) {
 	case ENA_ADMIN_TOEPLITZ:
-		if (key_len > sizeof(hash_key->key)) {
-			pr_err("key len (%hu) is bigger than the max supported (%zu)\n",
-			       key_len, sizeof(hash_key->key));
-			return -EINVAL;
+		if (key) {
+			if (key_len != sizeof(hash_key->key)) {
+				pr_err("key len (%hu) doesn't equal the supported size (%zu)\n",
+				       key_len, sizeof(hash_key->key));
+				return -EINVAL;
+			}
+			memcpy(hash_key->key, key, key_len);
+			rss->hash_init_val = init_val;
+			hash_key->keys_num = key_len >> 2;
 		}
-
-		memcpy(hash_key->key, key, key_len);
-		rss->hash_init_val = init_val;
-		hash_key->keys_num = key_len >> 2;
 		break;
 	case ENA_ADMIN_CRC32:
 		rss->hash_init_val = init_val;
@@ -2342,7 +2356,11 @@
 	if (unlikely(rc))
 		return rc;
 
-	rss->hash_func = get_resp.u.flow_hash_func.selected_func;
+	/* ffs() returns 1 in case the lsb is set */
+	rss->hash_func = ffs(get_resp.u.flow_hash_func.selected_func);
+	if (rss->hash_func)
+		rss->hash_func--;
+
 	if (func)
 		*func = rss->hash_func;
 
@@ -2606,10 +2624,6 @@
 	if (!ind_tbl)
 		return 0;
 
-	rc = ena_com_ind_tbl_convert_from_device(ena_dev);
-	if (unlikely(rc))
-		return rc;
-
 	for (i = 0; i < (1 << rss->tbl_log_size); i++)
 		ind_tbl[i] = rss->host_rss_ind_tbl[i];
 
@@ -2626,9 +2640,15 @@
 	if (unlikely(rc))
 		goto err_indr_tbl;
 
+	/* The following function might return unsupported in case the
+	 * device doesn't support setting the key / hash function. We can safely
+	 * ignore this error and have indirection table support only.
+	 */
 	rc = ena_com_hash_key_allocate(ena_dev);
-	if (unlikely(rc))
+	if (unlikely(rc) && rc != -EOPNOTSUPP)
 		goto err_hash_key;
+	else if (rc != -EOPNOTSUPP)
+		ena_com_hash_key_fill_default_key(ena_dev);
 
 	rc = ena_com_hash_ctrl_init(ena_dev);
 	if (unlikely(rc))
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 0ce37d5..469f298 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -44,6 +44,7 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/wait.h>
+#include <linux/netdevice.h>
 
 #include "ena_common_defs.h"
 #include "ena_admin_defs.h"
@@ -655,6 +656,14 @@
  */
 void ena_com_rss_destroy(struct ena_com_dev *ena_dev);
 
+/* ena_com_get_current_hash_function - Get RSS hash function
+ * @ena_dev: ENA communication layer struct
+ *
+ * Return the current hash function.
+ * @return: 0 or one of the ena_admin_hash_functions values.
+ */
+int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev);
+
 /* ena_com_fill_hash_function - Fill RSS hash function
  * @ena_dev: ENA communication layer struct
  * @func: The hash function (Toeplitz or crc)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index b4e891d..ced1d57 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -636,6 +636,28 @@
 	return ENA_HASH_KEY_SIZE;
 }
 
+static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir)
+{
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
+	int i, rc;
+
+	if (!indir)
+		return 0;
+
+	rc = ena_com_indirect_table_get(ena_dev, indir);
+	if (rc)
+		return rc;
+
+	/* Our internal representation of the indices is: even indices
+	 * for Tx and uneven indices for Rx. We need to convert the Rx
+	 * indices to be consecutive
+	 */
+	for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++)
+		indir[i] = ENA_IO_RXQ_IDX_TO_COMBINED_IDX(indir[i]);
+
+	return rc;
+}
+
 static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 			u8 *hfunc)
 {
@@ -644,11 +666,25 @@
 	u8 func;
 	int rc;
 
-	rc = ena_com_indirect_table_get(adapter->ena_dev, indir);
+	rc = ena_indirection_table_get(adapter, indir);
 	if (rc)
 		return rc;
 
+	/* We call this function in order to check if the device
+	 * supports getting/setting the hash function.
+	 */
 	rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key);
+
+	if (rc) {
+		if (rc == -EOPNOTSUPP) {
+			key = NULL;
+			hfunc = NULL;
+			rc = 0;
+		}
+
+		return rc;
+	}
+
 	if (rc)
 		return rc;
 
@@ -657,7 +693,7 @@
 		func = ETH_RSS_HASH_TOP;
 		break;
 	case ENA_ADMIN_CRC32:
-		func = ETH_RSS_HASH_XOR;
+		func = ETH_RSS_HASH_CRC32;
 		break;
 	default:
 		netif_err(adapter, drv, netdev,
@@ -700,10 +736,13 @@
 	}
 
 	switch (hfunc) {
+	case ETH_RSS_HASH_NO_CHANGE:
+		func = ena_com_get_current_hash_function(ena_dev);
+		break;
 	case ETH_RSS_HASH_TOP:
 		func = ENA_ADMIN_TOEPLITZ;
 		break;
-	case ETH_RSS_HASH_XOR:
+	case ETH_RSS_HASH_CRC32:
 		func = ENA_ADMIN_CRC32;
 		break;
 	default:
@@ -814,6 +853,7 @@
 	.set_channels		= ena_set_channels,
 	.get_tunable		= ena_get_tunable,
 	.set_tunable		= ena_set_tunable,
+	.get_ts_info            = ethtool_op_get_ts_info,
 };
 
 void ena_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 894e8c1..0b2fd96 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3706,8 +3706,8 @@
 	if (adapter->keep_alive_timeout == ENA_HW_HINTS_NO_TIMEOUT)
 		return;
 
-	keep_alive_expired = round_jiffies(adapter->last_keep_alive_jiffies +
-					   adapter->keep_alive_timeout);
+	keep_alive_expired = adapter->last_keep_alive_jiffies +
+			     adapter->keep_alive_timeout;
 	if (unlikely(time_is_before_jiffies(keep_alive_expired))) {
 		netif_err(adapter, drv, adapter->netdev,
 			  "Keep alive watchdog timeout.\n");
@@ -3809,7 +3809,7 @@
 	}
 
 	/* Reset the timer */
-	mod_timer(&adapter->timer_service, jiffies + HZ);
+	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 }
 
 static int ena_calc_max_io_queue_num(struct pci_dev *pdev,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 094324f..8795e0b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -130,6 +130,8 @@
 
 #define ENA_IO_TXQ_IDX(q)	(2 * (q))
 #define ENA_IO_RXQ_IDX(q)	(2 * (q) + 1)
+#define ENA_IO_TXQ_IDX_TO_COMBINED_IDX(q)	((q) / 2)
+#define ENA_IO_RXQ_IDX_TO_COMBINED_IDX(q)	(((q) - 1) / 2)
 
 #define ENA_MGMNT_IRQ_IDX		0
 #define ENA_IO_IRQ_FIRST_IDX		1
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index a1f99be..7b55633 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -722,6 +722,11 @@
 	if (flags & ~AQ_PRIV_FLAGS_MASK)
 		return -EOPNOTSUPP;
 
+	if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) {
+		netdev_info(ndev, "Can't enable more than one loopback simultaneously\n");
+		return -EINVAL;
+	}
+
 	cfg->priv_flags = flags;
 
 	if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 6102251..03ff92b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -163,7 +163,7 @@
 	}
 
 	if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
-	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci),
+	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK,
 		       aq_nic->active_vlans))) {
 		netdev_err(aq_nic->ndev,
 			   "ethtool: unknown vlan-id specified");
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index cc70c60..251767c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -337,6 +337,8 @@
 
 	void (*enable_ptp)(struct aq_hw_s *self, int enable);
 
+	void (*adjust_ptp)(struct aq_hw_s *self, uint64_t adj);
+
 	int (*set_eee_rate)(struct aq_hw_s *self, u32 speed);
 
 	int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index c85e3e2..e95f6a6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -533,8 +533,10 @@
 				     dx_buff->len,
 				     DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa)))
+	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) {
+		ret = 0;
 		goto exit;
+	}
 
 	first = dx_buff;
 	dx_buff->len_pkt = skb->len;
@@ -655,10 +657,6 @@
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
-		if (err >= 0) {
-			++ring->stats.tx.packets;
-			ring->stats.tx.bytes += skb->len;
-		}
 	} else {
 		err = NETDEV_TX_BUSY;
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 6b27af0..78b6f32 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -359,7 +359,8 @@
 	netif_device_detach(nic->ndev);
 	netif_tx_stop_all_queues(nic->ndev);
 
-	aq_nic_stop(nic);
+	if (netif_running(nic->ndev))
+		aq_nic_stop(nic);
 
 	if (deep) {
 		aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol);
@@ -375,7 +376,7 @@
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct aq_nic_s *nic;
-	int ret;
+	int ret = 0;
 
 	nic = pci_get_drvdata(pdev);
 
@@ -390,9 +391,11 @@
 			goto err_exit;
 	}
 
-	ret = aq_nic_start(nic);
-	if (ret)
-		goto err_exit;
+	if (netif_running(nic->ndev)) {
+		ret = aq_nic_start(nic);
+		if (ret)
+			goto err_exit;
+	}
 
 	netif_device_attach(nic->ndev);
 	netif_tx_start_all_queues(nic->ndev);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 951d86f..bae95a6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -272,9 +272,12 @@
 			}
 		}
 
-		if (unlikely(buff->is_eop))
-			dev_kfree_skb_any(buff->skb);
+		if (unlikely(buff->is_eop)) {
+			++self->stats.rx.packets;
+			self->stats.tx.bytes += buff->skb->len;
 
+			dev_kfree_skb_any(buff->skb);
+		}
 		buff->pa = 0U;
 		buff->eop_index = 0xffffU;
 		self->sw_head = aq_ring_next_dx(self, self->sw_head);
@@ -351,7 +354,8 @@
 				err = 0;
 				goto err_exit;
 			}
-			if (buff->is_error || buff->is_cso_err) {
+			if (buff->is_error ||
+			    (buff->is_lro && buff->is_cso_err)) {
 				buff_ = buff;
 				do {
 					next_ = buff_->next,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 991e4d3..2c96f20 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -78,7 +78,8 @@
 			u32 is_cleaned:1;
 			u32 is_error:1;
 			u32 is_vlan:1;
-			u32 rsvd3:4;
+			u32 is_lro:1;
+			u32 rsvd3:3;
 			u16 eop_index;
 			u16 rsvd4;
 		};
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index ec041f7..d20d91c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -823,6 +823,8 @@
 			}
 		}
 
+		buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
+				  rxd_wb->status);
 		if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
 			buff->len = rxd_wb->pkt_len %
 				AQ_CFG_RX_FRAME_MAX;
@@ -835,8 +837,7 @@
 				rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ?
 				AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len;
 
-			if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
-				rxd_wb->status) {
+			if (buff->is_lro) {
 				/* LRO */
 				buff->next = rxd_wb->next_desc_ptr;
 				++ring->stats.rx.lro_packets;
@@ -884,13 +885,16 @@
 {
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	unsigned int i = 0U;
+	u32 vlan_promisc;
+	u32 l2_promisc;
 
-	hw_atl_rpfl2promiscuous_mode_en_set(self,
-					    IS_FILTER_ENABLED(IFF_PROMISC));
+	l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) ||
+		     !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET));
+	vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc;
 
-	hw_atl_rpf_vlan_prom_mode_en_set(self,
-				     IS_FILTER_ENABLED(IFF_PROMISC) ||
-				     cfg->is_vlan_force_promisc);
+	hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc);
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc);
 
 	hw_atl_rpfl2multicast_flr_en_set(self,
 					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
@@ -1161,6 +1165,8 @@
 {
 	self->ptp_clk_offset += delta;
 
+	self->aq_fw_ops->adjust_ptp(self, self->ptp_clk_offset);
+
 	return 0;
 }
 
@@ -1211,7 +1217,7 @@
 	fwreq.ptp_gpio_ctrl.index = index;
 	fwreq.ptp_gpio_ctrl.period = period;
 	/* Apply time offset */
-	fwreq.ptp_gpio_ctrl.start = start - self->ptp_clk_offset;
+	fwreq.ptp_gpio_ctrl.start = start;
 
 	size = sizeof(fwreq.msg_id) + sizeof(fwreq.ptp_gpio_ctrl);
 	return self->aq_fw_ops->send_fw_request(self, &fwreq, size);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index f547baa..354705f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -22,6 +22,7 @@
 #define HW_ATL_MIF_ADDR         0x0208U
 #define HW_ATL_MIF_VAL          0x020CU
 
+#define HW_ATL_MPI_RPC_ADDR     0x0334U
 #define HW_ATL_RPC_CONTROL_ADR  0x0338U
 #define HW_ATL_RPC_STATE_ADR    0x033CU
 
@@ -53,15 +54,14 @@
 };
 
 static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
-
 static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 				      enum hal_atl_utils_fw_state_e state);
-
 static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
 static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self);
 static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self);
 static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self);
 static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self);
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self);
 
 int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
@@ -476,6 +476,10 @@
 					self, self->mbox_addr,
 					self->mbox_addr != 0U,
 					1000U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self,
+					self->rpc_addr,
+					self->rpc_addr != 0U,
+					1000U, 100000U);
 
 	return err;
 }
@@ -531,6 +535,12 @@
 						self, fw.val,
 						sw.tid == fw.tid,
 						1000U, 100000U);
+		if (err < 0)
+			goto err_exit;
+
+		err = aq_hw_err_from_flags(self);
+		if (err < 0)
+			goto err_exit;
 
 		if (fw.len == 0xFFFFU) {
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
@@ -1025,6 +1035,11 @@
 	return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR);
 }
 
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR);
+}
+
 const struct aq_fw_ops aq_fw_1x_ops = {
 	.init = hw_atl_utils_mpi_create,
 	.deinit = hw_atl_fw1x_deinit,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 97ebf84..77a4ed6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -30,6 +30,9 @@
 #define HW_ATL_FW3X_EXT_CONTROL_ADDR     0x378
 #define HW_ATL_FW3X_EXT_STATE_ADDR       0x37c
 
+#define HW_ATL_FW3X_PTP_ADJ_LSW_ADDR	 0x50a0
+#define HW_ATL_FW3X_PTP_ADJ_MSW_ADDR	 0x50a4
+
 #define HW_ATL_FW2X_CAP_PAUSE            BIT(CAPS_HI_PAUSE)
 #define HW_ATL_FW2X_CAP_ASYM_PAUSE       BIT(CAPS_HI_ASYMMETRIC_PAUSE)
 #define HW_ATL_FW2X_CAP_SLEEP_PROXY      BIT(CAPS_HI_SLEEP_PROXY)
@@ -475,6 +478,14 @@
 	aq_hw_write_reg(self, HW_ATL_FW3X_EXT_CONTROL_ADDR, ptp_opts);
 }
 
+static void aq_fw3x_adjust_ptp(struct aq_hw_s *self, uint64_t adj)
+{
+	aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_LSW_ADDR,
+			(adj >>  0) & 0xffffffff);
+	aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_MSW_ADDR,
+			(adj >> 32) & 0xffffffff);
+}
+
 static int aq_fw2x_led_control(struct aq_hw_s *self, u32 mode)
 {
 	if (self->fw_ver_actual < HW_ATL_FW_VER_LED)
@@ -633,4 +644,5 @@
 	.enable_ptp         = aq_fw3x_enable_ptp,
 	.led_control        = aq_fw2x_led_control,
 	.set_phyloopback    = aq_fw2x_set_phyloopback,
+	.adjust_ptp         = aq_fw3x_adjust_ptp,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 597e6fd..fd6e0e4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11786,6 +11786,14 @@
 	if (version_printed++ == 0)
 		pr_info("%s", version);
 
+	/* Clear any pending DMA transactions from crash kernel
+	 * while loading driver in capture kernel.
+	 */
+	if (is_kdump_kernel()) {
+		pci_clear_master(pdev);
+		pcie_flr(pdev);
+	}
+
 	max_irqs = bnxt_get_max_irq(pdev);
 	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
 	if (!dev)
@@ -11983,10 +11991,10 @@
 		dev_close(dev);
 
 	bnxt_ulp_shutdown(bp);
+	bnxt_clear_int_mode(bp);
+	pci_disable_device(pdev);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		bnxt_clear_int_mode(bp);
-		pci_disable_device(pdev);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h
index b384997..99e2c6d 100644
--- a/drivers/net/ethernet/broadcom/cnic_defs.h
+++ b/drivers/net/ethernet/broadcom/cnic_defs.h
@@ -543,13 +543,13 @@
 #define L4_KWQ_UPDATE_PG_RESERVERD2_SHIFT 2
 #endif
 #if defined(__BIG_ENDIAN)
-	u16 reserverd3;
+	u16 reserved3;
 	u8 da0;
 	u8 da1;
 #elif defined(__LITTLE_ENDIAN)
 	u8 da1;
 	u8 da0;
-	u16 reserverd3;
+	u16 reserved3;
 #endif
 #if defined(__BIG_ENDIAN)
 	u8 da2;
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index dbf7070..a3f0f27 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -652,6 +652,7 @@
 #define MACB_CAPS_GEM_HAS_PTP			0x00000040
 #define MACB_CAPS_BD_RD_PREFETCH		0x00000080
 #define MACB_CAPS_NEEDS_RSTONUBR		0x00000100
+#define MACB_CAPS_MACB_IS_EMAC			0x08000000
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4508f0d..2c28da1 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -572,8 +572,21 @@
 	old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR);
 
 	/* Clear all the bits we might set later */
-	ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) |
-		  GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+	ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE));
+
+	if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
+		if (state->interface == PHY_INTERFACE_MODE_RMII)
+			ctrl |= MACB_BIT(RM9200_RMII);
+	} else {
+		ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+
+		/* We do not support MLO_PAUSE_RX yet */
+		if (state->pause & MLO_PAUSE_TX)
+			ctrl |= MACB_BIT(PAE);
+
+		if (state->interface == PHY_INTERFACE_MODE_SGMII)
+			ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
+	}
 
 	if (state->speed == SPEED_1000)
 		ctrl |= GEM_BIT(GBE);
@@ -583,13 +596,6 @@
 	if (state->duplex)
 		ctrl |= MACB_BIT(FD);
 
-	/* We do not support MLO_PAUSE_RX yet */
-	if (state->pause & MLO_PAUSE_TX)
-		ctrl |= MACB_BIT(PAE);
-
-	if (state->interface == PHY_INTERFACE_MODE_SGMII)
-		ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
-
 	/* Apply the new configuration, if any */
 	if (old_ctrl ^ ctrl)
 		macb_or_gem_writel(bp, NCFGR, ctrl);
@@ -608,9 +614,10 @@
 	unsigned int q;
 	u32 ctrl;
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
-		queue_writel(queue, IDR,
-			     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+			queue_writel(queue, IDR,
+				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
 
 	/* Disable Rx and Tx */
 	ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE));
@@ -627,17 +634,19 @@
 	struct macb_queue *queue;
 	unsigned int q;
 
-	macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
+		macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
 
-	/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
-	 * cleared the pipeline and control registers.
-	 */
-	bp->macbgem_ops.mog_init_rings(bp);
-	macb_init_buffers(bp);
+		/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
+		 * cleared the pipeline and control registers.
+		 */
+		bp->macbgem_ops.mog_init_rings(bp);
+		macb_init_buffers(bp);
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
-		queue_writel(queue, IER,
-			     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+			queue_writel(queue, IER,
+				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+	}
 
 	/* Enable Rx and Tx */
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
@@ -3790,6 +3799,10 @@
 	u32 ctl;
 	int ret;
 
+	ret = pm_runtime_get_sync(&lp->pdev->dev);
+	if (ret < 0)
+		return ret;
+
 	/* Clear internal statistics */
 	ctl = macb_readl(lp, NCR);
 	macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT));
@@ -3854,7 +3867,7 @@
 			  q->rx_buffers, q->rx_buffers_dma);
 	q->rx_buffers = NULL;
 
-	return 0;
+	return pm_runtime_put(&lp->pdev->dev);
 }
 
 /* Transmit packet */
@@ -4037,7 +4050,6 @@
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct macb *bp = netdev_priv(dev);
 	int err;
-	u32 reg;
 
 	bp->queues[0].bp = bp;
 
@@ -4051,11 +4063,7 @@
 
 	macb_writel(bp, NCR, 0);
 
-	reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG);
-	if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
-		reg |= MACB_BIT(RM9200_RMII);
-
-	macb_writel(bp, NCFGR, reg);
+	macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG));
 
 	return 0;
 }
@@ -4214,7 +4222,7 @@
 };
 
 static const struct macb_config emac_config = {
-	.caps = MACB_CAPS_NEEDS_RSTONUBR,
+	.caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC,
 	.clk_init = at91ether_clk_init,
 	.init = at91ether_init,
 };
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 17a4110..8ff28ed 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -410,10 +410,19 @@
 	lmac = &bgx->lmac[lmacid];
 
 	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	if (enable)
+	if (enable) {
 		cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN;
-	else
+
+		/* enable TX FIFO Underflow interrupt */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S,
+			       GMI_TXX_INT_UNDFLW);
+	} else {
 		cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+
+		/* Disable TX FIFO Underflow interrupt */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C,
+			       GMI_TXX_INT_UNDFLW);
+	}
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
 
 	if (bgx->is_rgx)
@@ -1535,6 +1544,48 @@
 	return bgx_init_of_phy(bgx);
 }
 
+static irqreturn_t bgx_intr_handler(int irq, void *data)
+{
+	struct bgx *bgx = (struct bgx *)data;
+	u64 status, val;
+	int lmac;
+
+	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
+		status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT);
+		if (status & GMI_TXX_INT_UNDFLW) {
+			pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n",
+				bgx->bgx_id, lmac);
+			val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG);
+			val &= ~CMR_EN;
+			bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+			val |= CMR_EN;
+			bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+		}
+		/* clear interrupts */
+		bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void bgx_register_intr(struct pci_dev *pdev)
+{
+	struct bgx *bgx = pci_get_drvdata(pdev);
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET,
+				    BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES);
+	if (ret < 0) {
+		pci_err(pdev, "Req for #%d msix vectors failed\n",
+			BGX_LMAC_VEC_OFFSET);
+		return;
+	}
+	ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL,
+			      bgx, "BGX%d", bgx->bgx_id);
+	if (ret)
+		pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+}
+
 static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int err;
@@ -1550,7 +1601,7 @@
 
 	pci_set_drvdata(pdev, bgx);
 
-	err = pci_enable_device(pdev);
+	err = pcim_enable_device(pdev);
 	if (err) {
 		dev_err(dev, "Failed to enable PCI device\n");
 		pci_set_drvdata(pdev, NULL);
@@ -1604,6 +1655,8 @@
 
 	bgx_init_hw(bgx);
 
+	bgx_register_intr(pdev);
+
 	/* Enable all LMACs */
 	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
 		err = bgx_lmac_enable(bgx, lmac);
@@ -1620,6 +1673,7 @@
 
 err_enable:
 	bgx_vnic[bgx->bgx_id] = NULL;
+	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 err_release_regions:
 	pci_release_regions(pdev);
 err_disable_device:
@@ -1637,6 +1691,8 @@
 	for (lmac = 0; lmac < bgx->lmac_count; lmac++)
 		bgx_lmac_disable(bgx, lmac);
 
+	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+
 	bgx_vnic[bgx->bgx_id] = NULL;
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 2588870..cdea493 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -180,6 +180,15 @@
 #define BGX_GMP_GMI_TXX_BURST		0x38228
 #define BGX_GMP_GMI_TXX_MIN_PKT		0x38240
 #define BGX_GMP_GMI_TXX_SGMII_CTL	0x38300
+#define BGX_GMP_GMI_TXX_INT		0x38500
+#define BGX_GMP_GMI_TXX_INT_W1S		0x38508
+#define BGX_GMP_GMI_TXX_INT_ENA_W1C	0x38510
+#define BGX_GMP_GMI_TXX_INT_ENA_W1S	0x38518
+#define  GMI_TXX_INT_PTP_LOST			BIT_ULL(4)
+#define  GMI_TXX_INT_LATE_COL			BIT_ULL(3)
+#define  GMI_TXX_INT_XSDEF			BIT_ULL(2)
+#define  GMI_TXX_INT_XSCOL			BIT_ULL(1)
+#define  GMI_TXX_INT_UNDFLW			BIT_ULL(0)
 
 #define BGX_MSIX_VEC_0_29_ADDR		0x400000 /* +(0..29) << 4 */
 #define BGX_MSIX_VEC_0_29_CTL		0x400008
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index bbd7b31..ddf60dc 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2013,10 +2013,10 @@
 		napi_disable(&enic->napi[i]);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 	if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX)
 		for (i = 0; i < enic->wq_count; i++)
 			napi_disable(&enic->napi[enic_cq_wq(enic, i)]);
+	netif_tx_disable(netdev);
 
 	if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic))
 		enic_dev_del_station_addr(enic);
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 1ea3372..e94ae9b 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1405,6 +1405,8 @@
 	mac_addr = of_get_mac_address(np);
 	if (!IS_ERR(mac_addr))
 		ether_addr_copy(pdata->dev_addr, mac_addr);
+	else if (PTR_ERR(mac_addr) == -EPROBE_DEFER)
+		return ERR_CAST(mac_addr);
 
 	return pdata;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ec5f6ee..492bc94 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6113,6 +6113,9 @@
 static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys,
 				     struct hclge_fd_rule_tuples *tuples)
 {
+#define flow_ip6_src fkeys->addrs.v6addrs.src.in6_u.u6_addr32
+#define flow_ip6_dst fkeys->addrs.v6addrs.dst.in6_u.u6_addr32
+
 	tuples->ether_proto = be16_to_cpu(fkeys->basic.n_proto);
 	tuples->ip_proto = fkeys->basic.ip_proto;
 	tuples->dst_port = be16_to_cpu(fkeys->ports.dst);
@@ -6121,12 +6124,12 @@
 		tuples->src_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.src);
 		tuples->dst_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.dst);
 	} else {
-		memcpy(tuples->src_ip,
-		       fkeys->addrs.v6addrs.src.in6_u.u6_addr32,
-		       sizeof(tuples->src_ip));
-		memcpy(tuples->dst_ip,
-		       fkeys->addrs.v6addrs.dst.in6_u.u6_addr32,
-		       sizeof(tuples->dst_ip));
+		int i;
+
+		for (i = 0; i < IPV6_SIZE; i++) {
+			tuples->src_ip[i] = be32_to_cpu(flow_ip6_src[i]);
+			tuples->dst_ip[i] = be32_to_cpu(flow_ip6_dst[i]);
+		}
 	}
 }
 
@@ -9834,6 +9837,13 @@
 		return ret;
 	}
 
+	ret = init_mgr_tbl(hdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"failed to reinit manager table, ret = %d\n", ret);
+		return ret;
+	}
+
 	ret = hclge_init_fd_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "fd table init fail, ret=%d\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 180224e..28db132 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -566,7 +566,7 @@
 	 */
 	kinfo->num_tc = vport->vport_id ? 1 :
 			min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc);
-	vport->qs_offset = (vport->vport_id ? hdev->tm_info.num_tc : 0) +
+	vport->qs_offset = (vport->vport_id ? HNAE3_MAX_TC : 0) +
 				(vport->vport_id ? (vport->vport_id - 1) : 0);
 
 	max_rss_size = min_t(u16, hdev->rss_size_max,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 69523ac..56b9e44 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2362,7 +2362,7 @@
 		goto error_param;
 	}
 
-	if (i40e_vc_validate_vqs_bitmaps(vqs)) {
+	if (!i40e_vc_validate_vqs_bitmaps(vqs)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2424,7 +2424,7 @@
 		goto error_param;
 	}
 
-	if (i40e_vc_validate_vqs_bitmaps(vqs)) {
+	if (!i40e_vc_validate_vqs_bitmaps(vqs)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 4459bc5..6873998 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1660,6 +1660,7 @@
 	__le32 count;
 	struct ice_aqc_get_pkg_info pkg_info[1];
 };
+
 /**
  * struct ice_aq_desc - Admin Queue (AQ) descriptor
  * @flags: ICE_AQ_FLAG_* flags
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index d8e975c..81885ef 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -324,7 +324,7 @@
 			if (err)
 				return err;
 
-			dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
+			dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
 				 ring->q_index);
 		} else {
 			ring->zca.free = NULL;
@@ -405,8 +405,7 @@
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
 	if (err) {
-		dev_err(&vsi->back->pdev->dev,
-			"Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
 			pf_q, err);
 		return -EIO;
 	}
@@ -428,8 +427,7 @@
 	      ice_alloc_rx_bufs_slow_zc(ring, ICE_DESC_UNUSED(ring)) :
 	      ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
 	if (err)
-		dev_info(&vsi->back->pdev->dev,
-			 "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
+		dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
 			 ring->xsk_umem ? "UMEM enabled " : "",
 			 ring->q_index, pf_q);
 
@@ -490,8 +488,7 @@
 	/* wait for the change to finish */
 	ret = ice_pf_rxq_wait(pf, pf_q, ena);
 	if (ret)
-		dev_err(ice_pf_to_dev(pf),
-			"VSI idx %d Rx ring %d %sable timeout\n",
+		dev_err(ice_pf_to_dev(pf), "VSI idx %d Rx ring %d %sable timeout\n",
 			vsi->idx, pf_q, (ena ? "en" : "dis"));
 
 	return ret;
@@ -506,20 +503,15 @@
  */
 int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 {
-	struct ice_pf *pf = vsi->back;
-	int v_idx = 0, num_q_vectors;
-	struct device *dev;
-	int err;
+	struct device *dev = ice_pf_to_dev(vsi->back);
+	int v_idx, err;
 
-	dev = ice_pf_to_dev(pf);
 	if (vsi->q_vectors[0]) {
 		dev_dbg(dev, "VSI %d has existing q_vectors\n", vsi->vsi_num);
 		return -EEXIST;
 	}
 
-	num_q_vectors = vsi->num_q_vectors;
-
-	for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
+	for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) {
 		err = ice_vsi_alloc_q_vector(vsi, v_idx);
 		if (err)
 			goto err_out;
@@ -648,8 +640,7 @@
 	status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle,
 				 1, qg_buf, buf_len, NULL);
 	if (status) {
-		dev_err(ice_pf_to_dev(pf),
-			"Failed to set LAN Tx queue context, error: %d\n",
+		dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %d\n",
 			status);
 		return -ENODEV;
 	}
@@ -815,14 +806,12 @@
 	 * queues at the hardware level anyway.
 	 */
 	if (status == ICE_ERR_RESET_ONGOING) {
-		dev_dbg(&vsi->back->pdev->dev,
-			"Reset in progress. LAN Tx queues already disabled\n");
+		dev_dbg(ice_pf_to_dev(vsi->back), "Reset in progress. LAN Tx queues already disabled\n");
 	} else if (status == ICE_ERR_DOES_NOT_EXIST) {
-		dev_dbg(&vsi->back->pdev->dev,
-			"LAN Tx queues do not exist, nothing to disable\n");
+		dev_dbg(ice_pf_to_dev(vsi->back), "LAN Tx queues do not exist, nothing to disable\n");
 	} else if (status) {
-		dev_err(&vsi->back->pdev->dev,
-			"Failed to disable LAN Tx queues, error: %d\n", status);
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %d\n",
+			status);
 		return -ENODEV;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 0207e28..04d5db0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -25,20 +25,6 @@
 }
 
 /**
- * ice_dev_onetime_setup - Temporary HW/FW workarounds
- * @hw: pointer to the HW structure
- *
- * This function provides temporary workarounds for certain issues
- * that are expected to be fixed in the HW/FW.
- */
-void ice_dev_onetime_setup(struct ice_hw *hw)
-{
-#define MBX_PF_VT_PFALLOC	0x00231E80
-	/* set VFs per PF */
-	wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF));
-}
-
-/**
  * ice_clear_pf_cfg - Clear PF configuration
  * @hw: pointer to the hardware structure
  *
@@ -602,10 +588,10 @@
 }
 
 /**
- * ice_get_itr_intrl_gran - determine int/intrl granularity
+ * ice_get_itr_intrl_gran
  * @hw: pointer to the HW struct
  *
- * Determines the ITR/intrl granularities based on the maximum aggregate
+ * Determines the ITR/INTRL granularities based on the maximum aggregate
  * bandwidth according to the device's configuration during power-on.
  */
 static void ice_get_itr_intrl_gran(struct ice_hw *hw)
@@ -763,8 +749,6 @@
 	if (status)
 		goto err_unroll_sched;
 
-	ice_dev_onetime_setup(hw);
-
 	/* Get MAC information */
 	/* A single port can report up to two (LAN and WoL) addresses */
 	mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
@@ -834,7 +818,7 @@
  */
 enum ice_status ice_check_reset(struct ice_hw *hw)
 {
-	u32 cnt, reg = 0, grst_delay;
+	u32 cnt, reg = 0, grst_delay, uld_mask;
 
 	/* Poll for Device Active state in case a recent CORER, GLOBR,
 	 * or EMPR has occurred. The grst delay value is in 100ms units.
@@ -856,13 +840,20 @@
 		return ICE_ERR_RESET_FAILED;
 	}
 
-#define ICE_RESET_DONE_MASK	(GLNVM_ULD_CORER_DONE_M | \
-				 GLNVM_ULD_GLOBR_DONE_M)
+#define ICE_RESET_DONE_MASK	(GLNVM_ULD_PCIER_DONE_M |\
+				 GLNVM_ULD_PCIER_DONE_1_M |\
+				 GLNVM_ULD_CORER_DONE_M |\
+				 GLNVM_ULD_GLOBR_DONE_M |\
+				 GLNVM_ULD_POR_DONE_M |\
+				 GLNVM_ULD_POR_DONE_1_M |\
+				 GLNVM_ULD_PCIER_DONE_2_M)
+
+	uld_mask = ICE_RESET_DONE_MASK;
 
 	/* Device is Active; check Global Reset processes are done */
 	for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) {
-		reg = rd32(hw, GLNVM_ULD) & ICE_RESET_DONE_MASK;
-		if (reg == ICE_RESET_DONE_MASK) {
+		reg = rd32(hw, GLNVM_ULD) & uld_mask;
+		if (reg == uld_mask) {
 			ice_debug(hw, ICE_DBG_INIT,
 				  "Global reset processes done. %d\n", cnt);
 			break;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index b5c013f..f9fc005 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -54,8 +54,6 @@
 
 void ice_set_safe_mode_caps(struct ice_hw *hw);
 
-void ice_dev_onetime_setup(struct ice_hw *hw);
-
 enum ice_status
 ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
 		  u32 rxq_index);
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 713e8a8..adb8dab 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -1323,13 +1323,13 @@
 }
 
 /**
- * ice_aq_query_port_ets - query port ets configuration
+ * ice_aq_query_port_ets - query port ETS configuration
  * @pi: port information structure
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
  * @cd: pointer to command details structure or NULL
  *
- * query current port ets configuration
+ * query current port ETS configuration
  */
 static enum ice_status
 ice_aq_query_port_ets(struct ice_port_info *pi,
@@ -1416,13 +1416,13 @@
 }
 
 /**
- * ice_query_port_ets - query port ets configuration
+ * ice_query_port_ets - query port ETS configuration
  * @pi: port information structure
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
  * @cd: pointer to command details structure or NULL
  *
- * query current port ets configuration and update the
+ * query current port ETS configuration and update the
  * SW DB with the TC changes
  */
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 0664e5b..7108fb4 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -315,9 +315,9 @@
  */
 void ice_dcb_rebuild(struct ice_pf *pf)
 {
-	struct ice_dcbx_cfg *local_dcbx_cfg, *desired_dcbx_cfg, *prev_cfg;
 	struct ice_aqc_port_ets_elem buf = { 0 };
 	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_dcbx_cfg *err_cfg;
 	enum ice_status ret;
 
 	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
@@ -330,53 +330,25 @@
 	if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags))
 		return;
 
-	local_dcbx_cfg = &pf->hw.port_info->local_dcbx_cfg;
-	desired_dcbx_cfg = &pf->hw.port_info->desired_dcbx_cfg;
+	mutex_lock(&pf->tc_mutex);
 
-	/* Save current willing state and force FW to unwilling */
-	local_dcbx_cfg->etscfg.willing = 0x0;
-	local_dcbx_cfg->pfc.willing = 0x0;
-	local_dcbx_cfg->app_mode = ICE_DCBX_APPS_NON_WILLING;
+	if (!pf->hw.port_info->is_sw_lldp)
+		ice_cfg_etsrec_defaults(pf->hw.port_info);
 
-	ice_cfg_etsrec_defaults(pf->hw.port_info);
 	ret = ice_set_dcb_cfg(pf->hw.port_info);
 	if (ret) {
-		dev_err(dev, "Failed to set DCB to unwilling\n");
+		dev_err(dev, "Failed to set DCB config in rebuild\n");
 		goto dcb_error;
 	}
 
-	/* Retrieve DCB config and ensure same as current in SW */
-	prev_cfg = kmemdup(local_dcbx_cfg, sizeof(*prev_cfg), GFP_KERNEL);
-	if (!prev_cfg)
-		goto dcb_error;
-
-	ice_init_dcb(&pf->hw, true);
-	if (pf->hw.port_info->dcbx_status == ICE_DCBX_STATUS_DIS)
-		pf->hw.port_info->is_sw_lldp = true;
-	else
-		pf->hw.port_info->is_sw_lldp = false;
-
-	if (ice_dcb_need_recfg(pf, prev_cfg, local_dcbx_cfg)) {
-		/* difference in cfg detected - disable DCB till next MIB */
-		dev_err(dev, "Set local MIB not accurate\n");
-		kfree(prev_cfg);
-		goto dcb_error;
+	if (!pf->hw.port_info->is_sw_lldp) {
+		ret = ice_cfg_lldp_mib_change(&pf->hw, true);
+		if (ret && !pf->hw.port_info->is_sw_lldp) {
+			dev_err(dev, "Failed to register for MIB changes\n");
+			goto dcb_error;
+		}
 	}
 
-	/* fetched config congruent to previous configuration */
-	kfree(prev_cfg);
-
-	/* Set the local desired config */
-	if (local_dcbx_cfg->dcbx_mode == ICE_DCBX_MODE_CEE)
-		memcpy(local_dcbx_cfg, desired_dcbx_cfg,
-		       sizeof(*local_dcbx_cfg));
-
-	ice_cfg_etsrec_defaults(pf->hw.port_info);
-	ret = ice_set_dcb_cfg(pf->hw.port_info);
-	if (ret) {
-		dev_err(dev, "Failed to set desired config\n");
-		goto dcb_error;
-	}
 	dev_info(dev, "DCB restored after reset\n");
 	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
 	if (ret) {
@@ -384,26 +356,32 @@
 		goto dcb_error;
 	}
 
+	mutex_unlock(&pf->tc_mutex);
+
 	return;
 
 dcb_error:
 	dev_err(dev, "Disabling DCB until new settings occur\n");
-	prev_cfg = kzalloc(sizeof(*prev_cfg), GFP_KERNEL);
-	if (!prev_cfg)
+	err_cfg = kzalloc(sizeof(*err_cfg), GFP_KERNEL);
+	if (!err_cfg) {
+		mutex_unlock(&pf->tc_mutex);
 		return;
+	}
 
-	prev_cfg->etscfg.willing = true;
-	prev_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
-	prev_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
-	memcpy(&prev_cfg->etsrec, &prev_cfg->etscfg, sizeof(prev_cfg->etsrec));
+	err_cfg->etscfg.willing = true;
+	err_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
+	err_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
+	memcpy(&err_cfg->etsrec, &err_cfg->etscfg, sizeof(err_cfg->etsrec));
 	/* Coverity warns the return code of ice_pf_dcb_cfg() is not checked
 	 * here as is done for other calls to that function. That check is
 	 * not necessary since this is in this function's error cleanup path.
 	 * Suppress the Coverity warning with the following comment...
 	 */
 	/* coverity[check_return] */
-	ice_pf_dcb_cfg(pf, prev_cfg, false);
-	kfree(prev_cfg);
+	ice_pf_dcb_cfg(pf, err_cfg, false);
+	kfree(err_cfg);
+
+	mutex_unlock(&pf->tc_mutex);
 }
 
 /**
@@ -434,9 +412,9 @@
 }
 
 /**
- * ice_dcb_sw_default_config - Apply a default DCB config
+ * ice_dcb_sw_dflt_cfg - Apply a default DCB config
  * @pf: PF to apply config to
- * @ets_willing: configure ets willing
+ * @ets_willing: configure ETS willing
  * @locked: was this function called with RTNL held
  */
 static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked)
@@ -599,8 +577,7 @@
 		goto dcb_init_err;
 	}
 
-	dev_info(dev,
-		 "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n",
+	dev_info(dev, "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n",
 		 pf->hw.func_caps.common_cap.maxtc);
 	if (err) {
 		struct ice_vsi *pf_vsi;
@@ -610,8 +587,8 @@
 		clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);
 		err = ice_dcb_sw_dflt_cfg(pf, true, locked);
 		if (err) {
-			dev_err(dev,
-				"Failed to set local DCB config %d\n", err);
+			dev_err(dev, "Failed to set local DCB config %d\n",
+				err);
 			err = -EIO;
 			goto dcb_init_err;
 		}
@@ -777,6 +754,8 @@
 		}
 	}
 
+	mutex_lock(&pf->tc_mutex);
+
 	/* store the old configuration */
 	tmp_dcbx_cfg = pf->hw.port_info->local_dcbx_cfg;
 
@@ -787,20 +766,20 @@
 	ret = ice_get_dcb_cfg(pf->hw.port_info);
 	if (ret) {
 		dev_err(dev, "Failed to get DCB config\n");
-		return;
+		goto out;
 	}
 
 	/* No change detected in DCBX configs */
 	if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) {
 		dev_dbg(dev, "No change detected in DCBX configuration.\n");
-		return;
+		goto out;
 	}
 
 	need_reconfig = ice_dcb_need_recfg(pf, &tmp_dcbx_cfg,
 					   &pi->local_dcbx_cfg);
 	ice_dcbnl_flush_apps(pf, &tmp_dcbx_cfg, &pi->local_dcbx_cfg);
 	if (!need_reconfig)
-		return;
+		goto out;
 
 	/* Enable DCB tagging only when more than one TC */
 	if (ice_dcb_get_num_tc(&pi->local_dcbx_cfg) > 1) {
@@ -814,7 +793,7 @@
 	pf_vsi = ice_get_main_vsi(pf);
 	if (!pf_vsi) {
 		dev_dbg(dev, "PF VSI doesn't exist\n");
-		return;
+		goto out;
 	}
 
 	rtnl_lock();
@@ -823,13 +802,15 @@
 	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
 	if (ret) {
 		dev_err(dev, "Query Port ETS failed\n");
-		rtnl_unlock();
-		return;
+		goto unlock_rtnl;
 	}
 
 	/* changes in configuration update VSI */
 	ice_pf_dcb_recfg(pf);
 
 	ice_ena_vsi(pf_vsi, true);
+unlock_rtnl:
 	rtnl_unlock();
+out:
+	mutex_unlock(&pf->tc_mutex);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index d870c1a..b61aba4 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -297,8 +297,7 @@
 		return;
 
 	*setting = (pi->local_dcbx_cfg.pfc.pfcena >> prio) & 0x1;
-	dev_dbg(ice_pf_to_dev(pf),
-		"Get PFC Config up=%d, setting=%d, pfcenable=0x%x\n",
+	dev_dbg(ice_pf_to_dev(pf), "Get PFC Config up=%d, setting=%d, pfcenable=0x%x\n",
 		prio, *setting, pi->local_dcbx_cfg.pfc.pfcena);
 }
 
@@ -418,8 +417,8 @@
 		return;
 
 	*pgid = pi->local_dcbx_cfg.etscfg.prio_table[prio];
-	dev_dbg(ice_pf_to_dev(pf),
-		"Get PG config prio=%d tc=%d\n", prio, *pgid);
+	dev_dbg(ice_pf_to_dev(pf), "Get PG config prio=%d tc=%d\n", prio,
+		*pgid);
 }
 
 /**
@@ -713,13 +712,13 @@
 		return -EINVAL;
 
 	mutex_lock(&pf->tc_mutex);
-	ret = dcb_ieee_delapp(netdev, app);
-	if (ret)
-		goto delapp_out;
-
 	old_cfg = &pf->hw.port_info->local_dcbx_cfg;
 
-	if (old_cfg->numapps == 1)
+	if (old_cfg->numapps <= 1)
+		goto delapp_out;
+
+	ret = dcb_ieee_delapp(netdev, app);
+	if (ret)
 		goto delapp_out;
 
 	new_cfg = &pf->hw.port_info->desired_dcbx_cfg;
@@ -882,8 +881,7 @@
 	sapp.protocol = app->prot_id;
 	sapp.priority = app->priority;
 	err = ice_dcbnl_delapp(vsi->netdev, &sapp);
-	dev_dbg(&vsi->back->pdev->dev,
-		"Deleting app for VSI idx=%d err=%d sel=%d proto=0x%x, prio=%d\n",
+	dev_dbg(ice_pf_to_dev(vsi->back), "Deleting app for VSI idx=%d err=%d sel=%d proto=0x%x, prio=%d\n",
 		vsi->idx, err, app->selector, app->prot_id, app->priority);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 90c6a3c..77c412a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -166,13 +166,24 @@
 ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	u8 oem_ver, oem_patch, nvm_ver_hi, nvm_ver_lo;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	u16 oem_build;
 
 	strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, ice_drv_ver, sizeof(drvinfo->version));
-	strlcpy(drvinfo->fw_version, ice_nvm_version_str(&pf->hw),
-		sizeof(drvinfo->fw_version));
+
+	/* Display NVM version (from which the firmware version can be
+	 * determined) which contains more pertinent information.
+	 */
+	ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch,
+			    &nvm_ver_hi, &nvm_ver_lo);
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "%x.%02x 0x%x %d.%d.%d", nvm_ver_hi, nvm_ver_lo,
+		 hw->nvm.eetrack, oem_ver, oem_build, oem_patch);
+
 	strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
 		sizeof(drvinfo->bus_info));
 	drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE;
@@ -363,8 +374,7 @@
 		val = rd32(hw, reg);
 		if (val == pattern)
 			continue;
-		dev_err(dev,
-			"%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n"
+		dev_err(dev, "%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n"
 			, __func__, reg, pattern, val);
 		return 1;
 	}
@@ -372,8 +382,7 @@
 	wr32(hw, reg, orig_val);
 	val = rd32(hw, reg);
 	if (val != orig_val) {
-		dev_err(dev,
-			"%s: reg restore test failed - reg 0x%08x orig 0x%08x val 0x%08x\n"
+		dev_err(dev, "%s: reg restore test failed - reg 0x%08x orig 0x%08x val 0x%08x\n"
 			, __func__, reg, orig_val, val);
 		return 1;
 	}
@@ -791,8 +800,7 @@
 		set_bit(__ICE_TESTING, pf->state);
 
 		if (ice_active_vfs(pf)) {
-			dev_warn(dev,
-				 "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n");
+			dev_warn(dev, "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n");
 			data[ICE_ETH_TEST_REG] = 1;
 			data[ICE_ETH_TEST_EEPROM] = 1;
 			data[ICE_ETH_TEST_INTR] = 1;
@@ -1047,7 +1055,7 @@
 		fec = ICE_FEC_NONE;
 		break;
 	default:
-		dev_warn(&vsi->back->pdev->dev, "Unsupported FEC mode: %d\n",
+		dev_warn(ice_pf_to_dev(vsi->back), "Unsupported FEC mode: %d\n",
 			 fecparam->fec);
 		return -EINVAL;
 	}
@@ -1200,8 +1208,7 @@
 			 * events to respond to.
 			 */
 			if (status)
-				dev_info(dev,
-					 "Failed to unreg for LLDP events\n");
+				dev_info(dev, "Failed to unreg for LLDP events\n");
 
 			/* The AQ call to stop the FW LLDP agent will generate
 			 * an error if the agent is already stopped.
@@ -1256,8 +1263,7 @@
 			/* Register for MIB change events */
 			status = ice_cfg_lldp_mib_change(&pf->hw, true);
 			if (status)
-				dev_dbg(dev,
-					"Fail to enable MIB change events\n");
+				dev_dbg(dev, "Fail to enable MIB change events\n");
 		}
 	}
 	if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) {
@@ -1710,291 +1716,13 @@
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_port_info *pi = np->vsi->port_info;
-	struct ethtool_link_ksettings cap_ksettings;
 	struct ice_link_status *link_info;
 	struct ice_vsi *vsi = np->vsi;
-	bool unrecog_phy_high = false;
-	bool unrecog_phy_low = false;
 
 	link_info = &vsi->port_info->phy.link_info;
 
-	/* Initialize supported and advertised settings based on PHY settings */
-	switch (link_info->phy_type_low) {
-	case ICE_PHY_TYPE_LOW_100BASE_TX:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100baseT_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     100baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100M_SGMII:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_1000BASE_T:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     1000baseT_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     1000baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_1G_SGMII:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     1000baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_1000BASE_SX:
-	case ICE_PHY_TYPE_LOW_1000BASE_LX:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     1000baseX_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_1000BASE_KX:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     1000baseKX_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     1000baseKX_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_2500BASE_T:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     2500baseT_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     2500baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_2500BASE_X:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     2500baseX_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_2500BASE_KX:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     2500baseX_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     2500baseX_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_5GBASE_T:
-	case ICE_PHY_TYPE_LOW_5GBASE_KR:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     5000baseT_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     5000baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_10GBASE_T:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     10000baseT_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     10000baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_10G_SFI_DA:
-	case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_10G_SFI_C2C:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     10000baseT_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_10GBASE_SR:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     10000baseSR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_10GBASE_LR:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     10000baseLR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     10000baseKR_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     10000baseKR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_25GBASE_T:
-	case ICE_PHY_TYPE_LOW_25GBASE_CR:
-	case ICE_PHY_TYPE_LOW_25GBASE_CR_S:
-	case ICE_PHY_TYPE_LOW_25GBASE_CR1:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     25000baseCR_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     25000baseCR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     25000baseCR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_25GBASE_SR:
-	case ICE_PHY_TYPE_LOW_25GBASE_LR:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     25000baseSR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_25GBASE_KR:
-	case ICE_PHY_TYPE_LOW_25GBASE_KR1:
-	case ICE_PHY_TYPE_LOW_25GBASE_KR_S:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     25000baseKR_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     25000baseKR_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_40GBASE_CR4:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     40000baseCR4_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     40000baseCR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_40G_XLAUI:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     40000baseCR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_40GBASE_SR4:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     40000baseSR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_40GBASE_LR4:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     40000baseLR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_40GBASE_KR4:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     40000baseKR4_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     40000baseKR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_50GBASE_CR2:
-	case ICE_PHY_TYPE_LOW_50GBASE_CP:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     50000baseCR2_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     50000baseCR2_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_50G_LAUI2:
-	case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_50G_AUI2:
-	case ICE_PHY_TYPE_LOW_50GBASE_SR:
-	case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_50G_AUI1:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     50000baseCR2_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_50GBASE_KR2:
-	case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     50000baseKR2_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     50000baseKR2_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_50GBASE_SR2:
-	case ICE_PHY_TYPE_LOW_50GBASE_LR2:
-	case ICE_PHY_TYPE_LOW_50GBASE_FR:
-	case ICE_PHY_TYPE_LOW_50GBASE_LR:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     50000baseSR2_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100GBASE_CR4:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseCR4_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     100000baseCR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_100G_CAUI4:
-	case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
-	case ICE_PHY_TYPE_LOW_100G_AUI4:
-	case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseCR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100GBASE_CP2:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseCR4_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     100000baseCR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100GBASE_SR4:
-	case ICE_PHY_TYPE_LOW_100GBASE_SR2:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseSR4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100GBASE_LR4:
-	case ICE_PHY_TYPE_LOW_100GBASE_DR:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseLR4_ER4_Full);
-		break;
-	case ICE_PHY_TYPE_LOW_100GBASE_KR4:
-	case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseKR4_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     100000baseKR4_Full);
-		break;
-	default:
-		unrecog_phy_low = true;
-	}
-
-	switch (link_info->phy_type_high) {
-	case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
-		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseKR4_Full);
-		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
-		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     100000baseKR4_Full);
-		break;
-	case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
-	case ICE_PHY_TYPE_HIGH_100G_CAUI2:
-	case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
-	case ICE_PHY_TYPE_HIGH_100G_AUI2:
-		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     100000baseCR4_Full);
-		break;
-	default:
-		unrecog_phy_high = true;
-	}
-
-	if (unrecog_phy_low && unrecog_phy_high) {
-		/* if we got here and link is up something bad is afoot */
-		netdev_info(netdev,
-			    "WARNING: Unrecognized PHY_Low (0x%llx).\n",
-			    (u64)link_info->phy_type_low);
-		netdev_info(netdev,
-			    "WARNING: Unrecognized PHY_High (0x%llx).\n",
-			    (u64)link_info->phy_type_high);
-	}
-
-	/* Now that we've worked out everything that could be supported by the
-	 * current PHY type, get what is supported by the NVM and intersect
-	 * them to get what is truly supported
-	 */
-	memset(&cap_ksettings, 0, sizeof(cap_ksettings));
-	ice_phy_type_to_ethtool(netdev, &cap_ksettings);
-	ethtool_intersect_link_masks(ks, &cap_ksettings);
+	/* Get supported and advertised settings from PHY ability with media */
+	ice_phy_type_to_ethtool(netdev, ks);
 
 	switch (link_info->link_speed) {
 	case ICE_AQ_LINK_SPEED_100GB:
@@ -2028,8 +1756,7 @@
 		ks->base.speed = SPEED_100;
 		break;
 	default:
-		netdev_info(netdev,
-			    "WARNING: Unrecognized link_speed (0x%x).\n",
+		netdev_info(netdev, "WARNING: Unrecognized link_speed (0x%x).\n",
 			    link_info->link_speed);
 		break;
 	}
@@ -2845,13 +2572,11 @@
 
 	new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE);
 	if (new_tx_cnt != ring->tx_pending)
-		netdev_info(netdev,
-			    "Requested Tx descriptor count rounded up to %d\n",
+		netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n",
 			    new_tx_cnt);
 	new_rx_cnt = ALIGN(ring->rx_pending, ICE_REQ_DESC_MULTIPLE);
 	if (new_rx_cnt != ring->rx_pending)
-		netdev_info(netdev,
-			    "Requested Rx descriptor count rounded up to %d\n",
+		netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n",
 			    new_rx_cnt);
 
 	/* if nothing to do return success */
@@ -3211,13 +2936,6 @@
 	else
 		return -EINVAL;
 
-	/* Tell the OS link is going down, the link will go back up when fw
-	 * says it is ready asynchronously
-	 */
-	ice_print_link_msg(vsi, false);
-	netif_carrier_off(netdev);
-	netif_tx_stop_all_queues(netdev);
-
 	/* Set the FC mode and only restart AN if link is up */
 	status = ice_set_fc(pi, &aq_failures, link_up);
 
@@ -3718,8 +3436,7 @@
 		if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL ||
 		    (ec->rx_coalesce_usecs_high &&
 		     ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) {
-			netdev_info(vsi->netdev,
-				    "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n",
+			netdev_info(vsi->netdev, "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n",
 				    c_type_str, pf->hw.intrl_gran,
 				    ICE_MAX_INTRL);
 			return -EINVAL;
@@ -3737,8 +3454,7 @@
 		break;
 	case ICE_TX_CONTAINER:
 		if (ec->tx_coalesce_usecs_high) {
-			netdev_info(vsi->netdev,
-				    "setting %s-usecs-high is not supported\n",
+			netdev_info(vsi->netdev, "setting %s-usecs-high is not supported\n",
 				    c_type_str);
 			return -EINVAL;
 		}
@@ -3755,35 +3471,24 @@
 
 	itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC;
 	if (coalesce_usecs != itr_setting && use_adaptive_coalesce) {
-		netdev_info(vsi->netdev,
-			    "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n",
+		netdev_info(vsi->netdev, "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n",
 			    c_type_str, c_type_str);
 		return -EINVAL;
 	}
 
 	if (coalesce_usecs > ICE_ITR_MAX) {
-		netdev_info(vsi->netdev,
-			    "Invalid value, %s-usecs range is 0-%d\n",
+		netdev_info(vsi->netdev, "Invalid value, %s-usecs range is 0-%d\n",
 			    c_type_str, ICE_ITR_MAX);
 		return -EINVAL;
 	}
 
-	/* hardware only supports an ITR granularity of 2us */
-	if (coalesce_usecs % 2 != 0) {
-		netdev_info(vsi->netdev,
-			    "Invalid value, %s-usecs must be even\n",
-			    c_type_str);
-		return -EINVAL;
-	}
-
 	if (use_adaptive_coalesce) {
 		rc->itr_setting |= ICE_ITR_DYNAMIC;
 	} else {
-		/* store user facing value how it was set */
+		/* save the user set usecs */
 		rc->itr_setting = coalesce_usecs;
-		/* set to static and convert to value HW understands */
-		rc->target_itr =
-			ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting));
+		/* device ITR granularity is in 2 usec increments */
+		rc->target_itr = ITR_REG_ALIGN(rc->itr_setting);
 	}
 
 	return 0;
@@ -3877,6 +3582,30 @@
 }
 
 /**
+ * ice_print_if_odd_usecs - print message if user tries to set odd [tx|rx]-usecs
+ * @netdev: netdev used for print
+ * @itr_setting: previous user setting
+ * @use_adaptive_coalesce: if adaptive coalesce is enabled or being enabled
+ * @coalesce_usecs: requested value of [tx|rx]-usecs
+ * @c_type_str: either "rx" or "tx" to match user set field of [tx|rx]-usecs
+ */
+static void
+ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting,
+		       u32 use_adaptive_coalesce, u32 coalesce_usecs,
+		       const char *c_type_str)
+{
+	if (use_adaptive_coalesce)
+		return;
+
+	itr_setting = ITR_TO_REG(itr_setting);
+
+	if (itr_setting != coalesce_usecs && (coalesce_usecs % 2))
+		netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n",
+			    c_type_str, coalesce_usecs, c_type_str,
+			    ITR_REG_ALIGN(coalesce_usecs));
+}
+
+/**
  * __ice_set_coalesce - set ITR/INTRL values for the device
  * @netdev: pointer to the netdev associated with this query
  * @ec: ethtool structure to fill with driver's coalesce settings
@@ -3896,8 +3625,19 @@
 		return -EINVAL;
 
 	if (q_num < 0) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[0];
 		int v_idx;
 
+		if (q_vector) {
+			ice_print_if_odd_usecs(netdev, q_vector->rx.itr_setting,
+					       ec->use_adaptive_rx_coalesce,
+					       ec->rx_coalesce_usecs, "rx");
+
+			ice_print_if_odd_usecs(netdev, q_vector->tx.itr_setting,
+					       ec->use_adaptive_tx_coalesce,
+					       ec->tx_coalesce_usecs, "tx");
+		}
+
 		ice_for_each_q_vector(vsi, v_idx) {
 			/* In some cases if DCB is configured the num_[rx|tx]q
 			 * can be less than vsi->num_q_vectors. This check
@@ -4012,8 +3752,7 @@
 		}
 		break;
 	default:
-		netdev_warn(netdev,
-			    "SFF Module Type not recognized.\n");
+		netdev_warn(netdev, "SFF Module Type not recognized.\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -4081,11 +3820,11 @@
 static const struct ethtool_ops ice_ethtool_ops = {
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
-	.get_drvinfo            = ice_get_drvinfo,
-	.get_regs_len           = ice_get_regs_len,
-	.get_regs               = ice_get_regs,
-	.get_msglevel           = ice_get_msglevel,
-	.set_msglevel           = ice_set_msglevel,
+	.get_drvinfo		= ice_get_drvinfo,
+	.get_regs_len		= ice_get_regs_len,
+	.get_regs		= ice_get_regs,
+	.get_msglevel		= ice_get_msglevel,
+	.set_msglevel		= ice_set_msglevel,
 	.self_test		= ice_self_test,
 	.get_link		= ethtool_op_get_link,
 	.get_eeprom_len		= ice_get_eeprom_len,
@@ -4112,8 +3851,8 @@
 	.get_channels		= ice_get_channels,
 	.set_channels		= ice_set_channels,
 	.get_ts_info		= ethtool_op_get_ts_info,
-	.get_per_queue_coalesce = ice_get_per_q_coalesce,
-	.set_per_queue_coalesce = ice_set_per_q_coalesce,
+	.get_per_queue_coalesce	= ice_get_per_q_coalesce,
+	.set_per_queue_coalesce	= ice_set_per_q_coalesce,
 	.get_fecparam		= ice_get_fecparam,
 	.set_fecparam		= ice_set_fecparam,
 	.get_module_info	= ice_get_module_info,
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index f2cabab..6db3d04 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -267,8 +267,14 @@
 #define GLNVM_GENS_SR_SIZE_S			5
 #define GLNVM_GENS_SR_SIZE_M			ICE_M(0x7, 5)
 #define GLNVM_ULD				0x000B6008
+#define GLNVM_ULD_PCIER_DONE_M			BIT(0)
+#define GLNVM_ULD_PCIER_DONE_1_M		BIT(1)
 #define GLNVM_ULD_CORER_DONE_M			BIT(3)
 #define GLNVM_ULD_GLOBR_DONE_M			BIT(4)
+#define GLNVM_ULD_POR_DONE_M			BIT(5)
+#define GLNVM_ULD_POR_DONE_1_M			BIT(8)
+#define GLNVM_ULD_PCIER_DONE_2_M		BIT(9)
+#define GLNVM_ULD_PE_DONE_M			BIT(10)
 #define GLPCI_CNF2				0x000BE004
 #define GLPCI_CNF2_CACHELINE_SIZE_M		BIT(1)
 #define PF_FUNC_RID				0x0009E880
@@ -331,7 +337,6 @@
 #define GLV_TEPC(_VSI)				(0x00312000 + ((_VSI) * 4))
 #define GLV_UPRCL(_i)				(0x003B2000 + ((_i) * 8))
 #define GLV_UPTCL(_i)				(0x0030A000 + ((_i) * 8))
-#define PF_VT_PFALLOC_HIF			0x0009DD80
 #define VSIQF_HKEY_MAX_INDEX			12
 #define VSIQF_HLUT_MAX_INDEX			15
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 1874c9f..d974e2f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -117,8 +117,7 @@
 		vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC;
 		break;
 	default:
-		dev_dbg(&vsi->back->pdev->dev,
-			"Not setting number of Tx/Rx descriptors for VSI type %d\n",
+		dev_dbg(ice_pf_to_dev(vsi->back), "Not setting number of Tx/Rx descriptors for VSI type %d\n",
 			vsi->type);
 		break;
 	}
@@ -724,7 +723,7 @@
 	vsi->num_txq = tx_count;
 
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
-		dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
+		dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
 		/* since there is a chance that num_rxq could have been changed
 		 * in the above for loop, make num_txq equal to num_rxq.
 		 */
@@ -929,8 +928,7 @@
 	vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors,
 				       vsi->idx);
 	if (vsi->base_vector < 0) {
-		dev_err(dev,
-			"Failed to get tracking for %d vectors for VSI %d, err=%d\n",
+		dev_err(dev, "Failed to get tracking for %d vectors for VSI %d, err=%d\n",
 			num_q_vectors, vsi->vsi_num, vsi->base_vector);
 		return -ENOENT;
 	}
@@ -1232,8 +1230,9 @@
  *
  * Returns 0 on success or ENOMEM on failure.
  */
-int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
-			const u8 *macaddr)
+int
+ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
+		    const u8 *macaddr)
 {
 	struct ice_fltr_list_entry *tmp;
 	struct ice_pf *pf = vsi->back;
@@ -1392,12 +1391,10 @@
 
 	status = ice_remove_vlan(&pf->hw, &tmp_add_list);
 	if (status == ICE_ERR_DOES_NOT_EXIST) {
-		dev_dbg(dev,
-			"Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n",
+		dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n",
 			vid, vsi->vsi_num, status);
 	} else if (status) {
-		dev_err(dev,
-			"Error removing VLAN %d on vsi %i error: %d\n",
+		dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n",
 			vid, vsi->vsi_num, status);
 		err = -EIO;
 	}
@@ -1453,8 +1450,7 @@
 
 		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
 		if (err) {
-			dev_err(&vsi->back->pdev->dev,
-				"ice_setup_rx_ctx failed for RxQ %d, err %d\n",
+			dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
 				i, err);
 			return err;
 		}
@@ -1623,7 +1619,7 @@
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(&vsi->back->pdev->dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %d\n",
 			status, hw->adminq.sq_last_status);
 		ret = -EIO;
 		goto out;
@@ -1669,7 +1665,7 @@
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(&vsi->back->pdev->dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n",
 			ena, status, hw->adminq.sq_last_status);
 		ret = -EIO;
 		goto out;
@@ -1834,8 +1830,7 @@
 		struct ice_q_vector *q_vector = vsi->q_vectors[i];
 
 		if (!q_vector) {
-			dev_err(&vsi->back->pdev->dev,
-				"Failed to set reg_idx on q_vector %d VSI %d\n",
+			dev_err(ice_pf_to_dev(vsi->back), "Failed to set reg_idx on q_vector %d VSI %d\n",
 				i, vsi->vsi_num);
 			goto clear_reg_idx;
 		}
@@ -1898,8 +1893,7 @@
 		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
 
 	if (status)
-		dev_err(dev,
-			"Failure Adding or Removing Ethertype on VSI %i error: %d\n",
+		dev_err(dev, "Failure Adding or Removing Ethertype on VSI %i error: %d\n",
 			vsi->vsi_num, status);
 
 	ice_free_fltr_list(dev, &tmp_add_list);
@@ -2384,8 +2378,7 @@
 		return -EINVAL;
 
 	if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) {
-		dev_err(ice_pf_to_dev(pf),
-			"param err: needed=%d, num_entries = %d id=0x%04x\n",
+		dev_err(ice_pf_to_dev(pf), "param err: needed=%d, num_entries = %d id=0x%04x\n",
 			needed, res->num_entries, id);
 		return -EINVAL;
 	}
@@ -2686,7 +2679,6 @@
 	ice_vsi_put_qs(vsi);
 	ice_vsi_clear_rings(vsi);
 	ice_vsi_free_arrays(vsi);
-	ice_dev_onetime_setup(&pf->hw);
 	if (vsi->type == ICE_VSI_VF)
 		ice_vsi_set_num_qs(vsi, vf->vf_id);
 	else
@@ -2765,8 +2757,7 @@
 	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 				 max_txqs);
 	if (status) {
-		dev_err(ice_pf_to_dev(pf),
-			"VSI %d failed lan queue config, error %d\n",
+		dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n",
 			vsi->vsi_num, status);
 		if (init_vsi) {
 			ret = -EIO;
@@ -2834,8 +2825,8 @@
 int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
-	struct ice_vsi_ctx *ctx;
 	struct ice_pf *pf = vsi->back;
+	struct ice_vsi_ctx *ctx;
 	enum ice_status status;
 	struct device *dev;
 	int i, ret = 0;
@@ -2892,25 +2883,6 @@
 #endif /* CONFIG_DCB */
 
 /**
- * ice_nvm_version_str - format the NVM version strings
- * @hw: ptr to the hardware info
- */
-char *ice_nvm_version_str(struct ice_hw *hw)
-{
-	u8 oem_ver, oem_patch, ver_hi, ver_lo;
-	static char buf[ICE_NVM_VER_LEN];
-	u16 oem_build;
-
-	ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, &ver_hi,
-			    &ver_lo);
-
-	snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d", ver_hi, ver_lo,
-		 hw->nvm.eetrack, oem_ver, oem_build, oem_patch);
-
-	return buf;
-}
-
-/**
  * ice_update_ring_stats - Update ring statistics
  * @ring: ring to update
  * @cont: used to increment per-vector counters
@@ -2981,7 +2953,7 @@
 		status = ice_remove_mac(&vsi->back->hw, &tmp_add_list);
 
 cfg_mac_fltr_exit:
-	ice_free_fltr_list(&vsi->back->pdev->dev, &tmp_add_list);
+	ice_free_fltr_list(ice_pf_to_dev(vsi->back), &tmp_add_list);
 	return status;
 }
 
@@ -3043,16 +3015,14 @@
 
 	/* another VSI is already the default VSI for this switch */
 	if (ice_is_dflt_vsi_in_use(sw)) {
-		dev_err(dev,
-			"Default forwarding VSI %d already in use, disable it and try again\n",
+		dev_err(dev, "Default forwarding VSI %d already in use, disable it and try again\n",
 			sw->dflt_vsi->vsi_num);
 		return -EEXIST;
 	}
 
 	status = ice_cfg_dflt_vsi(&vsi->back->hw, vsi->idx, true, ICE_FLTR_RX);
 	if (status) {
-		dev_err(dev,
-			"Failed to set VSI %d as the default forwarding VSI, error %d\n",
+		dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %d\n",
 			vsi->vsi_num, status);
 		return -EIO;
 	}
@@ -3091,8 +3061,7 @@
 	status = ice_cfg_dflt_vsi(&dflt_vsi->back->hw, dflt_vsi->idx, false,
 				  ICE_FLTR_RX);
 	if (status) {
-		dev_err(dev,
-			"Failed to clear the default forwarding VSI %d, error %d\n",
+		dev_err(dev, "Failed to clear the default forwarding VSI %d, error %d\n",
 			dflt_vsi->vsi_num, status);
 		return -EIO;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 68fd0d4..e2c0dad 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -97,8 +97,6 @@
 
 u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran);
 
-char *ice_nvm_version_str(struct ice_hw *hw);
-
 enum ice_status
 ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 5ae67160..5ef2805 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -162,8 +162,7 @@
 	 * had an error
 	 */
 	if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
-		dev_err(ice_pf_to_dev(pf),
-			"Could not add MAC filters error %d. Unregistering device\n",
+		dev_err(ice_pf_to_dev(pf), "Could not add MAC filters error %d. Unregistering device\n",
 			status);
 		unregister_netdev(vsi->netdev);
 		free_netdev(vsi->netdev);
@@ -269,7 +268,7 @@
  */
 static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 {
-	struct device *dev = &vsi->back->pdev->dev;
+	struct device *dev = ice_pf_to_dev(vsi->back);
 	struct net_device *netdev = vsi->netdev;
 	bool promisc_forced_on = false;
 	struct ice_pf *pf = vsi->back;
@@ -335,8 +334,7 @@
 		    !test_and_set_bit(__ICE_FLTR_OVERFLOW_PROMISC,
 				      vsi->state)) {
 			promisc_forced_on = true;
-			netdev_warn(netdev,
-				    "Reached MAC filter limit, forcing promisc mode on VSI %d\n",
+			netdev_warn(netdev, "Reached MAC filter limit, forcing promisc mode on VSI %d\n",
 				    vsi->vsi_num);
 		} else {
 			err = -EIO;
@@ -382,8 +380,7 @@
 			if (!ice_is_dflt_vsi_in_use(pf->first_sw)) {
 				err = ice_set_dflt_vsi(pf->first_sw, vsi);
 				if (err && err != -EEXIST) {
-					netdev_err(netdev,
-						   "Error %d setting default VSI %i Rx rule\n",
+					netdev_err(netdev, "Error %d setting default VSI %i Rx rule\n",
 						   err, vsi->vsi_num);
 					vsi->current_netdev_flags &=
 						~IFF_PROMISC;
@@ -395,8 +392,7 @@
 			if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) {
 				err = ice_clear_dflt_vsi(pf->first_sw);
 				if (err) {
-					netdev_err(netdev,
-						   "Error %d clearing default VSI %i Rx rule\n",
+					netdev_err(netdev, "Error %d clearing default VSI %i Rx rule\n",
 						   err, vsi->vsi_num);
 					vsi->current_netdev_flags |=
 						IFF_PROMISC;
@@ -752,7 +748,7 @@
 	kfree(caps);
 
 done:
-	netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n",
+	netdev_info(vsi->netdev, "NIC Link is up %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n",
 		    speed, fec_req, fec, an, fc);
 	ice_print_topo_conflict(vsi);
 }
@@ -815,8 +811,7 @@
 	 */
 	result = ice_update_link_info(pi);
 	if (result)
-		dev_dbg(dev,
-			"Failed to update link status and re-enable link events for port %d\n",
+		dev_dbg(dev, "Failed to update link status and re-enable link events for port %d\n",
 			pi->lport);
 
 	/* if the old link up/down and speed is the same as the new */
@@ -834,13 +829,13 @@
 
 		result = ice_aq_set_link_restart_an(pi, false, NULL);
 		if (result) {
-			dev_dbg(dev,
-				"Failed to set link down, VSI %d error %d\n",
+			dev_dbg(dev, "Failed to set link down, VSI %d error %d\n",
 				vsi->vsi_num, result);
 			return result;
 		}
 	}
 
+	ice_dcb_rebuild(pf);
 	ice_vsi_link_event(vsi, link_up);
 	ice_print_link_msg(vsi, link_up);
 
@@ -892,15 +887,13 @@
 		       ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL));
 
 	if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) {
-		dev_dbg(ice_hw_to_dev(pi->hw),
-			"Failed to set link event mask for port %d\n",
+		dev_dbg(ice_hw_to_dev(pi->hw), "Failed to set link event mask for port %d\n",
 			pi->lport);
 		return -EIO;
 	}
 
 	if (ice_aq_get_link_info(pi, true, NULL, NULL)) {
-		dev_dbg(ice_hw_to_dev(pi->hw),
-			"Failed to enable link events for port %d\n",
+		dev_dbg(ice_hw_to_dev(pi->hw), "Failed to enable link events for port %d\n",
 			pi->lport);
 		return -EIO;
 	}
@@ -929,8 +922,8 @@
 				!!(link_data->link_info & ICE_AQ_LINK_UP),
 				le16_to_cpu(link_data->link_speed));
 	if (status)
-		dev_dbg(ice_pf_to_dev(pf),
-			"Could not process link event, error %d\n", status);
+		dev_dbg(ice_pf_to_dev(pf), "Could not process link event, error %d\n",
+			status);
 
 	return status;
 }
@@ -979,13 +972,11 @@
 			dev_dbg(dev, "%s Receive Queue VF Error detected\n",
 				qtype);
 		if (val & PF_FW_ARQLEN_ARQOVFL_M) {
-			dev_dbg(dev,
-				"%s Receive Queue Overflow Error detected\n",
+			dev_dbg(dev, "%s Receive Queue Overflow Error detected\n",
 				qtype);
 		}
 		if (val & PF_FW_ARQLEN_ARQCRIT_M)
-			dev_dbg(dev,
-				"%s Receive Queue Critical Error detected\n",
+			dev_dbg(dev, "%s Receive Queue Critical Error detected\n",
 				qtype);
 		val &= ~(PF_FW_ARQLEN_ARQVFE_M | PF_FW_ARQLEN_ARQOVFL_M |
 			 PF_FW_ARQLEN_ARQCRIT_M);
@@ -998,8 +989,8 @@
 		   PF_FW_ATQLEN_ATQCRIT_M)) {
 		oldval = val;
 		if (val & PF_FW_ATQLEN_ATQVFE_M)
-			dev_dbg(dev,
-				"%s Send Queue VF Error detected\n", qtype);
+			dev_dbg(dev, "%s Send Queue VF Error detected\n",
+				qtype);
 		if (val & PF_FW_ATQLEN_ATQOVFL_M) {
 			dev_dbg(dev, "%s Send Queue Overflow Error detected\n",
 				qtype);
@@ -1048,8 +1039,7 @@
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
 			break;
 		default:
-			dev_dbg(dev,
-				"%s Receive Queue unknown event 0x%04x ignored\n",
+			dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n",
 				qtype, opcode);
 			break;
 		}
@@ -1238,7 +1228,7 @@
 		u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >>
 				GL_MDET_TX_TCLAN_QNUM_S);
 
-		if (netif_msg_rx_err(pf))
+		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
 		wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff);
@@ -1335,8 +1325,7 @@
 			vf->num_mdd_events++;
 			if (vf->num_mdd_events &&
 			    vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD)
-				dev_info(dev,
-					 "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n",
+				dev_info(dev, "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n",
 					 i, vf->num_mdd_events);
 		}
 	}
@@ -1367,7 +1356,7 @@
 	if (vsi->type != ICE_VSI_PF)
 		return 0;
 
-	dev = &vsi->back->pdev->dev;
+	dev = ice_pf_to_dev(vsi->back);
 
 	pi = vsi->port_info;
 
@@ -1378,8 +1367,7 @@
 	retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
 				      NULL);
 	if (retcode) {
-		dev_err(dev,
-			"Failed to get phy capabilities, VSI %d error %d\n",
+		dev_err(dev, "Failed to get phy capabilities, VSI %d error %d\n",
 			vsi->vsi_num, retcode);
 		retcode = -EIO;
 		goto out;
@@ -1649,8 +1637,8 @@
 		err = devm_request_irq(dev, irq_num, vsi->irq_handler, 0,
 				       q_vector->name, q_vector);
 		if (err) {
-			netdev_err(vsi->netdev,
-				   "MSIX request_irq failed, error: %d\n", err);
+			netdev_err(vsi->netdev, "MSIX request_irq failed, error: %d\n",
+				   err);
 			goto free_q_irqs;
 		}
 
@@ -1685,7 +1673,7 @@
  */
 static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 {
-	struct device *dev = &vsi->back->pdev->dev;
+	struct device *dev = ice_pf_to_dev(vsi->back);
 	int i;
 
 	for (i = 0; i < vsi->num_xdp_txq; i++) {
@@ -2664,14 +2652,12 @@
 	clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
 	if (func_caps->common_cap.dcb)
 		set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
-#ifdef CONFIG_PCI_IOV
 	clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
 	if (func_caps->common_cap.sr_iov_1_1) {
 		set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
 		pf->num_vfs_supported = min_t(int, func_caps->num_allocd_vfs,
 					      ICE_MAX_VF_COUNT);
 	}
-#endif /* CONFIG_PCI_IOV */
 	clear_bit(ICE_FLAG_RSS_ENA, pf->flags);
 	if (func_caps->common_cap.rss_table_size)
 		set_bit(ICE_FLAG_RSS_ENA, pf->flags);
@@ -2764,8 +2750,7 @@
 	}
 
 	if (v_actual < v_budget) {
-		dev_warn(dev,
-			 "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
+		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
 			 v_budget, v_actual);
 /* 2 vectors for LAN (traffic + OICR) */
 #define ICE_MIN_LAN_VECS 2
@@ -2787,8 +2772,7 @@
 	goto exit_err;
 
 no_hw_vecs_left_err:
-	dev_err(dev,
-		"not enough device MSI-X vectors. requested = %d, available = %d\n",
+	dev_err(dev, "not enough device MSI-X vectors. requested = %d, available = %d\n",
 		needed, v_left);
 	err = -ERANGE;
 exit_err:
@@ -2921,16 +2905,14 @@
 		    !memcmp(hw->pkg_name, hw->active_pkg_name,
 			    sizeof(hw->pkg_name))) {
 			if (hw->pkg_dwnld_status == ICE_AQ_RC_EEXIST)
-				dev_info(dev,
-					 "DDP package already present on device: %s version %d.%d.%d.%d\n",
+				dev_info(dev, "DDP package already present on device: %s version %d.%d.%d.%d\n",
 					 hw->active_pkg_name,
 					 hw->active_pkg_ver.major,
 					 hw->active_pkg_ver.minor,
 					 hw->active_pkg_ver.update,
 					 hw->active_pkg_ver.draft);
 			else
-				dev_info(dev,
-					 "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n",
+				dev_info(dev, "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n",
 					 hw->active_pkg_name,
 					 hw->active_pkg_ver.major,
 					 hw->active_pkg_ver.minor,
@@ -2938,8 +2920,7 @@
 					 hw->active_pkg_ver.draft);
 		} else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ ||
 			   hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) {
-			dev_err(dev,
-				"The device has a DDP package that is not supported by the driver.  The device has package '%s' version %d.%d.x.x.  The driver requires version %d.%d.x.x.  Entering Safe Mode.\n",
+			dev_err(dev, "The device has a DDP package that is not supported by the driver.  The device has package '%s' version %d.%d.x.x.  The driver requires version %d.%d.x.x.  Entering Safe Mode.\n",
 				hw->active_pkg_name,
 				hw->active_pkg_ver.major,
 				hw->active_pkg_ver.minor,
@@ -2947,8 +2928,7 @@
 			*status = ICE_ERR_NOT_SUPPORTED;
 		} else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
 			   hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) {
-			dev_info(dev,
-				 "The driver could not load the DDP package file because a compatible DDP package is already present on the device.  The device has package '%s' version %d.%d.%d.%d.  The package file found by the driver: '%s' version %d.%d.%d.%d.\n",
+			dev_info(dev, "The driver could not load the DDP package file because a compatible DDP package is already present on the device.  The device has package '%s' version %d.%d.%d.%d.  The package file found by the driver: '%s' version %d.%d.%d.%d.\n",
 				 hw->active_pkg_name,
 				 hw->active_pkg_ver.major,
 				 hw->active_pkg_ver.minor,
@@ -2960,54 +2940,46 @@
 				 hw->pkg_ver.update,
 				 hw->pkg_ver.draft);
 		} else {
-			dev_err(dev,
-				"An unknown error occurred when loading the DDP package, please reboot the system.  If the problem persists, update the NVM.  Entering Safe Mode.\n");
+			dev_err(dev, "An unknown error occurred when loading the DDP package, please reboot the system.  If the problem persists, update the NVM.  Entering Safe Mode.\n");
 			*status = ICE_ERR_NOT_SUPPORTED;
 		}
 		break;
 	case ICE_ERR_BUF_TOO_SHORT:
 		/* fall-through */
 	case ICE_ERR_CFG:
-		dev_err(dev,
-			"The DDP package file is invalid. Entering Safe Mode.\n");
+		dev_err(dev, "The DDP package file is invalid. Entering Safe Mode.\n");
 		break;
 	case ICE_ERR_NOT_SUPPORTED:
 		/* Package File version not supported */
 		if (hw->pkg_ver.major > ICE_PKG_SUPP_VER_MAJ ||
 		    (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
 		     hw->pkg_ver.minor > ICE_PKG_SUPP_VER_MNR))
-			dev_err(dev,
-				"The DDP package file version is higher than the driver supports.  Please use an updated driver.  Entering Safe Mode.\n");
+			dev_err(dev, "The DDP package file version is higher than the driver supports.  Please use an updated driver.  Entering Safe Mode.\n");
 		else if (hw->pkg_ver.major < ICE_PKG_SUPP_VER_MAJ ||
 			 (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ &&
 			  hw->pkg_ver.minor < ICE_PKG_SUPP_VER_MNR))
-			dev_err(dev,
-				"The DDP package file version is lower than the driver supports.  The driver requires version %d.%d.x.x.  Please use an updated DDP Package file.  Entering Safe Mode.\n",
+			dev_err(dev, "The DDP package file version is lower than the driver supports.  The driver requires version %d.%d.x.x.  Please use an updated DDP Package file.  Entering Safe Mode.\n",
 				ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR);
 		break;
 	case ICE_ERR_AQ_ERROR:
 		switch (hw->pkg_dwnld_status) {
 		case ICE_AQ_RC_ENOSEC:
 		case ICE_AQ_RC_EBADSIG:
-			dev_err(dev,
-				"The DDP package could not be loaded because its signature is not valid.  Please use a valid DDP Package.  Entering Safe Mode.\n");
+			dev_err(dev, "The DDP package could not be loaded because its signature is not valid.  Please use a valid DDP Package.  Entering Safe Mode.\n");
 			return;
 		case ICE_AQ_RC_ESVN:
-			dev_err(dev,
-				"The DDP Package could not be loaded because its security revision is too low.  Please use an updated DDP Package.  Entering Safe Mode.\n");
+			dev_err(dev, "The DDP Package could not be loaded because its security revision is too low.  Please use an updated DDP Package.  Entering Safe Mode.\n");
 			return;
 		case ICE_AQ_RC_EBADMAN:
 		case ICE_AQ_RC_EBADBUF:
-			dev_err(dev,
-				"An error occurred on the device while loading the DDP package.  The device will be reset.\n");
+			dev_err(dev, "An error occurred on the device while loading the DDP package.  The device will be reset.\n");
 			return;
 		default:
 			break;
 		}
 		/* fall-through */
 	default:
-		dev_err(dev,
-			"An unknown error (%d) occurred when loading the DDP package.  Entering Safe Mode.\n",
+		dev_err(dev, "An unknown error (%d) occurred when loading the DDP package.  Entering Safe Mode.\n",
 			*status);
 		break;
 	}
@@ -3038,8 +3010,7 @@
 		status = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size);
 		ice_log_pkg_init(hw, &status);
 	} else {
-		dev_err(dev,
-			"The DDP package file failed to load. Entering Safe Mode.\n");
+		dev_err(dev, "The DDP package file failed to load. Entering Safe Mode.\n");
 	}
 
 	if (status) {
@@ -3065,8 +3036,7 @@
 static void ice_verify_cacheline_size(struct ice_pf *pf)
 {
 	if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M)
-		dev_warn(ice_pf_to_dev(pf),
-			 "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n",
+		dev_warn(ice_pf_to_dev(pf), "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n",
 			 ICE_CACHE_LINE_BYTES);
 }
 
@@ -3159,8 +3129,7 @@
 dflt_pkg_load:
 	err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
 	if (err) {
-		dev_err(dev,
-			"The DDP package file was not found or could not be read. Entering Safe Mode\n");
+		dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
 		return;
 	}
 
@@ -3184,7 +3153,9 @@
 	struct ice_hw *hw;
 	int err;
 
-	/* this driver uses devres, see Documentation/driver-api/driver-model/devres.rst */
+	/* this driver uses devres, see
+	 * Documentation/driver-api/driver-model/devres.rst
+	 */
 	err = pcim_enable_device(pdev);
 	if (err)
 		return err;
@@ -3245,11 +3216,6 @@
 		goto err_exit_unroll;
 	}
 
-	dev_info(dev, "firmware %d.%d.%d api %d.%d.%d nvm %s build 0x%08x\n",
-		 hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch,
-		 hw->api_maj_ver, hw->api_min_ver, hw->api_patch,
-		 ice_nvm_version_str(hw), hw->fw_build);
-
 	ice_request_fw(pf);
 
 	/* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be
@@ -3257,8 +3223,7 @@
 	 * true
 	 */
 	if (ice_is_safe_mode(pf)) {
-		dev_err(dev,
-			"Package download failed. Advanced features disabled - Device now in Safe Mode\n");
+		dev_err(dev, "Package download failed. Advanced features disabled - Device now in Safe Mode\n");
 		/* we already got function/device capabilities but these don't
 		 * reflect what the driver needs to do in safe mode. Instead of
 		 * adding conditional logic everywhere to ignore these
@@ -3335,8 +3300,7 @@
 	/* tell the firmware we are up */
 	err = ice_send_version(pf);
 	if (err) {
-		dev_err(dev,
-			"probe failed sending driver version %s. error: %d\n",
+		dev_err(dev, "probe failed sending driver version %s. error: %d\n",
 			ice_drv_ver, err);
 		goto err_alloc_sw_unroll;
 	}
@@ -3477,8 +3441,7 @@
 
 	err = pci_enable_device_mem(pdev);
 	if (err) {
-		dev_err(&pdev->dev,
-			"Cannot re-enable PCI device after reset, error %d\n",
+		dev_err(&pdev->dev, "Cannot re-enable PCI device after reset, error %d\n",
 			err);
 		result = PCI_ERS_RESULT_DISCONNECT;
 	} else {
@@ -3497,8 +3460,7 @@
 
 	err = pci_cleanup_aer_uncorrect_error_status(pdev);
 	if (err)
-		dev_dbg(&pdev->dev,
-			"pci_cleanup_aer_uncorrect_error_status failed, error %d\n",
+		dev_dbg(&pdev->dev, "pci_cleanup_aer_uncorrect_error_status failed, error %d\n",
 			err);
 		/* non-fatal, continue */
 
@@ -3517,8 +3479,8 @@
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 
 	if (!pf) {
-		dev_err(&pdev->dev,
-			"%s failed, device is unrecoverable\n", __func__);
+		dev_err(&pdev->dev, "%s failed, device is unrecoverable\n",
+			__func__);
 		return;
 	}
 
@@ -3766,8 +3728,7 @@
 
 	/* Validate maxrate requested is within permitted range */
 	if (maxrate && (maxrate > (ICE_SCHED_MAX_BW / 1000))) {
-		netdev_err(netdev,
-			   "Invalid max rate %d specified for the queue %d\n",
+		netdev_err(netdev, "Invalid max rate %d specified for the queue %d\n",
 			   maxrate, queue_index);
 		return -EINVAL;
 	}
@@ -3783,8 +3744,8 @@
 		status = ice_cfg_q_bw_lmt(vsi->port_info, vsi->idx, tc,
 					  q_handle, ICE_MAX_BW, maxrate * 1000);
 	if (status) {
-		netdev_err(netdev,
-			   "Unable to set Tx max rate, error %d\n", status);
+		netdev_err(netdev, "Unable to set Tx max rate, error %d\n",
+			   status);
 		return -EIO;
 	}
 
@@ -3876,15 +3837,13 @@
 
 	/* Don't set any netdev advanced features with device in Safe Mode */
 	if (ice_is_safe_mode(vsi->back)) {
-		dev_err(&vsi->back->pdev->dev,
-			"Device is in Safe Mode - not enabling advanced netdev features\n");
+		dev_err(ice_pf_to_dev(vsi->back), "Device is in Safe Mode - not enabling advanced netdev features\n");
 		return ret;
 	}
 
 	/* Do not change setting during reset */
 	if (ice_is_reset_in_progress(pf->state)) {
-		dev_err(&vsi->back->pdev->dev,
-			"Device is resetting, changing advanced netdev features temporarily unavailable.\n");
+		dev_err(ice_pf_to_dev(vsi->back), "Device is resetting, changing advanced netdev features temporarily unavailable.\n");
 		return -EBUSY;
 	}
 
@@ -4372,21 +4331,18 @@
 
 	tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
 	if (tx_err)
-		netdev_err(vsi->netdev,
-			   "Failed stop Tx rings, VSI %d error %d\n",
+		netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n",
 			   vsi->vsi_num, tx_err);
 	if (!tx_err && ice_is_xdp_ena_vsi(vsi)) {
 		tx_err = ice_vsi_stop_xdp_tx_rings(vsi);
 		if (tx_err)
-			netdev_err(vsi->netdev,
-				   "Failed stop XDP rings, VSI %d error %d\n",
+			netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n",
 				   vsi->vsi_num, tx_err);
 	}
 
 	rx_err = ice_vsi_stop_rx_rings(vsi);
 	if (rx_err)
-		netdev_err(vsi->netdev,
-			   "Failed stop Rx rings, VSI %d error %d\n",
+		netdev_err(vsi->netdev, "Failed stop Rx rings, VSI %d error %d\n",
 			   vsi->vsi_num, rx_err);
 
 	ice_napi_disable_all(vsi);
@@ -4394,8 +4350,7 @@
 	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
 		link_err = ice_force_phys_link_state(vsi, false);
 		if (link_err)
-			netdev_err(vsi->netdev,
-				   "Failed to set physical link down, VSI %d error %d\n",
+			netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
 				   vsi->vsi_num, link_err);
 	}
 
@@ -4406,8 +4361,7 @@
 		ice_clean_rx_ring(vsi->rx_rings[i]);
 
 	if (tx_err || rx_err || link_err) {
-		netdev_err(vsi->netdev,
-			   "Failed to close VSI 0x%04X on switch 0x%04X\n",
+		netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
 		return -EIO;
 	}
@@ -4426,7 +4380,7 @@
 	int i, err = 0;
 
 	if (!vsi->num_txq) {
-		dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Tx queues\n",
+		dev_err(ice_pf_to_dev(vsi->back), "VSI %d has 0 Tx queues\n",
 			vsi->vsi_num);
 		return -EINVAL;
 	}
@@ -4457,7 +4411,7 @@
 	int i, err = 0;
 
 	if (!vsi->num_rxq) {
-		dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Rx queues\n",
+		dev_err(ice_pf_to_dev(vsi->back), "VSI %d has 0 Rx queues\n",
 			vsi->vsi_num);
 		return -EINVAL;
 	}
@@ -4554,8 +4508,7 @@
 
 		err = ice_vsi_release(pf->vsi[i]);
 		if (err)
-			dev_dbg(ice_pf_to_dev(pf),
-				"Failed to release pf->vsi[%d], err %d, vsi_num = %d\n",
+			dev_dbg(ice_pf_to_dev(pf), "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n",
 				i, err, pf->vsi[i]->vsi_num);
 	}
 }
@@ -4582,8 +4535,7 @@
 		/* rebuild the VSI */
 		err = ice_vsi_rebuild(vsi, true);
 		if (err) {
-			dev_err(dev,
-				"rebuild VSI failed, err %d, VSI index %d, type %s\n",
+			dev_err(dev, "rebuild VSI failed, err %d, VSI index %d, type %s\n",
 				err, vsi->idx, ice_vsi_type_str(type));
 			return err;
 		}
@@ -4591,8 +4543,7 @@
 		/* replay filters for the VSI */
 		status = ice_replay_vsi(&pf->hw, vsi->idx);
 		if (status) {
-			dev_err(dev,
-				"replay VSI failed, status %d, VSI index %d, type %s\n",
+			dev_err(dev, "replay VSI failed, status %d, VSI index %d, type %s\n",
 				status, vsi->idx, ice_vsi_type_str(type));
 			return -EIO;
 		}
@@ -4605,8 +4556,7 @@
 		/* enable the VSI */
 		err = ice_ena_vsi(vsi, false);
 		if (err) {
-			dev_err(dev,
-				"enable VSI failed, err %d, VSI index %d, type %s\n",
+			dev_err(dev, "enable VSI failed, err %d, VSI index %d, type %s\n",
 				err, vsi->idx, ice_vsi_type_str(type));
 			return err;
 		}
@@ -4684,8 +4634,7 @@
 	}
 
 	if (pf->first_sw->dflt_vsi_ena)
-		dev_info(dev,
-			 "Clearing default VSI, re-enable after reset completes\n");
+		dev_info(dev, "Clearing default VSI, re-enable after reset completes\n");
 	/* clear the default VSI configuration if it exists */
 	pf->first_sw->dflt_vsi = NULL;
 	pf->first_sw->dflt_vsi_ena = false;
@@ -4736,8 +4685,7 @@
 	/* tell the firmware we are up */
 	ret = ice_send_version(pf);
 	if (ret) {
-		dev_err(dev,
-			"Rebuild failed due to error sending driver version: %d\n",
+		dev_err(dev, "Rebuild failed due to error sending driver version: %d\n",
 			ret);
 		goto err_vsi_rebuild;
 	}
@@ -4993,7 +4941,7 @@
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(&vsi->back->pdev->dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
 			bmode, status, hw->adminq.sq_last_status);
 		ret = -EIO;
 		goto out;
@@ -5185,8 +5133,7 @@
 	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
 		err = ice_force_phys_link_state(vsi, true);
 		if (err) {
-			netdev_err(netdev,
-				   "Failed to set physical link up, error %d\n",
+			netdev_err(netdev, "Failed to set physical link up, error %d\n",
 				   err);
 			return err;
 		}
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index fd17ace..4de61db 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -644,7 +644,7 @@
  * Update the offset within page so that Rx buf will be ready to be reused.
  * For systems with PAGE_SIZE < 8192 this function will flip the page offset
  * so the second half of page assigned to Rx buffer will be used, otherwise
- * the offset is moved by the @size bytes
+ * the offset is moved by "size" bytes
  */
 static void
 ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
@@ -1078,8 +1078,6 @@
 				skb = ice_build_skb(rx_ring, rx_buf, &xdp);
 			else
 				skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
-		} else {
-			skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
 		}
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -1621,11 +1619,11 @@
 {
 	u64 td_offset, td_tag, td_cmd;
 	u16 i = tx_ring->next_to_use;
-	skb_frag_t *frag;
 	unsigned int data_len, size;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
 	struct sk_buff *skb;
+	skb_frag_t *frag;
 	dma_addr_t dma;
 
 	td_tag = off->td_l2tag1;
@@ -1738,9 +1736,8 @@
 	ice_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more())
 		writel(i, tx_ring->tail);
-	}
 
 	return;
 
@@ -2078,7 +2075,7 @@
 	frag = &skb_shinfo(skb)->frags[0];
 
 	/* Initialize size to the negative value of gso_size minus 1. We
-	 * use this as the worst case scenerio in which the frag ahead
+	 * use this as the worst case scenario in which the frag ahead
 	 * of us only provides one byte which is why we are limited to 6
 	 * descriptors for a single transmit as the header and previous
 	 * fragment are already consuming 2 descriptors.
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index a862706..7ee00a1 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -33,8 +33,8 @@
  * frame.
  *
  * Note: For cache line sizes 256 or larger this value is going to end
- *       up negative.  In these cases we should fall back to the legacy
- *       receive path.
+ *	 up negative.  In these cases we should fall back to the legacy
+ *	 receive path.
  */
 #if (PAGE_SIZE < 8192)
 #define ICE_2K_TOO_SMALL_WITH_PADDING \
@@ -222,7 +222,7 @@
 #define ICE_ITR_GRAN_S		1	/* ITR granularity is always 2us */
 #define ICE_ITR_GRAN_US		BIT(ICE_ITR_GRAN_S)
 #define ICE_ITR_MASK		0x1FFE	/* ITR register value alignment mask */
-#define ITR_REG_ALIGN(setting)	__ALIGN_MASK(setting, ~ICE_ITR_MASK)
+#define ITR_REG_ALIGN(setting)	((setting) & ICE_ITR_MASK)
 
 #define ICE_ITR_ADAPTIVE_MIN_INC	0x0002
 #define ICE_ITR_ADAPTIVE_MIN_USECS	0x0002
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 35bbc4f..6da048a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -10,7 +10,7 @@
  */
 void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
 {
-	u16 prev_ntu = rx_ring->next_to_use;
+	u16 prev_ntu = rx_ring->next_to_use & ~0x7;
 
 	rx_ring->next_to_use = val;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index b361ffa..db0ef6b 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -517,7 +517,7 @@
 	struct ice_fw_log_cfg fw_log;
 
 /* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL
- * register. Used for determining the ITR/intrl granularity during
+ * register. Used for determining the ITR/INTRL granularity during
  * initialization.
  */
 #define ICE_MAX_AGG_BW_200G	0x0
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 82b1e7a..75c70d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -199,8 +199,7 @@
 	if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG)
 		wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0);
 	else
-		dev_err(dev,
-			"Scattered mode for VF Rx queues is not yet implemented\n");
+		dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n");
 }
 
 /**
@@ -402,8 +401,7 @@
 		if ((reg & VF_TRANS_PENDING_M) == 0)
 			break;
 
-		dev_err(dev,
-			"VF %d PCI transactions stuck\n", vf->vf_id);
+		dev_err(dev, "VF %d PCI transactions stuck\n", vf->vf_id);
 		udelay(ICE_PCI_CIAD_WAIT_DELAY_US);
 	}
 }
@@ -462,7 +460,7 @@
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_info(&vsi->back->pdev->dev, "update VSI for port VLAN failed, err %d aq_err %d\n",
+		dev_info(ice_pf_to_dev(vsi->back), "update VSI for port VLAN failed, err %d aq_err %d\n",
 			 status, hw->adminq.sq_last_status);
 		ret = -EIO;
 		goto out;
@@ -1095,7 +1093,6 @@
 	 * finished resetting.
 	 */
 	for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) {
-
 		/* Check each VF in sequence */
 		while (v < pf->num_alloc_vfs) {
 			u32 reg;
@@ -1553,8 +1550,7 @@
 		dev_info(dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id,
 			 v_opcode, v_retval);
 		if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) {
-			dev_err(dev,
-				"Number of invalid messages exceeded for VF %d\n",
+			dev_err(dev, "Number of invalid messages exceeded for VF %d\n",
 				vf->vf_id);
 			dev_err(dev, "Use PF Control I/F to enable the VF\n");
 			set_bit(ICE_VF_STATE_DIS, vf->vf_states);
@@ -1569,8 +1565,7 @@
 	aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval,
 				       msg, msglen, NULL);
 	if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) {
-		dev_info(dev,
-			 "Unable to send the message to VF %d ret %d aq_err %d\n",
+		dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %d\n",
 			 vf->vf_id, aq_ret, pf->hw.mailboxq.sq_last_status);
 		return -EIO;
 	}
@@ -1879,6 +1874,48 @@
 }
 
 /**
+ * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset
+ * @vf: The VF being resseting
+ *
+ * The max poll time is about ~800ms, which is about the maximum time it takes
+ * for a VF to be reset and/or a VF driver to be removed.
+ */
+static void ice_wait_on_vf_reset(struct ice_vf *vf)
+{
+	int i;
+
+	for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) {
+		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
+			break;
+		msleep(ICE_MAX_VF_RESET_SLEEP_MS);
+	}
+}
+
+/**
+ * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried
+ * @vf: VF to check if it's ready to be configured/queried
+ *
+ * The purpose of this function is to make sure the VF is not in reset, not
+ * disabled, and initialized so it can be configured and/or queried by a host
+ * administrator.
+ */
+static int ice_check_vf_ready_for_cfg(struct ice_vf *vf)
+{
+	struct ice_pf *pf;
+
+	ice_wait_on_vf_reset(vf);
+
+	if (ice_is_vf_disabled(vf))
+		return -EINVAL;
+
+	pf = vf->pf;
+	if (ice_check_vf_init(pf, vf))
+		return -EBUSY;
+
+	return 0;
+}
+
+/**
  * ice_set_vf_spoofchk
  * @netdev: network interface device structure
  * @vf_id: VF identifier
@@ -1895,16 +1932,16 @@
 	enum ice_status status;
 	struct device *dev;
 	struct ice_vf *vf;
-	int ret = 0;
+	int ret;
 
 	dev = ice_pf_to_dev(pf);
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	vf_vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vf_vsi) {
@@ -1914,8 +1951,7 @@
 	}
 
 	if (vf_vsi->type != ICE_VSI_VF) {
-		netdev_err(netdev,
-			   "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n",
+		netdev_err(netdev, "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n",
 			   vf_vsi->type, vf_vsi->vsi_num, vf->vf_id);
 		return -ENODEV;
 	}
@@ -1945,8 +1981,7 @@
 
 	status = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL);
 	if (status) {
-		dev_err(dev,
-			"Failed to %sable spoofchk on VF %d VSI %d\n error %d",
+		dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d",
 			ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, status);
 		ret = -EIO;
 		goto out;
@@ -2063,8 +2098,7 @@
 			continue;
 
 		if (ice_vsi_ctrl_rx_ring(vsi, true, vf_q_id)) {
-			dev_err(&vsi->back->pdev->dev,
-				"Failed to enable Rx ring %d on VSI %d\n",
+			dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n",
 				vf_q_id, vsi->vsi_num);
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
@@ -2166,8 +2200,7 @@
 
 			if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id,
 						 ring, &txq_meta)) {
-				dev_err(&vsi->back->pdev->dev,
-					"Failed to stop Tx ring %d on VSI %d\n",
+				dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n",
 					vf_q_id, vsi->vsi_num);
 				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				goto error_param;
@@ -2193,8 +2226,7 @@
 				continue;
 
 			if (ice_vsi_ctrl_rx_ring(vsi, false, vf_q_id)) {
-				dev_err(&vsi->back->pdev->dev,
-					"Failed to stop Rx ring %d on VSI %d\n",
+				dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n",
 					vf_q_id, vsi->vsi_num);
 				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				goto error_param;
@@ -2357,8 +2389,7 @@
 
 	if (qci->num_queue_pairs > ICE_MAX_BASE_QS_PER_VF ||
 	    qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
-		dev_err(ice_pf_to_dev(pf),
-			"VF-%d requesting more than supported number of queues: %d\n",
+		dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n",
 			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
@@ -2570,8 +2601,7 @@
 	 */
 	if (set && !ice_is_vf_trusted(vf) &&
 	    (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) {
-		dev_err(ice_pf_to_dev(pf),
-			"Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n",
+		dev_err(ice_pf_to_dev(pf), "Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n",
 			vf->vf_id);
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto handle_mac_exit;
@@ -2648,8 +2678,8 @@
 	struct ice_pf *pf = vf->pf;
 	u16 max_allowed_vf_queues;
 	u16 tx_rx_queue_left;
-	u16 cur_queues;
 	struct device *dev;
+	u16 cur_queues;
 
 	dev = ice_pf_to_dev(pf);
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
@@ -2670,8 +2700,7 @@
 		vfres->num_queue_pairs = ICE_MAX_BASE_QS_PER_VF;
 	} else if (req_queues > cur_queues &&
 		   req_queues - cur_queues > tx_rx_queue_left) {
-		dev_warn(dev,
-			 "VF %d requested %u more queues, but only %u left.\n",
+		dev_warn(dev, "VF %d requested %u more queues, but only %u left.\n",
 			 vf->vf_id, req_queues - cur_queues, tx_rx_queue_left);
 		vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues,
 					       ICE_MAX_BASE_QS_PER_VF);
@@ -2709,7 +2738,7 @@
 	struct ice_vsi *vsi;
 	struct device *dev;
 	struct ice_vf *vf;
-	int ret = 0;
+	int ret;
 
 	dev = ice_pf_to_dev(pf);
 	if (ice_validate_vf_id(pf, vf_id))
@@ -2727,13 +2756,15 @@
 
 	vf = &pf->vf[vf_id];
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	if (le16_to_cpu(vsi->info.pvid) == vlanprio) {
 		/* duplicate request, so just return success */
 		dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio);
-		return ret;
+		return 0;
 	}
 
 	/* If PVID, then remove all filters on the old VLAN */
@@ -2744,7 +2775,7 @@
 	if (vlan_id || qos) {
 		ret = ice_vsi_manage_pvid(vsi, vlanprio, true);
 		if (ret)
-			goto error_set_pvid;
+			return ret;
 	} else {
 		ice_vsi_manage_pvid(vsi, 0, false);
 		vsi->info.pvid = 0;
@@ -2757,7 +2788,7 @@
 		/* add new VLAN filter for each MAC */
 		ret = ice_vsi_add_vlan(vsi, vlan_id);
 		if (ret)
-			goto error_set_pvid;
+			return ret;
 	}
 
 	/* The Port VLAN needs to be saved across resets the same as the
@@ -2765,8 +2796,7 @@
 	 */
 	vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
 
-error_set_pvid:
-	return ret;
+	return 0;
 }
 
 /**
@@ -2821,8 +2851,8 @@
 	for (i = 0; i < vfl->num_elements; i++) {
 		if (vfl->vlan_id[i] > ICE_MAX_VLANID) {
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-			dev_err(dev,
-				"invalid VF VLAN id %d\n", vfl->vlan_id[i]);
+			dev_err(dev, "invalid VF VLAN id %d\n",
+				vfl->vlan_id[i]);
 			goto error_param;
 		}
 	}
@@ -2836,8 +2866,7 @@
 
 	if (add_v && !ice_is_vf_trusted(vf) &&
 	    vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) {
-		dev_info(dev,
-			 "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+		dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
 			 vf->vf_id);
 		/* There is no need to let VF know about being not trusted,
 		 * so we can just return success message here
@@ -2860,8 +2889,7 @@
 
 			if (!ice_is_vf_trusted(vf) &&
 			    vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) {
-				dev_info(dev,
-					 "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+				dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
 					 vf->vf_id);
 				/* There is no need to let VF know about being
 				 * not trusted, so we can just return success
@@ -2889,8 +2917,7 @@
 				status = ice_cfg_vlan_pruning(vsi, true, false);
 				if (status) {
 					v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-					dev_err(dev,
-						"Enable VLAN pruning on VLAN ID: %d failed error-%d\n",
+					dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n",
 						vid, status);
 					goto error_param;
 				}
@@ -2903,8 +2930,7 @@
 							     promisc_m, vid);
 				if (status) {
 					v_ret = VIRTCHNL_STATUS_ERR_PARAM;
-					dev_err(dev,
-						"Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n",
+					dev_err(dev, "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n",
 						vid, status);
 				}
 			}
@@ -3140,8 +3166,7 @@
 	case VIRTCHNL_OP_GET_VF_RESOURCES:
 		err = ice_vc_get_vf_res_msg(vf, msg);
 		if (ice_vf_init_vlan_stripping(vf))
-			dev_err(dev,
-				"Failed to initialize VLAN stripping for VF %d\n",
+			dev_err(dev, "Failed to initialize VLAN stripping for VF %d\n",
 				vf->vf_id);
 		ice_vc_notify_vf_link_state(vf);
 		break;
@@ -3255,23 +3280,6 @@
 }
 
 /**
- * ice_wait_on_vf_reset
- * @vf: The VF being resseting
- *
- * Poll to make sure a given VF is ready after reset
- */
-static void ice_wait_on_vf_reset(struct ice_vf *vf)
-{
-	int i;
-
-	for (i = 0; i < ICE_MAX_VF_RESET_WAIT; i++) {
-		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
-			break;
-		msleep(20);
-	}
-}
-
-/**
  * ice_set_vf_mac
  * @netdev: network interface device structure
  * @vf_id: VF identifier
@@ -3283,29 +3291,21 @@
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_vf *vf;
-	int ret = 0;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
-	vf = &pf->vf[vf_id];
-	/* Don't set MAC on disabled VF */
-	if (ice_is_vf_disabled(vf))
-		return -EINVAL;
-
-	/* In case VF is in reset mode, wait until it is completed. Depending
-	 * on factors like queue disabling routine, this could take ~250ms
-	 */
-	ice_wait_on_vf_reset(vf);
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
-
 	if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) {
 		netdev_err(netdev, "%pM not a valid unicast address\n", mac);
 		return -EINVAL;
 	}
 
+	vf = &pf->vf[vf_id];
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
+
 	/* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
 	 * flow will use the updated dflt_lan_addr and add a MAC filter
 	 * using ice_add_mac. Also set pf_set_mac to indicate that the PF has
@@ -3313,12 +3313,11 @@
 	 */
 	ether_addr_copy(vf->dflt_lan_addr.addr, mac);
 	vf->pf_set_mac = true;
-	netdev_info(netdev,
-		    "MAC on VF %d set to %pM. VF driver will be reinitialized\n",
+	netdev_info(netdev, "MAC on VF %d set to %pM. VF driver will be reinitialized\n",
 		    vf_id, mac);
 
 	ice_vc_reset_vf(vf);
-	return ret;
+	return 0;
 }
 
 /**
@@ -3332,25 +3331,16 @@
 int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted)
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
-	struct device *dev;
 	struct ice_vf *vf;
+	int ret;
 
-	dev = ice_pf_to_dev(pf);
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-	/* Don't set Trusted Mode on disabled VF */
-	if (ice_is_vf_disabled(vf))
-		return -EINVAL;
-
-	/* In case VF is in reset mode, wait until it is completed. Depending
-	 * on factors like queue disabling routine, this could take ~250ms
-	 */
-	ice_wait_on_vf_reset(vf);
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	/* Check if already trusted */
 	if (trusted == vf->trusted)
@@ -3358,7 +3348,7 @@
 
 	vf->trusted = trusted;
 	ice_vc_reset_vf(vf);
-	dev_info(dev, "VF %u is now %strusted\n",
+	dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n",
 		 vf_id, trusted ? "" : "un");
 
 	return 0;
@@ -3376,13 +3366,15 @@
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_vf *vf;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	switch (link_state) {
 	case IFLA_VF_LINK_STATE_AUTO:
@@ -3418,14 +3410,15 @@
 	struct ice_eth_stats *stats;
 	struct ice_vsi *vsi;
 	struct ice_vf *vf;
+	int ret;
 
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
 	vf = &pf->vf[vf_id];
-
-	if (ice_check_vf_init(pf, vf))
-		return -EBUSY;
+	ret = ice_check_vf_ready_for_cfg(vf);
+	if (ret)
+		return ret;
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi)
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 4647d63..ac67982 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -38,7 +38,8 @@
 #define ICE_MAX_POLICY_INTR_PER_VF	33
 #define ICE_MIN_INTR_PER_VF		(ICE_MIN_QS_PER_VF + 1)
 #define ICE_DFLT_INTR_PER_VF		(ICE_DFLT_QS_PER_VF + 1)
-#define ICE_MAX_VF_RESET_WAIT		15
+#define ICE_MAX_VF_RESET_TRIES		40
+#define ICE_MAX_VF_RESET_SLEEP_MS	20
 
 #define ice_for_each_vf(pf, i) \
 	for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++)
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 149dca0..4d3407b 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -338,8 +338,8 @@
 						    DMA_BIDIRECTIONAL,
 						    ICE_RX_DMA_ATTR);
 		if (dma_mapping_error(dev, dma)) {
-			dev_dbg(dev,
-				"XSK UMEM DMA mapping error on page num %d", i);
+			dev_dbg(dev, "XSK UMEM DMA mapping error on page num %d\n",
+				i);
 			goto out_unmap;
 		}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 3a97564..20b907dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -200,7 +200,7 @@
 	netdev_err(priv->netdev, err_str);
 
 	if (!reporter)
-		return err_ctx->recover(&err_ctx->ctx);
+		return err_ctx->recover(err_ctx->ctx);
 
 	return devlink_health_report(reporter, err_str, err_ctx);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 7c8796d..a226277 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -179,6 +179,14 @@
 	}
 }
 
+static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
+{
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		mlx5_wq_ll_reset(&rq->mpwqe.wq);
+	else
+		mlx5_wq_cyc_reset(&rq->wqe.wq);
+}
+
 /* SW parser related functions */
 
 struct mlx5e_swp_spec {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 454d345..9669836 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -712,6 +712,9 @@
 	if (!in)
 		return -ENOMEM;
 
+	if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY)
+		mlx5e_rqwq_reset(rq);
+
 	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
 
 	MLX5_SET(modify_rq_in, in, rq_state, curr_state);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 5acf60b..e49acd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -459,12 +459,16 @@
 
 static int esw_legacy_enable(struct mlx5_eswitch *esw)
 {
-	int ret;
+	struct mlx5_vport *vport;
+	int ret, i;
 
 	ret = esw_create_legacy_table(esw);
 	if (ret)
 		return ret;
 
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+
 	ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
 	if (ret)
 		esw_destroy_legacy_table(esw);
@@ -2452,25 +2456,17 @@
 
 int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
 {
-	int err = 0;
-
 	if (!esw)
 		return -EOPNOTSUPP;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
 
-	mutex_lock(&esw->state_lock);
-	if (esw->mode != MLX5_ESWITCH_LEGACY) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
+	if (esw->mode != MLX5_ESWITCH_LEGACY)
+		return -EOPNOTSUPP;
 
 	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
-
-out:
-	mutex_unlock(&esw->state_lock);
-	return err;
+	return 0;
 }
 
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 979f13b..1a57b2b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1172,7 +1172,7 @@
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable(esw, true);
+	mlx5_eswitch_disable(esw, false);
 	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
@@ -2065,7 +2065,7 @@
 {
 	int err, err1;
 
-	mlx5_eswitch_disable(esw, true);
+	mlx5_eswitch_disable(esw, false);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c
index c5a446e..4276194 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c
@@ -35,7 +35,7 @@
 static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024,
 					  1 * 1024 * 1024,
 					  64 * 1024,
-					  4 * 1024, };
+					  128 };
 
 struct mlx5_esw_chains_priv {
 	struct rhashtable chains_ht;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index c6c7d1d..aade62a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -2307,7 +2307,9 @@
 	struct mlx5dr_cmd_vport_cap *vport_cap;
 	struct mlx5dr_domain *dmn = sb->dmn;
 	struct mlx5dr_cmd_caps *caps;
+	u8 *bit_mask = sb->bit_mask;
 	u8 *tag = hw_ste->tag;
+	bool source_gvmi_set;
 
 	DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
 
@@ -2328,7 +2330,8 @@
 	if (!vport_cap)
 		return -EINVAL;
 
-	if (vport_cap->vport_gvmi)
+	source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi);
+	if (vport_cap->vport_gvmi && source_gvmi_set)
 		MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi);
 
 	misc->source_eswitch_owner_vhca_id = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 3abfc81..c202719 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -66,15 +66,20 @@
 					 struct mlx5_flow_table *next_ft)
 {
 	struct mlx5dr_table *tbl;
+	u32 flags;
 	int err;
 
 	if (mlx5_dr_is_fw_table(ft->flags))
 		return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
 								    log_size,
 								    next_ft);
+	flags = ft->flags;
+	/* turn off encap/decap if not supported for sw-str by fw */
+	if (!MLX5_CAP_FLOWTABLE(ns->dev, sw_owner_reformat_supported))
+		flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
+				      MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain,
-				  ft->level, ft->flags);
+	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags);
 	if (!tbl) {
 		mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index 02f7e4a..01f075f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -94,6 +94,13 @@
 	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
 }
 
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq)
+{
+	wq->wqe_ctr = 0;
+	wq->cur_sz = 0;
+	mlx5_wq_cyc_update_db_record(wq);
+}
+
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
@@ -192,6 +199,19 @@
 	return err;
 }
 
+static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq)
+{
+	struct mlx5_wqe_srq_next_seg *next_seg;
+	int i;
+
+	for (i = 0; i < wq->fbc.sz_m1; i++) {
+		next_seg = mlx5_wq_ll_get_wqe(wq, i);
+		next_seg->next_wqe_index = cpu_to_be16(i + 1);
+	}
+	next_seg = mlx5_wq_ll_get_wqe(wq, i);
+	wq->tail_next = &next_seg->next_wqe_index;
+}
+
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
@@ -199,9 +219,7 @@
 	u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride);
 	u8 log_wq_sz     = MLX5_GET(wq, wqc, log_wq_sz);
 	struct mlx5_frag_buf_ctrl *fbc = &wq->fbc;
-	struct mlx5_wqe_srq_next_seg *next_seg;
 	int err;
-	int i;
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -220,13 +238,7 @@
 
 	mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc);
 
-	for (i = 0; i < fbc->sz_m1; i++) {
-		next_seg = mlx5_wq_ll_get_wqe(wq, i);
-		next_seg->next_wqe_index = cpu_to_be16(i + 1);
-	}
-	next_seg = mlx5_wq_ll_get_wqe(wq, i);
-	wq->tail_next = &next_seg->next_wqe_index;
-
+	mlx5_wq_ll_init_list(wq);
 	wq_ctrl->mdev = mdev;
 
 	return 0;
@@ -237,6 +249,15 @@
 	return err;
 }
 
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq)
+{
+	wq->head = 0;
+	wq->wqe_ctr = 0;
+	wq->cur_sz = 0;
+	mlx5_wq_ll_init_list(wq);
+	mlx5_wq_ll_update_db_record(wq);
+}
+
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)
 {
 	mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index d9a94bc..4cadc33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -80,6 +80,7 @@
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
@@ -92,6 +93,7 @@
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl);
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
 
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index a41a90c..1c9e70c 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -157,24 +157,6 @@
  */
 
 /**
- * ks_rdreg8 - read 8 bit register from device
- * @ks	  : The chip information
- * @offset: The register address
- *
- * Read a 8bit register from the chip, returning the result
- */
-static u8 ks_rdreg8(struct ks_net *ks, int offset)
-{
-	u16 data;
-	u8 shift_bit = offset & 0x03;
-	u8 shift_data = (offset & 1) << 3;
-	ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit);
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	data  = ioread16(ks->hw_addr);
-	return (u8)(data >> shift_data);
-}
-
-/**
  * ks_rdreg16 - read 16 bit register from device
  * @ks	  : The chip information
  * @offset: The register address
@@ -184,28 +166,12 @@
 
 static u16 ks_rdreg16(struct ks_net *ks, int offset)
 {
-	ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
+	ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02));
 	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
 	return ioread16(ks->hw_addr);
 }
 
 /**
- * ks_wrreg8 - write 8bit register value to chip
- * @ks: The chip information
- * @offset: The register address
- * @value: The value to write
- *
- */
-static void ks_wrreg8(struct ks_net *ks, int offset, u8 value)
-{
-	u8  shift_bit = (offset & 0x03);
-	u16 value_write = (u16)(value << ((offset & 1) << 3));
-	ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit);
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	iowrite16(value_write, ks->hw_addr);
-}
-
-/**
  * ks_wrreg16 - write 16bit register value to chip
  * @ks: The chip information
  * @offset: The register address
@@ -215,7 +181,7 @@
 
 static void ks_wrreg16(struct ks_net *ks, int offset, u16 value)
 {
-	ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
+	ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02));
 	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
 	iowrite16(value, ks->hw_addr);
 }
@@ -231,7 +197,7 @@
 {
 	len >>= 1;
 	while (len--)
-		*wptr++ = (u16)ioread16(ks->hw_addr);
+		*wptr++ = be16_to_cpu(ioread16(ks->hw_addr));
 }
 
 /**
@@ -245,7 +211,7 @@
 {
 	len >>= 1;
 	while (len--)
-		iowrite16(*wptr++, ks->hw_addr);
+		iowrite16(cpu_to_be16(*wptr++), ks->hw_addr);
 }
 
 static void ks_disable_int(struct ks_net *ks)
@@ -324,8 +290,7 @@
 	u16 reg_data = 0;
 
 	/* Regardless of bus width, 8 bit read should always work.*/
-	reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF;
-	reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8;
+	reg_data = ks_rdreg16(ks, KS_CCR);
 
 	/* addr/data bus are multiplexed */
 	ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED;
@@ -429,7 +394,7 @@
 
 	/* 1. set sudo DMA mode */
 	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
-	ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 
 	/* 2. read prepend data */
 	/**
@@ -446,7 +411,7 @@
 	ks_inblk(ks, buf, ALIGN(len, 4));
 
 	/* 4. reset sudo DMA Mode */
-	ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 }
 
 /**
@@ -679,13 +644,13 @@
 	ks->txh.txw[1] = cpu_to_le16(len);
 
 	/* 1. set sudo-DMA mode */
-	ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 	/* 2. write status/lenth info */
 	ks_outblk(ks, ks->txh.txw, 4);
 	/* 3. write pkt data */
 	ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4));
 	/* 4. reset sudo-DMA mode */
-	ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 	/* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */
 	ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
 	/* 6. wait until TXQCR_METFE is auto-cleared */
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index b388208..1135a18 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -114,6 +114,14 @@
 		if (err != 4)
 			break;
 
+		/* At this point the IFH was read correctly, so it is safe to
+		 * presume that there is no error. The err needs to be reset
+		 * otherwise a frame could come in CPU queue between the while
+		 * condition and the check for error later on. And in that case
+		 * the new frame is just removed and not processed.
+		 */
+		err = 0;
+
 		ocelot_parse_ifh(ifh, &info);
 
 		ocelot_port = ocelot->ports[info.port];
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 87f82f3..46107de 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -103,7 +103,7 @@
 {
 	struct ionic_dev *idev = &ionic->idev;
 	unsigned long hb_time;
-	u32 fw_status;
+	u8 fw_status;
 	u32 hb;
 
 	/* wait a little more than one second before testing again */
@@ -111,9 +111,12 @@
 	if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period)))
 		return 0;
 
-	/* firmware is useful only if fw_status is non-zero */
-	fw_status = ioread32(&idev->dev_info_regs->fw_status);
-	if (!fw_status)
+	/* firmware is useful only if the running bit is set and
+	 * fw_status != 0xff (bad PCI read)
+	 */
+	fw_status = ioread8(&idev->dev_info_regs->fw_status);
+	if (fw_status == 0xff ||
+	    !(fw_status & IONIC_FW_STS_F_RUNNING))
 		return -ENXIO;
 
 	/* early FW has no heartbeat, else FW will return non-zero */
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index ce07c29..54547d5 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -2445,6 +2445,7 @@
 		u8     version;
 		u8     asic_type;
 		u8     asic_rev;
+#define IONIC_FW_STS_F_RUNNING	0x1
 		u8     fw_status;
 		u32    fw_heartbeat;
 		char   fw_version[IONIC_DEVINFO_FWVERS_BUFLEN];
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index e8a1b27d..234c6f3 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -163,6 +163,8 @@
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	struct kref refcnt;
+	struct completion event_comp;
 	bool exp_recovery;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index ffabc2d..2d873ae 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -59,6 +59,9 @@
 static int qede_rdma_create_wq(struct qede_dev *edev)
 {
 	INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list);
+	kref_init(&edev->rdma_info.refcnt);
+	init_completion(&edev->rdma_info.event_comp);
+
 	edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq");
 	if (!edev->rdma_info.rdma_wq) {
 		DP_NOTICE(edev, "qedr: Could not create workqueue\n");
@@ -83,8 +86,23 @@
 	}
 }
 
+static void qede_rdma_complete_event(struct kref *ref)
+{
+	struct qede_rdma_dev *rdma_dev =
+		container_of(ref, struct qede_rdma_dev, refcnt);
+
+	/* no more events will be added after this */
+	complete(&rdma_dev->event_comp);
+}
+
 static void qede_rdma_destroy_wq(struct qede_dev *edev)
 {
+	/* Avoid race with add_event flow, make sure it finishes before
+	 * we start accessing the list and cleaning up the work
+	 */
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
+	wait_for_completion(&edev->rdma_info.event_comp);
+
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
@@ -310,15 +328,24 @@
 	if (!edev->rdma_info.qedr_dev)
 		return;
 
+	/* We don't want the cleanup flow to start while we're allocating and
+	 * scheduling the work
+	 */
+	if (!kref_get_unless_zero(&edev->rdma_info.refcnt))
+		return; /* already being destroyed */
+
 	event_node = qede_rdma_get_free_event_node(edev);
 	if (!event_node)
-		return;
+		goto out;
 
 	event_node->event = event;
 	event_node->ptr = edev;
 
 	INIT_WORK(&event_node->work, qede_rdma_handle_event);
 	queue_work(edev->rdma_info.rdma_wq, &event_node->work);
+
+out:
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
 }
 
 void qede_rdma_dev_event_open(struct qede_dev *edev)
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index b703242..67ddf78 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1810,6 +1810,9 @@
 		break;
 	case PHY_INTERFACE_MODE_MII:
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		priv->pinmode_val = 0;
 		break;
 	default:
@@ -1854,6 +1857,9 @@
 		priv->pinmode_val = SG_ETPINMODE_RMII(0);
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		priv->pinmode_val = 0;
 		break;
 	default:
@@ -1876,6 +1882,9 @@
 		priv->pinmode_val = SG_ETPINMODE_RMII(arg);
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		priv->pinmode_val = 0;
 		break;
 	default:
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index c23ce83..8dc6c9f 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1350,27 +1350,12 @@
 		if (vio_version_after_eq(&port->vio, 1, 3))
 			localmtu -= VLAN_HLEN;
 
-		if (skb->protocol == htons(ETH_P_IP)) {
-			struct flowi4 fl4;
-			struct rtable *rt = NULL;
-
-			memset(&fl4, 0, sizeof(fl4));
-			fl4.flowi4_oif = dev->ifindex;
-			fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
-			fl4.daddr = ip_hdr(skb)->daddr;
-			fl4.saddr = ip_hdr(skb)->saddr;
-
-			rt = ip_route_output_key(dev_net(dev), &fl4);
-			if (!IS_ERR(rt)) {
-				skb_dst_set(skb, &rt->dst);
-				icmp_send(skb, ICMP_DEST_UNREACH,
-					  ICMP_FRAG_NEEDED,
-					  htonl(localmtu));
-			}
-		}
+		if (skb->protocol == htons(ETH_P_IP))
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				      htonl(localmtu));
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (skb->protocol == htons(ETH_P_IPV6))
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu);
 #endif
 		goto out_dropped;
 	}
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index af07ea7..672cd2c 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -546,8 +546,8 @@
 	    mtu < ntohs(iph->tot_len)) {
 		netdev_dbg(dev, "packet too big, fragmentation needed\n");
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(mtu));
+		icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+			      htonl(mtu));
 		goto err_rt;
 	}
 
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 7d68b28..a62229a 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -410,7 +410,7 @@
 	struct device_node *np = phydev->mdio.dev.of_node;
 	int ret;
 
-	/* Aneg firsly. */
+	/* Aneg firstly. */
 	ret = genphy_config_aneg(phydev);
 
 	/* Then we can set up the delay. */
@@ -463,7 +463,7 @@
 {
 	int ret;
 
-	/* Aneg firsly. */
+	/* Aneg firstly. */
 	if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX)
 		ret = genphy_c37_config_aneg(phydev);
 	else
diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index 7e9975d..f1ded03 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -178,6 +178,23 @@
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+int iproc_mdio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdio_priv *priv = platform_get_drvdata(pdev);
+
+	/* restore the mii clock configuration */
+	iproc_mdio_config_clk(priv->base);
+
+	return 0;
+}
+
+static const struct dev_pm_ops iproc_mdio_pm_ops = {
+	.resume = iproc_mdio_resume
+};
+#endif /* CONFIG_PM_SLEEP */
+
 static const struct of_device_id iproc_mdio_of_match[] = {
 	{ .compatible = "brcm,iproc-mdio", },
 	{ /* sentinel */ },
@@ -188,6 +205,9 @@
 	.driver = {
 		.name = "iproc-mdio",
 		.of_match_table = iproc_mdio_of_match,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &iproc_mdio_pm_ops,
+#endif
 	},
 	.probe = iproc_mdio_probe,
 	.remove = iproc_mdio_remove,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 9485c8d..3b7a3b8 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -61,7 +61,6 @@
 
 enum qmi_wwan_quirks {
 	QMI_WWAN_QUIRK_DTR = 1 << 0,	/* needs "set DTR" request */
-	QMI_WWAN_QUIRK_QUECTEL_DYNCFG = 1 << 1,	/* check num. endpoints */
 };
 
 struct qmimux_hdr {
@@ -916,16 +915,6 @@
 	.data           = QMI_WWAN_QUIRK_DTR,
 };
 
-static const struct driver_info	qmi_wwan_info_quirk_quectel_dyncfg = {
-	.description	= "WWAN/QMI device",
-	.flags		= FLAG_WWAN | FLAG_SEND_ZLP,
-	.bind		= qmi_wwan_bind,
-	.unbind		= qmi_wwan_unbind,
-	.manage_power	= qmi_wwan_manage_power,
-	.rx_fixup       = qmi_wwan_rx_fixup,
-	.data           = QMI_WWAN_QUIRK_DTR | QMI_WWAN_QUIRK_QUECTEL_DYNCFG,
-};
-
 #define HUAWEI_VENDOR_ID	0x12D1
 
 /* map QMI/wwan function by a fixed interface number */
@@ -946,14 +935,18 @@
 #define QMI_GOBI_DEVICE(vend, prod) \
 	QMI_FIXED_INTF(vend, prod, 0)
 
-/* Quectel does not use fixed interface numbers on at least some of their
- * devices. We need to check the number of endpoints to ensure that we bind to
- * the correct interface.
+/* Many devices have QMI and DIAG functions which are distinguishable
+ * from other vendor specific functions by class, subclass and
+ * protocol all being 0xff. The DIAG function has exactly 2 endpoints
+ * and is silently rejected when probed.
+ *
+ * This makes it possible to match dynamically numbered QMI functions
+ * as seen on e.g. many Quectel modems.
  */
-#define QMI_QUIRK_QUECTEL_DYNCFG(vend, prod) \
+#define QMI_MATCH_FF_FF_FF(vend, prod) \
 	USB_DEVICE_AND_INTERFACE_INFO(vend, prod, USB_CLASS_VENDOR_SPEC, \
 				      USB_SUBCLASS_VENDOR_SPEC, 0xff), \
-	.driver_info = (unsigned long)&qmi_wwan_info_quirk_quectel_dyncfg
+	.driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr
 
 static const struct usb_device_id products[] = {
 	/* 1. CDC ECM like devices match on the control interface */
@@ -1059,10 +1052,10 @@
 		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
 		.driver_info = (unsigned long)&qmi_wwan_info,
 	},
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0125)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0306)},	/* Quectel EP06/EG06/EM06 */
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0512)},	/* Quectel EG12/EM12 */
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0800)},	/* Quectel RM500Q-GL */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)},	/* Quectel EP06/EG06/EM06 */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)},	/* Quectel EG12/EM12 */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)},	/* Quectel RM500Q-GL */
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -1363,6 +1356,7 @@
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e preproduction config */
 	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
@@ -1454,7 +1448,6 @@
 {
 	struct usb_device_id *id = (struct usb_device_id *)prod;
 	struct usb_interface_descriptor *desc = &intf->cur_altsetting->desc;
-	const struct driver_info *info;
 
 	/* Workaround to enable dynamic IDs.  This disables usbnet
 	 * blacklisting functionality.  Which, if required, can be
@@ -1490,12 +1483,8 @@
 	 * different. Ignore the current interface if the number of endpoints
 	 * equals the number for the diag interface (two).
 	 */
-	info = (void *)id->driver_info;
-
-	if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) {
-		if (desc->bNumEndpoints == 2)
-			return -ENODEV;
-	}
+	if (desc->bNumEndpoints == 2)
+		return -ENODEV;
 
 	return usbnet_probe(intf, id);
 }
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 16b1982..cdc9696 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -203,9 +203,9 @@
 err:
 	++dev->stats.tx_errors;
 	if (skb->protocol == htons(ETH_P_IP))
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+		icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
 	else if (skb->protocol == htons(ETH_P_IPV6))
-		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
+		icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
 	kfree_skb(skb);
 	return ret;
 }
@@ -258,6 +258,8 @@
 	enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
 				    NETIF_F_SG | NETIF_F_GSO |
 				    NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
+	const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) +
+			     max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
 
 	dev->netdev_ops = &netdev_ops;
 	dev->hard_header_len = 0;
@@ -271,9 +273,8 @@
 	dev->features |= WG_NETDEV_FEATURES;
 	dev->hw_features |= WG_NETDEV_FEATURES;
 	dev->hw_enc_features |= WG_NETDEV_FEATURES;
-	dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
-		   sizeof(struct udphdr) -
-		   max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
+	dev->mtu = ETH_DATA_LEN - overhead;
+	dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead;
 
 	SET_NETDEV_DEVTYPE(dev, &device_type);
 
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 9c6bab9..4a15389 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -118,10 +118,13 @@
 
 	under_load = skb_queue_len(&wg->incoming_handshakes) >=
 		     MAX_QUEUED_INCOMING_HANDSHAKES / 8;
-	if (under_load)
+	if (under_load) {
 		last_under_load = ktime_get_coarse_boottime_ns();
-	else if (last_under_load)
+	} else if (last_under_load) {
 		under_load = !wg_birthdate_has_expired(last_under_load, 1);
+		if (!under_load)
+			last_under_load = 0;
+	}
 	mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
 					      under_load);
 	if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index c132605..7348c10 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -143,16 +143,22 @@
 
 static unsigned int calculate_skb_padding(struct sk_buff *skb)
 {
+	unsigned int padded_size, last_unit = skb->len;
+
+	if (unlikely(!PACKET_CB(skb)->mtu))
+		return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit;
+
 	/* We do this modulo business with the MTU, just in case the networking
 	 * layer gives us a packet that's bigger than the MTU. In that case, we
 	 * wouldn't want the final subtraction to overflow in the case of the
-	 * padded_size being clamped.
+	 * padded_size being clamped. Fortunately, that's very rarely the case,
+	 * so we optimize for that not happening.
 	 */
-	unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
-	unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
+	if (unlikely(last_unit > PACKET_CB(skb)->mtu))
+		last_unit %= PACKET_CB(skb)->mtu;
 
-	if (padded_size > PACKET_CB(skb)->mtu)
-		padded_size = PACKET_CB(skb)->mtu;
+	padded_size = min(PACKET_CB(skb)->mtu,
+			  ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE));
 	return padded_size - last_unit;
 }
 
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index 262f3b5..b0d6541 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -432,7 +432,6 @@
 		wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
 	mutex_unlock(&wg->socket_update_lock);
 	synchronize_rcu();
-	synchronize_net();
 	sock_free(old4);
 	sock_free(old6);
 }
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 720c89d..4ac8cb2 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -225,6 +225,7 @@
 
 out:
 	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
 }
 
 static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)
diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c
index 2b83156..b788870 100644
--- a/drivers/nfc/pn544/pn544.c
+++ b/drivers/nfc/pn544/pn544.c
@@ -682,7 +682,7 @@
 static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
 				   struct nfc_target *target)
 {
-	pr_debug("supported protocol %d\b", target->supported_protocols);
+	pr_debug("supported protocol %d\n", target->supported_protocols);
 	if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK |
 					NFC_PROTO_ISO14443_B_MASK)) {
 		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 5dc32b7..ada59df 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -66,8 +66,8 @@
  * nvme_reset_wq - hosts nvme reset works
  * nvme_delete_wq - hosts nvme delete works
  *
- * nvme_wq will host works such are scan, aen handling, fw activation,
- * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq
+ * nvme_wq will host works such as scan, aen handling, fw activation,
+ * keep-alive, periodic reconnects etc. nvme_reset_wq
  * runs reset works which also flush works hosted on nvme_wq for
  * serialization purposes. nvme_delete_wq host controller deletion
  * works which flush reset works for serialization.
@@ -976,7 +976,7 @@
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
@@ -1006,7 +1006,7 @@
 		dev_dbg(ctrl->device,
 			"reschedule traffic based keep-alive timer\n");
 		ctrl->comp_seen = false;
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 		return;
 	}
 
@@ -1023,7 +1023,7 @@
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
@@ -3867,7 +3867,7 @@
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
 			sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index da392b5..9c80f9f0 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1401,6 +1401,23 @@
 	nvme_poll_irqdisable(nvmeq, -1);
 }
 
+/*
+ * Called only on a device that has been disabled and after all other threads
+ * that can check this device's completion queues have synced. This is the
+ * last chance for the driver to see a natural completion before
+ * nvme_cancel_request() terminates all incomplete requests.
+ */
+static void nvme_reap_pending_cqes(struct nvme_dev *dev)
+{
+	u16 start, end;
+	int i;
+
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
+		nvme_process_cq(&dev->queues[i], &start, &end, -1);
+		nvme_complete_cqes(&dev->queues[i], start, end);
+	}
+}
+
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 				int entry_size)
 {
@@ -2235,11 +2252,6 @@
 		if (timeout == 0)
 			return false;
 
-		/* handle any remaining CQEs */
-		if (opcode == nvme_admin_delete_cq &&
-		    !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags))
-			nvme_poll_irqdisable(nvmeq, -1);
-
 		sent--;
 		if (nr_queues)
 			goto retry;
@@ -2428,6 +2440,7 @@
 	nvme_suspend_io_queues(dev);
 	nvme_suspend_queue(&dev->queues[0]);
 	nvme_pci_disable(dev);
+	nvme_reap_pending_cqes(dev);
 
 	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
 	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2a47c6c..3e85c5c 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1088,7 +1088,7 @@
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
-	queue_work(nvme_wq, &ctrl->err_work);
+	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
 static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 6d43b23a..49d4373 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -422,7 +422,7 @@
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
-	queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work);
+	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
@@ -1054,7 +1054,12 @@
 		} else if (unlikely(result < 0)) {
 			dev_err(queue->ctrl->ctrl.device,
 				"failed to send request %d\n", result);
-			if (result != -EPIPE)
+
+			/*
+			 * Fail the request unless peer closed the connection,
+			 * in which case error recovery flow will complete all.
+			 */
+			if ((result != -EPIPE) && (result != -ECONNRESET))
 				nvme_tcp_fail_request(queue->request);
 			nvme_tcp_done_send_req(queue);
 			return;
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index d704ecc..f01a57e 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -771,7 +771,7 @@
 		smmu_pmu->reloc_base = smmu_pmu->reg_base;
 	}
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq > 0)
 		smmu_pmu->irq = irq;
 
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 4b07984..ff74eb5 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -182,11 +182,9 @@
 };
 
 struct qdio_input_q {
-	/* input buffer acknowledgement flag */
-	int polling;
 	/* first ACK'ed buffer */
 	int ack_start;
-	/* how much sbals are acknowledged with qebsm */
+	/* how many SBALs are acknowledged */
 	int ack_count;
 	/* last time of noticing incoming data */
 	u64 timestamp;
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index 35410e6..9c0370b 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -124,9 +124,8 @@
 	seq_printf(m, "nr_used: %d  ftc: %d\n",
 		   atomic_read(&q->nr_buf_used), q->first_to_check);
 	if (q->is_input_q) {
-		seq_printf(m, "polling: %d  ack start: %d  ack count: %d\n",
-			   q->u.in.polling, q->u.in.ack_start,
-			   q->u.in.ack_count);
+		seq_printf(m, "ack start: %d  ack count: %d\n",
+			   q->u.in.ack_start, q->u.in.ack_count);
 		seq_printf(m, "DSCI: %x   IRQs disabled: %u\n",
 			   *(u8 *)q->irq_ptr->dsci,
 			   test_bit(QDIO_QUEUE_IRQS_DISABLED,
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index f8b897b..3475317c 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -393,19 +393,15 @@
 
 static inline void qdio_stop_polling(struct qdio_q *q)
 {
-	if (!q->u.in.polling)
+	if (!q->u.in.ack_count)
 		return;
 
-	q->u.in.polling = 0;
 	qperf_inc(q, stop_polling);
 
 	/* show the card that we are not polling anymore */
-	if (is_qebsm(q)) {
-		set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
-			       q->u.in.ack_count);
-		q->u.in.ack_count = 0;
-	} else
-		set_buf_state(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT);
+	set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
+		       q->u.in.ack_count);
+	q->u.in.ack_count = 0;
 }
 
 static inline void account_sbals(struct qdio_q *q, unsigned int count)
@@ -451,8 +447,7 @@
 
 	/* for QEBSM the ACK was already set by EQBS */
 	if (is_qebsm(q)) {
-		if (!q->u.in.polling) {
-			q->u.in.polling = 1;
+		if (!q->u.in.ack_count) {
 			q->u.in.ack_count = count;
 			q->u.in.ack_start = start;
 			return;
@@ -471,12 +466,12 @@
 	 * or by the next inbound run.
 	 */
 	new = add_buf(start, count - 1);
-	if (q->u.in.polling) {
+	if (q->u.in.ack_count) {
 		/* reset the previous ACK but first set the new one */
 		set_buf_state(q, new, SLSB_P_INPUT_ACK);
 		set_buf_state(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT);
 	} else {
-		q->u.in.polling = 1;
+		q->u.in.ack_count = 1;
 		set_buf_state(q, new, SLSB_P_INPUT_ACK);
 	}
 
@@ -1479,13 +1474,12 @@
 
 	qperf_inc(q, inbound_call);
 
-	if (!q->u.in.polling)
+	if (!q->u.in.ack_count)
 		goto set;
 
 	/* protect against stop polling setting an ACK for an emptied slsb */
 	if (count == QDIO_MAX_BUFFERS_PER_Q) {
 		/* overwriting everything, just delete polling status */
-		q->u.in.polling = 0;
 		q->u.in.ack_count = 0;
 		goto set;
 	} else if (buf_in_between(q->u.in.ack_start, bufnr, count)) {
@@ -1495,15 +1489,14 @@
 			diff = sub_buf(diff, q->u.in.ack_start);
 			q->u.in.ack_count -= diff;
 			if (q->u.in.ack_count <= 0) {
-				q->u.in.polling = 0;
 				q->u.in.ack_count = 0;
 				goto set;
 			}
 			q->u.in.ack_start = add_buf(q->u.in.ack_start, diff);
+		} else {
+			/* the only ACK will be deleted */
+			q->u.in.ack_count = 0;
 		}
-		else
-			/* the only ACK will be deleted, so stop polling */
-			q->u.in.polling = 0;
 	}
 
 set:
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index dc430bd..3ab8e80 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -536,7 +536,7 @@
 int qdio_enable_async_operation(struct qdio_output_q *outq)
 {
 	outq->aobs = kcalloc(QDIO_MAX_BUFFERS_PER_Q, sizeof(struct qaob *),
-			     GFP_ATOMIC);
+			     GFP_KERNEL);
 	if (!outq->aobs) {
 		outq->use_cq = 0;
 		return -ENOMEM;
diff --git a/drivers/s390/cio/vfio_ccw_trace.h b/drivers/s390/cio/vfio_ccw_trace.h
index 30162a3..f5d3188 100644
--- a/drivers/s390/cio/vfio_ccw_trace.h
+++ b/drivers/s390/cio/vfio_ccw_trace.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Tracepoints for vfio_ccw driver
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Tracepoints for vfio_ccw driver
  *
  * Copyright IBM Corp. 2018
  *
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index bb35ba4..4348fdf 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -162,7 +162,7 @@
 	unsigned int functions;		/* AP device function bitfield. */
 	int queue_depth;		/* AP queue depth.*/
 	int id;				/* AP card number. */
-	atomic_t total_request_count;	/* # requests ever for this AP device.*/
+	atomic64_t total_request_count;	/* # requests ever for this AP device.*/
 };
 
 #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device)
@@ -179,7 +179,7 @@
 	enum ap_state state;		/* State of the AP device. */
 	int pendingq_count;		/* # requests on pendingq list. */
 	int requestq_count;		/* # requests on requestq list. */
-	int total_request_count;	/* # requests ever for this AP device.*/
+	u64 total_request_count;	/* # requests ever for this AP device.*/
 	int request_timeout;		/* Request timeout in jiffies. */
 	struct timer_list timeout;	/* Timer for request timeouts. */
 	struct list_head pendingq;	/* List of message sent to AP queue. */
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index 63b4cc6..e85bfca 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -63,13 +63,13 @@
 				  char *buf)
 {
 	struct ap_card *ac = to_ap_card(dev);
-	unsigned int req_cnt;
+	u64 req_cnt;
 
 	req_cnt = 0;
 	spin_lock_bh(&ap_list_lock);
-	req_cnt = atomic_read(&ac->total_request_count);
+	req_cnt = atomic64_read(&ac->total_request_count);
 	spin_unlock_bh(&ap_list_lock);
-	return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt);
+	return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt);
 }
 
 static ssize_t request_count_store(struct device *dev,
@@ -83,7 +83,7 @@
 	for_each_ap_queue(aq, ac)
 		aq->total_request_count = 0;
 	spin_unlock_bh(&ap_list_lock);
-	atomic_set(&ac->total_request_count, 0);
+	atomic64_set(&ac->total_request_count, 0);
 
 	return count;
 }
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index 37c3bdc..a317ab4 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -479,12 +479,12 @@
 				  char *buf)
 {
 	struct ap_queue *aq = to_ap_queue(dev);
-	unsigned int req_cnt;
+	u64 req_cnt;
 
 	spin_lock_bh(&aq->lock);
 	req_cnt = aq->total_request_count;
 	spin_unlock_bh(&aq->lock);
-	return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt);
+	return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt);
 }
 
 static ssize_t request_count_store(struct device *dev,
@@ -676,7 +676,7 @@
 	list_add_tail(&ap_msg->list, &aq->requestq);
 	aq->requestq_count++;
 	aq->total_request_count++;
-	atomic_inc(&aq->card->total_request_count);
+	atomic64_inc(&aq->card->total_request_count);
 	/* Send/receive as many request from the queue as possible. */
 	ap_wait(ap_sm_event_loop(aq, AP_EVENT_POLL));
 	spin_unlock_bh(&aq->lock);
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 71dae64..2f33c5f 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -994,7 +994,7 @@
 			return -EFAULT;
 		rc = cca_sec2protkey(ksp.cardnr, ksp.domain,
 				     ksp.seckey.seckey, ksp.protkey.protkey,
-				     NULL, &ksp.protkey.type);
+				     &ksp.protkey.len, &ksp.protkey.type);
 		DEBUG_DBG("%s cca_sec2protkey()=%d\n", __func__, rc);
 		if (rc)
 			break;
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index a42257d..56a405d 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -606,8 +606,8 @@
 	weight += atomic_read(&zc->load);
 	pref_weight += atomic_read(&pref_zc->load);
 	if (weight == pref_weight)
-		return atomic_read(&zc->card->total_request_count) >
-			atomic_read(&pref_zc->card->total_request_count);
+		return atomic64_read(&zc->card->total_request_count) >
+			atomic64_read(&pref_zc->card->total_request_count);
 	return weight > pref_weight;
 }
 
@@ -1226,11 +1226,12 @@
 	spin_unlock(&zcrypt_list_lock);
 }
 
-static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters)
+static void zcrypt_perdev_reqcnt(u32 reqcnt[], size_t max_adapters)
 {
 	struct zcrypt_card *zc;
 	struct zcrypt_queue *zq;
 	int card;
+	u64 cnt;
 
 	memset(reqcnt, 0, sizeof(int) * max_adapters);
 	spin_lock(&zcrypt_list_lock);
@@ -1242,8 +1243,9 @@
 			    || card >= max_adapters)
 				continue;
 			spin_lock(&zq->queue->lock);
-			reqcnt[card] = zq->queue->total_request_count;
+			cnt = zq->queue->total_request_count;
 			spin_unlock(&zq->queue->lock);
+			reqcnt[card] = (cnt < UINT_MAX) ? (u32) cnt : UINT_MAX;
 		}
 	}
 	local_bh_enable();
@@ -1421,9 +1423,9 @@
 		return 0;
 	}
 	case ZCRYPT_PERDEV_REQCNT: {
-		int *reqcnt;
+		u32 *reqcnt;
 
-		reqcnt = kcalloc(AP_DEVICES, sizeof(int), GFP_KERNEL);
+		reqcnt = kcalloc(AP_DEVICES, sizeof(u32), GFP_KERNEL);
 		if (!reqcnt)
 			return -ENOMEM;
 		zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES);
@@ -1480,7 +1482,7 @@
 	}
 	case Z90STAT_PERDEV_REQCNT: {
 		/* the old ioctl supports only 64 adapters */
-		int reqcnt[MAX_ZDEV_CARDIDS];
+		u32 reqcnt[MAX_ZDEV_CARDIDS];
 
 		zcrypt_perdev_reqcnt(reqcnt, MAX_ZDEV_CARDIDS);
 		if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt)))
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 9639938..5efcaa4 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5344,7 +5344,7 @@
 	}
 
 	use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) ||
-		    ((skb_len >= card->options.rx_sg_cb) &&
+		    (skb_len > card->options.rx_sg_cb &&
 		     !atomic_read(&card->force_alloc_skb) &&
 		     !IS_OSN(card));
 
@@ -5447,7 +5447,6 @@
 {
 	int work_done = 0;
 
-	WARN_ON_ONCE(!budget);
 	*done = false;
 
 	while (budget) {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 692bd26..9972d96 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1707,15 +1707,14 @@
 
 	QETH_CARD_TEXT(card, 2, "vniccsch");
 
-	/* do not change anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and enable/disable are supported */
 	if (!(card->options.vnicc.sup_chars & vnicc) ||
 	    !(card->options.vnicc.set_char_sup & vnicc))
 		return -EOPNOTSUPP;
 
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* set enable/disable command and store wanted characteristic */
 	if (state) {
 		cmd = IPA_VNICC_ENABLE;
@@ -1761,14 +1760,13 @@
 
 	QETH_CARD_TEXT(card, 2, "vniccgch");
 
-	/* do not get anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic is supported */
 	if (!(card->options.vnicc.sup_chars & vnicc))
 		return -EOPNOTSUPP;
 
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* if card is ready, query current VNICC state */
 	if (qeth_card_hw_is_reachable(card))
 		rc = qeth_l2_vnicc_query_chars(card);
@@ -1786,15 +1784,14 @@
 
 	QETH_CARD_TEXT(card, 2, "vniccsto");
 
-	/* do not change anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and set_timeout are supported */
 	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
 	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
 		return -EOPNOTSUPP;
 
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* do we need to do anything? */
 	if (card->options.vnicc.learning_timeout == timeout)
 		return rc;
@@ -1823,14 +1820,14 @@
 
 	QETH_CARD_TEXT(card, 2, "vniccgto");
 
-	/* do not get anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and get_timeout are supported */
 	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
 	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
 		return -EOPNOTSUPP;
+
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* if card is ready, get timeout. Otherwise, just return stored value */
 	*timeout = card->options.vnicc.learning_timeout;
 	if (qeth_card_hw_is_reachable(card))
diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c
index f68f4e1..e6037f9 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra30.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra30.c
@@ -36,7 +36,8 @@
     defined(CONFIG_ARCH_TEGRA_124_SOC) || \
     defined(CONFIG_ARCH_TEGRA_132_SOC) || \
     defined(CONFIG_ARCH_TEGRA_210_SOC) || \
-    defined(CONFIG_ARCH_TEGRA_186_SOC)
+    defined(CONFIG_ARCH_TEGRA_186_SOC) || \
+    defined(CONFIG_ARCH_TEGRA_194_SOC)
 static u32 tegra30_fuse_read_early(struct tegra_fuse *fuse, unsigned int offset)
 {
 	if (WARN_ON(!fuse->base))
diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c
index 97acc2b..de844b4 100644
--- a/drivers/spmi/spmi-pmic-arb.c
+++ b/drivers/spmi/spmi-pmic-arb.c
@@ -731,6 +731,7 @@
 	return 0;
 }
 
+static struct lock_class_key qpnpint_irq_lock_class, qpnpint_irq_request_class;
 
 static void qpnpint_irq_domain_map(struct spmi_pmic_arb *pmic_arb,
 				   struct irq_domain *domain, unsigned int virq,
@@ -746,6 +747,9 @@
 	else
 		handler = handle_level_irq;
 
+
+	irq_set_lockdep_class(virq, &qpnpint_irq_lock_class,
+			      &qpnpint_irq_request_class);
 	irq_domain_set_info(domain, virq, hwirq, &pmic_arb_irqchip, pmic_arb,
 			    handler, NULL, NULL);
 }
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index ad5479f..7d6ecc3 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -348,6 +348,12 @@
 	return ret;
 }
 
+static int tb_switch_nvm_no_read(void *priv, unsigned int offset, void *val,
+				 size_t bytes)
+{
+	return -EPERM;
+}
+
 static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val,
 			       size_t bytes)
 {
@@ -393,6 +399,7 @@
 		config.read_only = true;
 	} else {
 		config.name = "nvm_non_active";
+		config.reg_read = tb_switch_nvm_no_read;
 		config.reg_write = tb_switch_nvm_write;
 		config.root_only = true;
 	}
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 26bc05e..b7918f6 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -256,6 +256,7 @@
 		struct usb_host_interface *ifp, int num_ep,
 		unsigned char *buffer, int size)
 {
+	struct usb_device *udev = to_usb_device(ddev);
 	unsigned char *buffer0 = buffer;
 	struct usb_endpoint_descriptor *d;
 	struct usb_host_endpoint *endpoint;
@@ -297,6 +298,16 @@
 		goto skip_to_next_endpoint_or_interface_descriptor;
 	}
 
+	/* Ignore blacklisted endpoints */
+	if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) {
+		if (usb_endpoint_is_blacklisted(udev, ifp, d)) {
+			dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n",
+					cfgno, inum, asnum,
+					d->bEndpointAddress);
+			goto skip_to_next_endpoint_or_interface_descriptor;
+		}
+	}
+
 	endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints];
 	++ifp->desc.bNumEndpoints;
 
@@ -311,7 +322,7 @@
 	j = 255;
 	if (usb_endpoint_xfer_int(d)) {
 		i = 1;
-		switch (to_usb_device(ddev)->speed) {
+		switch (udev->speed) {
 		case USB_SPEED_SUPER_PLUS:
 		case USB_SPEED_SUPER:
 		case USB_SPEED_HIGH:
@@ -332,8 +343,7 @@
 			/*
 			 * This quirk fixes bIntervals reported in ms.
 			 */
-			if (to_usb_device(ddev)->quirks &
-				USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
+			if (udev->quirks & USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
 				n = clamp(fls(d->bInterval) + 3, i, j);
 				i = j = n;
 			}
@@ -341,8 +351,7 @@
 			 * This quirk fixes bIntervals reported in
 			 * linear microframes.
 			 */
-			if (to_usb_device(ddev)->quirks &
-				USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) {
+			if (udev->quirks & USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) {
 				n = clamp(fls(d->bInterval), i, j);
 				i = j = n;
 			}
@@ -359,7 +368,7 @@
 	} else if (usb_endpoint_xfer_isoc(d)) {
 		i = 1;
 		j = 16;
-		switch (to_usb_device(ddev)->speed) {
+		switch (udev->speed) {
 		case USB_SPEED_HIGH:
 			n = 7;		/* 8 ms = 2^(7-1) uframes */
 			break;
@@ -381,8 +390,7 @@
 	 * explicitly forbidden by the USB spec.  In an attempt to make
 	 * them usable, we will try treating them as Interrupt endpoints.
 	 */
-	if (to_usb_device(ddev)->speed == USB_SPEED_LOW &&
-			usb_endpoint_xfer_bulk(d)) {
+	if (udev->speed == USB_SPEED_LOW && usb_endpoint_xfer_bulk(d)) {
 		dev_warn(ddev, "config %d interface %d altsetting %d "
 		    "endpoint 0x%X is Bulk; changing to Interrupt\n",
 		    cfgno, inum, asnum, d->bEndpointAddress);
@@ -406,7 +414,7 @@
 
 	/* Find the highest legal maxpacket size for this endpoint */
 	i = 0;		/* additional transactions per microframe */
-	switch (to_usb_device(ddev)->speed) {
+	switch (udev->speed) {
 	case USB_SPEED_LOW:
 		maxpacket_maxes = low_speed_maxpacket_maxes;
 		break;
@@ -442,8 +450,7 @@
 	 * maxpacket sizes other than 512.  High speed HCDs may not
 	 * be able to handle that particular bug, so let's warn...
 	 */
-	if (to_usb_device(ddev)->speed == USB_SPEED_HIGH
-			&& usb_endpoint_xfer_bulk(d)) {
+	if (udev->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) {
 		if (maxp != 512)
 			dev_warn(ddev, "config %d interface %d altsetting %d "
 				"bulk endpoint 0x%X has invalid maxpacket %d\n",
@@ -452,7 +459,7 @@
 	}
 
 	/* Parse a possible SuperSpeed endpoint companion descriptor */
-	if (to_usb_device(ddev)->speed >= USB_SPEED_SUPER)
+	if (udev->speed >= USB_SPEED_SUPER)
 		usb_parse_ss_endpoint_companion(ddev, cfgno,
 				inum, asnum, endpoint, buffer, size);
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 3405b14..1d212f8 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -38,7 +38,9 @@
 #include "otg_whitelist.h"
 
 #define USB_VENDOR_GENESYS_LOGIC		0x05e3
+#define USB_VENDOR_SMSC				0x0424
 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
+#define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
 
 #define USB_TP_TRANSMISSION_DELAY	40	/* ns */
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
@@ -1217,11 +1219,6 @@
 #ifdef CONFIG_PM
 			udev->reset_resume = 1;
 #endif
-			/* Don't set the change_bits when the device
-			 * was powered off.
-			 */
-			if (test_bit(port1, hub->power_bits))
-				set_bit(port1, hub->change_bits);
 
 		} else {
 			/* The power session is gone; tell hub_wq */
@@ -1731,6 +1728,10 @@
 	kfree(hub->buffer);
 
 	pm_suspend_ignore_children(&intf->dev, false);
+
+	if (hub->quirk_disable_autosuspend)
+		usb_autopm_put_interface(intf);
+
 	kref_put(&hub->kref, hub_release);
 }
 
@@ -1863,6 +1864,11 @@
 	if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND)
 		hub->quirk_check_port_auto_suspend = 1;
 
+	if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) {
+		hub->quirk_disable_autosuspend = 1;
+		usb_autopm_get_interface(intf);
+	}
+
 	if (hub_configure(hub, &desc->endpoint[0].desc) >= 0)
 		return 0;
 
@@ -5599,6 +5605,10 @@
 }
 
 static const struct usb_device_id hub_id_table[] = {
+    { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS,
+      .idVendor = USB_VENDOR_SMSC,
+      .bInterfaceClass = USB_CLASS_HUB,
+      .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
     { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
 			| USB_DEVICE_ID_MATCH_INT_CLASS,
       .idVendor = USB_VENDOR_GENESYS_LOGIC,
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index a9e24e4..a97dd1b 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -61,6 +61,7 @@
 	unsigned		quiescing:1;
 	unsigned		disconnected:1;
 	unsigned		in_reset:1;
+	unsigned		quirk_disable_autosuspend:1;
 
 	unsigned		quirk_check_port_auto_suspend:1;
 
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6b64130..2b24336 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -354,6 +354,10 @@
 	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
 
+	/* Sound Devices USBPre2 */
+	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
+			USB_QUIRK_ENDPOINT_BLACKLIST },
+
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -445,6 +449,9 @@
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* novation SoundControl XL */
+	{ USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	{ }  /* terminating entry must be last */
 };
 
@@ -472,6 +479,39 @@
 	{ }  /* terminating entry must be last */
 };
 
+/*
+ * Entries for blacklisted endpoints that should be ignored when parsing
+ * configuration descriptors.
+ *
+ * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST.
+ */
+static const struct usb_device_id usb_endpoint_blacklist[] = {
+	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
+	{ }
+};
+
+bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+		struct usb_host_interface *intf,
+		struct usb_endpoint_descriptor *epd)
+{
+	const struct usb_device_id *id;
+	unsigned int address;
+
+	for (id = usb_endpoint_blacklist; id->match_flags; ++id) {
+		if (!usb_match_device(udev, id))
+			continue;
+
+		if (!usb_match_one_id_intf(udev, intf, id))
+			continue;
+
+		address = id->driver_info;
+		if (address == epd->bEndpointAddress)
+			return true;
+	}
+
+	return false;
+}
+
 static bool usb_match_any_interface(struct usb_device *udev,
 				    const struct usb_device_id *id)
 {
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index cf4783c..3ad0ee5 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -37,6 +37,9 @@
 extern void usb_detect_quirks(struct usb_device *udev);
 extern void usb_detect_interface_quirks(struct usb_device *udev);
 extern void usb_release_quirk_list(void);
+extern bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+		struct usb_host_interface *intf,
+		struct usb_endpoint_descriptor *epd);
 extern int usb_remove_device(struct usb_device *udev);
 
 extern int usb_get_device_descriptor(struct usb_device *dev,
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 88f7d6d..92ed32e 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1083,11 +1083,6 @@
 	else
 		packets = 1;	/* send one packet if length is zero. */
 
-	if (hs_ep->isochronous && length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
-		dev_err(hsotg->dev, "req length > maxpacket*mc\n");
-		return;
-	}
-
 	if (dir_in && index != 0)
 		if (hs_ep->isochronous)
 			epsize = DXEPTSIZ_MC(packets);
@@ -1391,6 +1386,13 @@
 	req->actual = 0;
 	req->status = -EINPROGRESS;
 
+	/* Don't queue ISOC request if length greater than mps*mc */
+	if (hs_ep->isochronous &&
+	    req->length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
+		dev_err(hs->dev, "req length > maxpacket*mc\n");
+		return -EINVAL;
+	}
+
 	/* In DDMA mode for ISOC's don't queue request if length greater
 	 * than descriptor limits.
 	 */
@@ -1632,6 +1634,7 @@
 	struct dwc2_hsotg_ep *ep0 = hsotg->eps_out[0];
 	struct dwc2_hsotg_ep *ep;
 	__le16 reply;
+	u16 status;
 	int ret;
 
 	dev_dbg(hsotg->dev, "%s: USB_REQ_GET_STATUS\n", __func__);
@@ -1643,11 +1646,10 @@
 
 	switch (ctrl->bRequestType & USB_RECIP_MASK) {
 	case USB_RECIP_DEVICE:
-		/*
-		 * bit 0 => self powered
-		 * bit 1 => remote wakeup
-		 */
-		reply = cpu_to_le16(0);
+		status = 1 << USB_DEVICE_SELF_POWERED;
+		status |= hsotg->remote_wakeup_allowed <<
+			  USB_DEVICE_REMOTE_WAKEUP;
+		reply = cpu_to_le16(status);
 		break;
 
 	case USB_RECIP_INTERFACE:
@@ -1758,7 +1760,10 @@
 	case USB_RECIP_DEVICE:
 		switch (wValue) {
 		case USB_DEVICE_REMOTE_WAKEUP:
-			hsotg->remote_wakeup_allowed = 1;
+			if (set)
+				hsotg->remote_wakeup_allowed = 1;
+			else
+				hsotg->remote_wakeup_allowed = 0;
 			break;
 
 		case USB_DEVICE_TEST_MODE:
@@ -1768,16 +1773,17 @@
 				return -EINVAL;
 
 			hsotg->test_mode = wIndex >> 8;
-			ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
-			if (ret) {
-				dev_err(hsotg->dev,
-					"%s: failed to send reply\n", __func__);
-				return ret;
-			}
 			break;
 		default:
 			return -ENOENT;
 		}
+
+		ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
+		if (ret) {
+			dev_err(hsotg->dev,
+				"%s: failed to send reply\n", __func__);
+			return ret;
+		}
 		break;
 
 	case USB_RECIP_ENDPOINT:
diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h
index e56beb9..4a13cea 100644
--- a/drivers/usb/dwc3/debug.h
+++ b/drivers/usb/dwc3/debug.h
@@ -256,86 +256,77 @@
 	u8 epnum = event->endpoint_number;
 	size_t len;
 	int status;
-	int ret;
 
-	ret = snprintf(str, size, "ep%d%s: ", epnum >> 1,
+	len = scnprintf(str, size, "ep%d%s: ", epnum >> 1,
 			(epnum & 1) ? "in" : "out");
-	if (ret < 0)
-		return "UNKNOWN";
 
 	status = event->status;
 
 	switch (event->endpoint_event) {
 	case DWC3_DEPEVT_XFERCOMPLETE:
-		len = strlen(str);
-		snprintf(str + len, size - len, "Transfer Complete (%c%c%c)",
+		len += scnprintf(str + len, size - len,
+				"Transfer Complete (%c%c%c)",
 				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
 				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
 				status & DEPEVT_STATUS_LST ? 'L' : 'l');
 
-		len = strlen(str);
-
 		if (epnum <= 1)
-			snprintf(str + len, size - len, " [%s]",
+			scnprintf(str + len, size - len, " [%s]",
 					dwc3_ep0_state_string(ep0state));
 		break;
 	case DWC3_DEPEVT_XFERINPROGRESS:
-		len = strlen(str);
-
-		snprintf(str + len, size - len, "Transfer In Progress [%d] (%c%c%c)",
+		scnprintf(str + len, size - len,
+				"Transfer In Progress [%d] (%c%c%c)",
 				event->parameters,
 				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
 				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
 				status & DEPEVT_STATUS_LST ? 'M' : 'm');
 		break;
 	case DWC3_DEPEVT_XFERNOTREADY:
-		len = strlen(str);
-
-		snprintf(str + len, size - len, "Transfer Not Ready [%d]%s",
+		len += scnprintf(str + len, size - len,
+				"Transfer Not Ready [%d]%s",
 				event->parameters,
 				status & DEPEVT_STATUS_TRANSFER_ACTIVE ?
 				" (Active)" : " (Not Active)");
 
-		len = strlen(str);
-
 		/* Control Endpoints */
 		if (epnum <= 1) {
 			int phase = DEPEVT_STATUS_CONTROL_PHASE(event->status);
 
 			switch (phase) {
 			case DEPEVT_STATUS_CONTROL_DATA:
-				snprintf(str + ret, size - ret,
+				scnprintf(str + len, size - len,
 						" [Data Phase]");
 				break;
 			case DEPEVT_STATUS_CONTROL_STATUS:
-				snprintf(str + ret, size - ret,
+				scnprintf(str + len, size - len,
 						" [Status Phase]");
 			}
 		}
 		break;
 	case DWC3_DEPEVT_RXTXFIFOEVT:
-		snprintf(str + ret, size - ret, "FIFO");
+		scnprintf(str + len, size - len, "FIFO");
 		break;
 	case DWC3_DEPEVT_STREAMEVT:
 		status = event->status;
 
 		switch (status) {
 		case DEPEVT_STREAMEVT_FOUND:
-			snprintf(str + ret, size - ret, " Stream %d Found",
+			scnprintf(str + len, size - len, " Stream %d Found",
 					event->parameters);
 			break;
 		case DEPEVT_STREAMEVT_NOTFOUND:
 		default:
-			snprintf(str + ret, size - ret, " Stream Not Found");
+			scnprintf(str + len, size - len, " Stream Not Found");
 			break;
 		}
 
 		break;
 	case DWC3_DEPEVT_EPCMDCMPLT:
-		snprintf(str + ret, size - ret, "Endpoint Command Complete");
+		scnprintf(str + len, size - len, "Endpoint Command Complete");
 		break;
 	default:
-		snprintf(str, size, "UNKNOWN");
+		scnprintf(str + len, size - len, "UNKNOWN");
 	}
 
 	return str;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 1b8014a..1b7d2f9 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2429,7 +2429,8 @@
 	if (event->status & DEPEVT_STATUS_SHORT && !chain)
 		return 1;
 
-	if (event->status & DEPEVT_STATUS_IOC)
+	if ((trb->ctrl & DWC3_TRB_CTRL_IOC) ||
+	    (trb->ctrl & DWC3_TRB_CTRL_LST))
 		return 1;
 
 	return 0;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 3b4f670..223f72d 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -437,12 +437,14 @@
 		val = CONFIG_USB_GADGET_VBUS_DRAW;
 	if (!val)
 		return 0;
-	switch (speed) {
-	case USB_SPEED_SUPER:
-		return DIV_ROUND_UP(val, 8);
-	default:
-		return DIV_ROUND_UP(val, 2);
-	}
+	if (speed < USB_SPEED_SUPER)
+		return min(val, 500U) / 2;
+	else
+		/*
+		 * USB 3.x supports up to 900mA, but since 900 isn't divisible
+		 * by 8 the integral division will effectively cap to 896mA.
+		 */
+		return min(val, 900U) / 8;
 }
 
 static int config_buf(struct usb_configuration *config,
@@ -854,6 +856,10 @@
 
 	/* when we return, be sure our power usage is valid */
 	power = c->MaxPower ? c->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW;
+	if (gadget->speed < USB_SPEED_SUPER)
+		power = min(power, 500U);
+	else
+		power = min(power, 900U);
 done:
 	usb_gadget_vbus_draw(gadget, power);
 	if (result >= 0 && cdev->delayed_status)
@@ -2280,7 +2286,7 @@
 {
 	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
 	struct usb_function		*f;
-	u16				maxpower;
+	unsigned			maxpower;
 
 	/* REVISIT:  should we have config level
 	 * suspend/resume callbacks?
@@ -2294,10 +2300,14 @@
 				f->resume(f);
 		}
 
-		maxpower = cdev->config->MaxPower;
+		maxpower = cdev->config->MaxPower ?
+			cdev->config->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW;
+		if (gadget->speed < USB_SPEED_SUPER)
+			maxpower = min(maxpower, 500U);
+		else
+			maxpower = min(maxpower, 900U);
 
-		usb_gadget_vbus_draw(gadget, maxpower ?
-			maxpower : CONFIG_USB_GADGET_VBUS_DRAW);
+		usb_gadget_vbus_draw(gadget, maxpower);
 	}
 
 	cdev->suspended = 0;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 6171d28..5719176 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1162,18 +1162,19 @@
 {
 	struct ffs_io_data *io_data = kiocb->private;
 	struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
+	unsigned long flags;
 	int value;
 
 	ENTER();
 
-	spin_lock_irq(&epfile->ffs->eps_lock);
+	spin_lock_irqsave(&epfile->ffs->eps_lock, flags);
 
 	if (likely(io_data && io_data->ep && io_data->req))
 		value = usb_ep_dequeue(io_data->ep, io_data->req);
 	else
 		value = -EINVAL;
 
-	spin_unlock_irq(&epfile->ffs->eps_lock);
+	spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags);
 
 	return value;
 }
diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c
index 6d956f1..e6d32c5 100644
--- a/drivers/usb/gadget/function/u_audio.c
+++ b/drivers/usb/gadget/function/u_audio.c
@@ -361,7 +361,7 @@
 	ep = audio_dev->out_ep;
 	prm = &uac->c_prm;
 	config_ep_by_speed(gadget, &audio_dev->func, ep);
-	req_len = prm->max_psize;
+	req_len = ep->maxpacket;
 
 	prm->ep_enabled = true;
 	usb_ep_enable(ep);
@@ -379,7 +379,7 @@
 			req->context = &prm->ureq[i];
 			req->length = req_len;
 			req->complete = u_audio_iso_complete;
-			req->buf = prm->rbuf + i * prm->max_psize;
+			req->buf = prm->rbuf + i * ep->maxpacket;
 		}
 
 		if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC))
@@ -430,9 +430,9 @@
 	uac->p_pktsize = min_t(unsigned int,
 				uac->p_framesize *
 					(params->p_srate / uac->p_interval),
-				prm->max_psize);
+				ep->maxpacket);
 
-	if (uac->p_pktsize < prm->max_psize)
+	if (uac->p_pktsize < ep->maxpacket)
 		uac->p_pktsize_residue = uac->p_framesize *
 			(params->p_srate % uac->p_interval);
 	else
@@ -457,7 +457,7 @@
 			req->context = &prm->ureq[i];
 			req->length = req_len;
 			req->complete = u_audio_iso_complete;
-			req->buf = prm->rbuf + i * prm->max_psize;
+			req->buf = prm->rbuf + i * ep->maxpacket;
 		}
 
 		if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC))
diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index f986e5c..8167d37 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -561,8 +561,10 @@
 	port->n_read = 0;
 	started = gs_start_rx(port);
 
-	/* unblock any pending writes into our circular buffer */
 	if (started) {
+		gs_start_tx(port);
+		/* Unblock any pending writes into our circular buffer, in case
+		 * we didn't in gs_start_tx() */
 		tty_wakeup(port->port.tty);
 	} else {
 		gs_free_requests(ep, head, &port->read_allocated);
diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c
index 29d8e5f..b1cfc82 100644
--- a/drivers/usb/gadget/udc/udc-xilinx.c
+++ b/drivers/usb/gadget/udc/udc-xilinx.c
@@ -1399,7 +1399,6 @@
 /**
  * xudc_stop - stops the device.
  * @gadget: pointer to the usb gadget structure
- * @driver: pointer to usb gadget driver structure
  *
  * Return: zero always
  */
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 7a3a29e..af92b25 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -55,6 +55,7 @@
 static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 				     u16 wLength)
 {
+	struct xhci_port_cap *port_cap = NULL;
 	int i, ssa_count;
 	u32 temp;
 	u16 desc_size, ssp_cap_size, ssa_size = 0;
@@ -64,16 +65,24 @@
 	ssp_cap_size = sizeof(usb_bos_descriptor) - desc_size;
 
 	/* does xhci support USB 3.1 Enhanced SuperSpeed */
-	if (xhci->usb3_rhub.min_rev >= 0x01) {
+	for (i = 0; i < xhci->num_port_caps; i++) {
+		if (xhci->port_caps[i].maj_rev == 0x03 &&
+		    xhci->port_caps[i].min_rev >= 0x01) {
+			usb3_1 = true;
+			port_cap = &xhci->port_caps[i];
+			break;
+		}
+	}
+
+	if (usb3_1) {
 		/* does xhci provide a PSI table for SSA speed attributes? */
-		if (xhci->usb3_rhub.psi_count) {
+		if (port_cap->psi_count) {
 			/* two SSA entries for each unique PSI ID, RX and TX */
-			ssa_count = xhci->usb3_rhub.psi_uid_count * 2;
+			ssa_count = port_cap->psi_uid_count * 2;
 			ssa_size = ssa_count * sizeof(u32);
 			ssp_cap_size -= 16; /* skip copying the default SSA */
 		}
 		desc_size += ssp_cap_size;
-		usb3_1 = true;
 	}
 	memcpy(buf, &usb_bos_descriptor, min(desc_size, wLength));
 
@@ -99,7 +108,7 @@
 	}
 
 	/* If PSI table exists, add the custom speed attributes from it */
-	if (usb3_1 && xhci->usb3_rhub.psi_count) {
+	if (usb3_1 && port_cap->psi_count) {
 		u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp;
 		int offset;
 
@@ -111,7 +120,7 @@
 
 		/* attribute count SSAC bits 4:0 and ID count SSIC bits 8:5 */
 		bm_attrib = (ssa_count - 1) & 0x1f;
-		bm_attrib |= (xhci->usb3_rhub.psi_uid_count - 1) << 5;
+		bm_attrib |= (port_cap->psi_uid_count - 1) << 5;
 		put_unaligned_le32(bm_attrib, &buf[ssp_cap_base + 4]);
 
 		if (wLength < desc_size + ssa_size)
@@ -124,8 +133,8 @@
 		 * USB 3.1 requires two SSA entries (RX and TX) for every link
 		 */
 		offset = desc_size;
-		for (i = 0; i < xhci->usb3_rhub.psi_count; i++) {
-			psi = xhci->usb3_rhub.psi[i];
+		for (i = 0; i < port_cap->psi_count; i++) {
+			psi = port_cap->psi[i];
 			psi &= ~USB_SSP_SUBLINK_SPEED_RSVD;
 			psi_exp = XHCI_EXT_PORT_PSIE(psi);
 			psi_mant = XHCI_EXT_PORT_PSIM(psi);
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 3b1388f..884c601 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1475,9 +1475,15 @@
 	/* Allow 3 retries for everything but isoc, set CErr = 3 */
 	if (!usb_endpoint_xfer_isoc(&ep->desc))
 		err_count = 3;
-	/* Some devices get this wrong */
-	if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH)
-		max_packet = 512;
+	/* HS bulk max packet should be 512, FS bulk supports 8, 16, 32 or 64 */
+	if (usb_endpoint_xfer_bulk(&ep->desc)) {
+		if (udev->speed == USB_SPEED_HIGH)
+			max_packet = 512;
+		if (udev->speed == USB_SPEED_FULL) {
+			max_packet = rounddown_pow_of_two(max_packet);
+			max_packet = clamp_val(max_packet, 8, 64);
+		}
+	}
 	/* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */
 	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		avg_trb_len = 8;
@@ -1909,17 +1915,17 @@
 	xhci->usb3_rhub.num_ports = 0;
 	xhci->num_active_eps = 0;
 	kfree(xhci->usb2_rhub.ports);
-	kfree(xhci->usb2_rhub.psi);
 	kfree(xhci->usb3_rhub.ports);
-	kfree(xhci->usb3_rhub.psi);
 	kfree(xhci->hw_ports);
 	kfree(xhci->rh_bw);
 	kfree(xhci->ext_caps);
+	for (i = 0; i < xhci->num_port_caps; i++)
+		kfree(xhci->port_caps[i].psi);
+	kfree(xhci->port_caps);
+	xhci->num_port_caps = 0;
 
 	xhci->usb2_rhub.ports = NULL;
-	xhci->usb2_rhub.psi = NULL;
 	xhci->usb3_rhub.ports = NULL;
-	xhci->usb3_rhub.psi = NULL;
 	xhci->hw_ports = NULL;
 	xhci->rh_bw = NULL;
 	xhci->ext_caps = NULL;
@@ -2120,6 +2126,7 @@
 	u8 major_revision, minor_revision;
 	struct xhci_hub *rhub;
 	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
+	struct xhci_port_cap *port_cap;
 
 	temp = readl(addr);
 	major_revision = XHCI_EXT_PORT_MAJOR(temp);
@@ -2154,31 +2161,39 @@
 		/* WTF? "Valid values are ‘1’ to MaxPorts" */
 		return;
 
-	rhub->psi_count = XHCI_EXT_PORT_PSIC(temp);
-	if (rhub->psi_count) {
-		rhub->psi = kcalloc_node(rhub->psi_count, sizeof(*rhub->psi),
-				    GFP_KERNEL, dev_to_node(dev));
-		if (!rhub->psi)
-			rhub->psi_count = 0;
+	port_cap = &xhci->port_caps[xhci->num_port_caps++];
+	if (xhci->num_port_caps > max_caps)
+		return;
 
-		rhub->psi_uid_count++;
-		for (i = 0; i < rhub->psi_count; i++) {
-			rhub->psi[i] = readl(addr + 4 + i);
+	port_cap->maj_rev = major_revision;
+	port_cap->min_rev = minor_revision;
+	port_cap->psi_count = XHCI_EXT_PORT_PSIC(temp);
+
+	if (port_cap->psi_count) {
+		port_cap->psi = kcalloc_node(port_cap->psi_count,
+					     sizeof(*port_cap->psi),
+					     GFP_KERNEL, dev_to_node(dev));
+		if (!port_cap->psi)
+			port_cap->psi_count = 0;
+
+		port_cap->psi_uid_count++;
+		for (i = 0; i < port_cap->psi_count; i++) {
+			port_cap->psi[i] = readl(addr + 4 + i);
 
 			/* count unique ID values, two consecutive entries can
 			 * have the same ID if link is assymetric
 			 */
-			if (i && (XHCI_EXT_PORT_PSIV(rhub->psi[i]) !=
-				  XHCI_EXT_PORT_PSIV(rhub->psi[i - 1])))
-				rhub->psi_uid_count++;
+			if (i && (XHCI_EXT_PORT_PSIV(port_cap->psi[i]) !=
+				  XHCI_EXT_PORT_PSIV(port_cap->psi[i - 1])))
+				port_cap->psi_uid_count++;
 
 			xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n",
-				  XHCI_EXT_PORT_PSIV(rhub->psi[i]),
-				  XHCI_EXT_PORT_PSIE(rhub->psi[i]),
-				  XHCI_EXT_PORT_PLT(rhub->psi[i]),
-				  XHCI_EXT_PORT_PFD(rhub->psi[i]),
-				  XHCI_EXT_PORT_LP(rhub->psi[i]),
-				  XHCI_EXT_PORT_PSIM(rhub->psi[i]));
+				  XHCI_EXT_PORT_PSIV(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PSIE(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PLT(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PFD(port_cap->psi[i]),
+				  XHCI_EXT_PORT_LP(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PSIM(port_cap->psi[i]));
 		}
 	}
 	/* cache usb2 port capabilities */
@@ -2213,6 +2228,7 @@
 			continue;
 		}
 		hw_port->rhub = rhub;
+		hw_port->port_cap = port_cap;
 		rhub->num_ports++;
 	}
 	/* FIXME: Should we disable ports not in the Extended Capabilities? */
@@ -2303,6 +2319,11 @@
 	if (!xhci->ext_caps)
 		return -ENOMEM;
 
+	xhci->port_caps = kcalloc_node(cap_count, sizeof(*xhci->port_caps),
+				flags, dev_to_node(dev));
+	if (!xhci->port_caps)
+		return -ENOMEM;
+
 	offset = cap_start;
 
 	while (offset) {
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 4917c5b..5e9b537 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -49,6 +49,7 @@
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI		0x15ec
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI		0x15f0
 #define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI		0x8a13
+#define PCI_DEVICE_ID_INTEL_CML_XHCI			0xa3af
 
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
@@ -187,7 +188,8 @@
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
-		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) {
+		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) {
 		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
@@ -302,6 +304,9 @@
 	if (!usb_hcd_is_primary_hcd(hcd))
 		return 0;
 
+	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+		xhci_pme_acpi_rtd3_enable(pdev);
+
 	xhci_dbg(xhci, "Got SBRN %u\n", (unsigned int) xhci->sbrn);
 
 	/* Find any debug ports */
@@ -359,9 +364,6 @@
 			HCC_MAX_PSA(xhci->hcc_params) >= 4)
 		xhci->shared_hcd->can_do_streams = 1;
 
-	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
-		xhci_pme_acpi_rtd3_enable(dev);
-
 	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
 	pm_runtime_put_noidle(&dev->dev);
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 13d8838..3ecee10 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1702,12 +1702,20 @@
  * Intel Lynx Point LP xHCI host.
  */
 #define	XHCI_MAX_REXIT_TIMEOUT_MS	20
+struct xhci_port_cap {
+	u32			*psi;	/* array of protocol speed ID entries */
+	u8			psi_count;
+	u8			psi_uid_count;
+	u8			maj_rev;
+	u8			min_rev;
+};
 
 struct xhci_port {
 	__le32 __iomem		*addr;
 	int			hw_portnum;
 	int			hcd_portnum;
 	struct xhci_hub		*rhub;
+	struct xhci_port_cap	*port_cap;
 };
 
 struct xhci_hub {
@@ -1719,9 +1727,6 @@
 	/* supported prococol extended capabiliy values */
 	u8			maj_rev;
 	u8			min_rev;
-	u32			*psi;	/* array of protocol speed ID entries */
-	u8			psi_count;
-	u8			psi_uid_count;
 };
 
 /* There is one xhci_hcd structure per controller */
@@ -1880,6 +1885,9 @@
 	/* cached usb2 extened protocol capabilites */
 	u32                     *ext_caps;
 	unsigned int            num_ext_caps;
+	/* cached extended protocol port capabilities */
+	struct xhci_port_cap	*port_caps;
+	unsigned int		num_port_caps;
 	/* Compliance Mode Recovery Data */
 	struct timer_list	comp_mode_recovery_timer;
 	u32			port_status_u0;
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index dce44fb..dce2030 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -33,6 +33,14 @@
 #define USB_DEVICE_ID_CODEMERCS_IOWPV2	0x1512
 /* full speed iowarrior */
 #define USB_DEVICE_ID_CODEMERCS_IOW56	0x1503
+/* fuller speed iowarrior */
+#define USB_DEVICE_ID_CODEMERCS_IOW28	0x1504
+#define USB_DEVICE_ID_CODEMERCS_IOW28L	0x1505
+#define USB_DEVICE_ID_CODEMERCS_IOW100	0x1506
+
+/* OEMed devices */
+#define USB_DEVICE_ID_CODEMERCS_IOW24SAG	0x158a
+#define USB_DEVICE_ID_CODEMERCS_IOW56AM		0x158b
 
 /* Get a minor range for your devices from the usb maintainer */
 #ifdef CONFIG_USB_DYNAMIC_MINORS
@@ -133,6 +141,11 @@
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV1)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV2)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW100)},
 	{}			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, iowarrior_ids);
@@ -357,6 +370,7 @@
 	}
 	switch (dev->product_id) {
 	case USB_DEVICE_ID_CODEMERCS_IOW24:
+	case USB_DEVICE_ID_CODEMERCS_IOW24SAG:
 	case USB_DEVICE_ID_CODEMERCS_IOWPV1:
 	case USB_DEVICE_ID_CODEMERCS_IOWPV2:
 	case USB_DEVICE_ID_CODEMERCS_IOW40:
@@ -371,6 +385,10 @@
 		goto exit;
 		break;
 	case USB_DEVICE_ID_CODEMERCS_IOW56:
+	case USB_DEVICE_ID_CODEMERCS_IOW56AM:
+	case USB_DEVICE_ID_CODEMERCS_IOW28:
+	case USB_DEVICE_ID_CODEMERCS_IOW28L:
+	case USB_DEVICE_ID_CODEMERCS_IOW100:
 		/* The IOW56 uses asynchronous IO and more urbs */
 		if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) {
 			/* Wait until we are below the limit for submitted urbs */
@@ -493,6 +511,7 @@
 	switch (cmd) {
 	case IOW_WRITE:
 		if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 ||
+		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24SAG ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV1 ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV2 ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW40) {
@@ -767,7 +786,11 @@
 		goto error;
 	}
 
-	if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+	if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)) {
 		res = usb_find_last_int_out_endpoint(iface_desc,
 				&dev->int_out_endpoint);
 		if (res) {
@@ -780,7 +803,11 @@
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
-	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56))
+	    ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)))
 		/* IOWarrior56 has wMaxPacketSize different from report size */
 		dev->report_size = 7;
 
diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c
index 037e8ee..6153cc3 100644
--- a/drivers/usb/phy/phy-tegra-usb.c
+++ b/drivers/usb/phy/phy-tegra-usb.c
@@ -969,6 +969,10 @@
 		return  -ENXIO;
 	}
 
+	/*
+	 * Note that UTMI pad registers are shared by all PHYs, therefore
+	 * devm_platform_ioremap_resource() can't be used here.
+	 */
 	tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start,
 					   resource_size(res));
 	if (!tegra_phy->pad_regs) {
@@ -1087,6 +1091,10 @@
 		return  -ENXIO;
 	}
 
+	/*
+	 * Note that PHY and USB controller are using shared registers,
+	 * therefore devm_platform_ioremap_resource() can't be used here.
+	 */
 	tegra_phy->regs = devm_ioremap(&pdev->dev, res->start,
 				       resource_size(res));
 	if (!tegra_phy->regs) {
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index d3f420f..c5ecdcd 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -205,6 +205,16 @@
 			16 * speed - 16 * CH341_CLKRATE / (clk_div * (div + 1)))
 		div++;
 
+	/*
+	 * Prefer lower base clock (fact = 0) if even divisor.
+	 *
+	 * Note that this makes the receiver more tolerant to errors.
+	 */
+	if (fact == 1 && div % 2 == 0) {
+		div /= 2;
+		fact = 0;
+	}
+
 	return (0x100 - div) << 8 | fact << 2 | ps;
 }
 
diff --git a/drivers/usb/serial/ir-usb.c b/drivers/usb/serial/ir-usb.c
index 79d0586..172261a 100644
--- a/drivers/usb/serial/ir-usb.c
+++ b/drivers/usb/serial/ir-usb.c
@@ -448,7 +448,7 @@
 			usb_sndbulkpipe(udev, port->bulk_out_endpointAddress),
 			transfer_buffer, 1, &actual_length, 5000);
 	if (ret || actual_length != 1) {
-		if (actual_length != 1)
+		if (!ret)
 			ret = -EIO;
 		dev_err(&port->dev, "failed to change line speed: %d\n", ret);
 	}
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 95bba3b..3670fda 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -45,6 +45,7 @@
 	struct scsi_cmnd *cmnd[MAX_CMNDS];
 	spinlock_t lock;
 	struct work_struct work;
+	struct work_struct scan_work;      /* for async scanning */
 };
 
 enum {
@@ -114,6 +115,17 @@
 	spin_unlock_irqrestore(&devinfo->lock, flags);
 }
 
+static void uas_scan_work(struct work_struct *work)
+{
+	struct uas_dev_info *devinfo =
+		container_of(work, struct uas_dev_info, scan_work);
+	struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf);
+
+	dev_dbg(&devinfo->intf->dev, "starting scan\n");
+	scsi_scan_host(shost);
+	dev_dbg(&devinfo->intf->dev, "scan complete\n");
+}
+
 static void uas_add_work(struct uas_cmd_info *cmdinfo)
 {
 	struct scsi_pointer *scp = (void *)cmdinfo;
@@ -982,6 +994,7 @@
 	init_usb_anchor(&devinfo->data_urbs);
 	spin_lock_init(&devinfo->lock);
 	INIT_WORK(&devinfo->work, uas_do_work);
+	INIT_WORK(&devinfo->scan_work, uas_scan_work);
 
 	result = uas_configure_endpoints(devinfo);
 	if (result)
@@ -998,7 +1011,9 @@
 	if (result)
 		goto free_streams;
 
-	scsi_scan_host(shost);
+	/* Submit the delayed_work for SCSI-device scanning */
+	schedule_work(&devinfo->scan_work);
+
 	return result;
 
 free_streams:
@@ -1166,6 +1181,12 @@
 	usb_kill_anchored_urbs(&devinfo->data_urbs);
 	uas_zap_pending(devinfo, DID_NO_CONNECT);
 
+	/*
+	 * Prevent SCSI scanning (if it hasn't started yet)
+	 * or wait for the SCSI-scanning routine to stop.
+	 */
+	cancel_work_sync(&devinfo->scan_work);
+
 	scsi_remove_host(shost);
 	uas_free_streams(devinfo);
 	scsi_host_put(shost);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7fa9bb7..89422aa 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3164,6 +3164,7 @@
 	/* do not make disk changes in broken FS or nologreplay is given */
 	if (btrfs_super_log_root(disk_super) != 0 &&
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
+		btrfs_info(fs_info, "start tree-log replay");
 		ret = btrfs_replay_log(fs_info, fs_devices);
 		if (ret) {
 			err = ret;
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 6f417ff..bd6229f 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -237,6 +237,17 @@
 	struct extent_map *merge = NULL;
 	struct rb_node *rb;
 
+	/*
+	 * We can't modify an extent map that is in the tree and that is being
+	 * used by another task, as it can cause that other task to see it in
+	 * inconsistent state during the merging. We always have 1 reference for
+	 * the tree and 1 for this task (which is unpinning the extent map or
+	 * clearing the logging flag), so anything > 2 means it's being used by
+	 * other tasks too.
+	 */
+	if (refcount_read(&em->refs) > 2)
+		return;
+
 	if (em->start != 0) {
 		rb = rb_prev(&em->rb_node);
 		if (rb)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5b3ec93..36deef6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4085,6 +4085,8 @@
 	u64 bytes_deleted = 0;
 	bool be_nice = false;
 	bool should_throttle = false;
+	const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize);
+	struct extent_state *cached_state = NULL;
 
 	BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);
 
@@ -4101,6 +4103,9 @@
 		return -ENOMEM;
 	path->reada = READA_BACK;
 
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+			 &cached_state);
+
 	/*
 	 * We want to drop from the next block forward in case this new size is
 	 * not block aligned since we will be keeping the last block of the
@@ -4137,7 +4142,6 @@
 		goto out;
 	}
 
-	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
 		goto out;
@@ -4289,7 +4293,6 @@
 		     root == fs_info->tree_root)) {
 			struct btrfs_ref ref = { 0 };
 
-			btrfs_set_path_blocking(path);
 			bytes_deleted += extent_num_bytes;
 
 			btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF,
@@ -4367,6 +4370,9 @@
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
 	}
 
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+			     &cached_state);
+
 	btrfs_free_path(path);
 	return ret;
 }
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index b57f361..454a101 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -744,6 +744,7 @@
 		 */
 		be = add_block_entry(fs_info, bytenr, num_bytes, ref_root);
 		if (IS_ERR(be)) {
+			kfree(ref);
 			kfree(ra);
 			ret = PTR_ERR(be);
 			goto out;
@@ -757,6 +758,8 @@
 			"re-allocated a block that still has references to it!");
 			dump_block_entry(fs_info, be);
 			dump_ref_action(fs_info, ra);
+			kfree(ref);
+			kfree(ra);
 			goto out_unlock;
 		}
 
@@ -819,6 +822,7 @@
 "dropping a ref for a existing root that doesn't have a ref on the block");
 				dump_block_entry(fs_info, be);
 				dump_ref_action(fs_info, ra);
+				kfree(ref);
 				kfree(ra);
 				goto out_unlock;
 			}
@@ -834,6 +838,7 @@
 "attempting to add another ref for an existing ref on a tree block");
 			dump_block_entry(fs_info, be);
 			dump_ref_action(fs_info, ra);
+			kfree(ref);
 			kfree(ra);
 			goto out_unlock;
 		}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0616a54..67c6385 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1834,6 +1834,8 @@
 		}
 
 		if (btrfs_super_log_root(fs_info->super_copy) != 0) {
+			btrfs_warn(fs_info,
+		"mount required to replay tree-log, cannot remount read-write");
 			ret = -EINVAL;
 			goto restore;
 		}
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 7436422..3c10e78 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -901,6 +901,12 @@
 
 static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs)
 {
+	if (fs_devs->devinfo_kobj) {
+		kobject_del(fs_devs->devinfo_kobj);
+		kobject_put(fs_devs->devinfo_kobj);
+		fs_devs->devinfo_kobj = NULL;
+	}
+
 	if (fs_devs->devices_kobj) {
 		kobject_del(fs_devs->devices_kobj);
 		kobject_put(fs_devs->devices_kobj);
@@ -1289,7 +1295,7 @@
 
 		init_completion(&dev->kobj_unregister);
 		error = kobject_init_and_add(&dev->devid_kobj, &devid_ktype,
-					     fs_devices->devices_kobj, "%llu",
+					     fs_devices->devinfo_kobj, "%llu",
 					     dev->devid);
 		if (error) {
 			kobject_put(&dev->devid_kobj);
@@ -1369,6 +1375,15 @@
 		return -ENOMEM;
 	}
 
+	fs_devs->devinfo_kobj = kobject_create_and_add("devinfo",
+						       &fs_devs->fsid_kobj);
+	if (!fs_devs->devinfo_kobj) {
+		btrfs_err(fs_devs->fs_info,
+			  "failed to init sysfs devinfo kobject");
+		btrfs_sysfs_remove_fsid(fs_devs);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 409f481..f01552a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -258,6 +258,7 @@
 	/* sysfs kobjects */
 	struct kobject fsid_kobj;
 	struct kobject *devices_kobj;
+	struct kobject *devinfo_kobj;
 	struct completion kobj_unregister;
 };
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c3b8e8e..7e0190b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1418,6 +1418,7 @@
 	struct ceph_cap_flush *prealloc_cf;
 	ssize_t count, written = 0;
 	int err, want, got;
+	bool direct_lock = false;
 	loff_t pos;
 	loff_t limit = max(i_size_read(inode), fsc->max_file_size);
 
@@ -1428,8 +1429,11 @@
 	if (!prealloc_cf)
 		return -ENOMEM;
 
+	if ((iocb->ki_flags & (IOCB_DIRECT | IOCB_APPEND)) == IOCB_DIRECT)
+		direct_lock = true;
+
 retry_snap:
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (direct_lock)
 		ceph_start_io_direct(inode);
 	else
 		ceph_start_io_write(inode);
@@ -1519,14 +1523,15 @@
 
 		/* we might need to revert back to that point */
 		data = *from;
-		if (iocb->ki_flags & IOCB_DIRECT) {
+		if (iocb->ki_flags & IOCB_DIRECT)
 			written = ceph_direct_read_write(iocb, &data, snapc,
 							 &prealloc_cf);
-			ceph_end_io_direct(inode);
-		} else {
+		else
 			written = ceph_sync_write(iocb, &data, pos, snapc);
+		if (direct_lock)
+			ceph_end_io_direct(inode);
+		else
 			ceph_end_io_write(inode);
-		}
 		if (written > 0)
 			iov_iter_advance(from, written);
 		ceph_put_snap_context(snapc);
@@ -1577,7 +1582,7 @@
 
 	goto out_unlocked;
 out:
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (direct_lock)
 		ceph_end_io_direct(inode);
 	else
 		ceph_end_io_write(inode);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 1d9f083..c7f1506 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -203,6 +203,26 @@
 };
 
 /*
+ * Remove adjacent slashes and then the trailing slash, unless it is
+ * the only remaining character.
+ *
+ * E.g. "//dir1////dir2///" --> "/dir1/dir2", "///" --> "/".
+ */
+static void canonicalize_path(char *path)
+{
+	int i, j = 0;
+
+	for (i = 0; path[i] != '\0'; i++) {
+		if (path[i] != '/' || j < 1 || path[j - 1] != '/')
+			path[j++] = path[i];
+	}
+
+	if (j > 1 && path[j - 1] == '/')
+		j--;
+	path[j] = '\0';
+}
+
+/*
  * Parse the source parameter.  Distinguish the server list from the path.
  *
  * The source will look like:
@@ -224,15 +244,16 @@
 
 	dev_name_end = strchr(dev_name, '/');
 	if (dev_name_end) {
-		kfree(fsopt->server_path);
-
 		/*
 		 * The server_path will include the whole chars from userland
 		 * including the leading '/'.
 		 */
+		kfree(fsopt->server_path);
 		fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
 		if (!fsopt->server_path)
 			return -ENOMEM;
+
+		canonicalize_path(fsopt->server_path);
 	} else {
 		dev_name_end = dev_name + strlen(dev_name);
 	}
@@ -456,73 +477,6 @@
 	return strcmp(s1, s2);
 }
 
-/**
- * path_remove_extra_slash - Remove the extra slashes in the server path
- * @server_path: the server path and could be NULL
- *
- * Return NULL if the path is NULL or only consists of "/", or a string
- * without any extra slashes including the leading slash(es) and the
- * slash(es) at the end of the server path, such as:
- * "//dir1////dir2///" --> "dir1/dir2"
- */
-static char *path_remove_extra_slash(const char *server_path)
-{
-	const char *path = server_path;
-	const char *cur, *end;
-	char *buf, *p;
-	int len;
-
-	/* if the server path is omitted */
-	if (!path)
-		return NULL;
-
-	/* remove all the leading slashes */
-	while (*path == '/')
-		path++;
-
-	/* if the server path only consists of slashes */
-	if (*path == '\0')
-		return NULL;
-
-	len = strlen(path);
-
-	buf = kmalloc(len + 1, GFP_KERNEL);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
-
-	end = path + len;
-	p = buf;
-	do {
-		cur = strchr(path, '/');
-		if (!cur)
-			cur = end;
-
-		len = cur - path;
-
-		/* including one '/' */
-		if (cur != end)
-			len += 1;
-
-		memcpy(p, path, len);
-		p += len;
-
-		while (cur <= end && *cur == '/')
-			cur++;
-		path = cur;
-	} while (path < end);
-
-	*p = '\0';
-
-	/*
-	 * remove the last slash if there has and just to make sure that
-	 * we will get something like "dir1/dir2"
-	 */
-	if (*(--p) == '/')
-		*p = '\0';
-
-	return buf;
-}
-
 static int compare_mount_options(struct ceph_mount_options *new_fsopt,
 				 struct ceph_options *new_opt,
 				 struct ceph_fs_client *fsc)
@@ -530,7 +484,6 @@
 	struct ceph_mount_options *fsopt1 = new_fsopt;
 	struct ceph_mount_options *fsopt2 = fsc->mount_options;
 	int ofs = offsetof(struct ceph_mount_options, snapdir_name);
-	char *p1, *p2;
 	int ret;
 
 	ret = memcmp(fsopt1, fsopt2, ofs);
@@ -540,21 +493,12 @@
 	ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name);
 	if (ret)
 		return ret;
+
 	ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace);
 	if (ret)
 		return ret;
 
-	p1 = path_remove_extra_slash(fsopt1->server_path);
-	if (IS_ERR(p1))
-		return PTR_ERR(p1);
-	p2 = path_remove_extra_slash(fsopt2->server_path);
-	if (IS_ERR(p2)) {
-		kfree(p1);
-		return PTR_ERR(p2);
-	}
-	ret = strcmp_null(p1, p2);
-	kfree(p1);
-	kfree(p2);
+	ret = strcmp_null(fsopt1->server_path, fsopt2->server_path);
 	if (ret)
 		return ret;
 
@@ -957,7 +901,9 @@
 	mutex_lock(&fsc->client->mount_mutex);
 
 	if (!fsc->sb->s_root) {
-		const char *path, *p;
+		const char *path = fsc->mount_options->server_path ?
+				     fsc->mount_options->server_path + 1 : "";
+
 		err = __ceph_open_session(fsc->client, started);
 		if (err < 0)
 			goto out;
@@ -969,22 +915,11 @@
 				goto out;
 		}
 
-		p = path_remove_extra_slash(fsc->mount_options->server_path);
-		if (IS_ERR(p)) {
-			err = PTR_ERR(p);
-			goto out;
-		}
-		/* if the server path is omitted or just consists of '/' */
-		if (!p)
-			path = "";
-		else
-			path = p;
 		dout("mount opening path '%s'\n", path);
 
 		ceph_fs_debugfs_init(fsc);
 
 		root = open_root_dentry(fsc, path, started);
-		kfree(p);
 		if (IS_ERR(root)) {
 			err = PTR_ERR(root);
 			goto out;
@@ -1097,10 +1032,6 @@
 	if (!fc->source)
 		return invalfc(fc, "No source");
 
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
-	fc->sb_flags |= SB_POSIXACL;
-#endif
-
 	/* create client (which we may/may not use) */
 	fsc = create_fs_client(pctx->opts, pctx->copts);
 	pctx->opts = NULL;
@@ -1223,6 +1154,10 @@
 	fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
 	fsopt->congestion_kb = default_congestion_kb();
 
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	fc->sb_flags |= SB_POSIXACL;
+#endif
+
 	fc->fs_private = pctx;
 	fc->ops = &ceph_context_ops;
 	return 0;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1e456a9..037cdfb 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -91,7 +91,7 @@
 
 	char *snapdir_name;   /* default ".snap" */
 	char *mds_namespace;  /* default NULL */
-	char *server_path;    /* default  "/" */
+	char *server_path;    /* default NULL (means "/") */
 	char *fscache_uniq;   /* default NULL */
 };
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 440828a..716574a 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -601,7 +601,7 @@
 			((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
 		*pmode |= (S_IXUGO & (*pbits_to_set));
 
-	cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode);
+	cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode);
 	return;
 }
 
@@ -630,7 +630,7 @@
 	if (mode & S_IXUGO)
 		*pace_flags |= SET_FILE_EXEC_RIGHTS;
 
-	cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n",
+	cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n",
 		 mode, *pace_flags);
 	return;
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index febab27..46ebaf3 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -414,7 +414,7 @@
 		seq_puts(s, "ntlm");
 		break;
 	case Kerberos:
-		seq_printf(s, "krb5,cruid=%u", from_kuid_munged(&init_user_ns,ses->cred_uid));
+		seq_puts(s, "krb5");
 		break;
 	case RawNTLMSSP:
 		seq_puts(s, "ntlmssp");
@@ -427,6 +427,10 @@
 
 	if (ses->sign)
 		seq_puts(s, "i");
+
+	if (ses->sectype == Kerberos)
+		seq_printf(s, ",cruid=%u",
+			   from_kuid_munged(&init_user_ns, ses->cred_uid));
 }
 
 static void
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a941ac7..4804d1d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -4151,7 +4151,7 @@
 	cifs_sb->mnt_gid = pvolume_info->linux_gid;
 	cifs_sb->mnt_file_mode = pvolume_info->file_mode;
 	cifs_sb->mnt_dir_mode = pvolume_info->dir_mode;
-	cifs_dbg(FYI, "file mode: 0x%hx  dir mode: 0x%hx\n",
+	cifs_dbg(FYI, "file mode: %04ho  dir mode: %04ho\n",
 		 cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode);
 
 	cifs_sb->actimeo = pvolume_info->actimeo;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9ba623b..b5e6635 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1648,7 +1648,7 @@
 	struct TCP_Server_Info *server;
 	char *full_path;
 
-	cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n",
+	cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n",
 		 mode, inode);
 
 	cifs_sb = CIFS_SB(inode->i_sb);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index baa825f..e47190c 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1116,7 +1116,8 @@
 	void *data[1];
 	struct smb2_file_full_ea_info *ea = NULL;
 	struct kvec close_iov[1];
-	int rc;
+	struct smb2_query_info_rsp *rsp;
+	int rc, used_len = 0;
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
@@ -1139,6 +1140,38 @@
 							     cifs_sb);
 			if (rc == -ENODATA)
 				goto sea_exit;
+		} else {
+			/* If we are adding a attribute we should first check
+			 * if there will be enough space available to store
+			 * the new EA. If not we should not add it since we
+			 * would not be able to even read the EAs back.
+			 */
+			rc = smb2_query_info_compound(xid, tcon, utf16_path,
+				      FILE_READ_EA,
+				      FILE_FULL_EA_INFORMATION,
+				      SMB2_O_INFO_FILE,
+				      CIFSMaxBufSize -
+				      MAX_SMB2_CREATE_RESPONSE_SIZE -
+				      MAX_SMB2_CLOSE_RESPONSE_SIZE,
+				      &rsp_iov[1], &resp_buftype[1], cifs_sb);
+			if (rc == 0) {
+				rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
+				used_len = le32_to_cpu(rsp->OutputBufferLength);
+			}
+			free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+			resp_buftype[1] = CIFS_NO_BUFFER;
+			memset(&rsp_iov[1], 0, sizeof(rsp_iov[1]));
+			rc = 0;
+
+			/* Use a fudge factor of 256 bytes in case we collide
+			 * with a different set_EAs command.
+			 */
+			if(CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE -
+			   MAX_SMB2_CLOSE_RESPONSE_SIZE - 256 <
+			   used_len + ea_name_len + ea_value_len + 1) {
+				rc = -ENOSPC;
+				goto sea_exit;
+			}
 		}
 	}
 
@@ -4795,6 +4828,7 @@
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.enum_snapshots = smb3_enum_snapshots,
+	.notify = smb3_notify,
 	.get_dfs_refer = smb2_get_dfs_refer,
 	.select_sectype = smb2_select_sectype,
 #ifdef CONFIG_CIFS_XATTR
diff --git a/fs/dax.c b/fs/dax.c
index 1f1f020..35da144 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -937,12 +937,11 @@
  * on persistent storage prior to completion of the operation.
  */
 int dax_writeback_mapping_range(struct address_space *mapping,
-		struct block_device *bdev, struct writeback_control *wbc)
+		struct dax_device *dax_dev, struct writeback_control *wbc)
 {
 	XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT);
 	struct inode *inode = mapping->host;
 	pgoff_t end_index = wbc->range_end >> PAGE_SHIFT;
-	struct dax_device *dax_dev;
 	void *entry;
 	int ret = 0;
 	unsigned int scanned = 0;
@@ -953,10 +952,6 @@
 	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
 		return 0;
 
-	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
-	if (!dax_dev)
-		return -EIO;
-
 	trace_dax_writeback_range(inode, xas.xa_index, end_index);
 
 	tag_pages_for_writeback(mapping, xas.xa_index, end_index);
@@ -977,7 +972,6 @@
 		xas_lock_irq(&xas);
 	}
 	xas_unlock_irq(&xas);
-	put_dax(dax_dev);
 	trace_dax_writeback_range_done(inode, xas.xa_index, end_index);
 	return ret;
 }
@@ -1207,6 +1201,9 @@
 		lockdep_assert_held(&inode->i_rwsem);
 	}
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		flags |= IOMAP_NOWAIT;
+
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index db1ef14..2c449ae 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -311,8 +311,10 @@
 	struct extent_crypt_result ecr;
 	int rc = 0;
 
-	BUG_ON(!crypt_stat || !crypt_stat->tfm
-	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
+	if (!crypt_stat || !crypt_stat->tfm
+	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+		return -EINVAL;
+
 	if (unlikely(ecryptfs_verbosity > 0)) {
 		ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
 				crypt_stat->key_size);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 1c1a56b..e6ac78c 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -8,7 +8,7 @@
  * Copyright (C) 2004-2008 International Business Machines Corp.
  *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
  *              Trevor S. Highland <trevor.highland@gmail.com>
- *              Tyler Hicks <tyhicks@ou.edu>
+ *              Tyler Hicks <code@tyhicks.com>
  */
 
 #ifndef ECRYPTFS_KERNEL_H
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 7d326aa..af3eb02 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1304,7 +1304,7 @@
 		printk(KERN_WARNING "Tag 1 packet contains key larger "
 		       "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n");
 		rc = -EINVAL;
-		goto out;
+		goto out_free;
 	}
 	memcpy((*new_auth_tok)->session_key.encrypted_key,
 	       &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2)));
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index b8a7ce3..e63259f 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -7,7 +7,7 @@
  * Copyright (C) 2004-2007 International Business Machines Corp.
  *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
  *              Michael C. Thompson <mcthomps@us.ibm.com>
- *              Tyler Hicks <tyhicks@ou.edu>
+ *              Tyler Hicks <code@tyhicks.com>
  */
 
 #include <linux/dcache.h>
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index d668e60..8646ba7 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 2004-2008 International Business Machines Corp.
  *   Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com>
- *		Tyler Hicks <tyhicks@ou.edu>
+ *		Tyler Hicks <code@tyhicks.com>
  */
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -379,6 +379,7 @@
 					* ecryptfs_message_buf_len),
 				       GFP_KERNEL);
 	if (!ecryptfs_msg_ctx_arr) {
+		kfree(ecryptfs_daemon_hash);
 		rc = -ENOMEM;
 		goto out;
 	}
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 119667e..c885cf7 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -960,8 +960,9 @@
 static int
 ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
-	return dax_writeback_mapping_range(mapping,
-			mapping->host->i_sb->s_bdev, wbc);
+	struct ext2_sb_info *sbi = EXT2_SB(mapping->host->i_sb);
+
+	return dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
 }
 
 const struct address_space_operations ext2_aops = {
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 1ee04e7..0a734ff 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -207,6 +207,7 @@
 		return PTR_ERR(inode);
 	num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
 	while (i < num) {
+		cond_resched();
 		map.m_lblk = i;
 		map.m_len = num - i;
 		n = ext4_map_blocks(NULL, inode, &map, 0);
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1f34074..9aa1f75 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -129,12 +129,14 @@
 		if (err != ERR_BAD_DX_DIR) {
 			return err;
 		}
-		/*
-		 * We don't set the inode dirty flag since it's not
-		 * critical that it get flushed back to the disk.
-		 */
-		ext4_clear_inode_flag(file_inode(file),
-				      EXT4_INODE_INDEX);
+		/* Can we just clear INDEX flag to ignore htree information? */
+		if (!ext4_has_metadata_csum(sb)) {
+			/*
+			 * We don't set the inode dirty flag since it's not
+			 * critical that it gets flushed back to the disk.
+			 */
+			ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+		}
 	}
 
 	if (ext4_has_inline_data(inode)) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9a2ee24..4441331 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2544,8 +2544,11 @@
 			struct ext4_filename *fname);
 static inline void ext4_update_dx_flag(struct inode *inode)
 {
-	if (!ext4_has_feature_dir_index(inode->i_sb))
+	if (!ext4_has_feature_dir_index(inode->i_sb)) {
+		/* ext4_iget() should have caught this... */
+		WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
 		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+	}
 }
 static const unsigned char ext4_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3313168..e60aca7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2867,7 +2867,7 @@
 	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
-	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+	ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
 	percpu_up_read(&sbi->s_journal_flag_rwsem);
@@ -4644,6 +4644,18 @@
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	}
+	/*
+	 * If dir_index is not enabled but there's dir with INDEX flag set,
+	 * we'd normally treat htree data as empty space. But with metadata
+	 * checksumming that corrupts checksums so forbid that.
+	 */
+	if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
+		ext4_error_inode(inode, function, line, 0,
+			 "iget: Dir with htree data on filesystem without dir_index feature.");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_disksize = inode->i_size;
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 1c44b1a..87f7551 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -120,10 +120,10 @@
 {
 	__ext4_warning(sb, function, line, "%s", msg);
 	__ext4_warning(sb, function, line,
-		       "MMP failure info: last update time: %llu, last update "
-		       "node: %s, last update device: %s",
-		       (long long unsigned int) le64_to_cpu(mmp->mmp_time),
-		       mmp->mmp_nodename, mmp->mmp_bdevname);
+		       "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s",
+		       (unsigned long long)le64_to_cpu(mmp->mmp_time),
+		       (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename,
+		       (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname);
 }
 
 /*
@@ -154,6 +154,7 @@
 	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
 				 EXT4_MMP_MIN_CHECK_INTERVAL);
 	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
 	bdevname(bh->b_bdev, mmp->mmp_bdevname);
 
 	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
@@ -379,7 +380,8 @@
 	/*
 	 * Start a kernel thread to update the MMP block periodically.
 	 */
-	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s",
+					     (int)sizeof(mmp->mmp_bdevname),
 					     bdevname(bh->b_bdev,
 						      mmp->mmp_bdevname));
 	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 129d2eb..ceff4b4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2213,6 +2213,13 @@
 		retval = ext4_dx_add_entry(handle, &fname, dir, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
 			goto out;
+		/* Can we just ignore htree data? */
+		if (ext4_has_metadata_csum(sb)) {
+			EXT4_ERROR_INODE(dir,
+				"Directory has corrupted htree index.");
+			retval = -EFSCORRUPTED;
+			goto out;
+		}
 		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8434217..f464dff 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3009,17 +3009,11 @@
 		return 0;
 	}
 
-#ifndef CONFIG_QUOTA
-	if (ext4_has_feature_quota(sb) && !readonly) {
+#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2)
+	if (!readonly && (ext4_has_feature_quota(sb) ||
+			  ext4_has_feature_project(sb))) {
 		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
-		return 0;
-	}
-	if (ext4_has_feature_project(sb) && !readonly) {
-		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with project quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
+			 "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2");
 		return 0;
 	}
 #endif  /* CONFIG_QUOTA */
@@ -3814,6 +3808,15 @@
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
+	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
+	    blocksize > EXT4_MAX_BLOCK_SIZE) {
+		ext4_msg(sb, KERN_ERR,
+		       "Unsupported filesystem blocksize %d (%d log_block_size)",
+			 blocksize, le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
 		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
 		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
@@ -3831,6 +3834,7 @@
 			ext4_msg(sb, KERN_ERR,
 			       "unsupported inode size: %d",
 			       sbi->s_inode_size);
+			ext4_msg(sb, KERN_ERR, "blocksize: %d", blocksize);
 			goto failed_mount;
 		}
 		/*
@@ -4033,14 +4037,6 @@
 	if (!ext4_feature_set_ok(sb, (sb_rdonly(sb))))
 		goto failed_mount;
 
-	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
-	    blocksize > EXT4_MAX_BLOCK_SIZE) {
-		ext4_msg(sb, KERN_ERR,
-		       "Unsupported filesystem blocksize %d (%d log_block_size)",
-			 blocksize, le32_to_cpu(es->s_log_block_size));
-		goto failed_mount;
-	}
 	if (le32_to_cpu(es->s_log_block_size) >
 	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
 		ext4_msg(sb, KERN_ERR,
@@ -5585,10 +5581,7 @@
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = 0;
-	if (dquot->dq_dqb.dqb_bsoftlimit &&
-	    (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit))
-		limit = dquot->dq_dqb.dqb_bsoftlimit;
+	limit = dquot->dq_dqb.dqb_bsoftlimit;
 	if (dquot->dq_dqb.dqb_bhardlimit &&
 	    (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
 		limit = dquot->dq_dqb.dqb_bhardlimit;
@@ -5603,10 +5596,7 @@
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = 0;
-	if (dquot->dq_dqb.dqb_isoftlimit &&
-	    (!limit || dquot->dq_dqb.dqb_isoftlimit < limit))
-		limit = dquot->dq_dqb.dqb_isoftlimit;
+	limit = dquot->dq_dqb.dqb_isoftlimit;
 	if (dquot->dq_dqb.dqb_ihardlimit &&
 	    (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
 		limit = dquot->dq_dqb.dqb_ihardlimit;
diff --git a/fs/io-wq.c b/fs/io-wq.c
index cb60a42b..0a5ab1a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/rculist_nulls.h>
+#include <linux/fs_struct.h>
 
 #include "io-wq.h"
 
@@ -59,6 +60,7 @@
 	const struct cred *cur_creds;
 	const struct cred *saved_creds;
 	struct files_struct *restore_files;
+	struct fs_struct *restore_fs;
 };
 
 #if BITS_PER_LONG == 64
@@ -151,6 +153,9 @@
 		task_unlock(current);
 	}
 
+	if (current->fs != worker->restore_fs)
+		current->fs = worker->restore_fs;
+
 	/*
 	 * If we have an active mm, we need to drop the wq lock before unusing
 	 * it. If we do, return true and let the caller retry the idle loop.
@@ -311,6 +316,7 @@
 
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 	worker->restore_files = current->files;
+	worker->restore_fs = current->fs;
 	io_wqe_inc_running(wqe, worker);
 }
 
@@ -481,6 +487,8 @@
 			current->files = work->files;
 			task_unlock(current);
 		}
+		if (work->fs && current->fs != work->fs)
+			current->fs = work->fs;
 		if (work->mm != worker->mm)
 			io_wq_switch_mm(worker, work);
 		if (worker->cur_creds != work->creds)
@@ -691,11 +699,16 @@
 	/* create fixed workers */
 	refcount_set(&wq->refs, workers_to_create);
 	for_each_node(node) {
+		if (!node_online(node))
+			continue;
 		if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
 			goto err;
 		workers_to_create--;
 	}
 
+	while (workers_to_create--)
+		refcount_dec(&wq->refs);
+
 	complete(&wq->done);
 
 	while (!kthread_should_stop()) {
@@ -703,6 +716,9 @@
 			struct io_wqe *wqe = wq->wqes[node];
 			bool fork_worker[2] = { false, false };
 
+			if (!node_online(node))
+				continue;
+
 			spin_lock_irq(&wqe->lock);
 			if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
 				fork_worker[IO_WQ_ACCT_BOUND] = true;
@@ -821,7 +837,9 @@
 
 	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
 		if (io_worker_get(worker)) {
-			ret = func(worker, data);
+			/* no task if node is/was offline */
+			if (worker->task)
+				ret = func(worker, data);
 			io_worker_release(worker);
 			if (ret)
 				break;
@@ -929,17 +947,19 @@
 	return ret;
 }
 
+struct work_match {
+	bool (*fn)(struct io_wq_work *, void *data);
+	void *data;
+};
+
 static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 {
-	struct io_wq_work *work = data;
+	struct work_match *match = data;
 	unsigned long flags;
 	bool ret = false;
 
-	if (worker->cur_work != work)
-		return false;
-
 	spin_lock_irqsave(&worker->lock, flags);
-	if (worker->cur_work == work &&
+	if (match->fn(worker->cur_work, match->data) &&
 	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) {
 		send_sig(SIGINT, worker->task, 1);
 		ret = true;
@@ -950,15 +970,13 @@
 }
 
 static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
-					    struct io_wq_work *cwork)
+					    struct work_match *match)
 {
 	struct io_wq_work_node *node, *prev;
 	struct io_wq_work *work;
 	unsigned long flags;
 	bool found = false;
 
-	cwork->flags |= IO_WQ_WORK_CANCEL;
-
 	/*
 	 * First check pending list, if we're lucky we can just remove it
 	 * from there. CANCEL_OK means that the work is returned as-new,
@@ -968,7 +986,7 @@
 	wq_list_for_each(node, prev, &wqe->work_list) {
 		work = container_of(node, struct io_wq_work, list);
 
-		if (work == cwork) {
+		if (match->fn(work, match->data)) {
 			wq_node_del(&wqe->work_list, node, prev);
 			found = true;
 			break;
@@ -989,20 +1007,60 @@
 	 * completion will run normally in this case.
 	 */
 	rcu_read_lock();
-	found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork);
+	found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
 	rcu_read_unlock();
 	return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
 }
 
+static bool io_wq_work_match(struct io_wq_work *work, void *data)
+{
+	return work == data;
+}
+
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
 {
+	struct work_match match = {
+		.fn	= io_wq_work_match,
+		.data	= cwork
+	};
+	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
+	int node;
+
+	cwork->flags |= IO_WQ_WORK_CANCEL;
+
+	for_each_node(node) {
+		struct io_wqe *wqe = wq->wqes[node];
+
+		ret = io_wqe_cancel_work(wqe, &match);
+		if (ret != IO_WQ_CANCEL_NOTFOUND)
+			break;
+	}
+
+	return ret;
+}
+
+static bool io_wq_pid_match(struct io_wq_work *work, void *data)
+{
+	pid_t pid = (pid_t) (unsigned long) data;
+
+	if (work)
+		return work->task_pid == pid;
+	return false;
+}
+
+enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid)
+{
+	struct work_match match = {
+		.fn	= io_wq_pid_match,
+		.data	= (void *) (unsigned long) pid
+	};
 	enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
 	int node;
 
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
 
-		ret = io_wqe_cancel_work(wqe, cwork);
+		ret = io_wqe_cancel_work(wqe, &match);
 		if (ret != IO_WQ_CANCEL_NOTFOUND)
 			break;
 	}
@@ -1036,6 +1094,8 @@
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
 
+		if (!node_online(node))
+			continue;
 		init_completion(&data.done);
 		INIT_IO_WORK(&data.work, io_wq_flush_func);
 		data.work.flags |= IO_WQ_WORK_INTERNAL;
@@ -1067,12 +1127,15 @@
 
 	for_each_node(node) {
 		struct io_wqe *wqe;
+		int alloc_node = node;
 
-		wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, node);
+		if (!node_online(alloc_node))
+			alloc_node = NUMA_NO_NODE;
+		wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node);
 		if (!wqe)
 			goto err;
 		wq->wqes[node] = wqe;
-		wqe->node = node;
+		wqe->node = alloc_node;
 		wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
 		atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0);
 		if (wq->user) {
@@ -1080,7 +1143,6 @@
 					task_rlimit(current, RLIMIT_NPROC);
 		}
 		atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
-		wqe->node = node;
 		wqe->wq = wq;
 		spin_lock_init(&wqe->lock);
 		INIT_WQ_LIST(&wqe->work_list);
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 50b3378..ccc7d84 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -74,17 +74,20 @@
 	struct files_struct *files;
 	struct mm_struct *mm;
 	const struct cred *creds;
+	struct fs_struct *fs;
 	unsigned flags;
+	pid_t task_pid;
 };
 
 #define INIT_IO_WORK(work, _func)			\
 	do {						\
 		(work)->list.next = NULL;		\
 		(work)->func = _func;			\
-		(work)->flags = 0;			\
 		(work)->files = NULL;			\
 		(work)->mm = NULL;			\
 		(work)->creds = NULL;			\
+		(work)->fs = NULL;			\
+		(work)->flags = 0;			\
 	} while (0)					\
 
 typedef void (get_work_fn)(struct io_wq_work *);
@@ -107,6 +110,7 @@
 
 void io_wq_cancel_all(struct io_wq *wq);
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
+enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid);
 
 typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 77f22c3..5a82601 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -75,6 +75,7 @@
 #include <linux/fsnotify.h>
 #include <linux/fadvise.h>
 #include <linux/eventpoll.h>
+#include <linux/fs_struct.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -204,11 +205,11 @@
 
 	struct {
 		unsigned int		flags;
-		int			compat: 1;
-		int			account_mem: 1;
-		int			cq_overflow_flushed: 1;
-		int			drain_next: 1;
-		int			eventfd_async: 1;
+		unsigned int		compat: 1;
+		unsigned int		account_mem: 1;
+		unsigned int		cq_overflow_flushed: 1;
+		unsigned int		drain_next: 1;
+		unsigned int		eventfd_async: 1;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -441,6 +442,7 @@
 	struct iovec			*iov;
 	struct sockaddr __user		*uaddr;
 	struct msghdr			msg;
+	struct sockaddr_storage		addr;
 };
 
 struct io_async_rw {
@@ -450,17 +452,12 @@
 	ssize_t				size;
 };
 
-struct io_async_open {
-	struct filename			*filename;
-};
-
 struct io_async_ctx {
 	union {
 		struct io_async_rw	rw;
 		struct io_async_msghdr	msg;
 		struct io_async_connect	connect;
 		struct io_timeout_data	timeout;
-		struct io_async_open	open;
 	};
 };
 
@@ -483,6 +480,8 @@
 	REQ_F_MUST_PUNT_BIT,
 	REQ_F_TIMEOUT_NOSEQ_BIT,
 	REQ_F_COMP_LOCKED_BIT,
+	REQ_F_NEED_CLEANUP_BIT,
+	REQ_F_OVERFLOW_BIT,
 };
 
 enum {
@@ -521,6 +520,10 @@
 	REQ_F_TIMEOUT_NOSEQ	= BIT(REQ_F_TIMEOUT_NOSEQ_BIT),
 	/* completion under lock */
 	REQ_F_COMP_LOCKED	= BIT(REQ_F_COMP_LOCKED_BIT),
+	/* needs cleanup */
+	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
+	/* in overflow list */
+	REQ_F_OVERFLOW		= BIT(REQ_F_OVERFLOW_BIT),
 };
 
 /*
@@ -553,7 +556,6 @@
 	 * llist_node is only used for poll deferred completions
 	 */
 	struct llist_node		llist_node;
-	bool				has_user;
 	bool				in_async;
 	bool				needs_fixed_file;
 	u8				opcode;
@@ -614,6 +616,8 @@
 	unsigned		not_supported : 1;
 	/* needs file table */
 	unsigned		file_table : 1;
+	/* needs ->fs */
+	unsigned		needs_fs : 1;
 };
 
 static const struct io_op_def io_op_defs[] = {
@@ -656,12 +660,14 @@
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.needs_fs		= 1,
 	},
 	[IORING_OP_RECVMSG] = {
 		.async_ctx		= 1,
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
+		.needs_fs		= 1,
 	},
 	[IORING_OP_TIMEOUT] = {
 		.async_ctx		= 1,
@@ -692,6 +698,7 @@
 		.needs_file		= 1,
 		.fd_non_neg		= 1,
 		.file_table		= 1,
+		.needs_fs		= 1,
 	},
 	[IORING_OP_CLOSE] = {
 		.needs_file		= 1,
@@ -705,6 +712,7 @@
 		.needs_mm		= 1,
 		.needs_file		= 1,
 		.fd_non_neg		= 1,
+		.needs_fs		= 1,
 	},
 	[IORING_OP_READ] = {
 		.needs_mm		= 1,
@@ -736,6 +744,7 @@
 		.needs_file		= 1,
 		.fd_non_neg		= 1,
 		.file_table		= 1,
+		.needs_fs		= 1,
 	},
 	[IORING_OP_EPOLL_CTL] = {
 		.unbound_nonreg_file	= 1,
@@ -754,6 +763,7 @@
 				 unsigned nr_args);
 static int io_grab_files(struct io_kiocb *req);
 static void io_ring_file_ref_flush(struct fixed_file_data *data);
+static void io_cleanup_req(struct io_kiocb *req);
 
 static struct kmem_cache *req_cachep;
 
@@ -909,6 +919,18 @@
 	}
 	if (!req->work.creds)
 		req->work.creds = get_current_cred();
+	if (!req->work.fs && def->needs_fs) {
+		spin_lock(&current->fs->lock);
+		if (!current->fs->in_exec) {
+			req->work.fs = current->fs;
+			req->work.fs->users++;
+		} else {
+			req->work.flags |= IO_WQ_WORK_CANCEL;
+		}
+		spin_unlock(&current->fs->lock);
+	}
+	if (!req->work.task_pid)
+		req->work.task_pid = task_pid_vnr(current);
 }
 
 static inline void io_req_work_drop_env(struct io_kiocb *req)
@@ -921,6 +943,16 @@
 		put_cred(req->work.creds);
 		req->work.creds = NULL;
 	}
+	if (req->work.fs) {
+		struct fs_struct *fs = req->work.fs;
+
+		spin_lock(&req->work.fs->lock);
+		if (--fs->users)
+			fs = NULL;
+		spin_unlock(&req->work.fs->lock);
+		if (fs)
+			free_fs_struct(fs);
+	}
 }
 
 static inline bool io_prep_async_work(struct io_kiocb *req,
@@ -1074,6 +1106,7 @@
 		req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
 						list);
 		list_move(&req->list, &list);
+		req->flags &= ~REQ_F_OVERFLOW;
 		if (cqe) {
 			WRITE_ONCE(cqe->user_data, req->user_data);
 			WRITE_ONCE(cqe->res, req->result);
@@ -1126,6 +1159,7 @@
 			set_bit(0, &ctx->sq_check_overflow);
 			set_bit(0, &ctx->cq_check_overflow);
 		}
+		req->flags |= REQ_F_OVERFLOW;
 		refcount_inc(&req->refs);
 		req->result = res;
 		list_add_tail(&req->list, &ctx->cq_overflow_list);
@@ -1241,6 +1275,9 @@
 {
 	__io_req_aux_free(req);
 
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		io_cleanup_req(req);
+
 	if (req->flags & REQ_F_INFLIGHT) {
 		struct io_ring_ctx *ctx = req->ctx;
 		unsigned long flags;
@@ -2056,9 +2093,6 @@
 		return iorw->size;
 	}
 
-	if (!req->has_user)
-		return -EFAULT;
-
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
 		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
@@ -2137,6 +2171,8 @@
 		req->io->rw.iov = req->io->rw.fast_iov;
 		memcpy(req->io->rw.iov, fast_iov,
 			sizeof(struct iovec) * iter->nr_segs);
+	} else {
+		req->flags |= REQ_F_NEED_CLEANUP;
 	}
 }
 
@@ -2148,17 +2184,6 @@
 	return req->io == NULL;
 }
 
-static void io_rw_async(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct iovec *iov = NULL;
-
-	if (req->io->rw.iov != req->io->rw.fast_iov)
-		iov = req->io->rw.iov;
-	io_wq_submit_work(workptr);
-	kfree(iov);
-}
-
 static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
 			     struct iovec *iovec, struct iovec *fast_iov,
 			     struct iov_iter *iter)
@@ -2171,7 +2196,6 @@
 
 		io_req_map_rw(req, io_size, iovec, fast_iov, iter);
 	}
-	req->work.func = io_rw_async;
 	return 0;
 }
 
@@ -2189,7 +2213,8 @@
 	if (unlikely(!(req->file->f_mode & FMODE_READ)))
 		return -EBADF;
 
-	if (!req->io)
+	/* either don't need iovec imported or already have it */
+	if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 
 	io = req->io;
@@ -2258,8 +2283,8 @@
 		}
 	}
 out_free:
-	if (!io_wq_current_is_worker())
-		kfree(iovec);
+	kfree(iovec);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
 	return ret;
 }
 
@@ -2277,7 +2302,8 @@
 	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 
-	if (!req->io)
+	/* either don't need iovec imported or already have it */
+	if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 
 	io = req->io;
@@ -2352,6 +2378,12 @@
 			ret2 = call_write_iter(req->file, kiocb, &iter);
 		else
 			ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter);
+		/*
+		 * Raw bdev writes will -EOPNOTSUPP for IOCB_NOWAIT. Just
+		 * retry them without IOCB_NOWAIT.
+		 */
+		if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
+			ret2 = -EAGAIN;
 		if (!force_nonblock || ret2 != -EAGAIN) {
 			kiocb_done(kiocb, ret2, nxt, req->in_async);
 		} else {
@@ -2364,8 +2396,8 @@
 		}
 	}
 out_free:
-	if (!io_wq_current_is_worker())
-		kfree(iovec);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	kfree(iovec);
 	return ret;
 }
 
@@ -2534,6 +2566,10 @@
 
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
+	if (sqe->flags & IOSQE_FIXED_FILE)
+		return -EBADF;
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
 
 	req->open.dfd = READ_ONCE(sqe->fd);
 	req->open.how.mode = READ_ONCE(sqe->len);
@@ -2547,6 +2583,7 @@
 		return ret;
 	}
 
+	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
 
@@ -2559,6 +2596,10 @@
 
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
+	if (sqe->flags & IOSQE_FIXED_FILE)
+		return -EBADF;
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
 
 	req->open.dfd = READ_ONCE(sqe->fd);
 	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -2583,6 +2624,7 @@
 		return ret;
 	}
 
+	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
 
@@ -2614,6 +2656,7 @@
 	}
 err:
 	putname(req->open.filename);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
@@ -2754,6 +2797,10 @@
 
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
+	if (sqe->flags & IOSQE_FIXED_FILE)
+		return -EBADF;
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
 
 	req->open.dfd = READ_ONCE(sqe->fd);
 	req->open.mask = READ_ONCE(sqe->len);
@@ -2771,6 +2818,7 @@
 		return ret;
 	}
 
+	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
 
@@ -2808,6 +2856,7 @@
 		ret = cp_statx(&stat, ctx->buffer);
 err:
 	putname(ctx->filename);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
@@ -2827,7 +2876,7 @@
 	    sqe->rw_flags || sqe->buf_index)
 		return -EINVAL;
 	if (sqe->flags & IOSQE_FIXED_FILE)
-		return -EINVAL;
+		return -EBADF;
 
 	req->close.fd = READ_ONCE(sqe->fd);
 	if (req->file->f_op == &io_uring_fops ||
@@ -2837,24 +2886,25 @@
 	return 0;
 }
 
+/* only called when __close_fd_get_file() is done */
+static void __io_close_finish(struct io_kiocb *req, struct io_kiocb **nxt)
+{
+	int ret;
+
+	ret = filp_close(req->close.put_file, req->work.files);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	fput(req->close.put_file);
+	io_put_req_find_next(req, nxt);
+}
+
 static void io_close_finish(struct io_wq_work **workptr)
 {
 	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
 	struct io_kiocb *nxt = NULL;
 
-	/* Invoked with files, we need to do the close */
-	if (req->work.files) {
-		int ret;
-
-		ret = filp_close(req->close.put_file, req->work.files);
-		if (ret < 0)
-			req_set_fail_links(req);
-		io_cqring_add_event(req, ret);
-	}
-
-	fput(req->close.put_file);
-
-	io_put_req_find_next(req, &nxt);
+	__io_close_finish(req, &nxt);
 	if (nxt)
 		io_wq_assign_next(workptr, nxt);
 }
@@ -2877,22 +2927,8 @@
 	 * No ->flush(), safely close from here and just punt the
 	 * fput() to async context.
 	 */
-	ret = filp_close(req->close.put_file, current->files);
-
-	if (ret < 0)
-		req_set_fail_links(req);
-	io_cqring_add_event(req, ret);
-
-	if (io_wq_current_is_worker()) {
-		struct io_wq_work *old_work, *work;
-
-		old_work = work = &req->work;
-		io_close_finish(&work);
-		if (work && work != old_work)
-			*nxt = container_of(work, struct io_kiocb, work);
-		return 0;
-	}
-
+	__io_close_finish(req, nxt);
+	return 0;
 eagain:
 	req->work.func = io_close_finish;
 	/*
@@ -2960,24 +2996,12 @@
 	return 0;
 }
 
-#if defined(CONFIG_NET)
-static void io_sendrecv_async(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct iovec *iov = NULL;
-
-	if (req->io->rw.iov != req->io->rw.fast_iov)
-		iov = req->io->msg.iov;
-	io_wq_submit_work(workptr);
-	kfree(iov);
-}
-#endif
-
 static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 #if defined(CONFIG_NET)
 	struct io_sr_msg *sr = &req->sr_msg;
 	struct io_async_ctx *io = req->io;
+	int ret;
 
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -2985,10 +3009,16 @@
 
 	if (!io || req->opcode == IORING_OP_SEND)
 		return 0;
+	/* iovec is already imported */
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
 
 	io->msg.iov = io->msg.fast_iov;
-	return sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
+	ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
 					&io->msg.iov);
+	if (!ret)
+		req->flags |= REQ_F_NEED_CLEANUP;
+	return ret;
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -3008,12 +3038,11 @@
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_async_ctx io;
-		struct sockaddr_storage addr;
 		unsigned flags;
 
 		if (req->io) {
 			kmsg = &req->io->msg;
-			kmsg->msg.msg_name = &addr;
+			kmsg->msg.msg_name = &req->io->msg.addr;
 			/* if iov is set, it's allocated already */
 			if (!kmsg->iov)
 				kmsg->iov = kmsg->fast_iov;
@@ -3022,7 +3051,7 @@
 			struct io_sr_msg *sr = &req->sr_msg;
 
 			kmsg = &io.msg;
-			kmsg->msg.msg_name = &addr;
+			kmsg->msg.msg_name = &io.msg.addr;
 
 			io.msg.iov = io.msg.fast_iov;
 			ret = sendmsg_copy_msghdr(&io.msg.msg, sr->msg,
@@ -3041,18 +3070,22 @@
 		if (force_nonblock && ret == -EAGAIN) {
 			if (req->io)
 				return -EAGAIN;
-			if (io_alloc_async_ctx(req))
+			if (io_alloc_async_ctx(req)) {
+				if (kmsg && kmsg->iov != kmsg->fast_iov)
+					kfree(kmsg->iov);
 				return -ENOMEM;
+			}
+			req->flags |= REQ_F_NEED_CLEANUP;
 			memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
-			req->work.func = io_sendrecv_async;
 			return -EAGAIN;
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 	}
 
-	if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov)
+	if (kmsg && kmsg->iov != kmsg->fast_iov)
 		kfree(kmsg->iov);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_cqring_add_event(req, ret);
 	if (ret < 0)
 		req_set_fail_links(req);
@@ -3120,6 +3153,7 @@
 #if defined(CONFIG_NET)
 	struct io_sr_msg *sr = &req->sr_msg;
 	struct io_async_ctx *io = req->io;
+	int ret;
 
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -3127,10 +3161,16 @@
 
 	if (!io || req->opcode == IORING_OP_RECV)
 		return 0;
+	/* iovec is already imported */
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
 
 	io->msg.iov = io->msg.fast_iov;
-	return recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
+	ret = recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
 					&io->msg.uaddr, &io->msg.iov);
+	if (!ret)
+		req->flags |= REQ_F_NEED_CLEANUP;
+	return ret;
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -3150,12 +3190,11 @@
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_async_ctx io;
-		struct sockaddr_storage addr;
 		unsigned flags;
 
 		if (req->io) {
 			kmsg = &req->io->msg;
-			kmsg->msg.msg_name = &addr;
+			kmsg->msg.msg_name = &req->io->msg.addr;
 			/* if iov is set, it's allocated already */
 			if (!kmsg->iov)
 				kmsg->iov = kmsg->fast_iov;
@@ -3164,7 +3203,7 @@
 			struct io_sr_msg *sr = &req->sr_msg;
 
 			kmsg = &io.msg;
-			kmsg->msg.msg_name = &addr;
+			kmsg->msg.msg_name = &io.msg.addr;
 
 			io.msg.iov = io.msg.fast_iov;
 			ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg,
@@ -3185,18 +3224,22 @@
 		if (force_nonblock && ret == -EAGAIN) {
 			if (req->io)
 				return -EAGAIN;
-			if (io_alloc_async_ctx(req))
+			if (io_alloc_async_ctx(req)) {
+				if (kmsg && kmsg->iov != kmsg->fast_iov)
+					kfree(kmsg->iov);
 				return -ENOMEM;
+			}
 			memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
-			req->work.func = io_sendrecv_async;
+			req->flags |= REQ_F_NEED_CLEANUP;
 			return -EAGAIN;
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 	}
 
-	if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov)
+	if (kmsg && kmsg->iov != kmsg->fast_iov)
 		kfree(kmsg->iov);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_cqring_add_event(req, ret);
 	if (ret < 0)
 		req_set_fail_links(req);
@@ -4207,6 +4250,35 @@
 	return -EIOCBQUEUED;
 }
 
+static void io_cleanup_req(struct io_kiocb *req)
+{
+	struct io_async_ctx *io = req->io;
+
+	switch (req->opcode) {
+	case IORING_OP_READV:
+	case IORING_OP_READ_FIXED:
+	case IORING_OP_READ:
+	case IORING_OP_WRITEV:
+	case IORING_OP_WRITE_FIXED:
+	case IORING_OP_WRITE:
+		if (io->rw.iov != io->rw.fast_iov)
+			kfree(io->rw.iov);
+		break;
+	case IORING_OP_SENDMSG:
+	case IORING_OP_RECVMSG:
+		if (io->msg.iov != io->msg.fast_iov)
+			kfree(io->msg.iov);
+		break;
+	case IORING_OP_OPENAT:
+	case IORING_OP_OPENAT2:
+	case IORING_OP_STATX:
+		putname(req->open.filename);
+		break;
+	}
+
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+}
+
 static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			struct io_kiocb **nxt, bool force_nonblock)
 {
@@ -4446,7 +4518,6 @@
 	}
 
 	if (!ret) {
-		req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
 		req->in_async = true;
 		do {
 			ret = io_issue_sqe(req, NULL, &nxt, false);
@@ -4479,7 +4550,7 @@
 {
 	if (!io_op_defs[req->opcode].needs_file)
 		return 0;
-	if (fd == -1 && io_op_defs[req->opcode].fd_non_neg)
+	if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
 		return 0;
 	return 1;
 }
@@ -4950,6 +5021,7 @@
 	for (i = 0; i < nr; i++) {
 		const struct io_uring_sqe *sqe;
 		struct io_kiocb *req;
+		int err;
 
 		req = io_get_req(ctx, statep);
 		if (unlikely(!req)) {
@@ -4966,20 +5038,23 @@
 		submitted++;
 
 		if (unlikely(req->opcode >= IORING_OP_LAST)) {
-			io_cqring_add_event(req, -EINVAL);
+			err = -EINVAL;
+fail_req:
+			io_cqring_add_event(req, err);
 			io_double_put_req(req);
 			break;
 		}
 
 		if (io_op_defs[req->opcode].needs_mm && !*mm) {
 			mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
-			if (!mm_fault) {
-				use_mm(ctx->sqo_mm);
-				*mm = ctx->sqo_mm;
+			if (unlikely(mm_fault)) {
+				err = -EFAULT;
+				goto fail_req;
 			}
+			use_mm(ctx->sqo_mm);
+			*mm = ctx->sqo_mm;
 		}
 
-		req->has_user = *mm != NULL;
 		req->in_async = async;
 		req->needs_fixed_file = async;
 		trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
@@ -6301,7 +6376,7 @@
 	if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head !=
 	    ctx->rings->sq_ring_entries)
 		mask |= EPOLLOUT | EPOLLWRNORM;
-	if (READ_ONCE(ctx->rings->cq.head) != ctx->cached_cq_tail)
+	if (io_cqring_events(ctx, false))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	return mask;
@@ -6393,6 +6468,29 @@
 		if (!cancel_req)
 			break;
 
+		if (cancel_req->flags & REQ_F_OVERFLOW) {
+			spin_lock_irq(&ctx->completion_lock);
+			list_del(&cancel_req->list);
+			cancel_req->flags &= ~REQ_F_OVERFLOW;
+			if (list_empty(&ctx->cq_overflow_list)) {
+				clear_bit(0, &ctx->sq_check_overflow);
+				clear_bit(0, &ctx->cq_check_overflow);
+			}
+			spin_unlock_irq(&ctx->completion_lock);
+
+			WRITE_ONCE(ctx->rings->cq_overflow,
+				atomic_inc_return(&ctx->cached_cq_overflow));
+
+			/*
+			 * Put inflight ref and overflow ref. If that's
+			 * all we had, then we're done with this request.
+			 */
+			if (refcount_sub_and_test(2, &cancel_req->refs)) {
+				io_put_req(cancel_req);
+				continue;
+			}
+		}
+
 		io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
 		io_put_req(cancel_req);
 		schedule();
@@ -6405,6 +6503,13 @@
 	struct io_ring_ctx *ctx = file->private_data;
 
 	io_uring_cancel_files(ctx, data);
+
+	/*
+	 * If the task is going away, cancel work it may have pending
+	 */
+	if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
+		io_wq_cancel_pid(ctx->io_wq, task_pid_vnr(current));
+
 	return 0;
 }
 
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2494095..27373f5 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -976,29 +976,33 @@
 		 * it. */
 
 		/*
-		* A buffer which has been freed while still being journaled by
-		* a previous transaction.
-		*/
-		if (buffer_freed(bh)) {
+		 * A buffer which has been freed while still being journaled
+		 * by a previous transaction, refile the buffer to BJ_Forget of
+		 * the running transaction. If the just committed transaction
+		 * contains "add to orphan" operation, we can completely
+		 * invalidate the buffer now. We are rather through in that
+		 * since the buffer may be still accessible when blocksize <
+		 * pagesize and it is attached to the last partial page.
+		 */
+		if (buffer_freed(bh) && !jh->b_next_transaction) {
+			struct address_space *mapping;
+
+			clear_buffer_freed(bh);
+			clear_buffer_jbddirty(bh);
+
 			/*
-			 * If the running transaction is the one containing
-			 * "add to orphan" operation (b_next_transaction !=
-			 * NULL), we have to wait for that transaction to
-			 * commit before we can really get rid of the buffer.
-			 * So just clear b_modified to not confuse transaction
-			 * credit accounting and refile the buffer to
-			 * BJ_Forget of the running transaction. If the just
-			 * committed transaction contains "add to orphan"
-			 * operation, we can completely invalidate the buffer
-			 * now. We are rather through in that since the
-			 * buffer may be still accessible when blocksize <
-			 * pagesize and it is attached to the last partial
-			 * page.
+			 * Block device buffers need to stay mapped all the
+			 * time, so it is enough to clear buffer_jbddirty and
+			 * buffer_freed bits. For the file mapping buffers (i.e.
+			 * journalled data) we need to unmap buffer and clear
+			 * more bits. We also need to be careful about the check
+			 * because the data page mapping can get cleared under
+			 * out hands, which alse need not to clear more bits
+			 * because the page and buffers will be freed and can
+			 * never be reused once we are done with them.
 			 */
-			jh->b_modified = 0;
-			if (!jh->b_next_transaction) {
-				clear_buffer_freed(bh);
-				clear_buffer_jbddirty(bh);
+			mapping = READ_ONCE(bh->b_page->mapping);
+			if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) {
 				clear_buffer_mapped(bh);
 				clear_buffer_new(bh);
 				clear_buffer_req(bh);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e77a5a0..2dd848a 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2329,14 +2329,16 @@
 			return -EBUSY;
 		}
 		/*
-		 * OK, buffer won't be reachable after truncate. We just set
-		 * j_next_transaction to the running transaction (if there is
-		 * one) and mark buffer as freed so that commit code knows it
-		 * should clear dirty bits when it is done with the buffer.
+		 * OK, buffer won't be reachable after truncate. We just clear
+		 * b_modified to not confuse transaction credit accounting, and
+		 * set j_next_transaction to the running transaction (if there
+		 * is one) and mark buffer as freed so that commit code knows
+		 * it should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
 			jh->b_next_transaction = journal->j_running_transaction;
+		jh->b_modified = 0;
 		spin_unlock(&journal->j_list_lock);
 		spin_unlock(&jh->b_state_lock);
 		write_unlock(&journal->j_state_lock);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 4a84107..1865322 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -42,13 +42,27 @@
 	if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
 		delegation->stateid.type = NFS4_INVALID_STATEID_TYPE;
 		atomic_long_dec(&nfs_active_delegations);
+		if (!test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+			nfs_clear_verifier_delegated(delegation->inode);
 	}
 }
 
+static struct nfs_delegation *nfs_get_delegation(struct nfs_delegation *delegation)
+{
+	refcount_inc(&delegation->refcount);
+	return delegation;
+}
+
+static void nfs_put_delegation(struct nfs_delegation *delegation)
+{
+	if (refcount_dec_and_test(&delegation->refcount))
+		__nfs_free_delegation(delegation);
+}
+
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
 	nfs_mark_delegation_revoked(delegation);
-	__nfs_free_delegation(delegation);
+	nfs_put_delegation(delegation);
 }
 
 /**
@@ -241,13 +255,18 @@
 
 static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
 {
+	const struct cred *cred;
 	int res = 0;
 
-	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
-		res = nfs4_proc_delegreturn(inode,
-				delegation->cred,
+	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
+		spin_lock(&delegation->lock);
+		cred = get_cred(delegation->cred);
+		spin_unlock(&delegation->lock);
+		res = nfs4_proc_delegreturn(inode, cred,
 				&delegation->stateid,
 				issync);
+		put_cred(cred);
+	}
 	return res;
 }
 
@@ -273,9 +292,13 @@
 	if (delegation == NULL)
 		goto out;
 	spin_lock(&delegation->lock);
-	if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
-		ret = delegation;
+	if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+		/* Refcount matched in nfs_end_delegation_return() */
+		ret = nfs_get_delegation(delegation);
+	}
 	spin_unlock(&delegation->lock);
+	if (ret)
+		nfs_clear_verifier_delegated(&nfsi->vfs_inode);
 out:
 	return ret;
 }
@@ -393,6 +416,7 @@
 	if (delegation == NULL)
 		return -ENOMEM;
 	nfs4_stateid_copy(&delegation->stateid, stateid);
+	refcount_set(&delegation->refcount, 1);
 	delegation->type = type;
 	delegation->pagemod_limit = pagemod_limit;
 	delegation->change_attr = inode_peek_iversion_raw(inode);
@@ -492,6 +516,8 @@
 
 	err = nfs_do_return_delegation(inode, delegation, issync);
 out:
+	/* Refcount matched in nfs_start_delegation_return_locked() */
+	nfs_put_delegation(delegation);
 	return err;
 }
 
@@ -686,9 +712,12 @@
 		    list_empty(&NFS_I(inode)->open_files) &&
 		    !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
 			clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
-			ret = delegation;
+			/* Refcount matched in nfs_end_delegation_return() */
+			ret = nfs_get_delegation(delegation);
 		}
 		spin_unlock(&delegation->lock);
+		if (ret)
+			nfs_clear_verifier_delegated(inode);
 	}
 out:
 	rcu_read_unlock();
@@ -1088,10 +1117,11 @@
 			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
 			if (delegation != NULL) {
-				delegation = nfs_detach_delegation(NFS_I(inode),
-					delegation, server);
-				if (delegation != NULL)
+				if (nfs_detach_delegation(NFS_I(inode), delegation,
+							server) != NULL)
 					nfs_free_delegation(delegation);
+				/* Match nfs_start_delegation_return_locked */
+				nfs_put_delegation(delegation);
 			}
 			iput(inode);
 			nfs_sb_deactive(server->super);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 31b8460..9b00a0b 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -22,6 +22,7 @@
 	unsigned long pagemod_limit;
 	__u64 change_attr;
 	unsigned long flags;
+	refcount_t refcount;
 	spinlock_t lock;
 	struct rcu_head rcu;
 };
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 1320288..193d6fb 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -155,6 +155,7 @@
 	loff_t		current_index;
 	decode_dirent_t	decode;
 
+	unsigned long	dir_verifier;
 	unsigned long	timestamp;
 	unsigned long	gencount;
 	unsigned int	cache_entry_index;
@@ -353,6 +354,7 @@
  again:
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
+	desc->dir_verifier = nfs_save_change_attribute(inode);
 	error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages,
 					  NFS_SERVER(inode)->dtsize, desc->plus);
 	if (error < 0) {
@@ -455,13 +457,13 @@
 }
 
 static
-void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
+void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
+		unsigned long dir_verifier)
 {
 	struct qstr filename = QSTR_INIT(entry->name, entry->len);
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct dentry *dentry;
 	struct dentry *alias;
-	struct inode *dir = d_inode(parent);
 	struct inode *inode;
 	int status;
 
@@ -500,7 +502,7 @@
 		if (nfs_same_file(dentry, entry)) {
 			if (!entry->fh->size)
 				goto out;
-			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+			nfs_set_verifier(dentry, dir_verifier);
 			status = nfs_refresh_inode(d_inode(dentry), entry->fattr);
 			if (!status)
 				nfs_setsecurity(d_inode(dentry), entry->fattr, entry->label);
@@ -526,7 +528,7 @@
 		dput(dentry);
 		dentry = alias;
 	}
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	nfs_set_verifier(dentry, dir_verifier);
 out:
 	dput(dentry);
 }
@@ -564,7 +566,8 @@
 		count++;
 
 		if (desc->plus)
-			nfs_prime_dcache(file_dentry(desc->file), entry);
+			nfs_prime_dcache(file_dentry(desc->file), entry,
+					desc->dir_verifier);
 
 		status = nfs_readdir_add_to_array(entry, page);
 		if (status != 0)
@@ -983,14 +986,113 @@
  * full lookup on all child dentries of 'dir' whenever a change occurs
  * on the server that might have invalidated our dcache.
  *
+ * Note that we reserve bit '0' as a tag to let us know when a dentry
+ * was revalidated while holding a delegation on its inode.
+ *
  * The caller should be holding dir->i_lock
  */
 void nfs_force_lookup_revalidate(struct inode *dir)
 {
-	NFS_I(dir)->cache_change_attribute++;
+	NFS_I(dir)->cache_change_attribute += 2;
 }
 EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate);
 
+/**
+ * nfs_verify_change_attribute - Detects NFS remote directory changes
+ * @dir: pointer to parent directory inode
+ * @verf: previously saved change attribute
+ *
+ * Return "false" if the verifiers doesn't match the change attribute.
+ * This would usually indicate that the directory contents have changed on
+ * the server, and that any dentries need revalidating.
+ */
+static bool nfs_verify_change_attribute(struct inode *dir, unsigned long verf)
+{
+	return (verf & ~1UL) == nfs_save_change_attribute(dir);
+}
+
+static void nfs_set_verifier_delegated(unsigned long *verf)
+{
+	*verf |= 1UL;
+}
+
+#if IS_ENABLED(CONFIG_NFS_V4)
+static void nfs_unset_verifier_delegated(unsigned long *verf)
+{
+	*verf &= ~1UL;
+}
+#endif /* IS_ENABLED(CONFIG_NFS_V4) */
+
+static bool nfs_test_verifier_delegated(unsigned long verf)
+{
+	return verf & 1;
+}
+
+static bool nfs_verifier_is_delegated(struct dentry *dentry)
+{
+	return nfs_test_verifier_delegated(dentry->d_time);
+}
+
+static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (!nfs_verifier_is_delegated(dentry) &&
+	    !nfs_verify_change_attribute(d_inode(dentry->d_parent), verf))
+		goto out;
+	if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+		nfs_set_verifier_delegated(&verf);
+out:
+	dentry->d_time = verf;
+}
+
+/**
+ * nfs_set_verifier - save a parent directory verifier in the dentry
+ * @dentry: pointer to dentry
+ * @verf: verifier to save
+ *
+ * Saves the parent directory verifier in @dentry. If the inode has
+ * a delegation, we also tag the dentry as having been revalidated
+ * while holding a delegation so that we know we don't have to
+ * look it up again after a directory change.
+ */
+void nfs_set_verifier(struct dentry *dentry, unsigned long verf)
+{
+
+	spin_lock(&dentry->d_lock);
+	nfs_set_verifier_locked(dentry, verf);
+	spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_set_verifier);
+
+#if IS_ENABLED(CONFIG_NFS_V4)
+/**
+ * nfs_clear_verifier_delegated - clear the dir verifier delegation tag
+ * @inode: pointer to inode
+ *
+ * Iterates through the dentries in the inode alias list and clears
+ * the tag used to indicate that the dentry has been revalidated
+ * while holding a delegation.
+ * This function is intended for use when the delegation is being
+ * returned or revoked.
+ */
+void nfs_clear_verifier_delegated(struct inode *inode)
+{
+	struct dentry *alias;
+
+	if (!inode)
+		return;
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
+		spin_lock(&alias->d_lock);
+		nfs_unset_verifier_delegated(&alias->d_time);
+		spin_unlock(&alias->d_lock);
+	}
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated);
+#endif /* IS_ENABLED(CONFIG_NFS_V4) */
+
 /*
  * A check for whether or not the parent directory has changed.
  * In the case it has, we assume that the dentries are untrustworthy
@@ -1159,6 +1261,7 @@
 	struct nfs_fh *fhandle;
 	struct nfs_fattr *fattr;
 	struct nfs4_label *label;
+	unsigned long dir_verifier;
 	int ret;
 
 	ret = -ENOMEM;
@@ -1168,6 +1271,7 @@
 	if (fhandle == NULL || fattr == NULL || IS_ERR(label))
 		goto out;
 
+	dir_verifier = nfs_save_change_attribute(dir);
 	ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label);
 	if (ret < 0) {
 		switch (ret) {
@@ -1188,7 +1292,7 @@
 		goto out;
 
 	nfs_setsecurity(inode, fattr, label);
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	nfs_set_verifier(dentry, dir_verifier);
 
 	/* set a readdirplus hint that we had a cache miss */
 	nfs_force_use_readdirplus(dir);
@@ -1230,7 +1334,7 @@
 		goto out_bad;
 	}
 
-	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
+	if (nfs_verifier_is_delegated(dentry))
 		return nfs_lookup_revalidate_delegated(dir, dentry, inode);
 
 	/* Force a full look up iff the parent directory has changed */
@@ -1415,6 +1519,7 @@
 	struct nfs_fh *fhandle = NULL;
 	struct nfs_fattr *fattr = NULL;
 	struct nfs4_label *label = NULL;
+	unsigned long dir_verifier;
 	int error;
 
 	dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry);
@@ -1440,6 +1545,7 @@
 	if (IS_ERR(label))
 		goto out;
 
+	dir_verifier = nfs_save_change_attribute(dir);
 	trace_nfs_lookup_enter(dir, dentry, flags);
 	error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label);
 	if (error == -ENOENT)
@@ -1463,7 +1569,7 @@
 			goto out_label;
 		dentry = res;
 	}
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	nfs_set_verifier(dentry, dir_verifier);
 out_label:
 	trace_nfs_lookup_exit(dir, dentry, flags, error);
 	nfs4_label_free(label);
@@ -1668,7 +1774,7 @@
 	if (inode == NULL)
 		goto full_reval;
 
-	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
+	if (nfs_verifier_is_delegated(dentry))
 		return nfs_lookup_revalidate_delegated(dir, dentry, inode);
 
 	/* NFS only supports OPEN on regular files */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 1309e6f..11bf158 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2114,6 +2114,7 @@
 	init_rwsem(&nfsi->rmdir_sem);
 	mutex_init(&nfsi->commit_mutex);
 	nfs4_init_once(nfsi);
+	nfsi->cache_change_attribute = 0;
 }
 
 static int __init nfs_init_inodecache(void)
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index be4eb72..1297919 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -87,7 +87,6 @@
 	if (inode != d_inode(dentry))
 		goto out_drop;
 
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	nfs_file_set_open_context(filp, ctx);
 	nfs_fscache_open_file(inode, filp);
 	err = 0;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 95d07a3..69b7ab7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2974,10 +2974,13 @@
 	struct dentry *dentry;
 	struct nfs4_state *state;
 	fmode_t acc_mode = _nfs4_ctx_to_accessmode(ctx);
+	struct inode *dir = d_inode(opendata->dir);
+	unsigned long dir_verifier;
 	unsigned int seq;
 	int ret;
 
 	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+	dir_verifier = nfs_save_change_attribute(dir);
 
 	ret = _nfs4_proc_open(opendata, ctx);
 	if (ret != 0)
@@ -3005,8 +3008,19 @@
 			dput(ctx->dentry);
 			ctx->dentry = dentry = alias;
 		}
-		nfs_set_verifier(dentry,
-				nfs_save_change_attribute(d_inode(opendata->dir)));
+	}
+
+	switch(opendata->o_arg.claim) {
+	default:
+		break;
+	case NFS4_OPEN_CLAIM_NULL:
+	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
+		if (!opendata->rpc_done)
+			break;
+		if (opendata->o_res.delegation_type != 0)
+			dir_verifier = nfs_save_change_attribute(dir);
+		nfs_set_verifier(dentry, dir_verifier);
 	}
 
 	/* Parse layoutget results before we check for access */
@@ -5322,7 +5336,7 @@
 	hdr->timestamp   = jiffies;
 
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE];
-	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 1, 0);
+	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
 	nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr);
 }
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 5a34d6c..2144507 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -722,9 +722,10 @@
 	if (file->f_mode & FMODE_WRITE)
 		pipe->writers--;
 
-	if (pipe->readers || pipe->writers) {
-		wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLHUP);
-		wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM | EPOLLERR | EPOLLHUP);
+	/* Was that the last reader or writer, but not the other side? */
+	if (!pipe->readers != !pipe->writers) {
+		wake_up_interruptible_all(&pipe->rd_wait);
+		wake_up_interruptible_all(&pipe->wr_wait);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
@@ -1026,8 +1027,8 @@
 
 static void wake_up_partner(struct pipe_inode_info *pipe)
 {
-	wake_up_interruptible(&pipe->rd_wait);
-	wake_up_interruptible(&pipe->wr_wait);
+	wake_up_interruptible_all(&pipe->rd_wait);
+	wake_up_interruptible_all(&pipe->wr_wait);
 }
 
 static int fifo_open(struct inode *inode, struct file *filp)
@@ -1144,7 +1145,7 @@
 
 err_wr:
 	if (!--pipe->writers)
-		wake_up_interruptible(&pipe->rd_wait);
+		wake_up_interruptible_all(&pipe->rd_wait);
 	ret = -ERESTARTSYS;
 	goto err;
 
@@ -1271,8 +1272,9 @@
 	pipe->max_usage = nr_slots;
 	pipe->tail = tail;
 	pipe->head = head;
-	wake_up_interruptible_all(&pipe->rd_wait);
-	wake_up_interruptible_all(&pipe->wr_wait);
+
+	/* This might have made more room for writers */
+	wake_up_interruptible(&pipe->wr_wait);
 	return pipe->max_usage * PAGE_SIZE;
 
 out_revert_acct:
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 3a688eb..58e937b 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -587,7 +587,7 @@
 
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 	return dax_writeback_mapping_range(mapping,
-			xfs_inode_buftarg(ip)->bt_bdev, wbc);
+			xfs_inode_buftarg(ip)->bt_daxdev, wbc);
 }
 
 STATIC sector_t
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 00994b1..8e8be98 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -752,6 +752,8 @@
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
+ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(void))
+ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_fixed_event_status_set(void))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_get_gpe_device(u32 gpe_index,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 11083d8..df2475b 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -248,15 +248,6 @@
 	} _sifields;
 } compat_siginfo_t;
 
-/*
- * These functions operate on 32- or 64-bit specs depending on
- * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments.
- */
-extern int compat_get_timespec(struct timespec *, const void __user *);
-extern int compat_put_timespec(const struct timespec *, void __user *);
-extern int compat_get_timeval(struct timeval *, const void __user *);
-extern int compat_put_timeval(const struct timeval *, void __user *);
-
 struct compat_iovec {
 	compat_uptr_t	iov_base;
 	compat_size_t	iov_len;
@@ -416,26 +407,6 @@
 int get_compat_sigevent(struct sigevent *event,
 		const struct compat_sigevent __user *u_event);
 
-static inline int old_timeval32_compare(struct old_timeval32 *lhs,
-					struct old_timeval32 *rhs)
-{
-	if (lhs->tv_sec < rhs->tv_sec)
-		return -1;
-	if (lhs->tv_sec > rhs->tv_sec)
-		return 1;
-	return lhs->tv_usec - rhs->tv_usec;
-}
-
-static inline int old_timespec32_compare(struct old_timespec32 *lhs,
-					struct old_timespec32 *rhs)
-{
-	if (lhs->tv_sec < rhs->tv_sec)
-		return -1;
-	if (lhs->tv_sec > rhs->tv_sec)
-		return 1;
-	return lhs->tv_nsec - rhs->tv_nsec;
-}
-
 extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat);
 
 /*
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 018dce8..0fb561d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -201,9 +201,6 @@
 	return cpumask_weight(policy->cpus) > 1;
 }
 
-/* /sys/devices/system/cpu/cpufreq: entry point for global variables */
-extern struct kobject *cpufreq_global_kobject;
-
 #ifdef CONFIG_CPU_FREQ
 unsigned int cpufreq_get(unsigned int cpu);
 unsigned int cpufreq_quick_get(unsigned int cpu);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9bd8528..328c2db 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -129,11 +129,6 @@
 			sectors);
 }
 
-static inline struct dax_device *fs_dax_get_by_host(const char *host)
-{
-	return dax_get_by_host(host);
-}
-
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
 	put_dax(dax_dev);
@@ -141,7 +136,7 @@
 
 struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
 int dax_writeback_mapping_range(struct address_space *mapping,
-		struct block_device *bdev, struct writeback_control *wbc);
+		struct dax_device *dax_dev, struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
 dax_entry_t dax_lock_page(struct page *page);
@@ -160,11 +155,6 @@
 	return false;
 }
 
-static inline struct dax_device *fs_dax_get_by_host(const char *host)
-{
-	return NULL;
-}
-
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
 }
@@ -180,7 +170,7 @@
 }
 
 static inline int dax_writeback_mapping_range(struct address_space *mapping,
-		struct block_device *bdev, struct writeback_control *wbc)
+		struct dax_device *dax_dev, struct writeback_control *wbc)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index ef1cbb5..93338fd 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -31,6 +31,12 @@
 }
 #endif
 
+#if IS_ENABLED(CONFIG_NF_NAT)
+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info);
+#else
+#define icmpv6_ndo_send icmpv6_send
+#endif
+
 extern int				icmpv6_init(void);
 extern int				icmpv6_err_convert(u8 type, u8 code,
 							   int *err);
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index 94f047a..d7c403d 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -122,7 +122,7 @@
 	BUG();
 }
 
-static int intel_svm_is_pasid_valid(struct device *dev, int pasid)
+static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index b2bb44f..d1fb051 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -66,33 +66,15 @@
  */
 #define ktime_sub_ns(kt, nsval)		((kt) - (nsval))
 
-/* convert a timespec to ktime_t format: */
-static inline ktime_t timespec_to_ktime(struct timespec ts)
-{
-	return ktime_set(ts.tv_sec, ts.tv_nsec);
-}
-
 /* convert a timespec64 to ktime_t format: */
 static inline ktime_t timespec64_to_ktime(struct timespec64 ts)
 {
 	return ktime_set(ts.tv_sec, ts.tv_nsec);
 }
 
-/* convert a timeval to ktime_t format: */
-static inline ktime_t timeval_to_ktime(struct timeval tv)
-{
-	return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
-}
-
-/* Map the ktime_t to timespec conversion to ns_to_timespec function */
-#define ktime_to_timespec(kt)		ns_to_timespec((kt))
-
 /* Map the ktime_t to timespec conversion to ns_to_timespec function */
 #define ktime_to_timespec64(kt)		ns_to_timespec64((kt))
 
-/* Map the ktime_t to timeval conversion to ns_to_timeval function */
-#define ktime_to_timeval(kt)		ns_to_timeval((kt))
-
 /* Convert ktime_t to nanoseconds */
 static inline s64 ktime_to_ns(const ktime_t kt)
 {
@@ -216,25 +198,6 @@
 extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs);
 
 /**
- * ktime_to_timespec_cond - convert a ktime_t variable to timespec
- *			    format only if the variable contains data
- * @kt:		the ktime_t variable to convert
- * @ts:		the timespec variable to store the result in
- *
- * Return: %true if there was a successful conversion, %false if kt was 0.
- */
-static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt,
-						       struct timespec *ts)
-{
-	if (kt) {
-		*ts = ktime_to_timespec(kt);
-		return true;
-	} else {
-		return false;
-	}
-}
-
-/**
  * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64
  *			    format only if the variable contains data
  * @kt:		the ktime_t variable to convert
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ff8c9d5..bfdf415 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -688,7 +688,10 @@
 	u8         nic_rx_multi_path_tirs[0x1];
 	u8         nic_rx_multi_path_tirs_fts[0x1];
 	u8         allow_sniffer_and_nic_rx_shared_tir[0x1];
-	u8	   reserved_at_3[0x1d];
+	u8	   reserved_at_3[0x4];
+	u8	   sw_owner_reformat_supported[0x1];
+	u8	   reserved_at_8[0x18];
+
 	u8	   encap_general_header[0x1];
 	u8	   reserved_at_21[0xa];
 	u8	   log_max_packet_reformat_context[0x5];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a9c6b5c..6c3f703 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -72,6 +72,8 @@
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+#define MAX_NEST_DEV 8
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -1616,6 +1618,7 @@
  *				and drivers will need to set them appropriately.
  *
  *	@mpls_features:	Mask of features inheritable by MPLS
+ *	@gso_partial_features: value(s) from NETIF_F_GSO\*
  *
  *	@ifindex:	interface index
  *	@group:		The group the device belongs to
@@ -1640,8 +1643,11 @@
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@ethtool_ops:	Management operations
+ *	@l3mdev_ops:	Layer 3 master device operations
  *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
  *			discovery handling. Necessary for e.g. 6LoWPAN.
+ *	@xfrmdev_ops:	Transformation offload operations
+ *	@tlsdev_ops:	Transport Layer Security offload operations
  *	@header_ops:	Includes callbacks for creating,parsing,caching,etc
  *			of Layer 2 headers.
  *
@@ -1680,6 +1686,7 @@
  * 	@dev_port:		Used to differentiate devices that share
  * 				the same function
  *	@addr_list_lock:	XXX: need comments on this one
+ *	@name_assign_type:	network interface name assignment type
  *	@uc_promisc:		Counter that indicates promiscuous mode
  *				has been enabled due to the need to listen to
  *				additional unicast addresses in a device that
@@ -1702,6 +1709,9 @@
  *	@ip6_ptr:	IPv6 specific data
  *	@ax25_ptr:	AX.25 specific data
  *	@ieee80211_ptr:	IEEE 802.11 specific data, assign before registering
+ *	@ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network
+ *			 device struct
+ *	@mpls_ptr:	mpls_dev struct pointer
  *
  *	@dev_addr:	Hw address (before bcast,
  *			because most packets are unicast)
@@ -1710,6 +1720,8 @@
  *	@num_rx_queues:		Number of RX queues
  *				allocated at register_netdev() time
  *	@real_num_rx_queues: 	Number of RX queues currently active in device
+ *	@xdp_prog:		XDP sockets filter program pointer
+ *	@gro_flush_timeout:	timeout for GRO layer in NAPI
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
@@ -1731,10 +1743,14 @@
  *	@qdisc:			Root qdisc from userspace point of view
  *	@tx_queue_len:		Max frames per queue allowed
  *	@tx_global_lock: 	XXX: need comments on this one
+ *	@xdp_bulkq:		XDP device bulk queue
+ *	@xps_cpus_map:		all CPUs map for XPS device
+ *	@xps_rxqs_map:		all RXQs map for XPS device
  *
  *	@xps_maps:	XXX: need comments on this one
  *	@miniq_egress:		clsact qdisc specific data for
  *				egress processing
+ *	@qdisc_hash:		qdisc hash table
  *	@watchdog_timeo:	Represents the timeout that is used by
  *				the watchdog (see dev_watchdog())
  *	@watchdog_timer:	List of timers
@@ -3548,7 +3564,7 @@
 }
 
 /**
- *	netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p
+ *	netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p
  *	@n: CPU/Rx queue index
  *	@src1p: the first CPUs/Rx queues mask pointer
  *	@src2p: the second CPUs/Rx queues mask pointer
@@ -4375,11 +4391,8 @@
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
-						 struct list_head **iter);
-
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
 					void *data),
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index a5f8f03..5d5b91e 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -337,35 +337,17 @@
 	return NFS_SERVER(inode)->caps & cap;
 }
 
-static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf)
-{
-	dentry->d_time = verf;
-}
-
 /**
  * nfs_save_change_attribute - Returns the inode attribute change cookie
  * @dir - pointer to parent directory inode
- * The "change attribute" is updated every time we finish an operation
- * that will result in a metadata change on the server.
+ * The "cache change attribute" is updated when we need to revalidate
+ * our dentry cache after a directory was seen to change on the server.
  */
 static inline unsigned long nfs_save_change_attribute(struct inode *dir)
 {
 	return NFS_I(dir)->cache_change_attribute;
 }
 
-/**
- * nfs_verify_change_attribute - Detects NFS remote directory changes
- * @dir - pointer to parent directory inode
- * @chattr - previously saved change attribute
- * Return "false" if the verifiers doesn't match the change attribute.
- * This would usually indicate that the directory contents have changed on
- * the server, and that any dentries need revalidating.
- */
-static inline int nfs_verify_change_attribute(struct inode *dir, unsigned long chattr)
-{
-	return chattr == NFS_I(dir)->cache_change_attribute;
-}
-
 /*
  * linux/fs/nfs/inode.c
  */
@@ -495,6 +477,10 @@
 extern const struct dentry_operations nfs_dentry_operations;
 
 extern void nfs_force_lookup_revalidate(struct inode *dir);
+extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf);
+#if IS_ENABLED(CONFIG_NFS_V4)
+extern void nfs_clear_verifier_delegated(struct inode *inode);
+#endif /* IS_ENABLED(CONFIG_NFS_V4) */
 extern struct dentry *nfs_add_or_obtain(struct dentry *dentry,
 			struct nfs_fh *fh, struct nfs_fattr *fattr,
 			struct nfs4_label *label);
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index d576503..ae58fad 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -29,7 +29,8 @@
 /**
  *	struct pipe_inode_info - a linux kernel pipe
  *	@mutex: mutex protecting the whole thing
- *	@wait: reader/writer wait point in case of empty/full pipe
+ *	@rd_wait: reader wait point in case of empty pipe
+ *	@wr_wait: writer wait point in case of full pipe
  *	@head: The point of buffer production
  *	@tail: The point of buffer consumption
  *	@max_usage: The maximum number of slots that may be used in the ring
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index e5b7520..9670b54 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -145,6 +145,13 @@
 	}
 }
 
+/* after that hlist_nulls_del will work */
+static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
+{
+	n->pprev = &n->next;
+	n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL);
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index 1abe91f..6d67e9a 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -15,9 +15,11 @@
 
 #ifdef CONFIG_NO_HZ_COMMON
 void calc_load_nohz_start(void);
+void calc_load_nohz_remote(struct rq *rq);
 void calc_load_nohz_stop(void);
 #else
 static inline void calc_load_nohz_start(void) { }
+static inline void calc_load_nohz_remote(struct rq *rq) { }
 static inline void calc_load_nohz_stop(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ca8806b..5b50278 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -611,9 +611,15 @@
  *	@next: Next buffer in list
  *	@prev: Previous buffer in list
  *	@tstamp: Time we arrived/left
+ *	@skb_mstamp_ns: (aka @tstamp) earliest departure time; start point
+ *		for retransmit timer
  *	@rbnode: RB tree node, alternative to next/prev for netem/tcp
+ *	@list: queue head
  *	@sk: Socket we are owned by
+ *	@ip_defrag_offset: (aka @sk) alternate use of @sk, used in
+ *		fragmentation management
  *	@dev: Device we arrived on/are leaving by
+ *	@dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
  *	@sp: the security path, used for xfrm
@@ -632,6 +638,9 @@
  *	@pkt_type: Packet class
  *	@fclone: skbuff clone status
  *	@ipvs_property: skbuff is owned by ipvs
+ *	@inner_protocol_type: whether the inner protocol is
+ *		ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO
+ *	@remcsum_offload: remote checksum offload is enabled
  *	@offload_fwd_mark: Packet was L2-forwarded in hardware
  *	@offload_l3_fwd_mark: Packet was L3-forwarded in hardware
  *	@tc_skip_classify: do not classify packet. set by IFB device
@@ -650,6 +659,8 @@
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
+ *	@head_frag: skb was allocated from page fragments,
+ *		not allocated by kmalloc() or vmalloc().
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@active_extensions: active extensions (skb_ext_id types)
  *	@ndisc_nodetype: router type (from link layer)
@@ -660,15 +671,28 @@
  *	@wifi_acked_valid: wifi_acked was set
  *	@wifi_acked: whether frame was acked on wifi or not
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
+ *	@encapsulation: indicates the inner headers in the skbuff are valid
+ *	@encap_hdr_csum: software checksum is needed
+ *	@csum_valid: checksum is already valid
  *	@csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
+ *	@csum_complete_sw: checksum was completed by software
+ *	@csum_level: indicates the number of consecutive checksums found in
+ *		the packet minus one that have been verified as
+ *		CHECKSUM_UNNECESSARY (max 3)
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@napi_id: id of the NAPI struct this skb came from
+ *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@secmark: security marking
  *	@mark: Generic packet mark
+ *	@reserved_tailroom: (aka @mark) number of bytes of free space available
+ *		at the tail of an sk_buff
+ *	@vlan_present: VLAN tag is present
  *	@vlan_proto: vlan encapsulation protocol
  *	@vlan_tci: vlan tag control information
  *	@inner_protocol: Protocol (encapsulation)
+ *	@inner_ipproto: (aka @inner_protocol) stores ipproto when
+ *		skb->inner_protocol_type == ENCAP_TYPE_IPPROTO;
  *	@inner_transport_header: Inner transport layer header (encapsulation)
  *	@inner_network_header: Network layer header (encapsulation)
  *	@inner_mac_header: Link layer header (encapsulation)
@@ -750,7 +774,9 @@
 #endif
 #define CLONED_OFFSET()		offsetof(struct sk_buff, __cloned_offset)
 
+	/* private: */
 	__u8			__cloned_offset[0];
+	/* public: */
 	__u8			cloned:1,
 				nohdr:1,
 				fclone:2,
@@ -775,7 +801,9 @@
 #endif
 #define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)
 
+	/* private: */
 	__u8			__pkt_type_offset[0];
+	/* public: */
 	__u8			pkt_type:3;
 	__u8			ignore_df:1;
 	__u8			nf_trace:1;
@@ -798,7 +826,9 @@
 #define PKT_VLAN_PRESENT_BIT	0
 #endif
 #define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, __pkt_vlan_present_offset)
+	/* private: */
 	__u8			__pkt_vlan_present_offset[0];
+	/* public: */
 	__u8			vlan_present:1;
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 4a230c2..2b2055b 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -191,7 +191,7 @@
 	int (*begin)(void);
 	int (*prepare)(void);
 	int (*prepare_late)(void);
-	void (*wake)(void);
+	bool (*wake)(void);
 	void (*restore_early)(void);
 	void (*restore)(void);
 	void (*end)(void);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index cde3dc1..046bb94 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -64,6 +64,9 @@
 				    size_t size, enum dma_data_direction dir,
 				    enum dma_sync_target target);
 
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+
 #ifdef CONFIG_SWIOTLB
 extern enum swiotlb_force swiotlb_force;
 extern phys_addr_t io_tlb_start, io_tlb_end;
@@ -73,8 +76,6 @@
 	return paddr >= io_tlb_start && paddr < io_tlb_end;
 }
 
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
@@ -85,12 +86,6 @@
 {
 	return false;
 }
-static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys,
-		dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	return false;
-}
 static inline void swiotlb_exit(void)
 {
 }
diff --git a/include/linux/time32.h b/include/linux/time32.h
index cad4c31..cf9320c 100644
--- a/include/linux/time32.h
+++ b/include/linux/time32.h
@@ -12,8 +12,6 @@
 #include <linux/time64.h>
 #include <linux/timex.h>
 
-#define TIME_T_MAX	(__kernel_old_time_t)((1UL << ((sizeof(__kernel_old_time_t) << 3) - 1)) - 1)
-
 typedef s32		old_time32_t;
 
 struct old_timespec32 {
@@ -73,162 +71,12 @@
 int get_old_timex32(struct __kernel_timex *, const struct old_timex32 __user *);
 int put_old_timex32(struct old_timex32 __user *, const struct __kernel_timex *);
 
-#if __BITS_PER_LONG == 64
-
-/* timespec64 is defined as timespec here */
-static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
-{
-	return *(const struct timespec *)&ts64;
-}
-
-static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
-{
-	return *(const struct timespec64 *)&ts;
-}
-
-#else
-static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
-{
-	struct timespec ret;
-
-	ret.tv_sec = (time_t)ts64.tv_sec;
-	ret.tv_nsec = ts64.tv_nsec;
-	return ret;
-}
-
-static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
-{
-	struct timespec64 ret;
-
-	ret.tv_sec = ts.tv_sec;
-	ret.tv_nsec = ts.tv_nsec;
-	return ret;
-}
-#endif
-
-static inline int timespec_equal(const struct timespec *a,
-				 const struct timespec *b)
-{
-	return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec);
-}
-
-/*
- * lhs < rhs:  return <0
- * lhs == rhs: return 0
- * lhs > rhs:  return >0
- */
-static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs)
-{
-	if (lhs->tv_sec < rhs->tv_sec)
-		return -1;
-	if (lhs->tv_sec > rhs->tv_sec)
-		return 1;
-	return lhs->tv_nsec - rhs->tv_nsec;
-}
-
-/*
- * Returns true if the timespec is norm, false if denorm:
- */
-static inline bool timespec_valid(const struct timespec *ts)
-{
-	/* Dates before 1970 are bogus */
-	if (ts->tv_sec < 0)
-		return false;
-	/* Can't have more nanoseconds then a second */
-	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
-		return false;
-	return true;
-}
-
 /**
- * timespec_to_ns - Convert timespec to nanoseconds
- * @ts:		pointer to the timespec variable to be converted
- *
- * Returns the scalar nanosecond representation of the timespec
- * parameter.
- */
-static inline s64 timespec_to_ns(const struct timespec *ts)
-{
-	return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
-}
-
-/**
- * ns_to_timespec - Convert nanoseconds to timespec
- * @nsec:	the nanoseconds value to be converted
- *
- * Returns the timespec representation of the nsec parameter.
- */
-extern struct timespec ns_to_timespec(const s64 nsec);
-
-/**
- * timespec_add_ns - Adds nanoseconds to a timespec
- * @a:		pointer to timespec to be incremented
- * @ns:		unsigned nanoseconds value to be added
- *
- * This must always be inlined because its used from the x86-64 vdso,
- * which cannot call other kernel functions.
- */
-static __always_inline void timespec_add_ns(struct timespec *a, u64 ns)
-{
-	a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
-	a->tv_nsec = ns;
-}
-
-static inline unsigned long mktime(const unsigned int year,
-			const unsigned int mon, const unsigned int day,
-			const unsigned int hour, const unsigned int min,
-			const unsigned int sec)
-{
-	return mktime64(year, mon, day, hour, min, sec);
-}
-
-static inline bool timeval_valid(const struct timeval *tv)
-{
-	/* Dates before 1970 are bogus */
-	if (tv->tv_sec < 0)
-		return false;
-
-	/* Can't have more microseconds then a second */
-	if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
-		return false;
-
-	return true;
-}
-
-/**
- * timeval_to_ns - Convert timeval to nanoseconds
- * @ts:		pointer to the timeval variable to be converted
- *
- * Returns the scalar nanosecond representation of the timeval
- * parameter.
- */
-static inline s64 timeval_to_ns(const struct timeval *tv)
-{
-	return ((s64) tv->tv_sec * NSEC_PER_SEC) +
-		tv->tv_usec * NSEC_PER_USEC;
-}
-
-/**
- * ns_to_timeval - Convert nanoseconds to timeval
+ * ns_to_kernel_old_timeval - Convert nanoseconds to timeval
  * @nsec:	the nanoseconds value to be converted
  *
  * Returns the timeval representation of the nsec parameter.
  */
-extern struct timeval ns_to_timeval(const s64 nsec);
 extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec);
 
-/*
- * Old names for the 32-bit time_t interfaces, these will be removed
- * when everything uses the new names.
- */
-#define compat_time_t		old_time32_t
-#define compat_timeval		old_timeval32
-#define compat_timespec		old_timespec32
-#define compat_itimerspec	old_itimerspec32
-#define ns_to_compat_timeval	ns_to_old_timeval32
-#define get_compat_itimerspec64	get_old_itimerspec32
-#define put_compat_itimerspec64	put_old_itimerspec32
-#define compat_get_timespec64	get_old_timespec32
-#define compat_put_timespec64	put_old_timespec32
-
 #endif
diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h
index cc59cc9..266017f 100644
--- a/include/linux/timekeeping32.h
+++ b/include/linux/timekeeping32.h
@@ -11,36 +11,4 @@
 	return ktime_get_real_seconds();
 }
 
-static inline void getnstimeofday(struct timespec *ts)
-{
-	struct timespec64 ts64;
-
-	ktime_get_real_ts64(&ts64);
-	*ts = timespec64_to_timespec(ts64);
-}
-
-static inline void ktime_get_ts(struct timespec *ts)
-{
-	struct timespec64 ts64;
-
-	ktime_get_ts64(&ts64);
-	*ts = timespec64_to_timespec(ts64);
-}
-
-static inline void getrawmonotonic(struct timespec *ts)
-{
-	struct timespec64 ts64;
-
-	ktime_get_raw_ts64(&ts64);
-	*ts = timespec64_to_timespec(ts64);
-}
-
-static inline void getboottime(struct timespec *ts)
-{
-	struct timespec64 ts64;
-
-	getboottime64(&ts64);
-	*ts = timespec64_to_timespec(ts64);
-}
-
 #endif
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index af2c85d..6c7a10a 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -440,7 +440,7 @@
 	struct synth_event *event;
 	unsigned int cur_field;
 	unsigned int n_u64;
-	bool enabled;
+	bool disabled;
 	bool add_next;
 	bool add_name;
 };
diff --git a/include/linux/types.h b/include/linux/types.h
index eb870ad..d3021c8 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -65,11 +65,6 @@
 typedef __kernel_ptrdiff_t	ptrdiff_t;
 #endif
 
-#ifndef _TIME_T
-#define _TIME_T
-typedef __kernel_old_time_t	time_t;
-#endif
-
 #ifndef _CLOCK_T
 #define _CLOCK_T
 typedef __kernel_clock_t	clock_t;
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index a1be64c..22c1f57 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -69,4 +69,7 @@
 /* Hub needs extra delay after resetting its port. */
 #define USB_QUIRK_HUB_SLOW_RESET		BIT(14)
 
+/* device has blacklisted endpoints */
+#define USB_QUIRK_ENDPOINT_BLACKLIST		BIT(15)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index d93017a..6283839 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <linux/siphash.h>
+#include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
 struct sk_buff;
@@ -33,7 +34,6 @@
 
 /**
  * struct flow_dissector_key_basic:
- * @thoff: Transport header offset
  * @n_proto: Network header protocol (eg. IPv4/IPv6)
  * @ip_proto: Transport header protocol (eg. TCP/UDP)
  */
@@ -349,4 +349,12 @@
 	void			*data_end;
 };
 
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+			 struct flow_dissector_key_basic *key_basic)
+{
+	memset(key_control, 0, sizeof(*key_control));
+	memset(key_basic, 0, sizeof(*key_basic));
+}
+
 #endif
diff --git a/include/net/icmp.h b/include/net/icmp.h
index 5d4bfdb..9ac2d26 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -43,6 +43,12 @@
 	__icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt);
 }
 
+#if IS_ENABLED(CONFIG_NF_NAT)
+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info);
+#else
+#define icmp_ndo_send icmp_send
+#endif
+
 int icmp_rcv(struct sk_buff *skb);
 int icmp_err(struct sk_buff *skb, u32 info);
 int icmp_init(void);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index aa14580..77e6b5a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1004,12 +1004,11 @@
 struct ieee80211_tx_info {
 	/* common information */
 	u32 flags;
-	u8 band;
-
-	u8 hw_queue;
-
-	u16 ack_frame_id:6;
-	u16 tx_time_est:10;
+	u32 band:3,
+	    ack_frame_id:13,
+	    hw_queue:4,
+	    tx_time_est:10;
+	/* 2 free bits */
 
 	union {
 		struct {
diff --git a/include/net/sock.h b/include/net/sock.h
index 02162b0..3285645 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -117,19 +117,26 @@
  *	struct sock_common - minimal network layer representation of sockets
  *	@skc_daddr: Foreign IPv4 addr
  *	@skc_rcv_saddr: Bound local IPv4 addr
+ *	@skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr
  *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_u16hashes: two u16 hash values used by UDP lookup tables
  *	@skc_dport: placeholder for inet_dport/tw_dport
  *	@skc_num: placeholder for inet_num/tw_num
+ *	@skc_portpair: __u32 union of @skc_dport & @skc_num
  *	@skc_family: network address family
  *	@skc_state: Connection state
  *	@skc_reuse: %SO_REUSEADDR setting
  *	@skc_reuseport: %SO_REUSEPORT setting
+ *	@skc_ipv6only: socket is IPV6 only
+ *	@skc_net_refcnt: socket is using net ref counting
  *	@skc_bound_dev_if: bound device index if != 0
  *	@skc_bind_node: bind hash linkage for various protocol lookup tables
  *	@skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
  *	@skc_prot: protocol handlers inside a network family
  *	@skc_net: reference to the network namespace of this socket
+ *	@skc_v6_daddr: IPV6 destination address
+ *	@skc_v6_rcv_saddr: IPV6 source address
+ *	@skc_cookie: socket's cookie value
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
  *	@skc_tx_queue_mapping: tx queue number for this connection
@@ -137,7 +144,15 @@
  *	@skc_flags: place holder for sk_flags
  *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ *	@skc_listener: connection request listener socket (aka rsk_listener)
+ *		[union with @skc_flags]
+ *	@skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row
+ *		[union with @skc_flags]
  *	@skc_incoming_cpu: record/match cpu processing incoming packets
+ *	@skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled)
+ *		[union with @skc_incoming_cpu]
+ *	@skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number
+ *		[union with @skc_incoming_cpu]
  *	@skc_refcnt: reference count
  *
  *	This is the minimal network layer representation of sockets, the header
@@ -245,6 +260,7 @@
   *	@sk_dst_cache: destination cache
   *	@sk_dst_pending_confirm: need to confirm neighbour
   *	@sk_policy: flow policy
+  *	@sk_rx_skb_cache: cache copy of recently accessed RX skb
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
   *	@sk_tsq_flags: TCP Small Queues flags
@@ -265,6 +281,8 @@
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
+  *	@sk_route_forced_caps: static, forced route capabilities
+  *		(set in tcp_init_sock())
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
   *	@sk_gso_max_size: Maximum GSO segment size to build
   *	@sk_gso_max_segs: Maximum number of GSO segments
@@ -303,6 +321,8 @@
   *	@sk_frag: cached page frag
   *	@sk_peek_off: current peek_offset value
   *	@sk_send_head: front of stuff to transmit
+  *	@tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
+  *	@sk_tx_skb_cache: cache copy of recently accessed TX skb
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
   *	@sk_cgrp_data: cgroup data for this cgroup
@@ -313,11 +333,14 @@
   *	@sk_write_space: callback to indicate there is bf sending space available
   *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
   *	@sk_backlog_rcv: callback to process the backlog
+  *	@sk_validate_xmit_skb: ptr to an optional validate function
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
+  *	@sk_bpf_storage: ptr to cache and control for bpf_sk_storage
   *	@sk_rcu: used during RCU grace period
   *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
   *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+  *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   */
 struct sock {
@@ -393,7 +416,9 @@
 	struct sk_filter __rcu	*sk_filter;
 	union {
 		struct socket_wq __rcu	*sk_wq;
+		/* private: */
 		struct socket_wq	*sk_wq_raw;
+		/* public: */
 	};
 #ifdef CONFIG_XFRM
 	struct xfrm_policy __rcu *sk_policy[2];
@@ -2017,7 +2042,7 @@
  * sk_wmem_alloc_get - returns write allocations
  * @sk: socket
  *
- * Returns sk_wmem_alloc minus initial offset of one
+ * Return: sk_wmem_alloc minus initial offset of one
  */
 static inline int sk_wmem_alloc_get(const struct sock *sk)
 {
@@ -2028,7 +2053,7 @@
  * sk_rmem_alloc_get - returns read allocations
  * @sk: socket
  *
- * Returns sk_rmem_alloc
+ * Return: sk_rmem_alloc
  */
 static inline int sk_rmem_alloc_get(const struct sock *sk)
 {
@@ -2039,7 +2064,7 @@
  * sk_has_allocations - check if allocations are outstanding
  * @sk: socket
  *
- * Returns true if socket has write or read allocations
+ * Return: true if socket has write or read allocations
  */
 static inline bool sk_has_allocations(const struct sock *sk)
 {
@@ -2050,7 +2075,7 @@
  * skwq_has_sleeper - check if there are any waiting processes
  * @wq: struct socket_wq
  *
- * Returns true if socket_wq has waiting processes
+ * Return: true if socket_wq has waiting processes
  *
  * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
  * barrier call. They were added due to the race found within the tcp code.
@@ -2238,6 +2263,9 @@
  * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
  * inside other socket operations and end up recursing into sk_page_frag()
  * while it's already in use.
+ *
+ * Return: a per task page_frag if context allows that,
+ * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
@@ -2432,6 +2460,7 @@
 			   &skb_shinfo(skb)->tskey);
 }
 
+DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
@@ -2440,7 +2469,6 @@
  * This routine must be called with interrupts disabled or with the socket
  * locked so that the sk_buff queue operation is ok.
 */
-DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h
index 40ab204..a36b722 100644
--- a/include/sound/rawmidi.h
+++ b/include/sound/rawmidi.h
@@ -77,9 +77,9 @@
 	struct list_head list;		/* list of all substream for given stream */
 	int stream;			/* direction */
 	int number;			/* substream number */
-	unsigned int opened: 1,		/* open flag */
-		     append: 1,		/* append flag (merge more streams) */
-		     active_sensing: 1; /* send active sensing when close */
+	bool opened;			/* open flag */
+	bool append;			/* append flag (merge more streams) */
+	bool active_sensing;		/* send active sensing when close */
 	int use_count;			/* use counter (for output) */
 	size_t bytes;
 	struct snd_rawmidi *rmidi;
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 2a306c6..1b6afbc 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -392,8 +392,6 @@
 	struct snd_ctl_elem_value *ucontrol);
 int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol);
-int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol);
 int snd_soc_dapm_info_pin_switch(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_info *uinfo);
 int snd_soc_dapm_get_pin_switch(struct snd_kcontrol *kcontrol,
diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h
index 2f9c805..b5f7594 100644
--- a/include/uapi/asm-generic/posix_types.h
+++ b/include/uapi/asm-generic/posix_types.h
@@ -87,7 +87,9 @@
 typedef __kernel_long_t	__kernel_off_t;
 typedef long long	__kernel_loff_t;
 typedef __kernel_long_t	__kernel_old_time_t;
+#ifndef __KERNEL__
 typedef __kernel_long_t	__kernel_time_t;
+#endif
 typedef long long __kernel_time64_t;
 typedef __kernel_long_t	__kernel_clock_t;
 typedef int		__kernel_timer_t;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f1d74a2..22f2352 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1045,9 +1045,9 @@
  * 		supports redirection to the egress interface, and accepts no
  * 		flag at all.
  *
- * 		The same effect can be attained with the more generic
- * 		**bpf_redirect_map**\ (), which requires specific maps to be
- * 		used but offers better performance.
+ * 		The same effect can also be attained with the more generic
+ * 		**bpf_redirect_map**\ (), which uses a BPF map to store the
+ * 		redirect target instead of providing it directly to the helper.
  * 	Return
  * 		For XDP, the helper returns **XDP_REDIRECT** on success or
  * 		**XDP_ABORTED** on error. For other program types, the values
@@ -1611,13 +1611,11 @@
  * 		the caller. Any higher bits in the *flags* argument must be
  * 		unset.
  *
- * 		When used to redirect packets to net devices, this helper
- * 		provides a high performance increase over **bpf_redirect**\ ().
- * 		This is due to various implementation details of the underlying
- * 		mechanisms, one of which is the fact that **bpf_redirect_map**\
- * 		() tries to send packet as a "bulk" to the device.
+ * 		See also bpf_redirect(), which only supports redirecting to an
+ * 		ifindex, but doesn't require a map to do so.
  * 	Return
- * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * 		**XDP_REDIRECT** on success, or the value of the two lower bits
+ * 		of the **flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 336014b..b6f0bb1 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -97,6 +97,15 @@
 	IPS_UNTRACKED_BIT = 12,
 	IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
 
+#ifdef __KERNEL__
+	/* Re-purposed for in-kernel use:
+	 * Tags a conntrack entry that clashed with an existing entry
+	 * on insert.
+	 */
+	IPS_NAT_CLASH_BIT = IPS_UNTRACKED_BIT,
+	IPS_NAT_CLASH = IPS_UNTRACKED,
+#endif
+
 	/* Conntrack got a helper explicitly attached via CT target. */
 	IPS_HELPER_BIT = 13,
 	IPS_HELPER = (1 << IPS_HELPER_BIT),
@@ -110,7 +119,8 @@
 	 */
 	IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
 				 IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
-				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD),
+				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED |
+				 IPS_OFFLOAD),
 
 	__IPS_MAX_BIT = 15,
 };
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index fa7f97d..7272f85 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -135,9 +135,9 @@
 
 static __always_inline unsigned long __swab(const unsigned long y)
 {
-#if BITS_PER_LONG == 64
+#if __BITS_PER_LONG == 64
 	return __swab64(y);
-#else /* BITS_PER_LONG == 32 */
+#else /* __BITS_PER_LONG == 32 */
 	return __swab32(y);
 #endif
 }
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index a655aa2..4f4b6e4 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/time_types.h>
 
+#ifndef __KERNEL__
 #ifndef _STRUCT_TIMESPEC
 #define _STRUCT_TIMESPEC
 struct timespec {
@@ -18,6 +19,17 @@
 	__kernel_suseconds_t	tv_usec;	/* microseconds */
 };
 
+struct itimerspec {
+	struct timespec it_interval;/* timer period */
+	struct timespec it_value;	/* timer expiration */
+};
+
+struct itimerval {
+	struct timeval it_interval;/* timer interval */
+	struct timeval it_value;	/* current value */
+};
+#endif
+
 struct timezone {
 	int	tz_minuteswest;	/* minutes west of Greenwich */
 	int	tz_dsttime;	/* type of dst correction */
@@ -31,16 +43,6 @@
 #define	ITIMER_VIRTUAL		1
 #define	ITIMER_PROF		2
 
-struct itimerspec {
-	struct timespec it_interval;	/* timer period */
-	struct timespec it_value;	/* timer expiration */
-};
-
-struct itimerval {
-	struct timeval it_interval;	/* timer interval */
-	struct timeval it_value;	/* current value */
-};
-
 /*
  * The IDs of the various system clocks (for POSIX.1b interval timers):
  */
diff --git a/include/uapi/linux/usb/charger.h b/include/uapi/linux/usb/charger.h
index 5f72af3..ad22079 100644
--- a/include/uapi/linux/usb/charger.h
+++ b/include/uapi/linux/usb/charger.h
@@ -14,18 +14,18 @@
  * ACA (Accessory Charger Adapters)
  */
 enum usb_charger_type {
-	UNKNOWN_TYPE,
-	SDP_TYPE,
-	DCP_TYPE,
-	CDP_TYPE,
-	ACA_TYPE,
+	UNKNOWN_TYPE = 0,
+	SDP_TYPE = 1,
+	DCP_TYPE = 2,
+	CDP_TYPE = 3,
+	ACA_TYPE = 4,
 };
 
 /* USB charger state */
 enum usb_charger_state {
-	USB_CHARGER_DEFAULT,
-	USB_CHARGER_PRESENT,
-	USB_CHARGER_ABSENT,
+	USB_CHARGER_DEFAULT = 0,
+	USB_CHARGER_PRESENT = 1,
+	USB_CHARGER_ABSENT = 2,
 };
 
 #endif /* _UAPI__LINUX_USB_CHARGER_H */
diff --git a/init/Kconfig b/init/Kconfig
index cfee56c..452bc18 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1227,7 +1227,6 @@
 config BOOT_CONFIG
 	bool "Boot config support"
 	depends on BLK_DEV_INITRD
-	select LIBXBC
 	default y
 	help
 	  Extra boot config allows system admin to pass a config file as
diff --git a/init/main.c b/init/main.c
index cc0ee48..f95b014 100644
--- a/init/main.c
+++ b/init/main.c
@@ -142,6 +142,15 @@
 /* Extra init arguments */
 static char *extra_init_args;
 
+#ifdef CONFIG_BOOT_CONFIG
+/* Is bootconfig on command line? */
+static bool bootconfig_found;
+static bool initargs_found;
+#else
+# define bootconfig_found false
+# define initargs_found false
+#endif
+
 static char *execute_command;
 static char *ramdisk_execute_command;
 
@@ -336,17 +345,30 @@
 	return ret;
 }
 
+static int __init bootconfig_params(char *param, char *val,
+				    const char *unused, void *arg)
+{
+	if (strcmp(param, "bootconfig") == 0) {
+		bootconfig_found = true;
+	} else if (strcmp(param, "--") == 0) {
+		initargs_found = true;
+	}
+	return 0;
+}
+
 static void __init setup_boot_config(const char *cmdline)
 {
+	static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
 	u32 size, csum;
 	char *data, *copy;
-	const char *p;
 	u32 *hdr;
 	int ret;
 
-	p = strstr(cmdline, "bootconfig");
-	if (!p || (p != cmdline && !isspace(*(p-1))) ||
-	    (p[10] && !isspace(p[10])))
+	strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+	parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
+		   bootconfig_params);
+
+	if (!bootconfig_found)
 		return;
 
 	if (!initrd_end)
@@ -562,11 +584,12 @@
 		 * to init.
 		 */
 		len = strlen(saved_command_line);
-		if (!strstr(boot_command_line, " -- ")) {
+		if (initargs_found) {
+			saved_command_line[len++] = ' ';
+		} else {
 			strcpy(saved_command_line + len, " -- ");
 			len += 4;
-		} else
-			saved_command_line[len++] = ' ';
+		}
 
 		strcpy(saved_command_line + len, extra_init_args);
 	}
diff --git a/ipc/sem.c b/ipc/sem.c
index 4f4303f..3687b71 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -2384,11 +2384,9 @@
 		ipc_assert_locked_object(&sma->sem_perm);
 		list_del(&un->list_id);
 
-		/* we are the last process using this ulp, acquiring ulp->lock
-		 * isn't required. Besides that, we are also protected against
-		 * IPC_RMID as we hold sma->sem_perm lock now
-		 */
+		spin_lock(&ulp->lock);
 		list_del_rcu(&un->list_proc);
+		spin_unlock(&ulp->lock);
 
 		/* perform adjustments registered in un */
 		for (i = 0; i < sma->sem_nsems; i++) {
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 805c43b..7871400 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4142,9 +4142,9 @@
  * EFAULT - verifier bug
  * 0 - 99% match. The last 1% is validated by the verifier.
  */
-int btf_check_func_type_match(struct bpf_verifier_log *log,
-			      struct btf *btf1, const struct btf_type *t1,
-			      struct btf *btf2, const struct btf_type *t2)
+static int btf_check_func_type_match(struct bpf_verifier_log *log,
+				     struct btf *btf1, const struct btf_type *t1,
+				     struct btf *btf2, const struct btf_type *t2)
 {
 	const struct btf_param *args1, *args2;
 	const char *fn1, *fn2, *s1, *s2;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 2d182c4..a1468e3 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -56,6 +56,7 @@
 			union {
 				struct bpf_htab *htab;
 				struct pcpu_freelist_node fnode;
+				struct htab_elem *batch_flink;
 			};
 		};
 	};
@@ -126,6 +127,17 @@
 	bpf_map_area_free(htab->elems);
 }
 
+/* The LRU list has a lock (lru_lock). Each htab bucket has a lock
+ * (bucket_lock). If both locks need to be acquired together, the lock
+ * order is always lru_lock -> bucket_lock and this only happens in
+ * bpf_lru_list.c logic. For example, certain code path of
+ * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(),
+ * will acquire lru_lock first followed by acquiring bucket_lock.
+ *
+ * In hashtab.c, to avoid deadlock, lock acquisition of
+ * bucket_lock followed by lru_lock is not allowed. In such cases,
+ * bucket_lock needs to be released first before acquiring lru_lock.
+ */
 static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 					  u32 hash)
 {
@@ -1256,10 +1268,12 @@
 	void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
 	void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
 	u32 batch, max_count, size, bucket_size;
+	struct htab_elem *node_to_free = NULL;
 	u64 elem_map_flags, map_flags;
 	struct hlist_nulls_head *head;
 	struct hlist_nulls_node *n;
-	unsigned long flags;
+	unsigned long flags = 0;
+	bool locked = false;
 	struct htab_elem *l;
 	struct bucket *b;
 	int ret = 0;
@@ -1319,15 +1333,25 @@
 	dst_val = values;
 	b = &htab->buckets[batch];
 	head = &b->head;
-	raw_spin_lock_irqsave(&b->lock, flags);
+	/* do not grab the lock unless need it (bucket_cnt > 0). */
+	if (locked)
+		raw_spin_lock_irqsave(&b->lock, flags);
 
 	bucket_cnt = 0;
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		bucket_cnt++;
 
+	if (bucket_cnt && !locked) {
+		locked = true;
+		goto again_nocopy;
+	}
+
 	if (bucket_cnt > (max_count - total)) {
 		if (total == 0)
 			ret = -ENOSPC;
+		/* Note that since bucket_cnt > 0 here, it is implicit
+		 * that the locked was grabbed, so release it.
+		 */
 		raw_spin_unlock_irqrestore(&b->lock, flags);
 		rcu_read_unlock();
 		this_cpu_dec(bpf_prog_active);
@@ -1337,6 +1361,9 @@
 
 	if (bucket_cnt > bucket_size) {
 		bucket_size = bucket_cnt;
+		/* Note that since bucket_cnt > 0 here, it is implicit
+		 * that the locked was grabbed, so release it.
+		 */
 		raw_spin_unlock_irqrestore(&b->lock, flags);
 		rcu_read_unlock();
 		this_cpu_dec(bpf_prog_active);
@@ -1346,6 +1373,10 @@
 		goto alloc;
 	}
 
+	/* Next block is only safe to run if you have grabbed the lock */
+	if (!locked)
+		goto next_batch;
+
 	hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
 		memcpy(dst_key, l->key, key_size);
 
@@ -1370,16 +1401,33 @@
 		}
 		if (do_delete) {
 			hlist_nulls_del_rcu(&l->hash_node);
-			if (is_lru_map)
-				bpf_lru_push_free(&htab->lru, &l->lru_node);
-			else
+
+			/* bpf_lru_push_free() will acquire lru_lock, which
+			 * may cause deadlock. See comments in function
+			 * prealloc_lru_pop(). Let us do bpf_lru_push_free()
+			 * after releasing the bucket lock.
+			 */
+			if (is_lru_map) {
+				l->batch_flink = node_to_free;
+				node_to_free = l;
+			} else {
 				free_htab_elem(htab, l);
+			}
 		}
 		dst_key += key_size;
 		dst_val += value_size;
 	}
 
 	raw_spin_unlock_irqrestore(&b->lock, flags);
+	locked = false;
+
+	while (node_to_free) {
+		l = node_to_free;
+		node_to_free = node_to_free->batch_flink;
+		bpf_lru_push_free(&htab->lru, &l->lru_node);
+	}
+
+next_batch:
 	/* If we are not copying data, we can go to next bucket and avoid
 	 * unlocking the rcu.
 	 */
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 2c5dc65..bd09290 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -321,7 +321,7 @@
 
 	ulen = info->jited_prog_len;
 	info->jited_prog_len = aux->offload->jited_len;
-	if (info->jited_prog_len & ulen) {
+	if (info->jited_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info->jited_prog_insns);
 		ulen = min_t(u32, info->jited_prog_len, ulen);
 		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index db552b9..75f6873 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5927,11 +5927,14 @@
 
 	spin_lock_irq(&css_set_lock);
 
-	WARN_ON_ONCE(!list_empty(&child->cg_list));
-	cset = task_css_set(current); /* current is @child's parent */
-	get_css_set(cset);
-	cset->nr_tasks++;
-	css_set_move_task(child, NULL, cset, false);
+	/* init tasks are special, only link regular threads */
+	if (likely(child->pid)) {
+		WARN_ON_ONCE(!list_empty(&child->cg_list));
+		cset = task_css_set(current); /* current is @child's parent */
+		get_css_set(cset);
+		cset->nr_tasks++;
+		css_set_move_task(child, NULL, cset, false);
+	}
 
 	/*
 	 * If the cgroup has to be frozen, the new task has too.  Let's set
diff --git a/kernel/compat.c b/kernel/compat.c
index 95005f8..843dd17 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -26,70 +26,6 @@
 
 #include <linux/uaccess.h>
 
-static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv)
-{
-	return (!access_ok(ctv, sizeof(*ctv)) ||
-			__get_user(tv->tv_sec, &ctv->tv_sec) ||
-			__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
-}
-
-static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv)
-{
-	return (!access_ok(ctv, sizeof(*ctv)) ||
-			__put_user(tv->tv_sec, &ctv->tv_sec) ||
-			__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
-}
-
-static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts)
-{
-	return (!access_ok(cts, sizeof(*cts)) ||
-			__get_user(ts->tv_sec, &cts->tv_sec) ||
-			__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
-}
-
-static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts)
-{
-	return (!access_ok(cts, sizeof(*cts)) ||
-			__put_user(ts->tv_sec, &cts->tv_sec) ||
-			__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
-}
-
-int compat_get_timeval(struct timeval *tv, const void __user *utv)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0;
-	else
-		return __compat_get_timeval(tv, utv);
-}
-EXPORT_SYMBOL_GPL(compat_get_timeval);
-
-int compat_put_timeval(const struct timeval *tv, void __user *utv)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0;
-	else
-		return __compat_put_timeval(tv, utv);
-}
-EXPORT_SYMBOL_GPL(compat_put_timeval);
-
-int compat_get_timespec(struct timespec *ts, const void __user *uts)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
-	else
-		return __compat_get_timespec(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_get_timespec);
-
-int compat_put_timespec(const struct timespec *ts, void __user *uts)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
-	else
-		return __compat_put_timespec(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_put_timespec);
-
 #ifdef __ARCH_WANT_SYS_SIGPROCMASK
 
 /*
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index daa4e6e..8bc6f2d 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -302,9 +302,16 @@
 	phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
 	phys_addr_t mask = align - 1;
 	unsigned long node = rmem->fdt_node;
+	bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL);
 	struct cma *cma;
 	int err;
 
+	if (size_cmdline != -1 && default_cma) {
+		pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n",
+			rmem->name);
+		return -EBUSY;
+	}
+
 	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
 	    of_get_flat_dt_prop(node, "no-map", NULL))
 		return -EINVAL;
@@ -322,7 +329,7 @@
 	/* Architecture specific contiguous memory fixup. */
 	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
-	if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+	if (default_cma)
 		dma_contiguous_set_default(cma);
 
 	rmem->ops = &rmem_cma_ops;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 6af7ae8..ac7956c 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -23,18 +23,6 @@
  */
 unsigned int zone_dma_bits __ro_after_init = 24;
 
-static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	if (!dev->dma_mask) {
-		dev_err_once(dev, "DMA map on device without dma_mask\n");
-	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) {
-		dev_err_once(dev,
-			"overflow %pad+%zu of DMA mask %llx bus limit %llx\n",
-			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-	}
-	WARN_ON_ONCE(1);
-}
-
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
@@ -357,13 +345,6 @@
 EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
-static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
-		size_t size)
-{
-	return swiotlb_force != SWIOTLB_FORCE &&
-		dma_capable(dev, dma_addr, size, true);
-}
-
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -371,9 +352,16 @@
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
-	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
-		report_addr(dev, dma_addr, size);
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -411,7 +399,10 @@
 	dma_addr_t dma_addr = paddr;
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		report_addr(dev, dma_addr, size);
+		dev_err_once(dev,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		WARN_ON_ONCE(1);
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -472,28 +463,26 @@
 }
 #endif /* CONFIG_MMU */
 
-/*
- * Because 32-bit DMA masks are so common we expect every architecture to be
- * able to satisfy them - either by not supporting more physical memory, or by
- * providing a ZONE_DMA32.  If neither is the case, the architecture needs to
- * use an IOMMU instead of the direct mapping.
- */
 int dma_direct_supported(struct device *dev, u64 mask)
 {
-	u64 min_mask;
+	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		min_mask = DMA_BIT_MASK(zone_dma_bits);
-	else
-		min_mask = DMA_BIT_MASK(32);
-
-	min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);
+	/*
+	 * Because 32-bit DMA masks are so common we expect every architecture
+	 * to be able to satisfy them - either by not supporting more physical
+	 * memory, or by providing a ZONE_DMA32.  If neither is the case, the
+	 * architecture needs to use an IOMMU instead of the direct mapping.
+	 */
+	if (mask >= DMA_BIT_MASK(32))
+		return 1;
 
 	/*
 	 * This check needs to be against the actual bit mask value, so
 	 * use __phys_to_dma() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
 	return mask >= __phys_to_dma(dev, min_mask);
 }
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9280d6f..c19379fa 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -22,6 +22,7 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -656,35 +657,38 @@
 }
 
 /*
- * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
  * to the device copy the data into it as well.
  */
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
+	phys_addr_t swiotlb_addr;
+	dma_addr_t dma_addr;
 
-	if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
-		dev_warn_ratelimited(dev,
-			"Cannot do DMA to address %pa\n", phys);
-		return false;
-	}
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+			      swiotlb_force);
 
-	/* Oh well, have to allocate and map a bounce buffer. */
-	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, size, dir, attrs);
-	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
-		return false;
+	swiotlb_addr = swiotlb_tbl_map_single(dev,
+			__phys_to_dma(dev, io_tlb_start),
+			paddr, size, size, dir, attrs);
+	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
+		return DMA_MAPPING_ERROR;
 
 	/* Ensure that the address returned is DMA'ble */
-	*dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, *dma_addr, size, true))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
+	dma_addr = __phys_to_dma(dev, swiotlb_addr);
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-		return false;
+		dev_WARN_ONCE(dev, 1,
+			"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
 	}
 
-	return true;
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(swiotlb_addr, size, dir);
+	return dma_addr;
 }
 
 size_t swiotlb_max_mapping_size(struct device *dev)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 2c47280..8b1bb5e 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -131,11 +131,12 @@
 	 * to avoid them upfront.
 	 */
 	for (;;) {
-		if (s2idle_ops && s2idle_ops->wake)
-			s2idle_ops->wake();
-
-		if (pm_wakeup_pending())
+		if (s2idle_ops && s2idle_ops->wake) {
+			if (s2idle_ops->wake())
+				break;
+		} else if (pm_wakeup_pending()) {
 			break;
+		}
 
 		pm_wakeup_clear(false);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fc1dfc0..1a9983d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -552,27 +552,32 @@
  */
 int get_nohz_timer_target(void)
 {
-	int i, cpu = smp_processor_id();
+	int i, cpu = smp_processor_id(), default_cpu = -1;
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		return cpu;
+	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+		if (!idle_cpu(cpu))
+			return cpu;
+		default_cpu = cpu;
+	}
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd)) {
+		for_each_cpu_and(i, sched_domain_span(sd),
+			housekeeping_cpumask(HK_FLAG_TIMER)) {
 			if (cpu == i)
 				continue;
 
-			if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
+			if (!idle_cpu(i)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+	if (default_cpu == -1)
+		default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+	cpu = default_cpu;
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -1442,17 +1447,6 @@
 
 #ifdef CONFIG_SMP
 
-static inline bool is_per_cpu_kthread(struct task_struct *p)
-{
-	if (!(p->flags & PF_KTHREAD))
-		return false;
-
-	if (p->nr_cpus_allowed != 1)
-		return false;
-
-	return true;
-}
-
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -3669,28 +3663,32 @@
 	 * statistics and checks timeslices in a time-independent way, regardless
 	 * of when exactly it is running.
 	 */
-	if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+	if (!tick_nohz_tick_stopped_cpu(cpu))
 		goto out_requeue;
 
 	rq_lock_irq(rq, &rf);
 	curr = rq->curr;
-	if (is_idle_task(curr) || cpu_is_offline(cpu))
+	if (cpu_is_offline(cpu))
 		goto out_unlock;
 
+	curr = rq->curr;
 	update_rq_clock(rq);
-	delta = rq_clock_task(rq) - curr->se.exec_start;
 
-	/*
-	 * Make sure the next tick runs within a reasonable
-	 * amount of time.
-	 */
-	WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	if (!is_idle_task(curr)) {
+		/*
+		 * Make sure the next tick runs within a reasonable
+		 * amount of time.
+		 */
+		delta = rq_clock_task(rq) - curr->se.exec_start;
+		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	}
 	curr->sched_class->task_tick(rq, curr, 0);
 
+	calc_load_nohz_remote(rq);
 out_unlock:
 	rq_unlock_irq(rq, &rf);
-
 out_requeue:
+
 	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
@@ -7063,8 +7061,15 @@
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
-	if (running)
+	if (running) {
 		set_next_task(rq, tsk);
+		/*
+		 * After changing group, the running task may have joined a
+		 * throttled one but it's still the running task. Trigger a
+		 * resched to make sure that task can still run.
+		 */
+		resched_curr(rq);
+	}
 
 	task_rq_unlock(rq, tsk, &rf);
 }
@@ -7260,7 +7265,7 @@
 					     &req.percent);
 		if (req.ret)
 			return req;
-		if (req.percent > UCLAMP_PERCENT_SCALE) {
+		if ((u64)req.percent > UCLAMP_PERCENT_SCALE) {
 			req.ret = -ERANGE;
 			return req;
 		}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fe4e0d7..3c8a379 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3516,7 +3516,6 @@
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
- * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
@@ -5912,6 +5911,20 @@
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
 		return prev;
 
+	/*
+	 * Allow a per-cpu kthread to stack with the wakee if the
+	 * kworker thread and the tasks previous CPUs are the same.
+	 * The assumption is that the wakee queued work for the
+	 * per-cpu kthread that is now complete and the wakeup is
+	 * essentially a sync wakeup. An obvious example of this
+	 * pattern is IO completions.
+	 */
+	if (is_per_cpu_kthread(current) &&
+	    prev == smp_processor_id() &&
+	    this_rq()->nr_running <= 1) {
+		return prev;
+	}
+
 	/* Check a recently used CPU as a potential idle candidate: */
 	recent_used_cpu = p->recent_used_cpu;
 	if (recent_used_cpu != prev &&
@@ -8658,10 +8671,6 @@
 	/*
 	 * Try to use spare capacity of local group without overloading it or
 	 * emptying busiest.
-	 * XXX Spreading tasks across NUMA nodes is not always the best policy
-	 * and special care should be taken for SD_NUMA domain level before
-	 * spreading the tasks. For now, load_balance() fully relies on
-	 * NUMA_BALANCING and fbq_classify_group/rq to override the decision.
 	 */
 	if (local->group_type == group_has_spare) {
 		if (busiest->group_type > group_fully_busy) {
@@ -8701,16 +8710,37 @@
 			env->migration_type = migrate_task;
 			lsub_positive(&nr_diff, local->sum_nr_running);
 			env->imbalance = nr_diff >> 1;
-			return;
+		} else {
+
+			/*
+			 * If there is no overload, we just want to even the number of
+			 * idle cpus.
+			 */
+			env->migration_type = migrate_task;
+			env->imbalance = max_t(long, 0, (local->idle_cpus -
+						 busiest->idle_cpus) >> 1);
 		}
 
-		/*
-		 * If there is no overload, we just want to even the number of
-		 * idle cpus.
-		 */
-		env->migration_type = migrate_task;
-		env->imbalance = max_t(long, 0, (local->idle_cpus -
-						 busiest->idle_cpus) >> 1);
+		/* Consider allowing a small imbalance between NUMA groups */
+		if (env->sd->flags & SD_NUMA) {
+			unsigned int imbalance_min;
+
+			/*
+			 * Compute an allowed imbalance based on a simple
+			 * pair of communicating tasks that should remain
+			 * local and ignore them.
+			 *
+			 * NOTE: Generally this would have been based on
+			 * the domain size and this was evaluated. However,
+			 * the benefit is similar across a range of workloads
+			 * and machines but scaling by the domain size adds
+			 * the risk that lower domains have to be rebalanced.
+			 */
+			imbalance_min = 2;
+			if (busiest->sum_nr_running <= imbalance_min)
+				env->imbalance = 0;
+		}
+
 		return;
 	}
 
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 28a5165..de22da6 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -231,16 +231,11 @@
 	return calc_load_idx & 1;
 }
 
-void calc_load_nohz_start(void)
+static void calc_load_nohz_fold(struct rq *rq)
 {
-	struct rq *this_rq = this_rq();
 	long delta;
 
-	/*
-	 * We're going into NO_HZ mode, if there's any pending delta, fold it
-	 * into the pending NO_HZ delta.
-	 */
-	delta = calc_load_fold_active(this_rq, 0);
+	delta = calc_load_fold_active(rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
@@ -248,6 +243,24 @@
 	}
 }
 
+void calc_load_nohz_start(void)
+{
+	/*
+	 * We're going into NO_HZ mode, if there's any pending delta, fold it
+	 * into the pending NO_HZ delta.
+	 */
+	calc_load_nohz_fold(this_rq());
+}
+
+/*
+ * Keep track of the load for NOHZ_FULL, must be called between
+ * calc_load_nohz_{start,stop}().
+ */
+void calc_load_nohz_remote(struct rq *rq)
+{
+	calc_load_nohz_fold(rq);
+}
+
 void calc_load_nohz_stop(void)
 {
 	struct rq *this_rq = this_rq();
@@ -268,7 +281,7 @@
 		this_rq->calc_load_update += LOAD_FREQ;
 }
 
-static long calc_load_nohz_fold(void)
+static long calc_load_nohz_read(void)
 {
 	int idx = calc_load_read_idx();
 	long delta = 0;
@@ -323,7 +336,7 @@
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 
-static inline long calc_load_nohz_fold(void) { return 0; }
+static inline long calc_load_nohz_read(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -346,7 +359,7 @@
 	/*
 	 * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs.
 	 */
-	delta = calc_load_nohz_fold();
+	delta = calc_load_nohz_read();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ac4bd0c..0285207 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1199,6 +1199,9 @@
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	buf_size = min(nbytes, sizeof(buf));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1a88dc8..9ea6478 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -896,7 +896,7 @@
 	 */
 	unsigned long		nr_uninterruptible;
 
-	struct task_struct	*curr;
+	struct task_struct __rcu	*curr;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
 	unsigned long		next_balance;
@@ -2479,3 +2479,16 @@
 {
 }
 #endif
+
+#ifdef CONFIG_SMP
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+#endif
diff --git a/kernel/time/time.c b/kernel/time/time.c
index cdd7386..3985b2b 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -449,49 +449,6 @@
 }
 EXPORT_SYMBOL(mktime64);
 
-/**
- * ns_to_timespec - Convert nanoseconds to timespec
- * @nsec:       the nanoseconds value to be converted
- *
- * Returns the timespec representation of the nsec parameter.
- */
-struct timespec ns_to_timespec(const s64 nsec)
-{
-	struct timespec ts;
-	s32 rem;
-
-	if (!nsec)
-		return (struct timespec) {0, 0};
-
-	ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
-	if (unlikely(rem < 0)) {
-		ts.tv_sec--;
-		rem += NSEC_PER_SEC;
-	}
-	ts.tv_nsec = rem;
-
-	return ts;
-}
-EXPORT_SYMBOL(ns_to_timespec);
-
-/**
- * ns_to_timeval - Convert nanoseconds to timeval
- * @nsec:       the nanoseconds value to be converted
- *
- * Returns the timeval representation of the nsec parameter.
- */
-struct timeval ns_to_timeval(const s64 nsec)
-{
-	struct timespec ts = ns_to_timespec(nsec);
-	struct timeval tv;
-
-	tv.tv_sec = ts.tv_sec;
-	tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;
-
-	return tv;
-}
-EXPORT_SYMBOL(ns_to_timeval);
-
 struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec)
 {
 	struct timespec64 ts = ns_to_timespec64(nsec);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index e7ce7cd..483b3fd 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1798,6 +1798,60 @@
 }
 EXPORT_SYMBOL_GPL(synth_event_cmd_init);
 
+static inline int
+__synth_event_trace_start(struct trace_event_file *file,
+			  struct synth_event_trace_state *trace_state)
+{
+	int entry_size, fields_size = 0;
+	int ret = 0;
+
+	/*
+	 * Normal event tracing doesn't get called at all unless the
+	 * ENABLED bit is set (which attaches the probe thus allowing
+	 * this code to be called, etc).  Because this is called
+	 * directly by the user, we don't have that but we still need
+	 * to honor not logging when disabled.  For the the iterated
+	 * trace case, we save the enabed state upon start and just
+	 * ignore the following data calls.
+	 */
+	if (!(file->flags & EVENT_FILE_FL_ENABLED) ||
+	    trace_trigger_soft_disabled(file)) {
+		trace_state->disabled = true;
+		ret = -ENOENT;
+		goto out;
+	}
+
+	trace_state->event = file->event_call->data;
+
+	fields_size = trace_state->event->n_u64 * sizeof(u64);
+
+	/*
+	 * Avoid ring buffer recursion detection, as this event
+	 * is being performed within another event.
+	 */
+	trace_state->buffer = file->tr->array_buffer.buffer;
+	ring_buffer_nest_start(trace_state->buffer);
+
+	entry_size = sizeof(*trace_state->entry) + fields_size;
+	trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer,
+							file,
+							entry_size);
+	if (!trace_state->entry) {
+		ring_buffer_nest_end(trace_state->buffer);
+		ret = -EINVAL;
+	}
+out:
+	return ret;
+}
+
+static inline void
+__synth_event_trace_end(struct synth_event_trace_state *trace_state)
+{
+	trace_event_buffer_commit(&trace_state->fbuffer);
+
+	ring_buffer_nest_end(trace_state->buffer);
+}
+
 /**
  * synth_event_trace - Trace a synthetic event
  * @file: The trace_event_file representing the synthetic event
@@ -1819,71 +1873,38 @@
  */
 int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
 {
-	struct trace_event_buffer fbuffer;
-	struct synth_trace_event *entry;
-	struct trace_buffer *buffer;
-	struct synth_event *event;
+	struct synth_event_trace_state state;
 	unsigned int i, n_u64;
-	int fields_size = 0;
 	va_list args;
-	int ret = 0;
+	int ret;
 
-	/*
-	 * Normal event generation doesn't get called at all unless
-	 * the ENABLED bit is set (which attaches the probe thus
-	 * allowing this code to be called, etc).  Because this is
-	 * called directly by the user, we don't have that but we
-	 * still need to honor not logging when disabled.
-	 */
-	if (!(file->flags & EVENT_FILE_FL_ENABLED))
-		return 0;
-
-	event = file->event_call->data;
-
-	if (n_vals != event->n_fields)
-		return -EINVAL;
-
-	if (trace_trigger_soft_disabled(file))
-		return -EINVAL;
-
-	fields_size = event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	buffer = file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
-
-	entry = trace_event_buffer_reserve(&fbuffer, file,
-					   sizeof(*entry) + fields_size);
-	if (!entry) {
-		ret = -EINVAL;
-		goto out;
+	ret = __synth_event_trace_start(file, &state);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0; /* just disabled, not really an error */
+		return ret;
 	}
 
 	va_start(args, n_vals);
-	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
 		u64 val;
 
 		val = va_arg(args, u64);
 
-		if (event->fields[i]->is_string) {
+		if (state.event->fields[i]->is_string) {
 			char *str_val = (char *)(long)val;
-			char *str_field = (char *)&entry->fields[n_u64];
+			char *str_field = (char *)&state.entry->fields[n_u64];
 
 			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
 			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
 		} else {
-			entry->fields[n_u64] = val;
+			state.entry->fields[n_u64] = val;
 			n_u64++;
 		}
 	}
 	va_end(args);
 
-	trace_event_buffer_commit(&fbuffer);
-out:
-	ring_buffer_nest_end(buffer);
+	__synth_event_trace_end(&state);
 
 	return ret;
 }
@@ -1910,64 +1931,31 @@
 int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
 			    unsigned int n_vals)
 {
-	struct trace_event_buffer fbuffer;
-	struct synth_trace_event *entry;
-	struct trace_buffer *buffer;
-	struct synth_event *event;
+	struct synth_event_trace_state state;
 	unsigned int i, n_u64;
-	int fields_size = 0;
-	int ret = 0;
+	int ret;
 
-	/*
-	 * Normal event generation doesn't get called at all unless
-	 * the ENABLED bit is set (which attaches the probe thus
-	 * allowing this code to be called, etc).  Because this is
-	 * called directly by the user, we don't have that but we
-	 * still need to honor not logging when disabled.
-	 */
-	if (!(file->flags & EVENT_FILE_FL_ENABLED))
-		return 0;
-
-	event = file->event_call->data;
-
-	if (n_vals != event->n_fields)
-		return -EINVAL;
-
-	if (trace_trigger_soft_disabled(file))
-		return -EINVAL;
-
-	fields_size = event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	buffer = file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
-
-	entry = trace_event_buffer_reserve(&fbuffer, file,
-					   sizeof(*entry) + fields_size);
-	if (!entry) {
-		ret = -EINVAL;
-		goto out;
+	ret = __synth_event_trace_start(file, &state);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0; /* just disabled, not really an error */
+		return ret;
 	}
 
-	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
-		if (event->fields[i]->is_string) {
+	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
+		if (state.event->fields[i]->is_string) {
 			char *str_val = (char *)(long)vals[i];
-			char *str_field = (char *)&entry->fields[n_u64];
+			char *str_field = (char *)&state.entry->fields[n_u64];
 
 			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
 			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
 		} else {
-			entry->fields[n_u64] = vals[i];
+			state.entry->fields[n_u64] = vals[i];
 			n_u64++;
 		}
 	}
 
-	trace_event_buffer_commit(&fbuffer);
-out:
-	ring_buffer_nest_end(buffer);
+	__synth_event_trace_end(&state);
 
 	return ret;
 }
@@ -2004,58 +1992,17 @@
 int synth_event_trace_start(struct trace_event_file *file,
 			    struct synth_event_trace_state *trace_state)
 {
-	struct synth_trace_event *entry;
-	int fields_size = 0;
-	int ret = 0;
+	int ret;
 
-	if (!trace_state) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!trace_state)
+		return -EINVAL;
 
 	memset(trace_state, '\0', sizeof(*trace_state));
 
-	/*
-	 * Normal event tracing doesn't get called at all unless the
-	 * ENABLED bit is set (which attaches the probe thus allowing
-	 * this code to be called, etc).  Because this is called
-	 * directly by the user, we don't have that but we still need
-	 * to honor not logging when disabled.  For the the iterated
-	 * trace case, we save the enabed state upon start and just
-	 * ignore the following data calls.
-	 */
-	if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
-		trace_state->enabled = false;
-		goto out;
-	}
+	ret = __synth_event_trace_start(file, trace_state);
+	if (ret == -ENOENT)
+		ret = 0; /* just disabled, not really an error */
 
-	trace_state->enabled = true;
-
-	trace_state->event = file->event_call->data;
-
-	if (trace_trigger_soft_disabled(file)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	fields_size = trace_state->event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	trace_state->buffer = file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(trace_state->buffer);
-
-	entry = trace_event_buffer_reserve(&trace_state->fbuffer, file,
-					   sizeof(*entry) + fields_size);
-	if (!entry) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	trace_state->entry = entry;
-out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(synth_event_trace_start);
@@ -2088,7 +2035,7 @@
 		trace_state->add_next = true;
 	}
 
-	if (!trace_state->enabled)
+	if (trace_state->disabled)
 		goto out;
 
 	event = trace_state->event;
@@ -2223,9 +2170,7 @@
 	if (!trace_state)
 		return -EINVAL;
 
-	trace_event_buffer_commit(&trace_state->fbuffer);
-
-	ring_buffer_nest_end(trace_state->buffer);
+	__synth_event_trace_end(trace_state);
 
 	return 0;
 }
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d8264eb..362cca5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1012,7 +1012,7 @@
 {
 	struct dynevent_arg arg;
 	va_list args;
-	int ret;
+	int ret = 0;
 
 	if (cmd->type != DYNEVENT_TYPE_KPROBE)
 		return -EINVAL;
diff --git a/lib/Kconfig b/lib/Kconfig
index 0cf875f..bc7e563 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -573,9 +573,6 @@
 config LIBFDT
 	bool
 
-config LIBXBC
-	bool
-
 config OID_REGISTRY
 	tristate
 	help
diff --git a/lib/Makefile b/lib/Makefile
index 5d64890..611872c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -230,7 +230,7 @@
 	$(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt))
 lib-$(CONFIG_LIBFDT) += $(libfdt_files)
 
-lib-$(CONFIG_LIBXBC) += bootconfig.o
+lib-$(CONFIG_BOOT_CONFIG) += bootconfig.o
 
 obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
 obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index afb2e76..3ea601a 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -6,12 +6,13 @@
 
 #define pr_fmt(fmt)    "bootconfig: " fmt
 
+#include <linux/bootconfig.h>
 #include <linux/bug.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/memblock.h>
 #include <linux/printk.h>
-#include <linux/bootconfig.h>
 #include <linux/string.h>
 
 /*
@@ -23,7 +24,7 @@
  * node (for array).
  */
 
-static struct xbc_node xbc_nodes[XBC_NODE_MAX] __initdata;
+static struct xbc_node *xbc_nodes __initdata;
 static int xbc_node_num __initdata;
 static char *xbc_data __initdata;
 static size_t xbc_data_size __initdata;
@@ -719,7 +720,8 @@
 	xbc_data = NULL;
 	xbc_data_size = 0;
 	xbc_node_num = 0;
-	memset(xbc_nodes, 0, sizeof(xbc_nodes));
+	memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX);
+	xbc_nodes = NULL;
 }
 
 /**
@@ -748,6 +750,13 @@
 		return -ERANGE;
 	}
 
+	xbc_nodes = memblock_alloc(sizeof(struct xbc_node) * XBC_NODE_MAX,
+				   SMP_CACHE_BYTES);
+	if (!xbc_nodes) {
+		pr_err("Failed to allocate memory for bootconfig nodes.\n");
+		return -ENOMEM;
+	}
+	memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX);
 	xbc_data = buf;
 	xbc_data_size = ret + 1;
 	last_parent = NULL;
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index ed717dd..81c69c0 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -83,15 +83,19 @@
 		return true;
 	if (stack_slabs[depot_index] == NULL) {
 		stack_slabs[depot_index] = *prealloc;
+		*prealloc = NULL;
 	} else {
-		stack_slabs[depot_index + 1] = *prealloc;
+		/* If this is the last depot slab, do not touch the next one. */
+		if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) {
+			stack_slabs[depot_index + 1] = *prealloc;
+			*prealloc = NULL;
+		}
 		/*
 		 * This smp_store_release pairs with smp_load_acquire() from
 		 * |next_slab_inited| above and in stack_depot_save().
 		 */
 		smp_store_release(&next_slab_inited, 1);
 	}
-	*prealloc = NULL;
 	return true;
 }
 
diff --git a/lib/string.c b/lib/string.c
index f607b96..6012c38 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -699,6 +699,14 @@
  * @n:		number of strings in the array or -1 for NULL terminated arrays
  * @string:	string to match with
  *
+ * This routine will look for a string in an array of strings up to the
+ * n-th element in the array or until the first NULL element.
+ *
+ * Historically the value of -1 for @n, was used to search in arrays that
+ * are NULL terminated. However, the function does not make a distinction
+ * when finishing the search: either @n elements have been compared OR
+ * the first NULL element was found.
+ *
  * Return:
  * index of a @string in the @array if matches, or %-EINVAL otherwise.
  */
@@ -727,6 +735,14 @@
  *
  * Returns index of @str in the @array or -EINVAL, just like match_string().
  * Uses sysfs_streq instead of strcmp for matching.
+ *
+ * This routine will look for a string in an array of strings up to the
+ * n-th element in the array or until the first NULL element.
+ *
+ * Historically the value of -1 for @n, was used to search in arrays that
+ * are NULL terminated. However, the function does not make a distinction
+ * when finishing the search: either @n elements have been compared OR
+ * the first NULL element was found.
  */
 int __sysfs_match_string(const char * const *array, size_t n, const char *str)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6f6dc87..d09776c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -409,8 +409,10 @@
 		if (mem_cgroup_is_root(memcg))
 			continue;
 		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
-		if (ret)
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
 			goto unlock;
+		}
 	}
 unlock:
 	if (!ret)
diff --git a/mm/sparse.c b/mm/sparse.c
index c184b69..596b2a4 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -876,7 +876,7 @@
 	 * Poison uninitialized struct pages in order to catch invalid flags
 	 * combinations.
 	 */
-	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+	page_init_poison(memmap, sizeof(struct page) * nr_pages);
 
 	ms = __nr_to_section(section_nr);
 	set_section_nid(section_nr, nid);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2c33ff4..b2a2e45 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3157,7 +3157,7 @@
 	mapping = swap_file->f_mapping;
 	inode = mapping->host;
 
-	/* If S_ISREG(inode->i_mode) will do inode_lock(inode); */
+	/* will take i_rwsem; */
 	error = claim_swapfile(p, inode);
 	if (unlikely(error))
 		goto bad_swap;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c05eb9e..8763705 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2415,10 +2415,13 @@
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
-			 * Make sure we don't miss the last page
-			 * because of a round-off error.
+			 * Make sure we don't miss the last page on
+			 * the offlined memory cgroups because of a
+			 * round-off error.
 			 */
-			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+			scan = mem_cgroup_online(memcg) ?
+			       div64_u64(scan * fraction[file], denominator) :
+			       DIV64_U64_ROUND_UP(scan * fraction[file],
 						  denominator);
 			break;
 		case SCAN_FILE:
diff --git a/net/Kconfig b/net/Kconfig
index b0937a70..2eeb0e5 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -189,7 +189,6 @@
 	depends on NETFILTER_ADVANCED
 	select NETFILTER_FAMILY_BRIDGE
 	select SKB_EXTENSIONS
-	default m
 	---help---
 	  Enabling this option will let arptables resp. iptables see bridged
 	  ARP resp. IP traffic. If you want a bridging firewall, you probably
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 6856a6d..1f14b84 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -63,7 +63,8 @@
 {
 	struct net_bridge_port *p;
 
-	list_for_each_entry_rcu(p, &br->port_list, list) {
+	list_for_each_entry_rcu(p, &br->port_list, list,
+				lockdep_is_held(&br->lock)) {
 		if (p->port_no == port_no)
 			return p;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index a69e8bd..e10bd68 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,7 +146,6 @@
 #include "net-sysfs.h"
 
 #define MAX_GRO_SKBS 8
-#define MAX_NEST_DEV 8
 
 /* This should be increased if a protocol with a bigger head is added. */
 #define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -331,6 +330,12 @@
 	name_node = netdev_name_node_lookup(net, name);
 	if (!name_node)
 		return -ENOENT;
+	/* lookup might have found our primary name or a name belonging
+	 * to another device.
+	 */
+	if (name_node == dev->name_node || name_node->dev != dev)
+		return -EINVAL;
+
 	__netdev_name_node_alt_destroy(name_node);
 
 	return 0;
@@ -3657,26 +3662,8 @@
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
-		    qdisc_run_begin(q)) {
-			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state))) {
-				__qdisc_drop(skb, &to_free);
-				rc = NET_XMIT_DROP;
-				goto end_run;
-			}
-			qdisc_bstats_cpu_update(q, skb);
-
-			rc = NET_XMIT_SUCCESS;
-			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
-				__qdisc_run(q);
-
-end_run:
-			qdisc_run_end(q);
-		} else {
-			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-			qdisc_run(q);
-		}
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
@@ -4527,14 +4514,14 @@
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
 	 */
-	if (skb_cloned(skb) || skb_is_tc_redirected(skb))
+	if (skb_is_tc_redirected(skb))
 		return XDP_PASS;
 
 	/* XDP packets must be linear and must have sufficient headroom
 	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
 	 * native XDP provides, thus we need to do it here as well.
 	 */
-	if (skb_is_nonlinear(skb) ||
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
 	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
 		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
 		int troom = skb->tail + skb->data_len - skb->end;
@@ -7201,8 +7188,8 @@
 	return 0;
 }
 
-static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
-						    struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+					     struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
@@ -7214,6 +7201,7 @@
 
 	return lower->dev;
 }
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
 
 static u8 __netdev_upper_depth(struct net_device *dev)
 {
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 3e7e152..bd7eba9 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -974,7 +974,7 @@
 
 	frh = nlmsg_data(nlh);
 	frh->family = ops->family;
-	frh->table = rule->table;
+	frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, FRA_TABLE, rule->table))
 		goto nla_put_failure;
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 9b7cbe3..10d2b25 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -99,8 +99,7 @@
 static void __page_pool_return_page(struct page_pool *pool, struct page *page);
 
 noinline
-static struct page *page_pool_refill_alloc_cache(struct page_pool *pool,
-						 bool refill)
+static struct page *page_pool_refill_alloc_cache(struct page_pool *pool)
 {
 	struct ptr_ring *r = &pool->ring;
 	struct page *page;
@@ -141,8 +140,7 @@
 			page = NULL;
 			break;
 		}
-	} while (pool->alloc.count < PP_ALLOC_CACHE_REFILL &&
-		 refill);
+	} while (pool->alloc.count < PP_ALLOC_CACHE_REFILL);
 
 	/* Return last page */
 	if (likely(pool->alloc.count > 0))
@@ -155,20 +153,16 @@
 /* fast path */
 static struct page *__page_pool_get_cached(struct page_pool *pool)
 {
-	bool refill = false;
 	struct page *page;
 
-	/* Test for safe-context, caller should provide this guarantee */
-	if (likely(in_serving_softirq())) {
-		if (likely(pool->alloc.count)) {
-			/* Fast-path */
-			page = pool->alloc.cache[--pool->alloc.count];
-			return page;
-		}
-		refill = true;
+	/* Caller MUST guarantee safe non-concurrent access, e.g. softirq */
+	if (likely(pool->alloc.count)) {
+		/* Fast-path */
+		page = pool->alloc.cache[--pool->alloc.count];
+	} else {
+		page = page_pool_refill_alloc_cache(pool);
 	}
 
-	page = page_pool_refill_alloc_cache(pool, refill);
 	return page;
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 09c44bf..e1152f4 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3504,27 +3504,25 @@
 	if (err)
 		return err;
 
-	alt_ifname = nla_data(attr);
+	alt_ifname = nla_strdup(attr, GFP_KERNEL);
+	if (!alt_ifname)
+		return -ENOMEM;
+
 	if (cmd == RTM_NEWLINKPROP) {
-		alt_ifname = kstrdup(alt_ifname, GFP_KERNEL);
-		if (!alt_ifname)
-			return -ENOMEM;
 		err = netdev_name_node_alt_create(dev, alt_ifname);
-		if (err) {
-			kfree(alt_ifname);
-			return err;
-		}
+		if (!err)
+			alt_ifname = NULL;
 	} else if (cmd == RTM_DELLINKPROP) {
 		err = netdev_name_node_alt_destroy(dev, alt_ifname);
-		if (err)
-			return err;
 	} else {
-		WARN_ON(1);
-		return 0;
+		WARN_ON_ONCE(1);
+		err = -EINVAL;
 	}
 
-	*changed = true;
-	return 0;
+	kfree(alt_ifname);
+	if (!err)
+		*changed = true;
+	return err;
 }
 
 static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 864cb9e..e1101a4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -467,7 +467,6 @@
 		return NULL;
 	}
 
-	/* use OR instead of assignment to avoid clearing of bits in mask */
 	if (pfmemalloc)
 		skb->pfmemalloc = 1;
 	skb->head_frag = 1;
@@ -527,7 +526,6 @@
 		return NULL;
 	}
 
-	/* use OR instead of assignment to avoid clearing of bits in mask */
 	if (nc->page.pfmemalloc)
 		skb->pfmemalloc = 1;
 	skb->head_frag = 1;
@@ -4805,9 +4803,9 @@
 				      typeof(IPPROTO_IP) proto,
 				      unsigned int off)
 {
-	switch (proto) {
-		int err;
+	int err;
 
+	switch (proto) {
 	case IPPROTO_TCP:
 		err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
 					  off + MAX_TCP_HDR_LEN);
diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c
index 466ffa9..55b0069 100644
--- a/net/dsa/tag_ar9331.c
+++ b/net/dsa/tag_ar9331.c
@@ -31,7 +31,7 @@
 	__le16 *phdr;
 	u16 hdr;
 
-	if (skb_cow_head(skb, 0) < 0)
+	if (skb_cow_head(skb, AR9331_HDR_LEN) < 0)
 		return NULL;
 
 	phdr = skb_push(skb, AR9331_HDR_LEN);
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index c8a128c..70db7c9 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -33,7 +33,7 @@
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
-	if (skb_cow_head(skb, 0) < 0)
+	if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
 		return NULL;
 
 	skb_push(skb, QCA_HDR_LEN);
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index fce45da..8977fe1 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -447,7 +447,10 @@
 				    "mask only allowed in compact bitset");
 		return -EINVAL;
 	}
+
 	no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
+	if (no_mask)
+		ethnl_bitmap32_clear(bitmap, 0, nbits, mod);
 
 	nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) {
 		bool old_val, new_val;
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 364ea2c..3ba7f61 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -155,7 +155,8 @@
 		new_node->seq_out[i] = seq_out;
 
 	spin_lock_bh(&hsr->list_lock);
-	list_for_each_entry_rcu(node, node_db, mac_list) {
+	list_for_each_entry_rcu(node, node_db, mac_list,
+				lockdep_is_held(&hsr->list_lock)) {
 		if (ether_addr_equal(node->macaddress_A, addr))
 			goto out;
 		if (ether_addr_equal(node->macaddress_B, addr))
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 18068ed..f369e7c 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -748,6 +748,39 @@
 }
 EXPORT_SYMBOL(__icmp_send);
 
+#if IS_ENABLED(CONFIG_NF_NAT)
+#include <net/netfilter/nf_conntrack.h>
+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+{
+	struct sk_buff *cloned_skb = NULL;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+	__be32 orig_ip;
+
+	ct = nf_ct_get(skb_in, &ctinfo);
+	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+		icmp_send(skb_in, type, code, info);
+		return;
+	}
+
+	if (skb_shared(skb_in))
+		skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
+
+	if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
+	    (skb_network_header(skb_in) + sizeof(struct iphdr)) >
+	    skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
+	    skb_network_offset(skb_in) + sizeof(struct iphdr))))
+		goto out;
+
+	orig_ip = ip_hdr(skb_in)->saddr;
+	ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
+	icmp_send(skb_in, type, code, info);
+	ip_hdr(skb_in)->saddr = orig_ip;
+out:
+	consume_skb(cloned_skb);
+}
+EXPORT_SYMBOL(icmp_ndo_send);
+#endif
 
 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
 {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index db76b96..08a41f1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1857,8 +1857,12 @@
 	inet->inet_dport = 0;
 	sock_rps_reset_rxhash(sk);
 	sk->sk_bound_dev_if = 0;
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
 		inet_reset_saddr(sk);
+		if (sk->sk_prot->rehash &&
+		    (sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+			sk->sk_prot->rehash(sk);
+	}
 
 	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
 		sk->sk_prot->unhash(sk);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 58fbde2..72abf89 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1102,8 +1102,7 @@
 					found++;
 					break;
 				}
-				if (rt_can_ecmp)
-					fallback_ins = fallback_ins ?: ins;
+				fallback_ins = fallback_ins ?: ins;
 				goto next_iter;
 			}
 
@@ -1146,7 +1145,9 @@
 	}
 
 	if (fallback_ins && !found) {
-		/* No ECMP-able route found, replace first non-ECMP one */
+		/* No matching route with same ecmp-able-ness found, replace
+		 * first matching route
+		 */
 		ins = fallback_ins;
 		iter = rcu_dereference_protected(*ins,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 55bfc51..781ca8c 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -437,8 +437,6 @@
 		return -ENOENT;
 
 	switch (type) {
-		struct ipv6_tlv_tnl_enc_lim *tel;
-		__u32 teli;
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
@@ -452,7 +450,10 @@
 			break;
 		}
 		return 0;
-	case ICMPV6_PARAMPROB:
+	case ICMPV6_PARAMPROB: {
+		struct ipv6_tlv_tnl_enc_lim *tel;
+		__u32 teli;
+
 		teli = 0;
 		if (code == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
@@ -468,6 +469,7 @@
 					    t->parms.name);
 		}
 		return 0;
+	}
 	case ICMPV6_PKT_TOOBIG:
 		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
 		return 0;
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 0204549..e008675 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -45,4 +45,38 @@
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(icmpv6_send);
+
+#if IS_ENABLED(CONFIG_NF_NAT)
+#include <net/netfilter/nf_conntrack.h>
+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
+{
+	struct sk_buff *cloned_skb = NULL;
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr orig_ip;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb_in, &ctinfo);
+	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+		icmpv6_send(skb_in, type, code, info);
+		return;
+	}
+
+	if (skb_shared(skb_in))
+		skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
+
+	if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
+	    (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) >
+	    skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
+	    skb_network_offset(skb_in) + sizeof(struct ipv6hdr))))
+		goto out;
+
+	orig_ip = ipv6_hdr(skb_in)->saddr;
+	ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
+	icmpv6_send(skb_in, type, code, info);
+	ipv6_hdr(skb_in)->saddr = orig_ip;
+out:
+	consume_skb(cloned_skb);
+}
+EXPORT_SYMBOL(icmpv6_ndo_send);
+#endif
 #endif
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b5dd20c..4703b09 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -121,6 +121,7 @@
 
 /**
  * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
+ *   @link: ifindex of underlying interface
  *   @remote: the address of the tunnel exit-point
  *   @local: the address of the tunnel entry-point
  *
@@ -134,37 +135,56 @@
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
 static struct ip6_tnl *
-ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local)
+ip6_tnl_lookup(struct net *net, int link,
+	       const struct in6_addr *remote, const struct in6_addr *local)
 {
 	unsigned int hash = HASH(remote, local);
-	struct ip6_tnl *t;
+	struct ip6_tnl *t, *cand = NULL;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct in6_addr any;
 
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
-		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_equal(remote, &t->parms.raddr) &&
-		    (t->dev->flags & IFF_UP))
+		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
+		    !ipv6_addr_equal(remote, &t->parms.raddr) ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (link == t->parms.link)
 			return t;
+		else
+			cand = t;
 	}
 
 	memset(&any, 0, sizeof(any));
 	hash = HASH(&any, local);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
-		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_any(&t->parms.raddr) &&
-		    (t->dev->flags & IFF_UP))
+		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
+		    !ipv6_addr_any(&t->parms.raddr) ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (link == t->parms.link)
 			return t;
+		else if (!cand)
+			cand = t;
 	}
 
 	hash = HASH(remote, &any);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
-		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
-		    ipv6_addr_any(&t->parms.laddr) &&
-		    (t->dev->flags & IFF_UP))
+		if (!ipv6_addr_equal(remote, &t->parms.raddr) ||
+		    !ipv6_addr_any(&t->parms.laddr) ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (link == t->parms.link)
 			return t;
+		else if (!cand)
+			cand = t;
 	}
 
+	if (cand)
+		return cand;
+
 	t = rcu_dereference(ip6n->collect_md_tun);
 	if (t && t->dev->flags & IFF_UP)
 		return t;
@@ -351,7 +371,8 @@
 	     (t = rtnl_dereference(*tp)) != NULL;
 	     tp = &t->next) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_equal(remote, &t->parms.raddr)) {
+		    ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    p->link == t->parms.link) {
 			if (create)
 				return ERR_PTR(-EEXIST);
 
@@ -485,7 +506,7 @@
 	   processing of the error. */
 
 	rcu_read_lock();
-	t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr);
+	t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->daddr, &ipv6h->saddr);
 	if (!t)
 		goto out;
 
@@ -496,8 +517,6 @@
 	err = 0;
 
 	switch (*type) {
-		struct ipv6_tlv_tnl_enc_lim *tel;
-		__u32 mtu, teli;
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
@@ -510,7 +529,10 @@
 			rel_msg = 1;
 		}
 		break;
-	case ICMPV6_PARAMPROB:
+	case ICMPV6_PARAMPROB: {
+		struct ipv6_tlv_tnl_enc_lim *tel;
+		__u32 teli;
+
 		teli = 0;
 		if ((*code) == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
@@ -527,7 +549,10 @@
 					    t->parms.name);
 		}
 		break;
-	case ICMPV6_PKT_TOOBIG:
+	}
+	case ICMPV6_PKT_TOOBIG: {
+		__u32 mtu;
+
 		ip6_update_pmtu(skb, net, htonl(*info), 0, 0,
 				sock_net_uid(net, NULL));
 		mtu = *info - offset;
@@ -541,6 +566,7 @@
 			rel_msg = 1;
 		}
 		break;
+	}
 	case NDISC_REDIRECT:
 		ip6_redirect(skb, net, skb->dev->ifindex, 0,
 			     sock_net_uid(net, NULL));
@@ -887,7 +913,7 @@
 	int ret = -1;
 
 	rcu_read_lock();
-	t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
+	t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->saddr, &ipv6h->daddr);
 
 	if (t) {
 		u8 tproto = READ_ONCE(t->parms.proto);
@@ -1420,8 +1446,10 @@
 static void ip6_tnl_link_config(struct ip6_tnl *t)
 {
 	struct net_device *dev = t->dev;
+	struct net_device *tdev = NULL;
 	struct __ip6_tnl_parm *p = &t->parms;
 	struct flowi6 *fl6 = &t->fl.u.ip6;
+	unsigned int mtu;
 	int t_hlen;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
@@ -1457,22 +1485,25 @@
 		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
 						 p->link, NULL, strict);
+		if (rt) {
+			tdev = rt->dst.dev;
+			ip6_rt_put(rt);
+		}
 
-		if (!rt)
-			return;
+		if (!tdev && p->link)
+			tdev = __dev_get_by_index(t->net, p->link);
 
-		if (rt->dst.dev) {
-			dev->hard_header_len = rt->dst.dev->hard_header_len +
-				t_hlen;
+		if (tdev) {
+			dev->hard_header_len = tdev->hard_header_len + t_hlen;
+			mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
 
-			dev->mtu = rt->dst.dev->mtu - t_hlen;
+			dev->mtu = mtu - t_hlen;
 			if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 				dev->mtu -= 8;
 
 			if (dev->mtu < IPV6_MIN_MTU)
 				dev->mtu = IPV6_MIN_MTU;
 		}
-		ip6_rt_put(rt);
 	}
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4fbdc60..2931224 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5198,6 +5198,7 @@
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
 		nhn++;
 	}
 
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 000c742..6aee699 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3450,7 +3450,7 @@
 
 	spin_lock_irqsave(&local->ack_status_lock, spin_flags);
 	id = idr_alloc(&local->ack_status_frames, ack_skb,
-		       1, 0x40, GFP_ATOMIC);
+		       1, 0x2000, GFP_ATOMIC);
 	spin_unlock_irqrestore(&local->ack_status_lock, spin_flags);
 
 	if (id < 0) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 5fa1317..e041af2 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,7 +8,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
  */
 
 #include <linux/delay.h>
@@ -1311,7 +1311,7 @@
 	if (!res) {
 		ch_switch.timestamp = timestamp;
 		ch_switch.device_timestamp = device_timestamp;
-		ch_switch.block_tx =  beacon ? csa_ie.mode : 0;
+		ch_switch.block_tx = csa_ie.mode;
 		ch_switch.chandef = csa_ie.chandef;
 		ch_switch.count = csa_ie.count;
 		ch_switch.delay = csa_ie.max_switch_time;
@@ -1404,7 +1404,7 @@
 
 	sdata->vif.csa_active = true;
 	sdata->csa_chandef = csa_ie.chandef;
-	sdata->csa_block_tx = ch_switch.block_tx;
+	sdata->csa_block_tx = csa_ie.mode;
 	ifmgd->csa_ignored_same_chan = false;
 
 	if (sdata->csa_block_tx)
@@ -1438,7 +1438,7 @@
 	 * reset when the disconnection worker runs.
 	 */
 	sdata->vif.csa_active = true;
-	sdata->csa_block_tx = ch_switch.block_tx;
+	sdata->csa_block_tx = csa_ie.mode;
 
 	ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work);
 	mutex_unlock(&local->chanctx_mtx);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 4bd1faf..87def9c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2442,7 +2442,7 @@
 
 		spin_lock_irqsave(&local->ack_status_lock, flags);
 		id = idr_alloc(&local->ack_status_frames, ack_skb,
-			       1, 0x40, GFP_ATOMIC);
+			       1, 0x2000, GFP_ATOMIC);
 		spin_unlock_irqrestore(&local->ack_status_lock, flags);
 
 		if (id >= 0) {
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 32a7a53..decd46b3 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1063,16 +1063,22 @@
 				elem_parse_failed = true;
 			break;
 		case WLAN_EID_VHT_OPERATION:
-			if (elen >= sizeof(struct ieee80211_vht_operation))
+			if (elen >= sizeof(struct ieee80211_vht_operation)) {
 				elems->vht_operation = (void *)pos;
-			else
-				elem_parse_failed = true;
+				if (calc_crc)
+					crc = crc32_be(crc, pos - 2, elen + 2);
+				break;
+			}
+			elem_parse_failed = true;
 			break;
 		case WLAN_EID_OPMODE_NOTIF:
-			if (elen > 0)
+			if (elen > 0) {
 				elems->opmode_notif = pos;
-			else
-				elem_parse_failed = true;
+				if (calc_crc)
+					crc = crc32_be(crc, pos - 2, elen + 2);
+				break;
+			}
+			elem_parse_failed = true;
 			break;
 		case WLAN_EID_MESH_ID:
 			elems->mesh_id = pos;
@@ -2987,10 +2993,22 @@
 	int cf0, cf1;
 	int ccfs0, ccfs1, ccfs2;
 	int ccf0, ccf1;
+	u32 vht_cap;
+	bool support_80_80 = false;
+	bool support_160 = false;
 
 	if (!oper || !htop)
 		return false;
 
+	vht_cap = hw->wiphy->bands[chandef->chan->band]->vht_cap.cap;
+	support_160 = (vht_cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK |
+				  IEEE80211_VHT_CAP_EXT_NSS_BW_MASK));
+	support_80_80 = ((vht_cap &
+			 IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) ||
+			(vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
+			 vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) ||
+			((vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) >>
+				    IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT > 1));
 	ccfs0 = oper->center_freq_seg0_idx;
 	ccfs1 = oper->center_freq_seg1_idx;
 	ccfs2 = (le16_to_cpu(htop->operation_mode) &
@@ -3018,10 +3036,10 @@
 			unsigned int diff;
 
 			diff = abs(ccf1 - ccf0);
-			if (diff == 8) {
+			if ((diff == 8) && support_160) {
 				new.width = NL80211_CHAN_WIDTH_160;
 				new.center_freq1 = cf1;
-			} else if (diff > 8) {
+			} else if ((diff > 8) && support_80_80) {
 				new.width = NL80211_CHAN_WIDTH_80P80;
 				new.center_freq2 = cf1;
 			}
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig
index 49f6054..a9ed3bf 100644
--- a/net/mptcp/Kconfig
+++ b/net/mptcp/Kconfig
@@ -4,6 +4,7 @@
 	depends on INET
 	select SKB_EXTENSIONS
 	select CRYPTO_LIB_SHA256
+	select CRYPTO
 	help
 	  Multipath TCP (MPTCP) connections send and receive data over multiple
 	  subflows in order to utilize multiple network paths. Each subflow
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 73780b4..e9aa680 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -643,7 +643,7 @@
 }
 #endif
 
-struct sock *mptcp_sk_clone_lock(const struct sock *sk)
+static struct sock *mptcp_sk_clone_lock(const struct sock *sk)
 {
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
 
@@ -755,60 +755,50 @@
 			    char __user *optval, unsigned int optlen)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	int ret = -EOPNOTSUPP;
 	struct socket *ssock;
-	struct sock *ssk;
 
 	pr_debug("msk=%p", msk);
 
 	/* @@ the meaning of setsockopt() when the socket is connected and
-	 * there are multiple subflows is not defined.
+	 * there are multiple subflows is not yet defined. It is up to the
+	 * MPTCP-level socket to configure the subflows until the subflow
+	 * is in TCP fallback, when TCP socket options are passed through
+	 * to the one remaining subflow.
 	 */
 	lock_sock(sk);
-	ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
-	if (IS_ERR(ssock)) {
-		release_sock(sk);
-		return ret;
-	}
+	ssock = __mptcp_tcp_fallback(msk);
+	if (ssock)
+		return tcp_setsockopt(ssock->sk, level, optname, optval,
+				      optlen);
 
-	ssk = ssock->sk;
-	sock_hold(ssk);
 	release_sock(sk);
 
-	ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
-	sock_put(ssk);
-
-	return ret;
+	return -EOPNOTSUPP;
 }
 
 static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 			    char __user *optval, int __user *option)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	int ret = -EOPNOTSUPP;
 	struct socket *ssock;
-	struct sock *ssk;
 
 	pr_debug("msk=%p", msk);
 
-	/* @@ the meaning of getsockopt() when the socket is connected and
-	 * there are multiple subflows is not defined.
+	/* @@ the meaning of setsockopt() when the socket is connected and
+	 * there are multiple subflows is not yet defined. It is up to the
+	 * MPTCP-level socket to configure the subflows until the subflow
+	 * is in TCP fallback, when socket options are passed through
+	 * to the one remaining subflow.
 	 */
 	lock_sock(sk);
-	ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
-	if (IS_ERR(ssock)) {
-		release_sock(sk);
-		return ret;
-	}
+	ssock = __mptcp_tcp_fallback(msk);
+	if (ssock)
+		return tcp_getsockopt(ssock->sk, level, optname, optval,
+				      option);
 
-	ssk = ssock->sk;
-	sock_hold(ssk);
 	release_sock(sk);
 
-	ret = tcp_getsockopt(ssk, level, optname, optval, option);
-	sock_put(ssk);
-
-	return ret;
+	return -EOPNOTSUPP;
 }
 
 static int mptcp_get_port(struct sock *sk, unsigned short snum)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 8a99a29..9f8663b3 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -56,8 +56,8 @@
 #define MPTCP_DSS_FLAG_MASK	(0x1F)
 
 /* MPTCP socket flags */
-#define MPTCP_DATA_READY	BIT(0)
-#define MPTCP_SEND_SPACE	BIT(1)
+#define MPTCP_DATA_READY	0
+#define MPTCP_SEND_SPACE	1
 
 /* MPTCP connection sock */
 struct mptcp_sock {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index d130542..1927fc2 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -894,32 +894,175 @@
 	}
 }
 
-/* Resolve race on insertion if this protocol allows this. */
+static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
+{
+	struct nf_conn_tstamp *tstamp;
+
+	atomic_inc(&ct->ct_general.use);
+	ct->status |= IPS_CONFIRMED;
+
+	/* set conntrack timestamp, if enabled. */
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp)
+		tstamp->start = ktime_get_real_ns();
+}
+
+static int __nf_ct_resolve_clash(struct sk_buff *skb,
+				 struct nf_conntrack_tuple_hash *h)
+{
+	/* This is the conntrack entry already in hashes that won race. */
+	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *loser_ct;
+
+	loser_ct = nf_ct_get(skb, &ctinfo);
+
+	if (nf_ct_is_dying(ct))
+		return NF_DROP;
+
+	if (!atomic_inc_not_zero(&ct->ct_general.use))
+		return NF_DROP;
+
+	if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
+	    nf_ct_match(ct, loser_ct)) {
+		struct net *net = nf_ct_net(ct);
+
+		nf_ct_acct_merge(ct, ctinfo, loser_ct);
+		nf_ct_add_to_dying_list(loser_ct);
+		nf_conntrack_put(&loser_ct->ct_general);
+		nf_ct_set(skb, ct, ctinfo);
+
+		NF_CT_STAT_INC(net, insert_failed);
+		return NF_ACCEPT;
+	}
+
+	nf_ct_put(ct);
+	return NF_DROP;
+}
+
+/**
+ * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry
+ *
+ * @skb: skb that causes the collision
+ * @repl_idx: hash slot for reply direction
+ *
+ * Called when origin or reply direction had a clash.
+ * The skb can be handled without packet drop provided the reply direction
+ * is unique or there the existing entry has the identical tuple in both
+ * directions.
+ *
+ * Caller must hold conntrack table locks to prevent concurrent updates.
+ *
+ * Returns NF_DROP if the clash could not be handled.
+ */
+static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
+{
+	struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb);
+	const struct nf_conntrack_zone *zone;
+	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_node *n;
+	struct net *net;
+
+	zone = nf_ct_zone(loser_ct);
+	net = nf_ct_net(loser_ct);
+
+	/* Reply direction must never result in a clash, unless both origin
+	 * and reply tuples are identical.
+	 */
+	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) {
+		if (nf_ct_key_equal(h,
+				    &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+				    zone, net))
+			return __nf_ct_resolve_clash(skb, h);
+	}
+
+	/* We want the clashing entry to go away real soon: 1 second timeout. */
+	loser_ct->timeout = nfct_time_stamp + HZ;
+
+	/* IPS_NAT_CLASH removes the entry automatically on the first
+	 * reply.  Also prevents UDP tracker from moving the entry to
+	 * ASSURED state, i.e. the entry can always be evicted under
+	 * pressure.
+	 */
+	loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH;
+
+	__nf_conntrack_insert_prepare(loser_ct);
+
+	/* fake add for ORIGINAL dir: we want lookups to only find the entry
+	 * already in the table.  This also hides the clashing entry from
+	 * ctnetlink iteration, i.e. conntrack -L won't show them.
+	 */
+	hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+
+	hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
+				 &nf_conntrack_hash[repl_idx]);
+	return NF_ACCEPT;
+}
+
+/**
+ * nf_ct_resolve_clash - attempt to handle clash without packet drop
+ *
+ * @skb: skb that causes the clash
+ * @h: tuplehash of the clashing entry already in table
+ * @hash_reply: hash slot for reply direction
+ *
+ * A conntrack entry can be inserted to the connection tracking table
+ * if there is no existing entry with an identical tuple.
+ *
+ * If there is one, @skb (and the assocated, unconfirmed conntrack) has
+ * to be dropped.  In case @skb is retransmitted, next conntrack lookup
+ * will find the already-existing entry.
+ *
+ * The major problem with such packet drop is the extra delay added by
+ * the packet loss -- it will take some time for a retransmit to occur
+ * (or the sender to time out when waiting for a reply).
+ *
+ * This function attempts to handle the situation without packet drop.
+ *
+ * If @skb has no NAT transformation or if the colliding entries are
+ * exactly the same, only the to-be-confirmed conntrack entry is discarded
+ * and @skb is associated with the conntrack entry already in the table.
+ *
+ * Failing that, the new, unconfirmed conntrack is still added to the table
+ * provided that the collision only occurs in the ORIGINAL direction.
+ * The new entry will be added after the existing one in the hash list,
+ * so packets in the ORIGINAL direction will continue to match the existing
+ * entry.  The new entry will also have a fixed timeout so it expires --
+ * due to the collision, it will not see bidirectional traffic.
+ *
+ * Returns NF_DROP if the clash could not be resolved.
+ */
 static __cold noinline int
-nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
-		    enum ip_conntrack_info ctinfo,
-		    struct nf_conntrack_tuple_hash *h)
+nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h,
+		    u32 reply_hash)
 {
 	/* This is the conntrack entry already in hashes that won race. */
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
 	const struct nf_conntrack_l4proto *l4proto;
-	enum ip_conntrack_info oldinfo;
-	struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *loser_ct;
+	struct net *net;
+	int ret;
+
+	loser_ct = nf_ct_get(skb, &ctinfo);
+	net = nf_ct_net(loser_ct);
 
 	l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct));
-	if (l4proto->allow_clash &&
-	    !nf_ct_is_dying(ct) &&
-	    atomic_inc_not_zero(&ct->ct_general.use)) {
-		if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
-		    nf_ct_match(ct, loser_ct)) {
-			nf_ct_acct_merge(ct, ctinfo, loser_ct);
-			nf_conntrack_put(&loser_ct->ct_general);
-			nf_ct_set(skb, ct, oldinfo);
-			return NF_ACCEPT;
-		}
-		nf_ct_put(ct);
-	}
+	if (!l4proto->allow_clash)
+		goto drop;
+
+	ret = __nf_ct_resolve_clash(skb, h);
+	if (ret == NF_ACCEPT)
+		return ret;
+
+	ret = nf_ct_resolve_clash_harder(skb, reply_hash);
+	if (ret == NF_ACCEPT)
+		return ret;
+
+drop:
+	nf_ct_add_to_dying_list(loser_ct);
 	NF_CT_STAT_INC(net, drop);
+	NF_CT_STAT_INC(net, insert_failed);
 	return NF_DROP;
 }
 
@@ -932,7 +1075,6 @@
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
-	struct nf_conn_tstamp *tstamp;
 	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
@@ -989,6 +1131,7 @@
 
 	if (unlikely(nf_ct_is_dying(ct))) {
 		nf_ct_add_to_dying_list(ct);
+		NF_CT_STAT_INC(net, insert_failed);
 		goto dying;
 	}
 
@@ -1009,13 +1152,8 @@
 	   setting time, otherwise we'd get timer wrap in
 	   weird delay cases. */
 	ct->timeout += nfct_time_stamp;
-	atomic_inc(&ct->ct_general.use);
-	ct->status |= IPS_CONFIRMED;
 
-	/* set conntrack timestamp, if enabled. */
-	tstamp = nf_conn_tstamp_find(ct);
-	if (tstamp)
-		tstamp->start = ktime_get_real_ns();
+	__nf_conntrack_insert_prepare(ct);
 
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
@@ -1035,11 +1173,9 @@
 	return NF_ACCEPT;
 
 out:
-	nf_ct_add_to_dying_list(ct);
-	ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
+	ret = nf_ct_resolve_clash(skb, h, reply_hash);
 dying:
 	nf_conntrack_double_unlock(hash, reply_hash);
-	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
 	return ret;
 }
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 7365b43..760ca24 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -81,6 +81,18 @@
 	return false;
 }
 
+static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct,
+					       struct sk_buff *skb,
+					       enum ip_conntrack_info ctinfo,
+					       u32 extra_jiffies)
+{
+	if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY &&
+		     ct->status & IPS_NAT_CLASH))
+		nf_ct_kill(ct);
+	else
+		nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies);
+}
+
 /* Returns verdict for packet, and may modify conntracktype */
 int nf_conntrack_udp_packet(struct nf_conn *ct,
 			    struct sk_buff *skb,
@@ -116,8 +128,8 @@
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
 	} else {
-		nf_ct_refresh_acct(ct, ctinfo, skb,
-				   timeouts[UDP_CT_UNREPLIED]);
+		nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
+						   timeouts[UDP_CT_UNREPLIED]);
 	}
 	return NF_ACCEPT;
 }
@@ -198,8 +210,8 @@
 		if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
 			nf_conntrack_event_cache(IPCT_ASSURED, ct);
 	} else {
-		nf_ct_refresh_acct(ct, ctinfo, skb,
-				   timeouts[UDP_CT_UNREPLIED]);
+		nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo,
+						   timeouts[UDP_CT_UNREPLIED]);
 	}
 	return NF_ACCEPT;
 }
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 83e1db3..06f00cd 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -847,9 +847,6 @@
 {
 	int err;
 
-	if (!nf_flowtable_hw_offload(flowtable))
-		return 0;
-
 	if (!dev->netdev_ops->ndo_setup_tc)
 		return -EOPNOTSUPP;
 
@@ -876,6 +873,9 @@
 	struct flow_block_offload bo;
 	int err;
 
+	if (!nf_flowtable_hw_offload(flowtable))
+		return 0;
+
 	err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index f0cb1e1..feac855 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -203,7 +203,7 @@
  * ::
  *
  *       rule indices in last field:    0    1
- *       map to elements:             0x42  0x66
+ *       map to elements:             0x66  0x42
  *
  *
  * Matching
@@ -298,7 +298,7 @@
  * ::
  *
  *       rule indices in last field:    0    1
- *       map to elements:             0x42  0x66
+ *       map to elements:             0x66  0x42
  *
  *      the matching element is at 0x42.
  *
@@ -503,7 +503,7 @@
 				return -1;
 			}
 
-			if (unlikely(match_only)) {
+			if (match_only) {
 				bitmap_clear(map, i, 1);
 				return i;
 			}
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index bccd47c..7a2c4b8 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -36,6 +36,7 @@
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/mutex.h>
 #include <linux/kernel.h>
+#include <linux/refcount.h>
 #include <uapi/linux/netfilter/xt_hashlimit.h>
 
 #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \
@@ -114,7 +115,7 @@
 
 struct xt_hashlimit_htable {
 	struct hlist_node node;		/* global list of all htables */
-	int use;
+	refcount_t use;
 	u_int8_t family;
 	bool rnd_initialized;
 
@@ -315,7 +316,7 @@
 	for (i = 0; i < hinfo->cfg.size; i++)
 		INIT_HLIST_HEAD(&hinfo->hash[i]);
 
-	hinfo->use = 1;
+	refcount_set(&hinfo->use, 1);
 	hinfo->count = 0;
 	hinfo->family = family;
 	hinfo->rnd_initialized = false;
@@ -420,7 +421,7 @@
 	hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) {
 		if (!strcmp(name, hinfo->name) &&
 		    hinfo->family == family) {
-			hinfo->use++;
+			refcount_inc(&hinfo->use);
 			return hinfo;
 		}
 	}
@@ -429,12 +430,11 @@
 
 static void htable_put(struct xt_hashlimit_htable *hinfo)
 {
-	mutex_lock(&hashlimit_mutex);
-	if (--hinfo->use == 0) {
+	if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) {
 		hlist_del(&hinfo->node);
+		mutex_unlock(&hashlimit_mutex);
 		htable_destroy(hinfo);
 	}
-	mutex_unlock(&hashlimit_mutex);
 }
 
 /* The algorithm used is the Simple Token Bucket Filter (TBF)
@@ -837,6 +837,8 @@
 	return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3);
 }
 
+#define HASHLIMIT_MAX_SIZE 1048576
+
 static int hashlimit_mt_check_common(const struct xt_mtchk_param *par,
 				     struct xt_hashlimit_htable **hinfo,
 				     struct hashlimit_cfg3 *cfg,
@@ -847,6 +849,14 @@
 
 	if (cfg->gc_interval == 0 || cfg->expire == 0)
 		return -EINVAL;
+	if (cfg->size > HASHLIMIT_MAX_SIZE) {
+		cfg->size = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("size too large, truncated to %u\n", cfg->size);
+	}
+	if (cfg->max > HASHLIMIT_MAX_SIZE) {
+		cfg->max = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("max too large, truncated to %u\n", cfg->max);
+	}
 	if (par->family == NFPROTO_IPV4) {
 		if (cfg->srcmask > 32 || cfg->dstmask > 32)
 			return -EINVAL;
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index f5d34da..a1f2320 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -143,7 +143,8 @@
 	if (domain != NULL) {
 		bkt = netlbl_domhsh_hash(domain);
 		bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt];
-		list_for_each_entry_rcu(iter, bkt_list, list)
+		list_for_each_entry_rcu(iter, bkt_list, list,
+					lockdep_is_held(&netlbl_domhsh_lock))
 			if (iter->valid &&
 			    netlbl_family_match(iter->family, family) &&
 			    strcmp(iter->domain, domain) == 0)
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index d2e4ab8..77bb1bb 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -207,7 +207,8 @@
 
 	bkt = netlbl_unlhsh_hash(ifindex);
 	bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt];
-	list_for_each_entry_rcu(iter, bkt_list, list)
+	list_for_each_entry_rcu(iter, bkt_list, list,
+				lockdep_is_held(&netlbl_unlhsh_lock))
 		if (iter->valid && iter->ifindex == ifindex)
 			return iter;
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4e31721..edf3e28 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1014,7 +1014,8 @@
 	if (nlk->netlink_bind && groups) {
 		int group;
 
-		for (group = 0; group < nlk->ngroups; group++) {
+		/* nl_groups is a u32, so cap the maximum groups we can bind */
+		for (group = 0; group < BITS_PER_TYPE(u32); group++) {
 			if (!test_bit(group, &groups))
 				continue;
 			err = nlk->netlink_bind(net, group + 1);
@@ -1033,7 +1034,7 @@
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_undo_bind(nlk->ngroups, groups, sk);
+			netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk);
 			goto unlock;
 		}
 	}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 659c2a7..c047afd 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -179,7 +179,8 @@
 	struct hlist_head *head;
 
 	head = vport_hash_bucket(dp, port_no);
-	hlist_for_each_entry_rcu(vport, head, dp_hash_node) {
+	hlist_for_each_entry_rcu(vport, head, dp_hash_node,
+				lockdep_ovsl_is_held()) {
 		if (vport->port_no == port_no)
 			return vport;
 	}
@@ -2042,7 +2043,8 @@
 	int i;
 
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
-		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
+		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
+					lockdep_ovsl_is_held()) {
 			dev = vport->dev;
 			dev_headroom = netdev_get_fwd_headroom(dev);
 			if (dev_headroom > max_headroom)
@@ -2061,7 +2063,8 @@
 
 	dp->max_headroom = new_headroom;
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
-		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node)
+		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
+					lockdep_ovsl_is_held())
 			netdev_set_rx_headroom(vport->dev, new_headroom);
 }
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 7da4230..288122e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2708,10 +2708,6 @@
 		return -EINVAL;
 
 	switch (key_type) {
-	const struct ovs_key_ipv4 *ipv4_key;
-	const struct ovs_key_ipv6 *ipv6_key;
-	int err;
-
 	case OVS_KEY_ATTR_PRIORITY:
 	case OVS_KEY_ATTR_SKB_MARK:
 	case OVS_KEY_ATTR_CT_MARK:
@@ -2723,7 +2719,9 @@
 			return -EINVAL;
 		break;
 
-	case OVS_KEY_ATTR_TUNNEL:
+	case OVS_KEY_ATTR_TUNNEL: {
+		int err;
+
 		if (masked)
 			return -EINVAL; /* Masked tunnel set not supported. */
 
@@ -2732,8 +2730,10 @@
 		if (err)
 			return err;
 		break;
+	}
+	case OVS_KEY_ATTR_IPV4: {
+		const struct ovs_key_ipv4 *ipv4_key;
 
-	case OVS_KEY_ATTR_IPV4:
 		if (eth_type != htons(ETH_P_IP))
 			return -EINVAL;
 
@@ -2753,8 +2753,10 @@
 				return -EINVAL;
 		}
 		break;
+	}
+	case OVS_KEY_ATTR_IPV6: {
+		const struct ovs_key_ipv6 *ipv6_key;
 
-	case OVS_KEY_ATTR_IPV6:
 		if (eth_type != htons(ETH_P_IPV6))
 			return -EINVAL;
 
@@ -2781,7 +2783,7 @@
 			return -EINVAL;
 
 		break;
-
+	}
 	case OVS_KEY_ATTR_TCP:
 		if ((eth_type != htons(ETH_P_IP) &&
 		     eth_type != htons(ETH_P_IPV6)) ||
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 5904e93..fd8a01c 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -585,7 +585,8 @@
 	head = find_bucket(ti, hash);
 	(*n_mask_hit)++;
 
-	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
+	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver],
+				lockdep_ovsl_is_held()) {
 		if (flow->mask == mask && flow->flow_table.hash == hash &&
 		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
 			return flow;
@@ -769,7 +770,8 @@
 
 	hash = ufid_hash(ufid);
 	head = find_bucket(ti, hash);
-	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver],
+				lockdep_ovsl_is_held()) {
 		if (flow->ufid_table.hash == hash &&
 		    ovs_flow_cmp_ufid(flow, ufid))
 			return flow;
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 3323b79..5010d1d 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -61,7 +61,8 @@
 	struct hlist_head *head;
 
 	head = meter_hash_bucket(dp, meter_id);
-	hlist_for_each_entry_rcu(meter, head, dp_hash_node) {
+	hlist_for_each_entry_rcu(meter, head, dp_hash_node,
+				lockdep_ovsl_is_held()) {
 		if (meter->id == meter_id)
 			return meter;
 	}
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 5da9392..47febb4 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -96,7 +96,8 @@
 	struct hlist_head *bucket = hash_bucket(net, name);
 	struct vport *vport;
 
-	hlist_for_each_entry_rcu(vport, bucket, hash_node)
+	hlist_for_each_entry_rcu(vport, bucket, hash_node,
+				lockdep_ovsl_is_held())
 		if (!strcmp(name, ovs_vport_name(vport)) &&
 		    net_eq(ovs_dp_get_net(vport->dp), net))
 			return vport;
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 3341eee..585e6b3 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -162,10 +162,9 @@
 	if (write)
 		gup_flags |= FOLL_WRITE;
 
-	ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
+	ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages);
 	if (ret >= 0 && ret < nr_pages) {
-		while (ret--)
-			put_page(pages[ret]);
+		unpin_user_pages(pages, ret);
 		ret = -EFAULT;
 	}
 
@@ -300,8 +299,7 @@
 		 * to release anything.
 		 */
 		if (!need_odp) {
-			for (i = 0 ; i < nents; i++)
-				put_page(sg_page(&sg[i]));
+			unpin_user_pages(pages, nr_pages);
 			kfree(sg);
 		}
 		ret = PTR_ERR(trans_private);
@@ -325,7 +323,12 @@
 	if (cookie_ret)
 		*cookie_ret = cookie;
 
-	if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) {
+	if (args->cookie_addr &&
+	    put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) {
+		if (!need_odp) {
+			unpin_user_pages(pages, nr_pages);
+			kfree(sg);
+		}
 		ret = -EFAULT;
 		goto out;
 	}
@@ -496,9 +499,7 @@
 			 * is the case for a RDMA_READ which copies from remote
 			 * to local memory
 			 */
-			if (!ro->op_write)
-				set_page_dirty(page);
-			put_page(page);
+			unpin_user_pages_dirty_lock(&page, 1, !ro->op_write);
 		}
 	}
 
@@ -515,8 +516,7 @@
 	/* Mark page dirty if it was possibly modified, which
 	 * is the case for a RDMA_READ which copies from remote
 	 * to local memory */
-	set_page_dirty(page);
-	put_page(page);
+	unpin_user_pages_dirty_lock(&page, 1, true);
 
 	kfree(ao->op_notifier);
 	ao->op_notifier = NULL;
@@ -944,7 +944,7 @@
 	return ret;
 err:
 	if (page)
-		put_page(page);
+		unpin_user_page(page);
 	rm->atomic.op_active = 0;
 	kfree(rm->atomic.op_notifier);
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index f9c0d1e..d32d423 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -305,6 +305,7 @@
 	struct cls_fl_filter *f;
 
 	list_for_each_entry_rcu(mask, &head->masks, list) {
+		flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
 		fl_clear_masked_range(&skb_key, mask);
 
 		skb_flow_dissect_meta(skb, &mask->dissector, &skb_key);
@@ -691,6 +692,7 @@
 					    .len = 128 / BITS_PER_BYTE },
 	[TCA_FLOWER_KEY_CT_LABELS_MASK]	= { .type = NLA_BINARY,
 					    .len = 128 / BITS_PER_BYTE },
+	[TCA_FLOWER_FLAGS]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 039cc86..610a0b7 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -157,6 +157,7 @@
 static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
 	[TCA_MATCHALL_UNSPEC]		= { .type = NLA_UNSPEC },
 	[TCA_MATCHALL_CLASSID]		= { .type = NLA_U32 },
+	[TCA_MATCHALL_FLAGS]		= { .type = NLA_U32 },
 };
 
 static int mall_set_parms(struct net *net, struct tcf_proto *tp,
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 748e3b1..6a16af4 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -170,6 +170,16 @@
 	return true;
 }
 
+/* Check for format error in an ABORT chunk */
+static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk)
+{
+	struct sctp_errhdr *err;
+
+	sctp_walk_errors(err, chunk->chunk_hdr);
+
+	return (void *)err == (void *)chunk->chunk_end;
+}
+
 /**********************************************************
  * These are the state functions for handling chunk events.
  **********************************************************/
@@ -2255,6 +2265,9 @@
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2298,6 +2311,9 @@
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	/* Stop the T2-shutdown timer. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN));
@@ -2565,6 +2581,9 @@
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2582,16 +2601,8 @@
 
 	/* See if we have an error cause code in the chunk.  */
 	len = ntohs(chunk->chunk_hdr->length);
-	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) {
-		struct sctp_errhdr *err;
-
-		sctp_walk_errors(err, chunk->chunk_hdr);
-		if ((void *)err != (void *)chunk->chunk_end)
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg,
-						commands);
-
+	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((struct sctp_errhdr *)chunk->skb->data)->cause;
-	}
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
 	/* ASSOC_FAILED will DELETE_TCB. */
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index cee5bf4..90988a5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -470,6 +470,8 @@
 	if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
 		smc->clcsock->file = smc->sk.sk_socket->file;
 		smc->clcsock->file->private_data = smc->clcsock;
+		smc->clcsock->wq.fasync_list =
+			smc->sk.sk_socket->wq.fasync_list;
 	}
 }
 
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 0879f7b..86cccc2 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -372,7 +372,9 @@
 	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
 	dclc.hdr.version = SMC_CLC_V1;
 	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
-	memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
+	if (smc->conn.lgr && !smc->conn.lgr->is_smcd)
+		memcpy(dclc.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
 	dclc.peer_diagnosis = htonl(peer_diag_info);
 	memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index f38727e..e1f64f4 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -39,16 +39,15 @@
 {
 	struct smc_sock *smc = smc_sk(sk);
 
+	memset(r, 0, sizeof(*r));
 	r->diag_family = sk->sk_family;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (!smc->clcsock)
 		return;
 	r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
 	r->id.idiag_dport = smc->clcsock->sk->sk_dport;
 	r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
-	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (sk->sk_protocol == SMCPROTO_SMC) {
-		memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
-		memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
 		r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
 		r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 095be88..125297c 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -288,8 +288,8 @@
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	struct ib_reg_wr *reg_wr;
+	int i, n, dma_nents;
 	struct ib_mr *ibmr;
-	int i, n;
 	u8 key;
 
 	if (nsegs > ia->ri_max_frwr_depth)
@@ -313,15 +313,16 @@
 			break;
 	}
 	mr->mr_dir = rpcrdma_data_dir(writing);
+	mr->mr_nents = i;
 
-	mr->mr_nents =
-		ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, i, mr->mr_dir);
-	if (!mr->mr_nents)
+	dma_nents = ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, mr->mr_nents,
+				  mr->mr_dir);
+	if (!dma_nents)
 		goto out_dmamap_err;
 
 	ibmr = mr->frwr.fr_mr;
-	n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE);
-	if (unlikely(n != mr->mr_nents))
+	n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE);
+	if (n != dma_nents)
 		goto out_mapmr_err;
 
 	ibmr->iova &= 0x00000000ffffffff;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 99b28b6..0c88778 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -278,7 +278,7 @@
 }
 #endif
 
-void tipc_node_free(struct rcu_head *rp)
+static void tipc_node_free(struct rcu_head *rp)
 {
 	struct tipc_node *n = container_of(rp, struct tipc_node, rcu);
 
@@ -2798,7 +2798,7 @@
 	return 0;
 }
 
-int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
+static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1];
 	struct net *net = sock_net(skb->sk);
@@ -2875,7 +2875,8 @@
 	return err;
 }
 
-int __tipc_nl_node_flush_key(struct sk_buff *skb, struct genl_info *info)
+static int __tipc_nl_node_flush_key(struct sk_buff *skb,
+				    struct genl_info *info)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tipc_net *tn = tipc_net(net);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f9b4fb9..693e890 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2441,6 +2441,8 @@
 			return -ETIMEDOUT;
 		if (signal_pending(current))
 			return sock_intr_errno(*timeo_p);
+		if (sk->sk_state == TIPC_DISCONNECTING)
+			break;
 
 		add_wait_queue(sk_sleep(sk), &wait);
 		done = sk_wait_event(sk, timeo_p, tipc_sk_connected(sk),
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 1ba5a92..1c5574e 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -593,7 +593,7 @@
 				       u32 seq, u64 *p_record_sn)
 {
 	u64 record_sn = context->hint_record_sn;
-	struct tls_record_info *info;
+	struct tls_record_info *info, *last;
 
 	info = context->retransmit_hint;
 	if (!info ||
@@ -605,6 +605,24 @@
 						struct tls_record_info, list);
 		if (!info)
 			return NULL;
+		/* send the start_marker record if seq number is before the
+		 * tls offload start marker sequence number. This record is
+		 * required to handle TCP packets which are before TLS offload
+		 * started.
+		 *  And if it's not start marker, look if this seq number
+		 * belongs to the list.
+		 */
+		if (likely(!tls_record_is_start_marker(info))) {
+			/* we have the first record, get the last record to see
+			 * if this seq number belongs to the list.
+			 */
+			last = list_last_entry(&context->records_list,
+					       struct tls_record_info, list);
+
+			if (!between(seq, tls_record_start_seq(info),
+				     last->end_seq))
+				return NULL;
+		}
 		record_sn = context->unacked_record_sn;
 	}
 
diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c
index a9c0f36..24e1840 100644
--- a/net/wireless/ethtool.c
+++ b/net/wireless/ethtool.c
@@ -7,9 +7,13 @@
 void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct device *pdev = wiphy_dev(wdev->wiphy);
 
-	strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name,
-		sizeof(info->driver));
+	if (pdev->driver)
+		strlcpy(info->driver, pdev->driver->name,
+			sizeof(info->driver));
+	else
+		strlcpy(info->driver, "N/A", sizeof(info->driver));
 
 	strlcpy(info->version, init_utsname()->release, sizeof(info->version));
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 123b8d7..cedf17d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -437,6 +437,7 @@
 	[NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG },
 	[NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG },
+	[NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 },
 	[NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 },
 	[NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 },
 	[NL80211_ATTR_PID] = { .type = NLA_U32 },
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index df60048..356f90e 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -217,6 +217,7 @@
 static void xsk_flush(struct xdp_sock *xs)
 {
 	xskq_prod_submit(xs->rx);
+	__xskq_cons_release(xs->umem->fq);
 	sock_def_readable(&xs->sk);
 }
 
@@ -304,6 +305,7 @@
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+		__xskq_cons_release(xs->tx);
 		xs->sk.sk_write_space(&xs->sk);
 	}
 	rcu_read_unlock();
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index bec2af1..89a01ac 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -271,7 +271,8 @@
 {
 	/* To improve performance, only update local state here.
 	 * Reflect this to global state when we get new entries
-	 * from the ring in xskq_cons_get_entries().
+	 * from the ring in xskq_cons_get_entries() and whenever
+	 * Rx or Tx processing are completed in the NAPI loop.
 	 */
 	q->cached_cons++;
 }
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index dc651a6..3361e3a 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -300,10 +300,10 @@
 			if (mtu < IPV6_MIN_MTU)
 				mtu = IPV6_MIN_MTU;
 
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		} else {
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-				  htonl(mtu));
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				      htonl(mtu));
 		}
 
 		dst_release(dst);
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 34085d1..6cbcd1a 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -932,10 +932,6 @@
 	}
     }
 
-    foreach my $fix (@fixes) {
-	vcs_add_commit_signers($fix, "blamed_fixes");
-    }
-
     foreach my $email (@email_to, @list_to) {
 	$email->[0] = deduplicate_email($email->[0]);
     }
@@ -974,6 +970,10 @@
 	}
     }
 
+    foreach my $fix (@fixes) {
+	vcs_add_commit_signers($fix, "blamed_fixes");
+    }
+
     my @to = ();
     if ($email || $email_list) {
 	if ($email) {
@@ -1341,35 +1341,11 @@
 		    }
 		}
 	    } elsif ($ptype eq "M") {
-		my ($name, $address) = parse_email($pvalue);
-		if ($name eq "") {
-		    if ($i > 0) {
-			my $tv = $typevalue[$i - 1];
-			if ($tv =~ m/^([A-Z]):\s*(.*)/) {
-			    if ($1 eq "P") {
-				$name = $2;
-				$pvalue = format_email($name, $address, $email_usename);
-			    }
-			}
-		    }
-		}
 		if ($email_maintainer) {
 		    my $role = get_maintainer_role($i);
 		    push_email_addresses($pvalue, $role);
 		}
 	    } elsif ($ptype eq "R") {
-		my ($name, $address) = parse_email($pvalue);
-		if ($name eq "") {
-		    if ($i > 0) {
-			my $tv = $typevalue[$i - 1];
-			if ($tv =~ m/^([A-Z]):\s*(.*)/) {
-			    if ($1 eq "P") {
-				$name = $2;
-				$pvalue = format_email($name, $address, $email_usename);
-			    }
-			}
-		    }
-		}
 		if ($email_reviewer) {
 		    my $subsystem = get_subsystem_name($i);
 		    push_email_addresses($pvalue, "reviewer:$subsystem");
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index a566d82..0133dfa 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -210,7 +210,7 @@
 
 	len = strlen(name) + 1;
 
-	sym = malloc(sizeof(*sym) + len);
+	sym = malloc(sizeof(*sym) + len + 1);
 	if (!sym) {
 		fprintf(stderr, "kallsyms failure: "
 			"unable to allocate required amount of memory\n");
@@ -219,7 +219,7 @@
 	sym->addr = addr;
 	sym->len = len;
 	sym->sym[0] = type;
-	memcpy(sym_name(sym), name, len);
+	strcpy(sym_name(sym), name);
 	sym->percpu_absolute = 0;
 
 	return sym;
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 1919c31..dd484e9 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -239,7 +239,7 @@
 fi;
 
 # final build of init/
-${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init
+${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init need-builtin=1
 
 #link vmlinux.o
 info LD vmlinux.o
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 711ff10..3f3ee4e 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -112,6 +112,10 @@
 	config IMA_DEFAULT_HASH_WP512
 		bool "WP512"
 		depends on CRYPTO_WP512=y && !IMA_TEMPLATE
+
+	config IMA_DEFAULT_HASH_SM3
+		bool "SM3"
+		depends on CRYPTO_SM3=y && !IMA_TEMPLATE
 endchoice
 
 config IMA_DEFAULT_HASH
@@ -121,6 +125,7 @@
 	default "sha256" if IMA_DEFAULT_HASH_SHA256
 	default "sha512" if IMA_DEFAULT_HASH_SHA512
 	default "wp512" if IMA_DEFAULT_HASH_WP512
+	default "sm3" if IMA_DEFAULT_HASH_SM3
 
 config IMA_WRITE_POLICY
 	bool "Enable multiple writes to the IMA policy"
diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c
index 111898a..f0c9082 100644
--- a/security/integrity/platform_certs/load_uefi.c
+++ b/security/integrity/platform_certs/load_uefi.c
@@ -35,16 +35,18 @@
  * Get a certificate list blob from the named EFI variable.
  */
 static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid,
-				  unsigned long *size)
+				  unsigned long *size, efi_status_t *status)
 {
-	efi_status_t status;
 	unsigned long lsize = 4;
 	unsigned long tmpdb[4];
 	void *db;
 
-	status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
-	if (status != EFI_BUFFER_TOO_SMALL) {
-		pr_err("Couldn't get size: 0x%lx\n", status);
+	*status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
+	if (*status == EFI_NOT_FOUND)
+		return NULL;
+
+	if (*status != EFI_BUFFER_TOO_SMALL) {
+		pr_err("Couldn't get size: 0x%lx\n", *status);
 		return NULL;
 	}
 
@@ -52,10 +54,10 @@
 	if (!db)
 		return NULL;
 
-	status = efi.get_variable(name, guid, NULL, &lsize, db);
-	if (status != EFI_SUCCESS) {
+	*status = efi.get_variable(name, guid, NULL, &lsize, db);
+	if (*status != EFI_SUCCESS) {
 		kfree(db);
-		pr_err("Error reading db var: 0x%lx\n", status);
+		pr_err("Error reading db var: 0x%lx\n", *status);
 		return NULL;
 	}
 
@@ -74,6 +76,7 @@
 	efi_guid_t mok_var = EFI_SHIM_LOCK_GUID;
 	void *db = NULL, *dbx = NULL, *mok = NULL;
 	unsigned long dbsize = 0, dbxsize = 0, moksize = 0;
+	efi_status_t status;
 	int rc = 0;
 
 	if (!efi.get_variable)
@@ -83,9 +86,12 @@
 	 * an error if we can't get them.
 	 */
 	if (!uefi_check_ignore_db()) {
-		db = get_cert_list(L"db", &secure_var, &dbsize);
+		db = get_cert_list(L"db", &secure_var, &dbsize, &status);
 		if (!db) {
-			pr_err("MODSIGN: Couldn't get UEFI db list\n");
+			if (status == EFI_NOT_FOUND)
+				pr_debug("MODSIGN: db variable wasn't found\n");
+			else
+				pr_err("MODSIGN: Couldn't get UEFI db list\n");
 		} else {
 			rc = parse_efi_signature_list("UEFI:db",
 					db, dbsize, get_handler_for_db);
@@ -96,9 +102,12 @@
 		}
 	}
 
-	mok = get_cert_list(L"MokListRT", &mok_var, &moksize);
+	mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status);
 	if (!mok) {
-		pr_info("Couldn't get UEFI MokListRT\n");
+		if (status == EFI_NOT_FOUND)
+			pr_debug("MokListRT variable wasn't found\n");
+		else
+			pr_info("Couldn't get UEFI MokListRT\n");
 	} else {
 		rc = parse_efi_signature_list("UEFI:MokListRT",
 					      mok, moksize, get_handler_for_db);
@@ -107,9 +116,12 @@
 		kfree(mok);
 	}
 
-	dbx = get_cert_list(L"dbx", &secure_var, &dbxsize);
+	dbx = get_cert_list(L"dbx", &secure_var, &dbxsize, &status);
 	if (!dbx) {
-		pr_info("Couldn't get UEFI dbx list\n");
+		if (status == EFI_NOT_FOUND)
+			pr_debug("dbx variable wasn't found\n");
+		else
+			pr_info("Couldn't get UEFI dbx list\n");
 	} else {
 		rc = parse_efi_signature_list("UEFI:dbx",
 					      dbx, dbxsize,
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4b6991e..1659b59 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -698,7 +698,7 @@
 
 	if (!strcmp(sb->s_type->name, "debugfs") ||
 	    !strcmp(sb->s_type->name, "tracefs") ||
-	    !strcmp(sb->s_type->name, "binderfs") ||
+	    !strcmp(sb->s_type->name, "binder") ||
 	    !strcmp(sb->s_type->name, "pstore"))
 		sbsec->flags |= SE_SBGENFS;
 
diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c
index a308ce1..f511ffc 100644
--- a/security/selinux/ss/sidtab.c
+++ b/security/selinux/ss/sidtab.c
@@ -518,19 +518,13 @@
 			const char *str, u32 str_len)
 {
 	struct sidtab_str_cache *cache, *victim = NULL;
+	unsigned long flags;
 
 	/* do not cache invalid contexts */
 	if (entry->context.len)
 		return;
 
-	/*
-	 * Skip the put operation when in non-task context to avoid the need
-	 * to disable interrupts while holding s->cache_lock.
-	 */
-	if (!in_task())
-		return;
-
-	spin_lock(&s->cache_lock);
+	spin_lock_irqsave(&s->cache_lock, flags);
 
 	cache = rcu_dereference_protected(entry->cache,
 					  lockdep_is_held(&s->cache_lock));
@@ -561,7 +555,7 @@
 	rcu_assign_pointer(entry->cache, cache);
 
 out_unlock:
-	spin_unlock(&s->cache_lock);
+	spin_unlock_irqrestore(&s->cache_lock, flags);
 	kfree_rcu(victim, rcu_member);
 }
 
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 336406b..d5443ee 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -2594,7 +2594,8 @@
 
 	snd_pcm_drop(substream);
 	if (substream->hw_opened) {
-		do_hw_free(substream);
+		if (substream->runtime->status->state != SNDRV_PCM_STATE_OPEN)
+			do_hw_free(substream);
 		substream->ops->close(substream);
 		substream->hw_opened = 0;
 	}
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 6d9592f..cc93157 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -580,7 +580,7 @@
 	event->queue = queue;
 	event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK;
 	if (real_time) {
-		event->time.time = snd_seq_timer_get_cur_time(q->timer);
+		event->time.time = snd_seq_timer_get_cur_time(q->timer, true);
 		event->flags |= SNDRV_SEQ_TIME_STAMP_REAL;
 	} else {
 		event->time.tick = snd_seq_timer_get_cur_tick(q->timer);
@@ -1659,7 +1659,7 @@
 	tmr = queue->timer;
 	status->events = queue->tickq->cells + queue->timeq->cells;
 
-	status->time = snd_seq_timer_get_cur_time(tmr);
+	status->time = snd_seq_timer_get_cur_time(tmr, true);
 	status->tick = snd_seq_timer_get_cur_tick(tmr);
 
 	status->running = tmr->running;
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index caf68bf4..71a6ea6 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -238,6 +238,8 @@
 {
 	unsigned long flags;
 	struct snd_seq_event_cell *cell;
+	snd_seq_tick_time_t cur_tick;
+	snd_seq_real_time_t cur_time;
 
 	if (q == NULL)
 		return;
@@ -254,17 +256,18 @@
 
       __again:
 	/* Process tick queue... */
+	cur_tick = snd_seq_timer_get_cur_tick(q->timer);
 	for (;;) {
-		cell = snd_seq_prioq_cell_out(q->tickq,
-					      &q->timer->tick.cur_tick);
+		cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick);
 		if (!cell)
 			break;
 		snd_seq_dispatch_event(cell, atomic, hop);
 	}
 
 	/* Process time queue... */
+	cur_time = snd_seq_timer_get_cur_time(q->timer, false);
 	for (;;) {
-		cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time);
+		cell = snd_seq_prioq_cell_out(q->timeq, &cur_time);
 		if (!cell)
 			break;
 		snd_seq_dispatch_event(cell, atomic, hop);
@@ -392,6 +395,7 @@
 int snd_seq_queue_set_owner(int queueid, int client, int locked)
 {
 	struct snd_seq_queue *q = queueptr(queueid);
+	unsigned long flags;
 
 	if (q == NULL)
 		return -EINVAL;
@@ -401,8 +405,10 @@
 		return -EPERM;
 	}
 
+	spin_lock_irqsave(&q->owner_lock, flags);
 	q->locked = locked ? 1 : 0;
 	q->owner = client;
+	spin_unlock_irqrestore(&q->owner_lock, flags);
 	queue_access_unlock(q);
 	queuefree(q);
 
@@ -539,15 +545,17 @@
 	unsigned long flags;
 	int i;
 	struct snd_seq_queue *q;
+	bool matched;
 
 	for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
 		if ((q = queueptr(i)) == NULL)
 			continue;
 		spin_lock_irqsave(&q->owner_lock, flags);
-		if (q->owner == client)
+		matched = (q->owner == client);
+		if (matched)
 			q->klocked = 1;
 		spin_unlock_irqrestore(&q->owner_lock, flags);
-		if (q->owner == client) {
+		if (matched) {
 			if (q->timer->running)
 				snd_seq_timer_stop(q->timer);
 			snd_seq_timer_reset(q->timer);
@@ -739,6 +747,8 @@
 	int i, bpm;
 	struct snd_seq_queue *q;
 	struct snd_seq_timer *tmr;
+	bool locked;
+	int owner;
 
 	for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
 		if ((q = queueptr(i)) == NULL)
@@ -750,9 +760,14 @@
 		else
 			bpm = 0;
 
+		spin_lock_irq(&q->owner_lock);
+		locked = q->locked;
+		owner = q->owner;
+		spin_unlock_irq(&q->owner_lock);
+
 		snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name);
-		snd_iprintf(buffer, "owned by client    : %d\n", q->owner);
-		snd_iprintf(buffer, "lock status        : %s\n", q->locked ? "Locked" : "Free");
+		snd_iprintf(buffer, "owned by client    : %d\n", owner);
+		snd_iprintf(buffer, "lock status        : %s\n", locked ? "Locked" : "Free");
 		snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq));
 		snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq));
 		snd_iprintf(buffer, "timer state        : %s\n", tmr->running ? "Running" : "Stopped");
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index be59b59..1645e41 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -428,14 +428,15 @@
 }
 
 /* return current 'real' time. use timeofday() to get better granularity. */
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+					       bool adjust_ktime)
 {
 	snd_seq_real_time_t cur_time;
 	unsigned long flags;
 
 	spin_lock_irqsave(&tmr->lock, flags);
 	cur_time = tmr->cur_time;
-	if (tmr->running) { 
+	if (adjust_ktime && tmr->running) {
 		struct timespec64 tm;
 
 		ktime_get_ts64(&tm);
@@ -452,7 +453,13 @@
  high PPQ values) */
 snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr)
 {
-	return tmr->tick.cur_tick;
+	snd_seq_tick_time_t cur_tick;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tmr->lock, flags);
+	cur_tick = tmr->tick.cur_tick;
+	spin_unlock_irqrestore(&tmr->lock, flags);
+	return cur_tick;
 }
 
 
diff --git a/sound/core/seq/seq_timer.h b/sound/core/seq/seq_timer.h
index 66c3e34..4bec57d 100644
--- a/sound/core/seq/seq_timer.h
+++ b/sound/core/seq/seq_timer.h
@@ -120,7 +120,8 @@
 int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position);
 int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position);
 int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base);
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr);
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+					       bool adjust_ktime);
 snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr);
 
 extern int seq_default_timer_class;
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index a684f05..4d060d5 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -254,6 +254,7 @@
 int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 				struct hdac_ext_link *link)
 {
+	unsigned long codec_mask;
 	int ret = 0;
 
 	mutex_lock(&bus->lock);
@@ -280,9 +281,11 @@
 		 *  HDA spec section 4.3 - Codec Discovery
 		 */
 		udelay(521);
-		bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS);
-		dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask);
-		snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask);
+		codec_mask = snd_hdac_chip_readw(bus, STATESTS);
+		dev_dbg(bus->dev, "codec_mask = 0x%lx\n", codec_mask);
+		snd_hdac_chip_writew(bus, STATESTS, codec_mask);
+		if (!bus->codec_mask)
+			bus->codec_mask = codec_mask;
 	}
 
 	mutex_unlock(&bus->lock);
diff --git a/sound/hda/hdmi_chmap.c b/sound/hda/hdmi_chmap.c
index 5fd6d57..aad5c4b 100644
--- a/sound/hda/hdmi_chmap.c
+++ b/sound/hda/hdmi_chmap.c
@@ -250,7 +250,7 @@
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) {
 		if (spk_alloc & (1 << i))
-			j += snprintf(buf + j, buflen - j,  " %s",
+			j += scnprintf(buf + j, buflen - j,  " %s",
 					cea_speaker_allocation_names[i]);
 	}
 	buf[j] = '\0';	/* necessary when j == 0 */
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 5dc42f9..53e7732 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -4022,7 +4022,7 @@
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++)
 		if (pcm & (AC_SUPPCM_BITS_8 << i))
-			j += snprintf(buf + j, buflen - j,  " %d", bits[i]);
+			j += scnprintf(buf + j, buflen - j,  " %d", bits[i]);
 
 	buf[j] = '\0'; /* necessary when j == 0 */
 }
diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c
index bb46c89..136477ed 100644
--- a/sound/pci/hda/hda_eld.c
+++ b/sound/pci/hda/hda_eld.c
@@ -360,7 +360,7 @@
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++)
 		if (pcm & (1 << i))
-			j += snprintf(buf + j, buflen - j,  " %d",
+			j += scnprintf(buf + j, buflen - j,  " %d",
 				alsa_rates[i]);
 
 	buf[j] = '\0'; /* necessary when j == 0 */
diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c
index 0607ed5..eb8ec10 100644
--- a/sound/pci/hda/hda_sysfs.c
+++ b/sound/pci/hda/hda_sysfs.c
@@ -222,7 +222,7 @@
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
 	snd_array_for_each(&codec->init_verbs, i, v) {
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 				"0x%02x 0x%03x 0x%04x\n",
 				v->nid, v->verb, v->param);
 	}
@@ -272,7 +272,7 @@
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
 	snd_array_for_each(&codec->hints, i, hint) {
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 				"%s = %s\n", hint->key, hint->val);
 	}
 	mutex_unlock(&codec->user_mutex);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4770fb3..477589e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2447,6 +2447,9 @@
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
@@ -5701,8 +5704,11 @@
 		break;
 	case HDA_FIXUP_ACT_INIT:
 		switch (codec->core.vendor_id) {
+		case 0x10ec0215:
 		case 0x10ec0225:
+		case 0x10ec0285:
 		case 0x10ec0295:
+		case 0x10ec0289:
 		case 0x10ec0299:
 			alc_write_coef_idx(codec, 0x48, 0xd011);
 			alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
diff --git a/sound/soc/amd/raven/acp3x-i2s.c b/sound/soc/amd/raven/acp3x-i2s.c
index 31cd400..91a3881 100644
--- a/sound/soc/amd/raven/acp3x-i2s.c
+++ b/sound/soc/amd/raven/acp3x-i2s.c
@@ -170,6 +170,7 @@
 	struct snd_soc_card *card;
 	struct acp3x_platform_info *pinfo;
 	u32 ret, val, period_bytes, reg_val, ier_val, water_val;
+	u32 buf_size, buf_reg;
 
 	prtd = substream->private_data;
 	rtd = substream->runtime->private_data;
@@ -183,6 +184,8 @@
 	}
 	period_bytes = frames_to_bytes(substream->runtime,
 			substream->runtime->period_size);
+	buf_size = frames_to_bytes(substream->runtime,
+			substream->runtime->buffer_size);
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
@@ -196,6 +199,7 @@
 					mmACP_BT_TX_INTR_WATERMARK_SIZE;
 				reg_val = mmACP_BTTDM_ITER;
 				ier_val = mmACP_BTTDM_IER;
+				buf_reg = mmACP_BT_TX_RINGBUFSIZE;
 				break;
 			case I2S_SP_INSTANCE:
 			default:
@@ -203,6 +207,7 @@
 					mmACP_I2S_TX_INTR_WATERMARK_SIZE;
 				reg_val = mmACP_I2STDM_ITER;
 				ier_val = mmACP_I2STDM_IER;
+				buf_reg = mmACP_I2S_TX_RINGBUFSIZE;
 			}
 		} else {
 			switch (rtd->i2s_instance) {
@@ -211,6 +216,7 @@
 					mmACP_BT_RX_INTR_WATERMARK_SIZE;
 				reg_val = mmACP_BTTDM_IRER;
 				ier_val = mmACP_BTTDM_IER;
+				buf_reg = mmACP_BT_RX_RINGBUFSIZE;
 				break;
 			case I2S_SP_INSTANCE:
 			default:
@@ -218,9 +224,11 @@
 					mmACP_I2S_RX_INTR_WATERMARK_SIZE;
 				reg_val = mmACP_I2STDM_IRER;
 				ier_val = mmACP_I2STDM_IER;
+				buf_reg = mmACP_I2S_RX_RINGBUFSIZE;
 			}
 		}
 		rv_writel(period_bytes, rtd->acp3x_base + water_val);
+		rv_writel(buf_size, rtd->acp3x_base + buf_reg);
 		val = rv_readl(rtd->acp3x_base + reg_val);
 		val = val | BIT(0);
 		rv_writel(val, rtd->acp3x_base + reg_val);
diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c
index aecc3c0..d62c0d9 100644
--- a/sound/soc/amd/raven/acp3x-pcm-dma.c
+++ b/sound/soc/amd/raven/acp3x-pcm-dma.c
@@ -110,7 +110,7 @@
 {
 	u16 page_idx;
 	u32 low, high, val, acp_fifo_addr, reg_fifo_addr;
-	u32 reg_ringbuf_size, reg_dma_size, reg_fifo_size;
+	u32 reg_dma_size, reg_fifo_size;
 	dma_addr_t addr;
 
 	addr = rtd->dma_addr;
@@ -157,7 +157,6 @@
 	if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
 		switch (rtd->i2s_instance) {
 		case I2S_BT_INSTANCE:
-			reg_ringbuf_size = mmACP_BT_TX_RINGBUFSIZE;
 			reg_dma_size = mmACP_BT_TX_DMA_SIZE;
 			acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
 						BT_PB_FIFO_ADDR_OFFSET;
@@ -169,7 +168,6 @@
 
 		case I2S_SP_INSTANCE:
 		default:
-			reg_ringbuf_size = mmACP_I2S_TX_RINGBUFSIZE;
 			reg_dma_size = mmACP_I2S_TX_DMA_SIZE;
 			acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
 						SP_PB_FIFO_ADDR_OFFSET;
@@ -181,7 +179,6 @@
 	} else {
 		switch (rtd->i2s_instance) {
 		case I2S_BT_INSTANCE:
-			reg_ringbuf_size = mmACP_BT_RX_RINGBUFSIZE;
 			reg_dma_size = mmACP_BT_RX_DMA_SIZE;
 			acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
 						BT_CAPT_FIFO_ADDR_OFFSET;
@@ -193,7 +190,6 @@
 
 		case I2S_SP_INSTANCE:
 		default:
-			reg_ringbuf_size = mmACP_I2S_RX_RINGBUFSIZE;
 			reg_dma_size = mmACP_I2S_RX_DMA_SIZE;
 			acp_fifo_addr = ACP_SRAM_PTE_OFFSET +
 						SP_CAPT_FIFO_ADDR_OFFSET;
@@ -203,7 +199,6 @@
 				rtd->acp3x_base + mmACP_I2S_RX_RINGBUFADDR);
 		}
 	}
-	rv_writel(MAX_BUFFER, rtd->acp3x_base + reg_ringbuf_size);
 	rv_writel(DMA_SIZE, rtd->acp3x_base + reg_dma_size);
 	rv_writel(acp_fifo_addr, rtd->acp3x_base + reg_fifo_addr);
 	rv_writel(FIFO_SIZE, rtd->acp3x_base + reg_fifo_size);
diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c
index 65330bb..da60e2e 100644
--- a/sound/soc/amd/raven/pci-acp3x.c
+++ b/sound/soc/amd/raven/pci-acp3x.c
@@ -45,23 +45,6 @@
 	return -ETIMEDOUT;
 }
 
-static int acp3x_power_off(void __iomem *acp3x_base)
-{
-	u32 val;
-	int timeout;
-
-	rv_writel(ACP_PGFSM_CNTL_POWER_OFF_MASK,
-			acp3x_base + mmACP_PGFSM_CONTROL);
-	timeout = 0;
-	while (++timeout < 500) {
-		val = rv_readl(acp3x_base + mmACP_PGFSM_STATUS);
-		if ((val & ACP_PGFSM_STATUS_MASK) == ACP_POWERED_OFF)
-			return 0;
-		udelay(1);
-	}
-	return -ETIMEDOUT;
-}
-
 static int acp3x_reset(void __iomem *acp3x_base)
 {
 	u32 val;
@@ -115,12 +98,6 @@
 		pr_err("ACP3x reset failed\n");
 		return ret;
 	}
-	/* power off */
-	ret = acp3x_power_off(acp3x_base);
-	if (ret) {
-		pr_err("ACP3x power off failed\n");
-		return ret;
-	}
 	return 0;
 }
 
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index d1dc8e6..71f2d42 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -10,11 +10,11 @@
 if SND_ATMEL_SOC
 
 config SND_ATMEL_SOC_PDC
-	tristate
+	bool
 	depends on HAS_DMA
 
 config SND_ATMEL_SOC_DMA
-	tristate
+	bool
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 
 config SND_ATMEL_SOC_SSC
diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile
index 1f6890e..c7d2989 100644
--- a/sound/soc/atmel/Makefile
+++ b/sound/soc/atmel/Makefile
@@ -6,8 +6,14 @@
 snd-soc-atmel-i2s-objs := atmel-i2s.o
 snd-soc-mchp-i2s-mcc-objs := mchp-i2s-mcc.o
 
-obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o
-obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o
+# pdc and dma need to both be built-in if any user of
+# ssc is built-in.
+ifdef CONFIG_SND_ATMEL_SOC_PDC
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-pdc.o
+endif
+ifdef CONFIG_SND_ATMEL_SOC_DMA
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-dma.o
+endif
 obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o
 obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o
 obj-$(CONFIG_SND_MCHP_SOC_I2S_MCC) += snd-soc-mchp-i2s-mcc.o
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 444cc4e..f005751 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -779,7 +779,17 @@
 	return ret;
 }
 
+static void hdmi_remove(struct snd_soc_component *component)
+{
+	struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component);
+
+	if (hcp->hcd.ops->hook_plugged_cb)
+		hcp->hcd.ops->hook_plugged_cb(component->dev->parent,
+					      hcp->hcd.data, NULL, NULL);
+}
+
 static const struct snd_soc_component_driver hdmi_driver = {
+	.remove			= hdmi_remove,
 	.dapm_widgets		= hdmi_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(hdmi_widgets),
 	.of_xlate_dai_id	= hdmi_of_xlate_dai_id,
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 5bc2c64..032adc1 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -5,150 +5,24 @@
  * Copyright 2011-2012 Maxim Integrated Products
  */
 
-#include <linux/acpi.h>
-#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
+#include <linux/acpi.h>
+#include <linux/clk.h>
 #include <sound/jack.h>
-#include <sound/max98090.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/tlv.h>
+#include <sound/max98090.h>
 #include "max98090.h"
 
-static void max98090_shdn_save_locked(struct max98090_priv *max98090)
-{
-	int shdn = 0;
-
-	/* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */
-	regmap_read(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, &shdn);
-	max98090->saved_shdn |= shdn;
-	++max98090->saved_count;
-
-	if (shdn)
-		regmap_write(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, 0x0);
-}
-
-static void max98090_shdn_restore_locked(struct max98090_priv *max98090)
-{
-	/* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */
-	if (--max98090->saved_count == 0) {
-		if (max98090->saved_shdn) {
-			regmap_write(max98090->regmap,
-				     M98090_REG_DEVICE_SHUTDOWN,
-				     M98090_SHDNN_MASK);
-			max98090->saved_shdn = 0;
-		}
-	}
-}
-
-static void max98090_shdn_save(struct max98090_priv *max98090)
-{
-	mutex_lock_nested(&max98090->component->card->dapm_mutex,
-			  SND_SOC_DAPM_CLASS_RUNTIME);
-	max98090_shdn_save_locked(max98090);
-}
-
-static void max98090_shdn_restore(struct max98090_priv *max98090)
-{
-	max98090_shdn_restore_locked(max98090);
-	mutex_unlock(&max98090->component->card->dapm_mutex);
-}
-
-static int max98090_put_volsw(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component =
-		snd_soc_kcontrol_component(kcontrol);
-	struct max98090_priv *max98090 =
-		snd_soc_component_get_drvdata(component);
-	int ret;
-
-	max98090_shdn_save(max98090);
-	ret = snd_soc_put_volsw(kcontrol, ucontrol);
-	max98090_shdn_restore(max98090);
-
-	return ret;
-}
-
-static int max98090_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component =
-		snd_soc_dapm_kcontrol_component(kcontrol);
-	struct max98090_priv *max98090 =
-		snd_soc_component_get_drvdata(component);
-	int ret;
-
-	max98090_shdn_save(max98090);
-	ret = snd_soc_dapm_put_enum_double_locked(kcontrol, ucontrol);
-	max98090_shdn_restore(max98090);
-
-	return ret;
-}
-
-static int max98090_put_enum_double(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component =
-		snd_soc_kcontrol_component(kcontrol);
-	struct max98090_priv *max98090 =
-		snd_soc_component_get_drvdata(component);
-	int ret;
-
-	max98090_shdn_save(max98090);
-	ret = snd_soc_put_enum_double(kcontrol, ucontrol);
-	max98090_shdn_restore(max98090);
-
-	return ret;
-}
-
-static int max98090_bytes_put(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component =
-		snd_soc_kcontrol_component(kcontrol);
-	struct max98090_priv *max98090 =
-		snd_soc_component_get_drvdata(component);
-	int ret;
-
-	max98090_shdn_save(max98090);
-	ret = snd_soc_bytes_put(kcontrol, ucontrol);
-	max98090_shdn_restore(max98090);
-
-	return ret;
-}
-
-static int max98090_dapm_event(struct snd_soc_dapm_widget *w,
-	struct snd_kcontrol *kcontrol, int event)
-{
-	struct snd_soc_component *component =
-		snd_soc_dapm_to_component(w->dapm);
-	struct max98090_priv *max98090 =
-		snd_soc_component_get_drvdata(component);
-
-	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-	case SND_SOC_DAPM_PRE_PMD:
-		max98090_shdn_save_locked(max98090);
-		break;
-	case SND_SOC_DAPM_POST_PMU:
-	case SND_SOC_DAPM_POST_PMD:
-		max98090_shdn_restore_locked(max98090);
-		break;
-	}
-
-	return 0;
-}
-
 /* Allows for sparsely populated register maps */
 static const struct reg_default max98090_reg[] = {
 	{ 0x00, 0x00 }, /* 00 Software Reset */
@@ -632,13 +506,10 @@
 			    max98090_pwr_perf_text);
 
 static const struct snd_kcontrol_new max98090_snd_controls[] = {
-	SOC_ENUM_EXT("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
+	SOC_ENUM("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum),
 
-	SOC_SINGLE_EXT("DMIC MIC Comp Filter Config",
-		M98090_REG_DIGITAL_MIC_CONFIG,
-		M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
+	SOC_SINGLE("DMIC MIC Comp Filter Config", M98090_REG_DIGITAL_MIC_CONFIG,
+		M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0),
 
 	SOC_SINGLE_EXT_TLV("MIC1 Boost Volume",
 		M98090_REG_MIC1_INPUT_LEVEL, M98090_MIC_PA1EN_SHIFT,
@@ -693,34 +564,24 @@
 		M98090_AVR_SHIFT, M98090_AVR_NUM - 1, 1,
 		max98090_av_tlv),
 
-	SOC_ENUM_EXT("ADC Oversampling Rate", max98090_osr128_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_SINGLE_EXT("ADC Quantizer Dither", M98090_REG_ADC_CONTROL,
-		M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_ENUM_EXT("ADC High Performance Mode", max98090_adchp_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
+	SOC_ENUM("ADC Oversampling Rate", max98090_osr128_enum),
+	SOC_SINGLE("ADC Quantizer Dither", M98090_REG_ADC_CONTROL,
+		M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0),
+	SOC_ENUM("ADC High Performance Mode", max98090_adchp_enum),
 
-	SOC_SINGLE_EXT("DAC Mono Mode", M98090_REG_IO_CONFIGURATION,
-		M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_SINGLE_EXT("SDIN Mode", M98090_REG_IO_CONFIGURATION,
-		M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_SINGLE_EXT("SDOUT Mode", M98090_REG_IO_CONFIGURATION,
-		M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_SINGLE_EXT("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION,
-		M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_ENUM_EXT("Filter Mode", max98090_mode_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_SINGLE_EXT("Record Path DC Blocking", M98090_REG_FILTER_CONFIG,
-		M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_SINGLE_EXT("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG,
-		M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
+	SOC_SINGLE("DAC Mono Mode", M98090_REG_IO_CONFIGURATION,
+		M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0),
+	SOC_SINGLE("SDIN Mode", M98090_REG_IO_CONFIGURATION,
+		M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0),
+	SOC_SINGLE("SDOUT Mode", M98090_REG_IO_CONFIGURATION,
+		M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0),
+	SOC_SINGLE("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION,
+		M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1),
+	SOC_ENUM("Filter Mode", max98090_mode_enum),
+	SOC_SINGLE("Record Path DC Blocking", M98090_REG_FILTER_CONFIG,
+		M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0),
+	SOC_SINGLE("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG,
+		M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0),
 	SOC_SINGLE_TLV("Digital BQ Volume", M98090_REG_ADC_BIQUAD_LEVEL,
 		M98090_AVBQ_SHIFT, M98090_AVBQ_NUM - 1, 1, max98090_dv_tlv),
 	SOC_SINGLE_EXT_TLV("Digital Sidetone Volume",
@@ -733,17 +594,13 @@
 	SOC_SINGLE_TLV("Digital Volume", M98090_REG_DAI_PLAYBACK_LEVEL,
 		M98090_DV_SHIFT, M98090_DV_NUM - 1, 1,
 		max98090_dv_tlv),
-	SND_SOC_BYTES_E("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105,
-		snd_soc_bytes_get, max98090_bytes_put),
-	SOC_SINGLE_EXT("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
-		M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_SINGLE_EXT("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
-		M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_SINGLE_EXT("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
-		M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
+	SND_SOC_BYTES("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105),
+	SOC_SINGLE("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
+		M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0),
+	SOC_SINGLE("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
+		M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0),
+	SOC_SINGLE("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE,
+		M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0),
 	SOC_SINGLE("Digital EQ Clipping Detection", M98090_REG_DAI_PLAYBACK_LEVEL_EQ,
 		M98090_EQCLPN_SHIFT, M98090_EQCLPN_NUM - 1,
 		1),
@@ -751,34 +608,25 @@
 		M98090_DVEQ_SHIFT, M98090_DVEQ_NUM - 1, 1,
 		max98090_dv_tlv),
 
-	SOC_SINGLE_EXT("ALC Enable", M98090_REG_DRC_TIMING,
-		M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
-	SOC_ENUM_EXT("ALC Attack Time", max98090_drcatk_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_ENUM_EXT("ALC Release Time", max98090_drcrls_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
+	SOC_SINGLE("ALC Enable", M98090_REG_DRC_TIMING,
+		M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0),
+	SOC_ENUM("ALC Attack Time", max98090_drcatk_enum),
+	SOC_ENUM("ALC Release Time", max98090_drcrls_enum),
 	SOC_SINGLE_TLV("ALC Make Up Volume", M98090_REG_DRC_GAIN,
 		M98090_DRCG_SHIFT, M98090_DRCG_NUM - 1, 0,
 		max98090_alcmakeup_tlv),
-	SOC_ENUM_EXT("ALC Compression Ratio", max98090_alccmp_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_ENUM_EXT("ALC Expansion Ratio", max98090_drcexp_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_SINGLE_EXT_TLV("ALC Compression Threshold Volume",
+	SOC_ENUM("ALC Compression Ratio", max98090_alccmp_enum),
+	SOC_ENUM("ALC Expansion Ratio", max98090_drcexp_enum),
+	SOC_SINGLE_TLV("ALC Compression Threshold Volume",
 		M98090_REG_DRC_COMPRESSOR, M98090_DRCTHC_SHIFT,
-		M98090_DRCTHC_NUM - 1, 1,
-		snd_soc_get_volsw, max98090_put_volsw, max98090_alccomp_tlv),
-	SOC_SINGLE_EXT_TLV("ALC Expansion Threshold Volume",
+		M98090_DRCTHC_NUM - 1, 1, max98090_alccomp_tlv),
+	SOC_SINGLE_TLV("ALC Expansion Threshold Volume",
 		M98090_REG_DRC_EXPANDER, M98090_DRCTHE_SHIFT,
-		M98090_DRCTHE_NUM - 1, 1,
-		snd_soc_get_volsw, max98090_put_volsw, max98090_drcexp_tlv),
+		M98090_DRCTHE_NUM - 1, 1, max98090_drcexp_tlv),
 
-	SOC_ENUM_EXT("DAC HP Playback Performance Mode",
-		max98090_dac_perfmode_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_ENUM_EXT("DAC High Performance Mode", max98090_dachp_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
+	SOC_ENUM("DAC HP Playback Performance Mode",
+		max98090_dac_perfmode_enum),
+	SOC_ENUM("DAC High Performance Mode", max98090_dachp_enum),
 
 	SOC_SINGLE_TLV("Headphone Left Mixer Volume",
 		M98090_REG_HP_CONTROL, M98090_MIXHPLG_SHIFT,
@@ -836,12 +684,9 @@
 	SOC_SINGLE("Volume Adjustment Smoothing", M98090_REG_LEVEL_CONTROL,
 		M98090_VSENN_SHIFT, M98090_VSENN_NUM - 1, 1),
 
-	SND_SOC_BYTES_E("Biquad Coefficients",
-		M98090_REG_RECORD_BIQUAD_BASE, 15,
-		snd_soc_bytes_get, max98090_bytes_put),
-	SOC_SINGLE_EXT("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
-		M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
+	SND_SOC_BYTES("Biquad Coefficients", M98090_REG_RECORD_BIQUAD_BASE, 15),
+	SOC_SINGLE("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
+		M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0),
 };
 
 static const struct snd_kcontrol_new max98091_snd_controls[] = {
@@ -850,12 +695,10 @@
 		M98090_DMIC34_ZEROPAD_SHIFT,
 		M98090_DMIC34_ZEROPAD_NUM - 1, 0),
 
-	SOC_ENUM_EXT("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum,
-		snd_soc_get_enum_double, max98090_put_enum_double),
-	SOC_SINGLE_EXT("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG,
+	SOC_ENUM("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum),
+	SOC_SINGLE("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG,
 		M98090_FLT_DMIC34HPF_SHIFT,
-		M98090_FLT_DMIC34HPF_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
+		M98090_FLT_DMIC34HPF_NUM - 1, 0),
 
 	SOC_SINGLE_TLV("DMIC3 Boost Volume", M98090_REG_DMIC3_VOLUME,
 		M98090_DMIC_AV3G_SHIFT, M98090_DMIC_AV3G_NUM - 1, 0,
@@ -873,9 +716,8 @@
 
 	SND_SOC_BYTES("DMIC34 Biquad Coefficients",
 		M98090_REG_DMIC34_BIQUAD_BASE, 15),
-	SOC_SINGLE_EXT("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
-		M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0,
-		snd_soc_get_volsw, max98090_put_volsw),
+	SOC_SINGLE("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE,
+		M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0),
 
 	SOC_SINGLE_TLV("DMIC34 BQ PreAttenuation Volume",
 		M98090_REG_DMIC34_BQ_PREATTEN, M98090_AV34BQ_SHIFT,
@@ -929,6 +771,19 @@
 	return 0;
 }
 
+static int max98090_shdn_event(struct snd_soc_dapm_widget *w,
+				 struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
+
+	if (event & SND_SOC_DAPM_POST_PMU)
+		max98090->shdn_pending = true;
+
+	return 0;
+
+}
+
 static const char *mic1_mux_text[] = { "IN12", "IN56" };
 
 static SOC_ENUM_SINGLE_DECL(mic1_mux_enum,
@@ -1029,14 +884,10 @@
 			    lten_mux_text);
 
 static const struct snd_kcontrol_new max98090_ltenl_mux =
-	SOC_DAPM_ENUM_EXT("LTENL Mux", ltenl_mux_enum,
-			  snd_soc_dapm_get_enum_double,
-			  max98090_dapm_put_enum_double);
+	SOC_DAPM_ENUM("LTENL Mux", ltenl_mux_enum);
 
 static const struct snd_kcontrol_new max98090_ltenr_mux =
-	SOC_DAPM_ENUM_EXT("LTENR Mux", ltenr_mux_enum,
-			  snd_soc_dapm_get_enum_double,
-			  max98090_dapm_put_enum_double);
+	SOC_DAPM_ENUM("LTENR Mux", ltenr_mux_enum);
 
 static const char *lben_mux_text[] = { "Normal", "Loopback" };
 
@@ -1051,14 +902,10 @@
 			    lben_mux_text);
 
 static const struct snd_kcontrol_new max98090_lbenl_mux =
-	SOC_DAPM_ENUM_EXT("LBENL Mux", lbenl_mux_enum,
-			  snd_soc_dapm_get_enum_double,
-			  max98090_dapm_put_enum_double);
+	SOC_DAPM_ENUM("LBENL Mux", lbenl_mux_enum);
 
 static const struct snd_kcontrol_new max98090_lbenr_mux =
-	SOC_DAPM_ENUM_EXT("LBENR Mux", lbenr_mux_enum,
-			  snd_soc_dapm_get_enum_double,
-			  max98090_dapm_put_enum_double);
+	SOC_DAPM_ENUM("LBENR Mux", lbenr_mux_enum);
 
 static const char *stenl_mux_text[] = { "Normal", "Sidetone Left" };
 
@@ -1225,25 +1072,21 @@
 	SND_SOC_DAPM_INPUT("IN56"),
 
 	SND_SOC_DAPM_SUPPLY("MICBIAS", M98090_REG_INPUT_ENABLE,
-		M98090_MBEN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		M98090_MBEN_SHIFT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("SHDN", M98090_REG_DEVICE_SHUTDOWN,
 		M98090_SHDNN_SHIFT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("SDIEN", M98090_REG_IO_CONFIGURATION,
-		M98090_SDIEN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		M98090_SDIEN_SHIFT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("SDOEN", M98090_REG_IO_CONFIGURATION,
-		M98090_SDOEN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		M98090_SDOEN_SHIFT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("DMICL_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
-		M98090_DIGMICL_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		 M98090_DIGMICL_SHIFT, 0, max98090_shdn_event,
+			SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_SUPPLY("DMICR_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
-		M98090_DIGMICR_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		 M98090_DIGMICR_SHIFT, 0, max98090_shdn_event,
+			 SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_SUPPLY("AHPF", M98090_REG_FILTER_CONFIG,
-		M98090_AHPF_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		M98090_AHPF_SHIFT, 0, NULL, 0),
 
 /*
  * Note: Sysclk and misc power supplies are taken care of by SHDN
@@ -1273,12 +1116,10 @@
 		&max98090_lineb_mixer_controls[0],
 		ARRAY_SIZE(max98090_lineb_mixer_controls)),
 
-	SND_SOC_DAPM_PGA_E("LINEA Input", M98090_REG_INPUT_ENABLE,
-		M98090_LINEAEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-	SND_SOC_DAPM_PGA_E("LINEB Input", M98090_REG_INPUT_ENABLE,
-		M98090_LINEBEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+	SND_SOC_DAPM_PGA("LINEA Input", M98090_REG_INPUT_ENABLE,
+		M98090_LINEAEN_SHIFT, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("LINEB Input", M98090_REG_INPUT_ENABLE,
+		M98090_LINEBEN_SHIFT, 0, NULL, 0),
 
 	SND_SOC_DAPM_MIXER("Left ADC Mixer", SND_SOC_NOPM, 0, 0,
 		&max98090_left_adc_mixer_controls[0],
@@ -1289,11 +1130,11 @@
 		ARRAY_SIZE(max98090_right_adc_mixer_controls)),
 
 	SND_SOC_DAPM_ADC_E("ADCL", NULL, M98090_REG_INPUT_ENABLE,
-		M98090_ADLEN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		M98090_ADLEN_SHIFT, 0, max98090_shdn_event,
+		SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_ADC_E("ADCR", NULL, M98090_REG_INPUT_ENABLE,
-		M98090_ADREN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		M98090_ADREN_SHIFT, 0, max98090_shdn_event,
+		SND_SOC_DAPM_POST_PMU),
 
 	SND_SOC_DAPM_AIF_OUT("AIFOUTL", "HiFi Capture", 0,
 		SND_SOC_NOPM, 0, 0),
@@ -1321,12 +1162,10 @@
 	SND_SOC_DAPM_AIF_IN("AIFINL", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("AIFINR", "HiFi Playback", 1, SND_SOC_NOPM, 0, 0),
 
-	SND_SOC_DAPM_DAC_E("DACL", NULL, M98090_REG_OUTPUT_ENABLE,
-		M98090_DALEN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-	SND_SOC_DAPM_DAC_E("DACR", NULL, M98090_REG_OUTPUT_ENABLE,
-		M98090_DAREN_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+	SND_SOC_DAPM_DAC("DACL", NULL, M98090_REG_OUTPUT_ENABLE,
+		M98090_DALEN_SHIFT, 0),
+	SND_SOC_DAPM_DAC("DACR", NULL, M98090_REG_OUTPUT_ENABLE,
+		M98090_DAREN_SHIFT, 0),
 
 	SND_SOC_DAPM_MIXER("Left Headphone Mixer", SND_SOC_NOPM, 0, 0,
 		&max98090_left_hp_mixer_controls[0],
@@ -1361,26 +1200,20 @@
 	SND_SOC_DAPM_MUX("MIXHPRSEL Mux", SND_SOC_NOPM, 0, 0,
 		&max98090_mixhprsel_mux),
 
-	SND_SOC_DAPM_PGA_E("HP Left Out", M98090_REG_OUTPUT_ENABLE,
-		M98090_HPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-	SND_SOC_DAPM_PGA_E("HP Right Out", M98090_REG_OUTPUT_ENABLE,
-		M98090_HPREN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+	SND_SOC_DAPM_PGA("HP Left Out", M98090_REG_OUTPUT_ENABLE,
+		M98090_HPLEN_SHIFT, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("HP Right Out", M98090_REG_OUTPUT_ENABLE,
+		M98090_HPREN_SHIFT, 0, NULL, 0),
 
-	SND_SOC_DAPM_PGA_E("SPK Left Out", M98090_REG_OUTPUT_ENABLE,
-		M98090_SPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-	SND_SOC_DAPM_PGA_E("SPK Right Out", M98090_REG_OUTPUT_ENABLE,
-		M98090_SPREN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+	SND_SOC_DAPM_PGA("SPK Left Out", M98090_REG_OUTPUT_ENABLE,
+		M98090_SPLEN_SHIFT, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("SPK Right Out", M98090_REG_OUTPUT_ENABLE,
+		M98090_SPREN_SHIFT, 0, NULL, 0),
 
-	SND_SOC_DAPM_PGA_E("RCV Left Out", M98090_REG_OUTPUT_ENABLE,
-		M98090_RCVLEN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
-	SND_SOC_DAPM_PGA_E("RCV Right Out", M98090_REG_OUTPUT_ENABLE,
-		M98090_RCVREN_SHIFT, 0, NULL, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+	SND_SOC_DAPM_PGA("RCV Left Out", M98090_REG_OUTPUT_ENABLE,
+		M98090_RCVLEN_SHIFT, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("RCV Right Out", M98090_REG_OUTPUT_ENABLE,
+		M98090_RCVREN_SHIFT, 0, NULL, 0),
 
 	SND_SOC_DAPM_OUTPUT("HPL"),
 	SND_SOC_DAPM_OUTPUT("HPR"),
@@ -1395,11 +1228,9 @@
 	SND_SOC_DAPM_INPUT("DMIC4"),
 
 	SND_SOC_DAPM_SUPPLY("DMIC3_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
-		M98090_DIGMIC3_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		 M98090_DIGMIC3_SHIFT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("DMIC4_ENA", M98090_REG_DIGITAL_MIC_ENABLE,
-		M98090_DIGMIC4_SHIFT, 0, max98090_dapm_event,
-		SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD),
+		 M98090_DIGMIC4_SHIFT, 0, NULL, 0),
 };
 
 static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
@@ -1670,11 +1501,6 @@
 		return;
 	}
 
-	/*
-	 * Master mode: no need to save and restore SHDN for the following
-	 * sensitive registers.
-	 */
-
 	/* Check for supported PCLK to LRCLK ratios */
 	for (i = 0; i < ARRAY_SIZE(pclk_rates); i++) {
 		if ((pclk_rates[i] == max98090->sysclk) &&
@@ -1761,14 +1587,12 @@
 		switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 		case SND_SOC_DAIFMT_CBS_CFS:
 			/* Set to slave mode PLL - MAS mode off */
-			max98090_shdn_save(max98090);
 			snd_soc_component_write(component,
 				M98090_REG_CLOCK_RATIO_NI_MSB, 0x00);
 			snd_soc_component_write(component,
 				M98090_REG_CLOCK_RATIO_NI_LSB, 0x00);
 			snd_soc_component_update_bits(component, M98090_REG_CLOCK_MODE,
 				M98090_USE_M1_MASK, 0);
-			max98090_shdn_restore(max98090);
 			max98090->master = false;
 			break;
 		case SND_SOC_DAIFMT_CBM_CFM:
@@ -1794,9 +1618,7 @@
 			dev_err(component->dev, "DAI clock mode unsupported");
 			return -EINVAL;
 		}
-		max98090_shdn_save(max98090);
 		snd_soc_component_write(component, M98090_REG_MASTER_MODE, regval);
-		max98090_shdn_restore(max98090);
 
 		regval = 0;
 		switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
@@ -1841,10 +1663,8 @@
 		if (max98090->tdm_slots > 1)
 			regval ^= M98090_BCI_MASK;
 
-		max98090_shdn_save(max98090);
 		snd_soc_component_write(component,
 			M98090_REG_INTERFACE_FORMAT, regval);
-		max98090_shdn_restore(max98090);
 	}
 
 	return 0;
@@ -1856,7 +1676,6 @@
 	struct snd_soc_component *component = codec_dai->component;
 	struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
 	struct max98090_cdata *cdata;
-
 	cdata = &max98090->dai[0];
 
 	if (slots < 0 || slots > 4)
@@ -1866,7 +1685,6 @@
 	max98090->tdm_width = slot_width;
 
 	if (max98090->tdm_slots > 1) {
-		max98090_shdn_save(max98090);
 		/* SLOTL SLOTR SLOTDLY */
 		snd_soc_component_write(component, M98090_REG_TDM_FORMAT,
 			0 << M98090_TDM_SLOTL_SHIFT |
@@ -1877,7 +1695,6 @@
 		snd_soc_component_update_bits(component, M98090_REG_TDM_CONTROL,
 			M98090_TDM_MASK,
 			M98090_TDM_MASK);
-		max98090_shdn_restore(max98090);
 	}
 
 	/*
@@ -2077,7 +1894,6 @@
 	dmic_freq = dmic_table[pclk_index].settings[micclk_index].freq;
 	dmic_comp = dmic_table[pclk_index].settings[micclk_index].comp[i];
 
-	max98090_shdn_save(max98090);
 	regmap_update_bits(max98090->regmap, M98090_REG_DIGITAL_MIC_ENABLE,
 			   M98090_MICCLK_MASK,
 			   micclk_index << M98090_MICCLK_SHIFT);
@@ -2086,7 +1902,6 @@
 			   M98090_DMIC_COMP_MASK | M98090_DMIC_FREQ_MASK,
 			   dmic_comp << M98090_DMIC_COMP_SHIFT |
 			   dmic_freq << M98090_DMIC_FREQ_SHIFT);
-	max98090_shdn_restore(max98090);
 
 	return 0;
 }
@@ -2123,10 +1938,8 @@
 
 	switch (params_width(params)) {
 	case 16:
-		max98090_shdn_save(max98090);
 		snd_soc_component_update_bits(component, M98090_REG_INTERFACE_FORMAT,
 			M98090_WS_MASK, 0);
-		max98090_shdn_restore(max98090);
 		break;
 	default:
 		return -EINVAL;
@@ -2137,7 +1950,6 @@
 
 	cdata->rate = max98090->lrclk;
 
-	max98090_shdn_save(max98090);
 	/* Update filter mode */
 	if (max98090->lrclk < 24000)
 		snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG,
@@ -2153,7 +1965,6 @@
 	else
 		snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG,
 			M98090_DHF_MASK, M98090_DHF_MASK);
-	max98090_shdn_restore(max98090);
 
 	max98090_configure_dmic(max98090, max98090->dmic_freq, max98090->pclk,
 				max98090->lrclk);
@@ -2184,7 +1995,6 @@
 	 *		 0x02 (when master clk is 20MHz to 40MHz)..
 	 *		 0x03 (when master clk is 40MHz to 60MHz)..
 	 */
-	max98090_shdn_save(max98090);
 	if ((freq >= 10000000) && (freq <= 20000000)) {
 		snd_soc_component_write(component, M98090_REG_SYSTEM_CLOCK,
 			M98090_PSCLK_DIV1);
@@ -2199,10 +2009,8 @@
 		max98090->pclk = freq >> 2;
 	} else {
 		dev_err(component->dev, "Invalid master clock frequency\n");
-		max98090_shdn_restore(max98090);
 		return -EINVAL;
 	}
-	max98090_shdn_restore(max98090);
 
 	max98090->sysclk = freq;
 
@@ -2314,12 +2122,10 @@
 	 */
 
 	/* Toggle shutdown OFF then ON */
-	mutex_lock(&component->card->dapm_mutex);
 	snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
 			    M98090_SHDNN_MASK, 0);
 	snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
 			    M98090_SHDNN_MASK, M98090_SHDNN_MASK);
-	mutex_unlock(&component->card->dapm_mutex);
 
 	for (i = 0; i < 10; ++i) {
 		/* Give PLL time to lock */
@@ -2642,12 +2448,7 @@
 	 */
 	snd_soc_component_read32(component, M98090_REG_DEVICE_STATUS);
 
-	/*
-	 * SHDN should be 0 at the point, no need to save/restore for the
-	 * following registers.
-	 *
-	 * High Performance is default
-	 */
+	/* High Performance is default */
 	snd_soc_component_update_bits(component, M98090_REG_DAC_CONTROL,
 		M98090_DACHP_MASK,
 		1 << M98090_DACHP_SHIFT);
@@ -2658,12 +2459,7 @@
 		M98090_ADCHP_MASK,
 		1 << M98090_ADCHP_SHIFT);
 
-	/*
-	 * SHDN should be 0 at the point, no need to save/restore for the
-	 * following registers.
-	 *
-	 * Turn on VCM bandgap reference
-	 */
+	/* Turn on VCM bandgap reference */
 	snd_soc_component_write(component, M98090_REG_BIAS_CONTROL,
 		M98090_VCM_MODE_MASK);
 
@@ -2695,9 +2491,25 @@
 	max98090->component = NULL;
 }
 
+static void max98090_seq_notifier(struct snd_soc_component *component,
+	enum snd_soc_dapm_type event, int subseq)
+{
+	struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
+
+	if (max98090->shdn_pending) {
+		snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
+				M98090_SHDNN_MASK, 0);
+		msleep(40);
+		snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN,
+				M98090_SHDNN_MASK, M98090_SHDNN_MASK);
+		max98090->shdn_pending = false;
+	}
+}
+
 static const struct snd_soc_component_driver soc_component_dev_max98090 = {
 	.probe			= max98090_probe,
 	.remove			= max98090_remove,
+	.seq_notifier		= max98090_seq_notifier,
 	.set_bias_level		= max98090_set_bias_level,
 	.idle_bias_on		= 1,
 	.use_pmdown_time	= 1,
diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h
index 0a31708..a197114 100644
--- a/sound/soc/codecs/max98090.h
+++ b/sound/soc/codecs/max98090.h
@@ -1539,8 +1539,7 @@
 	unsigned int pa2en;
 	unsigned int sidetone;
 	bool master;
-	int saved_count;
-	int saved_shdn;
+	bool shdn_pending;
 };
 
 int max98090_mic_detect(struct snd_soc_component *component,
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 8c3ea73..9d436b0 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -1020,12 +1020,24 @@
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
 			&fsl_sai_dai, 1);
 	if (ret)
-		return ret;
+		goto err_pm_disable;
 
-	if (sai->soc_data->use_imx_pcm)
-		return imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
-	else
-		return devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	if (sai->soc_data->use_imx_pcm) {
+		ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
+		if (ret)
+			goto err_pm_disable;
+	} else {
+		ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+		if (ret)
+			goto err_pm_disable;
+	}
+
+	return ret;
+
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
 }
 
 static int fsl_sai_remove(struct platform_device *pdev)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index bc20ad9..9b13056 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3441,8 +3441,17 @@
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_get_enum_double);
 
-static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol, int locked)
+/**
+ * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback
+ * @kcontrol: mixer control
+ * @ucontrol: control element information
+ *
+ * Callback to set the value of a dapm enumerated double mixer control.
+ *
+ * Returns 0 for success.
+ */
+int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
 	struct snd_soc_card *card = dapm->card;
@@ -3465,9 +3474,7 @@
 		mask |= e->mask << e->shift_r;
 	}
 
-	if (!locked)
-		mutex_lock_nested(&card->dapm_mutex,
-				  SND_SOC_DAPM_CLASS_RUNTIME);
+	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 
 	change = dapm_kcontrol_set_value(kcontrol, val);
 
@@ -3489,51 +3496,16 @@
 		card->update = NULL;
 	}
 
-	if (!locked)
-		mutex_unlock(&card->dapm_mutex);
+	mutex_unlock(&card->dapm_mutex);
 
 	if (ret > 0)
 		soc_dpcm_runtime_update(card);
 
 	return change;
 }
-
-/**
- * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback
- * @kcontrol: mixer control
- * @ucontrol: control element information
- *
- * Callback to set the value of a dapm enumerated double mixer control.
- *
- * Returns 0 for success.
- */
-int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 0);
-}
 EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double);
 
 /**
- * snd_soc_dapm_put_enum_double_locked - dapm enumerated double mixer set
- * callback
- * @kcontrol: mixer control
- * @ucontrol: control element information
- *
- * Callback to set the value of a dapm enumerated double mixer control.
- * Must acquire dapm_mutex before calling the function.
- *
- * Returns 0 for success.
- */
-int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	dapm_assert_locked(snd_soc_dapm_kcontrol_dapm(kcontrol));
-	return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 1);
-}
-EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double_locked);
-
-/**
  * snd_soc_dapm_info_pin_switch - Info for a pin switch
  *
  * @kcontrol: mixer control
@@ -3916,9 +3888,6 @@
 	runtime->rate = params_rate(params);
 
 out:
-	if (ret < 0)
-		kfree(runtime);
-
 	kfree(params);
 	return ret;
 }
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 9106ab8..ff45075 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -174,8 +174,10 @@
 {
 	struct hdac_bus *bus = sof_to_bus(sdev);
 
-	dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable);
-	snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable);
+	if (HDA_IDISP_CODEC(bus->codec_mask)) {
+		dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable);
+		snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable);
+	}
 }
 EXPORT_SYMBOL_NS(hda_codec_i915_display_power, SND_SOC_SOF_HDA_AUDIO_CODEC_I915);
 
@@ -189,7 +191,8 @@
 	if (ret < 0)
 		return ret;
 
-	hda_codec_i915_display_power(sdev, true);
+	/* codec_mask not yet known, power up for probe */
+	snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, true);
 
 	return 0;
 }
@@ -200,7 +203,8 @@
 	struct hdac_bus *bus = sof_to_bus(sdev);
 	int ret;
 
-	hda_codec_i915_display_power(sdev, false);
+	/* power down unconditionally */
+	snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false);
 
 	ret = snd_hdac_i915_exit(bus);
 
diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index 4a4d318..0848b79 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -428,6 +428,9 @@
 		return ret;
 	}
 
+	/* display codec can powered off after link reset */
+	hda_codec_i915_display_power(sdev, false);
+
 	return 0;
 }
 
@@ -439,6 +442,9 @@
 #endif
 	int ret;
 
+	/* display codec must be powered before link reset */
+	hda_codec_i915_display_power(sdev, true);
+
 	/*
 	 * clear TCSEL to clear playback on some HD Audio
 	 * codecs. PCI TCSEL is defined in the Intel manuals.
@@ -482,6 +488,8 @@
 	struct pci_dev *pci = to_pci_dev(sdev->dev);
 
 	if (sdev->s0_suspend) {
+		hda_codec_i915_display_power(sdev, true);
+
 		/* restore L1SEN bit */
 		if (hda->l1_support_changed)
 			snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
@@ -531,6 +539,9 @@
 	int ret;
 
 	if (sdev->s0_suspend) {
+		/* we can't keep a wakeref to display driver at suspend */
+		hda_codec_i915_display_power(sdev, false);
+
 		/* enable L1SEN to make sure the system can enter S0Ix */
 		hda->l1_support_changed =
 			snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 65b86dd..25946a1 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -286,6 +286,13 @@
 	/* HDA base */
 	sdev->bar[HDA_DSP_HDA_BAR] = bus->remap_addr;
 
+	/* init i915 and HDMI codecs */
+	ret = hda_codec_i915_init(sdev);
+	if (ret < 0) {
+		dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n");
+		return ret;
+	}
+
 	/* get controller capabilities */
 	ret = hda_dsp_ctrl_get_caps(sdev);
 	if (ret < 0)
@@ -353,15 +360,6 @@
 	if (bus->ppcap)
 		dev_dbg(sdev->dev, "PP capability, will probe DSP later.\n");
 
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
-	/* init i915 and HDMI codecs */
-	ret = hda_codec_i915_init(sdev);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n");
-		return ret;
-	}
-#endif
-
 	/* Init HDA controller after i915 init */
 	ret = hda_dsp_ctrl_init_chip(sdev, true);
 	if (ret < 0) {
@@ -381,7 +379,7 @@
 	hda_codec_probe_bus(sdev, hda_codec_use_common_hdmi);
 
 	if (!HDA_IDISP_CODEC(bus->codec_mask))
-		hda_codec_i915_display_power(sdev, false);
+		hda_codec_i915_exit(sdev);
 
 	/*
 	 * we are done probing so decrement link counts
@@ -611,6 +609,7 @@
 	iounmap(sdev->bar[HDA_DSP_BAR]);
 hdac_bus_unmap:
 	iounmap(bus->remap_addr);
+	hda_codec_i915_exit(sdev);
 err:
 	return ret;
 }
diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c
index 55798bc..686561d 100644
--- a/sound/soc/sunxi/sun8i-codec.c
+++ b/sound/soc/sunxi/sun8i-codec.c
@@ -80,6 +80,7 @@
 
 #define SUN8I_SYS_SR_CTRL_AIF1_FS_MASK		GENMASK(15, 12)
 #define SUN8I_SYS_SR_CTRL_AIF2_FS_MASK		GENMASK(11, 8)
+#define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK	GENMASK(3, 2)
 #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_MASK	GENMASK(5, 4)
 #define SUN8I_AIF1CLK_CTRL_AIF1_LRCK_DIV_MASK	GENMASK(8, 6)
 #define SUN8I_AIF1CLK_CTRL_AIF1_BCLK_DIV_MASK	GENMASK(12, 9)
@@ -241,7 +242,7 @@
 		return -EINVAL;
 	}
 	regmap_update_bits(scodec->regmap, SUN8I_AIF1CLK_CTRL,
-			   BIT(SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT),
+			   SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK,
 			   value << SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT);
 
 	return 0;
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 018b1ec..a48313d 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -151,8 +151,34 @@
 	return ret;
 }
 
+/*
+ * Assume the clock is valid if clock source supports only one single sample
+ * rate, the terminal is connected directly to it (there is no clock selector)
+ * and clock type is internal. This is to deal with some Denon DJ controllers
+ * that always reports that clock is invalid.
+ */
+static bool uac_clock_source_is_valid_quirk(struct snd_usb_audio *chip,
+					    struct audioformat *fmt,
+					    int source_id)
+{
+	if (fmt->protocol == UAC_VERSION_2) {
+		struct uac_clock_source_descriptor *cs_desc =
+			snd_usb_find_clock_source(chip->ctrl_intf, source_id);
+
+		if (!cs_desc)
+			return false;
+
+		return (fmt->nr_rates == 1 &&
+			(fmt->clock & 0xff) == cs_desc->bClockID &&
+			(cs_desc->bmAttributes & 0x3) !=
+				UAC_CLOCK_SOURCE_TYPE_EXT);
+	}
+
+	return false;
+}
+
 static bool uac_clock_source_is_valid(struct snd_usb_audio *chip,
-				      int protocol,
+				      struct audioformat *fmt,
 				      int source_id)
 {
 	int err;
@@ -160,7 +186,7 @@
 	struct usb_device *dev = chip->dev;
 	u32 bmControls;
 
-	if (protocol == UAC_VERSION_3) {
+	if (fmt->protocol == UAC_VERSION_3) {
 		struct uac3_clock_source_descriptor *cs_desc =
 			snd_usb_find_clock_source_v3(chip->ctrl_intf, source_id);
 
@@ -194,10 +220,14 @@
 		return false;
 	}
 
-	return data ? true :  false;
+	if (data)
+		return true;
+	else
+		return uac_clock_source_is_valid_quirk(chip, fmt, source_id);
 }
 
-static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
+static int __uac_clock_find_source(struct snd_usb_audio *chip,
+				   struct audioformat *fmt, int entity_id,
 				   unsigned long *visited, bool validate)
 {
 	struct uac_clock_source_descriptor *source;
@@ -217,7 +247,7 @@
 	source = snd_usb_find_clock_source(chip->ctrl_intf, entity_id);
 	if (source) {
 		entity_id = source->bClockID;
-		if (validate && !uac_clock_source_is_valid(chip, UAC_VERSION_2,
+		if (validate && !uac_clock_source_is_valid(chip, fmt,
 								entity_id)) {
 			usb_audio_err(chip,
 				"clock source %d is not valid, cannot use\n",
@@ -248,8 +278,9 @@
 		}
 
 		cur = ret;
-		ret = __uac_clock_find_source(chip, selector->baCSourceID[ret - 1],
-					       visited, validate);
+		ret = __uac_clock_find_source(chip, fmt,
+					      selector->baCSourceID[ret - 1],
+					      visited, validate);
 		if (!validate || ret > 0 || !chip->autoclock)
 			return ret;
 
@@ -260,8 +291,9 @@
 			if (i == cur)
 				continue;
 
-			ret = __uac_clock_find_source(chip, selector->baCSourceID[i - 1],
-				visited, true);
+			ret = __uac_clock_find_source(chip, fmt,
+						      selector->baCSourceID[i - 1],
+						      visited, true);
 			if (ret < 0)
 				continue;
 
@@ -281,14 +313,16 @@
 	/* FIXME: multipliers only act as pass-thru element for now */
 	multiplier = snd_usb_find_clock_multiplier(chip->ctrl_intf, entity_id);
 	if (multiplier)
-		return __uac_clock_find_source(chip, multiplier->bCSourceID,
-						visited, validate);
+		return __uac_clock_find_source(chip, fmt,
+					       multiplier->bCSourceID,
+					       visited, validate);
 
 	return -EINVAL;
 }
 
-static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
-				   unsigned long *visited, bool validate)
+static int __uac3_clock_find_source(struct snd_usb_audio *chip,
+				    struct audioformat *fmt, int entity_id,
+				    unsigned long *visited, bool validate)
 {
 	struct uac3_clock_source_descriptor *source;
 	struct uac3_clock_selector_descriptor *selector;
@@ -307,7 +341,7 @@
 	source = snd_usb_find_clock_source_v3(chip->ctrl_intf, entity_id);
 	if (source) {
 		entity_id = source->bClockID;
-		if (validate && !uac_clock_source_is_valid(chip, UAC_VERSION_3,
+		if (validate && !uac_clock_source_is_valid(chip, fmt,
 								entity_id)) {
 			usb_audio_err(chip,
 				"clock source %d is not valid, cannot use\n",
@@ -338,7 +372,8 @@
 		}
 
 		cur = ret;
-		ret = __uac3_clock_find_source(chip, selector->baCSourceID[ret - 1],
+		ret = __uac3_clock_find_source(chip, fmt,
+					       selector->baCSourceID[ret - 1],
 					       visited, validate);
 		if (!validate || ret > 0 || !chip->autoclock)
 			return ret;
@@ -350,8 +385,9 @@
 			if (i == cur)
 				continue;
 
-			ret = __uac3_clock_find_source(chip, selector->baCSourceID[i - 1],
-				visited, true);
+			ret = __uac3_clock_find_source(chip, fmt,
+						       selector->baCSourceID[i - 1],
+						       visited, true);
 			if (ret < 0)
 				continue;
 
@@ -372,7 +408,8 @@
 	multiplier = snd_usb_find_clock_multiplier_v3(chip->ctrl_intf,
 						      entity_id);
 	if (multiplier)
-		return __uac3_clock_find_source(chip, multiplier->bCSourceID,
+		return __uac3_clock_find_source(chip, fmt,
+						multiplier->bCSourceID,
 						visited, validate);
 
 	return -EINVAL;
@@ -389,18 +426,18 @@
  *
  * Returns the clock source UnitID (>=0) on success, or an error.
  */
-int snd_usb_clock_find_source(struct snd_usb_audio *chip, int protocol,
-			      int entity_id, bool validate)
+int snd_usb_clock_find_source(struct snd_usb_audio *chip,
+			      struct audioformat *fmt, bool validate)
 {
 	DECLARE_BITMAP(visited, 256);
 	memset(visited, 0, sizeof(visited));
 
-	switch (protocol) {
+	switch (fmt->protocol) {
 	case UAC_VERSION_2:
-		return __uac_clock_find_source(chip, entity_id, visited,
+		return __uac_clock_find_source(chip, fmt, fmt->clock, visited,
 					       validate);
 	case UAC_VERSION_3:
-		return __uac3_clock_find_source(chip, entity_id, visited,
+		return __uac3_clock_find_source(chip, fmt, fmt->clock, visited,
 					       validate);
 	default:
 		return -EINVAL;
@@ -501,8 +538,7 @@
 	 * automatic clock selection if the current clock is not
 	 * valid.
 	 */
-	clock = snd_usb_clock_find_source(chip, fmt->protocol,
-					  fmt->clock, true);
+	clock = snd_usb_clock_find_source(chip, fmt, true);
 	if (clock < 0) {
 		/* We did not find a valid clock, but that might be
 		 * because the current sample rate does not match an
@@ -510,8 +546,7 @@
 		 * and we will do another validation after setting the
 		 * rate.
 		 */
-		clock = snd_usb_clock_find_source(chip, fmt->protocol,
-						  fmt->clock, false);
+		clock = snd_usb_clock_find_source(chip, fmt, false);
 		if (clock < 0)
 			return clock;
 	}
@@ -577,7 +612,7 @@
 
 validation:
 	/* validate clock after rate change */
-	if (!uac_clock_source_is_valid(chip, fmt->protocol, clock))
+	if (!uac_clock_source_is_valid(chip, fmt, clock))
 		return -ENXIO;
 	return 0;
 }
diff --git a/sound/usb/clock.h b/sound/usb/clock.h
index 076e31b..68df0fb 100644
--- a/sound/usb/clock.h
+++ b/sound/usb/clock.h
@@ -6,7 +6,7 @@
 			     struct usb_host_interface *alts,
 			     struct audioformat *fmt, int rate);
 
-int snd_usb_clock_find_source(struct snd_usb_audio *chip, int protocol,
-			     int entity_id, bool validate);
+int snd_usb_clock_find_source(struct snd_usb_audio *chip,
+			      struct audioformat *fmt, bool validate);
 
 #endif /* __USBAUDIO_CLOCK_H */
diff --git a/sound/usb/format.c b/sound/usb/format.c
index 9260136..9f5cb4e 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -151,6 +151,19 @@
 	return pcm_formats;
 }
 
+static int set_fixed_rate(struct audioformat *fp, int rate, int rate_bits)
+{
+	kfree(fp->rate_table);
+	fp->rate_table = kmalloc(sizeof(int), GFP_KERNEL);
+	if (!fp->rate_table)
+		return -ENOMEM;
+	fp->nr_rates = 1;
+	fp->rate_min = rate;
+	fp->rate_max = rate;
+	fp->rates = rate_bits;
+	fp->rate_table[0] = rate;
+	return 0;
+}
 
 /*
  * parse the format descriptor and stores the possible sample rates
@@ -223,6 +236,14 @@
 		fp->rate_min = combine_triple(&fmt[offset + 1]);
 		fp->rate_max = combine_triple(&fmt[offset + 4]);
 	}
+
+	/* Jabra Evolve 65 headset */
+	if (chip->usb_id == USB_ID(0x0b0e, 0x030b)) {
+		/* only 48kHz for playback while keeping 16kHz for capture */
+		if (fp->nr_rates != 1)
+			return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000);
+	}
+
 	return 0;
 }
 
@@ -299,17 +320,7 @@
 	case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */
 	case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */
 	case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */
-		/* supported rates: 48Khz */
-		kfree(fp->rate_table);
-		fp->rate_table = kmalloc(sizeof(int), GFP_KERNEL);
-		if (!fp->rate_table)
-			return -ENOMEM;
-		fp->nr_rates = 1;
-		fp->rate_min = 48000;
-		fp->rate_max = 48000;
-		fp->rates = SNDRV_PCM_RATE_48000;
-		fp->rate_table[0] = 48000;
-		return 0;
+		return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000);
 	}
 
 	return -ENODEV;
@@ -325,8 +336,7 @@
 	struct usb_device *dev = chip->dev;
 	unsigned char tmp[2], *data;
 	int nr_triplets, data_size, ret = 0, ret_l6;
-	int clock = snd_usb_clock_find_source(chip, fp->protocol,
-					      fp->clock, false);
+	int clock = snd_usb_clock_find_source(chip, fp, false);
 
 	if (clock < 0) {
 		dev_err(&dev->dev,
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index d659fdb..81b2db0 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -897,6 +897,15 @@
 	return 0;
 }
 
+static int parse_term_effect_unit(struct mixer_build *state,
+				  struct usb_audio_term *term,
+				  void *p1, int id)
+{
+	term->type = UAC3_EFFECT_UNIT << 16; /* virtual type */
+	term->id = id;
+	return 0;
+}
+
 static int parse_term_uac2_clock_source(struct mixer_build *state,
 					struct usb_audio_term *term,
 					void *p1, int id)
@@ -981,8 +990,7 @@
 						    UAC3_PROCESSING_UNIT);
 		case PTYPE(UAC_VERSION_2, UAC2_EFFECT_UNIT):
 		case PTYPE(UAC_VERSION_3, UAC3_EFFECT_UNIT):
-			return parse_term_proc_unit(state, term, p1, id,
-						    UAC3_EFFECT_UNIT);
+			return parse_term_effect_unit(state, term, p1, id);
 		case PTYPE(UAC_VERSION_1, UAC1_EXTENSION_UNIT):
 		case PTYPE(UAC_VERSION_2, UAC2_EXTENSION_UNIT_V2):
 		case PTYPE(UAC_VERSION_3, UAC3_EXTENSION_UNIT):
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 3a5242e3..7f558f4 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1440,6 +1440,7 @@
 	case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */
 	case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
 	case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */
+	case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */
 		return true;
 	}
 
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 820e575..ba85bb2 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -220,10 +220,18 @@
 #define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
 #define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
 
-/* EL0 Virtual Timer Registers */
+/*
+ * EL0 Virtual Timer Registers
+ *
+ * WARNING:
+ *      KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined
+ *      with the appropriate register encodings.  Their values have been
+ *      accidentally swapped.  As this is set API, the definitions here
+ *      must be used, rather than ones derived from the encodings.
+ */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 
 /* KVM-as-firmware specific pseudo-registers */
 #define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 4703d21..f83a70e 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
 
 #include <asm-generic/unistd.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index e9b6249..f3327cb 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -220,6 +220,7 @@
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
+#define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -357,6 +358,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM		(18*32+ 4) /* Fast Short Rep Mov */
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 8e1d0bb..4ea8584 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
  * cpu_feature_enabled().
  */
 
-#ifdef CONFIG_X86_INTEL_MPX
-# define DISABLE_MPX	0
-#else
-# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
-#endif
-
 #ifdef CONFIG_X86_SMAP
 # define DISABLE_SMAP	0
 #else
@@ -74,7 +68,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
+#define DISABLED_MASK9	(DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h
new file mode 100644
index 0000000..7862f21
--- /dev/null
+++ b/tools/bootconfig/include/linux/memblock.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XBC_LINUX_MEMBLOCK_H
+#define _XBC_LINUX_MEMBLOCK_H
+
+#include <stdlib.h>
+
+#define __pa(addr)	(addr)
+#define SMP_CACHE_BYTES	0
+#define memblock_alloc(size, align)	malloc(size)
+#define memblock_free(paddr, size)	free(paddr)
+
+#endif
diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h
index 017bcd69..e978a63 100644
--- a/tools/bootconfig/include/linux/printk.h
+++ b/tools/bootconfig/include/linux/printk.h
@@ -7,7 +7,7 @@
 /* controllable printf */
 extern int pr_output;
 #define printk(fmt, ...)	\
-	(pr_output ? printf(fmt, __VA_ARGS__) : 0)
+	(pr_output ? printf(fmt, ##__VA_ARGS__) : 0)
 
 #define pr_err printk
 #define pr_warn	printk
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 47f4884..e18eeb0 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -140,7 +140,7 @@
 		return 0;
 
 	if (lseek(fd, -8, SEEK_END) < 0) {
-		printf("Failed to lseek: %d\n", -errno);
+		pr_err("Failed to lseek: %d\n", -errno);
 		return -errno;
 	}
 
@@ -155,7 +155,7 @@
 		return 0;
 
 	if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) {
-		printf("Failed to lseek: %d\n", -errno);
+		pr_err("Failed to lseek: %d\n", -errno);
 		return -errno;
 	}
 
@@ -166,7 +166,7 @@
 	/* Wrong Checksum, maybe no boot config here */
 	rcsum = checksum((unsigned char *)*buf, size);
 	if (csum != rcsum) {
-		printf("checksum error: %d != %d\n", csum, rcsum);
+		pr_err("checksum error: %d != %d\n", csum, rcsum);
 		return 0;
 	}
 
@@ -185,13 +185,13 @@
 
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
-		printf("Failed to open initrd %s: %d\n", path, fd);
+		pr_err("Failed to open initrd %s: %d\n", path, fd);
 		return -errno;
 	}
 
 	ret = load_xbc_from_initrd(fd, &buf);
 	if (ret < 0)
-		printf("Failed to load a boot config from initrd: %d\n", ret);
+		pr_err("Failed to load a boot config from initrd: %d\n", ret);
 	else
 		xbc_show_compact_tree();
 
@@ -209,7 +209,7 @@
 
 	fd = open(path, O_RDWR);
 	if (fd < 0) {
-		printf("Failed to open initrd %s: %d\n", path, fd);
+		pr_err("Failed to open initrd %s: %d\n", path, fd);
 		return -errno;
 	}
 
@@ -222,7 +222,7 @@
 	pr_output = 1;
 	if (size < 0) {
 		ret = size;
-		printf("Failed to load a boot config from initrd: %d\n", ret);
+		pr_err("Failed to load a boot config from initrd: %d\n", ret);
 	} else if (size > 0) {
 		ret = fstat(fd, &stat);
 		if (!ret)
@@ -245,7 +245,7 @@
 
 	ret = load_xbc_file(xbc_path, &buf);
 	if (ret < 0) {
-		printf("Failed to load %s : %d\n", xbc_path, ret);
+		pr_err("Failed to load %s : %d\n", xbc_path, ret);
 		return ret;
 	}
 	size = strlen(buf) + 1;
@@ -262,7 +262,7 @@
 	/* Check the data format */
 	ret = xbc_init(buf);
 	if (ret < 0) {
-		printf("Failed to parse %s: %d\n", xbc_path, ret);
+		pr_err("Failed to parse %s: %d\n", xbc_path, ret);
 		free(data);
 		free(buf);
 		return ret;
@@ -279,20 +279,20 @@
 	/* Remove old boot config if exists */
 	ret = delete_xbc(path);
 	if (ret < 0) {
-		printf("Failed to delete previous boot config: %d\n", ret);
+		pr_err("Failed to delete previous boot config: %d\n", ret);
 		return ret;
 	}
 
 	/* Apply new one */
 	fd = open(path, O_RDWR | O_APPEND);
 	if (fd < 0) {
-		printf("Failed to open %s: %d\n", path, fd);
+		pr_err("Failed to open %s: %d\n", path, fd);
 		return fd;
 	}
 	/* TODO: Ensure the @path is initramfs/initrd image */
 	ret = write(fd, data, size + 8);
 	if (ret < 0) {
-		printf("Failed to apply a boot config: %d\n", ret);
+		pr_err("Failed to apply a boot config: %d\n", ret);
 		return ret;
 	}
 	close(fd);
@@ -334,12 +334,12 @@
 	}
 
 	if (apply && delete) {
-		printf("Error: You can not specify both -a and -d at once.\n");
+		pr_err("Error: You can not specify both -a and -d at once.\n");
 		return usage();
 	}
 
 	if (optind >= argc) {
-		printf("Error: No initrd is specified.\n");
+		pr_err("Error: No initrd is specified.\n");
 		return usage();
 	}
 
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index 87725e8..1de06de 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -64,6 +64,15 @@
 new_size=$(stat -c %s $INITRD)
 xpass test $new_size -eq $initrd_size
 
+echo "No error messge while applying"
+OUTFILE=`mktemp tempout-XXXX`
+dd if=/dev/zero of=$INITRD bs=4096 count=1
+printf " \0\0\0 \0\0\0" >> $INITRD
+$BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1
+xfail grep -i "failed" $OUTFILE
+xfail grep -i "error" $OUTFILE
+rm $OUTFILE
+
 echo "Max node number check"
 
 echo -n > $TEMPCONF
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index c160a53..f94f65d 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -11,6 +11,8 @@
 #define PROT_WRITE	0x2		/* page can be written */
 #define PROT_EXEC	0x4		/* page can be executed */
 #define PROT_SEM	0x8		/* page may be used for atomic ops */
+/*			0x10		   reserved for arch-specific use */
+/*			0x20		   reserved for arch-specific use */
 #define PROT_NONE	0x0		/* page can not be accessed */
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 1fc8faa..3a3201e 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -851,8 +851,13 @@
 __SYSCALL(__NR_clone3, sys_clone3)
 #endif
 
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+
 #undef __NR_syscalls
-#define __NR_syscalls 436
+#define __NR_syscalls 439
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 5400d7e..829c0a4 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -395,6 +395,7 @@
 #define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
 #define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
 #define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
 #define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
 #define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
 #define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
@@ -793,6 +794,37 @@
 	__u64 offset;
 };
 
+struct drm_i915_gem_mmap_offset {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/**
+	 * Fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+
+	/**
+	 * Flags for extended behaviour.
+	 *
+	 * It is mandatory that one of the MMAP_OFFSET types
+	 * (GTT, WC, WB, UC, etc) should be included.
+	 */
+	__u64 flags;
+#define I915_MMAP_OFFSET_GTT 0
+#define I915_MMAP_OFFSET_WC  1
+#define I915_MMAP_OFFSET_WB  2
+#define I915_MMAP_OFFSET_UC  3
+
+	/*
+	 * Zero-terminated chain of extensions.
+	 *
+	 * No current extensions defined; mbz.
+	 */
+	__u64 extensions;
+};
+
 struct drm_i915_gem_set_domain {
 	/** Handle for the object */
 	__u32 handle;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f1d74a2..22f2352 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1045,9 +1045,9 @@
  * 		supports redirection to the egress interface, and accepts no
  * 		flag at all.
  *
- * 		The same effect can be attained with the more generic
- * 		**bpf_redirect_map**\ (), which requires specific maps to be
- * 		used but offers better performance.
+ * 		The same effect can also be attained with the more generic
+ * 		**bpf_redirect_map**\ (), which uses a BPF map to store the
+ * 		redirect target instead of providing it directly to the helper.
  * 	Return
  * 		For XDP, the helper returns **XDP_REDIRECT** on success or
  * 		**XDP_ABORTED** on error. For other program types, the values
@@ -1611,13 +1611,11 @@
  * 		the caller. Any higher bits in the *flags* argument must be
  * 		unset.
  *
- * 		When used to redirect packets to net devices, this helper
- * 		provides a high performance increase over **bpf_redirect**\ ().
- * 		This is due to various implementation details of the underlying
- * 		mechanisms, one of which is the fact that **bpf_redirect_map**\
- * 		() tries to send packet as a "bulk" to the device.
+ * 		See also bpf_redirect(), which only supports redirecting to an
+ * 		ifindex, but doesn't require a map to do so.
  * 	Return
- * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * 		**XDP_REDIRECT** on success, or the value of the two lower bits
+ * 		of the **flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 1f97b33..ca88b7b 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -3,6 +3,7 @@
 #define _UAPI_LINUX_FCNTL_H
 
 #include <asm/fcntl.h>
+#include <linux/openat2.h>
 
 #define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
 #define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
@@ -100,5 +101,4 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
-
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 1beb174..0d8a6f4 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -8,6 +8,7 @@
 #ifndef _UAPI_LINUX_FSCRYPT_H
 #define _UAPI_LINUX_FSCRYPT_H
 
+#include <linux/ioctl.h>
 #include <linux/types.h>
 
 /* Encryption policy flags */
@@ -109,11 +110,22 @@
 	} u;
 };
 
+/*
+ * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by
+ * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw.
+ */
+struct fscrypt_provisioning_key_payload {
+	__u32 type;
+	__u32 __reserved;
+	__u8 raw[];
+};
+
 /* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
 struct fscrypt_add_key_arg {
 	struct fscrypt_key_specifier key_spec;
 	__u32 raw_size;
-	__u32 __reserved[9];
+	__u32 key_id;
+	__u32 __reserved[8];
 	__u8 raw[];
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f0a16b4..4b95f9a 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1009,6 +1009,7 @@
 #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1473,6 +1474,10 @@
 /* Available with KVM_CAP_ARM_SVE */
 #define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
 
+/* Available with  KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
+#define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
new file mode 100644
index 0000000..58b1eb7
--- /dev/null
+++ b/tools/include/uapi/linux/openat2.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_OPENAT2_H
+#define _UAPI_LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+	__u64 flags;
+	__u64 mode;
+	__u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+
+#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 7da1b37..07b4f81 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -234,4 +234,8 @@
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
 
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER		57
+#define PR_GET_IO_FLUSHER		58
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 4a02178..2e3bc22 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -36,6 +36,12 @@
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
 
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME	0x00000080	/* New time namespace */
+
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index df1153c..535a722 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -26,7 +26,9 @@
 
 #if defined(__KERNEL__) || defined(__linux__)
 #include <linux/types.h>
+#include <asm/byteorder.h>
 #else
+#include <endian.h>
 #include <sys/ioctl.h>
 #endif
 
@@ -154,7 +156,7 @@
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 14)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 15)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -301,7 +303,9 @@
 #define SNDRV_PCM_INFO_DRAIN_TRIGGER	0x40000000		/* internal kernel flag - trigger in drain */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 
-
+#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__
+#define __SND_STRUCT_TIME64
+#endif
 
 typedef int __bitwise snd_pcm_state_t;
 #define	SNDRV_PCM_STATE_OPEN		((__force snd_pcm_state_t) 0) /* stream is open */
@@ -317,8 +321,17 @@
 
 enum {
 	SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
-	SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
-	SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000,
+#ifdef __SND_STRUCT_TIME64
+	SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW,
+#else
+	SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD,
+#endif
 };
 
 union snd_pcm_sync_id {
@@ -456,8 +469,13 @@
 	SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED
 };
 
+#ifndef __KERNEL__
+/* explicit padding avoids incompatibility between i386 and x86-64 */
+typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad;
+
 struct snd_pcm_status {
 	snd_pcm_state_t state;		/* stream state */
+	__time_pad pad1;		/* align to timespec */
 	struct timespec trigger_tstamp;	/* time when stream was started/stopped/paused */
 	struct timespec tstamp;		/* reference timestamp */
 	snd_pcm_uframes_t appl_ptr;	/* appl ptr */
@@ -473,17 +491,48 @@
 	__u32 audio_tstamp_accuracy;	/* in ns units, only valid if indicated in audio_tstamp_data */
 	unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */
 };
+#endif
 
-struct snd_pcm_mmap_status {
+/*
+ * For mmap operations, we need the 64-bit layout, both for compat mode,
+ * and for y2038 compatibility. For 64-bit applications, the two definitions
+ * are identical, so we keep the traditional version.
+ */
+#ifdef __SND_STRUCT_TIME64
+#define __snd_pcm_mmap_status64		snd_pcm_mmap_status
+#define __snd_pcm_mmap_control64	snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr64		snd_pcm_sync_ptr
+#ifdef __KERNEL__
+#define __snd_timespec64		__kernel_timespec
+#else
+#define __snd_timespec64		timespec
+#endif
+struct __snd_timespec {
+	__s32 tv_sec;
+	__s32 tv_nsec;
+};
+#else
+#define __snd_pcm_mmap_status		snd_pcm_mmap_status
+#define __snd_pcm_mmap_control		snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr		snd_pcm_sync_ptr
+#define __snd_timespec			timespec
+struct __snd_timespec64 {
+	__s64 tv_sec;
+	__s64 tv_nsec;
+};
+
+#endif
+
+struct __snd_pcm_mmap_status {
 	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
 	int pad1;			/* Needed for 64 bit alignment */
 	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
-	struct timespec tstamp;		/* Timestamp */
+	struct __snd_timespec tstamp;	/* Timestamp */
 	snd_pcm_state_t suspended_state; /* RO: suspended stream state */
-	struct timespec audio_tstamp;	/* from sample counter or wall clock */
+	struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */
 };
 
-struct snd_pcm_mmap_control {
+struct __snd_pcm_mmap_control {
 	snd_pcm_uframes_t appl_ptr;	/* RW: appl ptr (0...boundary-1) */
 	snd_pcm_uframes_t avail_min;	/* RW: min available frames for wakeup */
 };
@@ -492,14 +541,59 @@
 #define SNDRV_PCM_SYNC_PTR_APPL		(1<<1)	/* get appl_ptr from driver (r/w op) */
 #define SNDRV_PCM_SYNC_PTR_AVAIL_MIN	(1<<2)	/* get avail_min from driver */
 
-struct snd_pcm_sync_ptr {
+struct __snd_pcm_sync_ptr {
 	unsigned int flags;
 	union {
-		struct snd_pcm_mmap_status status;
+		struct __snd_pcm_mmap_status status;
 		unsigned char reserved[64];
 	} s;
 	union {
-		struct snd_pcm_mmap_control control;
+		struct __snd_pcm_mmap_control control;
+		unsigned char reserved[64];
+	} c;
+};
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+typedef char __pad_after_uframe[0];
+#endif
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+typedef char __pad_before_uframe[0];
+typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+#endif
+
+struct __snd_pcm_mmap_status64 {
+	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
+	__u32 pad1;			/* Needed for 64 bit alignment */
+	__pad_before_uframe __pad1;
+	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
+	__pad_after_uframe __pad2;
+	struct __snd_timespec64 tstamp;	/* Timestamp */
+	snd_pcm_state_t suspended_state;/* RO: suspended stream state */
+	__u32 pad3;			/* Needed for 64 bit alignment */
+	struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */
+};
+
+struct __snd_pcm_mmap_control64 {
+	__pad_before_uframe __pad1;
+	snd_pcm_uframes_t appl_ptr;	 /* RW: appl ptr (0...boundary-1) */
+	__pad_before_uframe __pad2;
+
+	__pad_before_uframe __pad3;
+	snd_pcm_uframes_t  avail_min;	 /* RW: min available frames for wakeup */
+	__pad_after_uframe __pad4;
+};
+
+struct __snd_pcm_sync_ptr64 {
+	__u32 flags;
+	__u32 pad1;
+	union {
+		struct __snd_pcm_mmap_status64 status;
+		unsigned char reserved[64];
+	} s;
+	union {
+		struct __snd_pcm_mmap_control64 control;
 		unsigned char reserved[64];
 	} c;
 };
@@ -584,6 +678,8 @@
 #define SNDRV_PCM_IOCTL_STATUS		_IOR('A', 0x20, struct snd_pcm_status)
 #define SNDRV_PCM_IOCTL_DELAY		_IOR('A', 0x21, snd_pcm_sframes_t)
 #define SNDRV_PCM_IOCTL_HWSYNC		_IO('A', 0x22)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct __snd_pcm_sync_ptr)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR64	_IOWR('A', 0x23, struct __snd_pcm_sync_ptr64)
 #define SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct snd_pcm_sync_ptr)
 #define SNDRV_PCM_IOCTL_STATUS_EXT	_IOWR('A', 0x24, struct snd_pcm_status)
 #define SNDRV_PCM_IOCTL_CHANNEL_INFO	_IOR('A', 0x32, struct snd_pcm_channel_info)
@@ -614,7 +710,7 @@
  *  Raw MIDI section - /dev/snd/midi??
  */
 
-#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 0)
+#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 1)
 
 enum {
 	SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
@@ -648,13 +744,16 @@
 	unsigned char reserved[16];	/* reserved for future use */
 };
 
+#ifndef __KERNEL__
 struct snd_rawmidi_status {
 	int stream;
+	__time_pad pad1;
 	struct timespec tstamp;		/* Timestamp */
 	size_t avail;			/* available bytes */
 	size_t xruns;			/* count of overruns since last status (in bytes) */
 	unsigned char reserved[16];	/* reserved for future use */
 };
+#endif
 
 #define SNDRV_RAWMIDI_IOCTL_PVERSION	_IOR('W', 0x00, int)
 #define SNDRV_RAWMIDI_IOCTL_INFO	_IOR('W', 0x01, struct snd_rawmidi_info)
@@ -667,7 +766,7 @@
  *  Timer section - /dev/snd/timer
  */
 
-#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 6)
+#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
 
 enum {
 	SNDRV_TIMER_CLASS_NONE = -1,
@@ -761,6 +860,7 @@
 	unsigned char reserved[60];	/* reserved */
 };
 
+#ifndef __KERNEL__
 struct snd_timer_status {
 	struct timespec tstamp;		/* Timestamp - last update */
 	unsigned int resolution;	/* current period resolution in ns */
@@ -769,10 +869,11 @@
 	unsigned int queue;		/* used queue size */
 	unsigned char reserved[64];	/* reserved */
 };
+#endif
 
 #define SNDRV_TIMER_IOCTL_PVERSION	_IOR('T', 0x00, int)
 #define SNDRV_TIMER_IOCTL_NEXT_DEVICE	_IOWR('T', 0x01, struct snd_timer_id)
-#define SNDRV_TIMER_IOCTL_TREAD		_IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_TREAD_OLD	_IOW('T', 0x02, int)
 #define SNDRV_TIMER_IOCTL_GINFO		_IOWR('T', 0x03, struct snd_timer_ginfo)
 #define SNDRV_TIMER_IOCTL_GPARAMS	_IOW('T', 0x04, struct snd_timer_gparams)
 #define SNDRV_TIMER_IOCTL_GSTATUS	_IOWR('T', 0x05, struct snd_timer_gstatus)
@@ -785,6 +886,15 @@
 #define SNDRV_TIMER_IOCTL_STOP		_IO('T', 0xa1)
 #define SNDRV_TIMER_IOCTL_CONTINUE	_IO('T', 0xa2)
 #define SNDRV_TIMER_IOCTL_PAUSE		_IO('T', 0xa3)
+#define SNDRV_TIMER_IOCTL_TREAD64	_IOW('T', 0xa4, int)
+
+#if __BITS_PER_LONG == 64
+#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD
+#else
+#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \
+				 SNDRV_TIMER_IOCTL_TREAD_OLD : \
+				 SNDRV_TIMER_IOCTL_TREAD64)
+#endif
 
 struct snd_timer_read {
 	unsigned int resolution;
@@ -810,11 +920,15 @@
 	SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
 };
 
+#ifndef __KERNEL__
 struct snd_timer_tread {
 	int event;
+	__time_pad pad1;
 	struct timespec tstamp;
 	unsigned int val;
+	__time_pad pad2;
 };
+#endif
 
 /****************************************************************************
  *                                                                          *
@@ -822,7 +936,7 @@
  *                                                                          *
  ****************************************************************************/
 
-#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
+#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 8)
 
 struct snd_ctl_card_info {
 	int card;			/* card number */
@@ -860,7 +974,7 @@
 #define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
 #define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
 #define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP		(1<<3)	/* when was control changed */
+// (1 << 3) is unused.
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
@@ -926,11 +1040,7 @@
 		} enumerated;
 		unsigned char reserved[128];
 	} value;
-	union {
-		unsigned short d[4];		/* dimensions */
-		unsigned short *d_ptr;		/* indirect - obsoleted */
-	} dimen;
-	unsigned char reserved[64-4*sizeof(unsigned short)];
+	unsigned char reserved[64];
 };
 
 struct snd_ctl_elem_value {
@@ -955,8 +1065,7 @@
 		} bytes;
 		struct snd_aes_iec958 iec958;
 	} value;		/* RO */
-	struct timespec tstamp;
-	unsigned char reserved[128-sizeof(struct timespec)];
+	unsigned char reserved[128];
 };
 
 struct snd_ctl_tlv {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 514b1a5..7469c7d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -24,6 +24,7 @@
 #include <endian.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <ctype.h>
 #include <asm/unistd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -1283,7 +1284,7 @@
 static char *internal_map_name(struct bpf_object *obj,
 			       enum libbpf_map_type type)
 {
-	char map_name[BPF_OBJ_NAME_LEN];
+	char map_name[BPF_OBJ_NAME_LEN], *p;
 	const char *sfx = libbpf_type_to_btf_name[type];
 	int sfx_len = max((size_t)7, strlen(sfx));
 	int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
@@ -1292,6 +1293,11 @@
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
 		 sfx_len, libbpf_type_to_btf_name[type]);
 
+	/* sanitise map name to characters allowed by kernel */
+	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
+		if (!isalnum(*p) && *p != '_' && *p != '.')
+			*p = '_';
+
 	return strdup(map_name);
 }
 
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index a32e4b7..d730666 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,8 +1,10 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
+#include <util/cpumap.h>
 #include <internal/cpumap.h>
 #include <api/fs/fs.h>
+#include <errno.h>
 #include "debug.h"
 #include "header.h"
 
@@ -12,26 +14,21 @@
 #define MIDR_VARIANT_SHIFT      20
 #define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
 
-char *get_cpuid_str(struct perf_pmu *pmu)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 {
-	char *buf = NULL;
-	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
-	int cpu;
 	u64 midr = 0;
-	struct perf_cpu_map *cpus;
-	FILE *file;
+	int cpu;
 
-	if (!sysfs || !pmu || !pmu->cpus)
-		return NULL;
+	if (!sysfs || sz < MIDR_SIZE)
+		return EINVAL;
 
-	buf = malloc(MIDR_SIZE);
-	if (!buf)
-		return NULL;
+	cpus = perf_cpu_map__get(cpus);
 
-	/* read midr from list of cpus mapped to this pmu */
-	cpus = perf_cpu_map__get(pmu->cpus);
 	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+		char path[PATH_MAX];
+		FILE *file;
+
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
 				sysfs, cpus->map[cpu]);
 
@@ -57,12 +54,48 @@
 		break;
 	}
 
-	if (!midr) {
+	perf_cpu_map__put(cpus);
+
+	if (!midr)
+		return EINVAL;
+
+	return 0;
+}
+
+int get_cpuid(char *buf, size_t sz)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	int ret;
+
+	if (!cpus)
+		return EINVAL;
+
+	ret = _get_cpuid(buf, sz, cpus);
+
+	perf_cpu_map__put(cpus);
+
+	return ret;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+	char *buf = NULL;
+	int res;
+
+	if (!pmu || !pmu->cpus)
+		return NULL;
+
+	buf = malloc(MIDR_SIZE);
+	if (!buf)
+		return NULL;
+
+	/* read midr from list of cpus mapped to this pmu */
+	res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+	if (res) {
 		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
 		free(buf);
 		buf = NULL;
 	}
 
-	perf_cpu_map__put(cpus);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index c29976e..44d510b 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -357,6 +357,8 @@
 433	common	fspick			__x64_sys_fspick
 434	common	pidfd_open		__x64_sys_pidfd_open
 435	common	clone3			__x64_sys_clone3/ptregs
+437	common	openat2			__x64_sys_openat2
+438	common	pidfd_getfd		__x64_sys_pidfd_getfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 46a72ec..01d5420 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1065,7 +1065,9 @@
 	{ .name	    = "poll", .timeout = true, },
 	{ .name	    = "ppoll", .timeout = true, },
 	{ .name	    = "prctl",
-	  .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
+	  .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */
+			   .strtoul   = STUL_STRARRAY,
+			   .parm      = &strarray__prctl_options, },
 		   [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
 		   [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
 	{ .name	    = "pread", .alias = "pread64", },
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 68039a96..bfb21d0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -13,6 +13,7 @@
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
 include/uapi/linux/mount.h
+include/uapi/linux/openat2.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 5a61043..d6dfe68 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -213,6 +213,8 @@
 size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option
 
+extern struct strarray strarray__prctl_options;
+
 size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index ba2179a..6fe5ad5 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -11,9 +11,10 @@
 
 #include "trace/beauty/generated/prctl_option_array.c"
 
+DEFINE_STRARRAY(prctl_options, "PR_");
+
 static size_t prctl__scnprintf_option(int option, char *bf, size_t size, bool show_prefix)
 {
-	static DEFINE_STRARRAY(prctl_options, "PR_");
 	return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", show_prefix, option);
 }
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index eae47c2..b5af680 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -288,6 +288,7 @@
 "obj-y := dummy.o\n"
 "\\$(obj)/%.o: \\$(src)/%.c\n"
 "\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
+"\t\\$(CC) -c -o \\$@ \\$<\n"
 "EOF\n"
 "touch $TMPDIR/dummy.c\n"
 "make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c8c5410..fb5c2cd 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -686,6 +686,7 @@
 
 		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
+		dso->kernel = DSO_TYPE_KERNEL;
 	}
 
 	dso__get(dso);
@@ -726,9 +727,17 @@
 	struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr);
 
 	if (!map) {
-		map = dso__new_map(event->ksymbol.name);
-		if (!map)
+		struct dso *dso = dso__new(event->ksymbol.name);
+
+		if (dso) {
+			dso->kernel = DSO_TYPE_KERNEL;
+			map = map__new2(0, dso);
+		}
+
+		if (!dso || !map) {
+			dso__put(dso);
 			return -ENOMEM;
+		}
 
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
@@ -972,7 +981,6 @@
 
 	kmap = map__kmap(map);
 
-	kmap->kmaps = &machine->kmaps;
 	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
 
 	maps__insert(&machine->kmaps, map);
@@ -1082,9 +1090,6 @@
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-	struct kmap *kmap;
-	struct map *map;
-
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
 
@@ -1093,14 +1098,7 @@
 		return -1;
 
 	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
-	map = machine__kernel_map(machine);
-	kmap = map__kmap(map);
-	if (!kmap)
-		return -1;
-
-	kmap->kmaps = &machine->kmaps;
-	maps__insert(&machine->kmaps, map);
-
+	maps__insert(&machine->kmaps, machine->vmlinux_map);
 	return 0;
 }
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f67960b..a08ca27 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -375,8 +375,13 @@
 
 struct map *map__clone(struct map *from)
 {
-	struct map *map = memdup(from, sizeof(*map));
+	size_t size = sizeof(struct map);
+	struct map *map;
 
+	if (from->dso && from->dso->kernel)
+		size += sizeof(struct kmap);
+
+	map = memdup(from, size);
 	if (map != NULL) {
 		refcount_set(&map->refcnt, 1);
 		RB_CLEAR_NODE(&map->rb_node);
@@ -538,6 +543,16 @@
 	__maps__insert(maps, map);
 	++maps->nr_maps;
 
+	if (map->dso && map->dso->kernel) {
+		struct kmap *kmap = map__kmap(map);
+
+		if (kmap)
+			kmap->kmaps = maps;
+		else
+			pr_err("Internal error: kernel dso with non kernel map\n");
+	}
+
+
 	/*
 	 * If we already performed some search by name, then we need to add the just
 	 * inserted map and resort.
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2c41d47..90d23cc 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -18,7 +18,6 @@
  * AGGR_NONE: Use matching CPU
  * AGGR_THREAD: Not supported?
  */
-static bool have_frontend_stalled;
 
 struct runtime_stat rt_stat;
 struct stats walltime_nsecs_stats;
@@ -144,7 +143,6 @@
 
 void perf_stat__init_shadow_stats(void)
 {
-	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
 	runtime_stat__init(&rt_stat);
 }
 
@@ -853,10 +851,6 @@
 			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
-		} else if (have_frontend_stalled) {
-			out->new_line(config, ctxp);
-			print_metric(config, ctxp, NULL, "%7.2f ",
-				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b379b1..1077013 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -635,9 +635,12 @@
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"acpi_idle_do_entry",
+		"acpi_processor_ffh_cstate_enter",
 		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
+		"idle_cpu",
 		"intel_idle",
 		"default_idle",
 		"native_safe_halt",
@@ -651,13 +654,17 @@
 		NULL
 	};
 	int i;
+	static struct strlist *idle_symbols_list;
 
-	for (i = 0; idle_symbols[i]; i++) {
-		if (!strcmp(idle_symbols[i], name))
-			return true;
-	}
+	if (idle_symbols_list)
+		return strlist__has_entry(idle_symbols_list, name);
 
-	return false;
+	idle_symbols_list = strlist__new(NULL, NULL);
+
+	for (i = 0; idle_symbols[i]; i++)
+		strlist__add(idle_symbols_list, idle_symbols[i]);
+
+	return strlist__has_entry(idle_symbols_list, name);
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 63430e2..6ec5039 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -77,6 +77,12 @@
 	override TARGETS := $(TMP)
 endif
 
+# User can set FORCE_TARGETS to 1 to require all targets to be successfully
+# built; make will fail if any of the targets cannot be built. If
+# FORCE_TARGETS is not set (the default), make will succeed if at least one
+# of the targets gets built.
+FORCE_TARGETS ?=
+
 # Clear LDFLAGS and MAKEFLAGS if called from main
 # Makefile to avoid test build failures when test
 # Makefile doesn't have explicit build rules.
@@ -151,7 +157,8 @@
 	for TARGET in $(TARGETS); do				\
 		BUILD_TARGET=$$BUILD/$$TARGET;			\
 		mkdir $$BUILD_TARGET  -p;			\
-		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET;	\
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET	\
+				$(if $(FORCE_TARGETS),|| exit);	\
 		ret=$$((ret * $$?));				\
 	done; exit $$ret;
 
@@ -205,7 +212,8 @@
 	@ret=1;	\
 	for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
-		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \
+				$(if $(FORCE_TARGETS),|| exit);	\
 		ret=$$((ret * $$?));		\
 	done; exit $$ret;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 098bcae..0800036e 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -506,8 +506,10 @@
 		.pass_on_failure = 0,
 	};
 
-	if (type != SOCK_STREAM)
+	if (type != SOCK_STREAM) {
+		test__skip();
 		return;
+	}
 
 	/*
 	 * +1 for TCP-SYN and
@@ -822,8 +824,10 @@
 		goto out;
 
 	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
+	if (saved_tcp_fo < 0)
+		goto out;
 	saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
-	if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0)
+	if (saved_tcp_syncookie < 0)
 		goto out;
 
 	if (enable_fastopen())
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 07f5b46..aa43e0b 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -3,6 +3,11 @@
 
 #include "test_progs.h"
 
+#define TCP_REPAIR		19	/* TCP sock is under repair right now */
+
+#define TCP_REPAIR_ON		1
+#define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
+
 static int connected_socket_v4(void)
 {
 	struct sockaddr_in addr = {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 64cfcc7..f2ee1e8 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -1,6 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function pid filters
+# flags: instance
 
 # Make sure that function pid matching filter works.
 # Also test it on an instance directory
@@ -96,13 +97,6 @@
 }
 
 do_test
-
-mkdir instances/foo
-cd instances/foo
-do_test
-cd ../../
-rmdir instances/foo
-
 do_reset
 
 exit 0
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index 30996306..2320782 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 INCLUDES := -I../include -I../../
 CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES)
-LDFLAGS := $(LDFLAGS) -pthread -lrt
+LDLIBS := -lpthread -lrt
 
 HEADERS := \
 	../include/futextest.h \
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 67abc1d..d91c53b7 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -8,7 +8,7 @@
 UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/ucall.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
 
@@ -26,6 +26,7 @@
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index aa6451b..7428513 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -36,24 +36,24 @@
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
-/* The enum values match the intruction encoding of each register */
-enum x86_register {
-	RAX = 0,
-	RCX,
-	RDX,
-	RBX,
-	RSP,
-	RBP,
-	RSI,
-	RDI,
-	R8,
-	R9,
-	R10,
-	R11,
-	R12,
-	R13,
-	R14,
-	R15,
+/* General Registers in 64-Bit Mode */
+struct gpr64_regs {
+	u64 rax;
+	u64 rcx;
+	u64 rdx;
+	u64 rbx;
+	u64 rsp;
+	u64 rbp;
+	u64 rsi;
+	u64 rdi;
+	u64 r8;
+	u64 r9;
+	u64 r10;
+	u64 r11;
+	u64 r12;
+	u64 r13;
+	u64 r14;
+	u64 r15;
 };
 
 struct desc64 {
@@ -220,20 +220,20 @@
 	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
 }
 
-static inline uint64_t get_gdt_base(void)
+static inline struct desc_ptr get_gdt(void)
 {
 	struct desc_ptr gdt;
 	__asm__ __volatile__("sgdt %[gdt]"
 			     : /* output */ [gdt]"=m"(gdt));
-	return gdt.address;
+	return gdt;
 }
 
-static inline uint64_t get_idt_base(void)
+static inline struct desc_ptr get_idt(void)
 {
 	struct desc_ptr idt;
 	__asm__ __volatile__("sidt %[idt]"
 			     : /* output */ [idt]"=m"(idt));
-	return idt.address;
+	return idt;
 }
 
 #define SET_XMM(__var, __xmm) \
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h
new file mode 100644
index 0000000..f4ea235
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/svm.h
@@ -0,0 +1,297 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/svm.h
+ * This is a copy of arch/x86/include/asm/svm.h
+ *
+ */
+
+#ifndef SELFTEST_KVM_SVM_H
+#define SELFTEST_KVM_SVM_H
+
+enum {
+	INTERCEPT_INTR,
+	INTERCEPT_NMI,
+	INTERCEPT_SMI,
+	INTERCEPT_INIT,
+	INTERCEPT_VINTR,
+	INTERCEPT_SELECTIVE_CR0,
+	INTERCEPT_STORE_IDTR,
+	INTERCEPT_STORE_GDTR,
+	INTERCEPT_STORE_LDTR,
+	INTERCEPT_STORE_TR,
+	INTERCEPT_LOAD_IDTR,
+	INTERCEPT_LOAD_GDTR,
+	INTERCEPT_LOAD_LDTR,
+	INTERCEPT_LOAD_TR,
+	INTERCEPT_RDTSC,
+	INTERCEPT_RDPMC,
+	INTERCEPT_PUSHF,
+	INTERCEPT_POPF,
+	INTERCEPT_CPUID,
+	INTERCEPT_RSM,
+	INTERCEPT_IRET,
+	INTERCEPT_INTn,
+	INTERCEPT_INVD,
+	INTERCEPT_PAUSE,
+	INTERCEPT_HLT,
+	INTERCEPT_INVLPG,
+	INTERCEPT_INVLPGA,
+	INTERCEPT_IOIO_PROT,
+	INTERCEPT_MSR_PROT,
+	INTERCEPT_TASK_SWITCH,
+	INTERCEPT_FERR_FREEZE,
+	INTERCEPT_SHUTDOWN,
+	INTERCEPT_VMRUN,
+	INTERCEPT_VMMCALL,
+	INTERCEPT_VMLOAD,
+	INTERCEPT_VMSAVE,
+	INTERCEPT_STGI,
+	INTERCEPT_CLGI,
+	INTERCEPT_SKINIT,
+	INTERCEPT_RDTSCP,
+	INTERCEPT_ICEBP,
+	INTERCEPT_WBINVD,
+	INTERCEPT_MONITOR,
+	INTERCEPT_MWAIT,
+	INTERCEPT_MWAIT_COND,
+	INTERCEPT_XSETBV,
+	INTERCEPT_RDPRU,
+};
+
+
+struct __attribute__ ((__packed__)) vmcb_control_area {
+	u32 intercept_cr;
+	u32 intercept_dr;
+	u32 intercept_exceptions;
+	u64 intercept;
+	u8 reserved_1[40];
+	u16 pause_filter_thresh;
+	u16 pause_filter_count;
+	u64 iopm_base_pa;
+	u64 msrpm_base_pa;
+	u64 tsc_offset;
+	u32 asid;
+	u8 tlb_ctl;
+	u8 reserved_2[3];
+	u32 int_ctl;
+	u32 int_vector;
+	u32 int_state;
+	u8 reserved_3[4];
+	u32 exit_code;
+	u32 exit_code_hi;
+	u64 exit_info_1;
+	u64 exit_info_2;
+	u32 exit_int_info;
+	u32 exit_int_info_err;
+	u64 nested_ctl;
+	u64 avic_vapic_bar;
+	u8 reserved_4[8];
+	u32 event_inj;
+	u32 event_inj_err;
+	u64 nested_cr3;
+	u64 virt_ext;
+	u32 clean;
+	u32 reserved_5;
+	u64 next_rip;
+	u8 insn_len;
+	u8 insn_bytes[15];
+	u64 avic_backing_page;	/* Offset 0xe0 */
+	u8 reserved_6[8];	/* Offset 0xe8 */
+	u64 avic_logical_id;	/* Offset 0xf0 */
+	u64 avic_physical_id;	/* Offset 0xf8 */
+	u8 reserved_7[768];
+};
+
+
+#define TLB_CONTROL_DO_NOTHING 0
+#define TLB_CONTROL_FLUSH_ALL_ASID 1
+#define TLB_CONTROL_FLUSH_ASID 3
+#define TLB_CONTROL_FLUSH_ASID_LOCAL 7
+
+#define V_TPR_MASK 0x0f
+
+#define V_IRQ_SHIFT 8
+#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
+
+#define V_GIF_SHIFT 9
+#define V_GIF_MASK (1 << V_GIF_SHIFT)
+
+#define V_INTR_PRIO_SHIFT 16
+#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
+
+#define V_IGN_TPR_SHIFT 20
+#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+
+#define V_INTR_MASKING_SHIFT 24
+#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
+
+#define V_GIF_ENABLE_SHIFT 25
+#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT)
+
+#define AVIC_ENABLE_SHIFT 31
+#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
+
+#define LBR_CTL_ENABLE_MASK BIT_ULL(0)
+#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1)
+
+#define SVM_INTERRUPT_SHADOW_MASK 1
+
+#define SVM_IOIO_STR_SHIFT 2
+#define SVM_IOIO_REP_SHIFT 3
+#define SVM_IOIO_SIZE_SHIFT 4
+#define SVM_IOIO_ASIZE_SHIFT 7
+
+#define SVM_IOIO_TYPE_MASK 1
+#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
+#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
+#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
+#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
+
+#define SVM_VM_CR_VALID_MASK	0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK  0x0010ULL
+
+#define SVM_NESTED_CTL_NP_ENABLE	BIT(0)
+#define SVM_NESTED_CTL_SEV_ENABLE	BIT(1)
+
+struct __attribute__ ((__packed__)) vmcb_seg {
+	u16 selector;
+	u16 attrib;
+	u32 limit;
+	u64 base;
+};
+
+struct __attribute__ ((__packed__)) vmcb_save_area {
+	struct vmcb_seg es;
+	struct vmcb_seg cs;
+	struct vmcb_seg ss;
+	struct vmcb_seg ds;
+	struct vmcb_seg fs;
+	struct vmcb_seg gs;
+	struct vmcb_seg gdtr;
+	struct vmcb_seg ldtr;
+	struct vmcb_seg idtr;
+	struct vmcb_seg tr;
+	u8 reserved_1[43];
+	u8 cpl;
+	u8 reserved_2[4];
+	u64 efer;
+	u8 reserved_3[112];
+	u64 cr4;
+	u64 cr3;
+	u64 cr0;
+	u64 dr7;
+	u64 dr6;
+	u64 rflags;
+	u64 rip;
+	u8 reserved_4[88];
+	u64 rsp;
+	u8 reserved_5[24];
+	u64 rax;
+	u64 star;
+	u64 lstar;
+	u64 cstar;
+	u64 sfmask;
+	u64 kernel_gs_base;
+	u64 sysenter_cs;
+	u64 sysenter_esp;
+	u64 sysenter_eip;
+	u64 cr2;
+	u8 reserved_6[32];
+	u64 g_pat;
+	u64 dbgctl;
+	u64 br_from;
+	u64 br_to;
+	u64 last_excp_from;
+	u64 last_excp_to;
+};
+
+struct __attribute__ ((__packed__)) vmcb {
+	struct vmcb_control_area control;
+	struct vmcb_save_area save;
+};
+
+#define SVM_CPUID_FUNC 0x8000000a
+
+#define SVM_VM_CR_SVM_DISABLE 4
+
+#define SVM_SELECTOR_S_SHIFT 4
+#define SVM_SELECTOR_DPL_SHIFT 5
+#define SVM_SELECTOR_P_SHIFT 7
+#define SVM_SELECTOR_AVL_SHIFT 8
+#define SVM_SELECTOR_L_SHIFT 9
+#define SVM_SELECTOR_DB_SHIFT 10
+#define SVM_SELECTOR_G_SHIFT 11
+
+#define SVM_SELECTOR_TYPE_MASK (0xf)
+#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
+#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
+#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
+#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
+#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
+#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
+#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
+
+#define SVM_SELECTOR_WRITE_MASK (1 << 1)
+#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
+#define SVM_SELECTOR_CODE_MASK (1 << 3)
+
+#define INTERCEPT_CR0_READ	0
+#define INTERCEPT_CR3_READ	3
+#define INTERCEPT_CR4_READ	4
+#define INTERCEPT_CR8_READ	8
+#define INTERCEPT_CR0_WRITE	(16 + 0)
+#define INTERCEPT_CR3_WRITE	(16 + 3)
+#define INTERCEPT_CR4_WRITE	(16 + 4)
+#define INTERCEPT_CR8_WRITE	(16 + 8)
+
+#define INTERCEPT_DR0_READ	0
+#define INTERCEPT_DR1_READ	1
+#define INTERCEPT_DR2_READ	2
+#define INTERCEPT_DR3_READ	3
+#define INTERCEPT_DR4_READ	4
+#define INTERCEPT_DR5_READ	5
+#define INTERCEPT_DR6_READ	6
+#define INTERCEPT_DR7_READ	7
+#define INTERCEPT_DR0_WRITE	(16 + 0)
+#define INTERCEPT_DR1_WRITE	(16 + 1)
+#define INTERCEPT_DR2_WRITE	(16 + 2)
+#define INTERCEPT_DR3_WRITE	(16 + 3)
+#define INTERCEPT_DR4_WRITE	(16 + 4)
+#define INTERCEPT_DR5_WRITE	(16 + 5)
+#define INTERCEPT_DR6_WRITE	(16 + 6)
+#define INTERCEPT_DR7_WRITE	(16 + 7)
+
+#define SVM_EVTINJ_VEC_MASK 0xff
+
+#define SVM_EVTINJ_TYPE_SHIFT 8
+#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_VALID (1 << 31)
+#define SVM_EVTINJ_VALID_ERR (1 << 11)
+
+#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK
+
+#define	SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
+#define	SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
+#define	SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
+#define	SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
+
+#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
+#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
+
+#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
+#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
+
+#define SVM_EXITINFO_REG_MASK 0x0F
+
+#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
+
+#endif /* SELFTEST_KVM_SVM_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
new file mode 100644
index 0000000..cd03791
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/x86_64/svm_utils.h
+ * Header for nested SVM testing
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+
+#ifndef SELFTEST_KVM_SVM_UTILS_H
+#define SELFTEST_KVM_SVM_UTILS_H
+
+#include <stdint.h>
+#include "svm.h"
+#include "processor.h"
+
+#define CPUID_SVM_BIT		2
+#define CPUID_SVM		BIT_ULL(CPUID_SVM_BIT)
+
+#define SVM_EXIT_VMMCALL	0x081
+
+struct svm_test_data {
+	/* VMCB */
+	struct vmcb *vmcb; /* gva */
+	void *vmcb_hva;
+	uint64_t vmcb_gpa;
+
+	/* host state-save area */
+	struct vmcb_save_area *save_area; /* gva */
+	void *save_area_hva;
+	uint64_t save_area_gpa;
+};
+
+struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva);
+void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp);
+void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa);
+void nested_svm_check_supported(void);
+
+#endif /* SELFTEST_KVM_SVM_UTILS_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
new file mode 100644
index 0000000..6e05a8f
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/svm.c
+ * Helpers used for nested SVM testing
+ * Largely inspired from KVM unit test svm.c
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "svm_util.h"
+
+struct gpr64_regs guest_regs;
+u64 rflags;
+
+/* Allocate memory regions for nested SVM tests.
+ *
+ * Input Args:
+ *   vm - The VM to allocate guest-virtual addresses in.
+ *
+ * Output Args:
+ *   p_svm_gva - The guest virtual address for the struct svm_test_data.
+ *
+ * Return:
+ *   Pointer to structure with the addresses of the SVM areas.
+ */
+struct svm_test_data *
+vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva)
+{
+	vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(),
+					    0x10000, 0, 0);
+	struct svm_test_data *svm = addr_gva2hva(vm, svm_gva);
+
+	svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(),
+					   0x10000, 0, 0);
+	svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb);
+	svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb);
+
+	svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(),
+						0x10000, 0, 0);
+	svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area);
+	svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area);
+
+	*p_svm_gva = svm_gva;
+	return svm;
+}
+
+static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector,
+			 u64 base, u32 limit, u32 attr)
+{
+	seg->selector = selector;
+	seg->attrib = attr;
+	seg->limit = limit;
+	seg->base = base;
+}
+
+void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp)
+{
+	struct vmcb *vmcb = svm->vmcb;
+	uint64_t vmcb_gpa = svm->vmcb_gpa;
+	struct vmcb_save_area *save = &vmcb->save;
+	struct vmcb_control_area *ctrl = &vmcb->control;
+	u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK
+	      | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK;
+	u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK
+		| SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK;
+	uint64_t efer;
+
+	efer = rdmsr(MSR_EFER);
+	wrmsr(MSR_EFER, efer | EFER_SVME);
+	wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa);
+
+	memset(vmcb, 0, sizeof(*vmcb));
+	asm volatile ("vmsave\n\t" : : "a" (vmcb_gpa) : "memory");
+	vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr);
+	vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr);
+	vmcb_set_seg(&save->ss, get_ss(), 0, -1U, data_seg_attr);
+	vmcb_set_seg(&save->ds, get_ds(), 0, -1U, data_seg_attr);
+	vmcb_set_seg(&save->gdtr, 0, get_gdt().address, get_gdt().size, 0);
+	vmcb_set_seg(&save->idtr, 0, get_idt().address, get_idt().size, 0);
+
+	ctrl->asid = 1;
+	save->cpl = 0;
+	save->efer = rdmsr(MSR_EFER);
+	asm volatile ("mov %%cr4, %0" : "=r"(save->cr4) : : "memory");
+	asm volatile ("mov %%cr3, %0" : "=r"(save->cr3) : : "memory");
+	asm volatile ("mov %%cr0, %0" : "=r"(save->cr0) : : "memory");
+	asm volatile ("mov %%dr7, %0" : "=r"(save->dr7) : : "memory");
+	asm volatile ("mov %%dr6, %0" : "=r"(save->dr6) : : "memory");
+	asm volatile ("mov %%cr2, %0" : "=r"(save->cr2) : : "memory");
+	save->g_pat = rdmsr(MSR_IA32_CR_PAT);
+	save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR);
+	ctrl->intercept = (1ULL << INTERCEPT_VMRUN) |
+				(1ULL << INTERCEPT_VMMCALL);
+
+	vmcb->save.rip = (u64)guest_rip;
+	vmcb->save.rsp = (u64)guest_rsp;
+	guest_regs.rdi = (u64)svm;
+}
+
+/*
+ * save/restore 64-bit general registers except rax, rip, rsp
+ * which are directly handed through the VMCB guest processor state
+ */
+#define SAVE_GPR_C				\
+	"xchg %%rbx, guest_regs+0x20\n\t"	\
+	"xchg %%rcx, guest_regs+0x10\n\t"	\
+	"xchg %%rdx, guest_regs+0x18\n\t"	\
+	"xchg %%rbp, guest_regs+0x30\n\t"	\
+	"xchg %%rsi, guest_regs+0x38\n\t"	\
+	"xchg %%rdi, guest_regs+0x40\n\t"	\
+	"xchg %%r8,  guest_regs+0x48\n\t"	\
+	"xchg %%r9,  guest_regs+0x50\n\t"	\
+	"xchg %%r10, guest_regs+0x58\n\t"	\
+	"xchg %%r11, guest_regs+0x60\n\t"	\
+	"xchg %%r12, guest_regs+0x68\n\t"	\
+	"xchg %%r13, guest_regs+0x70\n\t"	\
+	"xchg %%r14, guest_regs+0x78\n\t"	\
+	"xchg %%r15, guest_regs+0x80\n\t"
+
+#define LOAD_GPR_C      SAVE_GPR_C
+
+/*
+ * selftests do not use interrupts so we dropped clgi/sti/cli/stgi
+ * for now. registers involved in LOAD/SAVE_GPR_C are eventually
+ * unmodified so they do not need to be in the clobber list.
+ */
+void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa)
+{
+	asm volatile (
+		"vmload\n\t"
+		"mov rflags, %%r15\n\t"	// rflags
+		"mov %%r15, 0x170(%[vmcb])\n\t"
+		"mov guest_regs, %%r15\n\t"	// rax
+		"mov %%r15, 0x1f8(%[vmcb])\n\t"
+		LOAD_GPR_C
+		"vmrun\n\t"
+		SAVE_GPR_C
+		"mov 0x170(%[vmcb]), %%r15\n\t"	// rflags
+		"mov %%r15, rflags\n\t"
+		"mov 0x1f8(%[vmcb]), %%r15\n\t"	// rax
+		"mov %%r15, guest_regs\n\t"
+		"vmsave\n\t"
+		: : [vmcb] "r" (vmcb), [vmcb_gpa] "a" (vmcb_gpa)
+		: "r15", "memory");
+}
+
+void nested_svm_check_supported(void)
+{
+	struct kvm_cpuid_entry2 *entry =
+		kvm_get_supported_cpuid_entry(0x80000001);
+
+	if (!(entry->ecx & CPUID_SVM)) {
+		fprintf(stderr, "nested SVM not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+}
+
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 85064ba..7aaa99c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -288,9 +288,9 @@
 	vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
 	vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
 	vmwrite(HOST_TR_BASE,
-		get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
-	vmwrite(HOST_GDTR_BASE, get_gdt_base());
-	vmwrite(HOST_IDTR_BASE, get_idt_base());
+		get_desc64_base((struct desc64 *)(get_gdt().address + get_tr())));
+	vmwrite(HOST_GDTR_BASE, get_gdt().address);
+	vmwrite(HOST_IDTR_BASE, get_idt().address);
 	vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
 	vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
 }
diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
new file mode 100644
index 0000000..e280f68
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_vmcall_test
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * Nested SVM testing: VMCALL
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+
+#define VCPU_ID		5
+
+static struct kvm_vm *vm;
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct svm_test_data *svm)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+
+	/* Prepare for L2 execution. */
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	run_guest(vmcb, svm->vmcb_gpa);
+
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t svm_gva;
+
+	nested_svm_check_supported();
+
+	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	vcpu_alloc_svm(vm, &svm_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, svm_gva);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+		struct ucall uc;
+
+		vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s",
+				    (const char *)uc.args[0]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false,
+				    "Unknown ucall 0x%x.", uc.cmd);
+		}
+	}
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 1c8a196..3ed0134 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -83,17 +83,20 @@
 	$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
 endif
 
+define INSTALL_SINGLE_RULE
+	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
+	$(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+	$(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+endef
+
 define INSTALL_RULE
-	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then					\
-		mkdir -p ${INSTALL_PATH};										\
-		echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";	\
-		rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;		\
-	fi
-	@if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then					\
-		mkdir -p ${INSTALL_PATH};										\
-		echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";	\
-		rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;		\
-	fi
+	$(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE)
 endef
 
 install: all
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b569419..287ae91 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -27,5 +27,5 @@
 include ../lib.mk
 
 $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
-$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
-$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
+$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
+$(OUTPUT)/tcp_inq: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 6dd4031..60273f1 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -910,6 +910,12 @@
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
+	# multipath with dev-only
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+	check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with dev-only"
+
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh
index e6fd7a1..0266443 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh
@@ -63,22 +63,23 @@
 {
 	local tundev=$1; shift
 	local direction=$1; shift
-	local prot=$1; shift
 	local what=$1; shift
 
-	local swp3mac=$(mac_get $swp3)
-	local h3mac=$(mac_get $h3)
+	case "$direction" in
+	ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2)
+		;;
+	egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1)
+		;;
+	esac
 
 	RET=0
 
 	mirror_install $swp1 $direction $tundev "matchall $tcflags"
-	tc filter add dev $h3 ingress pref 77 prot $prot \
-		flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
-		action pass
+	icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac"
 
-	mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+	mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10
 
-	tc filter del dev $h3 ingress pref 77
+	icmp_capture_uninstall h3-${tundev}
 	mirror_uninstall $swp1 $direction
 
 	log_test "$direction $what: envelope MAC ($tcflags)"
@@ -120,14 +121,14 @@
 
 test_gretap_mac()
 {
-	test_span_gre_mac gt4 ingress ip "mirror to gretap"
-	test_span_gre_mac gt4 egress ip "mirror to gretap"
+	test_span_gre_mac gt4 ingress "mirror to gretap"
+	test_span_gre_mac gt4 egress "mirror to gretap"
 }
 
 test_ip6gretap_mac()
 {
-	test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
-	test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+	test_span_gre_mac gt6 ingress "mirror to ip6gretap"
+	test_span_gre_mac gt6 egress "mirror to ip6gretap"
 }
 
 test_all()
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index bb10e33..ce6bea967 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -516,9 +516,9 @@
 	RET=0
 
 	tc filter add dev v1 egress pref 77 prot ip \
-		flower ip_tos 0x40 action pass
-	vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
-	vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+		flower ip_tos 0x14 action pass
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0
 	tc filter del dev v1 egress pref 77 prot ip
 
 	log_test "VXLAN: envelope TOS inheritance"
diff --git a/tools/testing/selftests/openat2/helpers.c b/tools/testing/selftests/openat2/helpers.c
index e9a6557..5074681 100644
--- a/tools/testing/selftests/openat2/helpers.c
+++ b/tools/testing/selftests/openat2/helpers.c
@@ -46,7 +46,7 @@
 
 int touchat(int dfd, const char *path)
 {
-	int fd = openat(dfd, path, O_CREAT);
+	int fd = openat(dfd, path, O_CREAT, 0700);
 	if (fd >= 0)
 		close(fd);
 	return fd;
diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c
index 7a94b1d..bbafad4 100644
--- a/tools/testing/selftests/openat2/resolve_test.c
+++ b/tools/testing/selftests/openat2/resolve_test.c
@@ -230,7 +230,7 @@
 		{ .name = "[in_root] garbage link to /root",
 		  .path = "cheeky/garbageself",	.how.resolve = RESOLVE_IN_ROOT,
 		  .out.path = "root",		.pass = true },
-		{ .name = "[in_root] chainged garbage links to /root",
+		{ .name = "[in_root] chained garbage links to /root",
 		  .path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT,
 		  .out.path = "root",		.pass = true },
 		{ .name = "[in_root] relative path to 'root'",
diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile
index de9c856..2d93d65 100644
--- a/tools/testing/selftests/rtc/Makefile
+++ b/tools/testing/selftests/rtc/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm
 
 TEST_GEN_PROGS = rtctest
 
diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile
index e9fb30b..b4fd9a9 100644
--- a/tools/testing/selftests/timens/Makefile
+++ b/tools/testing/selftests/timens/Makefile
@@ -2,6 +2,6 @@
 TEST_GEN_PROGS_EXTENDED := gettime_perf
 
 CFLAGS := -Wall -Werror -pthread
-LDFLAGS := -lrt -ldl
+LDLIBS := -lrt -ldl
 
 include ../lib.mk
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index 8155c2e..b630c7b 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -1,8 +1,17 @@
 #!/bin/bash
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+self.flags = flags
 
-python -m unittest -v tpm2_tests.SmokeTest
-python -m unittest -v tpm2_tests.AsyncTest
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+
+if [ -f /dev/tpm0 ] ; then
+	python -m unittest -v tpm2_tests.SmokeTest
+	python -m unittest -v tpm2_tests.AsyncTest
+else
+	exit $ksft_skip
+fi
 
 CLEAR_CMD=$(which tpm2_clear)
 if [ -n $CLEAR_CMD ]; then
diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh
index a6f5e34..180b469 100755
--- a/tools/testing/selftests/tpm2/test_space.sh
+++ b/tools/testing/selftests/tpm2/test_space.sh
@@ -1,4 +1,11 @@
 #!/bin/bash
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 
-python -m unittest -v tpm2_tests.SpaceTest
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if [ -f /dev/tpmrm0 ] ; then
+	python -m unittest -v tpm2_tests.SpaceTest
+else
+	exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index a692ea82..f337148 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -112,6 +112,17 @@
 echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
 echo "      hugetlb regression testing."
 
+echo "---------------------------"
+echo "running map_fixed_noreplace"
+echo "---------------------------"
+./map_fixed_noreplace
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 echo "-------------------"
 echo "running userfaultfd"
 echo "-------------------"
@@ -186,6 +197,17 @@
 	echo "[PASS]"
 fi
 
+echo "-------------------------"
+echo "running mlock-random-test"
+echo "-------------------------"
+./mlock-random-test
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 echo "--------------------"
 echo "running mlock2-tests"
 echo "--------------------"
@@ -197,6 +219,17 @@
 	echo "[PASS]"
 fi
 
+echo "-----------------"
+echo "running thuge-gen"
+echo "-----------------"
+./thuge-gen
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 if [ $VADDR64 -ne 0 ]; then
 echo "-----------------------------"
 echo "running virtual_address_range"
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index f5ab1cd..138d46b 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -24,6 +24,7 @@
 set -e
 
 exec 3>&1
+export LANG=C
 export WG_HIDE_KEYS=never
 netns0="wg-test-$$-0"
 netns1="wg-test-$$-1"
@@ -297,7 +298,17 @@
 n1 ping -W 1 -c 100 -f 192.168.99.7
 n1 ping -W 1 -c 100 -f abab::1111
 
+# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route.
+n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2
+n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit.
+n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
+ip0 -4 route add 192.168.241.1 via 10.0.0.100
+n2 wg set wg0 peer "$pub1" remove
+[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]]
+
 n0 iptables -t nat -F
+n0 iptables -t filter -F
+n2 iptables -t nat -F
 ip0 link del vethrc
 ip0 link del vethrs
 ip1 link del wg0
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index f10aa35..28d4776 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -38,19 +38,17 @@
 define file_download =
 $(DISTFILES_PATH)/$(1):
 	mkdir -p $(DISTFILES_PATH)
-	flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
-	if echo "$(3)  $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
+	flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3)  $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
 endef
 
 $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
-$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
 $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
 $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
 $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
 $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
 $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
 $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
 
 KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
 rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
@@ -295,21 +293,13 @@
 	$(MAKE) -C $(IPERF_PATH)
 	$(STRIP) -s $@
 
-$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
-	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-	touch $@
-
-$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
-	cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
-	$(MAKE) -C $(LIBMNL_PATH)
-	sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
-
 $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
+	mkdir -p $(BUILD_PATH)
 	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
 	touch $@
 
-$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS)
+	$(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg
 	$(STRIP) -s $@
 
 $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
@@ -340,17 +330,17 @@
 $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
 	mkdir -p $(BUILD_PATH)
 	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-	printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
+	printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
 	printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
 	touch $@
 
-$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
-	$(STRIP) -s $(IPROUTE2_PATH)/ip/ip
+$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+	$(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
+	$(STRIP) -s $@
 
-$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
-	$(STRIP) -s $(IPROUTE2_PATH)/misc/ss
+$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
+	$(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
+	$(STRIP) -s $@
 
 $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
 	mkdir -p $(BUILD_PATH)
@@ -358,8 +348,8 @@
 	sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
 	touch $@
 
-$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-	cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS)
+	cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include
 	$(MAKE) -C $(IPTABLES_PATH)
 	$(STRIP) -s $@
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index d656ebd..97fb2a4 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -179,18 +179,6 @@
 	return value;
 }
 
-/*
- * This function will return the VCPU that performed the MMIO access and
- * trapped from within the VM, and will return NULL if this is a userspace
- * access.
- *
- * We can disable preemption locally around accessing the per-CPU variable,
- * and use the resolved vcpu pointer after enabling preemption again, because
- * even if the current thread is migrated to another CPU, reading the per-CPU
- * value later will give us the same value as we update the per-CPU variable
- * in the preempt notifier handlers.
- */
-
 /* Must be called with irq->irq_lock held */
 static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 				 bool is_uaccess)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 67ae2d5..70f03ce 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4409,12 +4409,22 @@
 
 /**
  * kvm_get_running_vcpu - get the vcpu running on the current CPU.
- * Thanks to preempt notifiers, this can also be called from
- * preemptible context.
+ *
+ * We can disable preemption locally around accessing the per-CPU variable,
+ * and use the resolved vcpu pointer after enabling preemption again,
+ * because even if the current thread is migrated to another CPU, reading
+ * the per-CPU value later will give us the same value as we update the
+ * per-CPU variable in the preempt notifier handlers.
  */
 struct kvm_vcpu *kvm_get_running_vcpu(void)
 {
-        return __this_cpu_read(kvm_running_vcpu);
+	struct kvm_vcpu *vcpu;
+
+	preempt_disable();
+	vcpu = __this_cpu_read(kvm_running_vcpu);
+	preempt_enable();
+
+	return vcpu;
 }
 
 /**