Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Encap offset calculation is incorrect in esp6, from Sabrina Dubroca.

 2) Better parameter validation in pfkey_dump(), from Mark Salyzyn.

 3) Fix several clang issues on powerpc in selftests, from Tanner Love.

 4) cmsghdr_from_user_compat_to_kern() uses the wrong length, from Al
    Viro.

 5) Out of bounds access in mlx5e driver, from Raed Salem.

 6) Fix transfer buffer memleak in lan78xx, from Johan Havold.

 7) RCU fixups in rhashtable, from Herbert Xu.

 8) Fix ipv6 nexthop refcnt leak, from Xiyu Yang.

 9) vxlan FDB dump must be done under RCU, from Ido Schimmel.

10) Fix use after free in mlxsw, from Ido Schimmel.

11) Fix map leak in HASH_OF_MAPS bpf code, from Andrii Nakryiko.

12) Fix bug in mac80211 Tx ack status reporting, from Vasanthakumar
    Thiagarajan.

13) Fix memory leaks in IPV6_ADDRFORM code, from Cong Wang.

14) Fix bpf program reference count leaks in mlx5 during
    mlx5e_alloc_rq(), from Xin Xiong.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (86 commits)
  vxlan: fix memleak of fdb
  rds: Prevent kernel-infoleak in rds_notify_queue_get()
  net/sched: The error lable position is corrected in ct_init_module
  net/mlx5e: fix bpf_prog reference count leaks in mlx5e_alloc_rq
  net/mlx5e: E-Switch, Specify flow_source for rule with no in_port
  net/mlx5e: E-Switch, Add misc bit when misc fields changed for mirroring
  net/mlx5e: CT: Support restore ipv6 tunnel
  net: gemini: Fix missing clk_disable_unprepare() in error path of gemini_ethernet_port_probe()
  ionic: unlock queue mutex in error path
  atm: fix atm_dev refcnt leaks in atmtcp_remove_persistent
  net: ethernet: mtk_eth_soc: fix MTU warnings
  net: nixge: fix potential memory leak in nixge_probe()
  devlink: ignore -EOPNOTSUPP errors on dumpit
  rxrpc: Fix race between recvmsg and sendmsg on immediate call failure
  MAINTAINERS: Replace Thor Thayer as Altera Triple Speed Ethernet maintainer
  selftests/bpf: fix netdevsim trap_flow_action_cookie read
  ipv6: fix memory leaks on IPV6_ADDRFORM path
  net/bpfilter: Initialize pos in __bpfilter_process_sockopt
  igb: reinit_locked() should be called with rtnl_lock
  e1000e: continue to init PHY even when failed to disable ULP
  ...
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs
index f6d9c2a..2e9ae31 100644
--- a/Documentation/ABI/testing/debugfs-driver-habanalabs
+++ b/Documentation/ABI/testing/debugfs-driver-habanalabs
@@ -16,7 +16,16 @@
                 gating mechanism in Gaudi. Due to how Gaudi is built, the
                 clock gating needs to be disabled in order to access the
                 registers of the TPC and MME engines. This is sometimes needed
-                during debug by the user and hence the user needs this option
+                during debug by the user and hence the user needs this option.
+                The user can supply a bitmask value, each bit represents
+                a different engine to disable/enable its clock gating feature.
+                The bitmask is composed of 20 bits:
+                0  -  7 : DMA channels
+                8  - 11 : MME engines
+                12 - 19 : TPC engines
+                The bit's location of a specific engine can be determined
+                using (1 << GAUDI_ENGINE_ID_*). GAUDI_ENGINE_ID_* values
+                are defined in uapi habanalabs.h file in enum gaudi_engine_id
 
 What:           /sys/kernel/debug/habanalabs/hl<n>/command_buffers
 Date:           Jan 2019
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
index 526593c..4cc1a67 100644
--- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
+++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
@@ -47,6 +47,9 @@
     $ref: /schemas/types.yaml#/definitions/phandle-array
     description: Phandle to the device SRAM
 
+  iommus:
+    maxItems: 1
+
   memory-region:
     description:
       CMA pool to use for buffers allocation instead of the default
diff --git a/MAINTAINERS b/MAINTAINERS
index 9fb2328..4e2698c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1425,7 +1425,7 @@
 F:	arch/arm*/kernel/hw_breakpoint.c
 F:	arch/arm*/kernel/perf_*
 F:	arch/arm/oprofile/common.c
-F:	drivers/perf/*
+F:	drivers/perf/
 F:	include/linux/perf/arm_pmu.h
 
 ARM PORT
@@ -14188,7 +14188,8 @@
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
 
 QUALCOMM GENERIC INTERFACE I2C DRIVER
-M:	Alok Chauhan <alokc@codeaurora.org>
+M:	Akash Asthana <akashast@codeaurora.org>
+M:	Mukesh Savaliya <msavaliy@codeaurora.org>
 L:	linux-i2c@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Supported
diff --git a/Makefile b/Makefile
index 249a51d..229e67f 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -567,7 +567,7 @@
 ifneq ($(CROSS_COMPILE),)
 CLANG_FLAGS	+= --target=$(notdir $(CROSS_COMPILE:%-=%))
 GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
-CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)
+CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
 GCC_TOOLCHAIN	:= $(realpath $(GCC_TOOLCHAIN_DIR)/..)
 endif
 ifneq ($(GCC_TOOLCHAIN),)
@@ -1754,7 +1754,7 @@
 descend: $(build-dirs)
 $(build-dirs): prepare
 	$(Q)$(MAKE) $(build)=$@ \
-	single-build=$(if $(filter-out $@/, $(filter $@/%, $(single-no-ko))),1) \
+	single-build=$(if $(filter-out $@/, $(filter $@/%, $(KBUILD_SINGLE_TARGETS))),1) \
 	need-builtin=1 need-modorder=1
 
 clean-dirs := $(addprefix _clean_, $(clean-dirs))
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 3481165..9b1a24c 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -342,7 +342,8 @@
 
 			comphy: phy@18300 {
 				compatible = "marvell,armada-380-comphy";
-				reg = <0x18300 0x100>;
+				reg-names = "comphy", "conf";
+				reg = <0x18300 0x100>, <0x18460 4>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi
index 756f3a9..12997da 100644
--- a/arch/arm/boot/dts/imx6qdl-icore.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi
@@ -397,7 +397,7 @@
 
 	pinctrl_usbotg: usbotggrp {
 		fsl,pins = <
-			MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
 		>;
 	};
 
@@ -409,6 +409,7 @@
 			MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070
 			MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070
 			MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070
+			MX6QDL_PAD_GPIO_1__GPIO1_IO01  0x1b0b0
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 8259244..14fd1de 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -99,7 +99,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	fsl,magic-packet;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index 3e5fb72..c99aa27 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -213,7 +213,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy2>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts
index db640ba..8b3d64c 100644
--- a/arch/arm/boot/dts/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2g-evm.dts
@@ -402,7 +402,7 @@
 
 &gbe0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii-id";
+	phy-mode = "rgmii-rxid";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index bf531ef..0f95a6e 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -198,7 +198,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index e6b0367..c2b4fbf 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -117,7 +117,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index ffe1d10..6d6a379 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -181,7 +181,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index f44f448..1a3eedb 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -5,6 +5,8 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
+#include <asm/thread_info.h>
+
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
  * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 02ca7ad..7fff88e 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -683,6 +683,12 @@
 	arch_install_hw_breakpoint(bp);
 }
 
+static int watchpoint_fault_on_uaccess(struct pt_regs *regs,
+				       struct arch_hw_breakpoint *info)
+{
+	return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER;
+}
+
 static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 			       struct pt_regs *regs)
 {
@@ -742,16 +748,27 @@
 		}
 
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+
+		/*
+		 * If we triggered a user watchpoint from a uaccess routine,
+		 * then handle the stepping ourselves since userspace really
+		 * can't help us with this.
+		 */
+		if (watchpoint_fault_on_uaccess(regs, info))
+			goto step;
+
 		perf_bp_event(wp, regs);
 
 		/*
-		 * If no overflow handler is present, insert a temporary
-		 * mismatch breakpoint so we can single-step over the
-		 * watchpoint trigger.
+		 * Defer stepping to the overflow handler if one is installed.
+		 * Otherwise, insert a temporary mismatch breakpoint so that
+		 * we can single-step over the watchpoint trigger.
 		 */
-		if (is_default_overflow_handler(wp))
-			enable_single_step(wp, instruction_pointer(regs));
+		if (!is_default_overflow_handler(wp))
+			goto unlock;
 
+step:
+		enable_single_step(wp, instruction_pointer(regs));
 unlock:
 		rcu_read_unlock();
 	}
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 6bfdca4..fddd08a 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -184,6 +184,7 @@
 	if (!cntvct_ok) {
 		vdso_nullpatch_one(&einfo, "__vdso_gettimeofday");
 		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime");
+		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64");
 	}
 }
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 628028b..bcd8261 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -966,7 +966,7 @@
 	pud_t *pud;
 
 	p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
-	if (!WARN_ON(!p4d))
+	if (WARN_ON(!p4d))
 		return;
 	pud = pud_alloc(mm, p4d, md->virtual);
 	if (WARN_ON(!pud))
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 78b1361..9ce78a7 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -161,6 +161,7 @@
 			resets = <&ccu RST_BUS_VE>;
 			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 			allwinner,sram = <&ve_sram 1>;
+			iommus = <&iommu 3>;
 		};
 
 		gpu: gpu@1800000 {
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 12f0eb5..619db9b 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -77,9 +77,9 @@
 	"663:\n\t"							\
 	newinstr "\n"							\
 	"664:\n\t"							\
-	".previous\n\t"							\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
 	".endif\n"
 
 #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index b6f7bc6..93a161b 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -24,16 +24,17 @@
 {
 	__uint128_t tmp;
 	u64 sum;
+	int n = ihl; /* we want it signed */
 
 	tmp = *(const __uint128_t *)iph;
 	iph += 16;
-	ihl -= 4;
+	n -= 4;
 	tmp += ((tmp >> 64) | (tmp << 64));
 	sum = tmp >> 64;
 	do {
 		sum += *(const u32 *)iph;
 		iph += 4;
-	} while (--ihl);
+	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
 	return csum_fold((__force u32)(sum >> 32));
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index ea268d8..a0c8a0b 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -30,7 +30,6 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
-#include <asm/pointer_auth.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 118953d..6dd4171 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -212,6 +212,8 @@
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index ab5c215..0689585 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -60,6 +60,7 @@
 extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
 				   unsigned int new_);
 extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
@@ -71,6 +72,7 @@
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 70ffbcf..2e4d1f0 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -79,3 +79,15 @@
 	_atomic_spin_unlock_irqrestore(ptr, flags);
 	return (unsigned long)prev;
 }
+
+u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
+{
+	unsigned long flags;
+	u8 prev;
+
+	_atomic_spin_lock_irqsave(ptr, flags);
+	if ((prev = *ptr) == old)
+		*ptr = new;
+	_atomic_spin_unlock_irqrestore(ptr, flags);
+	return prev;
+}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0fc8bad..446e54c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -3072,10 +3072,18 @@
 	ori	r0,r0,DSISR_BAD_FAULT_64S@l
 	and.	r0,r5,r0		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
+
+	/*
+	 * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
+	 * don't call hash_page, just fail the fault. This is required to
+	 * prevent re-entrancy problems in the hash code, namely perf
+	 * interrupts hitting while something holds H_PAGE_BUSY, and taking a
+	 * hash fault. See the comment in hash_preload().
+	 */
 	ld	r11, PACA_THREAD_INFO(r13)
-	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
-	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
-	bne	77f			/* then don't call hash_page now */
+	lwz	r0,TI_PREEMPT(r11)
+	andis.	r0,r0,NMI_MASK@h
+	bne	77f
 
 	/*
 	 * r3 contains the trap number
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 468169e..9b9f92a 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1559,6 +1559,7 @@
 	pgd_t *pgdir;
 	int rc, ssize, update_flags = 0;
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0);
+	unsigned long flags;
 
 	BUG_ON(get_region_id(ea) != USER_REGION_ID);
 
@@ -1592,6 +1593,28 @@
 		return;
 #endif /* CONFIG_PPC_64K_PAGES */
 
+	/*
+	 * __hash_page_* must run with interrupts off, as it sets the
+	 * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any
+	 * time and may take a hash fault reading the user stack, see
+	 * read_user_stack_slow() in the powerpc/perf code.
+	 *
+	 * If that takes a hash fault on the same page as we lock here, it
+	 * will bail out when seeing H_PAGE_BUSY set, and retry the access
+	 * leading to an infinite loop.
+	 *
+	 * Disabling interrupts here does not prevent perf interrupts, but it
+	 * will prevent them taking hash faults (see the NMI test in
+	 * do_hash_page), then read_user_stack's copy_from_user_nofault will
+	 * fail and perf will fall back to read_user_stack_slow(), which
+	 * walks the Linux page tables.
+	 *
+	 * Interrupts must also be off for the duration of the
+	 * mm_is_thread_local test and update, to prevent preempt running the
+	 * mm on another CPU (XXX: this may be racy vs kthread_use_mm).
+	 */
+	local_irq_save(flags);
+
 	/* Is that local to this CPU ? */
 	if (mm_is_thread_local(mm))
 		update_flags |= HPTE_LOCAL_UPDATE;
@@ -1614,6 +1637,8 @@
 				   mm_ctx_user_psize(&mm->context),
 				   mm_ctx_user_psize(&mm->context),
 				   pte_val(*ptep));
+
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index cd6a742..01d7028 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2179,6 +2179,12 @@
 
 	perf_read_regs(regs);
 
+	/*
+	 * If perf interrupts hit in a local_irq_disable (soft-masked) region,
+	 * we consider them as NMIs. This is required to prevent hash faults on
+	 * user addresses when reading callchains. See the NMI test in
+	 * do_hash_page.
+	 */
 	nmi = perf_intr_is_nmi(regs);
 	if (nmi)
 		nmi_enter();
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 22d968b..d770da3 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -12,6 +12,7 @@
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
 extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
 extern void pmd_free(struct mm_struct *mm, pmd_t *pmd);
+#define __pmd_free_tlb(tlb, pmdp, addr)		pmd_free((tlb)->mm, (pmdp))
 #endif
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -33,13 +34,4 @@
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
-#if CONFIG_PGTABLE_LEVELS > 2
-#define __pmd_free_tlb(tlb, pmdp, addr)			\
-do {							\
-	struct page *page = virt_to_page(pmdp);		\
-	pgtable_pmd_page_dtor(page);			\
-	tlb_remove_page((tlb), page);			\
-} while (0);
-#endif
-
 #endif /* __ASM_SH_PGALLOC_H */
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 956a7a0..9bac5bb 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -199,7 +199,7 @@
 	mov.l	@(OFF_R7,r15), r7   ! arg3
 	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
 	!
-	mov.l	2f, r10			! Number of syscalls
+	mov.l	6f, r10			! Number of syscalls
 	cmp/hs	r10, r3
 	bf	syscall_call
 	mov	#-ENOSYS, r0
@@ -353,7 +353,7 @@
 	tst	r9, r8
 	bf	syscall_trace_entry
 	!
-	mov.l	2f, r8			! Number of syscalls
+	mov.l	6f, r8			! Number of syscalls
 	cmp/hs	r8, r3
 	bt	syscall_badsys
 	!
@@ -392,7 +392,7 @@
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
 #endif
-2:	.long	NR_syscalls
+6:	.long	NR_syscalls
 3:	.long	sys_call_table
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 42c672f..cbe6aa7 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -947,7 +947,7 @@
 		trace_binder_unmap_user_end(alloc, index);
 	}
 	mmap_read_unlock(mm);
-	mmput(mm);
+	mmput_async(mm);
 
 	trace_binder_unmap_kernel_start(alloc, index);
 
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 1e6d75e..d58aa98 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -721,7 +721,7 @@
 		return next;
 
 	/* When no more children in primary, continue with secondary */
-	if (!IS_ERR_OR_NULL(fwnode->secondary))
+	if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary))
 		next = fwnode_get_next_child_node(fwnode->secondary, child);
 
 	return next;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 934c92d..687d4af 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -814,7 +814,8 @@
 #ifdef CONFIG_IO_STRICT_DEVMEM
 void revoke_devmem(struct resource *res)
 {
-	struct inode *inode = READ_ONCE(devmem_inode);
+	/* pairs with smp_store_release() in devmem_init_inode() */
+	struct inode *inode = smp_load_acquire(&devmem_inode);
 
 	/*
 	 * Check that the initialization has completed. Losing the race
@@ -1028,8 +1029,11 @@
 		return rc;
 	}
 
-	/* publish /dev/mem initialized */
-	WRITE_ONCE(devmem_inode, inode);
+	/*
+	 * Publish /dev/mem initialized.
+	 * Pairs with smp_load_acquire() in revoke_devmem().
+	 */
+	smp_store_release(&devmem_inode, inode);
 
 	return 0;
 }
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2a41b21..d20ba1b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1277,6 +1277,7 @@
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
+	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 039e0f9..6945c3c 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -605,8 +605,10 @@
 	/* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */
 	err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype,
 				   fw_cfg_sel_ko, "%d", entry->select);
-	if (err)
-		goto err_register;
+	if (err) {
+		kobject_put(&entry->kobj);
+		return err;
+	}
 
 	/* add raw binary content access */
 	err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw);
@@ -622,7 +624,6 @@
 
 err_add_raw:
 	kobject_del(&entry->kobj);
-err_register:
 	kfree(entry);
 	return err;
 }
diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c
index b0c3178..3fa2c59 100644
--- a/drivers/fpga/dfl-afu-main.c
+++ b/drivers/fpga/dfl-afu-main.c
@@ -83,7 +83,8 @@
 	 * on this port and minimum soft reset pulse width has elapsed.
 	 * Driver polls port_soft_reset_ack to determine if reset done by HW.
 	 */
-	if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST,
+	if (readq_poll_timeout(base + PORT_HDR_CTRL, v,
+			       v & PORT_CTRL_SFTRST_ACK,
 			       RST_POLL_INVL, RST_POLL_TIMEOUT)) {
 		dev_err(&pdev->dev, "timeout, fail to reset device\n");
 		return -ETIMEDOUT;
diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c
index 5387550..a78c409 100644
--- a/drivers/fpga/dfl-pci.c
+++ b/drivers/fpga/dfl-pci.c
@@ -227,7 +227,6 @@
 {
 	struct cci_drvdata *drvdata = pci_get_drvdata(pcidev);
 	struct dfl_fpga_cdev *cdev = drvdata->cdev;
-	int ret = 0;
 
 	if (!num_vfs) {
 		/*
@@ -239,6 +238,8 @@
 		dfl_fpga_cdev_config_ports_pf(cdev);
 
 	} else {
+		int ret;
+
 		/*
 		 * before enable SRIOV, put released ports into VF access mode
 		 * first of all.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index d7e17e3..2129209 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -692,9 +692,10 @@
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info = {};
+		struct drm_amdgpu_info_device dev_info;
 		uint64_t vm_size;
 
+		memset(&dev_info, 0, sizeof(dev_info));
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
 		dev_info.external_rev = adev->external_rev_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index ebb8a28..02e6f8c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -778,7 +778,8 @@
 		tmp_str++;
 	while (isspace(*++tmp_str));
 
-	while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) {
+	while (tmp_str[0]) {
+		sub_str = strsep(&tmp_str, delimiter);
 		ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
 		if (ret)
 			return -EINVAL;
@@ -1038,7 +1039,8 @@
 	memcpy(buf_cpy, buf, bytes);
 	buf_cpy[bytes] = '\0';
 	tmp = buf_cpy;
-	while ((sub_str = strsep(&tmp, delimiter)) != NULL) {
+	while (tmp[0]) {
+		sub_str = strsep(&tmp, delimiter);
 		if (strlen(sub_str)) {
 			ret = kstrtol(sub_str, 0, &level);
 			if (ret)
@@ -1635,7 +1637,8 @@
 			i++;
 		memcpy(buf_cpy, buf, count-i);
 		tmp_str = buf_cpy;
-		while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) {
+		while (tmp_str[0]) {
+			sub_str = strsep(&tmp_str, delimiter);
 			ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
 			if (ret)
 				return -EINVAL;
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 86ffa0c..710edc7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8717,20 +8717,38 @@
 		 * the same resource. If we have a new DC context as part of
 		 * the DM atomic state from validation we need to free it and
 		 * retain the existing one instead.
+		 *
+		 * Furthermore, since the DM atomic state only contains the DC
+		 * context and can safely be annulled, we can free the state
+		 * and clear the associated private object now to free
+		 * some memory and avoid a possible use-after-free later.
 		 */
-		struct dm_atomic_state *new_dm_state, *old_dm_state;
 
-		new_dm_state = dm_atomic_get_new_state(state);
-		old_dm_state = dm_atomic_get_old_state(state);
+		for (i = 0; i < state->num_private_objs; i++) {
+			struct drm_private_obj *obj = state->private_objs[i].ptr;
 
-		if (new_dm_state && old_dm_state) {
-			if (new_dm_state->context)
-				dc_release_state(new_dm_state->context);
+			if (obj->funcs == adev->dm.atomic_obj.funcs) {
+				int j = state->num_private_objs-1;
 
-			new_dm_state->context = old_dm_state->context;
+				dm_atomic_destroy_state(obj,
+						state->private_objs[i].state);
 
-			if (old_dm_state->context)
-				dc_retain_state(old_dm_state->context);
+				/* If i is not at the end of the array then the
+				 * last element needs to be moved to where i was
+				 * before the array can safely be truncated.
+				 */
+				if (i != j)
+					state->private_objs[i] =
+						state->private_objs[j];
+
+				state->private_objs[j].ptr = NULL;
+				state->private_objs[j].state = NULL;
+				state->private_objs[j].old_state = NULL;
+				state->private_objs[j].new_state = NULL;
+
+				state->num_private_objs = j;
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 05d8373..079f46f 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -146,6 +146,7 @@
 	bochs->dev->mode_config.preferred_depth = 24;
 	bochs->dev->mode_config.prefer_shadow = 0;
 	bochs->dev->mode_config.prefer_shadow_fbdev = 1;
+	bochs->dev->mode_config.fbdev_use_iomem = true;
 	bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
 
 	bochs->dev->mode_config.funcs = &bochs_mode_funcs;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 87b58c1..648eb23d 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -1224,6 +1224,7 @@
 
 	adv7511->bridge.funcs = &adv7511_bridge_funcs;
 	adv7511->bridge.of_node = dev->of_node;
+	adv7511->bridge.type = DRM_MODE_CONNECTOR_HDMIA;
 
 	drm_bridge_add(&adv7511->bridge);
 
diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c
index b14d725..c7bc194 100644
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@@ -917,11 +917,6 @@
 	struct drm_panel *panel;
 	int ret;
 
-	if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) {
-		DRM_ERROR("Fix bridge driver to make connector optional!");
-		return -EINVAL;
-	}
-
 	ret = drm_of_find_panel_or_bridge(dsi->dev->of_node, 1, 0, &panel,
 					  &panel_bridge);
 	if (ret)
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 5609e16..89cfd68 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -399,7 +399,11 @@
 	unsigned int y;
 
 	for (y = clip->y1; y < clip->y2; y++) {
-		memcpy(dst, src, len);
+		if (!fb_helper->dev->mode_config.fbdev_use_iomem)
+			memcpy(dst, src, len);
+		else
+			memcpy_toio((void __iomem *)dst, src, len);
+
 		src += fb->pitches[0];
 		dst += fb->pitches[0];
 	}
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 7bf628e..ee2058a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -871,9 +871,6 @@
  * @file_priv: drm file-private structure
  *
  * Open an object using the global name, returning a handle and the size.
- *
- * This handle (of course) holds a reference to the object, so the object
- * will not go away until the handle is deleted.
  */
 int
 drm_gem_open_ioctl(struct drm_device *dev, void *data,
@@ -898,14 +895,15 @@
 
 	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
 	ret = drm_gem_handle_create_tail(file_priv, obj, &handle);
-	drm_gem_object_put_unlocked(obj);
 	if (ret)
-		return ret;
+		goto err;
 
 	args->handle = handle;
 	args->size = obj->size;
 
-	return 0;
+err:
+	drm_gem_object_put_unlocked(obj);
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index bb27c82..bf7888a 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -923,7 +923,7 @@
 			}
 		}
 
-		tr.len = chunk;
+		tr.len = chunk * 2;
 		len -= chunk;
 
 		ret = spi_sync(spi, &m);
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index b50b44e..8fc3f67 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -322,10 +322,8 @@
 		 * configurations by passing the endpoints explicitly to
 		 * drm_of_lvds_get_dual_link_pixel_order().
 		 */
-		if (!current_pt || pixels_type != current_pt) {
-			of_node_put(remote_port);
+		if (!current_pt || pixels_type != current_pt)
 			return -EINVAL;
-		}
 	}
 
 	return pixels_type;
diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c
index 08802e5..4d2290f 100644
--- a/drivers/gpu/drm/mcde/mcde_display.c
+++ b/drivers/gpu/drm/mcde/mcde_display.c
@@ -1060,9 +1060,14 @@
 	 */
 	if (fb) {
 		mcde_set_extsrc(mcde, drm_fb_cma_get_gem_addr(fb, pstate, 0));
-		if (!mcde->video_mode)
-			/* Send a single frame using software sync */
-			mcde_display_send_one_frame(mcde);
+		if (!mcde->video_mode) {
+			/*
+			 * Send a single frame using software sync if the flow
+			 * is not active yet.
+			 */
+			if (mcde->flow_active == 0)
+				mcde_display_send_one_frame(mcde);
+		}
 		dev_info_once(mcde->dev, "sent first display update\n");
 	} else {
 		/*
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 519f998..800b775 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2073,7 +2073,7 @@
 	 */
 	if (core->assign_windows) {
 		core->func->wndw.owner(core);
-		core->func->update(core, interlock, false);
+		nv50_disp_atomic_commit_core(state, interlock);
 		core->assign_windows = false;
 		interlock[NV50_DISP_INTERLOCK_CORE] = 0;
 	}
@@ -2506,7 +2506,7 @@
 	if (disp->disp->object.oclass >= TU102_DISP)
 		nouveau_display(dev)->format_modifiers = wndwc57e_modifiers;
 	else
-	if (disp->disp->object.oclass >= GF110_DISP)
+	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI)
 		nouveau_display(dev)->format_modifiers = disp90xx_modifiers;
 	else
 		nouveau_display(dev)->format_modifiers = disp50xx_modifiers;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 496c462..07373bb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -191,6 +191,7 @@
 		   uint32_t *tile_mode,
 		   uint8_t *kind)
 {
+	struct nouveau_display *disp = nouveau_display(drm->dev);
 	BUG_ON(!tile_mode || !kind);
 
 	if (modifier == DRM_FORMAT_MOD_LINEAR) {
@@ -202,6 +203,12 @@
 		 * Extract the block height and kind from the corresponding
 		 * modifier fields.  See drm_fourcc.h for details.
 		 */
+
+		if ((modifier & (0xffull << 12)) == 0ull) {
+			/* Legacy modifier.  Translate to this dev's 'kind.' */
+			modifier |= disp->format_modifiers[0] & (0xffull << 12);
+		}
+
 		*tile_mode = (uint32_t)(modifier & 0xF);
 		*kind = (uint8_t)((modifier >> 12) & 0xFF);
 
@@ -227,6 +234,16 @@
 	}
 }
 
+static const u64 legacy_modifiers[] = {
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0),
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1),
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2),
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3),
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4),
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5),
+	DRM_FORMAT_MOD_INVALID
+};
+
 static int
 nouveau_validate_decode_mod(struct nouveau_drm *drm,
 			    uint64_t modifier,
@@ -247,8 +264,14 @@
 	     (disp->format_modifiers[mod] != modifier);
 	     mod++);
 
-	if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID)
-		return -EINVAL;
+	if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) {
+		for (mod = 0;
+		     (legacy_modifiers[mod] != DRM_FORMAT_MOD_INVALID) &&
+		     (legacy_modifiers[mod] != modifier);
+		     mod++);
+		if (legacy_modifiers[mod] == DRM_FORMAT_MOD_INVALID)
+			return -EINVAL;
+	}
 
 	nouveau_decode_mod(drm, modifier, tile_mode, kind);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 3d11b84..d5c23d1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -315,7 +315,7 @@
 	struct drm_framebuffer *fb;
 	struct nouveau_channel *chan;
 	struct nouveau_bo *nvbo;
-	struct drm_mode_fb_cmd2 mode_cmd;
+	struct drm_mode_fb_cmd2 mode_cmd = {};
 	int ret;
 
 	mode_cmd.width = sizes->surface_width;
@@ -590,6 +590,7 @@
 	drm_fb_helper_fini(&fbcon->helper);
 free:
 	kfree(fbcon);
+	drm->fbcon = NULL;
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
index dcf0824..dffcac24 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
@@ -117,15 +117,6 @@
 {
 	struct nvkm_ior *ior;
 
-	/* First preference is to reuse the OR that is currently armed
-	 * on HW, if any, in order to prevent unnecessary switching.
-	 */
-	list_for_each_entry(ior, &outp->disp->ior, head) {
-		if (!ior->identity && !!ior->func->hda.hpd == hda &&
-		    !ior->asy.outp && ior->arm.outp == outp)
-			return nvkm_outp_acquire_ior(outp, user, ior);
-	}
-
 	/* Failing that, a completely unused OR is the next best thing. */
 	list_for_each_entry(ior, &outp->disp->ior, head) {
 		if (!ior->identity && !!ior->func->hda.hpd == hda &&
@@ -173,6 +164,27 @@
 		return nvkm_outp_acquire_ior(outp, user, ior);
 	}
 
+	/* First preference is to reuse the OR that is currently armed
+	 * on HW, if any, in order to prevent unnecessary switching.
+	 */
+	list_for_each_entry(ior, &outp->disp->ior, head) {
+		if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) {
+			/*XXX: For various complicated reasons, we can't outright switch
+			 *     the boot-time OR on the first modeset without some fairly
+			 *     invasive changes.
+			 *
+			 *     The systems that were fixed by modifying the OR selection
+			 *     code to account for HDA support shouldn't regress here as
+			 *     the HDA-enabled ORs match the relevant output's pad macro
+			 *     index, and the firmware seems to select an OR this way.
+			 *
+			 *     This warning is to make it obvious if that proves wrong.
+			 */
+			WARN_ON(hda && !ior->func->hda.hpd);
+			return nvkm_outp_acquire_ior(outp, user, ior);
+		}
+	}
+
 	/* If we don't need HDA, first try to acquire an OR that doesn't
 	 * support it to leave free the ones that do.
 	 */
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index 46fe180..2649469 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -615,9 +615,9 @@
 static const struct drm_display_mode auo_kd101n80_45na_default_mode = {
 	.clock = 157000,
 	.hdisplay = 1200,
-	.hsync_start = 1200 + 80,
-	.hsync_end = 1200 + 80 + 24,
-	.htotal = 1200 + 80 + 24 + 36,
+	.hsync_start = 1200 + 60,
+	.hsync_end = 1200 + 60 + 24,
+	.htotal = 1200 + 60 + 24 + 56,
 	.vdisplay = 1920,
 	.vsync_start = 1920 + 16,
 	.vsync_end = 1920 + 16 + 4,
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 5178f87..4aeb960 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1250,7 +1250,21 @@
 		.height = 165,
 	},
 	.delay = {
-		.hpd_absent_delay = 200,
+		/*
+		 * When power is first given to the panel there's a short
+		 * spike on the HPD line.  It was explained that this spike
+		 * was until the TCON data download was complete.  On
+		 * one system this was measured at 8 ms.  We'll put 15 ms
+		 * in the prepare delay just to be safe and take it away
+		 * from the hpd_absent_delay (which would otherwise be 200 ms)
+		 * to handle this.  That means:
+		 * - If HPD isn't hooked up you still have 200 ms delay.
+		 * - If HPD is hooked up we won't try to look at it for the
+		 *   first 15 ms.
+		 */
+		.prepare = 15,
+		.hpd_absent_delay = 185,
+
 		.unprepare = 500,
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c
index 5427f04..1589179 100644
--- a/drivers/i2c/i2c-core-slave.c
+++ b/drivers/i2c/i2c-core-slave.c
@@ -18,10 +18,8 @@
 {
 	int ret;
 
-	if (!client || !slave_cb) {
-		WARN(1, "insufficient data\n");
+	if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n"))
 		return -EINVAL;
-	}
 
 	if (!(client->flags & I2C_CLIENT_SLAVE))
 		dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n",
@@ -60,6 +58,9 @@
 {
 	int ret;
 
+	if (IS_ERR_OR_NULL(client))
+		return -EINVAL;
+
 	if (!client->adapter->algo->unreg_slave) {
 		dev_err(&client->dev, "%s: not supported by adapter\n", __func__);
 		return -EOPNOTSUPP;
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 655795b..513825e 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -72,6 +72,15 @@
 	INIT_WORK(&dim->work, ib_cq_rdma_dim_work);
 }
 
+static void rdma_dim_destroy(struct ib_cq *cq)
+{
+	if (!cq->dim)
+		return;
+
+	cancel_work_sync(&cq->dim->work);
+	kfree(cq->dim);
+}
+
 static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc)
 {
 	int rc;
@@ -266,6 +275,7 @@
 	return cq;
 
 out_destroy_cq:
+	rdma_dim_destroy(cq);
 	rdma_restrack_del(&cq->res);
 	cq->device->ops.destroy_cq(cq, udata);
 out_free_wc:
@@ -331,12 +341,10 @@
 		WARN_ON_ONCE(1);
 	}
 
+	rdma_dim_destroy(cq);
 	trace_cq_free(cq);
 	rdma_restrack_del(&cq->res);
 	cq->device->ops.destroy_cq(cq, udata);
-	if (cq->dim)
-		cancel_work_sync(&cq->dim->work);
-	kfree(cq->dim);
 	kfree(cq->wc);
 	kfree(cq);
 }
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 5b87eee..d03daca 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1084,6 +1084,8 @@
 	size_t in_size;
 	int ret;
 
+	if (in_len < offsetofend(typeof(cmd), reserved))
+		return -EINVAL;
 	in_size = min_t(size_t, in_len, sizeof(cmd));
 	if (copy_from_user(&cmd, inbuf, in_size))
 		return -EFAULT;
@@ -1141,6 +1143,8 @@
 	size_t in_size;
 	int ret;
 
+	if (in_len < offsetofend(typeof(cmd), reserved))
+		return -EINVAL;
 	in_size = min_t(size_t, in_len, sizeof(cmd));
 	if (copy_from_user(&cmd, inbuf, in_size))
 		return -EFAULT;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 1ab676b6..77dca1e 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -1797,9 +1797,7 @@
 		work->frags[i].mr =
 			get_prefetchable_mr(pd, advice, sg_list[i].lkey);
 		if (!work->frags[i].mr) {
-			work->num_sge = i - 1;
-			if (i)
-				destroy_prefetch_work(work);
+			work->num_sge = i;
 			return false;
 		}
 
@@ -1865,6 +1863,7 @@
 	srcu_key = srcu_read_lock(&dev->odp_srcu);
 	if (!init_prefetch_work(pd, advice, pf_flags, work, sg_list, num_sge)) {
 		srcu_read_unlock(&dev->odp_srcu, srcu_key);
+		destroy_prefetch_work(work);
 		return -EINVAL;
 	}
 	queue_work(system_unbound_wq, &work->work);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index e050ead..1225b8d 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1766,15 +1766,14 @@
 }
 
 static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,
+					 struct mlx5_ib_qp *qp,
 					 struct ib_qp_init_attr *init_attr,
-					 struct mlx5_ib_create_qp *ucmd,
 					 void *qpc)
 {
 	int scqe_sz;
 	bool allow_scat_cqe = false;
 
-	if (ucmd)
-		allow_scat_cqe = ucmd->flags & MLX5_QP_FLAG_ALLOW_SCATTER_CQE;
+	allow_scat_cqe = qp->flags_en & MLX5_QP_FLAG_ALLOW_SCATTER_CQE;
 
 	if (!allow_scat_cqe && init_attr->sq_sig_type != IB_SIGNAL_ALL_WR)
 		return;
@@ -1853,8 +1852,6 @@
 	u32 *in;
 	int err;
 
-	mutex_init(&qp->mutex);
-
 	if (attr->sq_sig_type == IB_SIGNAL_ALL_WR)
 		qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE;
 
@@ -1938,7 +1935,6 @@
 	u32 *in;
 	int err;
 
-	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 
@@ -2012,7 +2008,7 @@
 	}
 	if ((qp->flags_en & MLX5_QP_FLAG_SCATTER_CQE) &&
 	    (qp->type == MLX5_IB_QPT_DCI || qp->type == IB_QPT_RC))
-		configure_requester_scat_cqe(dev, init_attr, ucmd, qpc);
+		configure_requester_scat_cqe(dev, qp, init_attr, qpc);
 
 	if (qp->rq.wqe_cnt) {
 		MLX5_SET(qpc, qpc, log_rq_stride, qp->rq.wqe_shift - 4);
@@ -2129,7 +2125,6 @@
 	u32 *in;
 	int err;
 
-	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 
@@ -2543,13 +2538,18 @@
 		return;
 	}
 
-	if (flag == MLX5_QP_FLAG_SCATTER_CQE) {
+	switch (flag) {
+	case MLX5_QP_FLAG_SCATTER_CQE:
+	case MLX5_QP_FLAG_ALLOW_SCATTER_CQE:
 		/*
-		 * We don't return error if this flag was provided,
-		 * and mlx5 doesn't have right capability.
-		 */
-		*flags &= ~MLX5_QP_FLAG_SCATTER_CQE;
+			 * We don't return error if these flags were provided,
+			 * and mlx5 doesn't have right capability.
+			 */
+		*flags &= ~(MLX5_QP_FLAG_SCATTER_CQE |
+			    MLX5_QP_FLAG_ALLOW_SCATTER_CQE);
 		return;
+	default:
+		break;
 	}
 	mlx5_ib_dbg(dev, "Vendor create QP flag 0x%X is not supported\n", flag);
 }
@@ -2589,6 +2589,8 @@
 	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SIGNATURE, true, qp);
 	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SCATTER_CQE,
 			    MLX5_CAP_GEN(mdev, sctr_data_cqe), qp);
+	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_ALLOW_SCATTER_CQE,
+			    MLX5_CAP_GEN(mdev, sctr_data_cqe), qp);
 
 	if (qp->type == IB_QPT_RAW_PACKET) {
 		cond = MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) ||
@@ -2963,6 +2965,7 @@
 		goto free_ucmd;
 	}
 
+	mutex_init(&qp->mutex);
 	qp->type = type;
 	if (udata) {
 		err = process_vendor_flags(dev, qp, params.ucmd, attr);
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 7db35dd..332a8ba 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -901,8 +901,6 @@
 	qp->s_tail_ack_queue = 0;
 	qp->s_acked_ack_queue = 0;
 	qp->s_num_rd_atomic = 0;
-	if (qp->r_rq.kwq)
-		qp->r_rq.kwq->count = qp->r_rq.size;
 	qp->r_sge.num_sge = 0;
 	atomic_set(&qp->s_reserved_used, 0);
 }
@@ -2367,31 +2365,6 @@
 }
 
 /**
- * get_count - count numbers of request work queue entries
- * in circular buffer
- * @rq: data structure for request queue entry
- * @tail: tail indices of the circular buffer
- * @head: head indices of the circular buffer
- *
- * Return - total number of entries in the circular buffer
- */
-static u32 get_count(struct rvt_rq *rq, u32 tail, u32 head)
-{
-	u32 count;
-
-	count = head;
-
-	if (count >= rq->size)
-		count = 0;
-	if (count < tail)
-		count += rq->size - tail;
-	else
-		count -= tail;
-
-	return count;
-}
-
-/**
  * get_rvt_head - get head indices of the circular buffer
  * @rq: data structure for request queue entry
  * @ip: the QP
@@ -2465,7 +2438,7 @@
 
 	if (kwq->count < RVT_RWQ_COUNT_THRESHOLD) {
 		head = get_rvt_head(rq, ip);
-		kwq->count = get_count(rq, tail, head);
+		kwq->count = rvt_get_rq_count(rq, head, tail);
 	}
 	if (unlikely(kwq->count == 0)) {
 		ret = 0;
@@ -2500,7 +2473,9 @@
 		 * the number of remaining WQEs.
 		 */
 		if (kwq->count < srq->limit) {
-			kwq->count = get_count(rq, tail, get_rvt_head(rq, ip));
+			kwq->count =
+				rvt_get_rq_count(rq,
+						 get_rvt_head(rq, ip), tail);
 			if (kwq->count < srq->limit) {
 				struct ib_event ev;
 
diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c
index 977906c..c58735f 100644
--- a/drivers/infiniband/sw/rdmavt/rc.c
+++ b/drivers/infiniband/sw/rdmavt/rc.c
@@ -127,9 +127,7 @@
 			 * not atomic, which is OK, since the fuzziness is
 			 * resolved as further ACKs go out.
 			 */
-			credits = head - tail;
-			if ((int)credits < 0)
-				credits += qp->r_rq.size;
+			credits = rvt_get_rq_count(&qp->r_rq, head, tail);
 		}
 		/*
 		 * Binary search the credit table to find the code to
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index e5f9987..9e1ab70 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -243,6 +243,7 @@
 {
 	struct icc_provider *p = node->provider;
 	struct icc_req *r;
+	u32 avg_bw, peak_bw;
 
 	node->avg_bw = 0;
 	node->peak_bw = 0;
@@ -251,9 +252,14 @@
 		p->pre_aggregate(node);
 
 	hlist_for_each_entry(r, &node->req_list, req_node) {
-		if (!r->enabled)
-			continue;
-		p->aggregate(node, r->tag, r->avg_bw, r->peak_bw,
+		if (r->enabled) {
+			avg_bw = r->avg_bw;
+			peak_bw = r->peak_bw;
+		} else {
+			avg_bw = 0;
+			peak_bw = 0;
+		}
+		p->aggregate(node, r->tag, avg_bw, peak_bw,
 			     &node->avg_bw, &node->peak_bw);
 	}
 
diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c
index e94f3c5..42c6c55 100644
--- a/drivers/interconnect/qcom/msm8916.c
+++ b/drivers/interconnect/qcom/msm8916.c
@@ -197,13 +197,13 @@
 DEFINE_QNODE(pcnoc_int_1, MSM8916_PNOC_INT_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS);
 DEFINE_QNODE(pcnoc_m_0, MSM8916_PNOC_MAS_0, 8, -1, -1, MSM8916_PNOC_INT_0);
 DEFINE_QNODE(pcnoc_m_1, MSM8916_PNOC_MAS_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS);
-DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 8, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS);
-DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 8, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG);
-DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 8, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB);
-DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 8, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG);
-DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 8, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG);
-DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 8, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1);
-DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 8, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG);
+DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 4, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS);
+DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 4, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG);
+DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 4, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB);
+DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 4, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG);
+DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 4, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG);
+DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 4, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1);
+DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 4, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG);
 DEFINE_QNODE(pcnoc_snoc_mas, MSM8916_PNOC_SNOC_MAS, 8, 29, -1, MSM8916_PNOC_SNOC_SLV);
 DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1);
 DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC);
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index b0f62cb..f3a8f11 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -499,11 +499,19 @@
 	struct asic_fixed_properties *asic = &hdev->asic_prop;
 	struct hw_queue_properties *hw_queue_prop;
 
+	/* This must be checked here to prevent out-of-bounds access to
+	 * hw_queues_props array
+	 */
+	if (chunk->queue_index >= HL_MAX_QUEUES) {
+		dev_err(hdev->dev, "Queue index %d is invalid\n",
+			chunk->queue_index);
+		return -EINVAL;
+	}
+
 	hw_queue_prop = &asic->hw_queues_props[chunk->queue_index];
 
-	if ((chunk->queue_index >= HL_MAX_QUEUES) ||
-			(hw_queue_prop->type == QUEUE_TYPE_NA)) {
-		dev_err(hdev->dev, "Queue index %d is invalid\n",
+	if (hw_queue_prop->type == QUEUE_TYPE_NA) {
+		dev_err(hdev->dev, "Queue index %d is not applicable\n",
 			chunk->queue_index);
 		return -EINVAL;
 	}
diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index fc4372c..0bc036e 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/drivers/misc/habanalabs/debugfs.c
@@ -36,7 +36,7 @@
 	pkt.i2c_reg = i2c_reg;
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					HL_DEVICE_TIMEOUT_USEC, (long *) val);
+						0, (long *) val);
 
 	if (rc)
 		dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc);
@@ -63,7 +63,7 @@
 	pkt.value = cpu_to_le64(val);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					HL_DEVICE_TIMEOUT_USEC, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev, "Failed to write to I2C, error %d\n", rc);
@@ -87,7 +87,7 @@
 	pkt.value = cpu_to_le64(state);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						HL_DEVICE_TIMEOUT_USEC, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev, "Failed to set LED %d, error %d\n", led, rc);
@@ -981,7 +981,7 @@
 	if (*ppos)
 		return 0;
 
-	sprintf(tmp_buf, "%d\n", hdev->clock_gating);
+	sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask);
 	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
 			strlen(tmp_buf) + 1);
 
@@ -993,7 +993,7 @@
 {
 	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
 	struct hl_device *hdev = entry->hdev;
-	u32 value;
+	u64 value;
 	ssize_t rc;
 
 	if (atomic_read(&hdev->in_reset)) {
@@ -1002,19 +1002,12 @@
 		return 0;
 	}
 
-	rc = kstrtouint_from_user(buf, count, 10, &value);
+	rc = kstrtoull_from_user(buf, count, 16, &value);
 	if (rc)
 		return rc;
 
-	if (value) {
-		hdev->clock_gating = 1;
-		if (hdev->asic_funcs->enable_clock_gating)
-			hdev->asic_funcs->enable_clock_gating(hdev);
-	} else {
-		if (hdev->asic_funcs->disable_clock_gating)
-			hdev->asic_funcs->disable_clock_gating(hdev);
-		hdev->clock_gating = 0;
-	}
+	hdev->clock_gating_mask = value;
+	hdev->asic_funcs->set_clock_gating(hdev);
 
 	return count;
 }
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 2b38a11..59608d1b 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -608,7 +608,7 @@
 		hdev->in_debug = 0;
 
 		if (!hdev->hard_reset_pending)
-			hdev->asic_funcs->enable_clock_gating(hdev);
+			hdev->asic_funcs->set_clock_gating(hdev);
 
 		goto out;
 	}
diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c
index baf790c..d27841c 100644
--- a/drivers/misc/habanalabs/firmware_if.c
+++ b/drivers/misc/habanalabs/firmware_if.c
@@ -61,7 +61,7 @@
 	pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT);
 
 	return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt,
-				sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL);
+						sizeof(pkt), 0, NULL);
 }
 
 int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
@@ -144,7 +144,7 @@
 	pkt.value = cpu_to_le64(event_type);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-			HL_DEVICE_TIMEOUT_USEC, &result);
+						0, &result);
 
 	if (rc)
 		dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type);
@@ -183,7 +183,7 @@
 						ARMCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt,
-			total_pkt_size, HL_DEVICE_TIMEOUT_USEC, &result);
+						total_pkt_size, 0, &result);
 
 	if (rc)
 		dev_err(hdev->dev, "failed to unmask IRQ array\n");
@@ -204,7 +204,7 @@
 	test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt,
-			sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
+						sizeof(test_pkt), 0, &result);
 
 	if (!rc) {
 		if (result != ARMCP_PACKET_FENCE_VAL)
@@ -248,7 +248,7 @@
 	hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt,
-			sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
+						sizeof(hb_pkt), 0, &result);
 
 	if ((rc) || (result != ARMCP_PACKET_FENCE_VAL))
 		rc = -EIO;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 834470d..637a9d6 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -80,6 +80,7 @@
 #define GAUDI_PLDM_QMAN0_TIMEOUT_USEC	(HL_DEVICE_TIMEOUT_USEC * 30)
 #define GAUDI_PLDM_TPC_KERNEL_WAIT_USEC	(HL_DEVICE_TIMEOUT_USEC * 30)
 #define GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC	1000000		/* 1s */
+#define GAUDI_MSG_TO_CPU_TIMEOUT_USEC	4000000		/* 4s */
 
 #define GAUDI_QMAN0_FENCE_VAL		0x72E91AB9
 
@@ -98,6 +99,11 @@
 
 #define GAUDI_ARB_WDT_TIMEOUT		0x1000000
 
+#define GAUDI_CLK_GATE_DEBUGFS_MASK	(\
+		BIT(GAUDI_ENGINE_ID_MME_0) |\
+		BIT(GAUDI_ENGINE_ID_MME_2) |\
+		GENMASK_ULL(GAUDI_ENGINE_ID_TPC_7, GAUDI_ENGINE_ID_TPC_0))
+
 static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
 		"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
 		"gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3",
@@ -106,14 +112,14 @@
 };
 
 static const u8 gaudi_dma_assignment[GAUDI_DMA_MAX] = {
-	[GAUDI_PCI_DMA_1] = 0,
-	[GAUDI_PCI_DMA_2] = 1,
-	[GAUDI_PCI_DMA_3] = 5,
-	[GAUDI_HBM_DMA_1] = 2,
-	[GAUDI_HBM_DMA_2] = 3,
-	[GAUDI_HBM_DMA_3] = 4,
-	[GAUDI_HBM_DMA_4] = 6,
-	[GAUDI_HBM_DMA_5] = 7
+	[GAUDI_PCI_DMA_1] = GAUDI_ENGINE_ID_DMA_0,
+	[GAUDI_PCI_DMA_2] = GAUDI_ENGINE_ID_DMA_1,
+	[GAUDI_PCI_DMA_3] = GAUDI_ENGINE_ID_DMA_5,
+	[GAUDI_HBM_DMA_1] = GAUDI_ENGINE_ID_DMA_2,
+	[GAUDI_HBM_DMA_2] = GAUDI_ENGINE_ID_DMA_3,
+	[GAUDI_HBM_DMA_3] = GAUDI_ENGINE_ID_DMA_4,
+	[GAUDI_HBM_DMA_4] = GAUDI_ENGINE_ID_DMA_6,
+	[GAUDI_HBM_DMA_5] = GAUDI_ENGINE_ID_DMA_7
 };
 
 static const u8 gaudi_cq_assignment[NUMBER_OF_CMPLT_QUEUES] = {
@@ -1819,7 +1825,7 @@
 
 	gaudi_init_rate_limiter(hdev);
 
-	gaudi_disable_clock_gating(hdev);
+	hdev->asic_funcs->disable_clock_gating(hdev);
 
 	for (tpc_id = 0, tpc_offset = 0;
 				tpc_id < TPC_NUMBER_OF_ENGINES;
@@ -2531,46 +2537,55 @@
 	WREG32(mmTPC7_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT);
 }
 
-static void gaudi_enable_clock_gating(struct hl_device *hdev)
+static void gaudi_set_clock_gating(struct hl_device *hdev)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
 	u32 qman_offset;
 	int i;
 
-	if (!hdev->clock_gating)
-		return;
-
-	if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE)
-		return;
-
 	/* In case we are during debug session, don't enable the clock gate
 	 * as it may interfere
 	 */
 	if (hdev->in_debug)
 		return;
 
-	for (i = 0, qman_offset = 0 ; i < PCI_DMA_NUMBER_OF_CHNLS ; i++) {
+	for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) {
+		if (!(hdev->clock_gating_mask &
+					(BIT_ULL(gaudi_dma_assignment[i]))))
+			continue;
+
 		qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET;
 		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN);
 		WREG32(mmDMA0_QM_CGM_CFG + qman_offset,
 				QMAN_UPPER_CP_CGM_PWR_GATE_EN);
 	}
 
-	for (; i < HBM_DMA_NUMBER_OF_CHNLS ; i++) {
+	for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) {
+		if (!(hdev->clock_gating_mask &
+					(BIT_ULL(gaudi_dma_assignment[i]))))
+			continue;
+
 		qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET;
 		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN);
 		WREG32(mmDMA0_QM_CGM_CFG + qman_offset,
 				QMAN_COMMON_CP_CGM_PWR_GATE_EN);
 	}
 
-	WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN);
-	WREG32(mmMME0_QM_CGM_CFG,
-			QMAN_COMMON_CP_CGM_PWR_GATE_EN);
-	WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN);
-	WREG32(mmMME2_QM_CGM_CFG,
-			QMAN_COMMON_CP_CGM_PWR_GATE_EN);
+	if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))) {
+		WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN);
+		WREG32(mmMME0_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN);
+	}
+
+	if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))) {
+		WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN);
+		WREG32(mmMME2_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN);
+	}
 
 	for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) {
+		if (!(hdev->clock_gating_mask &
+					(BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i))))
+			continue;
+
 		WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset,
 				QMAN_CGM1_PWR_GATE_EN);
 		WREG32(mmTPC0_QM_CGM_CFG + qman_offset,
@@ -2663,7 +2678,7 @@
 	gaudi_stop_hbm_dma_qmans(hdev);
 	gaudi_stop_pci_dma_qmans(hdev);
 
-	gaudi_disable_clock_gating(hdev);
+	hdev->asic_funcs->disable_clock_gating(hdev);
 
 	msleep(wait_timeout_ms);
 
@@ -3003,7 +3018,7 @@
 
 	gaudi_init_tpc_qmans(hdev);
 
-	gaudi_enable_clock_gating(hdev);
+	hdev->asic_funcs->set_clock_gating(hdev);
 
 	gaudi_enable_timestamp(hdev);
 
@@ -3112,7 +3127,9 @@
 					HW_CAP_HBM_DMA | HW_CAP_PLL |
 					HW_CAP_MMU |
 					HW_CAP_SRAM_SCRAMBLER |
-					HW_CAP_HBM_SCRAMBLER);
+					HW_CAP_HBM_SCRAMBLER |
+					HW_CAP_CLK_GATE);
+
 	memset(gaudi->events_stat, 0, sizeof(gaudi->events_stat));
 }
 
@@ -3463,6 +3480,9 @@
 		return 0;
 	}
 
+	if (!timeout)
+		timeout = GAUDI_MSG_TO_CPU_TIMEOUT_USEC;
+
 	return hl_fw_send_cpu_message(hdev, GAUDI_QUEUE_ID_CPU_PQ, msg, len,
 						timeout, result);
 }
@@ -3865,6 +3885,12 @@
 			rc = -EPERM;
 			break;
 
+		case PACKET_WREG_BULK:
+			dev_err(hdev->dev,
+				"User not allowed to use WREG_BULK\n");
+			rc = -EPERM;
+			break;
+
 		case PACKET_LOAD_AND_EXE:
 			rc = gaudi_validate_load_and_exe_pkt(hdev, parser,
 				(struct packet_load_and_exe *) user_pkt);
@@ -3880,7 +3906,6 @@
 			break;
 
 		case PACKET_WREG_32:
-		case PACKET_WREG_BULK:
 		case PACKET_MSG_LONG:
 		case PACKET_MSG_SHORT:
 		case PACKET_REPEAT:
@@ -4521,13 +4546,18 @@
 	int rc = 0;
 
 	if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) {
-		if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) {
+
+		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
+				(hdev->clock_gating_mask &
+						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
+
 			dev_err_ratelimited(hdev->dev,
 				"Can't read register - clock gating is enabled!\n");
 			rc = -EFAULT;
 		} else {
 			*val = RREG32(addr - CFG_BASE);
 		}
+
 	} else if ((addr >= SRAM_BASE_ADDR) &&
 			(addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) {
 		*val = readl(hdev->pcie_bar[SRAM_BAR_ID] +
@@ -4563,13 +4593,18 @@
 	int rc = 0;
 
 	if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) {
-		if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) {
+
+		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
+				(hdev->clock_gating_mask &
+						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
+
 			dev_err_ratelimited(hdev->dev,
 				"Can't write register - clock gating is enabled!\n");
 			rc = -EFAULT;
 		} else {
 			WREG32(addr - CFG_BASE, val);
 		}
+
 	} else if ((addr >= SRAM_BASE_ADDR) &&
 			(addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) {
 		writel(val, hdev->pcie_bar[SRAM_BAR_ID] +
@@ -4605,7 +4640,11 @@
 	int rc = 0;
 
 	if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) {
-		if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) {
+
+		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
+				(hdev->clock_gating_mask &
+						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
+
 			dev_err_ratelimited(hdev->dev,
 				"Can't read register - clock gating is enabled!\n");
 			rc = -EFAULT;
@@ -4615,6 +4654,7 @@
 
 			*val = (((u64) val_h) << 32) | val_l;
 		}
+
 	} else if ((addr >= SRAM_BASE_ADDR) &&
 		   (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) {
 		*val = readq(hdev->pcie_bar[SRAM_BAR_ID] +
@@ -4651,7 +4691,11 @@
 	int rc = 0;
 
 	if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) {
-		if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) {
+
+		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
+				(hdev->clock_gating_mask &
+						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
+
 			dev_err_ratelimited(hdev->dev,
 				"Can't write register - clock gating is enabled!\n");
 			rc = -EFAULT;
@@ -4660,6 +4704,7 @@
 			WREG32(addr + sizeof(u32) - CFG_BASE,
 				upper_32_bits(val));
 		}
+
 	} else if ((addr >= SRAM_BASE_ADDR) &&
 		   (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) {
 		writeq(val, hdev->pcie_bar[SRAM_BAR_ID] +
@@ -4881,7 +4926,7 @@
 	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
 	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
 
-	hdev->asic_funcs->enable_clock_gating(hdev);
+	hdev->asic_funcs->set_clock_gating(hdev);
 
 	mutex_unlock(&gaudi->clk_gate_mutex);
 }
@@ -5262,7 +5307,7 @@
 	}
 
 	if (disable_clock_gating) {
-		hdev->asic_funcs->enable_clock_gating(hdev);
+		hdev->asic_funcs->set_clock_gating(hdev);
 		mutex_unlock(&gaudi->clk_gate_mutex);
 	}
 }
@@ -5749,7 +5794,7 @@
 	/* Clear interrupts */
 	WREG32(mmTPC0_CFG_TPC_INTR_CAUSE + tpc_offset, 0);
 
-	hdev->asic_funcs->enable_clock_gating(hdev);
+	hdev->asic_funcs->set_clock_gating(hdev);
 
 	mutex_unlock(&gaudi->clk_gate_mutex);
 
@@ -6265,7 +6310,7 @@
 	if (s)
 		seq_puts(s, "\n");
 
-	hdev->asic_funcs->enable_clock_gating(hdev);
+	hdev->asic_funcs->set_clock_gating(hdev);
 
 	mutex_unlock(&gaudi->clk_gate_mutex);
 
@@ -6366,7 +6411,7 @@
 		dev_err(hdev->dev,
 			"Timeout while waiting for TPC%d icache prefetch\n",
 			tpc_id);
-		hdev->asic_funcs->enable_clock_gating(hdev);
+		hdev->asic_funcs->set_clock_gating(hdev);
 		mutex_unlock(&gaudi->clk_gate_mutex);
 		return -EIO;
 	}
@@ -6395,7 +6440,7 @@
 		1000,
 		kernel_timeout);
 
-	hdev->asic_funcs->enable_clock_gating(hdev);
+	hdev->asic_funcs->set_clock_gating(hdev);
 	mutex_unlock(&gaudi->clk_gate_mutex);
 
 	if (rc) {
@@ -6736,7 +6781,7 @@
 	.mmu_invalidate_cache = gaudi_mmu_invalidate_cache,
 	.mmu_invalidate_cache_range = gaudi_mmu_invalidate_cache_range,
 	.send_heartbeat = gaudi_send_heartbeat,
-	.enable_clock_gating = gaudi_enable_clock_gating,
+	.set_clock_gating = gaudi_set_clock_gating,
 	.disable_clock_gating = gaudi_disable_clock_gating,
 	.debug_coresight = gaudi_debug_coresight,
 	.is_device_idle = gaudi_is_device_idle,
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 0d2952b..88460b2 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -88,6 +88,7 @@
 #define GOYA_PLDM_MMU_TIMEOUT_USEC	(MMU_CONFIG_TIMEOUT_USEC * 100)
 #define GOYA_PLDM_QMAN0_TIMEOUT_USEC	(HL_DEVICE_TIMEOUT_USEC * 30)
 #define GOYA_BOOT_FIT_REQ_TIMEOUT_USEC	1000000		/* 1s */
+#define GOYA_MSG_TO_CPU_TIMEOUT_USEC	4000000		/* 4s */
 
 #define GOYA_QMAN0_FENCE_VAL		0xD169B243
 
@@ -2830,6 +2831,9 @@
 		return 0;
 	}
 
+	if (!timeout)
+		timeout = GOYA_MSG_TO_CPU_TIMEOUT_USEC;
+
 	return hl_fw_send_cpu_message(hdev, GOYA_QUEUE_ID_CPU_PQ, msg, len,
 					timeout, result);
 }
@@ -4431,8 +4435,8 @@
 	pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
 						ARMCP_PKT_CTL_OPCODE_SHIFT);
 
-	rc = goya_send_cpu_message(hdev, (u32 *) pkt, total_pkt_size,
-			HL_DEVICE_TIMEOUT_USEC, &result);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt,
+						total_pkt_size,	0, &result);
 
 	if (rc)
 		dev_err(hdev->dev, "failed to unmask IRQ array\n");
@@ -4464,8 +4468,8 @@
 				ARMCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.value = cpu_to_le64(event_type);
 
-	rc = goya_send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-			HL_DEVICE_TIMEOUT_USEC, &result);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						0, &result);
 
 	if (rc)
 		dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type);
@@ -5028,14 +5032,14 @@
 	return 0;
 }
 
-static void goya_enable_clock_gating(struct hl_device *hdev)
+static void goya_set_clock_gating(struct hl_device *hdev)
 {
-
+	/* clock gating not supported in Goya */
 }
 
 static void goya_disable_clock_gating(struct hl_device *hdev)
 {
-
+	/* clock gating not supported in Goya */
 }
 
 static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask,
@@ -5259,7 +5263,7 @@
 	.mmu_invalidate_cache = goya_mmu_invalidate_cache,
 	.mmu_invalidate_cache_range = goya_mmu_invalidate_cache_range,
 	.send_heartbeat = goya_send_heartbeat,
-	.enable_clock_gating = goya_enable_clock_gating,
+	.set_clock_gating = goya_set_clock_gating,
 	.disable_clock_gating = goya_disable_clock_gating,
 	.debug_coresight = goya_debug_coresight,
 	.is_device_idle = goya_is_device_idle,
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 1ecdcf8..194d833 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -578,8 +578,9 @@
  * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with
  *                              ASID-VA-size mask.
  * @send_heartbeat: send is-alive packet to ArmCP and verify response.
- * @enable_clock_gating: enable clock gating for reducing power consumption.
- * @disable_clock_gating: disable clock for accessing registers on HBW.
+ * @set_clock_gating: enable/disable clock gating per engine according to
+ *                    clock gating mask in hdev
+ * @disable_clock_gating: disable clock gating completely
  * @debug_coresight: perform certain actions on Coresight for debugging.
  * @is_device_idle: return true if device is idle, false otherwise.
  * @soft_reset_late_init: perform certain actions needed after soft reset.
@@ -587,7 +588,11 @@
  * @hw_queues_unlock: release H/W queues lock.
  * @get_pci_id: retrieve PCI ID.
  * @get_eeprom_data: retrieve EEPROM data from F/W.
- * @send_cpu_message: send buffer to ArmCP.
+ * @send_cpu_message: send message to F/W. If the message is timedout, the
+ *                    driver will eventually reset the device. The timeout can
+ *                    be determined by the calling function or it can be 0 and
+ *                    then the timeout is the default timeout for the specific
+ *                    ASIC
  * @get_hw_state: retrieve the H/W state
  * @pci_bars_map: Map PCI BARs.
  * @set_dram_bar_base: Set DRAM BAR to map specific device address. Returns
@@ -680,7 +685,7 @@
 	int (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard,
 			u32 asid, u64 va, u64 size);
 	int (*send_heartbeat)(struct hl_device *hdev);
-	void (*enable_clock_gating)(struct hl_device *hdev);
+	void (*set_clock_gating)(struct hl_device *hdev);
 	void (*disable_clock_gating)(struct hl_device *hdev);
 	int (*debug_coresight)(struct hl_device *hdev, void *data);
 	bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
@@ -1398,6 +1403,9 @@
  * @max_power: the max power of the device, as configured by the sysadmin. This
  *             value is saved so in case of hard-reset, the driver will restore
  *             this value and update the F/W after the re-initialization
+ * @clock_gating_mask: is clock gating enabled. bitmask that represents the
+ *                     different engines. See debugfs-driver-habanalabs for
+ *                     details.
  * @in_reset: is device in reset flow.
  * @curr_pll_profile: current PLL profile.
  * @cs_active_cnt: number of active command submissions on this device (active
@@ -1425,7 +1433,6 @@
  * @init_done: is the initialization of the device done.
  * @mmu_enable: is MMU enabled.
  * @mmu_huge_page_opt: is MMU huge pages optimization enabled.
- * @clock_gating: is clock gating enabled.
  * @device_cpu_disabled: is the device CPU disabled (due to timeouts)
  * @dma_mask: the dma mask that was set for this device
  * @in_debug: is device under debug. This, together with fpriv_list, enforces
@@ -1493,6 +1500,7 @@
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;
 	u64				max_power;
+	u64				clock_gating_mask;
 	atomic_t			in_reset;
 	enum hl_pll_frequency		curr_pll_profile;
 	int				cs_active_cnt;
@@ -1514,7 +1522,6 @@
 	u8				dram_default_page_mapping;
 	u8				pmmu_huge_range;
 	u8				init_done;
-	u8				clock_gating;
 	u8				device_cpu_disabled;
 	u8				dma_mask;
 	u8				in_debug;
diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c
index 8652c7e..22716da 100644
--- a/drivers/misc/habanalabs/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/habanalabs_drv.c
@@ -232,7 +232,7 @@
 	hdev->fw_loading = 1;
 	hdev->cpu_queues_enable = 1;
 	hdev->heartbeat = 1;
-	hdev->clock_gating = 1;
+	hdev->clock_gating_mask = ULONG_MAX;
 
 	hdev->reset_pcilink = 0;
 	hdev->axi_drain = 0;
diff --git a/drivers/misc/habanalabs/hwmon.c b/drivers/misc/habanalabs/hwmon.c
index 8c6cd77..b997336 100644
--- a/drivers/misc/habanalabs/hwmon.c
+++ b/drivers/misc/habanalabs/hwmon.c
@@ -10,7 +10,6 @@
 #include <linux/pci.h>
 #include <linux/hwmon.h>
 
-#define SENSORS_PKT_TIMEOUT		1000000	/* 1s */
 #define HWMON_NR_SENSOR_TYPES		(hwmon_pwm + 1)
 
 int hl_build_hwmon_channel_info(struct hl_device *hdev,
@@ -323,7 +322,7 @@
 	pkt.type = __cpu_to_le16(attr);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-			SENSORS_PKT_TIMEOUT, value);
+						0, value);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -350,7 +349,7 @@
 	pkt.value = __cpu_to_le64(value);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						SENSORS_PKT_TIMEOUT, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev,
@@ -374,7 +373,7 @@
 	pkt.type = __cpu_to_le16(attr);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SENSORS_PKT_TIMEOUT, value);
+						0, value);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -400,7 +399,7 @@
 	pkt.type = __cpu_to_le16(attr);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SENSORS_PKT_TIMEOUT, value);
+						0, value);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -426,7 +425,7 @@
 	pkt.type = __cpu_to_le16(attr);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SENSORS_PKT_TIMEOUT, value);
+						0, value);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -452,7 +451,7 @@
 	pkt.type = __cpu_to_le16(attr);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SENSORS_PKT_TIMEOUT, value);
+						0, value);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -479,7 +478,7 @@
 	pkt.value = cpu_to_le64(value);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SENSORS_PKT_TIMEOUT, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev,
@@ -502,7 +501,7 @@
 	pkt.value = __cpu_to_le64(value);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						SENSORS_PKT_TIMEOUT, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev,
@@ -527,7 +526,7 @@
 	pkt.value = __cpu_to_le64(value);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						SENSORS_PKT_TIMEOUT, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev,
diff --git a/drivers/misc/habanalabs/sysfs.c b/drivers/misc/habanalabs/sysfs.c
index 5d78d5e..70b6b18 100644
--- a/drivers/misc/habanalabs/sysfs.c
+++ b/drivers/misc/habanalabs/sysfs.c
@@ -9,9 +9,6 @@
 
 #include <linux/pci.h>
 
-#define SET_CLK_PKT_TIMEOUT	1000000	/* 1s */
-#define SET_PWR_PKT_TIMEOUT	1000000	/* 1s */
-
 long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
 {
 	struct armcp_packet pkt;
@@ -29,7 +26,7 @@
 	pkt.pll_index = cpu_to_le32(pll_index);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						SET_CLK_PKT_TIMEOUT, &result);
+						0, &result);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -54,7 +51,7 @@
 	pkt.value = cpu_to_le64(freq);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SET_CLK_PKT_TIMEOUT, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev,
@@ -74,7 +71,7 @@
 				ARMCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						SET_PWR_PKT_TIMEOUT, &result);
+						0, &result);
 
 	if (rc) {
 		dev_err(hdev->dev, "Failed to get max power, error %d\n", rc);
@@ -96,7 +93,7 @@
 	pkt.value = cpu_to_le64(value);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					SET_PWR_PKT_TIMEOUT, NULL);
+						0, NULL);
 
 	if (rc)
 		dev_err(hdev->dev, "Failed to set max power, error %d\n", rc);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index add0401..4ee2330 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1102,6 +1102,9 @@
 	int pos;
 	int len;
 
+	if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST)
+		return 0;
+
 	c.identify.opcode = nvme_admin_identify;
 	c.identify.nsid = cpu_to_le32(nsid);
 	c.identify.cns = NVME_ID_CNS_NS_DESC_LIST;
@@ -1115,18 +1118,6 @@
 	if (status) {
 		dev_warn(ctrl->device,
 			"Identify Descriptors failed (%d)\n", status);
-		 /*
-		  * Don't treat non-retryable errors as fatal, as we potentially
-		  * already have a NGUID or EUI-64.  If we failed with DNR set,
-		  * we want to silently ignore the error as we can still
-		  * identify the device, but if the status has DNR set, we want
-		  * to propagate the error back specifically for the disk
-		  * revalidation flow to make sure we don't abandon the
-		  * device just because of a temporal retry-able error (such
-		  * as path of transport errors).
-		  */
-		if (status > 0 && (status & NVME_SC_DNR))
-			status = 0;
 		goto free_data;
 	}
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 1de3f9b..09ffc32 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -129,6 +129,13 @@
 	 * Don't change the value of the temperature threshold feature
 	 */
 	NVME_QUIRK_NO_TEMP_THRESH_CHANGE	= (1 << 14),
+
+	/*
+	 * The controller doesn't handle the Identify Namespace
+	 * Identification Descriptor list subcommand despite claiming
+	 * NVMe 1.3 compliance.
+	 */
+	NVME_QUIRK_NO_NS_DESC_LIST		= (1 << 15),
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index b1d18f0..d4b1ff7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3099,6 +3099,8 @@
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS |
 				NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x126f, 0x2263),	/* Silicon Motion unidentified */
+		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST, },
 	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
@@ -3122,6 +3124,8 @@
 	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 79ef2b8..f3a9181 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1382,6 +1382,9 @@
 	if (nctrl->opts->tos >= 0)
 		ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos);
 
+	/* Set 10 seconds timeout for icresp recvmsg */
+	queue->sock->sk->sk_rcvtimeo = 10 * HZ;
+
 	queue->sock->sk->sk_allocation = GFP_ATOMIC;
 	nvme_tcp_set_queue_io_cpu(queue);
 	queue->request = NULL;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 812bfc3..2ea61ab 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2330,6 +2330,19 @@
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s);
 
+static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev)
+{
+	pci_info(dev, "Disabling ASPM L0s/L1\n");
+	pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+}
+
+/*
+ * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the
+ * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected;
+ * disable both L0s and L1 for now to be safe.
+ */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1);
+
 /*
  * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain
  * Link bit cleared after starting the link retrain process to allow this
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index ff1ee15..f8ff30c 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -7,6 +7,8 @@
 	select PINCONF
 	select GENERIC_PINCONF
 	select GPIOLIB_IRQCHIP
+	select IRQ_DOMAIN_HIERARCHY
+	select IRQ_FASTEOI_HIERARCHY_HANDLERS
 
 config PINCTRL_APQ8064
 	tristate "Qualcomm APQ8064 pin controller driver"
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 83b7d64..c322f30 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -832,6 +832,52 @@
 	msm_gpio_irq_clear_unmask(d, false);
 }
 
+/**
+ * msm_gpio_update_dual_edge_parent() - Prime next edge for IRQs handled by parent.
+ * @d: The irq dta.
+ *
+ * This is much like msm_gpio_update_dual_edge_pos() but for IRQs that are
+ * normally handled by the parent irqchip.  The logic here is slightly
+ * different due to what's easy to do with our parent, but in principle it's
+ * the same.
+ */
+static void msm_gpio_update_dual_edge_parent(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq];
+	int loop_limit = 100;
+	unsigned int val;
+	unsigned int type;
+
+	/* Read the value and make a guess about what edge we need to catch */
+	val = msm_readl_io(pctrl, g) & BIT(g->in_bit);
+	type = val ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING;
+
+	do {
+		/* Set the parent to catch the next edge */
+		irq_chip_set_type_parent(d, type);
+
+		/*
+		 * Possibly the line changed between when we last read "val"
+		 * (and decided what edge we needed) and when set the edge.
+		 * If the value didn't change (or changed and then changed
+		 * back) then we're done.
+		 */
+		val = msm_readl_io(pctrl, g) & BIT(g->in_bit);
+		if (type == IRQ_TYPE_EDGE_RISING) {
+			if (!val)
+				return;
+			type = IRQ_TYPE_EDGE_FALLING;
+		} else if (type == IRQ_TYPE_EDGE_FALLING) {
+			if (val)
+				return;
+			type = IRQ_TYPE_EDGE_RISING;
+		}
+	} while (loop_limit-- > 0);
+	dev_warn_once(pctrl->dev, "dual-edge irq failed to stabilize\n");
+}
+
 static void msm_gpio_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -840,8 +886,11 @@
 	unsigned long flags;
 	u32 val;
 
-	if (test_bit(d->hwirq, pctrl->skip_wake_irqs))
+	if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) {
+		if (test_bit(d->hwirq, pctrl->dual_edge_irqs))
+			msm_gpio_update_dual_edge_parent(d);
 		return;
+	}
 
 	g = &pctrl->soc->groups[d->hwirq];
 
@@ -860,6 +909,17 @@
 	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 }
 
+static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d,
+						       unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+
+	return type == IRQ_TYPE_EDGE_BOTH &&
+	       pctrl->soc->wakeirq_dual_edge_errata && d->parent_data &&
+	       test_bit(d->hwirq, pctrl->skip_wake_irqs);
+}
+
 static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -868,11 +928,21 @@
 	unsigned long flags;
 	u32 val;
 
+	if (msm_gpio_needs_dual_edge_parent_workaround(d, type)) {
+		set_bit(d->hwirq, pctrl->dual_edge_irqs);
+		irq_set_handler_locked(d, handle_fasteoi_ack_irq);
+		msm_gpio_update_dual_edge_parent(d);
+		return 0;
+	}
+
 	if (d->parent_data)
 		irq_chip_set_type_parent(d, type);
 
-	if (test_bit(d->hwirq, pctrl->skip_wake_irqs))
+	if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) {
+		clear_bit(d->hwirq, pctrl->dual_edge_irqs);
+		irq_set_handler_locked(d, handle_fasteoi_irq);
 		return 0;
+	}
 
 	g = &pctrl->soc->groups[d->hwirq];
 
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h
index 9452da1..7486fe0 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.h
+++ b/drivers/pinctrl/qcom/pinctrl-msm.h
@@ -113,6 +113,9 @@
  * @pull_no_keeper: The SoC does not support keeper bias.
  * @wakeirq_map:    The map of wakeup capable GPIOs and the pin at PDC/MPM
  * @nwakeirq_map:   The number of entries in @wakeirq_map
+ * @wakeirq_dual_edge_errata: If true then GPIOs using the wakeirq_map need
+ *                            to be aware that their parent can't handle dual
+ *                            edge interrupts.
  */
 struct msm_pinctrl_soc_data {
 	const struct pinctrl_pin_desc *pins;
@@ -128,6 +131,7 @@
 	const int *reserved_gpios;
 	const struct msm_gpio_wakeirq_map *wakeirq_map;
 	unsigned int nwakeirq_map;
+	bool wakeirq_dual_edge_errata;
 };
 
 extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops;
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c
index 1b6465a..1d9acad 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7180.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c
@@ -1147,6 +1147,7 @@
 	.ntiles = ARRAY_SIZE(sc7180_tiles),
 	.wakeirq_map = sc7180_pdc_map,
 	.nwakeirq_map = ARRAY_SIZE(sc7180_pdc_map),
+	.wakeirq_dual_edge_errata = true,
 };
 
 static int sc7180_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 0ba7a65..06056e9 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -547,6 +547,15 @@
 	scsi_uninit_cmd(cmd);
 }
 
+static void scsi_run_queue_async(struct scsi_device *sdev)
+{
+	if (scsi_target(sdev)->single_lun ||
+	    !list_empty(&sdev->host->starved_list))
+		kblockd_schedule_work(&sdev->requeue_work);
+	else
+		blk_mq_run_hw_queues(sdev->request_queue, true);
+}
+
 /* Returns false when no more bytes to process, true if there are more */
 static bool scsi_end_request(struct request *req, blk_status_t error,
 		unsigned int bytes)
@@ -591,11 +600,7 @@
 
 	__blk_mq_end_request(req, error);
 
-	if (scsi_target(sdev)->single_lun ||
-	    !list_empty(&sdev->host->starved_list))
-		kblockd_schedule_work(&sdev->requeue_work);
-	else
-		blk_mq_run_hw_queues(q, true);
+	scsi_run_queue_async(sdev);
 
 	percpu_ref_put(&q->q_usage_counter);
 	return false;
@@ -1702,6 +1707,7 @@
 		 */
 		if (req->rq_flags & RQF_DONTPREP)
 			scsi_mq_uninit_cmd(cmd);
+		scsi_run_queue_async(sdev);
 		break;
 	}
 	return ret;
diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index 560649b..e035c9f 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -106,14 +106,22 @@
 				    unsigned int *data)
 {
 	struct apci1032_private *devpriv = dev->private;
-	unsigned int shift, oldmask;
+	unsigned int shift, oldmask, himask, lomask;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIGITAL_TRIG:
 		if (data[1] != 0)
 			return -EINVAL;
 		shift = data[3];
-		oldmask = (1U << shift) - 1;
+		if (shift < 32) {
+			oldmask = (1U << shift) - 1;
+			himask = data[4] << shift;
+			lomask = data[5] << shift;
+		} else {
+			oldmask = 0xffffffffu;
+			himask = 0;
+			lomask = 0;
+		}
 		switch (data[2]) {
 		case COMEDI_DIGITAL_TRIG_DISABLE:
 			devpriv->ctrl = 0;
@@ -136,8 +144,8 @@
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS:
 			if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA |
@@ -154,8 +162,8 @@
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c
index 689acd6..816dd25 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1500.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1500.c
@@ -452,13 +452,14 @@
 	struct apci1500_private *devpriv = dev->private;
 	unsigned int trig = data[1];
 	unsigned int shift = data[3];
-	unsigned int hi_mask = data[4] << shift;
-	unsigned int lo_mask = data[5] << shift;
-	unsigned int chan_mask = hi_mask | lo_mask;
-	unsigned int old_mask = (1 << shift) - 1;
+	unsigned int hi_mask;
+	unsigned int lo_mask;
+	unsigned int chan_mask;
+	unsigned int old_mask;
 	unsigned int pm;
 	unsigned int pt;
 	unsigned int pp;
+	unsigned int invalid_chan;
 
 	if (trig > 1) {
 		dev_dbg(dev->class_dev,
@@ -466,7 +467,20 @@
 		return -EINVAL;
 	}
 
-	if (chan_mask > 0xffff) {
+	if (shift <= 16) {
+		hi_mask = data[4] << shift;
+		lo_mask = data[5] << shift;
+		old_mask = (1U << shift) - 1;
+		invalid_chan = (data[4] | data[5]) >> (16 - shift);
+	} else {
+		hi_mask = 0;
+		lo_mask = 0;
+		old_mask = 0xffff;
+		invalid_chan = data[4] | data[5];
+	}
+	chan_mask = hi_mask | lo_mask;
+
+	if (invalid_chan) {
 		dev_dbg(dev->class_dev, "invalid digital trigger channel\n");
 		return -EINVAL;
 	}
diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c
index 10501fe..1268ba34 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1564.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1564.c
@@ -331,14 +331,22 @@
 				    unsigned int *data)
 {
 	struct apci1564_private *devpriv = dev->private;
-	unsigned int shift, oldmask;
+	unsigned int shift, oldmask, himask, lomask;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIGITAL_TRIG:
 		if (data[1] != 0)
 			return -EINVAL;
 		shift = data[3];
-		oldmask = (1U << shift) - 1;
+		if (shift < 32) {
+			oldmask = (1U << shift) - 1;
+			himask = data[4] << shift;
+			lomask = data[5] << shift;
+		} else {
+			oldmask = 0xffffffffu;
+			himask = 0;
+			lomask = 0;
+		}
 		switch (data[2]) {
 		case COMEDI_DIGITAL_TRIG_DISABLE:
 			devpriv->ctrl = 0;
@@ -362,8 +370,8 @@
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS:
 			if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA |
@@ -380,8 +388,8 @@
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c
index 4d1eccb..4518c26 100644
--- a/drivers/staging/comedi/drivers/ni_6527.c
+++ b/drivers/staging/comedi/drivers/ni_6527.c
@@ -332,7 +332,7 @@
 		case COMEDI_DIGITAL_TRIG_ENABLE_EDGES:
 			/* check shift amount */
 			shift = data[3];
-			if (shift >= s->n_chan) {
+			if (shift >= 32) {
 				mask = 0;
 				rising = 0;
 				falling = 0;
diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c
index 4689b21..456603f 100644
--- a/drivers/staging/wlan-ng/prism2usb.c
+++ b/drivers/staging/wlan-ng/prism2usb.c
@@ -61,11 +61,25 @@
 			       const struct usb_device_id *id)
 {
 	struct usb_device *dev;
-
+	const struct usb_endpoint_descriptor *epd;
+	const struct usb_host_interface *iface_desc = interface->cur_altsetting;
 	struct wlandevice *wlandev = NULL;
 	struct hfa384x *hw = NULL;
 	int result = 0;
 
+	if (iface_desc->desc.bNumEndpoints != 2) {
+		result = -ENODEV;
+		goto failed;
+	}
+
+	result = -EINVAL;
+	epd = &iface_desc->endpoint[1].desc;
+	if (!usb_endpoint_is_bulk_in(epd))
+		goto failed;
+	epd = &iface_desc->endpoint[2].desc;
+	if (!usb_endpoint_is_bulk_out(epd))
+		goto failed;
+
 	dev = interface_to_usbdev(interface);
 	wlandev = create_wlan();
 	if (!wlandev) {
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index fc118f6..cae61d1 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -524,6 +524,7 @@
 		 */
 		up->mcr_mask = ~ALPHA_KLUDGE_MCR;
 		up->mcr_force = ALPHA_KLUDGE_MCR;
+		serial8250_set_defaults(up);
 	}
 
 	/* chain base port ops to support Remote Supervisor Adapter */
@@ -547,7 +548,6 @@
 		port->membase  = old_serial_port[i].iomem_base;
 		port->iotype   = old_serial_port[i].io_type;
 		port->regshift = old_serial_port[i].iomem_reg_shift;
-		serial8250_set_defaults(up);
 
 		port->irqflags |= irqflag;
 		if (serial8250_isa_config != NULL)
diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index ddb6aeb..04b9af7 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -326,7 +326,17 @@
 	 * devices will export them as GPIOs, so we pre-configure them safely
 	 * as inputs.
 	 */
-	u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00;
+
+	u8 dir = 0x00;
+
+	if  ((pcidev->vendor == PCI_VENDOR_ID_EXAR) &&
+		(pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) {
+		// Configure GPIO as inputs for Commtech adapters
+		dir = 0xff;
+	} else {
+		// Configure GPIO as outputs for SeaLevel adapters
+		dir = 0x00;
+	}
 
 	writeb(0x00, p + UART_EXAR_MPIOINT_7_0);
 	writeb(0x00, p + UART_EXAR_MPIOLVL_7_0);
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index f839380..98b8a3e 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -306,8 +306,21 @@
 	}
 #endif
 
+	/*
+	 * Store the requested baud rate before calling the generic 8250
+	 * set_termios method. Standard 8250 port expects bauds to be
+	 * no higher than (uartclk / 16) so the baud will be clamped if it
+	 * gets out of that bound. Mediatek 8250 port supports speed
+	 * higher than that, therefore we'll get original baud rate back
+	 * after calling the generic set_termios method and recalculate
+	 * the speed later in this method.
+	 */
+	baud = tty_termios_baud_rate(termios);
+
 	serial8250_do_set_termios(port, termios, old);
 
+	tty_termios_encode_baud_rate(termios, baud, baud);
+
 	/*
 	 * Mediatek UARTs use an extra highspeed register (MTK_UART_HIGHS)
 	 *
@@ -339,6 +352,11 @@
 	 */
 	spin_lock_irqsave(&port->lock, flags);
 
+	/*
+	 * Update the per-port timeout.
+	 */
+	uart_update_timeout(port, termios->c_cflag, baud);
+
 	/* set DLAB we have cval saved in up->lcr from the call to the core */
 	serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB);
 	serial_dl_write(up, quot);
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 8de8bac..04d1b08 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -635,7 +635,7 @@
 }
 
 static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup,
-		struct tty_port *tty)
+		struct tty_port *port)
 {
 	do {
 		char flag = TTY_NORMAL;
@@ -653,16 +653,18 @@
 		ch = (unsigned char) tegra_uart_read(tup, UART_RX);
 		tup->uport.icount.rx++;
 
-		if (!uart_handle_sysrq_char(&tup->uport, ch) && tty)
-			tty_insert_flip_char(tty, ch, flag);
+		if (uart_handle_sysrq_char(&tup->uport, ch))
+			continue;
 
 		if (tup->uport.ignore_status_mask & UART_LSR_DR)
 			continue;
+
+		tty_insert_flip_char(port, ch, flag);
 	} while (1);
 }
 
 static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup,
-				      struct tty_port *tty,
+				      struct tty_port *port,
 				      unsigned int count)
 {
 	int copied;
@@ -672,17 +674,13 @@
 		return;
 
 	tup->uport.icount.rx += count;
-	if (!tty) {
-		dev_err(tup->uport.dev, "No tty port\n");
-		return;
-	}
 
 	if (tup->uport.ignore_status_mask & UART_LSR_DR)
 		return;
 
 	dma_sync_single_for_cpu(tup->uport.dev, tup->rx_dma_buf_phys,
 				count, DMA_FROM_DEVICE);
-	copied = tty_insert_flip_string(tty,
+	copied = tty_insert_flip_string(port,
 			((unsigned char *)(tup->rx_dma_buf_virt)), count);
 	if (copied != count) {
 		WARN_ON(1);
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 672cfa0..2833f14 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1580,8 +1580,10 @@
 	 * If register_console() don't assign value, then console_port pointer
 	 * is cleanup.
 	 */
-	if (!console_port)
+	if (!console_port) {
+		cdns_uart_console.index = id;
 		console_port = port;
+	}
 #endif
 
 	rc = uart_add_one_port(&cdns_uart_uart_driver, port);
@@ -1594,8 +1596,10 @@
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
 	/* This is not port which is used for console that's why clean it up */
 	if (console_port == port &&
-	    !(cdns_uart_uart_driver.cons->flags & CON_ENABLED))
+	    !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) {
 		console_port = NULL;
+		cdns_uart_console.index = -1;
+	}
 #endif
 
 	cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node,
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 48a8199..42d8c67 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1092,10 +1092,19 @@
 	.destruct = vc_port_destruct,
 };
 
+/*
+ * Change # of rows and columns (0 means unchanged/the size of fg_console)
+ * [this is to be used together with some user program
+ * like resize that changes the hardware videomode]
+ */
+#define VC_MAXCOL (32767)
+#define VC_MAXROW (32767)
+
 int vc_allocate(unsigned int currcons)	/* return 0 on success */
 {
 	struct vt_notifier_param param;
 	struct vc_data *vc;
+	int err;
 
 	WARN_CONSOLE_UNLOCKED();
 
@@ -1125,6 +1134,11 @@
 	if (!*vc->vc_uni_pagedir_loc)
 		con_set_default_unimap(vc);
 
+	err = -EINVAL;
+	if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW ||
+	    vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size)
+		goto err_free;
+	err = -ENOMEM;
 	vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL);
 	if (!vc->vc_screenbuf)
 		goto err_free;
@@ -1143,7 +1157,7 @@
 	visual_deinit(vc);
 	kfree(vc);
 	vc_cons[currcons].d = NULL;
-	return -ENOMEM;
+	return err;
 }
 
 static inline int resize_screen(struct vc_data *vc, int width, int height,
@@ -1158,14 +1172,6 @@
 	return err;
 }
 
-/*
- * Change # of rows and columns (0 means unchanged/the size of fg_console)
- * [this is to be used together with some user program
- * like resize that changes the hardware videomode]
- */
-#define VC_RESIZE_MAXCOL (32767)
-#define VC_RESIZE_MAXROW (32767)
-
 /**
  *	vc_do_resize	-	resizing method for the tty
  *	@tty: tty being resized
@@ -1201,7 +1207,7 @@
 	user = vc->vc_resize_user;
 	vc->vc_resize_user = 0;
 
-	if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW)
+	if (cols > VC_MAXCOL || lines > VC_MAXROW)
 		return -EINVAL;
 
 	new_cols = (cols ? cols : vc->vc_cols);
@@ -1212,7 +1218,7 @@
 	if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
 		return 0;
 
-	if (new_screen_size > KMALLOC_MAX_SIZE)
+	if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size)
 		return -EINVAL;
 	newscreen = kzalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
@@ -3393,6 +3399,7 @@
 		INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK);
 		tty_port_init(&vc->port);
 		visual_init(vc, currcons, 1);
+		/* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */
 		vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT);
 		vc_init(vc, vc->vc_rows, vc->vc_cols,
 			currcons || !vc->vc_sw->con_save_screen);
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index fea5555..45c54d56 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -557,6 +557,10 @@
 	if (is_fs_or_ls(speed) && !has_tt)
 		return false;
 
+	/* skip endpoint with zero maxpkt */
+	if (usb_endpoint_maxp(&ep->desc) == 0)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index ef513c2..9234c82 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -265,6 +265,9 @@
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 			pdev->device == 0x1142)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
+			pdev->device == 0x2142)
+		xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 2eaf5c0..ee6bf01 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -856,7 +856,7 @@
 	if (!tegra->context.ipfs)
 		return -ENOMEM;
 
-	tegra->context.fpci = devm_kcalloc(tegra->dev, soc->ipfs.num_offsets,
+	tegra->context.fpci = devm_kcalloc(tegra->dev, soc->fpci.num_offsets,
 					   sizeof(u32), GFP_KERNEL);
 	if (!tegra->context.fpci)
 		return -ENOMEM;
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 6fb4d7e..b22adf0 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1215,7 +1215,7 @@
 			continue;
 		}
 
-		switch (v_req.type) {
+		switch (vhost32_to_cpu(vq, v_req.type)) {
 		case VIRTIO_SCSI_T_TMF:
 			vc.req = &v_req.tmf;
 			vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req);
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index ca935c0..35ebeec 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -216,7 +216,7 @@
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = info->var.xoffset + rs;
 		region.dy = 0;
 		region.width = rw;
@@ -224,7 +224,7 @@
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset;
 		region.dy = info->var.yoffset + bs;
 		region.width = rs;
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index dfa9a8a..78f3a56 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -201,7 +201,7 @@
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = 0;
 		region.dy = info->var.yoffset;
 		region.height = rw;
@@ -209,7 +209,7 @@
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset + bs;
 		region.dy = 0;
                 region.height = info->var.yres_virtual;
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index ce08251..fd098ff 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -184,7 +184,7 @@
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = 0;
 		region.dy = info->var.yoffset + rs;
 		region.height = rw;
@@ -192,7 +192,7 @@
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset;
 		region.dy = info->var.yoffset;
                 region.height = info->var.yres;
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index 1936afc..e165a3f 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -231,7 +231,7 @@
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dy = 0;
 		region.dx = info->var.xoffset;
 		region.width  = rw;
@@ -239,7 +239,7 @@
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dy = info->var.yoffset;
 		region.dx = info->var.xoffset;
                 region.height  = bh;
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 5809e5f..5c92e4a 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -85,7 +85,7 @@
 	depends on VIRTIO
 	depends on MEMORY_HOTPLUG_SPARSE
 	depends on MEMORY_HOTREMOVE
-	select CONTIG_ALLOC
+	depends on CONTIG_ALLOC
 	help
 	 This driver provides access to virtio-mem paravirtualized memory
 	 devices, allowing to hotplug and hotunplug memory.
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 1f157d2..8be02f3 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -578,10 +578,14 @@
 static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
 {
 	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
-			       &vb->config_read_bitmap))
+			       &vb->config_read_bitmap)) {
 		virtio_cread(vb->vdev, struct virtio_balloon_config,
 			     free_page_hint_cmd_id,
 			     &vb->cmd_id_received_cache);
+		/* Legacy balloon config space is LE, unlike all other devices. */
+		if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
+			vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache);
+	}
 
 	return vb->cmd_id_received_cache;
 }
@@ -974,6 +978,11 @@
 		/*
 		 * Let the hypervisor know that we are expecting a
 		 * specific value to be written back in balloon pages.
+		 *
+		 * If the PAGE_POISON value was larger than a byte we would
+		 * need to byte swap poison_val here to guarantee it is
+		 * little-endian. However for now it is a single byte so we
+		 * can pass it as-is.
 		 */
 		if (!want_init_on_free())
 			memset(&poison_val, PAGE_POISON, sizeof(poison_val));
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 32b0064..493e504 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4199,10 +4199,9 @@
 
 	hash_del(&req->hash_node);
 	io_poll_complete(req, req->result, 0);
-	req->flags |= REQ_F_COMP_LOCKED;
-	io_put_req_find_next(req, nxt);
 	spin_unlock_irq(&ctx->completion_lock);
 
+	io_put_req_find_next(req, nxt);
 	io_cqring_ev_posted(ctx);
 }
 
@@ -4658,6 +4657,10 @@
 	struct io_poll_table ipt;
 	__poll_t mask;
 
+	/* ->work is in union with hash_node and others */
+	io_req_work_drop_env(req);
+	req->flags &= ~REQ_F_WORK_INITIALIZED;
+
 	INIT_HLIST_NODE(&req->hash_node);
 	INIT_LIST_HEAD(&req->list);
 	ipt.pt._qproc = io_poll_queue_proc;
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 8b1e020..30a3aab 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -456,7 +456,7 @@
 
 #if !defined(inb) && !defined(_inb)
 #define _inb _inb
-static inline u16 _inb(unsigned long addr)
+static inline u8 _inb(unsigned long addr)
 {
 	u8 val;
 
@@ -482,7 +482,7 @@
 
 #if !defined(inl) && !defined(_inl)
 #define _inl _inl
-static inline u16 _inl(unsigned long addr)
+static inline u32 _inl(unsigned long addr)
 {
 	u32 val;
 
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index 6c3ef49..e73dea5 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -866,6 +866,18 @@
 	bool prefer_shadow_fbdev;
 
 	/**
+	 * @fbdev_use_iomem:
+	 *
+	 * Set to true if framebuffer reside in iomem.
+	 * When set to true memcpy_toio() is used when copying the framebuffer in
+	 * drm_fb_helper.drm_fb_helper_dirty_blit_real().
+	 *
+	 * FIXME: This should be replaced with a per-mapping is_iomem
+	 * flag (like ttm does), and then used everywhere in fbdev code.
+	 */
+	bool fbdev_use_iomem;
+
+	/**
 	 * @quirk_addfb_prefer_xbgr_30bpp:
 	 *
 	 * Special hack for legacy ADDFB to keep nouveau userspace happy. Should
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index ee328cf..4e7714c 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -1001,7 +1001,7 @@
 static inline struct i2c_client *i2c_acpi_new_device(struct device *dev,
 					int index, struct i2c_board_info *info)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle)
 {
diff --git a/include/linux/random.h b/include/linux/random.h
index 45e1f8f..9ab7443 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/once.h>
+#include <asm/percpu.h>
 
 #include <uapi/linux/random.h>
 
@@ -119,6 +120,8 @@
 	__u32 s1, s2, s3, s4;
 };
 
+DECLARE_PER_CPU(struct rnd_state, net_rand_state);
+
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index c4369a6..2f1fc23 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -305,6 +305,25 @@
 	spinlock_t lock ____cacheline_aligned_in_smp;
 };
 
+/**
+ * rvt_get_rq_count - count numbers of request work queue entries
+ * in circular buffer
+ * @rq: data structure for request queue entry
+ * @head: head indices of the circular buffer
+ * @tail: tail indices of the circular buffer
+ *
+ * Return - total number of entries in the Receive Queue
+ */
+
+static inline u32 rvt_get_rq_count(struct rvt_rq *rq, u32 head, u32 tail)
+{
+	u32 count = head - tail;
+
+	if ((s32)count < 0)
+		count += rq->size;
+	return count;
+}
+
 /*
  * This structure holds the information that the send tasklet needs
  * to send a RDMA read response or atomic operation.
diff --git a/kernel/audit.c b/kernel/audit.c
index 8c201f4..b2301bd 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1851,7 +1851,6 @@
 	}
 
 	audit_get_stamp(ab->ctx, &t, &serial);
-	audit_clear_dummy(ab->ctx);
 	audit_log_format(ab, "audit(%llu.%03lu:%u): ",
 			 (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial);
 
diff --git a/kernel/audit.h b/kernel/audit.h
index f0233dc..ddc2287 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -290,13 +290,6 @@
 extern void audit_filter_inodes(struct task_struct *tsk,
 				struct audit_context *ctx);
 extern struct list_head *audit_killed_trees(void);
-
-static inline void audit_clear_dummy(struct audit_context *ctx)
-{
-	if (ctx)
-		ctx->dummy = 0;
-}
-
 #else /* CONFIG_AUDITSYSCALL */
 #define auditsc_get_stamp(c, t, s) 0
 #define audit_put_watch(w) {}
@@ -330,7 +323,6 @@
 }
 
 #define audit_filter_inodes(t, c) AUDIT_DISABLED
-#define audit_clear_dummy(c) {}
 #endif /* CONFIG_AUDITSYSCALL */
 
 extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 468a233..fd840c4 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1417,6 +1417,9 @@
 	struct audit_context *context = audit_context();
 	struct audit_buffer *ab;
 
+	if (!context || context->dummy)
+		return;
+
 	ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE);
 	if (!ab)
 		return;	/* audit_panic or being filtered */
diff --git a/kernel/signal.c b/kernel/signal.c
index ee22ec7..6f16f7c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -719,7 +719,7 @@
 	 * Return the first synchronous signal in the queue.
 	 */
 	list_for_each_entry(q, &pending->list, list) {
-		/* Synchronous signals have a postive si_code */
+		/* Synchronous signals have a positive si_code */
 		if ((q->info.si_code > SI_USER) &&
 		    (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) {
 			sync = q;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index df1ff80..026ac01 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -43,6 +43,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/random.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -1742,6 +1743,13 @@
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers();
+
+	/* The current CPU might make use of net randoms without receiving IRQs
+	 * to renew them often enough. Let's update the net_rand_state from a
+	 * non-constant value that's not affine to the number of calls to make
+	 * sure it's updated when there's some activity (we don't care in idle).
+	 */
+	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
diff --git a/lib/random32.c b/lib/random32.c
index 763b920..3d749ab 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -48,7 +48,7 @@
 }
 #endif
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 13cd683..12ecacf 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -362,6 +362,10 @@
 		if (m->rreq->status == REQ_STATUS_SENT) {
 			list_del(&m->rreq->req_list);
 			p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD);
+		} else if (m->rreq->status == REQ_STATUS_FLSHD) {
+			/* Ignore replies associated with a cancelled request. */
+			p9_debug(P9_DEBUG_TRANS,
+				 "Ignore replies associated with a cancelled request\n");
 		} else {
 			spin_unlock(&m->client->lock);
 			p9_debug(P9_DEBUG_ERROR,
@@ -703,11 +707,20 @@
 {
 	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
 
+	spin_lock(&client->lock);
+	/* Ignore cancelled request if message has been received
+	 * before lock.
+	 */
+	if (req->status == REQ_STATUS_RCVD) {
+		spin_unlock(&client->lock);
+		return 0;
+	}
+
 	/* we haven't received a response for oldreq,
 	 * remove it from the list.
 	 */
-	spin_lock(&client->lock);
 	list_del(&req->req_list);
+	req->status = REQ_STATUS_FLSHD;
 	spin_unlock(&client->lock);
 	p9_req_put(req);
 
@@ -803,20 +816,28 @@
 		return -ENOMEM;
 
 	ts->rd = fget(rfd);
+	if (!ts->rd)
+		goto out_free_ts;
+	if (!(ts->rd->f_mode & FMODE_READ))
+		goto out_put_rd;
 	ts->wr = fget(wfd);
-	if (!ts->rd || !ts->wr) {
-		if (ts->rd)
-			fput(ts->rd);
-		if (ts->wr)
-			fput(ts->wr);
-		kfree(ts);
-		return -EIO;
-	}
+	if (!ts->wr)
+		goto out_put_rd;
+	if (!(ts->wr->f_mode & FMODE_WRITE))
+		goto out_put_wr;
 
 	client->trans = ts;
 	client->status = Connected;
 
 	return 0;
+
+out_put_wr:
+	fput(ts->wr);
+out_put_rd:
+	fput(ts->rd);
+out_free_ts:
+	kfree(ts);
+	return -EIO;
 }
 
 static int p9_socket_open(struct p9_client *client, struct socket *csocket)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index cfeaee3..af9d7f2 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1338,6 +1338,9 @@
 {
 	struct discovery_state *d = &hdev->discovery;
 
+	if (len > HCI_MAX_AD_LENGTH)
+		return;
+
 	bacpy(&d->last_adv_addr, bdaddr);
 	d->last_adv_addr_type = bdaddr_type;
 	d->last_adv_rssi = rssi;
@@ -5355,7 +5358,8 @@
 
 static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 			       u8 bdaddr_type, bdaddr_t *direct_addr,
-			       u8 direct_addr_type, s8 rssi, u8 *data, u8 len)
+			       u8 direct_addr_type, s8 rssi, u8 *data, u8 len,
+			       bool ext_adv)
 {
 	struct discovery_state *d = &hdev->discovery;
 	struct smp_irk *irk;
@@ -5377,6 +5381,11 @@
 		return;
 	}
 
+	if (!ext_adv && len > HCI_MAX_AD_LENGTH) {
+		bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes");
+		return;
+	}
+
 	/* Find the end of the data in case the report contains padded zero
 	 * bytes at the end causing an invalid length value.
 	 *
@@ -5437,7 +5446,7 @@
 	 */
 	conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type,
 								direct_addr);
-	if (conn && type == LE_ADV_IND) {
+	if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) {
 		/* Store report for later inclusion by
 		 * mgmt_device_connected
 		 */
@@ -5491,7 +5500,7 @@
 	 * event or send an immediate device found event if the data
 	 * should not be stored for later.
 	 */
-	if (!has_pending_adv_report(hdev)) {
+	if (!ext_adv &&	!has_pending_adv_report(hdev)) {
 		/* If the report will trigger a SCAN_REQ store it for
 		 * later merging.
 		 */
@@ -5526,7 +5535,8 @@
 		/* If the new report will trigger a SCAN_REQ store it for
 		 * later merging.
 		 */
-		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+		if (!ext_adv && (type == LE_ADV_IND ||
+				 type == LE_ADV_SCAN_IND)) {
 			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
 						 rssi, flags, data, len);
 			return;
@@ -5566,7 +5576,7 @@
 			rssi = ev->data[ev->length];
 			process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
 					   ev->bdaddr_type, NULL, 0, rssi,
-					   ev->data, ev->length);
+					   ev->data, ev->length, false);
 		} else {
 			bt_dev_err(hdev, "Dropping invalid advertising data");
 		}
@@ -5638,7 +5648,8 @@
 		if (legacy_evt_type != LE_ADV_INVALID) {
 			process_adv_report(hdev, legacy_evt_type, &ev->bdaddr,
 					   ev->bdaddr_type, NULL, 0, ev->rssi,
-					   ev->data, ev->length);
+					   ev->data, ev->length,
+					   !(evt_type & LE_EXT_ADV_LEGACY_PDU));
 		}
 
 		ptr += sizeof(*ev) + ev->length;
@@ -5836,7 +5847,8 @@
 
 		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
 				   ev->bdaddr_type, &ev->direct_addr,
-				   ev->direct_addr_type, ev->rssi, NULL, 0);
+				   ev->direct_addr_type, ev->rssi, NULL, 0,
+				   false);
 
 		ptr += sizeof(*ev);
 	}
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 6aea65c..45f2ab2e 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -138,11 +138,19 @@
 
 char *get_line(char **stringp)
 {
+	char *orig = *stringp, *next;
+
 	/* do not return the unwanted extra line at EOF */
-	if (*stringp && **stringp == '\0')
+	if (!orig || *orig == '\0')
 		return NULL;
 
-	return strsep(stringp, "\n");
+	next = strchr(orig, '\n');
+	if (next)
+		*next++ = '\0';
+
+	*stringp = next;
+
+	return orig;
 }
 
 /* A list of all modules we processed */
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 7e3ae45..803978d 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2935,6 +2935,10 @@
 	struct hda_codec *codec = dev_to_hda_codec(dev);
 	unsigned int state;
 
+	/* Nothing to do if card registration fails and the component driver never probes */
+	if (!codec->card)
+		return 0;
+
 	cancel_delayed_work_sync(&codec->jackpoll_work);
 	state = hda_call_codec_suspend(codec);
 	if (codec->link_down_at_suspend ||
@@ -2949,6 +2953,10 @@
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
 
+	/* Nothing to do if card registration fails and the component driver never probes */
+	if (!codec->card)
+		return 0;
+
 	codec_display_power(codec, true);
 	snd_hdac_codec_link_up(&codec->core);
 	hda_call_codec_resume(codec);
diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h
index 82e2644..a356fb0 100644
--- a/sound/pci/hda/hda_controller.h
+++ b/sound/pci/hda/hda_controller.h
@@ -41,7 +41,7 @@
 /* 24 unused */
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
-/* 27 unused */
+#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */
 #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28)	/* CORBRP clears itself after reset */
 #define AZX_DCAPS_NO_MSI64      (1 << 29)	/* Stick to 32-bit MSIs */
 #define AZX_DCAPS_SEPARATE_STREAM_TAG	(1 << 30) /* capture and playback use separate stream tag */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 3565e2a..3fbba2e 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -298,7 +298,8 @@
 /* PCH for HSW/BDW; with runtime PM */
 /* no i915 binding for this as HSW/BDW has another controller for HDMI */
 #define AZX_DCAPS_INTEL_PCH \
-	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME)
+	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
+	 AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
 
 /* HSW HDMI */
 #define AZX_DCAPS_INTEL_HASWELL \
@@ -1028,7 +1029,14 @@
 	chip = card->private_data;
 	bus = azx_bus(chip);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
-	pm_runtime_force_suspend(dev);
+	/* An ugly workaround: direct call of __azx_runtime_suspend() and
+	 * __azx_runtime_resume() for old Intel platforms that suffer from
+	 * spurious wakeups after S3 suspend
+	 */
+	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+		__azx_runtime_suspend(chip);
+	else
+		pm_runtime_force_suspend(dev);
 	if (bus->irq >= 0) {
 		free_irq(bus->irq, chip);
 		bus->irq = -1;
@@ -1057,7 +1065,10 @@
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
 
-	pm_runtime_force_resume(dev);
+	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+		__azx_runtime_resume(chip, false);
+	else
+		pm_runtime_force_resume(dev);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 41eaa89..cd46247 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2440,6 +2440,7 @@
 	mutex_lock(&spec->bind_lock);
 	spec->use_acomp_notifier = use_acomp;
 	spec->codec->relaxed_resume = use_acomp;
+	spec->codec->bus->keep_power = 0;
 	/* reprogram each jack detection logic depending on the notifier */
 	for (i = 0; i < spec->num_pins; i++)
 		reprogram_jack_detect(spec->codec,
@@ -2534,7 +2535,6 @@
 	if (!snd_hdac_acomp_init(&codec->bus->core, &spec->drm_audio_ops,
 				 match_bound_vga, 0)) {
 		spec->acomp_registered = true;
-		codec->bus->keep_power = 0;
 	}
 }
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1b2d8e5..29f5878 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5975,6 +5975,16 @@
 		snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ);
 }
 
+static void  alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec,
+			      const struct hda_fixup *fix, int action)
+{
+	if (action != HDA_FIXUP_ACT_INIT)
+		return;
+
+	msleep(100);
+	alc_write_coef_idx(codec, 0x65, 0x0);
+}
+
 /* for hda_fixup_thinkpad_acpi() */
 #include "thinkpad_helper.c"
 
@@ -6152,8 +6162,10 @@
 	ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS,
 	ALC269VC_FIXUP_ACER_HEADSET_MIC,
 	ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE,
-	ALC289_FIXUP_ASUS_G401,
+	ALC289_FIXUP_ASUS_GA401,
+	ALC289_FIXUP_ASUS_GA502,
 	ALC256_FIXUP_ACER_MIC_NO_PRESENCE,
+	ALC285_FIXUP_HP_GPIO_AMP_INIT,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -7363,7 +7375,14 @@
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MIC
 	},
-	[ALC289_FIXUP_ASUS_G401] = {
+	[ALC289_FIXUP_ASUS_GA401] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a11020 }, /* headset mic with jack detect */
+			{ }
+		},
+	},
+	[ALC289_FIXUP_ASUS_GA502] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
 			{ 0x19, 0x03a11020 }, /* headset mic with jack detect */
@@ -7379,6 +7398,12 @@
 		.chained = true,
 		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
 	},
+	[ALC285_FIXUP_HP_GPIO_AMP_INIT] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_gpio_amp_init,
+		.chained = true,
+		.chain_id = ALC285_FIXUP_HP_GPIO_LED
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7529,7 +7554,7 @@
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
-	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
@@ -7561,7 +7586,8 @@
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_G401),
+	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
+	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
@@ -7581,7 +7607,7 @@
 	SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
-	SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC225_FIXUP_HEADSET_JACK),
+	SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 40b7cd1..a69d9e7 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -367,6 +367,7 @@
 		ifnum = 0;
 		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
+	case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */
 	case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */
 	case USB_ID(0x0d9a, 0x00df): /* RTX6001 */
 		ep = 0x81;
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 5b36c58..ba4f338 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2861,6 +2861,7 @@
 	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
+	free_token(token);
 	type = read_token(&token);
 	*tok = token;
 
diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile
index 349bb81..680d883 100644
--- a/tools/lib/traceevent/plugins/Makefile
+++ b/tools/lib/traceevent/plugins/Makefile
@@ -197,7 +197,7 @@
 	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
 	if [ "$$symbol_type" = "U W" ];then				\
 		(echo '{';                                              \
-		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+		$(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\
 		echo '};';                                              \
 		) > $2;                                                 \
 	else                                                            \
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 0a6e75b..28a5d0c 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -56,7 +56,7 @@
 	struct perf_pmu	*cs_etm_pmu;
 	struct evsel *evsel;
 	bool found_etm = false;
-	bool found_spe = false;
+	struct perf_pmu *found_spe = NULL;
 	static struct perf_pmu **arm_spe_pmus = NULL;
 	static int nr_spes = 0;
 	int i = 0;
@@ -74,12 +74,12 @@
 		    evsel->core.attr.type == cs_etm_pmu->type)
 			found_etm = true;
 
-		if (!nr_spes)
+		if (!nr_spes || found_spe)
 			continue;
 
 		for (i = 0; i < nr_spes; i++) {
 			if (evsel->core.attr.type == arm_spe_pmus[i]->type) {
-				found_spe = true;
+				found_spe = arm_spe_pmus[i];
 				break;
 			}
 		}
@@ -96,7 +96,7 @@
 
 #if defined(__aarch64__)
 	if (found_spe)
-		return arm_spe_recording_init(err, arm_spe_pmus[i]);
+		return arm_spe_recording_init(err, found_spe);
 #endif
 
 	/*
diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
index 63a91ec..045723b 100755
--- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh
+++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
@@ -12,7 +12,8 @@
 
 collect_z_record() {
 	echo "Collecting compressed record file:"
-	$perf_tool record -o $trace_file -g -z -F 5000 -- \
+	[[ "$(uname -m)" != s390x ]] && gflag='-g'
+	$perf_tool record -o $trace_file $gflag -z -F 5000 -- \
 		dd count=500 if=/dev/urandom of=/dev/null
 }