diff --git a/Makefile b/Makefile
index 0faa647332816..2d85216b1493d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 6
+SUBLEVEL = 7
 EXTRAVERSION =
 NAME = Trick or Treat
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 327120c0089fe..f67a561e0935e 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -91,7 +91,7 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
-#define TCR_EL2_RES1		((1 << 31) | (1 << 23))
+#define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
 #define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
@@ -276,7 +276,7 @@
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
-#define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index b3e4f9a088b1a..8cf970d219f5d 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -77,11 +77,17 @@
 	.endm
 
 SYM_CODE_START(ftrace_regs_caller)
+#ifdef BTI_C
+	BTI_C
+#endif
 	ftrace_regs_entry	1
 	b	ftrace_common
 SYM_CODE_END(ftrace_regs_caller)
 
 SYM_CODE_START(ftrace_caller)
+#ifdef BTI_C
+	BTI_C
+#endif
 	ftrace_regs_entry	0
 	b	ftrace_common
 SYM_CODE_END(ftrace_caller)
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index fcde3ffa02213..fadb098de1545 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -17,7 +17,12 @@
 # Mike Shaver, Helge Deller and Martin K. Petersen
 #
 
+ifdef CONFIG_PARISC_SELF_EXTRACT
+boot := arch/parisc/boot
+KBUILD_IMAGE := $(boot)/bzImage
+else
 KBUILD_IMAGE := vmlinuz
+endif
 
 NM		= sh $(srctree)/arch/parisc/nm
 CHECKFLAGS	+= -D__hppa__=1
diff --git a/arch/parisc/install.sh b/arch/parisc/install.sh
index 056d588befdd6..70d3cffb02515 100644
--- a/arch/parisc/install.sh
+++ b/arch/parisc/install.sh
@@ -39,6 +39,7 @@ verify "$3"
 if [ -n "${INSTALLKERNEL}" ]; then
   if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
   if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
+  if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi
 fi
 
 # Default install
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 9fb1e794831b0..061119a56fbe8 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -249,30 +249,16 @@ void __init time_init(void)
 static int __init init_cr16_clocksource(void)
 {
 	/*
-	 * The cr16 interval timers are not syncronized across CPUs on
-	 * different sockets, so mark them unstable and lower rating on
-	 * multi-socket SMP systems.
+	 * The cr16 interval timers are not syncronized across CPUs, even if
+	 * they share the same socket.
 	 */
 	if (num_online_cpus() > 1 && !running_on_qemu) {
-		int cpu;
-		unsigned long cpu0_loc;
-		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
-
-		for_each_online_cpu(cpu) {
-			if (cpu == 0)
-				continue;
-			if ((cpu0_loc != 0) &&
-			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
-				continue;
-
-			/* mark sched_clock unstable */
-			clear_sched_clock_stable();
-
-			clocksource_cr16.name = "cr16_unstable";
-			clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
-			clocksource_cr16.rating = 0;
-			break;
-		}
+		/* mark sched_clock unstable */
+		clear_sched_clock_stable();
+
+		clocksource_cr16.name = "cr16_unstable";
+		clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
+		clocksource_cr16.rating = 0;
 	}
 
 	/* register at clocksource framework */
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index a52af8fbf5711..8322ca86d5acf 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1092,15 +1092,6 @@ static phys_addr_t ddw_memory_hotplug_max(void)
 	phys_addr_t max_addr = memory_hotplug_max();
 	struct device_node *memory;
 
-	/*
-	 * The "ibm,pmemory" can appear anywhere in the address space.
-	 * Assuming it is still backed by page structs, set the upper limit
-	 * for the huge DMA window as MAX_PHYSMEM_BITS.
-	 */
-	if (of_find_node_by_type(NULL, "ibm,pmemory"))
-		return (sizeof(phys_addr_t) * 8 <= MAX_PHYSMEM_BITS) ?
-			(phys_addr_t) -1 : (1ULL << MAX_PHYSMEM_BITS);
-
 	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
 		int n_mem_addr_cells, n_mem_size_cells, len;
@@ -1365,8 +1356,10 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		len = order_base_2(query.largest_available_block << page_shift);
 		win_name = DMA64_PROPNAME;
 	} else {
-		direct_mapping = true;
-		win_name = DIRECT64_PROPNAME;
+		direct_mapping = !default_win_removed ||
+			(len == MAX_PHYSMEM_BITS) ||
+			(!pmem_present && (len == max_ram_len));
+		win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
 	}
 
 	ret = create_ddw(dev, ddw_avail, &create, page_shift, len);
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index e4dc64cc9c555..287bb88f76986 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -14,12 +14,13 @@
 
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
-#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
+#define ZPCI_IOMAP_ADDR_SHIFT		62
+#define ZPCI_IOMAP_ADDR_BASE		(1UL << ZPCI_IOMAP_ADDR_SHIFT)
 #define ZPCI_IOMAP_ADDR_OFF_MASK	((1UL << ZPCI_IOMAP_SHIFT) - 1)
 #define ZPCI_IOMAP_MAX_ENTRIES							\
-	((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT))
+	(1UL << (ZPCI_IOMAP_ADDR_SHIFT - ZPCI_IOMAP_SHIFT))
 #define ZPCI_IOMAP_ADDR_IDX_MASK						\
-	(~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE)
+	((ZPCI_IOMAP_ADDR_BASE - 1) & ~ZPCI_IOMAP_ADDR_OFF_MASK)
 
 struct zpci_iomap_entry {
 	u32 fh;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d77269f168948..ee67215a678a5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -816,9 +816,6 @@ static void __init setup_memory(void)
 		storage_key_init_range(start, end);
 
 	psw_set_key(PAGE_DEFAULT_KEY);
-
-	/* Only cosmetics */
-	memblock_enforce_memory_limit(memblock_end_of_DRAM());
 }
 
 static void __init relocate_amode31_section(void)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index e38a4cf795d96..97b1f84bb53f8 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	ud2
 1:
 #endif
+#ifdef CONFIG_XEN_PV
+	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
+#endif
+
 	POP_REGS pop_rdi=0
 
 	/*
@@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 .Lparanoid_entry_checkgs:
 	/* EBX = 1 -> kernel GSBASE active, no restore required */
 	movl	$1, %ebx
+
 	/*
 	 * The kernel-enforced convention is a negative GSBASE indicates
 	 * a kernel value. No SWAPGS needed on entry and exit.
@@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
 	testl	%edx, %edx
-	jns	.Lparanoid_entry_swapgs
-	ret
+	js	.Lparanoid_kernel_gsbase
 
-.Lparanoid_entry_swapgs:
+	/* EBX = 0 -> SWAPGS required on exit */
+	xorl	%ebx, %ebx
 	swapgs
+.Lparanoid_kernel_gsbase:
 
-	/*
-	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
-	 * unconditional CR3 write, even in the PTI case.  So do an lfence
-	 * to prevent GS speculation, regardless of whether PTI is enabled.
-	 */
 	FENCE_SWAPGS_KERNEL_ENTRY
-
-	/* EBX = 0 -> SWAPGS required on exit */
-	xorl	%ebx, %ebx
 	ret
 SYM_CODE_END(paranoid_entry)
 
@@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry)
 	pushq	%r12
 	ret
 
-.Lerror_entry_done_lfence:
-	FENCE_SWAPGS_KERNEL_ENTRY
-.Lerror_entry_done:
-	ret
-
 	/*
 	 * There are two places in the kernel that can potentially fault with
 	 * usergs. Handle them here.  B stepping K8s sometimes report a
@@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
-	FENCE_SWAPGS_USER_ENTRY
-	jmp .Lerror_entry_done
+
+	/*
+	 * Issue an LFENCE to prevent GS speculation, regardless of whether it is a
+	 * kernel or user gsbase.
+	 */
+.Lerror_entry_done_lfence:
+	FENCE_SWAPGS_KERNEL_ENTRY
+	ret
 
 .Lbstep_iret:
 	/* Fix truncated RIP */
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index d20eef3d452a5..b6d48ca5b0f17 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -348,20 +348,13 @@ static void __init hv_get_partition_id(void)
  */
 void __init hyperv_init(void)
 {
-	u64 guest_id, required_msrs;
+	u64 guest_id;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int cpuhp;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
 
-	/* Absolutely required MSRs */
-	required_msrs = HV_MSR_HYPERCALL_AVAILABLE |
-		HV_MSR_VP_INDEX_AVAILABLE;
-
-	if ((ms_hyperv.features & required_msrs) != required_msrs)
-		return;
-
 	if (hv_common_init())
 		return;
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e095c28d27ae8..ef6316fef99ff 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -163,12 +163,22 @@ static uint32_t  __init ms_hyperv_platform(void)
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
-	if (eax >= HYPERV_CPUID_MIN &&
-	    eax <= HYPERV_CPUID_MAX &&
-	    !memcmp("Microsoft Hv", hyp_signature, 12))
-		return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+	if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX ||
+	    memcmp("Microsoft Hv", hyp_signature, 12))
+		return 0;
 
-	return 0;
+	/* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */
+	eax = cpuid_eax(HYPERV_CPUID_FEATURES);
+	if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) {
+		pr_warn("x86/hyperv: HYPERCALL MSR not available.\n");
+		return 0;
+	}
+	if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) {
+		pr_warn("x86/hyperv: VP_INDEX MSR not available.\n");
+		return 0;
+	}
+
+	return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
 }
 
 static unsigned char hv_get_nmi_reason(void)
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 88401675dabb0..a0064cf77e562 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -294,11 +294,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 				   char *dst, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
-	char __user *target = (char __user *)dst;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __put_user() independent of whether kernel or user
@@ -320,26 +315,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *target = (u8 __user *)dst;
+
 		memcpy(&d1, buf, 1);
 		if (__put_user(d1, target))
 			goto fault;
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *target = (u16 __user *)dst;
+
 		memcpy(&d2, buf, 2);
 		if (__put_user(d2, target))
 			goto fault;
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *target = (u32 __user *)dst;
+
 		memcpy(&d4, buf, 4);
 		if (__put_user(d4, target))
 			goto fault;
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *target = (u64 __user *)dst;
+
 		memcpy(&d8, buf, 8);
 		if (__put_user(d8, target))
 			goto fault;
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
@@ -362,11 +373,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 				  char *src, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT;
-	char __user *s = (char __user *)src;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __get_user() independent of whether kernel or user
@@ -388,26 +394,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *s = (u8 __user *)src;
+
 		if (__get_user(d1, s))
 			goto fault;
 		memcpy(buf, &d1, 1);
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *s = (u16 __user *)src;
+
 		if (__get_user(d2, s))
 			goto fault;
 		memcpy(buf, &d2, 2);
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *s = (u32 __user *)src;
+
 		if (__get_user(d4, s))
 			goto fault;
 		memcpy(buf, &d4, 4);
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *s = (u64 __user *)src;
 		if (__get_user(d8, s))
 			goto fault;
 		memcpy(buf, &d8, 8);
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2e076a459a0c0..a698196377be9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason)
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
+static void __init tsc_disable_clocksource_watchdog(void)
+{
+	clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+	clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+}
+
 static void __init check_system_tsc_reliable(void)
 {
 #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
@@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void)
 #endif
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		tsc_clocksource_reliable = 1;
+
+	/*
+	 * Disable the clocksource watchdog when the system has:
+	 *  - TSC running at constant frequency
+	 *  - TSC which does not stop in C-States
+	 *  - the TSC_ADJUST register which allows to detect even minimal
+	 *    modifications
+	 *  - not more than two sockets. As the number of sockets cannot be
+	 *    evaluated at the early boot stage where this has to be
+	 *    invoked, check the number of online memory nodes as a
+	 *    fallback solution which is an reasonable estimate.
+	 */
+	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
+	    boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
+	    nr_online_nodes <= 2)
+		tsc_disable_clocksource_watchdog();
 }
 
 /*
@@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void)
 	if (tsc_unstable)
 		goto unreg;
 
-	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
 
@@ -1527,7 +1547,7 @@ void __init tsc_init(void)
 	}
 
 	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+		tsc_disable_clocksource_watchdog();
 
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 50a4515fe0ad1..9452dc9664b51 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -30,6 +30,7 @@ struct tsc_adjust {
 };
 
 static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust);
+static struct timer_list tsc_sync_check_timer;
 
 /*
  * TSC's on different sockets may be reset asynchronously.
@@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume)
 	}
 }
 
+/*
+ * Normally the tsc_sync will be checked every time system enters idle
+ * state, but there is still caveat that a system won't enter idle,
+ * either because it's too busy or configured purposely to not enter
+ * idle.
+ *
+ * So setup a periodic timer (every 10 minutes) to make sure the check
+ * is always on.
+ */
+
+#define SYNC_CHECK_INTERVAL		(HZ * 600)
+
+static void tsc_sync_check_timer_fn(struct timer_list *unused)
+{
+	int next_cpu;
+
+	tsc_verify_tsc_adjust(false);
+
+	/* Run the check for all onlined CPUs in turn */
+	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(cpu_online_mask);
+
+	tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL;
+	add_timer_on(&tsc_sync_check_timer, next_cpu);
+}
+
+static int __init start_sync_check_timer(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable)
+		return 0;
+
+	timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0);
+	tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL;
+	add_timer(&tsc_sync_check_timer);
+
+	return 0;
+}
+late_initcall(start_sync_check_timer);
+
 static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
 				   unsigned int cpu, bool bootcpu)
 {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d6ac32f3f650c..95f5527646e4a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
 {
 	int highest_irr;
-	if (apic->vcpu->arch.apicv_active)
+	if (kvm_x86_ops.sync_pir_to_irr)
 		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
 	else
 		highest_irr = apic_find_highest_irr(apic);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0e0f960a0bf8e..0a88cb4f731f4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1592,7 +1592,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 		flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp);
 
 	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
+		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
 
 	return flush;
 }
@@ -2188,10 +2188,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
 	iterator->shadow_addr = root;
 	iterator->level = vcpu->arch.mmu->shadow_root_level;
 
-	if (iterator->level == PT64_ROOT_4LEVEL &&
+	if (iterator->level >= PT64_ROOT_4LEVEL &&
 	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
 	    !vcpu->arch.mmu->direct_map)
-		--iterator->level;
+		iterator->level = PT32E_ROOT_LEVEL;
 
 	if (iterator->level == PT32E_ROOT_LEVEL) {
 		/*
@@ -4852,7 +4852,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	struct kvm_mmu_role_regs regs = {
 		.cr0 = cr0,
-		.cr4 = cr4,
+		.cr4 = cr4 & ~X86_CR4_PKE,
 		.efer = efer,
 	};
 	union kvm_mmu_role new_role;
@@ -4916,7 +4916,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->direct_map = false;
 
 	update_permission_bitmask(context, true);
-	update_pkru_bitmask(context);
+	context->pkru_mask = 0;
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
@@ -5369,7 +5369,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE);
+	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -5474,8 +5474,8 @@ slot_handle_level(struct kvm *kvm, const struct kvm_memory_slot *memslot,
 }
 
 static __always_inline bool
-slot_handle_leaf(struct kvm *kvm, const struct kvm_memory_slot *memslot,
-		 slot_level_handler fn, bool flush_on_yield)
+slot_handle_level_4k(struct kvm *kvm, const struct kvm_memory_slot *memslot,
+		     slot_level_handler fn, bool flush_on_yield)
 {
 	return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K,
 				 PG_LEVEL_4K, flush_on_yield);
@@ -5855,21 +5855,21 @@ restart:
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
-		flush = slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
-		if (flush)
+		/*
+		 * Zap only 4k SPTEs since the legacy MMU only supports dirty
+		 * logging at a 4k granularity and never creates collapsible
+		 * 2m SPTEs during dirty logging.
+		 */
+		if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true))
 			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
-		if (flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
 		read_unlock(&kvm->mmu_lock);
 	}
 }
@@ -5896,8 +5896,11 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
-		flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty,
-					 false);
+		/*
+		 * Clear dirty bits only on 4k SPTEs since the legacy MMU only
+		 * support dirty logging at a 4k granularity.
+		 */
+		flush = slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false);
 		write_unlock(&kvm->mmu_lock);
 	}
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 64ccfc1fa5535..0e4227b59d7bb 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -316,9 +316,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
 	int level = sp->role.level;
 	gfn_t base_gfn = sp->gfn;
-	u64 old_child_spte;
-	u64 *sptep;
-	gfn_t gfn;
 	int i;
 
 	trace_kvm_mmu_prepare_zap_page(sp);
@@ -326,8 +323,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = rcu_dereference(pt) + i;
-		gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 *sptep = rcu_dereference(pt) + i;
+		gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 old_child_spte;
 
 		if (shared) {
 			/*
@@ -373,7 +371,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 				    shared);
 	}
 
-	kvm_flush_remote_tlbs_with_address(kvm, gfn,
+	kvm_flush_remote_tlbs_with_address(kvm, base_gfn,
 					   KVM_PAGES_PER_HPAGE(level + 1));
 
 	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
@@ -1083,8 +1081,8 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 	struct kvm_mmu_page *root;
 
 	for_each_tdp_mmu_root(kvm, root, range->slot->as_id)
-		flush |= zap_gfn_range(kvm, root, range->start, range->end,
-				       range->may_block, flush, false);
+		flush = zap_gfn_range(kvm, root, range->start, range->end,
+				      range->may_block, flush, false);
 
 	return flush;
 }
@@ -1415,10 +1413,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
  * Clear leaf entries which could be replaced by large mappings, for
  * GFNs within the slot.
  */
-static bool zap_collapsible_spte_range(struct kvm *kvm,
+static void zap_collapsible_spte_range(struct kvm *kvm,
 				       struct kvm_mmu_page *root,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+				       const struct kvm_memory_slot *slot)
 {
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
@@ -1429,10 +1426,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
-			flush = false;
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
-		}
 
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
@@ -1444,6 +1439,7 @@ retry:
 							    pfn, PG_LEVEL_NUM))
 			continue;
 
+		/* Note, a successful atomic zap also does a remote TLB flush. */
 		if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) {
 			/*
 			 * The iter must explicitly re-read the SPTE because
@@ -1452,30 +1448,24 @@ retry:
 			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
 			goto retry;
 		}
-		flush = true;
 	}
 
 	rcu_read_unlock();
-
-	return flush;
 }
 
 /*
  * Clear non-leaf entries (and free associated page tables) which could
  * be replaced by large mappings, for GFNs within the slot.
  */
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot)
 {
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
-		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
-
-	return flush;
+		zap_collapsible_spte_range(kvm, root, slot);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 358f447d40120..ba3681cd38ab4 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -66,9 +66,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				       struct kvm_memory_slot *slot,
 				       gfn_t gfn, unsigned long mask,
 				       bool wrprot);
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush);
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot);
 
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 8052d92069e01..2fb6a6f00290d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -988,16 +988,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int cpu = get_cpu();
 
+	WARN_ON(cpu != vcpu->cpu);
 	svm->avic_is_running = is_run;
 
-	if (!kvm_vcpu_apicv_active(vcpu))
-		return;
-
-	if (is_run)
-		avic_vcpu_load(vcpu, vcpu->cpu);
-	else
-		avic_vcpu_put(vcpu);
+	if (kvm_vcpu_apicv_active(vcpu)) {
+		if (is_run)
+			avic_vcpu_load(vcpu, cpu);
+		else
+			avic_vcpu_put(vcpu);
+	}
+	put_cpu();
 }
 
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index fdf587f19c5fb..e152241d1d709 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -282,7 +282,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
-	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->reserved_bits = 0xfffffff000280000ull;
 	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index ff19ce0780fea..134c4ea5e6ad8 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1805,6 +1805,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 	mirror_sev->fd = source_sev.fd;
 	mirror_sev->es_active = source_sev.es_active;
 	mirror_sev->handle = source_sev.handle;
+	INIT_LIST_HEAD(&mirror_sev->regions_list);
 	/*
 	 * Do not copy ap_jump_table. Since the mirror does not share the same
 	 * KVM contexts as the original, and they may have different
@@ -2316,7 +2317,7 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 }
 
 #define GHCB_SCRATCH_AREA_LIMIT		(16ULL * PAGE_SIZE)
-static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
+static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct ghcb *ghcb = svm->ghcb;
@@ -2327,14 +2328,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
-		return false;
+		return -EINVAL;
 	}
 
 	scratch_gpa_end = scratch_gpa_beg + len;
 	if (scratch_gpa_end < scratch_gpa_beg) {
 		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
 		       len, scratch_gpa_beg);
-		return false;
+		return -EINVAL;
 	}
 
 	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
@@ -2352,7 +2353,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		    scratch_gpa_end > ghcb_scratch_end) {
 			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
 			       scratch_gpa_beg, scratch_gpa_end);
-			return false;
+			return -EINVAL;
 		}
 
 		scratch_va = (void *)svm->ghcb;
@@ -2365,18 +2366,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		if (len > GHCB_SCRATCH_AREA_LIMIT) {
 			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
 			       len, GHCB_SCRATCH_AREA_LIMIT);
-			return false;
+			return -EINVAL;
 		}
 		scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT);
 		if (!scratch_va)
-			return false;
+			return -ENOMEM;
 
 		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
 			/* Unable to copy scratch area from guest */
 			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
 
 			kfree(scratch_va);
-			return false;
+			return -EFAULT;
 		}
 
 		/*
@@ -2392,7 +2393,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	svm->ghcb_sa = scratch_va;
 	svm->ghcb_sa_len = len;
 
-	return true;
+	return 0;
 }
 
 static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
@@ -2531,10 +2532,10 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-	ret = -EINVAL;
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
-		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
+		ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
+		if (ret)
 			break;
 
 		ret = kvm_sev_es_mmio_read(vcpu,
@@ -2543,7 +2544,8 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 					   svm->ghcb_sa);
 		break;
 	case SVM_VMGEXIT_MMIO_WRITE:
-		if (!setup_vmgexit_scratch(svm, false, control->exit_info_2))
+		ret = setup_vmgexit_scratch(svm, false, control->exit_info_2);
+		if (ret)
 			break;
 
 		ret = kvm_sev_es_mmio_write(vcpu,
@@ -2586,6 +2588,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
 			    control->exit_info_1, control->exit_info_2);
+		ret = -EINVAL;
 		break;
 	default:
 		ret = svm_invoke_exit_handler(vcpu, exit_code);
@@ -2598,6 +2601,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 {
 	int count;
 	int bytes;
+	int r;
 
 	if (svm->vmcb->control.exit_info_2 > INT_MAX)
 		return -EINVAL;
@@ -2606,8 +2610,9 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 	if (unlikely(check_mul_overflow(count, size, &bytes)))
 		return -EINVAL;
 
-	if (!setup_vmgexit_scratch(svm, in, bytes))
-		return -EINVAL;
+	r = setup_vmgexit_scratch(svm, in, bytes);
+	if (r)
+		return r;
 
 	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 989685098b3ea..1fce044beebea 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4592,7 +4592,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_irr_update = svm_hwapic_irr_update,
 	.hwapic_isr_update = svm_hwapic_isr_update,
-	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
 	.apicv_post_state_restore = avic_post_state_restore,
 
 	.set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8936d8383b2ee..e97a11abc1d85 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1180,29 +1180,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	WARN_ON(!enable_vpid);
 
 	/*
-	 * If VPID is enabled and used by vmc12, but L2 does not have a unique
-	 * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate
-	 * a VPID for L2, flush the current context as the effective ASID is
-	 * common to both L1 and L2.
-	 *
-	 * Defer the flush so that it runs after vmcs02.EPTP has been set by
-	 * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid
-	 * redundant flushes further down the nested pipeline.
-	 *
-	 * If a TLB flush isn't required due to any of the above, and vpid12 is
-	 * changing then the new "virtual" VPID (vpid12) will reuse the same
-	 * "real" VPID (vpid02), and so needs to be flushed.  There's no direct
-	 * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for
-	 * all nested vCPUs.  Remember, a flush on VM-Enter does not invalidate
-	 * guest-physical mappings, so there is no need to sync the nEPT MMU.
+	 * VPID is enabled and in use by vmcs12.  If vpid12 is changing, then
+	 * emulate a guest TLB flush as KVM does not track vpid12 history nor
+	 * is the VPID incorporated into the MMU context.  I.e. KVM must assume
+	 * that the new vpid12 has never been used and thus represents a new
+	 * guest ASID that cannot have entries in the TLB.
 	 */
-	if (!nested_has_guest_tlb_tag(vcpu)) {
-		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-	} else if (is_vmenter &&
-		   vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+	if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
 		vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+		return;
 	}
+
+	/*
+	 * If VPID is enabled, used by vmc12, and vpid12 is not changing but
+	 * does not have a unique TLB tag (ASID), i.e. EPT is disabled and
+	 * KVM was unable to allocate a VPID for L2, flush the current context
+	 * as the effective ASID is common to both L1 and L2.
+	 */
+	if (!nested_has_guest_tlb_tag(vcpu))
+		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 }
 
 static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
@@ -2612,8 +2609,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-				     vmcs12->guest_ia32_perf_global_ctrl)))
+				     vmcs12->guest_ia32_perf_global_ctrl))) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
+	}
 
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
@@ -3358,8 +3357,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	};
 	u32 failed_index;
 
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
 		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
@@ -4516,9 +4514,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		(void)nested_get_evmcs_page(vcpu);
 	}
 
-	/* Service the TLB flush request for L2 before switching to L1. */
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	/* Service pending TLB flush requests for L2 before switching to L1. */
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	/*
 	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 5f81ef092bd43..1c94783b5a54c 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 
 #include "lapic.h"
+#include "irq.h"
 #include "posted_intr.h"
 #include "trace.h"
 #include "vmx.h"
@@ -77,13 +78,18 @@ after_clear_sn:
 		pi_set_on(pi_desc);
 }
 
+static bool vmx_can_use_vtd_pi(struct kvm *kvm)
+{
+	return irqchip_in_kernel(kvm) && enable_apicv &&
+		kvm_arch_has_assigned_device(kvm) &&
+		irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return 0;
 
 	WARN_ON(irqs_disabled());
@@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 	struct vcpu_data vcpu_info;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP) ||
-	    !kvm_vcpu_apicv_active(kvm->vcpus[0]))
+	if (!vmx_can_use_vtd_pi(kvm))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 671ff4150fcbf..dacdf2395f01a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2916,6 +2916,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return nested_get_vpid02(vcpu);
+	return to_vmx(vcpu)->vpid;
+}
+
 static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
@@ -2928,31 +2935,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 	if (enable_ept)
 		ept_sync_context(construct_eptp(vcpu, root_hpa,
 						mmu->shadow_root_level));
-	else if (!is_guest_mode(vcpu))
-		vpid_sync_context(to_vmx(vcpu)->vpid);
 	else
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
 {
 	/*
-	 * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in
+	 * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
 	 * vmx_flush_tlb_guest() for an explanation of why this is ok.
 	 */
-	vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr);
+	vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr);
 }
 
 static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 {
 	/*
-	 * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0
-	 * or a vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit
-	 * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is
+	 * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a
+	 * vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit are
+	 * required to flush GVA->{G,H}PA mappings from the TLB if vpid is
 	 * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed),
 	 * i.e. no explicit INVVPID is necessary.
 	 */
-	vpid_sync_context(to_vmx(vcpu)->vpid);
+	vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
@@ -6237,9 +6242,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
-	bool max_irr_updated;
+	bool got_posted_interrupt;
 
-	if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm))
+	if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
 		return -EIO;
 
 	if (pi_test_on(&vmx->pi_desc)) {
@@ -6249,22 +6254,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
-		max_irr_updated =
+		got_posted_interrupt =
 			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
-
-		/*
-		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, this may cause a vmexit or it may
-		 * be injected into L2.  Either way, this interrupt will be
-		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
-		 * virtual interrupt delivery to inject L1 interrupts into L2.
-		 */
-		if (is_guest_mode(vcpu) && max_irr_updated)
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
+		got_posted_interrupt = false;
 	}
-	vmx_hwapic_irr_update(vcpu, max_irr);
+
+	/*
+	 * Newly recognized interrupts are injected via either virtual interrupt
+	 * delivery (RVI) or KVM_REQ_EVENT.  Virtual interrupt delivery is
+	 * disabled in two cases:
+	 *
+	 * 1) If L2 is running and the vCPU has a new pending interrupt.  If L1
+	 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a
+	 * VM-Exit to L1.  If L1 doesn't want to exit, the interrupt is injected
+	 * into L2, but KVM doesn't use virtual interrupt delivery to inject
+	 * interrupts into L2, and so KVM_REQ_EVENT is again needed.
+	 *
+	 * 2) If APICv is disabled for this vCPU, assigned devices may still
+	 * attempt to post interrupts.  The posted interrupt vector will cause
+	 * a VM-Exit and the subsequent entry will call sync_pir_to_irr.
+	 */
+	if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu))
+		vmx_set_rvi(max_irr);
+	else if (got_posted_interrupt)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
 	return max_irr;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 16c7465619f7a..b7aa845f7beee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3193,6 +3193,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	static_call(kvm_x86_tlb_flush_guest)(vcpu);
 }
 
+
+static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	static_call(kvm_x86_tlb_flush_current)(vcpu);
+}
+
+/*
+ * Service "local" TLB flush requests, which are specific to the current MMU
+ * context.  In addition to the generic event handling in vcpu_enter_guest(),
+ * TLB flushes that are targeted at an MMU context also need to be serviced
+ * prior before nested VM-Enter/VM-Exit.
+ */
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
+		kvm_vcpu_flush_tlb_guest(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests);
+
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
@@ -4382,8 +4405,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	if (vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
 }
@@ -9410,8 +9432,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 		if (ioapic_in_kernel(vcpu->kvm))
 			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
@@ -9530,10 +9551,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			/* Flushing all ASIDs flushes the current ASID... */
 			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-			kvm_vcpu_flush_tlb_current(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
-			kvm_vcpu_flush_tlb_guest(vcpu);
+		kvm_service_local_tlb_flush_requests(vcpu);
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -9684,10 +9702,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	/*
 	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.
+	 * notified with kvm_vcpu_kick.  Assigned devices can
+	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
+	 * so do it even if APICv is disabled on this vCPU.
 	 */
-	if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	if (kvm_lapic_enabled(vcpu))
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	if (kvm_vcpu_exit_request(vcpu)) {
 		vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -9723,8 +9743,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		if (kvm_lapic_enabled(vcpu))
+			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
 			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 9776a1db8ea85..bc7ef6820ac8f 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
 
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
 int kvm_check_nested_events(struct kvm_vcpu *vcpu);
 
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
@@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
 }
 
-static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.tlb_flush;
-	static_call(kvm_x86_tlb_flush_current)(vcpu);
-}
-
 static inline int is_pae(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 31b5856010cba..d3eee1ebcf1d5 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -72,6 +72,7 @@ static void __init setup_real_mode(void)
 #ifdef CONFIG_X86_64
 	u64 *trampoline_pgd;
 	u64 efer;
+	int i;
 #endif
 
 	base = (unsigned char *)real_mode_header;
@@ -128,8 +129,17 @@ static void __init setup_real_mode(void)
 	trampoline_header->flags = 0;
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+
+	/* Map the real mode stub as virtual == physical */
 	trampoline_pgd[0] = trampoline_pgd_entry.pgd;
-	trampoline_pgd[511] = init_top_pgt[511].pgd;
+
+	/*
+	 * Include the entirety of the kernel mapping into the trampoline
+	 * PGD.  This way, all mappings present in the normal kernel page
+	 * tables are usable while running on trampoline_pgd.
+	 */
+	for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+		trampoline_pgd[i] = init_top_pgt[i].pgd;
 #endif
 
 	sme_sev_setup_real_mode(trampoline_header);
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1e626444712be..3bebf66569b48 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -20,6 +20,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <../entry/calling.h>
 
 /*
  * Enable events.  This clears the event mask and tests the pending
@@ -191,6 +192,25 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
+/*
+ * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is
+ * also the kernel stack.  Reusing swapgs_restore_regs_and_return_to_usermode()
+ * in XEN pv would cause %rsp to move up to the top of the kernel stack and
+ * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI
+ * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET
+ * frame at the same address is useless.
+ */
+SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode)
+	UNWIND_HINT_REGS
+	POP_REGS
+
+	/* stackleak_erase() can work safely on the kernel stack. */
+	STACKLEAK_ERASE_NOCLOBBER
+
+	addq	$8, %rsp	/* skip regs->orig_ax */
+	jmp xen_iret
+SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)
+
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 186cbf90c8ead..812731e80f8e0 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -442,6 +442,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	/* AMD */
 	{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
 	{ PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
+	{ PCI_VDEVICE(AMD, 0x7901), board_ahci_mobile }, /* AMD Green Sardine */
 	/* AMD is using RAID class only for ahci controllers */
 	{ PCI_VENDOR_ID_AMD, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
 	  PCI_CLASS_STORAGE_RAID << 8, 0xffffff, board_ahci },
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 5b3fa2cbe7223..395772fa39432 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -2305,6 +2305,18 @@ int ahci_port_resume(struct ata_port *ap)
 EXPORT_SYMBOL_GPL(ahci_port_resume);
 
 #ifdef CONFIG_PM
+static void ahci_handle_s2idle(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	u32 devslp;
+
+	if (pm_suspend_via_firmware())
+		return;
+	devslp = readl(port_mmio + PORT_DEVSLP);
+	if ((devslp & PORT_DEVSLP_ADSE))
+		ata_msleep(ap, devslp_idle_timeout);
+}
+
 static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
 {
 	const char *emsg = NULL;
@@ -2318,6 +2330,9 @@ static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
 		ata_port_freeze(ap);
 	}
 
+	if (acpi_storage_d3(ap->host->dev))
+		ahci_handle_s2idle(ap);
+
 	ahci_rpm_put_port(ap);
 	return rc;
 }
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index e5838b23c9e0a..3b31a4f596d86 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1394,6 +1394,14 @@ static int sata_fsl_init_controller(struct ata_host *host)
 	return 0;
 }
 
+static void sata_fsl_host_stop(struct ata_host *host)
+{
+        struct sata_fsl_host_priv *host_priv = host->private_data;
+
+        iounmap(host_priv->hcr_base);
+        kfree(host_priv);
+}
+
 /*
  * scsi mid-layer and libata interface structures
  */
@@ -1426,6 +1434,8 @@ static struct ata_port_operations sata_fsl_ops = {
 	.port_start = sata_fsl_port_start,
 	.port_stop = sata_fsl_port_stop,
 
+	.host_stop      = sata_fsl_host_stop,
+
 	.pmp_attach = sata_fsl_pmp_attach,
 	.pmp_detach = sata_fsl_pmp_detach,
 };
@@ -1480,9 +1490,9 @@ static int sata_fsl_probe(struct platform_device *ofdev)
 	host_priv->ssr_base = ssr_base;
 	host_priv->csr_base = csr_base;
 
-	irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
-	if (!irq) {
-		dev_err(&ofdev->dev, "invalid irq from platform\n");
+	irq = platform_get_irq(ofdev, 0);
+	if (irq < 0) {
+		retval = irq;
 		goto error_exit_with_cleanup;
 	}
 	host_priv->irq = irq;
@@ -1557,10 +1567,6 @@ static int sata_fsl_remove(struct platform_device *ofdev)
 
 	ata_host_detach(host);
 
-	irq_dispose_mapping(host_priv->irq);
-	iounmap(host_priv->hcr_base);
-	kfree(host_priv);
-
 	return 0;
 }
 
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a08f53f208bfe..b404cc46cbda7 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -191,6 +191,8 @@ struct ipmi_user {
 	struct work_struct remove_work;
 };
 
+static struct workqueue_struct *remove_work_wq;
+
 static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
 	__acquires(user->release_barrier)
 {
@@ -1261,7 +1263,7 @@ static void free_user(struct kref *ref)
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
 
 	/* SRCU cleanup must happen in task context. */
-	schedule_work(&user->remove_work);
+	queue_work(remove_work_wq, &user->remove_work);
 }
 
 static void _ipmi_destroy_user(struct ipmi_user *user)
@@ -5153,6 +5155,13 @@ static int ipmi_init_msghandler(void)
 
 	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
 
+	remove_work_wq = create_singlethread_workqueue("ipmi-msghandler-remove-wq");
+	if (!remove_work_wq) {
+		pr_err("unable to create ipmi-msghandler-remove-wq workqueue");
+		rv = -ENOMEM;
+		goto out;
+	}
+
 	initialized = true;
 
 out:
@@ -5178,6 +5187,8 @@ static void __exit cleanup_ipmi(void)
 	int count;
 
 	if (initialized) {
+		destroy_workqueue(remove_work_wq);
+
 		atomic_notifier_chain_unregister(&panic_notifier_list,
 						 &panic_block);
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 284e940084c61..fcb44352623ee 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1004,10 +1004,9 @@ static struct kobj_type ktype_cpufreq = {
 	.release	= cpufreq_sysfs_release,
 };
 
-static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
+static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu,
+				struct device *dev)
 {
-	struct device *dev = get_cpu_device(cpu);
-
 	if (unlikely(!dev))
 		return;
 
@@ -1391,7 +1390,7 @@ static int cpufreq_online(unsigned int cpu)
 	if (new_policy) {
 		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
-			add_cpu_dev_symlink(policy, j);
+			add_cpu_dev_symlink(policy, j, get_cpu_device(j));
 		}
 
 		policy->min_freq_req = kzalloc(2 * sizeof(*policy->min_freq_req),
@@ -1565,7 +1564,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	/* Create sysfs link on CPU registration */
 	policy = per_cpu(cpufreq_cpu_data, cpu);
 	if (policy)
-		add_cpu_dev_symlink(policy, cpu);
+		add_cpu_dev_symlink(policy, cpu, dev);
 
 	return 0;
 }
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index 23a7e74ef9666..8660508f3684f 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -289,7 +289,7 @@ static void system_heap_dma_buf_release(struct dma_buf *dmabuf)
 	int i;
 
 	table = &buffer->sg_table;
-	for_each_sg(table->sgl, sg, table->nents, i) {
+	for_each_sgtable_sg(table, sg, i) {
 		struct page *page = sg_page(sg);
 
 		__free_pages(page, compound_order(page));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 978ac927ac11d..a799e0b1ff736 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -386,6 +386,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 			"%s", "xgmi_hive_info");
 	if (ret) {
 		dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+		kobject_put(&hive->kobj);
 		kfree(hive);
 		hive = NULL;
 		goto pro_end;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f8fce9d05f50c..4f2e0cc8a51a8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1225,6 +1225,11 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	bool hanging;
 
 	dqm_lock(dqm);
+	if (!dqm->sched_running) {
+		dqm_unlock(dqm);
+		return 0;
+	}
+
 	if (!dqm->is_hws_hang)
 		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	hanging = dqm->is_hws_hang || dqm->is_resetting;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 7af0d58c231b6..74885ff77f96a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -36,6 +36,8 @@
 #include "dm_helpers.h"
 
 #include "dc_link_ddc.h"
+#include "ddc_service_types.h"
+#include "dpcd_defs.h"
 
 #include "i2caux_interface.h"
 #include "dmub_cmd.h"
@@ -155,6 +157,16 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 };
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
+static bool needs_dsc_aux_workaround(struct dc_link *link)
+{
+	if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 &&
+	    (link->dpcd_caps.dpcd_rev.raw == DPCD_REV_14 || link->dpcd_caps.dpcd_rev.raw == DPCD_REV_12) &&
+	    link->dpcd_caps.sink_count.bits.SINK_COUNT >= 2)
+		return true;
+
+	return false;
+}
+
 static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector)
 {
 	struct dc_sink *dc_sink = aconnector->dc_sink;
@@ -164,7 +176,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
 	u8 *dsc_branch_dec_caps = NULL;
 
 	aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port);
-#if defined(CONFIG_HP_HOOK_WORKAROUND)
+
 	/*
 	 * drm_dp_mst_dsc_aux_for_port() will return NULL for certain configs
 	 * because it only check the dsc/fec caps of the "port variable" and not the dock
@@ -174,10 +186,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
 	 * Workaround: explicitly check the use case above and use the mst dock's aux as dsc_aux
 	 *
 	 */
-
-	if (!aconnector->dsc_aux && !port->parent->port_parent)
+	if (!aconnector->dsc_aux && !port->parent->port_parent &&
+	    needs_dsc_aux_workaround(aconnector->dc_link))
 		aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux;
-#endif
+
 	if (!aconnector->dsc_aux)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index b1ad451af06bd..dfba0bc732073 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1265,7 +1265,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			enum smu_clk_type clk_type, char *buf)
 {
 	uint16_t *curve_settings;
-	int i, size = 0, ret = 0;
+	int i, levels, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t freq_values[3] = {0};
 	uint32_t mark_index = 0;
@@ -1319,14 +1319,17 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			freq_values[1] = cur_value;
 			mark_index = cur_value == freq_values[0] ? 0 :
 				     cur_value == freq_values[2] ? 2 : 1;
-			if (mark_index != 1)
-				freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
 
-			for (i = 0; i < 3; i++) {
+			levels = 3;
+			if (mark_index != 1) {
+				levels = 2;
+				freq_values[1] = freq_values[2];
+			}
+
+			for (i = 0; i < levels; i++) {
 				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, freq_values[i],
 						i == mark_index ? "*" : "");
 			}
-
 		}
 		break;
 	case SMU_PCIE:
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 6beeeeba1bed2..b56850d964919 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1639,6 +1639,9 @@ struct intel_dp {
 	struct intel_dp_pcon_frl frl;
 
 	struct intel_psr psr;
+
+	/* When we last wrote the OUI for eDP */
+	unsigned long last_oui_write;
 };
 
 enum lspcon_vendor {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index b4c7355f89b69..d55363f1fa102 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -29,6 +29,7 @@
 #include <linux/i2c.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/timekeeping.h>
 #include <linux/types.h>
 
 #include <asm/byteorder.h>
@@ -1864,6 +1865,16 @@ intel_edp_init_source_oui(struct intel_dp *intel_dp, bool careful)
 
 	if (drm_dp_dpcd_write(&intel_dp->aux, DP_SOURCE_OUI, oui, sizeof(oui)) < 0)
 		drm_err(&i915->drm, "Failed to write source OUI\n");
+
+	intel_dp->last_oui_write = jiffies;
+}
+
+void intel_dp_wait_source_oui(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	drm_dbg_kms(&i915->drm, "Performing OUI wait\n");
+	wait_remaining_ms_from_jiffies(intel_dp->last_oui_write, 30);
 }
 
 /* If the device supports it, try to set the power state appropriately */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 680631b5b4378..2121aaa9b8db0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -129,4 +129,6 @@ void intel_dp_pcon_dsc_configure(struct intel_dp *intel_dp,
 				 const struct intel_crtc_state *crtc_state);
 void intel_dp_phy_test(struct intel_encoder *encoder);
 
+void intel_dp_wait_source_oui(struct intel_dp *intel_dp);
+
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 6ac568617ef37..c82f8febe7303 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -35,6 +35,7 @@
  */
 
 #include "intel_display_types.h"
+#include "intel_dp.h"
 #include "intel_dp_aux_backlight.h"
 #include "intel_panel.h"
 
@@ -106,6 +107,8 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector)
 	int ret;
 	u8 tcon_cap[4];
 
+	intel_dp_wait_source_oui(intel_dp);
+
 	ret = drm_dp_dpcd_read(aux, INTEL_EDP_HDR_TCON_CAP0, tcon_cap, sizeof(tcon_cap));
 	if (ret != sizeof(tcon_cap))
 		return false;
@@ -204,6 +207,8 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state,
 	int ret;
 	u8 old_ctrl, ctrl;
 
+	intel_dp_wait_source_oui(intel_dp);
+
 	ret = drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &old_ctrl);
 	if (ret != 1) {
 		drm_err(&i915->drm, "Failed to read current backlight control mode: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index aae609d7d85dd..6b5ab19a2ada9 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -621,13 +621,6 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	       FF_MODE2_GS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224,
 	       0, false);
-
-	/*
-	 * Wa_14012131227:dg1
-	 * Wa_1508744258:tgl,rkl,dg1,adl-s,adl-p
-	 */
-	wa_masked_en(wal, GEN7_COMMON_SLICE_CHICKEN1,
-		     GEN9_RHWO_OPTIMIZATION_DISABLE);
 }
 
 static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index e8f65cd8eca6e..bfac7e47cb396 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -777,12 +777,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 
 	a6xx_state->gmu_registers = state_kcalloc(a6xx_state,
-		2, sizeof(*a6xx_state->gmu_registers));
+		3, sizeof(*a6xx_state->gmu_registers));
 
 	if (!a6xx_state->gmu_registers)
 		return;
 
-	a6xx_state->nr_gmu_registers = 2;
+	a6xx_state->nr_gmu_registers = 3;
 
 	/* Get the CX GMU registers from AHB */
 	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0],
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 09d2d279c30ae..dee13fedee3b5 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -77,6 +77,7 @@ static int msm_gpu_open(struct inode *inode, struct file *file)
 		goto free_priv;
 
 	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_hw_init(gpu);
 	show_priv->state = gpu->funcs->gpu_state_get(gpu);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index d4e09703a87db..27f737a253c77 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -938,29 +938,18 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 	return ret;
 }
 
-static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
-		struct drm_file *file)
+static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
+		      ktime_t timeout)
 {
-	struct msm_drm_private *priv = dev->dev_private;
-	struct drm_msm_wait_fence *args = data;
-	ktime_t timeout = to_ktime(args->timeout);
-	struct msm_gpu_submitqueue *queue;
-	struct msm_gpu *gpu = priv->gpu;
 	struct dma_fence *fence;
 	int ret;
 
-	if (args->pad) {
-		DRM_ERROR("invalid pad: %08x\n", args->pad);
+	if (fence_id > queue->last_fence) {
+		DRM_ERROR_RATELIMITED("waiting on invalid fence: %u (of %u)\n",
+				      fence_id, queue->last_fence);
 		return -EINVAL;
 	}
 
-	if (!gpu)
-		return 0;
-
-	queue = msm_submitqueue_get(file->driver_priv, args->queueid);
-	if (!queue)
-		return -ENOENT;
-
 	/*
 	 * Map submitqueue scoped "seqno" (which is actually an idr key)
 	 * back to underlying dma-fence
@@ -972,7 +961,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	ret = mutex_lock_interruptible(&queue->lock);
 	if (ret)
 		return ret;
-	fence = idr_find(&queue->fence_idr, args->fence);
+	fence = idr_find(&queue->fence_idr, fence_id);
 	if (fence)
 		fence = dma_fence_get_rcu(fence);
 	mutex_unlock(&queue->lock);
@@ -988,6 +977,32 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	}
 
 	dma_fence_put(fence);
+
+	return ret;
+}
+
+static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_msm_wait_fence *args = data;
+	struct msm_gpu_submitqueue *queue;
+	int ret;
+
+	if (args->pad) {
+		DRM_ERROR("invalid pad: %08x\n", args->pad);
+		return -EINVAL;
+	}
+
+	if (!priv->gpu)
+		return 0;
+
+	queue = msm_submitqueue_get(file->driver_priv, args->queueid);
+	if (!queue)
+		return -ENOENT;
+
+	ret = wait_fence(queue, args->fence, to_ktime(args->timeout));
+
 	msm_submitqueue_put(queue);
 
 	return ret;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index bd6ec04f345e1..cb52ac01e5122 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1055,8 +1055,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
+	vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags));
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 151d19e4453cd..a38f23be497d8 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -911,6 +911,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	drm_sched_entity_push_job(&submit->base, queue->entity);
 
 	args->fence = submit->fence_id;
+	queue->last_fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index ee25d556c8a10..2e2424066e701 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -352,6 +352,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
  * @ring_nr:   the ringbuffer used by this submitqueue, which is determined
  *             by the submitqueue's priority
  * @faults:    the number of GPU hangs associated with this submitqueue
+ * @last_fence: the sequence number of the last allocated fence (for error
+ *             checking)
  * @ctx:       the per-drm_file context associated with the submitqueue (ie.
  *             which set of pgtables do submits jobs associated with the
  *             submitqueue use)
@@ -367,6 +369,7 @@ struct msm_gpu_submitqueue {
 	u32 flags;
 	u32 ring_nr;
 	int faults;
+	uint32_t last_fence;
 	struct msm_file_private *ctx;
 	struct list_head node;
 	struct idr fence_idr;
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index 20006d060b5b5..4ac2a4eb984d8 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -20,6 +20,10 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq,
 	struct msm_gpu *gpu = dev_to_gpu(dev);
 	struct dev_pm_opp *opp;
 
+	/*
+	 * Note that devfreq_recommended_opp() can modify the freq
+	 * to something that actually is in the opp table:
+	 */
 	opp = devfreq_recommended_opp(dev, freq, flags);
 
 	/*
@@ -28,6 +32,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq,
 	 */
 	if (gpu->devfreq.idle_freq) {
 		gpu->devfreq.idle_freq = *freq;
+		dev_pm_opp_put(opp);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 5755f0432e774..8c796de53222c 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -46,6 +46,7 @@ config DRM_SUN6I_DSI
 	default MACH_SUN8I
 	select CRC_CCITT
 	select DRM_MIPI_DSI
+	select RESET_CONTROLLER
 	select PHY_SUN6I_MIPI_DPHY
 	help
 	  Choose this option if you want have an Allwinner SoC with
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index f0b3e4cf5bceb..b61792d2aa657 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -337,10 +337,10 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_device *dev = state->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_hvs *hvs = vc4->hvs;
-	struct drm_crtc_state *old_crtc_state;
 	struct drm_crtc_state *new_crtc_state;
 	struct drm_crtc *crtc;
 	struct vc4_hvs_state *old_hvs_state;
+	unsigned int channel;
 	int i;
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
@@ -353,30 +353,32 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 		vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel);
 	}
 
-	if (vc4->hvs->hvs5)
-		clk_set_min_rate(hvs->core_clk, 500000000);
-
 	old_hvs_state = vc4_hvs_get_old_global_state(state);
-	if (!old_hvs_state)
+	if (IS_ERR(old_hvs_state))
 		return;
 
-	for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
-		struct vc4_crtc_state *vc4_crtc_state =
-			to_vc4_crtc_state(old_crtc_state);
-		unsigned int channel = vc4_crtc_state->assigned_channel;
+	for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) {
+		struct drm_crtc_commit *commit;
 		int ret;
 
-		if (channel == VC4_HVS_CHANNEL_DISABLED)
+		if (!old_hvs_state->fifo_state[channel].in_use)
 			continue;
 
-		if (!old_hvs_state->fifo_state[channel].in_use)
+		commit = old_hvs_state->fifo_state[channel].pending_commit;
+		if (!commit)
 			continue;
 
-		ret = drm_crtc_commit_wait(old_hvs_state->fifo_state[channel].pending_commit);
+		ret = drm_crtc_commit_wait(commit);
 		if (ret)
 			drm_err(dev, "Timed out waiting for commit\n");
+
+		drm_crtc_commit_put(commit);
+		old_hvs_state->fifo_state[channel].pending_commit = NULL;
 	}
 
+	if (vc4->hvs->hvs5)
+		clk_set_min_rate(hvs->core_clk, 500000000);
+
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
 	vc4_ctm_commit(vc4, state);
@@ -410,8 +412,8 @@ static int vc4_atomic_commit_setup(struct drm_atomic_state *state)
 	unsigned int i;
 
 	hvs_state = vc4_hvs_get_new_global_state(state);
-	if (!hvs_state)
-		return -EINVAL;
+	if (WARN_ON(IS_ERR(hvs_state)))
+		return PTR_ERR(hvs_state);
 
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		struct vc4_crtc_state *vc4_crtc_state =
@@ -668,12 +670,6 @@ vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj)
 
 	for (i = 0; i < HVS_NUM_CHANNELS; i++) {
 		state->fifo_state[i].in_use = old_state->fifo_state[i].in_use;
-
-		if (!old_state->fifo_state[i].pending_commit)
-			continue;
-
-		state->fifo_state[i].pending_commit =
-			drm_crtc_commit_get(old_state->fifo_state[i].pending_commit);
 	}
 
 	return &state->base;
@@ -762,8 +758,8 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev,
 	unsigned int i;
 
 	hvs_new_state = vc4_hvs_get_global_state(state);
-	if (!hvs_new_state)
-		return -EINVAL;
+	if (IS_ERR(hvs_new_state))
+		return PTR_ERR(hvs_new_state);
 
 	for (i = 0; i < ARRAY_SIZE(hvs_new_state->fifo_state); i++)
 		if (!hvs_new_state->fifo_state[i].in_use)
diff --git a/drivers/i2c/busses/i2c-cbus-gpio.c b/drivers/i2c/busses/i2c-cbus-gpio.c
index 72df563477b1c..f8639a4457d23 100644
--- a/drivers/i2c/busses/i2c-cbus-gpio.c
+++ b/drivers/i2c/busses/i2c-cbus-gpio.c
@@ -195,8 +195,9 @@ static u32 cbus_i2c_func(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm cbus_i2c_algo = {
-	.smbus_xfer	= cbus_i2c_smbus_xfer,
-	.functionality	= cbus_i2c_func,
+	.smbus_xfer		= cbus_i2c_smbus_xfer,
+	.smbus_xfer_atomic	= cbus_i2c_smbus_xfer,
+	.functionality		= cbus_i2c_func,
 };
 
 static int cbus_i2c_remove(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index b9b19a2a2ffa0..50d5ae81d2271 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -1493,6 +1493,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
 	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
+	struct stm32_i2c_dma *dma = i2c_dev->dma;
 	void __iomem *base = i2c_dev->base;
 	u32 status, mask;
 	int ret = IRQ_HANDLED;
@@ -1518,6 +1519,10 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
 			__func__, f7_msg->addr);
 		writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR);
+		if (i2c_dev->use_dma) {
+			stm32f7_i2c_disable_dma_req(i2c_dev);
+			dmaengine_terminate_all(dma->chan_using);
+		}
 		f7_msg->result = -ENXIO;
 	}
 
@@ -1533,7 +1538,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		/* Clear STOP flag */
 		writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR);
 
-		if (i2c_dev->use_dma) {
+		if (i2c_dev->use_dma && !f7_msg->result) {
 			ret = IRQ_WAKE_THREAD;
 		} else {
 			i2c_dev->master_mode = false;
@@ -1546,7 +1551,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		if (f7_msg->stop) {
 			mask = STM32F7_I2C_CR2_STOP;
 			stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask);
-		} else if (i2c_dev->use_dma) {
+		} else if (i2c_dev->use_dma && !f7_msg->result) {
 			ret = IRQ_WAKE_THREAD;
 		} else if (f7_msg->smbus) {
 			stm32f7_i2c_smbus_rep_start(i2c_dev);
@@ -1696,12 +1701,23 @@ static int stm32f7_i2c_xfer(struct i2c_adapter *i2c_adap,
 	time_left = wait_for_completion_timeout(&i2c_dev->complete,
 						i2c_dev->adap.timeout);
 	ret = f7_msg->result;
+	if (ret) {
+		/*
+		 * It is possible that some unsent data have already been
+		 * written into TXDR. To avoid sending old data in a
+		 * further transfer, flush TXDR in case of any error
+		 */
+		writel_relaxed(STM32F7_I2C_ISR_TXE,
+			       i2c_dev->base + STM32F7_I2C_ISR);
+		goto pm_free;
+	}
 
 	if (!time_left) {
 		dev_dbg(i2c_dev->dev, "Access to slave 0x%x timed out\n",
 			i2c_dev->msg->addr);
 		if (i2c_dev->use_dma)
 			dmaengine_terminate_all(dma->chan_using);
+		stm32f7_i2c_wait_free_bus(i2c_dev);
 		ret = -ETIMEDOUT;
 	}
 
@@ -1744,13 +1760,22 @@ static int stm32f7_i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
 	timeout = wait_for_completion_timeout(&i2c_dev->complete,
 					      i2c_dev->adap.timeout);
 	ret = f7_msg->result;
-	if (ret)
+	if (ret) {
+		/*
+		 * It is possible that some unsent data have already been
+		 * written into TXDR. To avoid sending old data in a
+		 * further transfer, flush TXDR in case of any error
+		 */
+		writel_relaxed(STM32F7_I2C_ISR_TXE,
+			       i2c_dev->base + STM32F7_I2C_ISR);
 		goto pm_free;
+	}
 
 	if (!timeout) {
 		dev_dbg(dev, "Access to slave 0x%x timed out\n", f7_msg->addr);
 		if (i2c_dev->use_dma)
 			dmaengine_terminate_all(dma->chan_using);
+		stm32f7_i2c_wait_free_bus(i2c_dev);
 		ret = -ETIMEDOUT;
 		goto pm_free;
 	}
diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c
index 01e37b75471e1..2b88f03e52521 100644
--- a/drivers/net/dsa/b53/b53_spi.c
+++ b/drivers/net/dsa/b53/b53_spi.c
@@ -349,6 +349,19 @@ static const struct of_device_id b53_spi_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, b53_spi_of_match);
 
+static const struct spi_device_id b53_spi_ids[] = {
+	{ .name = "bcm5325" },
+	{ .name = "bcm5365" },
+	{ .name = "bcm5395" },
+	{ .name = "bcm5397" },
+	{ .name = "bcm5398" },
+	{ .name = "bcm53115" },
+	{ .name = "bcm53125" },
+	{ .name = "bcm53128" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(spi, b53_spi_ids);
+
 static struct spi_driver b53_spi_driver = {
 	.driver = {
 		.name	= "b53-switch",
@@ -357,6 +370,7 @@ static struct spi_driver b53_spi_driver = {
 	.probe	= b53_spi_probe,
 	.remove	= b53_spi_remove,
 	.shutdown = b53_spi_shutdown,
+	.id_table = b53_spi_ids,
 };
 
 module_spi_driver(b53_spi_driver);
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 6ea0036787986..55273013bfb55 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -50,11 +50,22 @@ static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip,
 }
 
 static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip,
-					  u16 status, u16 lpa,
+					  u16 ctrl, u16 status, u16 lpa,
 					  struct phylink_link_state *state)
 {
+	state->link = !!(status & MV88E6390_SGMII_PHY_STATUS_LINK);
+
 	if (status & MV88E6390_SGMII_PHY_STATUS_SPD_DPL_VALID) {
-		state->link = !!(status & MV88E6390_SGMII_PHY_STATUS_LINK);
+		/* The Spped and Duplex Resolved register is 1 if AN is enabled
+		 * and complete, or if AN is disabled. So with disabled AN we
+		 * still get here on link up. But we want to set an_complete
+		 * only if AN was enabled, thus we look at BMCR_ANENABLE.
+		 * (According to 802.3-2008 section 22.2.4.2.10, we should be
+		 *  able to get this same value from BMSR_ANEGCAPABLE, but tests
+		 *  show that these Marvell PHYs don't conform to this part of
+		 *  the specificaion - BMSR_ANEGCAPABLE is simply always 1.)
+		 */
+		state->an_complete = !!(ctrl & BMCR_ANENABLE);
 		state->duplex = status &
 				MV88E6390_SGMII_PHY_STATUS_DUPLEX_FULL ?
 			                         DUPLEX_FULL : DUPLEX_HALF;
@@ -81,6 +92,18 @@ static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip,
 			dev_err(chip->dev, "invalid PHY speed\n");
 			return -EINVAL;
 		}
+	} else if (state->link &&
+		   state->interface != PHY_INTERFACE_MODE_SGMII) {
+		/* If Speed and Duplex Resolved register is 0 and link is up, it
+		 * means that AN was enabled, but link partner had it disabled
+		 * and the PHY invoked the Auto-Negotiation Bypass feature and
+		 * linked anyway.
+		 */
+		state->duplex = DUPLEX_FULL;
+		if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
+			state->speed = SPEED_2500;
+		else
+			state->speed = SPEED_1000;
 	} else {
 		state->link = false;
 	}
@@ -168,9 +191,15 @@ int mv88e6352_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
 int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 				   int lane, struct phylink_link_state *state)
 {
-	u16 lpa, status;
+	u16 lpa, status, ctrl;
 	int err;
 
+	err = mv88e6352_serdes_read(chip, MII_BMCR, &ctrl);
+	if (err) {
+		dev_err(chip->dev, "can't read Serdes PHY control: %d\n", err);
+		return err;
+	}
+
 	err = mv88e6352_serdes_read(chip, 0x11, &status);
 	if (err) {
 		dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err);
@@ -183,7 +212,7 @@ int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 		return err;
 	}
 
-	return mv88e6xxx_serdes_pcs_get_state(chip, status, lpa, state);
+	return mv88e6xxx_serdes_pcs_get_state(chip, ctrl, status, lpa, state);
 }
 
 int mv88e6352_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
@@ -883,9 +912,16 @@ int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
 static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip,
 	int port, int lane, struct phylink_link_state *state)
 {
-	u16 lpa, status;
+	u16 lpa, status, ctrl;
 	int err;
 
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_SGMII_BMCR, &ctrl);
+	if (err) {
+		dev_err(chip->dev, "can't read Serdes PHY control: %d\n", err);
+		return err;
+	}
+
 	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
 				    MV88E6390_SGMII_PHY_STATUS, &status);
 	if (err) {
@@ -900,7 +936,7 @@ static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip,
 		return err;
 	}
 
-	return mv88e6xxx_serdes_pcs_get_state(chip, status, lpa, state);
+	return mv88e6xxx_serdes_pcs_get_state(chip, ctrl, status, lpa, state);
 }
 
 static int mv88e6390_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip,
@@ -1271,9 +1307,31 @@ void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p)
 	}
 }
 
-static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane)
+static int mv88e6393x_serdes_power_lane(struct mv88e6xxx_chip *chip, int lane,
+					bool on)
 {
-	u16 reg, pcs;
+	u16 reg;
+	int err;
+
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6393X_SERDES_CTRL1, &reg);
+	if (err)
+		return err;
+
+	if (on)
+		reg &= ~(MV88E6393X_SERDES_CTRL1_TX_PDOWN |
+			 MV88E6393X_SERDES_CTRL1_RX_PDOWN);
+	else
+		reg |= MV88E6393X_SERDES_CTRL1_TX_PDOWN |
+		       MV88E6393X_SERDES_CTRL1_RX_PDOWN;
+
+	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				      MV88E6393X_SERDES_CTRL1, reg);
+}
+
+static int mv88e6393x_serdes_erratum_4_6(struct mv88e6xxx_chip *chip, int lane)
+{
+	u16 reg;
 	int err;
 
 	/* mv88e6393x family errata 4.6:
@@ -1284,26 +1342,45 @@ static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane)
 	 * It seems that after this workaround the SERDES is automatically
 	 * powered up (the bit is cleared), so power it down.
 	 */
-	if (lane == MV88E6393X_PORT0_LANE || lane == MV88E6393X_PORT9_LANE ||
-	    lane == MV88E6393X_PORT10_LANE) {
-		err = mv88e6390_serdes_read(chip, lane,
-					    MDIO_MMD_PHYXS,
-					    MV88E6393X_SERDES_POC, &reg);
-		if (err)
-			return err;
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6393X_SERDES_POC, &reg);
+	if (err)
+		return err;
 
-		reg &= ~MV88E6393X_SERDES_POC_PDOWN;
-		reg |= MV88E6393X_SERDES_POC_RESET;
+	reg &= ~MV88E6393X_SERDES_POC_PDOWN;
+	reg |= MV88E6393X_SERDES_POC_RESET;
 
-		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-					     MV88E6393X_SERDES_POC, reg);
-		if (err)
-			return err;
+	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				     MV88E6393X_SERDES_POC, reg);
+	if (err)
+		return err;
 
-		err = mv88e6390_serdes_power_sgmii(chip, lane, false);
-		if (err)
-			return err;
-	}
+	err = mv88e6390_serdes_power_sgmii(chip, lane, false);
+	if (err)
+		return err;
+
+	return mv88e6393x_serdes_power_lane(chip, lane, false);
+}
+
+int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	int err;
+
+	err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT0_LANE);
+	if (err)
+		return err;
+
+	err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT9_LANE);
+	if (err)
+		return err;
+
+	return mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT10_LANE);
+}
+
+static int mv88e6393x_serdes_erratum_4_8(struct mv88e6xxx_chip *chip, int lane)
+{
+	u16 reg, pcs;
+	int err;
 
 	/* mv88e6393x family errata 4.8:
 	 * When a SERDES port is operating in 1000BASE-X or SGMII mode link may
@@ -1334,38 +1411,149 @@ static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane)
 				      MV88E6393X_ERRATA_4_8_REG, reg);
 }
 
-int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip)
+static int mv88e6393x_serdes_erratum_5_2(struct mv88e6xxx_chip *chip, int lane,
+					 u8 cmode)
+{
+	static const struct {
+		u16 dev, reg, val, mask;
+	} fixes[] = {
+		{ MDIO_MMD_VEND1, 0x8093, 0xcb5a, 0xffff },
+		{ MDIO_MMD_VEND1, 0x8171, 0x7088, 0xffff },
+		{ MDIO_MMD_VEND1, 0x80c9, 0x311a, 0xffff },
+		{ MDIO_MMD_VEND1, 0x80a2, 0x8000, 0xff7f },
+		{ MDIO_MMD_VEND1, 0x80a9, 0x0000, 0xfff0 },
+		{ MDIO_MMD_VEND1, 0x80a3, 0x0000, 0xf8ff },
+		{ MDIO_MMD_PHYXS, MV88E6393X_SERDES_POC,
+		  MV88E6393X_SERDES_POC_RESET, MV88E6393X_SERDES_POC_RESET },
+	};
+	int err, i;
+	u16 reg;
+
+	/* mv88e6393x family errata 5.2:
+	 * For optimal signal integrity the following sequence should be applied
+	 * to SERDES operating in 10G mode. These registers only apply to 10G
+	 * operation and have no effect on other speeds.
+	 */
+	if (cmode != MV88E6393X_PORT_STS_CMODE_10GBASER)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(fixes); ++i) {
+		err = mv88e6390_serdes_read(chip, lane, fixes[i].dev,
+					    fixes[i].reg, &reg);
+		if (err)
+			return err;
+
+		reg &= ~fixes[i].mask;
+		reg |= fixes[i].val;
+
+		err = mv88e6390_serdes_write(chip, lane, fixes[i].dev,
+					     fixes[i].reg, reg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int mv88e6393x_serdes_fix_2500basex_an(struct mv88e6xxx_chip *chip,
+					      int lane, u8 cmode, bool on)
 {
+	u16 reg;
 	int err;
 
-	err = mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT0_LANE);
+	if (cmode != MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+		return 0;
+
+	/* Inband AN is broken on Amethyst in 2500base-x mode when set by
+	 * standard mechanism (via cmode).
+	 * We can get around this by configuring the PCS mode to 1000base-x
+	 * and then writing value 0x58 to register 1e.8000. (This must be done
+	 * while SerDes receiver and transmitter are disabled, which is, when
+	 * this function is called.)
+	 * It seem that when we do this configuration to 2500base-x mode (by
+	 * changing PCS mode to 1000base-x and frequency to 3.125 GHz from
+	 * 1.25 GHz) and then configure to sgmii or 1000base-x, the device
+	 * thinks that it already has SerDes at 1.25 GHz and does not change
+	 * the 1e.8000 register, leaving SerDes at 3.125 GHz.
+	 * To avoid this, change PCS mode back to 2500base-x when disabling
+	 * SerDes from 2500base-x mode.
+	 */
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6393X_SERDES_POC, &reg);
+	if (err)
+		return err;
+
+	reg &= ~(MV88E6393X_SERDES_POC_PCS_MASK | MV88E6393X_SERDES_POC_AN);
+	if (on)
+		reg |= MV88E6393X_SERDES_POC_PCS_1000BASEX |
+		       MV88E6393X_SERDES_POC_AN;
+	else
+		reg |= MV88E6393X_SERDES_POC_PCS_2500BASEX;
+	reg |= MV88E6393X_SERDES_POC_RESET;
+
+	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				     MV88E6393X_SERDES_POC, reg);
 	if (err)
 		return err;
 
-	err = mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT9_LANE);
+	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_VEND1, 0x8000, 0x58);
 	if (err)
 		return err;
 
-	return mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT10_LANE);
+	return 0;
 }
 
 int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			    bool on)
 {
 	u8 cmode = chip->ports[port].cmode;
+	int err;
 
 	if (port != 0 && port != 9 && port != 10)
 		return -EOPNOTSUPP;
 
+	if (on) {
+		err = mv88e6393x_serdes_erratum_4_8(chip, lane);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_erratum_5_2(chip, lane, cmode);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode,
+							 true);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_power_lane(chip, lane, true);
+		if (err)
+			return err;
+	}
+
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
 	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_power_sgmii(chip, lane, on);
+		err = mv88e6390_serdes_power_sgmii(chip, lane, on);
+		break;
 	case MV88E6393X_PORT_STS_CMODE_5GBASER:
 	case MV88E6393X_PORT_STS_CMODE_10GBASER:
-		return mv88e6390_serdes_power_10g(chip, lane, on);
+		err = mv88e6390_serdes_power_10g(chip, lane, on);
+		break;
 	}
 
-	return 0;
+	if (err)
+		return err;
+
+	if (!on) {
+		err = mv88e6393x_serdes_power_lane(chip, lane, false);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode,
+							 false);
+	}
+
+	return err;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index cbb3ba30caea9..8dd8ed225b459 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -93,6 +93,10 @@
 #define MV88E6393X_SERDES_POC_PCS_MASK		0x0007
 #define MV88E6393X_SERDES_POC_RESET		BIT(15)
 #define MV88E6393X_SERDES_POC_PDOWN		BIT(5)
+#define MV88E6393X_SERDES_POC_AN		BIT(3)
+#define MV88E6393X_SERDES_CTRL1			0xf003
+#define MV88E6393X_SERDES_CTRL1_TX_PDOWN	BIT(9)
+#define MV88E6393X_SERDES_CTRL1_RX_PDOWN	BIT(8)
 
 #define MV88E6393X_ERRATA_4_8_REG		0xF074
 #define MV88E6393X_ERRATA_4_8_BIT		BIT(14)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index 23b2d390fcdda..ace691d7cd759 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -40,10 +40,12 @@
 
 #define AQ_DEVICE_ID_AQC113DEV	0x00C0
 #define AQ_DEVICE_ID_AQC113CS	0x94C0
+#define AQ_DEVICE_ID_AQC113CA	0x34C0
 #define AQ_DEVICE_ID_AQC114CS	0x93C0
 #define AQ_DEVICE_ID_AQC113	0x04C0
 #define AQ_DEVICE_ID_AQC113C	0x14C0
 #define AQ_DEVICE_ID_AQC115C	0x12C0
+#define AQ_DEVICE_ID_AQC116C	0x11C0
 
 #define HW_ATL_NIC_NAME "Marvell (aQuantia) AQtion 10Gbit Network Adapter"
 
@@ -53,20 +55,19 @@
 
 #define AQ_NIC_RATE_10G		BIT(0)
 #define AQ_NIC_RATE_5G		BIT(1)
-#define AQ_NIC_RATE_5GSR	BIT(2)
-#define AQ_NIC_RATE_2G5		BIT(3)
-#define AQ_NIC_RATE_1G		BIT(4)
-#define AQ_NIC_RATE_100M	BIT(5)
-#define AQ_NIC_RATE_10M		BIT(6)
-#define AQ_NIC_RATE_1G_HALF	BIT(7)
-#define AQ_NIC_RATE_100M_HALF	BIT(8)
-#define AQ_NIC_RATE_10M_HALF	BIT(9)
+#define AQ_NIC_RATE_2G5		BIT(2)
+#define AQ_NIC_RATE_1G		BIT(3)
+#define AQ_NIC_RATE_100M	BIT(4)
+#define AQ_NIC_RATE_10M		BIT(5)
+#define AQ_NIC_RATE_1G_HALF	BIT(6)
+#define AQ_NIC_RATE_100M_HALF	BIT(7)
+#define AQ_NIC_RATE_10M_HALF	BIT(8)
 
-#define AQ_NIC_RATE_EEE_10G	BIT(10)
-#define AQ_NIC_RATE_EEE_5G	BIT(11)
-#define AQ_NIC_RATE_EEE_2G5	BIT(12)
-#define AQ_NIC_RATE_EEE_1G	BIT(13)
-#define AQ_NIC_RATE_EEE_100M	BIT(14)
+#define AQ_NIC_RATE_EEE_10G	BIT(9)
+#define AQ_NIC_RATE_EEE_5G	BIT(10)
+#define AQ_NIC_RATE_EEE_2G5	BIT(11)
+#define AQ_NIC_RATE_EEE_1G	BIT(12)
+#define AQ_NIC_RATE_EEE_100M	BIT(13)
 #define AQ_NIC_RATE_EEE_MSK     (AQ_NIC_RATE_EEE_10G |\
 				 AQ_NIC_RATE_EEE_5G |\
 				 AQ_NIC_RATE_EEE_2G5 |\
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index bed481816ea31..7442850ca95f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -80,6 +80,8 @@ struct aq_hw_link_status_s {
 };
 
 struct aq_stats_s {
+	u64 brc;
+	u64 btc;
 	u64 uprc;
 	u64 mprc;
 	u64 bprc;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 6c049864dac08..9de0065f89b90 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -903,8 +903,14 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 	data[++i] = stats->mbtc;
 	data[++i] = stats->bbrc;
 	data[++i] = stats->bbtc;
-	data[++i] = stats->ubrc + stats->mbrc + stats->bbrc;
-	data[++i] = stats->ubtc + stats->mbtc + stats->bbtc;
+	if (stats->brc)
+		data[++i] = stats->brc;
+	else
+		data[++i] = stats->ubrc + stats->mbrc + stats->bbrc;
+	if (stats->btc)
+		data[++i] = stats->btc;
+	else
+		data[++i] = stats->ubtc + stats->mbtc + stats->bbtc;
 	data[++i] = stats->dma_pkt_rc;
 	data[++i] = stats->dma_pkt_tc;
 	data[++i] = stats->dma_oct_rc;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index d4b1976ee69b9..797a95142d1f4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -49,6 +49,8 @@ static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113), },
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113C), },
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC115C), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113CA), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC116C), },
 
 	{}
 };
@@ -85,7 +87,10 @@ static const struct aq_board_revision_s hw_atl_boards[] = {
 	{ AQ_DEVICE_ID_AQC113CS,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
 	{ AQ_DEVICE_ID_AQC114CS,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
 	{ AQ_DEVICE_ID_AQC113C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
-	{ AQ_DEVICE_ID_AQC115C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC115C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc115c, },
+	{ AQ_DEVICE_ID_AQC113CA,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC116C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc116c, },
+
 };
 
 MODULE_DEVICE_TABLE(pci, aq_pci_tbl);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index d281322d7dd29..f4774cf051c97 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -362,9 +362,6 @@ unsigned int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u
 {
 	unsigned int count;
 
-	WARN_ONCE(!aq_vec_is_valid_tc(self, tc),
-		  "Invalid tc %u (#rx=%u, #tx=%u)\n",
-		  tc, self->rx_rings, self->tx_rings);
 	if (!aq_vec_is_valid_tc(self, tc))
 		return 0;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 404cbf60d3f2f..65b9e5846be45 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -559,6 +559,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 			goto err_exit;
 
 		if (fw.len == 0xFFFFU) {
+			if (sw.len > sizeof(self->rpc)) {
+				printk(KERN_INFO "Invalid sw len: %x\n", sw.len);
+				err = -EINVAL;
+				goto err_exit;
+			}
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
 			if (err < 0)
 				goto err_exit;
@@ -567,6 +572,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 
 	if (rpc) {
 		if (fw.len) {
+			if (fw.len > sizeof(self->rpc)) {
+				printk(KERN_INFO "Invalid fw len: %x\n", fw.len);
+				err = -EINVAL;
+				goto err_exit;
+			}
 			err =
 			hw_atl_utils_fw_downld_dwords(self,
 						      self->rpc_addr,
@@ -857,12 +867,20 @@ static int hw_atl_fw1x_deinit(struct aq_hw_s *self)
 int hw_atl_utils_update_stats(struct aq_hw_s *self)
 {
 	struct aq_stats_s *cs = &self->curr_stats;
+	struct aq_stats_s curr_stats = *cs;
 	struct hw_atl_utils_mbox mbox;
+	bool corrupted_stats = false;
 
 	hw_atl_utils_mpi_read_stats(self, &mbox);
 
-#define AQ_SDELTA(_N_) (self->curr_stats._N_ += \
-			mbox.stats._N_ - self->last_stats._N_)
+#define AQ_SDELTA(_N_)  \
+do { \
+	if (!corrupted_stats && \
+	    ((s64)(mbox.stats._N_ - self->last_stats._N_)) >= 0) \
+		curr_stats._N_ += mbox.stats._N_ - self->last_stats._N_; \
+	else \
+		corrupted_stats = true; \
+} while (0)
 
 	if (self->aq_link_status.mbps) {
 		AQ_SDELTA(uprc);
@@ -882,6 +900,9 @@ int hw_atl_utils_update_stats(struct aq_hw_s *self)
 		AQ_SDELTA(bbrc);
 		AQ_SDELTA(bbtc);
 		AQ_SDELTA(dpc);
+
+		if (!corrupted_stats)
+			*cs = curr_stats;
 	}
 #undef AQ_SDELTA
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index ee0c22d049354..05086f0040fd9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -132,9 +132,6 @@ static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed)
 	if (speed & AQ_NIC_RATE_5G)
 		rate |= FW2X_RATE_5G;
 
-	if (speed & AQ_NIC_RATE_5GSR)
-		rate |= FW2X_RATE_5G;
-
 	if (speed & AQ_NIC_RATE_2G5)
 		rate |= FW2X_RATE_2G5;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 92f64048bf691..c76ccdc77ba60 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -65,11 +65,25 @@ const struct aq_hw_caps_s hw_atl2_caps_aqc113 = {
 			  AQ_NIC_RATE_5G  |
 			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G  |
-			  AQ_NIC_RATE_1G_HALF   |
 			  AQ_NIC_RATE_100M      |
-			  AQ_NIC_RATE_100M_HALF |
-			  AQ_NIC_RATE_10M       |
-			  AQ_NIC_RATE_10M_HALF,
+			  AQ_NIC_RATE_10M,
+};
+
+const struct aq_hw_caps_s hw_atl2_caps_aqc115c = {
+	DEFAULT_BOARD_BASIC_CAPABILITIES,
+	.media_type = AQ_HW_MEDIA_TYPE_TP,
+	.link_speed_msk = AQ_NIC_RATE_2G5 |
+			  AQ_NIC_RATE_1G  |
+			  AQ_NIC_RATE_100M      |
+			  AQ_NIC_RATE_10M,
+};
+
+const struct aq_hw_caps_s hw_atl2_caps_aqc116c = {
+	DEFAULT_BOARD_BASIC_CAPABILITIES,
+	.media_type = AQ_HW_MEDIA_TYPE_TP,
+	.link_speed_msk = AQ_NIC_RATE_1G  |
+			  AQ_NIC_RATE_100M      |
+			  AQ_NIC_RATE_10M,
 };
 
 static u32 hw_atl2_sem_act_rslvr_get(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
index de8723f1c28a1..346f0dc9912e5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
@@ -9,6 +9,8 @@
 #include "aq_common.h"
 
 extern const struct aq_hw_caps_s hw_atl2_caps_aqc113;
+extern const struct aq_hw_caps_s hw_atl2_caps_aqc115c;
+extern const struct aq_hw_caps_s hw_atl2_caps_aqc116c;
 extern const struct aq_hw_ops hw_atl2_ops;
 
 #endif /* HW_ATL2_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
index b66fa346581ce..6bad64c77b87c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
@@ -239,7 +239,8 @@ struct version_s {
 		u8 minor;
 		u16 build;
 	} phy;
-	u32 rsvd;
+	u32 drv_iface_ver:4;
+	u32 rsvd:28;
 };
 
 struct link_status_s {
@@ -424,7 +425,7 @@ struct cable_diag_status_s {
 	u16 rsvd2;
 };
 
-struct statistics_s {
+struct statistics_a0_s {
 	struct {
 		u32 link_up;
 		u32 link_down;
@@ -457,6 +458,33 @@ struct statistics_s {
 	u32 reserve_fw_gap;
 };
 
+struct __packed statistics_b0_s {
+	u64 rx_good_octets;
+	u64 rx_pause_frames;
+	u64 rx_good_frames;
+	u64 rx_errors;
+	u64 rx_unicast_frames;
+	u64 rx_multicast_frames;
+	u64 rx_broadcast_frames;
+
+	u64 tx_good_octets;
+	u64 tx_pause_frames;
+	u64 tx_good_frames;
+	u64 tx_errors;
+	u64 tx_unicast_frames;
+	u64 tx_multicast_frames;
+	u64 tx_broadcast_frames;
+
+	u32 main_loop_cycles;
+};
+
+struct __packed statistics_s {
+	union __packed {
+		struct statistics_a0_s a0;
+		struct statistics_b0_s b0;
+	};
+};
+
 struct filter_caps_s {
 	u8 l2_filters_base_index:6;
 	u8 flexible_filter_mask:2;
@@ -545,7 +573,7 @@ struct management_status_s {
 	u32 rsvd5;
 };
 
-struct fw_interface_out {
+struct __packed fw_interface_out {
 	struct transaction_counter_s transaction_id;
 	struct version_s version;
 	struct link_status_s link_status;
@@ -569,7 +597,6 @@ struct fw_interface_out {
 	struct core_dump_s core_dump;
 	u32 rsvd11;
 	struct statistics_s stats;
-	u32 rsvd12;
 	struct filter_caps_s filter_caps;
 	struct device_caps_s device_caps;
 	u32 rsvd13;
@@ -592,6 +619,9 @@ struct fw_interface_out {
 #define  AQ_HOST_MODE_LOW_POWER    3U
 #define  AQ_HOST_MODE_SHUTDOWN     4U
 
+#define  AQ_A2_FW_INTERFACE_A0     0
+#define  AQ_A2_FW_INTERFACE_B0     1
+
 int hw_atl2_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops);
 
 int hw_atl2_utils_soft_reset(struct aq_hw_s *self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index dd259c8f2f4f3..58d426dda3edb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -84,7 +84,7 @@ static int hw_atl2_shared_buffer_read_block(struct aq_hw_s *self,
 			if (cnt > AQ_A2_FW_READ_TRY_MAX)
 				return -ETIME;
 			if (tid1.transaction_cnt_a != tid1.transaction_cnt_b)
-				udelay(1);
+				mdelay(1);
 		} while (tid1.transaction_cnt_a != tid1.transaction_cnt_b);
 
 		hw_atl2_mif_shared_buf_read(self, offset, (u32 *)data, dwords);
@@ -154,7 +154,7 @@ static void a2_link_speed_mask2fw(u32 speed,
 {
 	link_options->rate_10G = !!(speed & AQ_NIC_RATE_10G);
 	link_options->rate_5G = !!(speed & AQ_NIC_RATE_5G);
-	link_options->rate_N5G = !!(speed & AQ_NIC_RATE_5GSR);
+	link_options->rate_N5G = link_options->rate_5G;
 	link_options->rate_2P5G = !!(speed & AQ_NIC_RATE_2G5);
 	link_options->rate_N2P5G = link_options->rate_2P5G;
 	link_options->rate_1G = !!(speed & AQ_NIC_RATE_1G);
@@ -192,8 +192,6 @@ static u32 a2_fw_lkp_to_mask(struct lkp_link_caps_s *lkp_link_caps)
 		rate |= AQ_NIC_RATE_10G;
 	if (lkp_link_caps->rate_5G)
 		rate |= AQ_NIC_RATE_5G;
-	if (lkp_link_caps->rate_N5G)
-		rate |= AQ_NIC_RATE_5GSR;
 	if (lkp_link_caps->rate_2P5G)
 		rate |= AQ_NIC_RATE_2G5;
 	if (lkp_link_caps->rate_1G)
@@ -335,15 +333,22 @@ static int aq_a2_fw_get_mac_permanent(struct aq_hw_s *self, u8 *mac)
 	return 0;
 }
 
-static int aq_a2_fw_update_stats(struct aq_hw_s *self)
+static void aq_a2_fill_a0_stats(struct aq_hw_s *self,
+				struct statistics_s *stats)
 {
 	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
-	struct statistics_s stats;
-
-	hw_atl2_shared_buffer_read_safe(self, stats, &stats);
-
-#define AQ_SDELTA(_N_, _F_) (self->curr_stats._N_ += \
-			stats.msm._F_ - priv->last_stats.msm._F_)
+	struct aq_stats_s *cs = &self->curr_stats;
+	struct aq_stats_s curr_stats = *cs;
+	bool corrupted_stats = false;
+
+#define AQ_SDELTA(_N, _F)  \
+do { \
+	if (!corrupted_stats && \
+	    ((s64)(stats->a0.msm._F - priv->last_stats.a0.msm._F)) >= 0) \
+		curr_stats._N += stats->a0.msm._F - priv->last_stats.a0.msm._F;\
+	else \
+		corrupted_stats = true; \
+} while (0)
 
 	if (self->aq_link_status.mbps) {
 		AQ_SDELTA(uprc, rx_unicast_frames);
@@ -362,17 +367,76 @@ static int aq_a2_fw_update_stats(struct aq_hw_s *self)
 		AQ_SDELTA(mbtc, tx_multicast_octets);
 		AQ_SDELTA(bbrc, rx_broadcast_octets);
 		AQ_SDELTA(bbtc, tx_broadcast_octets);
+
+		if (!corrupted_stats)
+			*cs = curr_stats;
 	}
 #undef AQ_SDELTA
-	self->curr_stats.dma_pkt_rc =
-		hw_atl_stats_rx_dma_good_pkt_counter_get(self);
-	self->curr_stats.dma_pkt_tc =
-		hw_atl_stats_tx_dma_good_pkt_counter_get(self);
-	self->curr_stats.dma_oct_rc =
-		hw_atl_stats_rx_dma_good_octet_counter_get(self);
-	self->curr_stats.dma_oct_tc =
-		hw_atl_stats_tx_dma_good_octet_counter_get(self);
-	self->curr_stats.dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self);
+
+}
+
+static void aq_a2_fill_b0_stats(struct aq_hw_s *self,
+				struct statistics_s *stats)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct aq_stats_s *cs = &self->curr_stats;
+	struct aq_stats_s curr_stats = *cs;
+	bool corrupted_stats = false;
+
+#define AQ_SDELTA(_N, _F)  \
+do { \
+	if (!corrupted_stats && \
+	    ((s64)(stats->b0._F - priv->last_stats.b0._F)) >= 0) \
+		curr_stats._N += stats->b0._F - priv->last_stats.b0._F; \
+	else \
+		corrupted_stats = true; \
+} while (0)
+
+	if (self->aq_link_status.mbps) {
+		AQ_SDELTA(uprc, rx_unicast_frames);
+		AQ_SDELTA(mprc, rx_multicast_frames);
+		AQ_SDELTA(bprc, rx_broadcast_frames);
+		AQ_SDELTA(erpr, rx_errors);
+		AQ_SDELTA(brc, rx_good_octets);
+
+		AQ_SDELTA(uptc, tx_unicast_frames);
+		AQ_SDELTA(mptc, tx_multicast_frames);
+		AQ_SDELTA(bptc, tx_broadcast_frames);
+		AQ_SDELTA(erpt, tx_errors);
+		AQ_SDELTA(btc, tx_good_octets);
+
+		if (!corrupted_stats)
+			*cs = curr_stats;
+	}
+#undef AQ_SDELTA
+}
+
+static int aq_a2_fw_update_stats(struct aq_hw_s *self)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct aq_stats_s *cs = &self->curr_stats;
+	struct statistics_s stats;
+	struct version_s version;
+	int err;
+
+	err = hw_atl2_shared_buffer_read_safe(self, version, &version);
+	if (err)
+		return err;
+
+	err = hw_atl2_shared_buffer_read_safe(self, stats, &stats);
+	if (err)
+		return err;
+
+	if (version.drv_iface_ver == AQ_A2_FW_INTERFACE_A0)
+		aq_a2_fill_a0_stats(self, &stats);
+	else
+		aq_a2_fill_b0_stats(self, &stats);
+
+	cs->dma_pkt_rc = hw_atl_stats_rx_dma_good_pkt_counter_get(self);
+	cs->dma_pkt_tc = hw_atl_stats_tx_dma_good_pkt_counter_get(self);
+	cs->dma_oct_rc = hw_atl_stats_rx_dma_good_octet_counter_get(self);
+	cs->dma_oct_tc = hw_atl_stats_tx_dma_good_octet_counter_get(self);
+	cs->dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self);
 
 	memcpy(&priv->last_stats, &stats, sizeof(stats));
 
@@ -499,9 +563,9 @@ u32 hw_atl2_utils_get_fw_version(struct aq_hw_s *self)
 	hw_atl2_shared_buffer_read_safe(self, version, &version);
 
 	/* A2 FW version is stored in reverse order */
-	return version.mac.major << 24 |
-	       version.mac.minor << 16 |
-	       version.mac.build;
+	return version.bundle.major << 24 |
+	       version.bundle.minor << 16 |
+	       version.bundle.build;
 }
 
 int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self,
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 36ab4cbf2ad08..b9d967e419387 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -4708,6 +4708,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p)
         lp->ibn = 3;
         lp->active = *p++;
 	if (MOTO_SROM_BUG) lp->active = 0;
+	/* if (MOTO_SROM_BUG) statement indicates lp->active could
+	 * be 8 (i.e. the size of array lp->phy) */
+	if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy)))
+		return -EINVAL;
 	lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].mc  = get_unaligned_le16(p); p += 2;
@@ -4999,19 +5003,23 @@ mii_get_phy(struct net_device *dev)
 	}
 	if ((j == limit) && (i < DE4X5_MAX_MII)) {
 	    for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++);
-	    lp->phy[k].addr = i;
-	    lp->phy[k].id = id;
-	    lp->phy[k].spd.reg = GENERIC_REG;      /* ANLPA register         */
-	    lp->phy[k].spd.mask = GENERIC_MASK;    /* 100Mb/s technologies   */
-	    lp->phy[k].spd.value = GENERIC_VALUE;  /* TX & T4, H/F Duplex    */
-	    lp->mii_cnt++;
-	    lp->active++;
-	    printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
-	    j = de4x5_debug;
-	    de4x5_debug |= DEBUG_MII;
-	    de4x5_dbg_mii(dev, k);
-	    de4x5_debug = j;
-	    printk("\n");
+	    if (k < DE4X5_MAX_PHY) {
+		lp->phy[k].addr = i;
+		lp->phy[k].id = id;
+		lp->phy[k].spd.reg = GENERIC_REG;      /* ANLPA register         */
+		lp->phy[k].spd.mask = GENERIC_MASK;    /* 100Mb/s technologies   */
+		lp->phy[k].spd.value = GENERIC_VALUE;  /* TX & T4, H/F Duplex    */
+		lp->mii_cnt++;
+		lp->active++;
+		printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
+		j = de4x5_debug;
+		de4x5_debug |= DEBUG_MII;
+		de4x5_dbg_mii(dev, k);
+		de4x5_debug = j;
+		printk("\n");
+	    } else {
+		goto purgatory;
+	    }
 	}
     }
   purgatory:
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index f3e443f2d9cf9..1108e1730841b 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4538,6 +4538,8 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 
 	fsl_mc_portal_free(priv->mc_io);
 
+	destroy_workqueue(priv->dpaa2_ptp_wq);
+
 	dev_dbg(net_dev->dev.parent, "Removed interface %s\n", net_dev->name);
 
 	free_netdev(net_dev);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 23d9cbf262c32..740850b64aff5 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -400,6 +400,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
 		return;
 
 	if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
+		/* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8.
+		   We need check to prevent array overflow */
+		if (port >= DSAF_MAX_PORT_NUM)
+			return;
 		reg_val_1  = 0x1 << port;
 		port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off;
 		/* there is difference between V1 and V2 in register.*/
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index ed6d0c019573b..bbd054fcda8cd 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7457,7 +7457,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 
 	shared = num_present_cpus() - priv->nthreads;
 	if (shared > 0)
-		bitmap_fill(&priv->lock_map,
+		bitmap_set(&priv->lock_map, 0,
 			    min_t(int, shared, MVPP2_MAX_THREADS));
 
 	for (i = 0; i < MVPP2_MAX_THREADS; i++) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 35836903b7fbc..90dc5343827f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2281,7 +2281,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 			goto free_regions;
 		break;
 	default:
-		return err;
+		goto free_regions;
 	}
 
 	mw->mbox_wq = alloc_workqueue(name,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 8af7f28273225..3bd3603873e32 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2286,9 +2286,14 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
 				bool carry_xdp_prog)
 {
 	struct bpf_prog *xdp_prog;
-	int i, t;
+	int i, t, ret;
 
-	mlx4_en_copy_priv(tmp, priv, prof);
+	ret = mlx4_en_copy_priv(tmp, priv, prof);
+	if (ret) {
+		en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n",
+			__func__);
+		return ret;
+	}
 
 	if (mlx4_en_alloc_resources(tmp)) {
 		en_warn(priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index c698e4b5381d7..bea35530c2d0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -336,6 +336,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DEALLOC_SF:
 	case MLX5_CMD_OP_DESTROY_UCTX:
 	case MLX5_CMD_OP_DESTROY_UMEM:
+	case MLX5_CMD_OP_MODIFY_RQT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -441,7 +442,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_MODIFY_TIS:
 	case MLX5_CMD_OP_QUERY_TIS:
 	case MLX5_CMD_OP_CREATE_RQT:
-	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
 
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 03a7a4ce5cd5e..c10a107a3ea53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -244,6 +244,17 @@ enum mlx5e_priv_flag {
 
 #define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag))))
 
+enum packet_merge {
+	MLX5E_PACKET_MERGE_NONE,
+	MLX5E_PACKET_MERGE_LRO,
+	MLX5E_PACKET_MERGE_SHAMPO,
+};
+
+struct mlx5e_packet_merge_param {
+	enum packet_merge type;
+	u32 timeout;
+};
+
 struct mlx5e_params {
 	u8  log_sq_size;
 	u8  rq_wq_type;
@@ -258,13 +269,12 @@ struct mlx5e_params {
 	bool tunneled_offload_en;
 	struct dim_cq_moder rx_cq_moderation;
 	struct dim_cq_moder tx_cq_moderation;
-	bool lro_en;
+	struct mlx5e_packet_merge_param packet_merge;
 	u8  tx_min_inline_mode;
 	bool vlan_strip_disable;
 	bool scatter_fcs_en;
 	bool rx_dim_enabled;
 	bool tx_dim_enabled;
-	u32 lro_timeout;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
 	struct mlx5e_xsk *xsk;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 3cbb596821e89..15f441a1b80c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -87,7 +87,8 @@ bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params,
 	u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk),
 				 mlx5e_rx_get_linear_frag_sz(params, NULL));
 
-	return !params->lro_en && linear_frag_sz <= PAGE_SIZE;
+	return params->packet_merge.type == MLX5E_PACKET_MERGE_NONE &&
+		linear_frag_sz <= PAGE_SIZE;
 }
 
 bool mlx5e_verify_rx_mpwqe_strides(struct mlx5_core_dev *mdev,
@@ -164,19 +165,8 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 		mlx5e_rx_is_linear_skb(params, xsk) :
 		mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk);
 
-	return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0;
-}
-
-struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params)
-{
-	struct mlx5e_lro_param lro_param;
-
-	lro_param = (struct mlx5e_lro_param) {
-		.enabled = params->lro_en,
-		.timeout = params->lro_timeout,
-	};
-
-	return lro_param;
+	return is_linear_skb || params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO ?
+		mlx5e_get_linear_rq_headroom(params, xsk) : 0;
 }
 
 u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
@@ -485,10 +475,11 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev,
 
 static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
+	bool lro_en = params->packet_merge.type == MLX5E_PACKET_MERGE_LRO;
 	bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) &&
 		MLX5_CAP_GEN(mdev, relaxed_ordering_write);
 
-	return ro && params->lro_en ?
+	return ro && lro_en ?
 		MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 879ad46d754e1..e9593f5f06610 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -11,11 +11,6 @@ struct mlx5e_xsk_param {
 	u16 chunk_size;
 };
 
-struct mlx5e_lro_param {
-	bool enabled;
-	u32 timeout;
-};
-
 struct mlx5e_cq_param {
 	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
 	struct mlx5_wq_param       wq;
@@ -125,7 +120,6 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
 u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 			  struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk);
-struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params);
 
 /* Build queue parameters */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index 625cd49ef96c5..7b55b14d47ef7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -127,7 +127,7 @@ mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt)
 
 static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
 				enum mlx5_traffic_types tt,
-				const struct mlx5e_lro_param *init_lro_param,
+				const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				bool inner)
 {
 	struct mlx5e_rss_params_traffic_type rss_tt;
@@ -161,7 +161,7 @@ static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
 	rqtn = mlx5e_rqt_get_rqtn(&rss->rqt);
 	mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn,
 				    rqtn, rss->inner_ft_support);
-	mlx5e_tir_builder_build_lro(builder, init_lro_param);
+	mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
 	rss_tt = mlx5e_rss_get_tt_config(rss, tt);
 	mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner);
 
@@ -198,14 +198,14 @@ static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types
 }
 
 static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss,
-				 const struct mlx5e_lro_param *init_lro_param,
+				 const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				 bool inner)
 {
 	enum mlx5_traffic_types tt, max_tt;
 	int err;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner);
+		err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner);
 		if (err)
 			goto err_destroy_tirs;
 	}
@@ -297,7 +297,7 @@ int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 
 int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 		   bool inner_ft_support, u32 drop_rqn,
-		   const struct mlx5e_lro_param *init_lro_param)
+		   const struct mlx5e_packet_merge_param *init_pkt_merge_param)
 {
 	int err;
 
@@ -305,12 +305,12 @@ int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 	if (err)
 		goto err_out;
 
-	err = mlx5e_rss_create_tirs(rss, init_lro_param, false);
+	err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, false);
 	if (err)
 		goto err_destroy_rqt;
 
 	if (inner_ft_support) {
-		err = mlx5e_rss_create_tirs(rss, init_lro_param, true);
+		err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, true);
 		if (err)
 			goto err_destroy_tirs;
 	}
@@ -372,7 +372,7 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
  */
 int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  enum mlx5_traffic_types tt,
-			  const struct mlx5e_lro_param *init_lro_param,
+			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 			  bool inner, u32 *tirn)
 {
 	struct mlx5e_tir *tir;
@@ -381,7 +381,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 	if (!tir) { /* TIR doesn't exist, create one */
 		int err;
 
-		err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner);
+		err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner);
 		if (err)
 			return err;
 		tir = rss_get_tir(rss, tt, inner);
@@ -418,7 +418,8 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss)
 			       mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err);
 }
 
-int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param)
+int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
+				     struct mlx5e_packet_merge_param *pkt_merge_param)
 {
 	struct mlx5e_tir_builder *builder;
 	enum mlx5_traffic_types tt;
@@ -428,7 +429,7 @@ int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_p
 	if (!builder)
 		return -ENOMEM;
 
-	mlx5e_tir_builder_build_lro(builder, lro_param);
+	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 
 	final_err = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index d522a10dadf33..c6b2164163440 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -17,7 +17,7 @@ struct mlx5e_rss *mlx5e_rss_alloc(void);
 void mlx5e_rss_free(struct mlx5e_rss *rss);
 int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 		   bool inner_ft_support, u32 drop_rqn,
-		   const struct mlx5e_lro_param *init_lro_param);
+		   const struct mlx5e_packet_merge_param *init_pkt_merge_param);
 int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 			   bool inner_ft_support, u32 drop_rqn);
 int mlx5e_rss_cleanup(struct mlx5e_rss *rss);
@@ -30,13 +30,14 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 		       bool inner);
 int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  enum mlx5_traffic_types tt,
-			  const struct mlx5e_lro_param *init_lro_param,
+			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 			  bool inner, u32 *tirn);
 
 void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns);
 void mlx5e_rss_disable(struct mlx5e_rss *rss);
 
-int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param);
+int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
+				     struct mlx5e_packet_merge_param *pkt_merge_param);
 int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       const u8 *key, const u8 *hfunc,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 13056cb9757d4..0015a81eb9a17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -13,6 +13,9 @@ struct mlx5e_rx_res {
 	unsigned int max_nch;
 	u32 drop_rqn;
 
+	struct mlx5e_packet_merge_param pkt_merge_param;
+	struct rw_semaphore pkt_merge_param_sem;
+
 	struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS];
 	bool rss_active;
 	u32 rss_rqns[MLX5E_INDIR_RQT_SIZE];
@@ -34,7 +37,7 @@ struct mlx5e_rx_res {
 /* API for rx_res_rss_* */
 
 static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
-				     const struct mlx5e_lro_param *init_lro_param,
+				     const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				     unsigned int init_nch)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
@@ -49,7 +52,7 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
 		return -ENOMEM;
 
 	err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn,
-			     init_lro_param);
+			     init_pkt_merge_param);
 	if (err)
 		goto err_rss_free;
 
@@ -275,7 +278,7 @@ struct mlx5e_rx_res *mlx5e_rx_res_alloc(void)
 }
 
 static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
-				      const struct mlx5e_lro_param *init_lro_param)
+				      const struct mlx5e_packet_merge_param *init_pkt_merge_param)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
 	struct mlx5e_tir_builder *builder;
@@ -306,7 +309,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
 		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 					    inner_ft_support);
-		mlx5e_tir_builder_build_lro(builder, init_lro_param);
+		mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true);
@@ -336,7 +339,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
 		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
 					    inner_ft_support);
-		mlx5e_tir_builder_build_lro(builder, init_lro_param);
+		mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true);
@@ -392,6 +395,7 @@ static int mlx5e_rx_res_ptp_init(struct mlx5e_rx_res *res)
 	if (err)
 		goto out;
 
+	/* Separated from the channels RQs, does not share pkt_merge state with them */
 	mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 				    mlx5e_rqt_get_rqtn(&res->ptp.rqt),
 				    inner_ft_support);
@@ -437,7 +441,7 @@ static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res)
 
 int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 		      enum mlx5e_rx_res_features features, unsigned int max_nch,
-		      u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param,
+		      u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 		      unsigned int init_nch)
 {
 	int err;
@@ -447,11 +451,14 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 	res->max_nch = max_nch;
 	res->drop_rqn = drop_rqn;
 
-	err = mlx5e_rx_res_rss_init_def(res, init_lro_param, init_nch);
+	res->pkt_merge_param = *init_pkt_merge_param;
+	init_rwsem(&res->pkt_merge_param_sem);
+
+	err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch);
 	if (err)
 		goto err_out;
 
-	err = mlx5e_rx_res_channels_init(res, init_lro_param);
+	err = mlx5e_rx_res_channels_init(res, init_pkt_merge_param);
 	if (err)
 		goto err_rss_destroy;
 
@@ -513,7 +520,7 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res)
 	return mlx5e_tir_get_tirn(&res->ptp.tir);
 }
 
-u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
+static u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt);
 }
@@ -645,7 +652,8 @@ int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix)
 	return err;
 }
 
-int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param)
+int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
+					struct mlx5e_packet_merge_param *pkt_merge_param)
 {
 	struct mlx5e_tir_builder *builder;
 	int err, final_err;
@@ -655,7 +663,10 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param
 	if (!builder)
 		return -ENOMEM;
 
-	mlx5e_tir_builder_build_lro(builder, lro_param);
+	down_write(&res->pkt_merge_param_sem);
+	res->pkt_merge_param = *pkt_merge_param;
+
+	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 
 	final_err = 0;
 
@@ -665,7 +676,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param
 		if (!rss)
 			continue;
 
-		err = mlx5e_rss_lro_set_param(rss, lro_param);
+		err = mlx5e_rss_packet_merge_set_param(rss, pkt_merge_param);
 		if (err)
 			final_err = final_err ? : err;
 	}
@@ -673,13 +684,14 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param
 	for (ix = 0; ix < res->max_nch; ix++) {
 		err = mlx5e_tir_modify(&res->channels[ix].direct_tir, builder);
 		if (err) {
-			mlx5_core_warn(res->mdev, "Failed to update LRO state of direct TIR %#x for channel %u: err = %d\n",
+			mlx5_core_warn(res->mdev, "Failed to update packet merge state of direct TIR %#x for channel %u: err = %d\n",
 				       mlx5e_tir_get_tirn(&res->channels[ix].direct_tir), ix, err);
 			if (!final_err)
 				final_err = err;
 		}
 	}
 
+	up_write(&res->pkt_merge_param_sem);
 	mlx5e_tir_builder_free(builder);
 	return final_err;
 }
@@ -688,3 +700,31 @@ struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *
 {
 	return mlx5e_rss_get_hash(res->rss[0]);
 }
+
+int mlx5e_rx_res_tls_tir_create(struct mlx5e_rx_res *res, unsigned int rxq,
+				struct mlx5e_tir *tir)
+{
+	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_tir_builder *builder;
+	u32 rqtn;
+	int err;
+
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
+		return -ENOMEM;
+
+	rqtn = mlx5e_rx_res_get_rqtn_direct(res, rxq);
+
+	mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, rqtn,
+				    inner_ft_support);
+	mlx5e_tir_builder_build_direct(builder);
+	mlx5e_tir_builder_build_tls(builder);
+	down_read(&res->pkt_merge_param_sem);
+	mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
+	err = mlx5e_tir_init(tir, builder, res->mdev, false);
+	up_read(&res->pkt_merge_param_sem);
+
+	mlx5e_tir_builder_free(builder);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 4a15942d79f7d..b39b20a720e0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -25,7 +25,7 @@ enum mlx5e_rx_res_features {
 struct mlx5e_rx_res *mlx5e_rx_res_alloc(void);
 int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 		      enum mlx5e_rx_res_features features, unsigned int max_nch,
-		      u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param,
+		      u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 		      unsigned int init_nch);
 void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res);
 void mlx5e_rx_res_free(struct mlx5e_rx_res *res);
@@ -37,9 +37,6 @@ u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types
 u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
 
-/* RQTN getters for modules that create their own TIRs */
-u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
-
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
 void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res);
@@ -57,7 +54,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt,
 				     u8 rx_hash_fields);
-int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param);
+int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
+					struct mlx5e_packet_merge_param *pkt_merge_param);
 
 int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch);
 int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx);
@@ -68,4 +66,7 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx);
 /* Workaround for hairpin */
 struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res);
 
+/* Accel TIRs */
+int mlx5e_rx_res_tls_tir_create(struct mlx5e_rx_res *res, unsigned int rxq,
+				struct mlx5e_tir *tir);
 #endif /* __MLX5_EN_RX_RES_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
index de936dc4bc483..a1afb8585e37f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -70,24 +70,24 @@ void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn,
 	MLX5_SET(tirc, tirc, tunneled_offload_en, inner_ft_support);
 }
 
-void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
-				 const struct mlx5e_lro_param *lro_param)
+void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder,
+					  const struct mlx5e_packet_merge_param *pkt_merge_param)
 {
 	void *tirc = mlx5e_tir_builder_get_tirc(builder);
 	const unsigned int rough_max_l2_l3_hdr_sz = 256;
 
 	if (builder->modify)
-		MLX5_SET(modify_tir_in, builder->in, bitmask.lro, 1);
+		MLX5_SET(modify_tir_in, builder->in, bitmask.packet_merge, 1);
 
-	if (!lro_param->enabled)
+	if (pkt_merge_param->type == MLX5E_PACKET_MERGE_NONE)
 		return;
 
-	MLX5_SET(tirc, tirc, lro_enable_mask,
-		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
-		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
+	MLX5_SET(tirc, tirc, packet_merge_mask,
+		 MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO |
+		 MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
 		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8);
-	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout);
+	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, pkt_merge_param->timeout);
 }
 
 static int mlx5e_hfunc_to_hw(u8 hfunc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
index e45149a78ed9d..857a84bcd53af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
@@ -18,7 +18,7 @@ struct mlx5e_rss_params_traffic_type {
 };
 
 struct mlx5e_tir_builder;
-struct mlx5e_lro_param;
+struct mlx5e_packet_merge_param;
 
 struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify);
 void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder);
@@ -27,8 +27,8 @@ void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder);
 void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn);
 void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn,
 				 u32 rqtn, bool inner_ft_support);
-void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
-				 const struct mlx5e_lro_param *lro_param);
+void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder,
+					  const struct mlx5e_packet_merge_param *pkt_merge_param);
 void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 				 const struct mlx5e_rss_params_hash *rss_hash,
 				 const struct mlx5e_rss_params_traffic_type *rss_tt,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index fb5397324aa4f..2db9573a3fe69 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -191,7 +191,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 			eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
 			eseg->swp_inner_l4_offset =
 				(skb->csum_start + skb->head - skb->data) / 2;
-			if (skb->protocol == htons(ETH_P_IPV6))
+			if (inner_ip_hdr(skb)->version == 6)
 				eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
 			break;
 		default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index a2a9f68579dd8..15711814d2d28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -100,25 +100,6 @@ mlx5e_ktls_rx_resync_create_resp_list(void)
 	return resp_list;
 }
 
-static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 rqtn)
-{
-	struct mlx5e_tir_builder *builder;
-	int err;
-
-	builder = mlx5e_tir_builder_alloc(false);
-	if (!builder)
-		return -ENOMEM;
-
-	mlx5e_tir_builder_build_rqt(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqtn, false);
-	mlx5e_tir_builder_build_direct(builder);
-	mlx5e_tir_builder_build_tls(builder);
-	err = mlx5e_tir_init(tir, builder, mdev, false);
-
-	mlx5e_tir_builder_free(builder);
-
-	return err;
-}
-
 static void accel_rule_handle_work(struct work_struct *work)
 {
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
@@ -609,7 +590,6 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	struct mlx5_core_dev *mdev;
 	struct mlx5e_priv *priv;
 	int rxq, err;
-	u32 rqtn;
 
 	tls_ctx = tls_get_ctx(sk);
 	priv = netdev_priv(netdev);
@@ -635,9 +615,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	priv_rx->sw_stats = &priv->tls->sw_stats;
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx);
 
-	rqtn = mlx5e_rx_res_get_rqtn_direct(priv->rx_res, rxq);
-
-	err = mlx5e_ktls_create_tir(mdev, &priv_rx->tir, rqtn);
+	err = mlx5e_rx_res_tls_tir_create(priv->rx_res, rxq, &priv_rx->tir);
 	if (err)
 		goto err_create_tir;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 9d451b8ee467c..dc9b8718c3c10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1954,8 +1954,8 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 			return -EOPNOTSUPP;
 		if (!mlx5e_striding_rq_possible(mdev, &priv->channels.params))
 			return -EINVAL;
-	} else if (priv->channels.params.lro_en) {
-		netdev_warn(netdev, "Can't set legacy RQ with LRO, disable LRO first\n");
+	} else if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
+		netdev_warn(netdev, "Can't set legacy RQ with HW-GRO/LRO, disable them first\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 03693fa74a704..d32b70c62c949 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -411,7 +411,7 @@ static int flow_get_tirn(struct mlx5e_priv *priv,
 			 u32 rss_context, u32 *tirn)
 {
 	if (fs->flow_type & FLOW_RSS) {
-		struct mlx5e_lro_param lro_param;
+		struct mlx5e_packet_merge_param pkt_merge_param;
 		struct mlx5e_rss *rss;
 		u32 flow_type;
 		int err;
@@ -426,8 +426,8 @@ static int flow_get_tirn(struct mlx5e_priv *priv,
 		if (tt < 0)
 			return -EINVAL;
 
-		lro_param = mlx5e_get_lro_param(&priv->channels.params);
-		err = mlx5e_rss_obtain_tirn(rss, tt, &lro_param, false, tirn);
+		pkt_merge_param = priv->channels.params.packet_merge;
+		err = mlx5e_rss_obtain_tirn(rss, tt, &pkt_merge_param, false, tirn);
 		if (err)
 			return err;
 		eth_rule->rss = rss;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 41ef6eb70a585..8cf5fbebd674b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2185,17 +2185,14 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 	chs->num = 0;
 }
 
-static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
+static int mlx5e_modify_tirs_packet_merge(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rx_res *res = priv->rx_res;
-	struct mlx5e_lro_param lro_param;
 
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
-
-	return mlx5e_rx_res_lro_set_param(res, &lro_param);
+	return mlx5e_rx_res_packet_merge_set_param(res, &priv->channels.params.packet_merge);
 }
 
-static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro);
+static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_packet_merge);
 
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params, u16 mtu)
@@ -3270,16 +3267,25 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 	}
 
 	new_params = *cur_params;
-	new_params.lro_en = enable;
 
-	if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) ==
-		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL))
-			reset = false;
+	if (enable)
+		new_params.packet_merge.type = MLX5E_PACKET_MERGE_LRO;
+	else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO)
+		new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE;
+	else
+		goto out;
+
+	if (!(cur_params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO &&
+	      new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO)) {
+		if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+			if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) ==
+			    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL))
+				reset = false;
+		}
 	}
 
 	err = mlx5e_safe_switch_params(priv, &new_params,
-				       mlx5e_modify_tirs_lro_ctx, NULL, reset);
+				       mlx5e_modify_tirs_packet_merge_ctx, NULL, reset);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3606,7 +3612,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		goto out;
 	}
 
-	if (params->lro_en)
+	if (params->packet_merge.type == MLX5E_PACKET_MERGE_LRO)
 		reset = false;
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
@@ -4063,8 +4069,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	struct net_device *netdev = priv->netdev;
 	struct mlx5e_params new_params;
 
-	if (priv->channels.params.lro_en) {
-		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
+	if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
+		netdev_warn(netdev, "can't set XDP while HW-GRO/LRO is on, disable them first\n");
 		return -EINVAL;
 	}
 
@@ -4321,9 +4327,10 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		/* No XSK params: checking the availability of striding RQ in general. */
 		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-			params->lro_en = !slow_pci_heuristic(mdev);
+			params->packet_merge.type = slow_pci_heuristic(mdev) ?
+				MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
 	}
-	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
 	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
@@ -4608,7 +4615,6 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	enum mlx5e_rx_res_features features;
-	struct mlx5e_lro_param lro_param;
 	int err;
 
 	priv->rx_res = mlx5e_rx_res_alloc();
@@ -4626,9 +4632,9 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 	features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP;
 	if (priv->channels.params.tunneled_offload_en)
 		features |= MLX5E_RX_RES_FEATURE_INNER_FT;
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features,
-				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->max_nch, priv->drop_rq.rqn,
+				&priv->channels.params.packet_merge,
 				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0684ac6699b2d..edecd149dcab3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -793,7 +793,6 @@ int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup)
 static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_lro_param lro_param;
 	int err;
 
 	priv->rx_res = mlx5e_rx_res_alloc();
@@ -808,9 +807,9 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
-				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->max_nch, priv->drop_rq.rqn,
+				&priv->channels.params.packet_merge,
 				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
@@ -1070,6 +1069,10 @@ static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = {
 	&MLX5E_STATS_GRP(pme),
 	&MLX5E_STATS_GRP(channels),
 	&MLX5E_STATS_GRP(per_port_buff_congest),
+#ifdef CONFIG_MLX5_EN_IPSEC
+	&MLX5E_STATS_GRP(ipsec_sw),
+	&MLX5E_STATS_GRP(ipsec_hw),
+#endif
 };
 
 static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index c6cc67cb4f6ad..d377ddc70fc70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -130,7 +130,7 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
 	/* If vports min rate divider is 0 but their group has bw_share configured, then
 	 * need to set bw_share for vports to minimal value.
 	 */
-	if (!group_level && !max_guarantee && group->bw_share)
+	if (!group_level && !max_guarantee && group && group->bw_share)
 		return 1;
 	return 0;
 }
@@ -423,7 +423,7 @@ static int esw_qos_vport_update_group(struct mlx5_eswitch *esw,
 		return err;
 
 	/* Recalculate bw share weights of old and new groups */
-	if (vport->qos.bw_share) {
+	if (vport->qos.bw_share || new_group->bw_share) {
 		esw_qos_normalize_vports_min_rate(esw, curr_group, extack);
 		esw_qos_normalize_vports_min_rate(esw, new_group, extack);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 0c79e11339362..f3f23fdc20229 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2471,6 +2471,7 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
 	struct mlx5_eswitch *esw = master->priv.eswitch;
 	struct mlx5_flow_table_attr ft_attr = {
 		.max_fte = 1, .prio = 0, .level = 0,
+		.flags = MLX5_FLOW_TABLE_OTHER_VPORT,
 	};
 	struct mlx5_flow_namespace *egress_ns;
 	struct mlx5_flow_table *acl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 269ebb53eda67..cfde0a45b8b8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -67,7 +67,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE;
 
-	params->lro_en = false;
+	params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
 	params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
 	params->tunneled_offload_en = false;
 }
@@ -353,7 +353,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_lro_param lro_param;
 	int err;
 
 	priv->rx_res = mlx5e_rx_res_alloc();
@@ -368,9 +367,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
-				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->max_nch, priv->drop_rq.rqn,
+				&priv->channels.params.packet_merge,
 				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index ca4686094701c..0a02d8bd0a3e5 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -120,7 +120,7 @@ static const struct net_device_ops xtsonic_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 };
 
-static int __init sonic_probe1(struct net_device *dev)
+static int sonic_probe1(struct net_device *dev)
 {
 	unsigned int silicon_revision;
 	struct sonic_local *lp = netdev_priv(dev);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index d51bac7ba5afa..bd06076803295 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -1077,8 +1077,14 @@ static int qlcnic_83xx_add_rings(struct qlcnic_adapter *adapter)
 	sds_mbx_size = sizeof(struct qlcnic_sds_mbx);
 	context_id = recv_ctx->context_id;
 	num_sds = adapter->drv_sds_rings - QLCNIC_MAX_SDS_RINGS;
-	ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
-				    QLCNIC_CMD_ADD_RCV_RINGS);
+	err = ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
+					QLCNIC_CMD_ADD_RCV_RINGS);
+	if (err) {
+		dev_err(&adapter->pdev->dev,
+			"Failed to alloc mbx args %d\n", err);
+		return err;
+	}
+
 	cmd.req.arg[1] = 0 | (num_sds << 8) | (context_id << 16);
 
 	/* set up status rings, mbx 2-81 */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 1cf94248c2217..3422f0746d825 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5531,8 +5531,6 @@ static int stmmac_set_features(struct net_device *netdev,
 			       netdev_features_t features)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
-	bool sph_en;
-	u32 chan;
 
 	/* Keep the COE Type in case of csum is supporting */
 	if (features & NETIF_F_RXCSUM)
@@ -5544,10 +5542,13 @@ static int stmmac_set_features(struct net_device *netdev,
 	 */
 	stmmac_rx_ipc(priv, priv->hw);
 
-	sph_en = (priv->hw->rx_csum > 0) && priv->sph;
+	if (priv->sph_cap) {
+		bool sph_en = (priv->hw->rx_csum > 0) && priv->sph;
+		u32 chan;
 
-	for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++)
-		stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan);
+		for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++)
+			stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 63cd72c5f580c..a0401a9dade5b 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2228,7 +2228,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 	if (dev->domain_data.phyirq > 0)
 		phydev->irq = dev->domain_data.phyirq;
 	else
-		phydev->irq = 0;
+		phydev->irq = PHY_POLL;
 	netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq);
 
 	/* set to AUTOMDIX */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index f329e39100a7d..d3da350777a4d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -9603,12 +9603,9 @@ static int rtl8152_probe(struct usb_interface *intf,
 		netdev->hw_features &= ~NETIF_F_RXCSUM;
 	}
 
-	if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) {
-		switch (le16_to_cpu(udev->descriptor.idProduct)) {
-		case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2:
-		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
-			tp->lenovo_macpassthru = 1;
-		}
+	if (udev->parent &&
+			le16_to_cpu(udev->parent->descriptor.idVendor) == VENDOR_ID_LENOVO) {
+		tp->lenovo_macpassthru = 1;
 	}
 
 	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial &&
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index ccf677015d5bc..131c745dc7010 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -497,6 +497,7 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	/* strip the ethernet header added for pass through VRF device */
 	__skb_pull(skb, skb_network_offset(skb));
 
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 	ret = vrf_ip6_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		dev->stats.tx_errors++;
@@ -579,6 +580,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					       RT_SCOPE_LINK);
 	}
 
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 	ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		vrf_dev->stats.tx_errors++;
diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c
index b7197e80f2264..9a4c8ff32d9dd 100644
--- a/drivers/net/wireguard/allowedips.c
+++ b/drivers/net/wireguard/allowedips.c
@@ -163,7 +163,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
 	return exact;
 }
 
-static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node)
+static inline void connect_node(struct allowedips_node __rcu **parent, u8 bit, struct allowedips_node *node)
 {
 	node->parent_bit_packed = (unsigned long)parent | bit;
 	rcu_assign_pointer(*parent, node);
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 551ddaaaf5400..a46067c38bf5d 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -98,6 +98,7 @@ static int wg_stop(struct net_device *dev)
 {
 	struct wg_device *wg = netdev_priv(dev);
 	struct wg_peer *peer;
+	struct sk_buff *skb;
 
 	mutex_lock(&wg->device_update_lock);
 	list_for_each_entry(peer, &wg->peer_list, peer_list) {
@@ -108,7 +109,9 @@ static int wg_stop(struct net_device *dev)
 		wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
 	}
 	mutex_unlock(&wg->device_update_lock);
-	skb_queue_purge(&wg->incoming_handshakes);
+	while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL)
+		kfree_skb(skb);
+	atomic_set(&wg->handshake_queue_len, 0);
 	wg_socket_reinit(wg, NULL, NULL);
 	return 0;
 }
@@ -235,14 +238,13 @@ static void wg_destruct(struct net_device *dev)
 	destroy_workqueue(wg->handshake_receive_wq);
 	destroy_workqueue(wg->handshake_send_wq);
 	destroy_workqueue(wg->packet_crypt_wq);
-	wg_packet_queue_free(&wg->decrypt_queue);
-	wg_packet_queue_free(&wg->encrypt_queue);
+	wg_packet_queue_free(&wg->handshake_queue, true);
+	wg_packet_queue_free(&wg->decrypt_queue, false);
+	wg_packet_queue_free(&wg->encrypt_queue, false);
 	rcu_barrier(); /* Wait for all the peers to be actually freed. */
 	wg_ratelimiter_uninit();
 	memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
-	skb_queue_purge(&wg->incoming_handshakes);
 	free_percpu(dev->tstats);
-	free_percpu(wg->incoming_handshakes_worker);
 	kvfree(wg->index_hashtable);
 	kvfree(wg->peer_hashtable);
 	mutex_unlock(&wg->device_update_lock);
@@ -298,7 +300,6 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	init_rwsem(&wg->static_identity.lock);
 	mutex_init(&wg->socket_update_lock);
 	mutex_init(&wg->device_update_lock);
-	skb_queue_head_init(&wg->incoming_handshakes);
 	wg_allowedips_init(&wg->peer_allowedips);
 	wg_cookie_checker_init(&wg->cookie_checker, wg);
 	INIT_LIST_HEAD(&wg->peer_list);
@@ -316,16 +317,10 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	if (!dev->tstats)
 		goto err_free_index_hashtable;
 
-	wg->incoming_handshakes_worker =
-		wg_packet_percpu_multicore_worker_alloc(
-				wg_packet_handshake_receive_worker, wg);
-	if (!wg->incoming_handshakes_worker)
-		goto err_free_tstats;
-
 	wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s",
 			WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name);
 	if (!wg->handshake_receive_wq)
-		goto err_free_incoming_handshakes;
+		goto err_free_tstats;
 
 	wg->handshake_send_wq = alloc_workqueue("wg-kex-%s",
 			WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name);
@@ -347,10 +342,15 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	if (ret < 0)
 		goto err_free_encrypt_queue;
 
-	ret = wg_ratelimiter_init();
+	ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker,
+				   MAX_QUEUED_INCOMING_HANDSHAKES);
 	if (ret < 0)
 		goto err_free_decrypt_queue;
 
+	ret = wg_ratelimiter_init();
+	if (ret < 0)
+		goto err_free_handshake_queue;
+
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		goto err_uninit_ratelimiter;
@@ -367,18 +367,18 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 
 err_uninit_ratelimiter:
 	wg_ratelimiter_uninit();
+err_free_handshake_queue:
+	wg_packet_queue_free(&wg->handshake_queue, false);
 err_free_decrypt_queue:
-	wg_packet_queue_free(&wg->decrypt_queue);
+	wg_packet_queue_free(&wg->decrypt_queue, false);
 err_free_encrypt_queue:
-	wg_packet_queue_free(&wg->encrypt_queue);
+	wg_packet_queue_free(&wg->encrypt_queue, false);
 err_destroy_packet_crypt:
 	destroy_workqueue(wg->packet_crypt_wq);
 err_destroy_handshake_send:
 	destroy_workqueue(wg->handshake_send_wq);
 err_destroy_handshake_receive:
 	destroy_workqueue(wg->handshake_receive_wq);
-err_free_incoming_handshakes:
-	free_percpu(wg->incoming_handshakes_worker);
 err_free_tstats:
 	free_percpu(dev->tstats);
 err_free_index_hashtable:
@@ -398,6 +398,7 @@ static struct rtnl_link_ops link_ops __read_mostly = {
 static void wg_netns_pre_exit(struct net *net)
 {
 	struct wg_device *wg;
+	struct wg_peer *peer;
 
 	rtnl_lock();
 	list_for_each_entry(wg, &device_list, device_list) {
@@ -407,6 +408,8 @@ static void wg_netns_pre_exit(struct net *net)
 			mutex_lock(&wg->device_update_lock);
 			rcu_assign_pointer(wg->creating_net, NULL);
 			wg_socket_reinit(wg, NULL, NULL);
+			list_for_each_entry(peer, &wg->peer_list, peer_list)
+				wg_socket_clear_peer_endpoint_src(peer);
 			mutex_unlock(&wg->device_update_lock);
 		}
 	}
diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index 854bc3d97150e..43c7cebbf50b0 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -39,21 +39,18 @@ struct prev_queue {
 
 struct wg_device {
 	struct net_device *dev;
-	struct crypt_queue encrypt_queue, decrypt_queue;
+	struct crypt_queue encrypt_queue, decrypt_queue, handshake_queue;
 	struct sock __rcu *sock4, *sock6;
 	struct net __rcu *creating_net;
 	struct noise_static_identity static_identity;
-	struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
-	struct workqueue_struct *packet_crypt_wq;
-	struct sk_buff_head incoming_handshakes;
-	int incoming_handshake_cpu;
-	struct multicore_worker __percpu *incoming_handshakes_worker;
+	struct workqueue_struct *packet_crypt_wq,*handshake_receive_wq, *handshake_send_wq;
 	struct cookie_checker cookie_checker;
 	struct pubkey_hashtable *peer_hashtable;
 	struct index_hashtable *index_hashtable;
 	struct allowedips peer_allowedips;
 	struct mutex device_update_lock, socket_update_lock;
 	struct list_head device_list, peer_list;
+	atomic_t handshake_queue_len;
 	unsigned int num_peers, device_update_gen;
 	u32 fwmark;
 	u16 incoming_port;
diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
index 48e7b982a3073..1de413b19e342 100644
--- a/drivers/net/wireguard/queueing.c
+++ b/drivers/net/wireguard/queueing.c
@@ -38,11 +38,11 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 	return 0;
 }
 
-void wg_packet_queue_free(struct crypt_queue *queue)
+void wg_packet_queue_free(struct crypt_queue *queue, bool purge)
 {
 	free_percpu(queue->worker);
-	WARN_ON(!__ptr_ring_empty(&queue->ring));
-	ptr_ring_cleanup(&queue->ring, NULL);
+	WARN_ON(!purge && !__ptr_ring_empty(&queue->ring));
+	ptr_ring_cleanup(&queue->ring, purge ? (void(*)(void*))kfree_skb : NULL);
 }
 
 #define NEXT(skb) ((skb)->prev)
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 4ef2944a68bc9..e2388107f7fdc 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -23,7 +23,7 @@ struct sk_buff;
 /* queueing.c APIs: */
 int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 			 unsigned int len);
-void wg_packet_queue_free(struct crypt_queue *queue);
+void wg_packet_queue_free(struct crypt_queue *queue, bool purge);
 struct multicore_worker __percpu *
 wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
 
diff --git a/drivers/net/wireguard/ratelimiter.c b/drivers/net/wireguard/ratelimiter.c
index 3fedd1d21f5ee..dd55e5c26f468 100644
--- a/drivers/net/wireguard/ratelimiter.c
+++ b/drivers/net/wireguard/ratelimiter.c
@@ -176,12 +176,12 @@ int wg_ratelimiter_init(void)
 			(1U << 14) / sizeof(struct hlist_head)));
 	max_entries = table_size * 8;
 
-	table_v4 = kvzalloc(table_size * sizeof(*table_v4), GFP_KERNEL);
+	table_v4 = kvcalloc(table_size, sizeof(*table_v4), GFP_KERNEL);
 	if (unlikely(!table_v4))
 		goto err_kmemcache;
 
 #if IS_ENABLED(CONFIG_IPV6)
-	table_v6 = kvzalloc(table_size * sizeof(*table_v6), GFP_KERNEL);
+	table_v6 = kvcalloc(table_size, sizeof(*table_v6), GFP_KERNEL);
 	if (unlikely(!table_v6)) {
 		kvfree(table_v4);
 		goto err_kmemcache;
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 7dc84bcca2613..7b8df406c7737 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -116,8 +116,8 @@ static void wg_receive_handshake_packet(struct wg_device *wg,
 		return;
 	}
 
-	under_load = skb_queue_len(&wg->incoming_handshakes) >=
-		     MAX_QUEUED_INCOMING_HANDSHAKES / 8;
+	under_load = atomic_read(&wg->handshake_queue_len) >=
+			MAX_QUEUED_INCOMING_HANDSHAKES / 8;
 	if (under_load) {
 		last_under_load = ktime_get_coarse_boottime_ns();
 	} else if (last_under_load) {
@@ -212,13 +212,14 @@ static void wg_receive_handshake_packet(struct wg_device *wg,
 
 void wg_packet_handshake_receive_worker(struct work_struct *work)
 {
-	struct wg_device *wg = container_of(work, struct multicore_worker,
-					    work)->ptr;
+	struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr;
+	struct wg_device *wg = container_of(queue, struct wg_device, handshake_queue);
 	struct sk_buff *skb;
 
-	while ((skb = skb_dequeue(&wg->incoming_handshakes)) != NULL) {
+	while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
 		wg_receive_handshake_packet(wg, skb);
 		dev_kfree_skb(skb);
+		atomic_dec(&wg->handshake_queue_len);
 		cond_resched();
 	}
 }
@@ -553,22 +554,28 @@ void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb)
 	case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION):
 	case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE):
 	case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): {
-		int cpu;
-
-		if (skb_queue_len(&wg->incoming_handshakes) >
-			    MAX_QUEUED_INCOMING_HANDSHAKES ||
-		    unlikely(!rng_is_initialized())) {
+		int cpu, ret = -EBUSY;
+
+		if (unlikely(!rng_is_initialized()))
+			goto drop;
+		if (atomic_read(&wg->handshake_queue_len) > MAX_QUEUED_INCOMING_HANDSHAKES / 2) {
+			if (spin_trylock_bh(&wg->handshake_queue.ring.producer_lock)) {
+				ret = __ptr_ring_produce(&wg->handshake_queue.ring, skb);
+				spin_unlock_bh(&wg->handshake_queue.ring.producer_lock);
+			}
+		} else
+			ret = ptr_ring_produce_bh(&wg->handshake_queue.ring, skb);
+		if (ret) {
+	drop:
 			net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n",
 						wg->dev->name, skb);
 			goto err;
 		}
-		skb_queue_tail(&wg->incoming_handshakes, skb);
-		/* Queues up a call to packet_process_queued_handshake_
-		 * packets(skb):
-		 */
-		cpu = wg_cpumask_next_online(&wg->incoming_handshake_cpu);
+		atomic_inc(&wg->handshake_queue_len);
+		cpu = wg_cpumask_next_online(&wg->handshake_queue.last_cpu);
+		/* Queues up a call to packet_process_queued_handshake_packets(skb): */
 		queue_work_on(cpu, wg->handshake_receive_wq,
-			&per_cpu_ptr(wg->incoming_handshakes_worker, cpu)->work);
+			      &per_cpu_ptr(wg->handshake_queue.worker, cpu)->work);
 		break;
 	}
 	case cpu_to_le32(MESSAGE_DATA):
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index 8c496b7471082..6f07b949cb81d 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -308,7 +308,7 @@ void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer)
 {
 	write_lock_bh(&peer->endpoint_lock);
 	memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6));
-	dst_cache_reset(&peer->endpoint_cache);
+	dst_cache_reset_now(&peer->endpoint_cache);
 	write_unlock_bh(&peer->endpoint_lock);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index c875bf35533ce..009dd4be597b0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -86,6 +86,7 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans,
 		if (len < tlv_len) {
 			IWL_ERR(trans, "invalid TLV len: %zd/%u\n",
 				len, tlv_len);
+			kfree(reduce_power_data);
 			reduce_power_data = ERR_PTR(-EINVAL);
 			goto out;
 		}
@@ -105,6 +106,7 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans,
 				IWL_DEBUG_FW(trans,
 					     "Couldn't allocate (more) reduce_power_data\n");
 
+				kfree(reduce_power_data);
 				reduce_power_data = ERR_PTR(-ENOMEM);
 				goto out;
 			}
@@ -134,6 +136,10 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans,
 done:
 	if (!size) {
 		IWL_DEBUG_FW(trans, "Empty REDUCE_POWER, skipping.\n");
+		/* Better safe than sorry, but 'reduce_power_data' should
+		 * always be NULL if !size.
+		 */
+		kfree(reduce_power_data);
 		reduce_power_data = ERR_PTR(-ENOENT);
 		goto out;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 77124b8b235ee..94553f272d377 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1271,23 +1271,31 @@ _iwl_op_mode_start(struct iwl_drv *drv, struct iwlwifi_opmode_table *op)
 	const struct iwl_op_mode_ops *ops = op->ops;
 	struct dentry *dbgfs_dir = NULL;
 	struct iwl_op_mode *op_mode = NULL;
+	int retry, max_retry = !!iwlwifi_mod_params.fw_restart * IWL_MAX_INIT_RETRY;
+
+	for (retry = 0; retry <= max_retry; retry++) {
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	drv->dbgfs_op_mode = debugfs_create_dir(op->name,
-						drv->dbgfs_drv);
-	dbgfs_dir = drv->dbgfs_op_mode;
+		drv->dbgfs_op_mode = debugfs_create_dir(op->name,
+							drv->dbgfs_drv);
+		dbgfs_dir = drv->dbgfs_op_mode;
 #endif
 
-	op_mode = ops->start(drv->trans, drv->trans->cfg, &drv->fw, dbgfs_dir);
+		op_mode = ops->start(drv->trans, drv->trans->cfg,
+				     &drv->fw, dbgfs_dir);
+
+		if (op_mode)
+			return op_mode;
+
+		IWL_ERR(drv, "retry init count %d\n", retry);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	if (!op_mode) {
 		debugfs_remove_recursive(drv->dbgfs_op_mode);
 		drv->dbgfs_op_mode = NULL;
-	}
 #endif
+	}
 
-	return op_mode;
+	return NULL;
 }
 
 static void _iwl_op_mode_stop(struct iwl_drv *drv)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
index b6442df0c6439..56f2fd3b94906 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
@@ -90,4 +90,7 @@ void iwl_drv_stop(struct iwl_drv *drv);
 #define IWL_EXPORT_SYMBOL(sym)
 #endif
 
+/* max retry for init flow */
+#define IWL_MAX_INIT_RETRY 2
+
 #endif /* __iwl_drv_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 3a4585222d6d4..7e5ad943b20cb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -16,6 +16,7 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/tcp.h>
 
+#include "iwl-drv.h"
 #include "iwl-op-mode.h"
 #include "iwl-io.h"
 #include "mvm.h"
@@ -1116,9 +1117,30 @@ static int iwl_mvm_mac_start(struct ieee80211_hw *hw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
+	int retry, max_retry = 0;
 
 	mutex_lock(&mvm->mutex);
-	ret = __iwl_mvm_mac_start(mvm);
+
+	/* we are starting the mac not in error flow, and restart is enabled */
+	if (!test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) &&
+	    iwlwifi_mod_params.fw_restart) {
+		max_retry = IWL_MAX_INIT_RETRY;
+		/*
+		 * This will prevent mac80211 recovery flows to trigger during
+		 * init failures
+		 */
+		set_bit(IWL_MVM_STATUS_STARTING, &mvm->status);
+	}
+
+	for (retry = 0; retry <= max_retry; retry++) {
+		ret = __iwl_mvm_mac_start(mvm);
+		if (!ret)
+			break;
+
+		IWL_ERR(mvm, "mac start retry %d\n", retry);
+	}
+	clear_bit(IWL_MVM_STATUS_STARTING, &mvm->status);
+
 	mutex_unlock(&mvm->mutex);
 
 	return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index f877d86b038e3..46af8dd2dc930 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1121,6 +1121,8 @@ struct iwl_mvm {
  * @IWL_MVM_STATUS_FIRMWARE_RUNNING: firmware is running
  * @IWL_MVM_STATUS_NEED_FLUSH_P2P: need to flush P2P bcast STA
  * @IWL_MVM_STATUS_IN_D3: in D3 (or at least about to go into it)
+ * @IWL_MVM_STATUS_STARTING: starting mac,
+ *	used to disable restart flow while in STARTING state
  */
 enum iwl_mvm_status {
 	IWL_MVM_STATUS_HW_RFKILL,
@@ -1132,6 +1134,7 @@ enum iwl_mvm_status {
 	IWL_MVM_STATUS_FIRMWARE_RUNNING,
 	IWL_MVM_STATUS_NEED_FLUSH_P2P,
 	IWL_MVM_STATUS_IN_D3,
+	IWL_MVM_STATUS_STARTING,
 };
 
 /* Keep track of completed init configuration */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 77ea2d0a30916..49c32a8132a0f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -687,6 +687,7 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm)
 	int ret;
 
 	rtnl_lock();
+	wiphy_lock(mvm->hw->wiphy);
 	mutex_lock(&mvm->mutex);
 
 	ret = iwl_run_init_mvm_ucode(mvm);
@@ -702,6 +703,7 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm)
 		iwl_mvm_stop_device(mvm);
 
 	mutex_unlock(&mvm->mutex);
+	wiphy_unlock(mvm->hw->wiphy);
 	rtnl_unlock();
 
 	if (ret < 0)
@@ -1424,6 +1426,9 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	 */
 	if (!mvm->fw_restart && fw_error) {
 		iwl_fw_error_collect(&mvm->fwrt, false);
+	} else if (test_bit(IWL_MVM_STATUS_STARTING,
+			    &mvm->status)) {
+		IWL_ERR(mvm, "Starting mac, retry will be triggered anyway\n");
 	} else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		struct iwl_mvm_reprobe *reprobe;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index ba36d3caec8e1..7440f2b443eca 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -176,7 +176,7 @@ mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta)
 		if (ht_cap->ht_supported)
 			mode |= PHY_MODE_GN;
 
-		if (he_cap->has_he)
+		if (he_cap && he_cap->has_he)
 			mode |= PHY_MODE_AX_24G;
 	} else if (band == NL80211_BAND_5GHZ) {
 		mode |= PHY_MODE_A;
@@ -187,7 +187,7 @@ mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta)
 		if (vht_cap->vht_supported)
 			mode |= PHY_MODE_AC;
 
-		if (he_cap->has_he)
+		if (he_cap && he_cap->has_he)
 			mode |= PHY_MODE_AX_5G;
 	}
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
index e4473a5512415..74c3d8cb31002 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
@@ -25,6 +25,9 @@ static bool rt2x00usb_check_usb_error(struct rt2x00_dev *rt2x00dev, int status)
 	if (status == -ENODEV || status == -ENOENT)
 		return true;
 
+	if (!test_bit(DEVICE_STATE_STARTED, &rt2x00dev->flags))
+		return false;
+
 	if (status == -EPROTO || status == -ETIMEDOUT)
 		rt2x00dev->num_proto_errs++;
 	else
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index 5ff4207df66e1..f1b5176a5085b 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -189,6 +189,7 @@ config PINCTRL_QCOM_SPMI_PMIC
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
+  select GPIOLIB
 	select GPIOLIB_IRQCHIP
 	select IRQ_DOMAIN_HIERARCHY
 	help
@@ -203,6 +204,7 @@ config PINCTRL_QCOM_SSBI_PMIC
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
+  select GPIOLIB
 	select GPIOLIB_IRQCHIP
 	select IRQ_DOMAIN_HIERARCHY
 	help
diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig
index 2fffa57e596e4..fe224a54f24c0 100644
--- a/drivers/platform/x86/dell/Kconfig
+++ b/drivers/platform/x86/dell/Kconfig
@@ -187,7 +187,7 @@ config DELL_WMI_AIO
 
 config DELL_WMI_DESCRIPTOR
 	tristate
-	default m
+	default n
 	depends on ACPI_WMI
 
 config DELL_WMI_LED
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 27595aba214d9..3dc055ce6e61b 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -1178,15 +1178,6 @@ static int tpacpi_rfk_update_swstate(const struct tpacpi_rfk *tp_rfk)
 	return status;
 }
 
-/* Query FW and update rfkill sw state for all rfkill switches */
-static void tpacpi_rfk_update_swstate_all(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < TPACPI_RFK_SW_MAX; i++)
-		tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]);
-}
-
 /*
  * Sync the HW-blocking state of all rfkill switches,
  * do notice it causes the rfkill core to schedule uevents
@@ -3129,9 +3120,6 @@ static void tpacpi_send_radiosw_update(void)
 	if (wlsw == TPACPI_RFK_RADIO_OFF)
 		tpacpi_rfk_update_hwblock_state(true);
 
-	/* Sync sw blocking state */
-	tpacpi_rfk_update_swstate_all();
-
 	/* Sync hw blocking state last if it is hw-unblocked */
 	if (wlsw == TPACPI_RFK_RADIO_ON)
 		tpacpi_rfk_update_hwblock_state(false);
@@ -8853,6 +8841,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (1st gen) */
 	TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (2nd gen) */
 	TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (3nd gen) */
+	TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (4nd gen) */
 	TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL),	/* P15 (1st gen) / P15v (1st gen) */
 	TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL),	/* X1 Carbon (9th gen) */
 };
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 1a406df251cbf..f7197b7161d52 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -5075,14 +5075,9 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* NPort Recovery mode or node is just allocated */
 		if (!lpfc_nlp_not_used(ndlp)) {
 			/* A LOGO is completing and the node is in NPR state.
-			 * If this a fabric node that cleared its transport
-			 * registration, release the rpi.
+			 * Just unregister the RPI because the node is still
+			 * required.
 			 */
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (phba->sli_rev == LPFC_SLI_REV4)
-				ndlp->nlp_flag |= NLP_RELEASE_RPI;
-			spin_unlock_irq(&ndlp->lock);
 			lpfc_unreg_rpi(vport, ndlp);
 		} else {
 			/* Indicate the node has already released, should
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 78343d3f93857..554b6f7842236 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1899,12 +1899,12 @@ static void session_recovery_timedout(struct work_struct *work)
 	}
 	spin_unlock_irqrestore(&session->lock, flags);
 
-	if (session->transport->session_recovery_timedout)
-		session->transport->session_recovery_timedout(session);
-
 	ISCSI_DBG_TRANS_SESSION(session, "Unblocking SCSI target\n");
 	scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE);
 	ISCSI_DBG_TRANS_SESSION(session, "Completed unblocking SCSI target\n");
+
+	if (session->transport->session_recovery_timedout)
+		session->transport->session_recovery_timedout(session);
 }
 
 static void __iscsi_unblock_session(struct work_struct *work)
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index 51424557810da..f725248ba57f4 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -421,6 +421,13 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba)
 	return err;
 }
 
+static int ufs_intel_adl_init(struct ufs_hba *hba)
+{
+	hba->nop_out_timeout = 200;
+	hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8;
+	return ufs_intel_common_init(hba);
+}
+
 static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = {
 	.name                   = "intel-pci",
 	.init			= ufs_intel_common_init,
@@ -449,6 +456,15 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = {
 	.device_reset		= ufs_intel_device_reset,
 };
 
+static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = {
+	.name			= "intel-pci",
+	.init			= ufs_intel_adl_init,
+	.exit			= ufs_intel_common_exit,
+	.link_startup_notify	= ufs_intel_link_startup_notify,
+	.resume			= ufs_intel_resume,
+	.device_reset		= ufs_intel_device_reset,
+};
+
 #ifdef CONFIG_PM_SLEEP
 static int ufshcd_pci_restore(struct device *dev)
 {
@@ -563,6 +579,8 @@ static const struct pci_device_id ufshcd_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops },
 	{ PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops },
 	{ PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops },
 	{ }	/* terminate list */
 };
 
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 30134f49b037a..13891745a9719 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -419,6 +419,8 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 {
 	struct thermal_instance *pos;
 	tz->temperature = THERMAL_TEMP_INVALID;
+	tz->prev_low_trip = -INT_MAX;
+	tz->prev_high_trip = INT_MAX;
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
 		pos->initialized = false;
 }
diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c
index 7f656fac503fe..5163d60756b73 100644
--- a/drivers/tty/serial/8250/8250_bcm7271.c
+++ b/drivers/tty/serial/8250/8250_bcm7271.c
@@ -237,6 +237,7 @@ struct brcmuart_priv {
 	u32		rx_err;
 	u32		rx_timeout;
 	u32		rx_abort;
+	u32		saved_mctrl;
 };
 
 static struct dentry *brcmuart_debugfs_root;
@@ -1133,16 +1134,27 @@ static int brcmuart_remove(struct platform_device *pdev)
 static int __maybe_unused brcmuart_suspend(struct device *dev)
 {
 	struct brcmuart_priv *priv = dev_get_drvdata(dev);
+	struct uart_8250_port *up = serial8250_get_port(priv->line);
+	struct uart_port *port = &up->port;
 
 	serial8250_suspend_port(priv->line);
 	clk_disable_unprepare(priv->baud_mux_clk);
 
+	/*
+	 * This will prevent resume from enabling RTS before the
+	 *  baud rate has been resored.
+	 */
+	priv->saved_mctrl = port->mctrl;
+	port->mctrl = 0;
+
 	return 0;
 }
 
 static int __maybe_unused brcmuart_resume(struct device *dev)
 {
 	struct brcmuart_priv *priv = dev_get_drvdata(dev);
+	struct uart_8250_port *up = serial8250_get_port(priv->line);
+	struct uart_port *port = &up->port;
 	int ret;
 
 	ret = clk_prepare_enable(priv->baud_mux_clk);
@@ -1165,6 +1177,7 @@ static int __maybe_unused brcmuart_resume(struct device *dev)
 		start_rx_dma(serial8250_get_port(priv->line));
 	}
 	serial8250_resume_port(priv->line);
+	port->mctrl = priv->saved_mctrl;
 	return 0;
 }
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 726912b16a559..f7d89440076a1 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1349,29 +1349,33 @@ pericom_do_set_divisor(struct uart_port *port, unsigned int baud,
 {
 	int scr;
 	int lcr;
-	int actual_baud;
-	int tolerance;
 
-	for (scr = 5 ; scr <= 15 ; scr++) {
-		actual_baud = 921600 * 16 / scr;
-		tolerance = actual_baud / 50;
+	for (scr = 16; scr > 4; scr--) {
+		unsigned int maxrate = port->uartclk / scr;
+		unsigned int divisor = max(maxrate / baud, 1U);
+		int delta = maxrate / divisor - baud;
 
-		if ((baud < actual_baud + tolerance) &&
-			(baud > actual_baud - tolerance)) {
+		if (baud > maxrate + baud / 50)
+			continue;
 
+		if (delta > baud / 50)
+			divisor++;
+
+		if (divisor > 0xffff)
+			continue;
+
+		/* Update delta due to possible divisor change */
+		delta = maxrate / divisor - baud;
+		if (abs(delta) < baud / 50) {
 			lcr = serial_port_in(port, UART_LCR);
 			serial_port_out(port, UART_LCR, lcr | 0x80);
-
-			serial_port_out(port, UART_DLL, 1);
-			serial_port_out(port, UART_DLM, 0);
+			serial_port_out(port, UART_DLL, divisor & 0xff);
+			serial_port_out(port, UART_DLM, divisor >> 8 & 0xff);
 			serial_port_out(port, 2, 16 - scr);
 			serial_port_out(port, UART_LCR, lcr);
 			return;
-		} else if (baud > actual_baud) {
-			break;
 		}
 	}
-	serial8250_do_set_divisor(port, baud, quot, quot_frac);
 }
 static int pci_pericom_setup(struct serial_private *priv,
 		  const struct pciserial_board *board,
@@ -2317,12 +2321,19 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.setup      = pci_pericom_setup_four_at_eight,
 	},
 	{
-		.vendor     = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S,
+		.vendor     = PCI_VENDOR_ID_ACCESIO,
 		.device     = PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4,
 		.subvendor  = PCI_ANY_ID,
 		.subdevice  = PCI_ANY_ID,
 		.setup      = pci_pericom_setup_four_at_eight,
 	},
+	{
+		.vendor     = PCI_VENDOR_ID_ACCESIO,
+		.device     = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S,
+		.subvendor  = PCI_ANY_ID,
+		.subdevice  = PCI_ANY_ID,
+		.setup      = pci_pericom_setup_four_at_eight,
+	},
 	{
 		.vendor     = PCI_VENDOR_ID_ACCESIO,
 		.device     = PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4,
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index e4dd82fd7c2a5..ec88b706e882f 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2024,13 +2024,6 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl)
 	struct uart_8250_port *up = up_to_u8250p(port);
 	unsigned char mcr;
 
-	if (port->rs485.flags & SER_RS485_ENABLED) {
-		if (serial8250_in_MCR(up) & UART_MCR_RTS)
-			mctrl |= TIOCM_RTS;
-		else
-			mctrl &= ~TIOCM_RTS;
-	}
-
 	mcr = serial8250_TIOCM_to_MCR(mctrl);
 
 	mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr;
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index d361cd84ff8cf..52518a606c06a 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2947,6 +2947,7 @@ MODULE_DEVICE_TABLE(of, sbsa_uart_of_match);
 
 static const struct acpi_device_id __maybe_unused sbsa_uart_acpi_match[] = {
 	{ "ARMH0011", 0 },
+	{ "ARMHB000", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match);
diff --git a/drivers/tty/serial/liteuart.c b/drivers/tty/serial/liteuart.c
index dbc0559a91575..2941659e52747 100644
--- a/drivers/tty/serial/liteuart.c
+++ b/drivers/tty/serial/liteuart.c
@@ -270,8 +270,10 @@ static int liteuart_probe(struct platform_device *pdev)
 
 	/* get membase */
 	port->membase = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
-	if (IS_ERR(port->membase))
-		return PTR_ERR(port->membase);
+	if (IS_ERR(port->membase)) {
+		ret = PTR_ERR(port->membase);
+		goto err_erase_id;
+	}
 
 	/* values not from device tree */
 	port->dev = &pdev->dev;
@@ -285,7 +287,18 @@ static int liteuart_probe(struct platform_device *pdev)
 	port->line = dev_id;
 	spin_lock_init(&port->lock);
 
-	return uart_add_one_port(&liteuart_driver, &uart->port);
+	platform_set_drvdata(pdev, port);
+
+	ret = uart_add_one_port(&liteuart_driver, &uart->port);
+	if (ret)
+		goto err_erase_id;
+
+	return 0;
+
+err_erase_id:
+	xa_erase(&liteuart_array, uart->id);
+
+	return ret;
 }
 
 static int liteuart_remove(struct platform_device *pdev)
@@ -293,6 +306,7 @@ static int liteuart_remove(struct platform_device *pdev)
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct liteuart_port *uart = to_liteuart_port(port);
 
+	uart_remove_one_port(&liteuart_driver, port);
 	xa_erase(&liteuart_array, uart->id);
 
 	return 0;
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index fcef7a961430b..489d19274f9ad 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -598,6 +598,9 @@ static void msm_start_rx_dma(struct msm_port *msm_port)
 	u32 val;
 	int ret;
 
+	if (IS_ENABLED(CONFIG_CONSOLE_POLL))
+		return;
+
 	if (!dma->chan)
 		return;
 
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 45e2e4109acd0..b6223fab0687d 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -1506,7 +1506,7 @@ static struct tegra_uart_chip_data tegra20_uart_chip_data = {
 	.fifo_mode_enable_status	= false,
 	.uart_max_port			= 5,
 	.max_dma_burst_bytes		= 4,
-	.error_tolerance_low_range	= 0,
+	.error_tolerance_low_range	= -4,
 	.error_tolerance_high_range	= 4,
 };
 
@@ -1517,7 +1517,7 @@ static struct tegra_uart_chip_data tegra30_uart_chip_data = {
 	.fifo_mode_enable_status	= false,
 	.uart_max_port			= 5,
 	.max_dma_burst_bytes		= 4,
-	.error_tolerance_low_range	= 0,
+	.error_tolerance_low_range	= -4,
 	.error_tolerance_high_range	= 4,
 };
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 1e738f265eeaa..61e3dd0222af1 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1075,6 +1075,11 @@ uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 		goto out;
 
 	if (!tty_io_error(tty)) {
+		if (uport->rs485.flags & SER_RS485_ENABLED) {
+			set &= ~TIOCM_RTS;
+			clear &= ~TIOCM_RTS;
+		}
+
 		uart_update_mctrl(uport, set, clear);
 		ret = 0;
 	}
@@ -1549,6 +1554,7 @@ static void uart_tty_port_shutdown(struct tty_port *port)
 {
 	struct uart_state *state = container_of(port, struct uart_state, port);
 	struct uart_port *uport = uart_port_check(state);
+	char *buf;
 
 	/*
 	 * At this point, we stop accepting input.  To do this, we
@@ -1570,8 +1576,18 @@ static void uart_tty_port_shutdown(struct tty_port *port)
 	 */
 	tty_port_set_suspended(port, 0);
 
-	uart_change_pm(state, UART_PM_STATE_OFF);
+	/*
+	 * Free the transmit buffer.
+	 */
+	spin_lock_irq(&uport->lock);
+	buf = state->xmit.buf;
+	state->xmit.buf = NULL;
+	spin_unlock_irq(&uport->lock);
 
+	if (buf)
+		free_page((unsigned long)buf);
+
+	uart_change_pm(state, UART_PM_STATE_OFF);
 }
 
 static void uart_wait_until_sent(struct tty_struct *tty, int timeout)
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 1f3b4a1422126..f9af7ebe003d7 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -337,19 +337,6 @@ static void cdns3_ep_inc_deq(struct cdns3_endpoint *priv_ep)
 	cdns3_ep_inc_trb(&priv_ep->dequeue, &priv_ep->ccs, priv_ep->num_trbs);
 }
 
-static void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req)
-{
-	struct cdns3_endpoint *priv_ep = priv_req->priv_ep;
-	int current_trb = priv_req->start_trb;
-
-	while (current_trb != priv_req->end_trb) {
-		cdns3_ep_inc_deq(priv_ep);
-		current_trb = priv_ep->dequeue;
-	}
-
-	cdns3_ep_inc_deq(priv_ep);
-}
-
 /**
  * cdns3_allow_enable_l1 - enable/disable permits to transition to L1.
  * @priv_dev: Extended gadget object
@@ -1517,10 +1504,11 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 
 		trb = priv_ep->trb_pool + priv_ep->dequeue;
 
-		/* Request was dequeued and TRB was changed to TRB_LINK. */
-		if (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) {
+		/* The TRB was changed as link TRB, and the request was handled at ep_dequeue */
+		while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) {
 			trace_cdns3_complete_trb(priv_ep, trb);
-			cdns3_move_deq_to_next_trb(priv_req);
+			cdns3_ep_inc_deq(priv_ep);
+			trb = priv_ep->trb_pool + priv_ep->dequeue;
 		}
 
 		if (!request->stream_id) {
diff --git a/drivers/usb/cdns3/cdnsp-mem.c b/drivers/usb/cdns3/cdnsp-mem.c
index ad9aee3f1e398..97866bfb2da9d 100644
--- a/drivers/usb/cdns3/cdnsp-mem.c
+++ b/drivers/usb/cdns3/cdnsp-mem.c
@@ -987,6 +987,9 @@ int cdnsp_endpoint_init(struct cdnsp_device *pdev,
 
 	/* Set up the endpoint ring. */
 	pep->ring = cdnsp_ring_alloc(pdev, 2, ring_type, max_packet, mem_flags);
+	if (!pep->ring)
+		return -ENOMEM;
+
 	pep->skip = false;
 
 	/* Fill the endpoint context */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8239fe7129dd7..019351c0b52cf 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -434,6 +434,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1532, 0x0116), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Lenovo Powered USB-C Travel Hub (4X90S92381, RTL8153 GigE) */
+	{ USB_DEVICE(0x17ef, 0x721e), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Lenovo ThinkCenter A630Z TI024Gen3 usb-audio */
 	{ USB_DEVICE(0x17ef, 0xa012), .driver_info =
 			USB_QUIRK_DISCONNECT_SUSPEND },
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 311597bba80e2..eaa49aef29352 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -366,7 +366,9 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 /* Must be called with xhci->lock held, releases and aquires lock back */
 static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 {
-	u32 temp_32;
+	struct xhci_segment *new_seg	= xhci->cmd_ring->deq_seg;
+	union xhci_trb *new_deq		= xhci->cmd_ring->dequeue;
+	u64 crcr;
 	int ret;
 
 	xhci_dbg(xhci, "Abort command ring\n");
@@ -375,13 +377,18 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 
 	/*
 	 * The control bits like command stop, abort are located in lower
-	 * dword of the command ring control register. Limit the write
-	 * to the lower dword to avoid corrupting the command ring pointer
-	 * in case if the command ring is stopped by the time upper dword
-	 * is written.
+	 * dword of the command ring control register.
+	 * Some controllers require all 64 bits to be written to abort the ring.
+	 * Make sure the upper dword is valid, pointing to the next command,
+	 * avoiding corrupting the command ring pointer in case the command ring
+	 * is stopped by the time the upper dword is written.
 	 */
-	temp_32 = readl(&xhci->op_regs->cmd_ring);
-	writel(temp_32 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
+	next_trb(xhci, NULL, &new_seg, &new_deq);
+	if (trb_is_link(new_deq))
+		next_trb(xhci, NULL, &new_seg, &new_deq);
+
+	crcr = xhci_trb_virt_to_dma(new_seg, new_deq);
+	xhci_write_64(xhci, crcr | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
 
 	/* Section 4.6.1.2 of xHCI 1.0 spec says software should also time the
 	 * completion of the Command Abort operation. If CRR is not negated in 5
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 7f2f3ff1b3911..6010b99011261 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4110,11 +4110,7 @@ static void run_state_machine(struct tcpm_port *port)
 				       tcpm_try_src(port) ? SRC_TRY
 							  : SNK_ATTACHED,
 				       0);
-		else
-			/* Wait for VBUS, but not forever */
-			tcpm_set_state(port, PORT_RESET, PD_T_PS_SOURCE_ON);
 		break;
-
 	case SRC_TRY:
 		port->try_src_count++;
 		tcpm_set_cc(port, tcpm_rp_cc(port));
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index ef9c57ce09066..9a49ea6b5112f 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -366,11 +366,17 @@ static void vgacon_init(struct vc_data *c, int init)
 	struct uni_pagedir *p;
 
 	/*
-	 * We cannot be loaded as a module, therefore init is always 1,
-	 * but vgacon_init can be called more than once, and init will
-	 * not be 1.
+	 * We cannot be loaded as a module, therefore init will be 1
+	 * if we are the default console, however if we are a fallback
+	 * console, for example if fbcon has failed registration, then
+	 * init will be 0, so we need to make sure our boot parameters
+	 * have been copied to the console structure for vgacon_resize
+	 * ultimately called by vc_resize.  Any subsequent calls to
+	 * vgacon_init init will have init set to 0 too.
 	 */
 	c->vc_can_do_color = vga_can_do_color;
+	c->vc_scan_lines = vga_scan_lines;
+	c->vc_font.height = c->vc_cell_height = vga_video_font_height;
 
 	/* set dimensions manually if init != 0 since vc_resize() will fail */
 	if (init) {
@@ -379,8 +385,6 @@ static void vgacon_init(struct vc_data *c, int init)
 	} else
 		vc_resize(c, vga_video_num_columns, vga_video_num_lines);
 
-	c->vc_scan_lines = vga_scan_lines;
-	c->vc_font.height = c->vc_cell_height = vga_video_font_height;
 	c->vc_complement_mask = 0x7700;
 	if (vga_512_chars)
 		c->vc_hi_font_mask = 0x0800;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e00c4c1f622f3..c37239c8ac0c6 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3970,11 +3970,23 @@ static void btrfs_end_empty_barrier(struct bio *bio)
  */
 static void write_dev_flush(struct btrfs_device *device)
 {
-	struct request_queue *q = bdev_get_queue(device->bdev);
 	struct bio *bio = device->flush_bio;
 
+#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+	/*
+	 * When a disk has write caching disabled, we skip submission of a bio
+	 * with flush and sync requests before writing the superblock, since
+	 * it's not needed. However when the integrity checker is enabled, this
+	 * results in reports that there are metadata blocks referred by a
+	 * superblock that were not properly flushed. So don't skip the bio
+	 * submission only when the integrity checker is enabled for the sake
+	 * of simplicity, since this is a debug tool and not meant for use in
+	 * non-debug builds.
+	 */
+	struct request_queue *q = bdev_get_queue(device->bdev);
 	if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
 		return;
+#endif
 
 	bio_reset(bio);
 	bio->bi_end_io = btrfs_end_empty_barrier;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bc2e4683e8568..7bf09ca82137a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7488,6 +7488,19 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	 */
 	fs_info->fs_devices->total_rw_bytes = 0;
 
+	/*
+	 * Lockdep complains about possible circular locking dependency between
+	 * a disk's open_mutex (struct gendisk.open_mutex), the rw semaphores
+	 * used for freeze procection of a fs (struct super_block.s_writers),
+	 * which we take when starting a transaction, and extent buffers of the
+	 * chunk tree if we call read_one_dev() while holding a lock on an
+	 * extent buffer of the chunk tree. Since we are mounting the filesystem
+	 * and at this point there can't be any concurrent task modifying the
+	 * chunk tree, to keep it simple, just skip locking on the chunk tree.
+	 */
+	ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
+	path->skip_locking = 1;
+
 	/*
 	 * Read all device items, and then all the chunk items. All
 	 * device items are found before any chunk item (their object id
@@ -7513,10 +7526,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 				goto error;
 			break;
 		}
-		/*
-		 * The nodes on level 1 are not locked but we don't need to do
-		 * that during mount time as nothing else can access the tree
-		 */
 		node = path->nodes[1];
 		if (node) {
 			if (last_ra_node != node->start) {
@@ -7544,7 +7553,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 			 * requirement for chunk allocation, see the comment on
 			 * top of btrfs_chunk_alloc() for details.
 			 */
-			ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
 			chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
 			ret = read_one_chunk(&found_key, leaf, chunk);
 			if (ret)
diff --git a/fs/file.c b/fs/file.c
index 8627dacfc4246..ad4a8bf3cf109 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -858,6 +858,10 @@ loop:
 			file = NULL;
 		else if (!get_file_rcu_many(file, refs))
 			goto loop;
+		else if (files_lookup_fd_raw(files, fd) != file) {
+			fput_many(file, refs);
+			goto loop;
+		}
 	}
 	rcu_read_unlock();
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5414c2c335809..fba32141a651b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -940,7 +940,7 @@ do_alloc:
 		else if (height == ip->i_height)
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 		else
-			iomap->length = size - pos;
+			iomap->length = size - iomap->offset;
 	} else if (flags & IOMAP_WRITE) {
 		u64 alloc_size;
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 6e00d15ef0a82..cc51b5f5f52d8 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1402,13 +1402,6 @@ out:
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
-	if (ip->i_gl) {
-		glock_clear_object(ip->i_gl, ip);
-		wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
-		gfs2_glock_add_to_lru(ip->i_gl);
-		gfs2_glock_put_eventually(ip->i_gl);
-		ip->i_gl = NULL;
-	}
 	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
 
@@ -1421,6 +1414,13 @@ out:
 		gfs2_holder_uninit(&ip->i_iopen_gh);
 		gfs2_glock_put_eventually(gl);
 	}
+	if (ip->i_gl) {
+		glock_clear_object(ip->i_gl, ip);
+		wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
+		gfs2_glock_add_to_lru(ip->i_gl);
+		gfs2_glock_put_eventually(ip->i_gl);
+		ip->i_gl = NULL;
+	}
 }
 
 static struct inode *gfs2_alloc_inode(struct super_block *sb)
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 8c61315657546..e8f77903d7757 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -711,6 +711,13 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
 
 static inline bool io_should_retry_thread(long err)
 {
+	/*
+	 * Prevent perpetual task_work retry, if the task (or its group) is
+	 * exiting.
+	 */
+	if (fatal_signal_pending(current))
+		return false;
+
 	switch (err) {
 	case -EAGAIN:
 	case -ERESTARTSYS:
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 974d497a897dc..6224b1e32681c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -976,6 +976,15 @@ static inline int acpi_get_local_address(acpi_handle handle, u32 *addr)
 	return -ENODEV;
 }
 
+static inline int acpi_register_wakeup_handler(int wake_irq,
+	bool (*wakeup)(void *context), void *context)
+{
+	return -ENXIO;
+}
+
+static inline void acpi_unregister_wakeup_handler(
+	bool (*wakeup)(void *context), void *context) { }
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index e4f3bfe087570..ef8c7accbc689 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -154,6 +154,8 @@ struct kretprobe {
 	struct kretprobe_holder *rph;
 };
 
+#define KRETPROBE_MAX_DATA_SIZE	4096
+
 struct kretprobe_instance {
 	union {
 		struct freelist_node freelist;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 993204a6c1a13..25d775764a5ac 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -3309,8 +3309,8 @@ enum {
 };
 
 enum {
-	MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO  = 0x1,
-	MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO  = 0x2,
+	MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO  = BIT(0),
+	MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO  = BIT(1),
 };
 
 enum {
@@ -3335,7 +3335,7 @@ struct mlx5_ifc_tirc_bits {
 
 	u8         reserved_at_80[0x4];
 	u8         lro_timeout_period_usecs[0x10];
-	u8         lro_enable_mask[0x4];
+	u8         packet_merge_mask[0x4];
 	u8         lro_max_ip_payload_size[0x8];
 
 	u8         reserved_at_a0[0x40];
@@ -6369,7 +6369,7 @@ struct mlx5_ifc_modify_tir_bitmask_bits {
 	u8         reserved_at_3c[0x1];
 	u8         hash[0x1];
 	u8         reserved_at_3e[0x1];
-	u8         lro[0x1];
+	u8         packet_merge[0x1];
 };
 
 struct mlx5_ifc_modify_tir_out_bits {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d79163208dfdb..ce81cc96a98d9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4403,7 +4403,8 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
 	spin_lock(&txq->_xmit_lock);
-	txq->xmit_lock_owner = cpu;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, cpu);
 }
 
 static inline bool __netif_tx_acquire(struct netdev_queue *txq)
@@ -4420,26 +4421,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
 	spin_lock_bh(&txq->_xmit_lock);
-	txq->xmit_lock_owner = smp_processor_id();
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 }
 
 static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 {
 	bool ok = spin_trylock(&txq->_xmit_lock);
-	if (likely(ok))
-		txq->xmit_lock_owner = smp_processor_id();
+
+	if (likely(ok)) {
+		/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+		WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
+	}
 	return ok;
 }
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-	txq->xmit_lock_owner = -1;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-	txq->xmit_lock_owner = -1;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock_bh(&txq->_xmit_lock);
 }
 
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index bf21591a9e5e6..0cda61855d907 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key)
 }
 
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
-#endif
 
 u64 siphash_1u64(const u64 a, const siphash_key_t *key);
 u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key);
@@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len,
 static inline u64 siphash(const void *data, size_t len,
 			  const siphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
 		return __siphash_unaligned(data, len, key);
-#endif
 	return ___siphash_aligned(data, len, key);
 }
 
@@ -96,10 +93,8 @@ typedef struct {
 
 u32 __hsiphash_aligned(const void *data, size_t len,
 		       const hsiphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key);
-#endif
 
 u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key);
 u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key);
@@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len,
 static inline u32 hsiphash(const void *data, size_t len,
 			   const hsiphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
 		return __hsiphash_unaligned(data, len, key);
-#endif
 	return ___hsiphash_aligned(data, len, key);
 }
 
diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 67634675e9197..df6622a5fe98f 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -79,6 +79,17 @@ static inline void dst_cache_reset(struct dst_cache *dst_cache)
 	dst_cache->reset_ts = jiffies;
 }
 
+/**
+ *	dst_cache_reset_now - invalidate the cache contents immediately
+ *	@dst_cache: the cache
+ *
+ *	The caller must be sure there are no concurrent users, as this frees
+ *	all dst_cache users immediately, rather than waiting for the next
+ *	per-cpu usage like dst_cache_reset does. Most callers should use the
+ *	higher speed lazily-freed dst_cache_reset function instead.
+ */
+void dst_cache_reset_now(struct dst_cache *dst_cache);
+
 /**
  *	dst_cache_init - initialize the cache, allocating the required storage
  *	@dst_cache: the cache
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 4b10676c69d19..bd07484ab9dd5 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -69,7 +69,7 @@ struct fib_rules_ops {
 	int			(*action)(struct fib_rule *,
 					  struct flowi *, int,
 					  struct fib_lookup_arg *);
-	bool			(*suppress)(struct fib_rule *,
+	bool			(*suppress)(struct fib_rule *, int,
 					    struct fib_lookup_arg *);
 	int			(*match)(struct fib_rule *,
 					 struct flowi *, int);
@@ -218,7 +218,9 @@ INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule,
 			    struct fib_lookup_arg *arg));
 
 INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg));
 INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg));
 #endif
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index ab5348e57db1a..3417ba2d27ad6 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -438,7 +438,7 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
-	return net->ipv4.fib_num_tclassid_users;
+	return atomic_read(&net->ipv4.fib_num_tclassid_users);
 }
 #else
 static inline int fib_num_tclassid_users(struct net *net)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2f65701a43c95..6c5b2efc4f17d 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -65,7 +65,7 @@ struct netns_ipv4 {
 	bool			fib_has_custom_local_routes;
 	bool			fib_offload_disabled;
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	int			fib_num_tclassid_users;
+	atomic_t		fib_num_tclassid_users;
 #endif
 	struct hlist_head	*fib_table_hash;
 	struct sock		*fibnl;
diff --git a/include/net/sock.h b/include/net/sock.h
index 7b0c7f5aab676..7ac5075f9c18a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2400,19 +2400,22 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
  * @sk: socket
  *
  * Use the per task page_frag instead of the per socket one for
- * optimization when we know that we're in the normal context and owns
+ * optimization when we know that we're in process context and own
  * everything that's associated with %current.
  *
- * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
- * inside other socket operations and end up recursing into sk_page_frag()
- * while it's already in use.
+ * Both direct reclaim and page faults can nest inside other
+ * socket operations and end up recursing into sk_page_frag()
+ * while it's already in use: explicitly avoid task page_frag
+ * usage if the caller is potentially doing any of them.
+ * This assumes that page fault handlers use the GFP_NOFS flags.
  *
  * Return: a per task page_frag if context allows that,
  * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (gfpflags_normal_context(sk->sk_allocation))
+	if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) ==
+	    (__GFP_DIRECT_RECLAIM | __GFP_FS))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1cf8bca1ea861..2ef90d15699fb 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2006,6 +2006,9 @@ int register_kretprobe(struct kretprobe *rp)
 		}
 	}
 
+	if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+		return -E2BIG;
+
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6f4625f8276f1..0d12ec7be3017 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1914,7 +1914,7 @@ static void __init init_uclamp_rq(struct rq *rq)
 		};
 	}
 
-	rq->uclamp_flags = 0;
+	rq->uclamp_flags = UCLAMP_FLAG_IDLE;
 }
 
 static void __init init_uclamp(void)
@@ -6660,11 +6660,11 @@ static int __init setup_preempt_mode(char *str)
 	int mode = sched_dynamic_mode(str);
 	if (mode < 0) {
 		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
-		return 1;
+		return 0;
 	}
 
 	sched_dynamic_update(mode);
-	return 0;
+	return 1;
 }
 __setup("preempt=", setup_preempt_mode);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5e452dd57af01..18db461f77cdf 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3836,6 +3836,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		iter->fmt[i] = '\0';
 		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
 
+		/*
+		 * If iter->seq is full, the above call no longer guarantees
+		 * that ap is in sync with fmt processing, and further calls
+		 * to va_arg() can return wrong positional arguments.
+		 *
+		 * Ensure that ap is no longer used in this case.
+		 */
+		if (iter->seq.full) {
+			p = "";
+			break;
+		}
+
 		if (star)
 			len = va_arg(ap, int);
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index d860351b9dea6..12a735bd90a56 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3419,7 +3419,7 @@ static int check_synth_field(struct synth_event *event,
 
 	if (strcmp(field->type, hist_field->type) != 0) {
 		if (field->size != hist_field->size ||
-		    field->is_signed != hist_field->is_signed)
+		    (!field->is_string && field->is_signed != hist_field->is_signed))
 			return -EINVAL;
 	}
 
diff --git a/lib/siphash.c b/lib/siphash.c
index a90112ee72a1f..72b9068ab57bf 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -49,6 +49,7 @@
 	SIPROUND; \
 	return (v0 ^ v1) ^ (v2 ^ v3);
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));
@@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
 	POSTAMBLE
 }
 EXPORT_SYMBOL(__siphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));
@@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
 	POSTAMBLE
 }
 EXPORT_SYMBOL(__siphash_unaligned);
-#endif
 
 /**
  * siphash_1u64 - compute 64-bit siphash PRF value of a u64
@@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32);
 	HSIPROUND; \
 	return (v0 ^ v1) ^ (v2 ^ v3);
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));
@@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key)
 {
@@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
 
 /**
  * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
@@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32);
 	HSIPROUND; \
 	return v1 ^ v3;
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u32));
@@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key)
 {
@@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
 
 /**
  * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
diff --git a/net/core/dev.c b/net/core/dev.c
index aa7a98fd2d64b..91f53eeb0e79f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4195,7 +4195,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	if (dev->flags & IFF_UP) {
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
-		if (txq->xmit_lock_owner != cpu) {
+		/* Other cpus might concurrently change txq->xmit_lock_owner
+		 * to -1 or to their cpu id, but not to our id.
+		 */
+		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
 			if (dev_xmit_recursion())
 				goto recursion_alert;
 
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index be74ab4551c20..0ccfd5fa5cb9b 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -162,3 +162,22 @@ void dst_cache_destroy(struct dst_cache *dst_cache)
 	free_percpu(dst_cache->cache);
 }
 EXPORT_SYMBOL_GPL(dst_cache_destroy);
+
+void dst_cache_reset_now(struct dst_cache *dst_cache)
+{
+	int i;
+
+	if (!dst_cache->cache)
+		return;
+
+	dst_cache->reset_ts = jiffies;
+	for_each_possible_cpu(i) {
+		struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i);
+		struct dst_entry *dst = idst->dst;
+
+		idst->cookie = 0;
+		idst->dst = NULL;
+		dst_release(dst);
+	}
+}
+EXPORT_SYMBOL_GPL(dst_cache_reset_now);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 79df7cd9dbc16..1bb567a3b329c 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -323,7 +323,7 @@ jumped:
 		if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress,
 							      fib6_rule_suppress,
 							      fib4_rule_suppress,
-							      rule, arg))
+							      rule, flags, arg))
 			continue;
 
 		if (err != -EAGAIN) {
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f4468980b6757..4744c7839de53 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2587,7 +2587,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
 free:
 	kfree(t);
 out:
-	return -ENOBUFS;
+	return -ENOMEM;
 }
 
 static void __devinet_sysctl_unregister(struct net *net,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 9fe13e4f5d08a..4d61ddd8a0ecf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1582,7 +1582,7 @@ static int __net_init fib_net_init(struct net *net)
 	int error;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	net->ipv4.fib_num_tclassid_users = 0;
+	atomic_set(&net->ipv4.fib_num_tclassid_users, 0);
 #endif
 	error = ip_fib_net_init(net);
 	if (error < 0)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index ce54a30c2ef1e..d279cb8ac1584 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -141,6 +141,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule,
 }
 
 INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg)
 {
 	struct fib_result *result = (struct fib_result *) arg->result;
@@ -263,7 +264,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (tb[FRA_FLOW]) {
 		rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
 		if (rule4->tclassid)
-			net->ipv4.fib_num_tclassid_users++;
+			atomic_inc(&net->ipv4.fib_num_tclassid_users);
 	}
 #endif
 
@@ -295,7 +296,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (((struct fib4_rule *)rule)->tclassid)
-		net->ipv4.fib_num_tclassid_users--;
+		atomic_dec(&net->ipv4.fib_num_tclassid_users);
 #endif
 	net->ipv4.fib_has_custom_rules = true;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3364cb9c67e01..fde7797b58069 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -220,7 +220,7 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 {
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (fib_nh->nh_tclassid)
-		net->ipv4.fib_num_tclassid_users--;
+		atomic_dec(&net->ipv4.fib_num_tclassid_users);
 #endif
 	fib_nh_common_release(&fib_nh->nh_common);
 }
@@ -632,7 +632,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	nh->nh_tclassid = cfg->fc_flow;
 	if (nh->nh_tclassid)
-		net->ipv4.fib_num_tclassid_users++;
+		atomic_inc(&net->ipv4.fib_num_tclassid_users);
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	nh->fib_nh_weight = nh_weight;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index ed2f061b87685..f0bac6f7ab6bb 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -808,6 +808,12 @@ int esp6_input_done2(struct sk_buff *skb, int err)
 		struct tcphdr *th;
 
 		offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+
+		if (offset < 0) {
+			err = -EINVAL;
+			goto out;
+		}
+
 		uh = (void *)(skb->data + offset);
 		th = (void *)(skb->data + offset);
 		hdr_len += offset;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 40f3e4f9f33a2..dcedfe29d9d93 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -267,6 +267,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule,
 }
 
 INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg)
 {
 	struct fib6_result *res = arg->result;
@@ -294,8 +295,7 @@ INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule,
 	return false;
 
 suppress_route:
-	if (!(arg->flags & FIB_LOOKUP_NOREF))
-		ip6_rt_put(rt);
+	ip6_rt_put_flags(rt, flags);
 	return true;
 }
 
diff --git a/net/mac80211/led.h b/net/mac80211/led.h
index fb3aaa3c56069..b71a1428d883c 100644
--- a/net/mac80211/led.h
+++ b/net/mac80211/led.h
@@ -72,19 +72,19 @@ static inline void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local,
 #endif
 
 static inline void
-ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes)
+ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, int bytes)
 {
 #ifdef CONFIG_MAC80211_LEDS
-	if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
+	if (atomic_read(&local->tpt_led_active))
 		local->tpt_led_trigger->tx_bytes += bytes;
 #endif
 }
 
 static inline void
-ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes)
+ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, int bytes)
 {
 #ifdef CONFIG_MAC80211_LEDS
-	if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
+	if (atomic_read(&local->tpt_led_active))
 		local->tpt_led_trigger->rx_bytes += bytes;
 #endif
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 419f06ef8c986..1958e4d59b524 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1952,7 +1952,8 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 		int keyid = rx->sta->ptk_idx;
 		sta_ptk = rcu_dereference(rx->sta->ptk[keyid]);
 
-		if (ieee80211_has_protected(fc)) {
+		if (ieee80211_has_protected(fc) &&
+		    !(status->flag & RX_FLAG_IV_STRIPPED)) {
 			cs = rx->sta->cipher_scheme;
 			keyid = ieee80211_get_keyid(rx->skb, cs);
 
@@ -4873,6 +4874,7 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 	struct ieee80211_rate *rate = NULL;
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 
 	WARN_ON_ONCE(softirq_count() == 0);
 
@@ -4969,9 +4971,9 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 	if (!(status->flag & RX_FLAG_8023))
 		skb = ieee80211_rx_monitor(local, skb, rate);
 	if (skb) {
-		ieee80211_tpt_led_trig_rx(local,
-					  ((struct ieee80211_hdr *)skb->data)->frame_control,
-					  skb->len);
+		if ((status->flag & RX_FLAG_8023) ||
+			ieee80211_is_data_present(hdr->frame_control))
+			ieee80211_tpt_led_trig_rx(local, skb->len);
 
 		if (status->flag & RX_FLAG_8023)
 			__ieee80211_rx_handle_8023(hw, pubsta, skb, list);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8921088a5df65..0527bf41a32c7 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1720,21 +1720,19 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
  * Returns false if the frame couldn't be transmitted but was queued instead.
  */
 static bool __ieee80211_tx(struct ieee80211_local *local,
-			   struct sk_buff_head *skbs, int led_len,
-			   struct sta_info *sta, bool txpending)
+			   struct sk_buff_head *skbs, struct sta_info *sta,
+			   bool txpending)
 {
 	struct ieee80211_tx_info *info;
 	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_vif *vif;
 	struct sk_buff *skb;
 	bool result;
-	__le16 fc;
 
 	if (WARN_ON(skb_queue_empty(skbs)))
 		return true;
 
 	skb = skb_peek(skbs);
-	fc = ((struct ieee80211_hdr *)skb->data)->frame_control;
 	info = IEEE80211_SKB_CB(skb);
 	sdata = vif_to_sdata(info->control.vif);
 	if (sta && !sta->uploaded)
@@ -1768,8 +1766,6 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
 
 	result = ieee80211_tx_frags(local, vif, sta, skbs, txpending);
 
-	ieee80211_tpt_led_trig_tx(local, fc, led_len);
-
 	WARN_ON_ONCE(!skb_queue_empty(skbs));
 
 	return result;
@@ -1919,7 +1915,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 	ieee80211_tx_result res_prepare;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	bool result = true;
-	int led_len;
 
 	if (unlikely(skb->len < 10)) {
 		dev_kfree_skb(skb);
@@ -1927,7 +1922,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* initialises tx */
-	led_len = skb->len;
 	res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);
 
 	if (unlikely(res_prepare == TX_DROP)) {
@@ -1950,8 +1944,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 		return true;
 
 	if (!invoke_tx_handlers_late(&tx))
-		result = __ieee80211_tx(local, &tx.skbs, led_len,
-					tx.sta, txpending);
+		result = __ieee80211_tx(local, &tx.skbs, tx.sta, txpending);
 
 	return result;
 }
@@ -4174,6 +4167,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta;
 	struct sk_buff *next;
+	int len = skb->len;
 
 	if (unlikely(skb->len < ETH_HLEN)) {
 		kfree_skb(skb);
@@ -4220,10 +4214,8 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 		}
 	} else {
 		/* we cannot process non-linear frames on this path */
-		if (skb_linearize(skb)) {
-			kfree_skb(skb);
-			goto out;
-		}
+		if (skb_linearize(skb))
+			goto out_free;
 
 		/* the frame could be fragmented, software-encrypted, and other
 		 * things so we cannot really handle checksum offload with it -
@@ -4257,7 +4249,10 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 	goto out;
  out_free:
 	kfree_skb(skb);
+	len = 0;
  out:
+	if (len)
+		ieee80211_tpt_led_trig_tx(local, len);
 	rcu_read_unlock();
 }
 
@@ -4395,8 +4390,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 }
 
 static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
-			      struct sk_buff *skb, int led_len,
-			      struct sta_info *sta,
+			      struct sk_buff *skb, struct sta_info *sta,
 			      bool txpending)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -4409,6 +4403,8 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
 	if (sta)
 		sk_pacing_shift_update(skb->sk, local->hw.tx_sk_pacing_shift);
 
+	ieee80211_tpt_led_trig_tx(local, skb->len);
+
 	if (ieee80211_queue_skb(local, sdata, sta, skb))
 		return true;
 
@@ -4497,7 +4493,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 	if (key)
 		info->control.hw_key = &key->conf;
 
-	ieee80211_tx_8023(sdata, skb, skb->len, sta, false);
+	ieee80211_tx_8023(sdata, skb, sta, false);
 
 	return;
 
@@ -4636,7 +4632,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 		if (IS_ERR(sta) || (sta && !sta->uploaded))
 			sta = NULL;
 
-		result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true);
+		result = ieee80211_tx_8023(sdata, skb, sta, true);
 	} else {
 		struct sk_buff_head skbs;
 
@@ -4646,7 +4642,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 		hdr = (struct ieee80211_hdr *)skb->data;
 		sta = sta_info_get(sdata, hdr->addr1);
 
-		result = __ieee80211_tx(local, &skbs, skb->len, sta, true);
+		result = __ieee80211_tx(local, &skbs, sta, true);
 	}
 
 	return result;
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 5ca186d53cb0f..fb1bf4ec85296 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -760,7 +760,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start,
 }
 
 static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start,
-			     unsigned int daddr_extent)
+			     unsigned int daddr_extent, unsigned char type)
 {
 	struct net *net = dev_net(mdev->dev);
 	struct mctp_route *rt, *tmp;
@@ -777,7 +777,8 @@ static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start,
 
 	list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) {
 		if (rt->dev == mdev &&
-		    rt->min == daddr_start && rt->max == daddr_end) {
+		    rt->min == daddr_start && rt->max == daddr_end &&
+		    rt->type == type) {
 			list_del_rcu(&rt->list);
 			/* TODO: immediate RTM_DELROUTE */
 			mctp_route_release(rt);
@@ -795,7 +796,7 @@ int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr)
 
 int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr)
 {
-	return mctp_route_remove(mdev, addr, 0);
+	return mctp_route_remove(mdev, addr, 0, RTN_LOCAL);
 }
 
 /* removes all entries for a given device */
@@ -975,7 +976,7 @@ static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_type != RTN_UNICAST)
 		return -EINVAL;
 
-	rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len);
+	rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len, RTN_UNICAST);
 	return rc;
 }
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index ffeb2df8be7ae..6e587feb705c4 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1491,22 +1491,52 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head)
 	kfree(mdev);
 }
 
-static void mpls_ifdown(struct net_device *dev, int event)
+static int mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		bool nh_del = false;
+		u8 alive = 0;
 
 		if (!rt)
 			continue;
 
-		alive = 0;
-		deleted = 0;
+		if (event == NETDEV_UNREGISTER) {
+			u8 deleted = 0;
+
+			for_nexthops(rt) {
+				struct net_device *nh_dev =
+					rtnl_dereference(nh->nh_dev);
+
+				if (!nh_dev || nh_dev == dev)
+					deleted++;
+				if (nh_dev == dev)
+					nh_del = true;
+			} endfor_nexthops(rt);
+
+			/* if there are no more nexthops, delete the route */
+			if (deleted == rt->rt_nhn) {
+				mpls_route_update(net, index, NULL, NULL);
+				continue;
+			}
+
+			if (nh_del) {
+				size_t size = sizeof(*rt) + rt->rt_nhn *
+					rt->rt_nh_size;
+				struct mpls_route *orig = rt;
+
+				rt = kmalloc(size, GFP_KERNEL);
+				if (!rt)
+					return -ENOMEM;
+				memcpy(rt, orig, size);
+			}
+		}
+
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
 
@@ -1530,16 +1560,15 @@ static void mpls_ifdown(struct net_device *dev, int event)
 next:
 			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
 				alive++;
-			if (!rtnl_dereference(nh->nh_dev))
-				deleted++;
 		} endfor_nexthops(rt);
 
 		WRITE_ONCE(rt->rt_nhn_alive, alive);
 
-		/* if there are no more nexthops, delete the route */
-		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
-			mpls_route_update(net, index, NULL, NULL);
+		if (nh_del)
+			mpls_route_update(net, index, rt, NULL);
 	}
+
+	return 0;
 }
 
 static void mpls_ifup(struct net_device *dev, unsigned int flags)
@@ -1597,8 +1626,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		return NOTIFY_OK;
 
 	switch (event) {
+		int err;
+
 	case NETDEV_DOWN:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		break;
 	case NETDEV_UP:
 		flags = dev_get_flags(dev);
@@ -1609,13 +1642,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
-		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
-		else
-			mpls_ifdown(dev, event);
+		} else {
+			err = mpls_ifdown(dev, event);
+			if (err)
+				return notifier_from_errno(err);
+		}
 		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
 			mpls_dev_sysctl_unregister(dev, mdev);
@@ -1626,8 +1664,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			int err;
-
 			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index abf19c0e3ba0b..5327d130c4b56 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -500,7 +500,7 @@ void rds_tcp_tune(struct socket *sock)
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	}
 	if (rtn->rcvbuf_size > 0) {
-		sk->sk_sndbuf = rtn->rcvbuf_size;
+		sk->sk_rcvbuf = rtn->rcvbuf_size;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
 	release_sock(sk);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index dbea0bfee48e9..8120138dac018 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -135,16 +135,20 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle)
 	return bundle;
 }
 
+static void rxrpc_free_bundle(struct rxrpc_bundle *bundle)
+{
+	rxrpc_put_peer(bundle->params.peer);
+	kfree(bundle);
+}
+
 void rxrpc_put_bundle(struct rxrpc_bundle *bundle)
 {
 	unsigned int d = bundle->debug_id;
 	unsigned int u = atomic_dec_return(&bundle->usage);
 
 	_debug("PUT B=%x %u", d, u);
-	if (u == 0) {
-		rxrpc_put_peer(bundle->params.peer);
-		kfree(bundle);
-	}
+	if (u == 0)
+		rxrpc_free_bundle(bundle);
 }
 
 /*
@@ -328,7 +332,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
 	return candidate;
 
 found_bundle_free:
-	kfree(candidate);
+	rxrpc_free_bundle(candidate);
 found_bundle:
 	rxrpc_get_bundle(bundle);
 	spin_unlock(&local->client_bundles_lock);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 68396d0520525..0298fe2ad6d32 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -299,6 +299,12 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
 	return peer;
 }
 
+static void rxrpc_free_peer(struct rxrpc_peer *peer)
+{
+	rxrpc_put_local(peer->local);
+	kfree_rcu(peer, rcu);
+}
+
 /*
  * Set up a new incoming peer.  There shouldn't be any other matching peers
  * since we've already done a search in the list from the non-reentrant context
@@ -365,7 +371,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
 		spin_unlock_bh(&rxnet->peer_hash_lock);
 
 		if (peer)
-			kfree(candidate);
+			rxrpc_free_peer(candidate);
 		else
 			peer = candidate;
 	}
@@ -420,8 +426,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
-	rxrpc_put_local(peer->local);
-	kfree_rcu(peer, rcu);
+	rxrpc_free_peer(peer);
 }
 
 /*
@@ -457,8 +462,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
 	if (n == 0) {
 		hash_del_rcu(&peer->hash_link);
 		list_del_init(&peer->keepalive_link);
-		rxrpc_put_local(peer->local);
-		kfree_rcu(peer, rcu);
+		rxrpc_free_peer(peer);
 	}
 }
 
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 3d8219e3b0264..06e4a07bdcdc1 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -548,6 +548,10 @@ static void smc_stat_fallback(struct smc_sock *smc)
 
 static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 {
+	wait_queue_head_t *smc_wait = sk_sleep(&smc->sk);
+	wait_queue_head_t *clc_wait = sk_sleep(smc->clcsock->sk);
+	unsigned long flags;
+
 	smc->use_fallback = true;
 	smc->fallback_rsn = reason_code;
 	smc_stat_fallback(smc);
@@ -556,6 +560,16 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		smc->clcsock->file->private_data = smc->clcsock;
 		smc->clcsock->wq.fasync_list =
 			smc->sk.sk_socket->wq.fasync_list;
+
+		/* There may be some entries remaining in
+		 * smc socket->wq, which should be removed
+		 * to clcsocket->wq during the fallback.
+		 */
+		spin_lock_irqsave(&smc_wait->lock, flags);
+		spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING);
+		list_splice_init(&smc_wait->head, &clc_wait->head);
+		spin_unlock(&clc_wait->lock);
+		spin_unlock_irqrestore(&smc_wait->lock, flags);
 	}
 }
 
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 04620b53b74a7..84102db5bb314 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -195,6 +195,7 @@ int smc_close_active(struct smc_sock *smc)
 	int old_state;
 	long timeout;
 	int rc = 0;
+	int rc1 = 0;
 
 	timeout = current->flags & PF_EXITING ?
 		  0 : sock_flag(sk, SOCK_LINGER) ?
@@ -232,8 +233,11 @@ again:
 			/* actively shutdown clcsock before peer close it,
 			 * prevent peer from entering TIME_WAIT state.
 			 */
-			if (smc->clcsock && smc->clcsock->sk)
-				rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
+			if (smc->clcsock && smc->clcsock->sk) {
+				rc1 = kernel_sock_shutdown(smc->clcsock,
+							   SHUT_RDWR);
+				rc = rc ? rc : rc1;
+			}
 		} else {
 			/* peer event has changed the state */
 			goto again;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 508a14fc4f587..5a9c22ee75fa4 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -582,18 +582,17 @@ int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
 void smc_lgr_cleanup_early(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
-	struct list_head *lgr_list;
 	spinlock_t *lgr_lock;
 
 	if (!lgr)
 		return;
 
 	smc_conn_free(conn);
-	lgr_list = smc_lgr_list_head(lgr, &lgr_lock);
+	smc_lgr_list_head(lgr, &lgr_lock);
 	spin_lock_bh(lgr_lock);
 	/* do not use this link group for new connections */
-	if (!list_empty(lgr_list))
-		list_del_init(lgr_list);
+	if (!list_empty(&lgr->list))
+		list_del_init(&lgr->list);
 	spin_unlock_bh(lgr_lock);
 	__smc_lgr_terminate(lgr, true);
 }
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index b0cdcea101806..bd96ec26f4f99 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -515,7 +515,7 @@ static int tls_do_encryption(struct sock *sk,
 	memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv,
 	       prot->iv_size + prot->salt_size);
 
-	xor_iv_with_seq(prot, rec->iv_data, tls_ctx->tx.rec_seq);
+	xor_iv_with_seq(prot, rec->iv_data + iv_offset, tls_ctx->tx.rec_seq);
 
 	sge->offset += prot->prepend_size;
 	sge->length -= prot->prepend_size;
@@ -1487,7 +1487,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 	else
 		memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
 
-	xor_iv_with_seq(prot, iv, tls_ctx->rx.rec_seq);
+	xor_iv_with_seq(prot, iv + iv_offset, tls_ctx->rx.rec_seq);
 
 	/* Prepare AAD */
 	tls_make_aad(aad, rxm->full_len - prot->overhead_size +
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index 10a0bffc3cf6c..4208fa8a4db5b 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -252,6 +252,11 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = 0x02c8,
 	},
+	{
+		.flags = FLAG_SOF,
+		.device = 0x02c8,
+		.codec_hid = "ESSX8336",
+	},
 /* Cometlake-H */
 	{
 		.flags = FLAG_SOF,
@@ -276,6 +281,11 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = 0x06c8,
 	},
+		{
+		.flags = FLAG_SOF,
+		.device = 0x06c8,
+		.codec_hid = "ESSX8336",
+	},
 #endif
 
 /* Icelake */
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index ea8ab8b433378..d22c96eb2f8fb 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -438,6 +438,15 @@ int snd_hda_codec_set_pin_target(struct hda_codec *codec, hda_nid_t nid,
 #define for_each_hda_codec_node(nid, codec) \
 	for ((nid) = (codec)->core.start_nid; (nid) < (codec)->core.end_nid; (nid)++)
 
+/* Set the codec power_state flag to indicate to allow unsol event handling;
+ * see hda_codec_unsol_event() in hda_bind.c.  Calling this might confuse the
+ * state tracking, so use with care.
+ */
+static inline void snd_hda_codec_allow_unsol_events(struct hda_codec *codec)
+{
+	codec->core.dev.power.power_state = PMSG_ON;
+}
+
 /*
  * get widget capabilities
  */
diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 31ff11ab868e1..039b9f2f8e947 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -750,6 +750,11 @@ static void cs42l42_resume(struct sub_codec *cs42l42)
 	if (cs42l42->full_scale_vol)
 		cs8409_i2c_write(cs42l42, 0x2001, 0x01);
 
+	/* we have to explicitly allow unsol event handling even during the
+	 * resume phase so that the jack event is processed properly
+	 */
+	snd_hda_codec_allow_unsol_events(cs42l42->codec);
+
 	cs42l42_enable_jack_detect(cs42l42);
 }
 
diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c
index 943d7d933e81b..03f24edfe4f64 100644
--- a/sound/soc/codecs/rk817_codec.c
+++ b/sound/soc/codecs/rk817_codec.c
@@ -539,3 +539,4 @@ module_platform_driver(rk817_codec_driver);
 MODULE_DESCRIPTION("ASoC RK817 codec driver");
 MODULE_AUTHOR("binyuan <kevan.lan@rock-chips.com>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:rk817-codec");
diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c
index 8ee9a77bd83d3..a74c980ee7753 100644
--- a/sound/soc/tegra/tegra186_dspk.c
+++ b/sound/soc/tegra/tegra186_dspk.c
@@ -26,51 +26,162 @@ static const struct reg_default tegra186_dspk_reg_defaults[] = {
 	{ TEGRA186_DSPK_CODEC_CTRL,  0x03000000 },
 };
 
-static int tegra186_dspk_get_control(struct snd_kcontrol *kcontrol,
+static int tegra186_dspk_get_fifo_th(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
 	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
 
-	if (strstr(kcontrol->id.name, "FIFO Threshold"))
-		ucontrol->value.integer.value[0] = dspk->rx_fifo_th;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		ucontrol->value.integer.value[0] = dspk->osr_val;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		ucontrol->value.integer.value[0] = dspk->lrsel;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		ucontrol->value.integer.value[0] = dspk->ch_sel;
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		ucontrol->value.integer.value[0] = dspk->mono_to_stereo;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		ucontrol->value.integer.value[0] = dspk->stereo_to_mono;
+	ucontrol->value.integer.value[0] = dspk->rx_fifo_th;
 
 	return 0;
 }
 
-static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol,
+static int tegra186_dspk_put_fifo_th(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
 	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
-	int val = ucontrol->value.integer.value[0];
-
-	if (strstr(kcontrol->id.name, "FIFO Threshold"))
-		dspk->rx_fifo_th = val;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		dspk->osr_val = val;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		dspk->lrsel = val;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		dspk->ch_sel = val;
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		dspk->mono_to_stereo = val;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		dspk->stereo_to_mono = val;
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == dspk->rx_fifo_th)
+		return 0;
+
+	dspk->rx_fifo_th = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_osr_val(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->osr_val;
 
 	return 0;
 }
 
+static int tegra186_dspk_put_osr_val(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->osr_val)
+		return 0;
+
+	dspk->osr_val = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->lrsel;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->lrsel)
+		return 0;
+
+	dspk->lrsel = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_ch_sel(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->ch_sel;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_ch_sel(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->ch_sel)
+		return 0;
+
+	dspk->ch_sel = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->mono_to_stereo;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->mono_to_stereo)
+		return 0;
+
+	dspk->mono_to_stereo = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->stereo_to_mono;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->stereo_to_mono)
+		return 0;
+
+	dspk->stereo_to_mono = value;
+
+	return 1;
+}
+
 static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev)
 {
 	struct tegra186_dspk *dspk = dev_get_drvdata(dev);
@@ -279,17 +390,19 @@ static const struct soc_enum tegra186_dspk_lrsel_enum =
 static const struct snd_kcontrol_new tegrat186_dspk_controls[] = {
 	SOC_SINGLE_EXT("FIFO Threshold", SND_SOC_NOPM, 0,
 		       TEGRA186_DSPK_RX_FIFO_DEPTH - 1, 0,
-		       tegra186_dspk_get_control, tegra186_dspk_put_control),
+		       tegra186_dspk_get_fifo_th, tegra186_dspk_put_fifo_th),
 	SOC_ENUM_EXT("OSR Value", tegra186_dspk_osr_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_osr_val, tegra186_dspk_put_osr_val),
 	SOC_ENUM_EXT("LR Polarity Select", tegra186_dspk_lrsel_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_pol_sel, tegra186_dspk_put_pol_sel),
 	SOC_ENUM_EXT("Channel Select", tegra186_dspk_ch_sel_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_ch_sel, tegra186_dspk_put_ch_sel),
 	SOC_ENUM_EXT("Mono To Stereo", tegra186_dspk_mono_conv_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_mono_to_stereo,
+		     tegra186_dspk_put_mono_to_stereo),
 	SOC_ENUM_EXT("Stereo To Mono", tegra186_dspk_stereo_conv_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_stereo_to_mono,
+		     tegra186_dspk_put_stereo_to_mono),
 };
 
 static const struct snd_soc_component_driver tegra186_dspk_cmpnt = {
diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c
index bcccdf3ddc528..1a2e868a62209 100644
--- a/sound/soc/tegra/tegra210_admaif.c
+++ b/sound/soc/tegra/tegra210_admaif.c
@@ -424,46 +424,122 @@ static const struct snd_soc_dai_ops tegra_admaif_dai_ops = {
 	.trigger	= tegra_admaif_trigger,
 };
 
-static int tegra_admaif_get_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_admaif_pget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+
+	ucontrol->value.enumerated.item[0] =
+		admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg];
+
+	return 0;
+}
+
+static int tegra210_admaif_pput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg])
+		return 0;
+
+	admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
+static int tegra210_admaif_cget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+
+	ucontrol->value.enumerated.item[0] =
+		admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg];
+
+	return 0;
+}
+
+static int tegra210_admaif_cput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg])
+		return 0;
+
+	admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
+static int tegra210_admaif_pget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
-	long *uctl_val = &ucontrol->value.integer.value[0];
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
 
-	if (strstr(kcontrol->id.name, "Playback Mono To Stereo"))
-		*uctl_val = admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg];
-	else if (strstr(kcontrol->id.name, "Capture Mono To Stereo"))
-		*uctl_val = admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg];
-	else if (strstr(kcontrol->id.name, "Playback Stereo To Mono"))
-		*uctl_val = admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg];
-	else if (strstr(kcontrol->id.name, "Capture Stereo To Mono"))
-		*uctl_val = admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg];
+	ucontrol->value.enumerated.item[0] =
+		admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg];
 
 	return 0;
 }
 
-static int tegra_admaif_put_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_admaif_pput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg])
+		return 0;
+
+	admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
+static int tegra210_admaif_cget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
-	int value = ucontrol->value.integer.value[0];
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
 
-	if (strstr(kcontrol->id.name, "Playback Mono To Stereo"))
-		admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg] = value;
-	else if (strstr(kcontrol->id.name, "Capture Mono To Stereo"))
-		admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg] = value;
-	else if (strstr(kcontrol->id.name, "Playback Stereo To Mono"))
-		admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg] = value;
-	else if (strstr(kcontrol->id.name, "Capture Stereo To Mono"))
-		admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg] = value;
+	ucontrol->value.enumerated.item[0] =
+		admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg];
 
 	return 0;
 }
 
+static int tegra210_admaif_cput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg])
+		return 0;
+
+	admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
 static int tegra_admaif_dai_probe(struct snd_soc_dai *dai)
 {
 	struct tegra_admaif *admaif = snd_soc_dai_get_drvdata(dai);
@@ -559,17 +635,21 @@ static const char * const tegra_admaif_mono_conv_text[] = {
 }
 
 #define TEGRA_ADMAIF_CIF_CTRL(reg)					       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Mono To Stereo", reg - 1,\
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Mono To Stereo", reg - 1,     \
+			tegra210_admaif_pget_mono_to_stereo,		       \
+			tegra210_admaif_pput_mono_to_stereo,		       \
 			tegra_admaif_mono_conv_text),			       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Stereo To Mono", reg - 1,\
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Stereo To Mono", reg - 1,     \
+			tegra210_admaif_pget_stereo_to_mono,		       \
+			tegra210_admaif_pput_stereo_to_mono,		       \
 			tegra_admaif_stereo_conv_text),			       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Mono To Stereo", reg - 1, \
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Mono To Stereo", reg - 1,      \
+			tegra210_admaif_cget_mono_to_stereo,		       \
+			tegra210_admaif_cput_mono_to_stereo,		       \
 			tegra_admaif_mono_conv_text),			       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Stereo To Mono", reg - 1, \
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Stereo To Mono", reg - 1,      \
+			tegra210_admaif_cget_stereo_to_mono,		       \
+			tegra210_admaif_cput_stereo_to_mono,		       \
 			tegra_admaif_stereo_conv_text)
 
 static struct snd_kcontrol_new tegra210_admaif_controls[] = {
diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c
index 66287a7c9865d..1b2f7cb8c6adc 100644
--- a/sound/soc/tegra/tegra210_ahub.c
+++ b/sound/soc/tegra/tegra210_ahub.c
@@ -62,6 +62,7 @@ static int tegra_ahub_put_value_enum(struct snd_kcontrol *kctl,
 	unsigned int *item = uctl->value.enumerated.item;
 	unsigned int value = e->values[item[0]];
 	unsigned int i, bit_pos, reg_idx = 0, reg_val = 0;
+	int change = 0;
 
 	if (item[0] >= e->items)
 		return -EINVAL;
@@ -86,12 +87,14 @@ static int tegra_ahub_put_value_enum(struct snd_kcontrol *kctl,
 
 		/* Update widget power if state has changed */
 		if (snd_soc_component_test_bits(cmpnt, update[i].reg,
-						update[i].mask, update[i].val))
-			snd_soc_dapm_mux_update_power(dapm, kctl, item[0], e,
-						      &update[i]);
+						update[i].mask,
+						update[i].val))
+			change |= snd_soc_dapm_mux_update_power(dapm, kctl,
+								item[0], e,
+								&update[i]);
 	}
 
-	return 0;
+	return change;
 }
 
 static struct snd_soc_dai_driver tegra210_ahub_dais[] = {
diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c
index b096478cd2ef0..db95794530f46 100644
--- a/sound/soc/tegra/tegra210_dmic.c
+++ b/sound/soc/tegra/tegra210_dmic.c
@@ -156,51 +156,162 @@ static int tegra210_dmic_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int tegra210_dmic_get_control(struct snd_kcontrol *kcontrol,
+static int tegra210_dmic_get_boost_gain(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.integer.value[0] = dmic->boost_gain;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_boost_gain(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == dmic->boost_gain)
+		return 0;
+
+	dmic->boost_gain = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_ch_select(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->ch_select;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_ch_select(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->ch_select)
+		return 0;
+
+	dmic->ch_select = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->mono_to_stereo;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->mono_to_stereo)
+		return 0;
+
+	dmic->mono_to_stereo = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->stereo_to_mono;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->stereo_to_mono)
+		return 0;
+
+	dmic->stereo_to_mono = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_osr_val(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
 
-	if (strstr(kcontrol->id.name, "Boost Gain Volume"))
-		ucontrol->value.integer.value[0] = dmic->boost_gain;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		ucontrol->value.integer.value[0] = dmic->ch_select;
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		ucontrol->value.integer.value[0] = dmic->mono_to_stereo;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		ucontrol->value.integer.value[0] = dmic->stereo_to_mono;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		ucontrol->value.integer.value[0] = dmic->osr_val;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		ucontrol->value.integer.value[0] = dmic->lrsel;
+	ucontrol->value.enumerated.item[0] = dmic->osr_val;
 
 	return 0;
 }
 
-static int tegra210_dmic_put_control(struct snd_kcontrol *kcontrol,
+static int tegra210_dmic_put_osr_val(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
-	int value = ucontrol->value.integer.value[0];
+	unsigned int value = ucontrol->value.enumerated.item[0];
 
-	if (strstr(kcontrol->id.name, "Boost Gain Volume"))
-		dmic->boost_gain = value;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		dmic->ch_select = ucontrol->value.integer.value[0];
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		dmic->mono_to_stereo = value;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		dmic->stereo_to_mono = value;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		dmic->osr_val = value;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		dmic->lrsel = value;
+	if (value == dmic->osr_val)
+		return 0;
+
+	dmic->osr_val = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->lrsel;
 
 	return 0;
 }
 
+static int tegra210_dmic_put_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->lrsel)
+		return 0;
+
+	dmic->lrsel = value;
+
+	return 1;
+}
+
 static const struct snd_soc_dai_ops tegra210_dmic_dai_ops = {
 	.hw_params	= tegra210_dmic_hw_params,
 };
@@ -287,19 +398,22 @@ static const struct soc_enum tegra210_dmic_lrsel_enum =
 
 static const struct snd_kcontrol_new tegra210_dmic_controls[] = {
 	SOC_SINGLE_EXT("Boost Gain Volume", 0, 0, MAX_BOOST_GAIN, 0,
-		       tegra210_dmic_get_control, tegra210_dmic_put_control),
+		       tegra210_dmic_get_boost_gain,
+		       tegra210_dmic_put_boost_gain),
 	SOC_ENUM_EXT("Channel Select", tegra210_dmic_ch_enum,
-		     tegra210_dmic_get_control, tegra210_dmic_put_control),
+		     tegra210_dmic_get_ch_select, tegra210_dmic_put_ch_select),
 	SOC_ENUM_EXT("Mono To Stereo",
-		     tegra210_dmic_mono_conv_enum, tegra210_dmic_get_control,
-		     tegra210_dmic_put_control),
+		     tegra210_dmic_mono_conv_enum,
+		     tegra210_dmic_get_mono_to_stereo,
+		     tegra210_dmic_put_mono_to_stereo),
 	SOC_ENUM_EXT("Stereo To Mono",
-		     tegra210_dmic_stereo_conv_enum, tegra210_dmic_get_control,
-		     tegra210_dmic_put_control),
+		     tegra210_dmic_stereo_conv_enum,
+		     tegra210_dmic_get_stereo_to_mono,
+		     tegra210_dmic_put_stereo_to_mono),
 	SOC_ENUM_EXT("OSR Value", tegra210_dmic_osr_enum,
-		     tegra210_dmic_get_control, tegra210_dmic_put_control),
+		     tegra210_dmic_get_osr_val, tegra210_dmic_put_osr_val),
 	SOC_ENUM_EXT("LR Polarity Select", tegra210_dmic_lrsel_enum,
-		     tegra210_dmic_get_control, tegra210_dmic_put_control),
+		     tegra210_dmic_get_pol_sel, tegra210_dmic_put_pol_sel),
 };
 
 static const struct snd_soc_component_driver tegra210_dmic_compnt = {
diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c
index 45f31ccb49d89..9552bbb939dd1 100644
--- a/sound/soc/tegra/tegra210_i2s.c
+++ b/sound/soc/tegra/tegra210_i2s.c
@@ -302,85 +302,235 @@ static int tegra210_i2s_set_tdm_slot(struct snd_soc_dai *dai,
 	return 0;
 }
 
-static int tegra210_i2s_set_dai_bclk_ratio(struct snd_soc_dai *dai,
-					   unsigned int ratio)
+static int tegra210_i2s_get_loopback(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
 {
-	struct tegra210_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
 
-	i2s->bclk_ratio = ratio;
+	ucontrol->value.integer.value[0] = i2s->loopback;
 
 	return 0;
 }
 
-static int tegra210_i2s_get_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_i2s_put_loopback(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == i2s->loopback)
+		return 0;
+
+	i2s->loopback = value;
+
+	regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL, I2S_CTRL_LPBK_MASK,
+			   i2s->loopback << I2S_CTRL_LPBK_SHIFT);
+
+	return 1;
+}
+
+static int tegra210_i2s_get_fsync_width(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
-	long *uctl_val = &ucontrol->value.integer.value[0];
-
-	if (strstr(kcontrol->id.name, "Loopback"))
-		*uctl_val = i2s->loopback;
-	else if (strstr(kcontrol->id.name, "FSYNC Width"))
-		*uctl_val = i2s->fsync_width;
-	else if (strstr(kcontrol->id.name, "Capture Stereo To Mono"))
-		*uctl_val = i2s->stereo_to_mono[I2S_TX_PATH];
-	else if (strstr(kcontrol->id.name, "Capture Mono To Stereo"))
-		*uctl_val = i2s->mono_to_stereo[I2S_TX_PATH];
-	else if (strstr(kcontrol->id.name, "Playback Stereo To Mono"))
-		*uctl_val = i2s->stereo_to_mono[I2S_RX_PATH];
-	else if (strstr(kcontrol->id.name, "Playback Mono To Stereo"))
-		*uctl_val = i2s->mono_to_stereo[I2S_RX_PATH];
-	else if (strstr(kcontrol->id.name, "Playback FIFO Threshold"))
-		*uctl_val = i2s->rx_fifo_th;
-	else if (strstr(kcontrol->id.name, "BCLK Ratio"))
-		*uctl_val = i2s->bclk_ratio;
+
+	ucontrol->value.integer.value[0] = i2s->fsync_width;
 
 	return 0;
 }
 
-static int tegra210_i2s_put_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_i2s_put_fsync_width(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
 	int value = ucontrol->value.integer.value[0];
 
-	if (strstr(kcontrol->id.name, "Loopback")) {
-		i2s->loopback = value;
+	if (value == i2s->fsync_width)
+		return 0;
 
-		regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL,
-				   I2S_CTRL_LPBK_MASK,
-				   i2s->loopback << I2S_CTRL_LPBK_SHIFT);
+	i2s->fsync_width = value;
 
-	} else if (strstr(kcontrol->id.name, "FSYNC Width")) {
-		/*
-		 * Frame sync width is used only for FSYNC modes and not
-		 * applicable for LRCK modes. Reset value for this field is "0",
-		 * which means the width is one bit clock wide.
-		 * The width requirement may depend on the codec and in such
-		 * cases mixer control is used to update custom values. A value
-		 * of "N" here means, width is "N + 1" bit clock wide.
-		 */
-		i2s->fsync_width = value;
-
-		regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL,
-				   I2S_CTRL_FSYNC_WIDTH_MASK,
-				   i2s->fsync_width << I2S_FSYNC_WIDTH_SHIFT);
-
-	} else if (strstr(kcontrol->id.name, "Capture Stereo To Mono")) {
-		i2s->stereo_to_mono[I2S_TX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Capture Mono To Stereo")) {
-		i2s->mono_to_stereo[I2S_TX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Playback Stereo To Mono")) {
-		i2s->stereo_to_mono[I2S_RX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Playback Mono To Stereo")) {
-		i2s->mono_to_stereo[I2S_RX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Playback FIFO Threshold")) {
-		i2s->rx_fifo_th = value;
-	} else if (strstr(kcontrol->id.name, "BCLK Ratio")) {
-		i2s->bclk_ratio = value;
-	}
+	/*
+	 * Frame sync width is used only for FSYNC modes and not
+	 * applicable for LRCK modes. Reset value for this field is "0",
+	 * which means the width is one bit clock wide.
+	 * The width requirement may depend on the codec and in such
+	 * cases mixer control is used to update custom values. A value
+	 * of "N" here means, width is "N + 1" bit clock wide.
+	 */
+	regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL,
+			   I2S_CTRL_FSYNC_WIDTH_MASK,
+			   i2s->fsync_width << I2S_FSYNC_WIDTH_SHIFT);
+
+	return 1;
+}
+
+static int tegra210_i2s_cget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->stereo_to_mono[I2S_TX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_cput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->stereo_to_mono[I2S_TX_PATH])
+		return 0;
+
+	i2s->stereo_to_mono[I2S_TX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_cget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->mono_to_stereo[I2S_TX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_cput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->mono_to_stereo[I2S_TX_PATH])
+		return 0;
+
+	i2s->mono_to_stereo[I2S_TX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_pget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->stereo_to_mono[I2S_RX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_pput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->stereo_to_mono[I2S_RX_PATH])
+		return 0;
+
+	i2s->stereo_to_mono[I2S_RX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_pget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->mono_to_stereo[I2S_RX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_pput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->mono_to_stereo[I2S_RX_PATH])
+		return 0;
+
+	i2s->mono_to_stereo[I2S_RX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_pget_fifo_th(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.integer.value[0] = i2s->rx_fifo_th;
+
+	return 0;
+}
+
+static int tegra210_i2s_pput_fifo_th(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == i2s->rx_fifo_th)
+		return 0;
+
+	i2s->rx_fifo_th = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_get_bclk_ratio(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.integer.value[0] = i2s->bclk_ratio;
+
+	return 0;
+}
+
+static int tegra210_i2s_put_bclk_ratio(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == i2s->bclk_ratio)
+		return 0;
+
+	i2s->bclk_ratio = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_set_dai_bclk_ratio(struct snd_soc_dai *dai,
+					   unsigned int ratio)
+{
+	struct tegra210_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+
+	i2s->bclk_ratio = ratio;
 
 	return 0;
 }
@@ -598,22 +748,28 @@ static const struct soc_enum tegra210_i2s_stereo_conv_enum =
 			tegra210_i2s_stereo_conv_text);
 
 static const struct snd_kcontrol_new tegra210_i2s_controls[] = {
-	SOC_SINGLE_EXT("Loopback", 0, 0, 1, 0, tegra210_i2s_get_control,
-		       tegra210_i2s_put_control),
-	SOC_SINGLE_EXT("FSYNC Width", 0, 0, 255, 0, tegra210_i2s_get_control,
-		       tegra210_i2s_put_control),
+	SOC_SINGLE_EXT("Loopback", 0, 0, 1, 0, tegra210_i2s_get_loopback,
+		       tegra210_i2s_put_loopback),
+	SOC_SINGLE_EXT("FSYNC Width", 0, 0, 255, 0,
+		       tegra210_i2s_get_fsync_width,
+		       tegra210_i2s_put_fsync_width),
 	SOC_ENUM_EXT("Capture Stereo To Mono", tegra210_i2s_stereo_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_cget_stereo_to_mono,
+		     tegra210_i2s_cput_stereo_to_mono),
 	SOC_ENUM_EXT("Capture Mono To Stereo", tegra210_i2s_mono_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_cget_mono_to_stereo,
+		     tegra210_i2s_cput_mono_to_stereo),
 	SOC_ENUM_EXT("Playback Stereo To Mono", tegra210_i2s_stereo_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_pget_mono_to_stereo,
+		     tegra210_i2s_pput_mono_to_stereo),
 	SOC_ENUM_EXT("Playback Mono To Stereo", tegra210_i2s_mono_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_pget_stereo_to_mono,
+		     tegra210_i2s_pput_stereo_to_mono),
 	SOC_SINGLE_EXT("Playback FIFO Threshold", 0, 0, I2S_RX_FIFO_DEPTH - 1,
-		       0, tegra210_i2s_get_control, tegra210_i2s_put_control),
-	SOC_SINGLE_EXT("BCLK Ratio", 0, 0, INT_MAX, 0, tegra210_i2s_get_control,
-		       tegra210_i2s_put_control),
+		       0, tegra210_i2s_pget_fifo_th, tegra210_i2s_pput_fifo_th),
+	SOC_SINGLE_EXT("BCLK Ratio", 0, 0, INT_MAX, 0,
+		       tegra210_i2s_get_bclk_ratio,
+		       tegra210_i2s_put_bclk_ratio),
 };
 
 static const struct snd_soc_dapm_widget tegra210_i2s_widgets[] = {
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 860faaf249ea6..87f042d06ce08 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -74,8 +74,9 @@ struct snd_usb_endpoint {
 
 	atomic_t state;		/* running state */
 
-	void (*prepare_data_urb) (struct snd_usb_substream *subs,
-				  struct urb *urb);
+	int (*prepare_data_urb) (struct snd_usb_substream *subs,
+				 struct urb *urb,
+				 bool in_stream_lock);
 	void (*retire_data_urb) (struct snd_usb_substream *subs,
 				 struct urb *urb);
 
@@ -94,7 +95,6 @@ struct snd_usb_endpoint {
 	struct list_head ready_playback_urbs; /* playback URB FIFO for implicit fb */
 
 	unsigned int nurbs;		/* # urbs */
-	unsigned int nominal_queue_size; /* total buffer sizes in URBs */
 	unsigned long active_mask;	/* bitmask of active urbs */
 	unsigned long unlink_mask;	/* bitmask of unlinked urbs */
 	atomic_t submitted_urbs;	/* currently submitted urbs */
@@ -126,6 +126,7 @@ struct snd_usb_endpoint {
 	int skip_packets;		/* quirks for devices to ignore the first n packets
 					   in a stream */
 	bool implicit_fb_sync;		/* syncs with implicit feedback */
+	bool lowlatency_playback;	/* low-latency playback mode */
 	bool need_setup;		/* (re-)need for configure? */
 
 	/* for hw constraints */
@@ -137,6 +138,7 @@ struct snd_usb_endpoint {
 	unsigned int cur_period_frames;
 	unsigned int cur_period_bytes;
 	unsigned int cur_buffer_periods;
+	unsigned char cur_clock;
 
 	spinlock_t lock;
 	struct list_head list;
@@ -189,7 +191,7 @@ struct snd_usb_substream {
 	} dsd_dop;
 
 	bool trigger_tstamp_pending_update; /* trigger timestamp being updated from initial estimate */
-	bool early_playback_start;	/* early start needed for playback? */
+	bool lowlatency_playback;	/* low-latency playback mode */
 	struct media_ctl *media_ctl;
 };
 
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index ba2d7e6884207..743b8287cfcdd 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -148,18 +148,23 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep)
  * This won't be used for implicit feedback which takes the packet size
  * returned from the sync source
  */
-static int slave_next_packet_size(struct snd_usb_endpoint *ep)
+static int slave_next_packet_size(struct snd_usb_endpoint *ep,
+				  unsigned int avail)
 {
 	unsigned long flags;
+	unsigned int phase;
 	int ret;
 
 	if (ep->fill_max)
 		return ep->maxframesize;
 
 	spin_lock_irqsave(&ep->lock, flags);
-	ep->phase = (ep->phase & 0xffff)
-		+ (ep->freqm << ep->datainterval);
-	ret = min(ep->phase >> 16, ep->maxframesize);
+	phase = (ep->phase & 0xffff) + (ep->freqm << ep->datainterval);
+	ret = min(phase >> 16, ep->maxframesize);
+	if (avail && ret >= avail)
+		ret = -EAGAIN;
+	else
+		ep->phase = phase;
 	spin_unlock_irqrestore(&ep->lock, flags);
 
 	return ret;
@@ -169,20 +174,25 @@ static int slave_next_packet_size(struct snd_usb_endpoint *ep)
  * Return the number of samples to be sent in the next packet
  * for adaptive and synchronous endpoints
  */
-static int next_packet_size(struct snd_usb_endpoint *ep)
+static int next_packet_size(struct snd_usb_endpoint *ep, unsigned int avail)
 {
+	unsigned int sample_accum;
 	int ret;
 
 	if (ep->fill_max)
 		return ep->maxframesize;
 
-	ep->sample_accum += ep->sample_rem;
-	if (ep->sample_accum >= ep->pps) {
-		ep->sample_accum -= ep->pps;
+	sample_accum = ep->sample_accum + ep->sample_rem;
+	if (sample_accum >= ep->pps) {
+		sample_accum -= ep->pps;
 		ret = ep->packsize[1];
 	} else {
 		ret = ep->packsize[0];
 	}
+	if (avail && ret >= avail)
+		ret = -EAGAIN;
+	else
+		ep->sample_accum = sample_accum;
 
 	return ret;
 }
@@ -190,16 +200,27 @@ static int next_packet_size(struct snd_usb_endpoint *ep)
 /*
  * snd_usb_endpoint_next_packet_size: Return the number of samples to be sent
  * in the next packet
+ *
+ * If the size is equal or exceeds @avail, don't proceed but return -EAGAIN
+ * Exception: @avail = 0 for skipping the check.
  */
 int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
-				      struct snd_urb_ctx *ctx, int idx)
+				      struct snd_urb_ctx *ctx, int idx,
+				      unsigned int avail)
 {
-	if (ctx->packet_size[idx])
-		return ctx->packet_size[idx];
-	else if (ep->sync_source)
-		return slave_next_packet_size(ep);
+	unsigned int packet;
+
+	packet = ctx->packet_size[idx];
+	if (packet) {
+		if (avail && packet >= avail)
+			return -EAGAIN;
+		return packet;
+	}
+
+	if (ep->sync_source)
+		return slave_next_packet_size(ep, avail);
 	else
-		return next_packet_size(ep);
+		return next_packet_size(ep, avail);
 }
 
 static void call_retire_callback(struct snd_usb_endpoint *ep,
@@ -263,7 +284,7 @@ static void prepare_silent_urb(struct snd_usb_endpoint *ep,
 		unsigned int length;
 		int counts;
 
-		counts = snd_usb_endpoint_next_packet_size(ep, ctx, i);
+		counts = snd_usb_endpoint_next_packet_size(ep, ctx, i, 0);
 		length = counts * ep->stride; /* number of silent bytes */
 		offset = offs * ep->stride + extra * i;
 		urb->iso_frame_desc[i].offset = offset;
@@ -286,8 +307,9 @@ static void prepare_silent_urb(struct snd_usb_endpoint *ep,
 /*
  * Prepare a PLAYBACK urb for submission to the bus.
  */
-static void prepare_outbound_urb(struct snd_usb_endpoint *ep,
-				 struct snd_urb_ctx *ctx)
+static int prepare_outbound_urb(struct snd_usb_endpoint *ep,
+				struct snd_urb_ctx *ctx,
+				bool in_stream_lock)
 {
 	struct urb *urb = ctx->urb;
 	unsigned char *cp = urb->transfer_buffer;
@@ -299,9 +321,9 @@ static void prepare_outbound_urb(struct snd_usb_endpoint *ep,
 	case SND_USB_ENDPOINT_TYPE_DATA:
 		data_subs = READ_ONCE(ep->data_subs);
 		if (data_subs && ep->prepare_data_urb)
-			ep->prepare_data_urb(data_subs, urb);
-		else /* no data provider, so send silence */
-			prepare_silent_urb(ep, ctx);
+			return ep->prepare_data_urb(data_subs, urb, in_stream_lock);
+		/* no data provider, so send silence */
+		prepare_silent_urb(ep, ctx);
 		break;
 
 	case SND_USB_ENDPOINT_TYPE_SYNC:
@@ -330,13 +352,14 @@ static void prepare_outbound_urb(struct snd_usb_endpoint *ep,
 
 		break;
 	}
+	return 0;
 }
 
 /*
  * Prepare a CAPTURE or SYNC urb for submission to the bus.
  */
-static inline void prepare_inbound_urb(struct snd_usb_endpoint *ep,
-				       struct snd_urb_ctx *urb_ctx)
+static int prepare_inbound_urb(struct snd_usb_endpoint *ep,
+			       struct snd_urb_ctx *urb_ctx)
 {
 	int i, offs;
 	struct urb *urb = urb_ctx->urb;
@@ -361,6 +384,7 @@ static inline void prepare_inbound_urb(struct snd_usb_endpoint *ep,
 		urb->iso_frame_desc[0].offset = 0;
 		break;
 	}
+	return 0;
 }
 
 /* notify an error as XRUN to the assigned PCM data substream */
@@ -396,6 +420,16 @@ next_packet_fifo_dequeue(struct snd_usb_endpoint *ep)
 	return p;
 }
 
+static void push_back_to_ready_list(struct snd_usb_endpoint *ep,
+				    struct snd_urb_ctx *ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ep->lock, flags);
+	list_add_tail(&ctx->ready_list, &ep->ready_playback_urbs);
+	spin_unlock_irqrestore(&ep->lock, flags);
+}
+
 /*
  * Send output urbs that have been prepared previously. URBs are dequeued
  * from ep->ready_playback_urbs and in case there aren't any available
@@ -406,12 +440,14 @@ next_packet_fifo_dequeue(struct snd_usb_endpoint *ep)
  * is that host controllers don't guarantee the order in which they return
  * inbound and outbound packets to their submitters.
  *
- * This function is only used for implicit feedback endpoints. For endpoints
- * driven by dedicated sync endpoints, URBs are immediately re-submitted
- * from their completion handler.
+ * This function is used both for implicit feedback endpoints and in low-
+ * latency playback mode.
  */
-static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
+void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep,
+				       bool in_stream_lock)
 {
+	bool implicit_fb = snd_usb_endpoint_implicit_feedback_sink(ep);
+
 	while (ep_state_running(ep)) {
 
 		unsigned long flags;
@@ -420,14 +456,14 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 		int err, i;
 
 		spin_lock_irqsave(&ep->lock, flags);
-		if (ep->next_packet_queued > 0 &&
+		if ((!implicit_fb || ep->next_packet_queued > 0) &&
 		    !list_empty(&ep->ready_playback_urbs)) {
 			/* take URB out of FIFO */
 			ctx = list_first_entry(&ep->ready_playback_urbs,
 					       struct snd_urb_ctx, ready_list);
 			list_del_init(&ctx->ready_list);
-
-			packet = next_packet_fifo_dequeue(ep);
+			if (implicit_fb)
+				packet = next_packet_fifo_dequeue(ep);
 		}
 		spin_unlock_irqrestore(&ep->lock, flags);
 
@@ -435,11 +471,24 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 			return;
 
 		/* copy over the length information */
-		for (i = 0; i < packet->packets; i++)
-			ctx->packet_size[i] = packet->packet_size[i];
+		if (implicit_fb) {
+			for (i = 0; i < packet->packets; i++)
+				ctx->packet_size[i] = packet->packet_size[i];
+		}
 
 		/* call the data handler to fill in playback data */
-		prepare_outbound_urb(ep, ctx);
+		err = prepare_outbound_urb(ep, ctx, in_stream_lock);
+		/* can be stopped during prepare callback */
+		if (unlikely(!ep_state_running(ep)))
+			break;
+		if (err < 0) {
+			/* push back to ready list again for -EAGAIN */
+			if (err == -EAGAIN)
+				push_back_to_ready_list(ep, ctx);
+			else
+				notify_xrun(ep);
+			return;
+		}
 
 		err = usb_submit_urb(ctx->urb, GFP_ATOMIC);
 		if (err < 0) {
@@ -462,7 +511,6 @@ static void snd_complete_urb(struct urb *urb)
 {
 	struct snd_urb_ctx *ctx = urb->context;
 	struct snd_usb_endpoint *ep = ctx->ep;
-	unsigned long flags;
 	int err;
 
 	if (unlikely(urb->status == -ENOENT ||		/* unlinked */
@@ -483,17 +531,20 @@ static void snd_complete_urb(struct urb *urb)
 		if (unlikely(!ep_state_running(ep)))
 			goto exit_clear;
 
-		if (snd_usb_endpoint_implicit_feedback_sink(ep)) {
-			spin_lock_irqsave(&ep->lock, flags);
-			list_add_tail(&ctx->ready_list, &ep->ready_playback_urbs);
+		/* in low-latency and implicit-feedback modes, push back the
+		 * URB to ready list at first, then process as much as possible
+		 */
+		if (ep->lowlatency_playback ||
+		     snd_usb_endpoint_implicit_feedback_sink(ep)) {
+			push_back_to_ready_list(ep, ctx);
 			clear_bit(ctx->index, &ep->active_mask);
-			spin_unlock_irqrestore(&ep->lock, flags);
-			queue_pending_output_urbs(ep);
+			snd_usb_queue_pending_output_urbs(ep, false);
 			atomic_dec(&ep->submitted_urbs); /* decrement at last */
 			return;
 		}
 
-		prepare_outbound_urb(ep, ctx);
+		/* in non-lowlatency mode, no error handling for prepare */
+		prepare_outbound_urb(ep, ctx, false);
 		/* can be stopped during prepare callback */
 		if (unlikely(!ep_state_running(ep)))
 			goto exit_clear;
@@ -726,6 +777,7 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip,
 		ep->cur_period_frames = params_period_size(params);
 		ep->cur_period_bytes = ep->cur_period_frames * ep->cur_frame_bytes;
 		ep->cur_buffer_periods = params_periods(params);
+		ep->cur_clock = fp->clock;
 
 		if (ep->type == SND_USB_ENDPOINT_TYPE_SYNC)
 			endpoint_set_syncinterval(chip, ep);
@@ -785,14 +837,19 @@ void snd_usb_endpoint_set_sync(struct snd_usb_audio *chip,
  * Pass NULL to deactivate each callback.
  */
 void snd_usb_endpoint_set_callback(struct snd_usb_endpoint *ep,
-				   void (*prepare)(struct snd_usb_substream *subs,
-						   struct urb *urb),
+				   int (*prepare)(struct snd_usb_substream *subs,
+						  struct urb *urb,
+						  bool in_stream_lock),
 				   void (*retire)(struct snd_usb_substream *subs,
 						  struct urb *urb),
 				   struct snd_usb_substream *data_subs)
 {
 	ep->prepare_data_urb = prepare;
 	ep->retire_data_urb = retire;
+	if (data_subs)
+		ep->lowlatency_playback = data_subs->lowlatency_playback;
+	else
+		ep->lowlatency_playback = false;
 	WRITE_ONCE(ep->data_subs, data_subs);
 }
 
@@ -837,6 +894,7 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip,
 		ep->altsetting = 0;
 		ep->cur_audiofmt = NULL;
 		ep->cur_rate = 0;
+		ep->cur_clock = 0;
 		ep->iface_ref = NULL;
 		usb_audio_dbg(chip, "EP 0x%x closed\n", ep->ep_num);
 	}
@@ -897,9 +955,10 @@ void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep)
  *
  * This function moves the EP to STOPPING state if it's being RUNNING.
  */
-static int stop_urbs(struct snd_usb_endpoint *ep, bool force)
+static int stop_urbs(struct snd_usb_endpoint *ep, bool force, bool keep_pending)
 {
 	unsigned int i;
+	unsigned long flags;
 
 	if (!force && atomic_read(&ep->running))
 		return -EBUSY;
@@ -907,9 +966,14 @@ static int stop_urbs(struct snd_usb_endpoint *ep, bool force)
 	if (!ep_state_update(ep, EP_STATE_RUNNING, EP_STATE_STOPPING))
 		return 0;
 
+	spin_lock_irqsave(&ep->lock, flags);
 	INIT_LIST_HEAD(&ep->ready_playback_urbs);
 	ep->next_packet_head = 0;
 	ep->next_packet_queued = 0;
+	spin_unlock_irqrestore(&ep->lock, flags);
+
+	if (keep_pending)
+		return 0;
 
 	for (i = 0; i < ep->nurbs; i++) {
 		if (test_bit(i, &ep->active_mask)) {
@@ -934,7 +998,7 @@ static int release_urbs(struct snd_usb_endpoint *ep, bool force)
 	snd_usb_endpoint_set_callback(ep, NULL, NULL, NULL);
 
 	/* stop and unlink urbs */
-	err = stop_urbs(ep, force);
+	err = stop_urbs(ep, force, false);
 	if (err)
 		return err;
 
@@ -1136,10 +1200,6 @@ static int data_ep_set_params(struct snd_usb_endpoint *ep)
 		INIT_LIST_HEAD(&u->ready_list);
 	}
 
-	/* total buffer bytes of all URBs plus the next queue;
-	 * referred in pcm.c
-	 */
-	ep->nominal_queue_size = maxsize * urb_packs * (ep->nurbs + 1);
 	return 0;
 
 out_of_memory:
@@ -1344,6 +1404,25 @@ unlock:
 	return err;
 }
 
+/* get the current rate set to the given clock by any endpoint */
+int snd_usb_endpoint_get_clock_rate(struct snd_usb_audio *chip, int clock)
+{
+	struct snd_usb_endpoint *ep;
+	int rate = 0;
+
+	if (!clock)
+		return 0;
+	mutex_lock(&chip->mutex);
+	list_for_each_entry(ep, &chip->ep_list, list) {
+		if (ep->cur_clock == clock && ep->cur_rate) {
+			rate = ep->cur_rate;
+			break;
+		}
+	}
+	mutex_unlock(&chip->mutex);
+	return rate;
+}
+
 /**
  * snd_usb_endpoint_start: start an snd_usb_endpoint
  *
@@ -1359,6 +1438,7 @@ unlock:
  */
 int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 {
+	bool is_playback = usb_pipeout(ep->pipe);
 	int err;
 	unsigned int i;
 
@@ -1395,13 +1475,9 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 
 	if (snd_usb_endpoint_implicit_feedback_sink(ep) &&
 	    !(ep->chip->quirk_flags & QUIRK_FLAG_PLAYBACK_FIRST)) {
-		for (i = 0; i < ep->nurbs; i++) {
-			struct snd_urb_ctx *ctx = ep->urb + i;
-			list_add_tail(&ctx->ready_list, &ep->ready_playback_urbs);
-		}
-
 		usb_audio_dbg(ep->chip, "No URB submission due to implicit fb sync\n");
-		return 0;
+		i = 0;
+		goto fill_rest;
 	}
 
 	for (i = 0; i < ep->nurbs; i++) {
@@ -1410,10 +1486,18 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 		if (snd_BUG_ON(!urb))
 			goto __error;
 
-		if (usb_pipeout(ep->pipe)) {
-			prepare_outbound_urb(ep, urb->context);
-		} else {
-			prepare_inbound_urb(ep, urb->context);
+		if (is_playback)
+			err = prepare_outbound_urb(ep, urb->context, true);
+		else
+			err = prepare_inbound_urb(ep, urb->context);
+		if (err < 0) {
+			/* stop filling at applptr */
+			if (err == -EAGAIN)
+				break;
+			usb_audio_dbg(ep->chip,
+				      "EP 0x%x: failed to prepare urb: %d\n",
+				      ep->ep_num, err);
+			goto __error;
 		}
 
 		err = usb_submit_urb(urb, GFP_ATOMIC);
@@ -1427,12 +1511,26 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 		atomic_inc(&ep->submitted_urbs);
 	}
 
+	if (!i) {
+		usb_audio_dbg(ep->chip, "XRUN at starting EP 0x%x\n",
+			      ep->ep_num);
+		goto __error;
+	}
+
 	usb_audio_dbg(ep->chip, "%d URBs submitted for EP 0x%x\n",
-		      ep->nurbs, ep->ep_num);
+		      i, ep->ep_num);
+
+ fill_rest:
+	/* put the remaining URBs to ready list */
+	if (is_playback) {
+		for (; i < ep->nurbs; i++)
+			push_back_to_ready_list(ep, ep->urb + i);
+	}
+
 	return 0;
 
 __error:
-	snd_usb_endpoint_stop(ep);
+	snd_usb_endpoint_stop(ep, false);
 	return -EPIPE;
 }
 
@@ -1440,6 +1538,7 @@ __error:
  * snd_usb_endpoint_stop: stop an snd_usb_endpoint
  *
  * @ep: the endpoint to stop (may be NULL)
+ * @keep_pending: keep in-flight URBs
  *
  * A call to this function will decrement the running count of the endpoint.
  * In case the last user has requested the endpoint stop, the URBs will
@@ -1450,7 +1549,7 @@ __error:
  * The caller needs to synchronize the pending stop operation via
  * snd_usb_endpoint_sync_pending_stop().
  */
-void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep)
+void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep, bool keep_pending)
 {
 	if (!ep)
 		return;
@@ -1465,7 +1564,7 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep)
 	if (!atomic_dec_return(&ep->running)) {
 		if (ep->sync_source)
 			WRITE_ONCE(ep->sync_source->sync_sink, NULL);
-		stop_urbs(ep, false);
+		stop_urbs(ep, false, keep_pending);
 	}
 }
 
@@ -1580,7 +1679,7 @@ static void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep,
 		}
 
 		spin_unlock_irqrestore(&ep->lock, flags);
-		queue_pending_output_urbs(ep);
+		snd_usb_queue_pending_output_urbs(ep, false);
 
 		return;
 	}
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index a668f675b52b0..6a9af04cf175a 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -19,6 +19,7 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip,
 			    struct snd_usb_endpoint *ep);
 int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
 			       struct snd_usb_endpoint *ep);
+int snd_usb_endpoint_get_clock_rate(struct snd_usb_audio *chip, int clock);
 
 bool snd_usb_endpoint_compatible(struct snd_usb_audio *chip,
 				 struct snd_usb_endpoint *ep,
@@ -29,14 +30,15 @@ void snd_usb_endpoint_set_sync(struct snd_usb_audio *chip,
 			       struct snd_usb_endpoint *data_ep,
 			       struct snd_usb_endpoint *sync_ep);
 void snd_usb_endpoint_set_callback(struct snd_usb_endpoint *ep,
-				   void (*prepare)(struct snd_usb_substream *subs,
-						   struct urb *urb),
+				   int (*prepare)(struct snd_usb_substream *subs,
+						  struct urb *urb,
+						  bool in_stream_lock),
 				   void (*retire)(struct snd_usb_substream *subs,
 						  struct urb *urb),
 				   struct snd_usb_substream *data_subs);
 
 int snd_usb_endpoint_start(struct snd_usb_endpoint *ep);
-void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep);
+void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep, bool keep_pending);
 void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
@@ -45,6 +47,9 @@ void snd_usb_endpoint_free_all(struct snd_usb_audio *chip);
 
 int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
 int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
-				      struct snd_urb_ctx *ctx, int idx);
+				      struct snd_urb_ctx *ctx, int idx,
+				      unsigned int avail);
+void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep,
+				       bool in_stream_lock);
 
 #endif /* __USBAUDIO_ENDPOINT_H */
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 5dc9266180e37..2e51fb031ae01 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -219,16 +219,16 @@ int snd_usb_init_pitch(struct snd_usb_audio *chip,
 	return 0;
 }
 
-static bool stop_endpoints(struct snd_usb_substream *subs)
+static bool stop_endpoints(struct snd_usb_substream *subs, bool keep_pending)
 {
 	bool stopped = 0;
 
 	if (test_and_clear_bit(SUBSTREAM_FLAG_SYNC_EP_STARTED, &subs->flags)) {
-		snd_usb_endpoint_stop(subs->sync_endpoint);
+		snd_usb_endpoint_stop(subs->sync_endpoint, keep_pending);
 		stopped = true;
 	}
 	if (test_and_clear_bit(SUBSTREAM_FLAG_DATA_EP_STARTED, &subs->flags)) {
-		snd_usb_endpoint_stop(subs->data_endpoint);
+		snd_usb_endpoint_stop(subs->data_endpoint, keep_pending);
 		stopped = true;
 	}
 	return stopped;
@@ -261,7 +261,7 @@ static int start_endpoints(struct snd_usb_substream *subs)
 	return 0;
 
  error:
-	stop_endpoints(subs);
+	stop_endpoints(subs, false);
 	return err;
 }
 
@@ -437,7 +437,7 @@ static int configure_endpoints(struct snd_usb_audio *chip,
 
 	if (subs->data_endpoint->need_setup) {
 		/* stop any running stream beforehand */
-		if (stop_endpoints(subs))
+		if (stop_endpoints(subs, false))
 			sync_pending_stops(subs);
 		err = snd_usb_endpoint_configure(chip, subs->data_endpoint);
 		if (err < 0)
@@ -572,7 +572,7 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream)
 	subs->cur_audiofmt = NULL;
 	mutex_unlock(&chip->mutex);
 	if (!snd_usb_lock_shutdown(chip)) {
-		if (stop_endpoints(subs))
+		if (stop_endpoints(subs, false))
 			sync_pending_stops(subs);
 		close_endpoints(chip, subs);
 		snd_usb_unlock_shutdown(chip);
@@ -581,6 +581,31 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
+/* free-wheeling mode? (e.g. dmix) */
+static int in_free_wheeling_mode(struct snd_pcm_runtime *runtime)
+{
+	return runtime->stop_threshold > runtime->buffer_size;
+}
+
+/* check whether early start is needed for playback stream */
+static int lowlatency_playback_available(struct snd_pcm_runtime *runtime,
+					 struct snd_usb_substream *subs)
+{
+	struct snd_usb_audio *chip = subs->stream->chip;
+
+	if (subs->direction == SNDRV_PCM_STREAM_CAPTURE)
+		return false;
+	/* disabled via module option? */
+	if (!chip->lowlatency)
+		return false;
+	if (in_free_wheeling_mode(runtime))
+		return false;
+	/* implicit feedback mode has own operation mode */
+	if (snd_usb_endpoint_implicit_feedback_sink(subs->data_endpoint))
+		return false;
+	return true;
+}
+
 /*
  * prepare callback
  *
@@ -614,13 +639,9 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream)
 	subs->period_elapsed_pending = 0;
 	runtime->delay = 0;
 
-	/* check whether early start is needed for playback stream */
-	subs->early_playback_start =
-		subs->direction == SNDRV_PCM_STREAM_PLAYBACK &&
-		(!chip->lowlatency ||
-		 (subs->data_endpoint->nominal_queue_size >= subs->buffer_bytes));
-
-	if (subs->early_playback_start)
+	subs->lowlatency_playback = lowlatency_playback_available(runtime, subs);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
+	    !subs->lowlatency_playback)
 		ret = start_endpoints(subs);
 
  unlock:
@@ -734,6 +755,7 @@ static int hw_rule_rate(struct snd_pcm_hw_params *params,
 			struct snd_pcm_hw_rule *rule)
 {
 	struct snd_usb_substream *subs = rule->private;
+	struct snd_usb_audio *chip = subs->stream->chip;
 	const struct audioformat *fp;
 	struct snd_interval *it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
 	unsigned int rmin, rmax, r;
@@ -745,6 +767,14 @@ static int hw_rule_rate(struct snd_pcm_hw_params *params,
 	list_for_each_entry(fp, &subs->fmt_list, list) {
 		if (!hw_check_valid_format(subs, params, fp))
 			continue;
+		r = snd_usb_endpoint_get_clock_rate(chip, fp->clock);
+		if (r > 0) {
+			if (!snd_interval_test(it, r))
+				continue;
+			rmin = min(rmin, r);
+			rmax = max(rmax, r);
+			continue;
+		}
 		if (fp->rate_table && fp->nr_rates) {
 			for (i = 0; i < fp->nr_rates; i++) {
 				r = fp->rate_table[i];
@@ -1068,6 +1098,10 @@ static int snd_usb_pcm_open(struct snd_pcm_substream *substream)
 	int ret;
 
 	runtime->hw = snd_usb_hardware;
+	/* need an explicit sync to catch applptr update in low-latency mode */
+	if (direction == SNDRV_PCM_STREAM_PLAYBACK &&
+	    as->chip->lowlatency)
+		runtime->hw.info |= SNDRV_PCM_INFO_SYNC_APPLPTR;
 	runtime->private_data = subs;
 	subs->pcm_substream = substream;
 	/* runtime PM is also done there */
@@ -1320,44 +1354,66 @@ static unsigned int copy_to_urb_quirk(struct snd_usb_substream *subs,
 	return bytes;
 }
 
-static void prepare_playback_urb(struct snd_usb_substream *subs,
-				 struct urb *urb)
+static int prepare_playback_urb(struct snd_usb_substream *subs,
+				struct urb *urb,
+				bool in_stream_lock)
 {
 	struct snd_pcm_runtime *runtime = subs->pcm_substream->runtime;
 	struct snd_usb_endpoint *ep = subs->data_endpoint;
 	struct snd_urb_ctx *ctx = urb->context;
-	unsigned int counts, frames, bytes;
+	unsigned int frames, bytes;
+	int counts;
+	unsigned int transfer_done, frame_limit, avail = 0;
 	int i, stride, period_elapsed = 0;
 	unsigned long flags;
+	int err = 0;
 
 	stride = ep->stride;
 
 	frames = 0;
 	ctx->queued = 0;
 	urb->number_of_packets = 0;
+
 	spin_lock_irqsave(&subs->lock, flags);
-	subs->frame_limit += ep->max_urb_frames;
+	frame_limit = subs->frame_limit + ep->max_urb_frames;
+	transfer_done = subs->transfer_done;
+
+	if (subs->lowlatency_playback &&
+	    runtime->status->state != SNDRV_PCM_STATE_DRAINING) {
+		unsigned int hwptr = subs->hwptr_done / stride;
+
+		/* calculate the byte offset-in-buffer of the appl_ptr */
+		avail = (runtime->control->appl_ptr - runtime->hw_ptr_base)
+			% runtime->buffer_size;
+		if (avail <= hwptr)
+			avail += runtime->buffer_size;
+		avail -= hwptr;
+	}
+
 	for (i = 0; i < ctx->packets; i++) {
-		counts = snd_usb_endpoint_next_packet_size(ep, ctx, i);
+		counts = snd_usb_endpoint_next_packet_size(ep, ctx, i, avail);
+		if (counts < 0)
+			break;
 		/* set up descriptor */
 		urb->iso_frame_desc[i].offset = frames * stride;
 		urb->iso_frame_desc[i].length = counts * stride;
 		frames += counts;
+		avail -= counts;
 		urb->number_of_packets++;
-		subs->transfer_done += counts;
-		if (subs->transfer_done >= runtime->period_size) {
-			subs->transfer_done -= runtime->period_size;
-			subs->frame_limit = 0;
+		transfer_done += counts;
+		if (transfer_done >= runtime->period_size) {
+			transfer_done -= runtime->period_size;
+			frame_limit = 0;
 			period_elapsed = 1;
 			if (subs->fmt_type == UAC_FORMAT_TYPE_II) {
-				if (subs->transfer_done > 0) {
+				if (transfer_done > 0) {
 					/* FIXME: fill-max mode is not
 					 * supported yet */
-					frames -= subs->transfer_done;
-					counts -= subs->transfer_done;
+					frames -= transfer_done;
+					counts -= transfer_done;
 					urb->iso_frame_desc[i].length =
 						counts * stride;
-					subs->transfer_done = 0;
+					transfer_done = 0;
 				}
 				i++;
 				if (i < ctx->packets) {
@@ -1371,13 +1427,19 @@ static void prepare_playback_urb(struct snd_usb_substream *subs,
 			}
 		}
 		/* finish at the period boundary or after enough frames */
-		if ((period_elapsed ||
-				subs->transfer_done >= subs->frame_limit) &&
+		if ((period_elapsed || transfer_done >= frame_limit) &&
 		    !snd_usb_endpoint_implicit_feedback_sink(ep))
 			break;
 	}
-	bytes = frames * stride;
 
+	if (!frames) {
+		err = -EAGAIN;
+		goto unlock;
+	}
+
+	bytes = frames * stride;
+	subs->transfer_done = transfer_done;
+	subs->frame_limit = frame_limit;
 	if (unlikely(ep->cur_format == SNDRV_PCM_FORMAT_DSD_U16_LE &&
 		     subs->cur_audiofmt->dsd_dop)) {
 		fill_playback_urb_dsd_dop(subs, urb, bytes);
@@ -1403,14 +1465,23 @@ static void prepare_playback_urb(struct snd_usb_substream *subs,
 		subs->trigger_tstamp_pending_update = false;
 	}
 
-	if (period_elapsed && !subs->running && !subs->early_playback_start) {
+	if (period_elapsed && !subs->running && subs->lowlatency_playback) {
 		subs->period_elapsed_pending = 1;
 		period_elapsed = 0;
 	}
+
+ unlock:
 	spin_unlock_irqrestore(&subs->lock, flags);
+	if (err < 0)
+		return err;
 	urb->transfer_buffer_length = bytes;
-	if (period_elapsed)
-		snd_pcm_period_elapsed(subs->pcm_substream);
+	if (period_elapsed) {
+		if (in_stream_lock)
+			snd_pcm_period_elapsed_under_stream_lock(subs->pcm_substream);
+		else
+			snd_pcm_period_elapsed(subs->pcm_substream);
+	}
+	return 0;
 }
 
 /*
@@ -1442,6 +1513,27 @@ static void retire_playback_urb(struct snd_usb_substream *subs,
 		snd_pcm_period_elapsed(subs->pcm_substream);
 }
 
+/* PCM ack callback for the playback stream;
+ * this plays a role only when the stream is running in low-latency mode.
+ */
+static int snd_usb_pcm_playback_ack(struct snd_pcm_substream *substream)
+{
+	struct snd_usb_substream *subs = substream->runtime->private_data;
+	struct snd_usb_endpoint *ep;
+
+	if (!subs->lowlatency_playback || !subs->running)
+		return 0;
+	ep = subs->data_endpoint;
+	if (!ep)
+		return 0;
+	/* When no more in-flight URBs available, try to process the pending
+	 * outputs here
+	 */
+	if (!ep->active_mask)
+		snd_usb_queue_pending_output_urbs(ep, true);
+	return 0;
+}
+
 static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substream,
 					      int cmd)
 {
@@ -1457,8 +1549,10 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 					      prepare_playback_urb,
 					      retire_playback_urb,
 					      subs);
-		if (!subs->early_playback_start &&
+		if (subs->lowlatency_playback &&
 		    cmd == SNDRV_PCM_TRIGGER_START) {
+			if (in_free_wheeling_mode(substream->runtime))
+				subs->lowlatency_playback = false;
 			err = start_endpoints(subs);
 			if (err < 0) {
 				snd_usb_endpoint_set_callback(subs->data_endpoint,
@@ -1473,7 +1567,7 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 		return 0;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
-		stop_endpoints(subs);
+		stop_endpoints(subs, substream->runtime->status->state == SNDRV_PCM_STATE_DRAINING);
 		snd_usb_endpoint_set_callback(subs->data_endpoint,
 					      NULL, NULL, NULL);
 		subs->running = 0;
@@ -1521,7 +1615,7 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream
 		return 0;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
-		stop_endpoints(subs);
+		stop_endpoints(subs, false);
 		fallthrough;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		snd_usb_endpoint_set_callback(subs->data_endpoint,
@@ -1545,6 +1639,7 @@ static const struct snd_pcm_ops snd_usb_playback_ops = {
 	.trigger =	snd_usb_substream_playback_trigger,
 	.sync_stop =	snd_usb_pcm_sync_stop,
 	.pointer =	snd_usb_pcm_pointer,
+	.ack =		snd_usb_pcm_playback_ack,
 };
 
 static const struct snd_pcm_ops snd_usb_capture_ops = {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a0316ce910db6..997e0a4b0902a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -619,14 +619,17 @@ static int report__browse_hists(struct report *rep)
 	int ret;
 	struct perf_session *session = rep->session;
 	struct evlist *evlist = session->evlist;
-	const char *help = perf_tip(system_path(TIPDIR));
+	char *help = NULL, *path = NULL;
 
-	if (help == NULL) {
+	path = system_path(TIPDIR);
+	if (perf_tip(&help, path) || help == NULL) {
 		/* fallback for people who don't install perf ;-) */
-		help = perf_tip(DOCDIR);
-		if (help == NULL)
-			help = "Cannot load tips.txt file, please install perf!";
+		free(path);
+		path = system_path(DOCDIR);
+		if (perf_tip(&help, path) || help == NULL)
+			help = strdup("Cannot load tips.txt file, please install perf!");
 	}
+	free(path);
 
 	switch (use_browser) {
 	case 1:
@@ -651,7 +654,7 @@ static int report__browse_hists(struct report *rep)
 		ret = evlist__tty_browse_hists(evlist, rep, help);
 		break;
 	}
-
+	free(help);
 	return ret;
 }
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index c1f24d0048527..5075ecead5f3d 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -535,6 +535,18 @@ struct perf_hpp_list perf_hpp_list = {
 #undef __HPP_SORT_ACC_FN
 #undef __HPP_SORT_RAW_FN
 
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
+	if (fmt->free)
+		fmt->free(fmt);
+}
 
 void perf_hpp__init(void)
 {
@@ -598,9 +610,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 	list_add(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del_init(&format->list);
+	fmt_free(format);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -672,19 +685,6 @@ next:
 }
 
 
-static void fmt_free(struct perf_hpp_fmt *fmt)
-{
-	/*
-	 * At this point fmt should be completely
-	 * unhooked, if not it's a bug.
-	 */
-	BUG_ON(!list_empty(&fmt->list));
-	BUG_ON(!list_empty(&fmt->sort_list));
-
-	if (fmt->free)
-		fmt->free(fmt);
-}
-
 void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 58b7069c5a5f8..7054f23150e1b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -51,6 +51,7 @@ struct arm_spe {
 	u8				timeless_decoding;
 	u8				data_queued;
 
+	u64				sample_type;
 	u8				sample_flc;
 	u8				sample_llc;
 	u8				sample_tlb;
@@ -248,6 +249,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe,
 	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
+static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
+{
+	event->header.size = perf_event__sample_event_size(sample, type, 0);
+	return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
 static inline int
 arm_spe_deliver_synth_event(struct arm_spe *spe,
 			    struct arm_spe_queue *speq __maybe_unused,
@@ -256,6 +263,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,
 {
 	int ret;
 
+	if (spe->synth_opts.inject) {
+		ret = arm_spe__inject_event(event, sample, spe->sample_type);
+		if (ret)
+			return ret;
+	}
+
 	ret = perf_session__deliver_synth_event(spe->session, event, sample);
 	if (ret)
 		pr_err("ARM SPE: failed to deliver event, error %d\n", ret);
@@ -920,6 +933,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	else
 		attr.sample_type |= PERF_SAMPLE_TIME;
 
+	spe->sample_type = attr.sample_type;
+
 	attr.exclude_user = evsel->core.attr.exclude_user;
 	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
 	attr.exclude_hv = evsel->core.attr.exclude_hv;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 65fe65ba03c25..b776465e04ef3 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -289,15 +289,10 @@ static long hist_time(unsigned long htime)
 	return htime;
 }
 
-static void he_stat__add_period(struct he_stat *he_stat, u64 period,
-				u64 weight, u64 ins_lat, u64 p_stage_cyc)
+static void he_stat__add_period(struct he_stat *he_stat, u64 period)
 {
-
 	he_stat->period		+= period;
-	he_stat->weight		+= weight;
 	he_stat->nr_events	+= 1;
-	he_stat->ins_lat	+= ins_lat;
-	he_stat->p_stage_cyc	+= p_stage_cyc;
 }
 
 static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
@@ -308,9 +303,6 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
-	dest->weight		+= src->weight;
-	dest->ins_lat		+= src->ins_lat;
-	dest->p_stage_cyc		+= src->p_stage_cyc;
 }
 
 static void he_stat__decay(struct he_stat *he_stat)
@@ -598,9 +590,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	struct hist_entry *he;
 	int64_t cmp;
 	u64 period = entry->stat.period;
-	u64 weight = entry->stat.weight;
-	u64 ins_lat = entry->stat.ins_lat;
-	u64 p_stage_cyc = entry->stat.p_stage_cyc;
 	bool leftmost = true;
 
 	p = &hists->entries_in->rb_root.rb_node;
@@ -619,11 +608,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc);
+				he_stat__add_period(&he->stat, period);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
-				he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc);
+				he_stat__add_period(he->stat_acc, period);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -733,9 +722,6 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
-			.weight = sample->weight,
-			.ins_lat = sample->ins_lat,
-			.p_stage_cyc = sample->p_stage_cyc,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
@@ -748,6 +734,9 @@ __hists__add_entry(struct hists *hists,
 		.raw_size = sample->raw_size,
 		.ops = ops,
 		.time = hist_time(sample->time),
+		.weight = sample->weight,
+		.ins_lat = sample->ins_lat,
+		.p_stage_cyc = sample->p_stage_cyc,
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5343b62476e60..621f35ae1efa5 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -369,7 +369,6 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__cancel_cumulate(void);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 568a88c001c6c..a111065b484ef 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1325,88 +1325,68 @@ struct sort_entry sort_mispredict = {
 	.se_width_idx	= HISTC_MISPREDICT,
 };
 
-static u64 he_weight(struct hist_entry *he)
-{
-	return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
-}
-
 static int64_t
-sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__weight_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return he_weight(left) - he_weight(right);
+	return left->weight - right->weight;
 }
 
 static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
+	return repsep_snprintf(bf, size, "%-*llu", width, he->weight);
 }
 
 struct sort_entry sort_local_weight = {
 	.se_header	= "Local Weight",
-	.se_cmp		= sort__local_weight_cmp,
+	.se_cmp		= sort__weight_cmp,
 	.se_snprintf	= hist_entry__local_weight_snprintf,
 	.se_width_idx	= HISTC_LOCAL_WEIGHT,
 };
 
-static int64_t
-sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-	return left->stat.weight - right->stat.weight;
-}
-
 static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
 					      size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
+	return repsep_snprintf(bf, size, "%-*llu", width,
+			       he->weight * he->stat.nr_events);
 }
 
 struct sort_entry sort_global_weight = {
 	.se_header	= "Weight",
-	.se_cmp		= sort__global_weight_cmp,
+	.se_cmp		= sort__weight_cmp,
 	.se_snprintf	= hist_entry__global_weight_snprintf,
 	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
 };
 
-static u64 he_ins_lat(struct hist_entry *he)
-{
-		return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0;
-}
-
 static int64_t
-sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-		return he_ins_lat(left) - he_ins_lat(right);
+	return left->ins_lat - right->ins_lat;
 }
 
 static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf,
 					      size_t size, unsigned int width)
 {
-		return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he));
+	return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat);
 }
 
 struct sort_entry sort_local_ins_lat = {
 	.se_header	= "Local INSTR Latency",
-	.se_cmp		= sort__local_ins_lat_cmp,
+	.se_cmp		= sort__ins_lat_cmp,
 	.se_snprintf	= hist_entry__local_ins_lat_snprintf,
 	.se_width_idx	= HISTC_LOCAL_INS_LAT,
 };
 
-static int64_t
-sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-		return left->stat.ins_lat - right->stat.ins_lat;
-}
-
 static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf,
 					       size_t size, unsigned int width)
 {
-		return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat);
+	return repsep_snprintf(bf, size, "%-*u", width,
+			       he->ins_lat * he->stat.nr_events);
 }
 
 struct sort_entry sort_global_ins_lat = {
 	.se_header	= "INSTR Latency",
-	.se_cmp		= sort__global_ins_lat_cmp,
+	.se_cmp		= sort__ins_lat_cmp,
 	.se_snprintf	= hist_entry__global_ins_lat_snprintf,
 	.se_width_idx	= HISTC_GLOBAL_INS_LAT,
 };
@@ -1414,13 +1394,13 @@ struct sort_entry sort_global_ins_lat = {
 static int64_t
 sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return left->stat.p_stage_cyc - right->stat.p_stage_cyc;
+	return left->p_stage_cyc - right->p_stage_cyc;
 }
 
 static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc);
+	return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
 }
 
 struct sort_entry sort_p_stage_cyc = {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b67c469aba795..7b7145501933f 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,9 +49,6 @@ struct he_stat {
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
-	u64			weight;
-	u64			ins_lat;
-	u64			p_stage_cyc;
 	u32			nr_events;
 };
 
@@ -109,6 +106,9 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u64			code_page_size;
+	u64			weight;
+	u64			ins_lat;
+	u64			p_stage_cyc;
 	u8			cpumode;
 	u8			depth;
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 37a9492edb3eb..df3c4671be72a 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -379,32 +379,32 @@ fetch_kernel_version(unsigned int *puint, char *str,
 	return 0;
 }
 
-const char *perf_tip(const char *dirpath)
+int perf_tip(char **strp, const char *dirpath)
 {
 	struct strlist *tips;
 	struct str_node *node;
-	char *tip = NULL;
 	struct strlist_config conf = {
 		.dirname = dirpath,
 		.file_only = true,
 	};
+	int ret = 0;
 
+	*strp = NULL;
 	tips = strlist__new("tips.txt", &conf);
 	if (tips == NULL)
-		return errno == ENOENT ? NULL :
-			"Tip: check path of tips.txt or get more memory! ;-p";
+		return -errno;
 
 	if (strlist__nr_entries(tips) == 0)
 		goto out;
 
 	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
-	if (asprintf(&tip, "Tip: %s", node->s) < 0)
-		tip = (char *)"Tip: get more memory! ;-)";
+	if (asprintf(strp, "Tip: %s", node->s) < 0)
+		ret = -ENOMEM;
 
 out:
 	strlist__delete(tips);
 
-	return tip;
+	return ret;
 }
 
 char *perf_exe(char *buf, int len)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ad737052e5977..9f0d36ba77f2d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,7 +39,7 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_FMT	"%d.%d.%d"
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
-const char *perf_tip(const char *dirpath);
+int perf_tip(char **strp, const char *dirpath);
 
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 3313566ce9062..7f5b265fcb905 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4002,8 +4002,8 @@ EOF
 ################################################################################
 # main
 
-TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter"
-TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter"
+TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter"
+TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter"
 TESTS_OTHER="use_cases"
 
 PAUSE_ON_FAIL=no
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index ebc4ee0fe179f..8a9461aa0878a 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -276,7 +276,11 @@ n0 ping -W 1 -c 1 192.168.241.2
 n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
 ip2 link del wg0
 ip2 link del wg1
-! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
+read _ _ tx_bytes_before < <(n0 wg show wg1 transfer)
+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false
+sleep 1
+read _ _ tx_bytes_after < <(n0 wg show wg1 transfer)
+(( tx_bytes_after - tx_bytes_before < 70000 ))
 
 ip0 link del wg1
 ip1 link del wg0
@@ -609,6 +613,28 @@ ip0 link set wg0 up
 kill $ncat_pid
 ip0 link del wg0
 
+# Ensure that dst_cache references don't outlive netns lifetime
+ip1 link add dev wg0 type wireguard
+ip2 link add dev wg0 type wireguard
+configure_peers
+ip1 link add veth1 type veth peer name veth2
+ip1 link set veth2 netns $netns2
+ip1 addr add fd00:aa::1/64 dev veth1
+ip2 addr add fd00:aa::2/64 dev veth2
+ip1 link set veth1 up
+ip2 link set veth2 up
+waitiface $netns1 veth1
+waitiface $netns2 veth2
+ip1 -6 route add default dev veth1 via fd00:aa::2
+ip2 -6 route add default dev veth2 via fd00:aa::1
+n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2
+n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1
+n1 ping6 -c 1 fd00::2
+pp ip netns delete $netns1
+pp ip netns delete $netns2
+pp ip netns add $netns1
+pp ip netns add $netns2
+
 # Ensure there aren't circular reference loops
 ip1 link add wg1 type wireguard
 ip2 link add wg2 type wireguard
@@ -627,7 +653,7 @@ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
 done < /dev/kmsg
 alldeleted=1
 for object in "${!objects[@]}"; do
-	if [[ ${objects["$object"]} != *createddestroyed ]]; then
+	if [[ ${objects["$object"]} != *createddestroyed && ${objects["$object"]} != *createdcreateddestroyeddestroyed ]]; then
 		echo "Error: $object: merely ${objects["$object"]}" >&3
 		alldeleted=0
 	fi
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index fe07d97df9fa8..2b321b8a96cf3 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -47,7 +47,7 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_TRACE_IRQFLAGS=y
 CONFIG_DEBUG_BUGVERBOSE=y
 CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PI_LIST=y
+CONFIG_DEBUG_PLIST=y
 CONFIG_PROVE_RCU=y
 CONFIG_SPARSE_RCU_POINTER=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=21
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 74db83a0aedd8..a9b5a520a1d22 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -66,6 +66,7 @@ CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_PRINTK_TIME=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_LEGACY_VSYSCALL_NONE=y
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7851f3a1b5f7c..ce1847bc898b2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1523,11 +1523,10 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old,
 
 static int kvm_set_memslot(struct kvm *kvm,
 			   const struct kvm_userspace_memory_region *mem,
-			   struct kvm_memory_slot *old,
 			   struct kvm_memory_slot *new, int as_id,
 			   enum kvm_mr_change change)
 {
-	struct kvm_memory_slot *slot;
+	struct kvm_memory_slot *slot, old;
 	struct kvm_memslots *slots;
 	int r;
 
@@ -1558,7 +1557,7 @@ static int kvm_set_memslot(struct kvm *kvm,
 		 * Note, the INVALID flag needs to be in the appropriate entry
 		 * in the freshly allocated memslots, not in @old or @new.
 		 */
-		slot = id_to_memslot(slots, old->id);
+		slot = id_to_memslot(slots, new->id);
 		slot->flags |= KVM_MEMSLOT_INVALID;
 
 		/*
@@ -1589,6 +1588,26 @@ static int kvm_set_memslot(struct kvm *kvm,
 		kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id));
 	}
 
+	/*
+	 * Make a full copy of the old memslot, the pointer will become stale
+	 * when the memslots are re-sorted by update_memslots(), and the old
+	 * memslot needs to be referenced after calling update_memslots(), e.g.
+	 * to free its resources and for arch specific behavior.  This needs to
+	 * happen *after* (re)acquiring slots_arch_lock.
+	 */
+	slot = id_to_memslot(slots, new->id);
+	if (slot) {
+		old = *slot;
+	} else {
+		WARN_ON_ONCE(change != KVM_MR_CREATE);
+		memset(&old, 0, sizeof(old));
+		old.id = new->id;
+		old.as_id = as_id;
+	}
+
+	/* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */
+	memcpy(&new->arch, &old.arch, sizeof(old.arch));
+
 	r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
 	if (r)
 		goto out_slots;
@@ -1596,14 +1615,18 @@ static int kvm_set_memslot(struct kvm *kvm,
 	update_memslots(slots, new, change);
 	slots = install_new_memslots(kvm, as_id, slots);
 
-	kvm_arch_commit_memory_region(kvm, mem, old, new, change);
+	kvm_arch_commit_memory_region(kvm, mem, &old, new, change);
+
+	/* Free the old memslot's metadata.  Note, this is the full copy!!! */
+	if (change == KVM_MR_DELETE)
+		kvm_free_memslot(kvm, &old);
 
 	kvfree(slots);
 	return 0;
 
 out_slots:
 	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
-		slot = id_to_memslot(slots, old->id);
+		slot = id_to_memslot(slots, new->id);
 		slot->flags &= ~KVM_MEMSLOT_INVALID;
 		slots = install_new_memslots(kvm, as_id, slots);
 	} else {
@@ -1618,7 +1641,6 @@ static int kvm_delete_memslot(struct kvm *kvm,
 			      struct kvm_memory_slot *old, int as_id)
 {
 	struct kvm_memory_slot new;
-	int r;
 
 	if (!old->npages)
 		return -EINVAL;
@@ -1631,12 +1653,7 @@ static int kvm_delete_memslot(struct kvm *kvm,
 	 */
 	new.as_id = as_id;
 
-	r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE);
-	if (r)
-		return r;
-
-	kvm_free_memslot(kvm, old);
-	return 0;
+	return kvm_set_memslot(kvm, mem, &new, as_id, KVM_MR_DELETE);
 }
 
 /*
@@ -1664,7 +1681,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	id = (u16)mem->slot;
 
 	/* General sanity checks */
-	if (mem->memory_size & (PAGE_SIZE - 1))
+	if ((mem->memory_size & (PAGE_SIZE - 1)) ||
+	    (mem->memory_size != (unsigned long)mem->memory_size))
 		return -EINVAL;
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		return -EINVAL;
@@ -1710,7 +1728,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!old.npages) {
 		change = KVM_MR_CREATE;
 		new.dirty_bitmap = NULL;
-		memset(&new.arch, 0, sizeof(new.arch));
 	} else { /* Modify an existing slot. */
 		if ((new.userspace_addr != old.userspace_addr) ||
 		    (new.npages != old.npages) ||
@@ -1724,9 +1741,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		else /* Nothing to change. */
 			return 0;
 
-		/* Copy dirty_bitmap and arch from the current memslot. */
+		/* Copy dirty_bitmap from the current memslot. */
 		new.dirty_bitmap = old.dirty_bitmap;
-		memcpy(&new.arch, &old.arch, sizeof(new.arch));
 	}
 
 	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
@@ -1752,7 +1768,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			bitmap_set(new.dirty_bitmap, 0, new.npages);
 	}
 
-	r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change);
+	r = kvm_set_memslot(kvm, mem, &new, as_id, change);
 	if (r)
 		goto out_bitmap;