Merge tag 'v6.12-rc5' into android-mainline

Linux 6.12-rc5 Signed-off-by: Lee Jones <joneslee@google.com> Change-Id: Ie9f51e6441eda54ae6a21cad31da6edecae7e349
2024-10-31 16:02:50 +00:00
parent 7dceab7d60 8198375843
commit f0999a133a
295 changed files with 2967 additions and 3159 deletions
@@ -306,6 +306,11 @@ Jens Axboe <axboe@kernel.dk> <axboe@fb.com>
 Jens Axboe <axboe@kernel.dk> <axboe@meta.com>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
+Jesper Dangaard Brouer <hawk@kernel.org> <brouer@redhat.com>
+Jesper Dangaard Brouer <hawk@kernel.org> <hawk@comx.dk>
+Jesper Dangaard Brouer <hawk@kernel.org> <jbrouer@redhat.com>
+Jesper Dangaard Brouer <hawk@kernel.org> <jdb@comx.dk>
+Jesper Dangaard Brouer <hawk@kernel.org> <netoptimizer@brouer.com>
 Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>
 Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org>
 Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz>
@@ -425,8 +425,8 @@ This governor exposes only one tunable:

 ``rate_limit_us``
 	Minimum time (in microseconds) that has to pass between two consecutive
-	runs of governor computations (default: 1000 times the scaling driver's
-	transition latency).
+	runs of governor computations (default: 1.5 times the scaling driver's
+	transition latency or the maximum 2ms).

 	The purpose of this tunable is to reduce the scheduler context overhead
 	of the governor which might be excessive without it.
@@ -474,17 +474,17 @@ This governor exposes the following tunables:
 	This is how often the governor's worker routine should run, in
 	microseconds.

-	Typically, it is set to values of the order of 10000 (10 ms).  Its
-	default value is equal to the value of ``cpuinfo_transition_latency``
-	for each policy this governor is attached to (but since the unit here
-	is greater by 1000, this means that the time represented by
-	``sampling_rate`` is 1000 times greater than the transition latency by
-	default).
+	Typically, it is set to values of the order of 2000 (2 ms).  Its
+	default value is to add a 50% breathing room
+	to ``cpuinfo_transition_latency`` on each policy this governor is
+	attached to. The minimum is typically the length of two scheduler
+	ticks.

 	If this tunable is per-policy, the following shell command sets the time
-	represented by it to be 750 times as high as the transition latency::
+	represented by it to be 1.5 times as high as the transition latency
+	(the default)::

-	# echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate
+	# echo `$(($(cat cpuinfo_transition_latency) * 3 / 2)) > ondemand/sampling_rate

 ``up_threshold``
 	If the estimated CPU load is above this value (in percent), the governor
@@ -102,21 +102,21 @@ properties:
    default: 2

  interrupts:
-    oneOf:
-      - minItems: 1
-        items:
-          - description: TX interrupt
-          - description: RX interrupt
-      - items:
-          - description: common/combined interrupt
+    minItems: 1
+    maxItems: 2

  interrupt-names:
    oneOf:
-      - minItems: 1
+      - description: TX interrupt
+        const: tx
+      - description: RX interrupt
+        const: rx
+      - description: TX and RX interrupts
        items:
          - const: tx
          - const: rx
-      - const: common
+      - description: Common/combined interrupt
+        const: common

  fck_parent:
    $ref: /schemas/types.yaml#/definitions/string
@@ -592,4 +592,3 @@ API Function Reference

 .. kernel-doc:: include/linux/netfs.h
 .. kernel-doc:: fs/netfs/buffered_read.c
-.. kernel-doc:: fs/netfs/io.c
@@ -8098,13 +8098,15 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
                                    KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
                                    disabled.

-KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, KVM invalidates all SPTEs in
-                                    fast way for memslot deletion when VM type
-                                    is KVM_X86_DEFAULT_VM.
-                                    When this quirk is disabled or when VM type
-                                    is other than KVM_X86_DEFAULT_VM, KVM zaps
-                                    only leaf SPTEs that are within the range of
-                                    the memslot being deleted.
+KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, for KVM_X86_DEFAULT_VM VMs, KVM
+                                    invalidates all SPTEs in all memslots and
+                                    address spaces when a memslot is deleted or
+                                    moved.  When this quirk is disabled (or the
+                                    VM type isn't KVM_X86_DEFAULT_VM), KVM only
+                                    ensures the backing memory of the deleted
+                                    or moved memslot isn't reachable, i.e KVM
+                                    _may_ invalidate only SPTEs related to the
+                                    memslot.
 =================================== ============================================

 7.32 KVM_CAP_MAX_VCPU_ID
@@ -136,7 +136,7 @@ For direct sp, we can easily avoid it since the spte of direct sp is fixed
 to gfn.  For indirect sp, we disabled fast page fault for simplicity.

 A solution for indirect sp could be to pin the gfn, for example via
-kvm_vcpu_gfn_to_pfn_atomic, before the cmpxchg.  After the pinning:
+gfn_to_pfn_memslot_atomic, before the cmpxchg.  After the pinning:

 - We have held the refcount of pfn; that means the pfn can not be freed and
  be reused for another gfn.
@@ -9723,6 +9723,7 @@ F:	include/dt-bindings/gpio/
 F:	include/linux/gpio.h
 F:	include/linux/gpio/
 F:	include/linux/of_gpio.h
+K:	(devm_)?gpio_(request|free|direction|get|set)

 GPIO UAPI
 M:	Bartosz Golaszewski <brgl@bgdev.pl>
@@ -14993,6 +14994,7 @@ F:	drivers/spi/spi-at91-usart.c

 MICROCHIP AUDIO ASOC DRIVERS
 M:	Claudiu Beznea <claudiu.beznea@tuxon.dev>
+M:	Andrei Simion <andrei.simion@microchip.com>
 L:	linux-sound@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/sound/atmel*
@@ -15101,6 +15103,7 @@ F:	include/video/atmel_lcdc.h

 MICROCHIP MCP16502 PMIC DRIVER
 M:	Claudiu Beznea <claudiu.beznea@tuxon.dev>
+M:	Andrei Simion <andrei.simion@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	Documentation/devicetree/bindings/regulator/microchip,mcp16502.yaml
@@ -15231,6 +15234,7 @@ F:	drivers/spi/spi-atmel.*

 MICROCHIP SSC DRIVER
 M:	Claudiu Beznea <claudiu.beznea@tuxon.dev>
+M:	Andrei Simion <andrei.simion@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	Documentation/devicetree/bindings/misc/atmel-ssc.txt
@@ -16049,6 +16053,7 @@ M:	"David S. Miller" <davem@davemloft.net>
 M:	Eric Dumazet <edumazet@google.com>
 M:	Jakub Kicinski <kuba@kernel.org>
 M:	Paolo Abeni <pabeni@redhat.com>
+R:	Simon Horman <horms@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 P:	Documentation/process/maintainer-netdev.rst
@@ -16091,6 +16096,7 @@ F:	include/uapi/linux/rtnetlink.h
 F:	lib/net_utils.c
 F:	lib/random32.c
 F:	net/
+F:	samples/pktgen/
 F:	tools/net/
 F:	tools/testing/selftests/net/
 X:	Documentation/networking/mac80211-injection.rst
@@ -23150,7 +23156,7 @@ F:	Documentation/devicetree/bindings/iio/adc/ti,lmp92064.yaml
 F:	drivers/iio/adc/ti-lmp92064.c

 TI PCM3060 ASoC CODEC DRIVER
-M:	Kirill Marinushkin <kmarinushkin@birdec.com>
+M:	Kirill Marinushkin <k.marinushkin@gmail.com>
 L:	linux-sound@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/sound/pcm3060.txt
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse

 # *DOCUMENTATION*
@@ -178,6 +178,7 @@ struct kvm_nvhe_init_params {
 	unsigned long hcr_el2;
 	unsigned long vttbr;
 	unsigned long vtcr;
+	unsigned long tmp;
 };

 /*
@@ -51,6 +51,7 @@
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 #define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
 #define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP	KVM_ARCH_REQ(8)

 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -211,6 +212,12 @@ struct kvm_s2_mmu {
 	 */
 	bool	nested_stage2_enabled;

+	/*
+	 * true when this MMU needs to be unmapped before being used for a new
+	 * purpose.
+	 */
+	bool	pending_unmap;
+
 	/*
 	 *  0: Nobody is currently using this, check vttbr for validity
 	 * >0: Somebody is actively using this.
@@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);

-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block);
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);

@@ -78,6 +78,8 @@ extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);

+extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
+
 struct kvm_s2_trans {
 	phys_addr_t output;
 	unsigned long block_size;
@@ -124,7 +126,7 @@ extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
 				    struct kvm_s2_trans *trans);
 extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
 extern void kvm_nested_s2_wp(struct kvm *kvm);
-extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block);
 extern void kvm_nested_s2_flush(struct kvm *kvm);

 unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
@@ -146,6 +146,7 @@ int main(void)
  DEFINE(NVHE_INIT_HCR_EL2,	offsetof(struct kvm_nvhe_init_params, hcr_el2));
  DEFINE(NVHE_INIT_VTTBR,	offsetof(struct kvm_nvhe_init_params, vttbr));
  DEFINE(NVHE_INIT_VTCR,	offsetof(struct kvm_nvhe_init_params, vtcr));
+  DEFINE(NVHE_INIT_TMP,		offsetof(struct kvm_nvhe_init_params, tmp));
 #endif
 #ifdef CONFIG_CPU_PM
  DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
@@ -997,6 +997,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
 static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
 	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+			return -EIO;
+
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
 			kvm_vcpu_sleep(vcpu);

@@ -1031,6 +1034,8 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)

 		if (kvm_dirty_ring_check_request(vcpu))
 			return 0;
+
+		check_nested_vcpu_requests(vcpu);
 	}

 	return 1;
@@ -24,28 +24,25 @@
 	.align	11

 SYM_CODE_START(__kvm_hyp_init)
-	ventry	__invalid		// Synchronous EL2t
-	ventry	__invalid		// IRQ EL2t
-	ventry	__invalid		// FIQ EL2t
-	ventry	__invalid		// Error EL2t
+	ventry	.			// Synchronous EL2t
+	ventry	.			// IRQ EL2t
+	ventry	.			// FIQ EL2t
+	ventry	.			// Error EL2t

-	ventry	__invalid		// Synchronous EL2h
-	ventry	__invalid		// IRQ EL2h
-	ventry	__invalid		// FIQ EL2h
-	ventry	__invalid		// Error EL2h
+	ventry	.			// Synchronous EL2h
+	ventry	.			// IRQ EL2h
+	ventry	.			// FIQ EL2h
+	ventry	.			// Error EL2h

 	ventry	__do_hyp_init		// Synchronous 64-bit EL1
-	ventry	__invalid		// IRQ 64-bit EL1
-	ventry	__invalid		// FIQ 64-bit EL1
-	ventry	__invalid		// Error 64-bit EL1
+	ventry	.			// IRQ 64-bit EL1
+	ventry	.			// FIQ 64-bit EL1
+	ventry	.			// Error 64-bit EL1

-	ventry	__invalid		// Synchronous 32-bit EL1
-	ventry	__invalid		// IRQ 32-bit EL1
-	ventry	__invalid		// FIQ 32-bit EL1
-	ventry	__invalid		// Error 32-bit EL1
-
-__invalid:
-	b	.
+	ventry	.			// Synchronous 32-bit EL1
+	ventry	.			// IRQ 32-bit EL1
+	ventry	.			// FIQ 32-bit EL1
+	ventry	.			// Error 32-bit EL1

 	/*
 	 * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
@@ -76,6 +73,13 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)

+SYM_CODE_START_LOCAL(__kvm_init_el2_state)
+	/* Initialize EL2 CPU state to sane values. */
+	init_el2_state				// Clobbers x0..x2
+	finalise_el2_state
+	ret
+SYM_CODE_END(__kvm_init_el2_state)
+
 /*
 * Initialize the hypervisor in EL2.
 *
@@ -102,9 +106,12 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
 	// TPIDR_EL2 is used to preserve x0 across the macro maze...
 	isb
 	msr	tpidr_el2, x0
-	init_el2_state
-	finalise_el2_state
+	str	lr, [x0, #NVHE_INIT_TMP]
+
+	bl	__kvm_init_el2_state
+
 	mrs	x0, tpidr_el2
+	ldr	lr, [x0, #NVHE_INIT_TMP]

 1:
 	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
@@ -199,9 +206,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)

 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}

-	/* Initialize EL2 CPU state to sane values. */
-	init_el2_state				// Clobbers x0..x2
-	finalise_el2_state
+	bl	__kvm_init_el2_state
+
 	__init_el2_nvhe_prepare_eret

 	/* Enable MMU, set vectors and stack. */
@@ -317,7 +317,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 				 * to the guest, and hide SSBS so that the
 				 * guest stays protected.
 				 */
-				if (cpus_have_final_cap(ARM64_SSBS))
+				if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
 					break;
 				fallthrough;
 			case SPECTRE_UNAFFECTED:
@@ -428,7 +428,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 * Convert the workaround level into an easy-to-compare number, where higher
 * values mean better protection.
 */
-static int get_kernel_wa_level(u64 regid)
+static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
 {
 	switch (regid) {
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
@@ -449,7 +449,7 @@ static int get_kernel_wa_level(u64 regid)
 			 * don't have any FW mitigation if SSBS is there at
 			 * all times.
 			 */
-			if (cpus_have_final_cap(ARM64_SSBS))
+			if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
 				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
 			fallthrough;
 		case SPECTRE_UNAFFECTED:
@@ -486,7 +486,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+		val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
 		break;
 	case KVM_REG_ARM_STD_BMAP:
 		val = READ_ONCE(smccc_feat->std_bmap);
@@ -588,7 +588,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
 			return -EINVAL;

-		if (get_kernel_wa_level(reg->id) < val)
+		if (get_kernel_wa_level(vcpu, reg->id) < val)
 			return -EINVAL;

 		return 0;
@@ -624,7 +624,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
 		 * other way around.
 		 */
-		if (get_kernel_wa_level(reg->id) < wa_level)
+		if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
 			return -EINVAL;

 		return 0;
@@ -328,9 +328,10 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 				   may_block));
 }

-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block)
 {
-	__unmap_stage2_range(mmu, start, size, true);
+	__unmap_stage2_range(mmu, start, size, may_block);
 }

 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -1015,7 +1016,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,

 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1042,7 +1043,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);

-	kvm_nested_s2_unmap(kvm);
+	kvm_nested_s2_unmap(kvm, true);

 	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
@@ -1912,7 +1913,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 			     (range->end - range->start) << PAGE_SHIFT,
 			     range->may_block);

-	kvm_nested_s2_unmap(kvm);
+	kvm_nested_s2_unmap(kvm, range->may_block);
 	return false;
 }

@@ -2179,8 +2180,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;

 	write_lock(&kvm->mmu_lock);
-	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
-	kvm_nested_s2_unmap(kvm);
+	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
+	kvm_nested_s2_unmap(kvm, true);
 	write_unlock(&kvm->mmu_lock);
 }

@@ -632,9 +632,9 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
 	/* Set the scene for the next search */
 	kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;

-	/* Clear the old state */
+	/* Make sure we don't forget to do the laundry */
 	if (kvm_s2_mmu_valid(s2_mmu))
-		kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+		s2_mmu->pending_unmap = true;

 	/*
 	 * The virtual VMID (modulo CnP) will be used as a key when matching
@@ -650,6 +650,16 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)

 out:
 	atomic_inc(&s2_mmu->refcnt);
+
+	/*
+	 * Set the vCPU request to perform an unmap, even if the pending unmap
+	 * originates from another vCPU. This guarantees that the MMU has been
+	 * completely unmapped before any vCPU actually uses it, and allows
+	 * multiple vCPUs to lend a hand with completing the unmap.
+	 */
+	if (s2_mmu->pending_unmap)
+		kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu);
+
 	return s2_mmu;
 }

@@ -663,6 +673,13 @@ void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)

 void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The vCPU kept its reference on the MMU after the last put, keep
+	 * rolling with it.
+	 */
+	if (vcpu->arch.hw_mmu)
+		return;
+
 	if (is_hyp_ctxt(vcpu)) {
 		vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
 	} else {
@@ -674,10 +691,18 @@ void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)

 void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
 {
-	if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
+	/*
+	 * Keep a reference on the associated stage-2 MMU if the vCPU is
+	 * scheduling out and not in WFI emulation, suggesting it is likely to
+	 * reuse the MMU sometime soon.
+	 */
+	if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI))
+		return;
+
+	if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu))
 		atomic_dec(&vcpu->arch.hw_mmu->refcnt);
-		vcpu->arch.hw_mmu = NULL;
-	}
+
+	vcpu->arch.hw_mmu = NULL;
 }

 /*
@@ -730,7 +755,7 @@ void kvm_nested_s2_wp(struct kvm *kvm)
 	}
 }

-void kvm_nested_s2_unmap(struct kvm *kvm)
+void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
 {
 	int i;

@@ -740,7 +765,7 @@ void kvm_nested_s2_unmap(struct kvm *kvm)
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];

 		if (kvm_s2_mmu_valid(mmu))
-			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
 	}
 }

@@ -1184,3 +1209,17 @@ int kvm_init_nv_sysregs(struct kvm *kvm)

 	return 0;
 }
+
+void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) {
+		struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
+
+		write_lock(&vcpu->kvm->mmu_lock);
+		if (mmu->pending_unmap) {
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true);
+			mmu->pending_unmap = false;
+		}
+		write_unlock(&vcpu->kvm->mmu_lock);
+	}
+}
@@ -1527,6 +1527,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);

 		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
 		break;
 	case SYS_ID_AA64PFR2_EL1:
 		/* We only expose FPMR */
@@ -1550,7 +1558,8 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
 		break;
 	case SYS_ID_AA64MMFR3_EL1:
-		val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE;
+		val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE |
+			ID_AA64MMFR3_EL1_S1PIE;
 		break;
 	case SYS_ID_MMFR4_EL1:
 		val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
@@ -1985,7 +1994,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 * one cache line.
 	 */
 	if (kvm_has_mte(vcpu->kvm))
-		clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
+		clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);

 	__vcpu_sys_reg(vcpu, r->reg) = clidr;

@@ -2376,7 +2385,19 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 		   ID_AA64PFR0_EL1_RAS |
 		   ID_AA64PFR0_EL1_AdvSIMD |
 		   ID_AA64PFR0_EL1_FP), },
-	ID_SANITISED(ID_AA64PFR1_EL1),
+	ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR |
+				       ID_AA64PFR1_EL1_DF2 |
+				       ID_AA64PFR1_EL1_MTEX |
+				       ID_AA64PFR1_EL1_THE |
+				       ID_AA64PFR1_EL1_GCS |
+				       ID_AA64PFR1_EL1_MTE_frac |
+				       ID_AA64PFR1_EL1_NMI |
+				       ID_AA64PFR1_EL1_RNDR_trap |
+				       ID_AA64PFR1_EL1_SME |
+				       ID_AA64PFR1_EL1_RES0 |
+				       ID_AA64PFR1_EL1_MPAM_frac |
+				       ID_AA64PFR1_EL1_RAS_frac |
+				       ID_AA64PFR1_EL1_MTE)),
 	ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
 	ID_UNALLOCATED(4,3),
 	ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0),
@@ -2390,7 +2411,21 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  .get_user = get_id_reg,
 	  .set_user = set_id_aa64dfr0_el1,
 	  .reset = read_sanitised_id_aa64dfr0_el1,
-	  .val = ID_AA64DFR0_EL1_PMUVer_MASK |
+	/*
+	 * Prior to FEAT_Debugv8.9, the architecture defines context-aware
+	 * breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs).
+	 * KVM does not trap + emulate the breakpoint registers, and as such
+	 * cannot support a layout that misaligns with the underlying hardware.
+	 * While it may be possible to describe a subset that aligns with
+	 * hardware, just prevent changes to BRPs and CTX_CMPs altogether for
+	 * simplicity.
+	 *
+	 * See DDI0487K.a, section D2.8.3 Breakpoint types and linking
+	 * of breakpoints for more details.
+	 */
+	  .val = ID_AA64DFR0_EL1_DoubleLock_MASK |
+		 ID_AA64DFR0_EL1_WRPs_MASK |
+		 ID_AA64DFR0_EL1_PMUVer_MASK |
 		 ID_AA64DFR0_EL1_DebugVer_MASK, },
 	ID_SANITISED(ID_AA64DFR1_EL1),
 	ID_UNALLOCATED(5,2),
@@ -2433,6 +2468,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 					ID_AA64MMFR2_EL1_NV |
 					ID_AA64MMFR2_EL1_CCIDX)),
 	ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX	|
+				       ID_AA64MMFR3_EL1_S1PIE   |
 				       ID_AA64MMFR3_EL1_S1POE)),
 	ID_SANITISED(ID_AA64MMFR4_EL1),
 	ID_UNALLOCATED(7,5),
@@ -2903,7 +2939,7 @@ static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	 * Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
 	 * corresponding VMIDs.
 	 */
-	kvm_nested_s2_unmap(vcpu->kvm);
+	kvm_nested_s2_unmap(vcpu->kvm, true);

 	write_unlock(&vcpu->kvm->mmu_lock);

@@ -2955,7 +2991,30 @@ union tlbi_info {
 static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
 			       const union tlbi_info *info)
 {
-	kvm_stage2_unmap_range(mmu, info->range.start, info->range.size);
+	/*
+	 * The unmap operation is allowed to drop the MMU lock and block, which
+	 * means that @mmu could be used for a different context than the one
+	 * currently being invalidated.
+	 *
+	 * This behavior is still safe, as:
+	 *
+	 *  1) The vCPU(s) that recycled the MMU are responsible for invalidating
+	 *     the entire MMU before reusing it, which still honors the intent
+	 *     of a TLBI.
+	 *
+	 *  2) Until the guest TLBI instruction is 'retired' (i.e. increment PC
+	 *     and ERET to the guest), other vCPUs are allowed to use stale
+	 *     translations.
+	 *
+	 *  3) Accidentally unmapping an unrelated MMU context is nonfatal, and
+	 *     at worst may cause more aborts for shadow stage-2 fills.
+	 *
+	 * Dropping the MMU lock also implies that shadow stage-2 fills could
+	 * happen behind the back of the TLBI. This is still safe, though, as
+	 * the L1 needs to put its stage-2 in a consistent state before doing
+	 * the TLBI.
+	 */
+	kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
 }

 static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -3050,7 +3109,11 @@ static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
 	max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
 	base_addr &= ~(max_size - 1);

-	kvm_stage2_unmap_range(mmu, base_addr, max_size);
+	/*
+	 * See comment in s2_mmu_unmap_range() for why this is allowed to
+	 * reschedule.
+	 */
+	kvm_stage2_unmap_range(mmu, base_addr, max_size, true);
 }

 static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -417,8 +417,28 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kfree(vgic_cpu->private_irqs);
 	vgic_cpu->private_irqs = NULL;

-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		/*
+		 * If this vCPU is being destroyed because of a failed creation
+		 * then unregister the redistributor to avoid leaving behind a
+		 * dangling pointer to the vCPU struct.
+		 *
+		 * vCPUs that have been successfully created (i.e. added to
+		 * kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as
+		 * this function gets called while holding kvm->arch.config_lock
+		 * in the VM teardown path and would otherwise introduce a lock
+		 * inversion w.r.t. kvm->srcu.
+		 *
+		 * vCPUs that failed creation are torn down outside of the
+		 * kvm->arch.config_lock and do not get unregistered in
+		 * kvm_vgic_destroy(), meaning it is both safe and necessary to
+		 * do so here.
+		 */
+		if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu)
+			vgic_unregister_redist_iodev(vcpu);
+
 		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	}
 }

 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -524,22 +544,31 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	if (ret)
 		goto out;

-	dist->ready = true;
 	dist_base = dist->vgic_dist_base;
 	mutex_unlock(&kvm->arch.config_lock);

 	ret = vgic_register_dist_iodev(kvm, dist_base, type);
-	if (ret)
+	if (ret) {
 		kvm_err("Unable to register VGIC dist MMIO regions\n");
+		goto out_slots;
+	}

+	/*
+	 * kvm_io_bus_register_dev() guarantees all readers see the new MMIO
+	 * registration before returning through synchronize_srcu(), which also
+	 * implies a full memory barrier. As such, marking the distributor as
+	 * 'ready' here is guaranteed to be ordered after all vCPUs having seen
+	 * a completely configured distributor.
+	 */
+	dist->ready = true;
 	goto out_slots;
 out:
 	mutex_unlock(&kvm->arch.config_lock);
 out_slots:
-	mutex_unlock(&kvm->slots_lock);
-
 	if (ret)
-		kvm_vgic_destroy(kvm);
+		kvm_vm_dead(kvm);
+
+	mutex_unlock(&kvm->slots_lock);

 	return ret;
 }
@@ -236,7 +236,12 @@ static int vgic_set_common_attr(struct kvm_device *dev,

 		mutex_lock(&dev->kvm->arch.config_lock);

-		if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
+		/*
+		 * Either userspace has already configured NR_IRQS or
+		 * the vgic has already been initialized and vgic_init()
+		 * supplied a default amount of SPIs.
+		 */
+		if (dev->kvm->arch.vgic.nr_spis)
 			ret = -EBUSY;
 		else
 			dev->kvm->arch.vgic.nr_spis =
@@ -2220,7 +2220,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 	emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);

 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+		/* for the first pass, assume the worst case */
+		if (!ctx->image)
+			ctx->idx += 4;
+		else
+			emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
 		emit_call((const u64)__bpf_tramp_enter, ctx);
 	}

@@ -2264,7 +2268,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,

 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		im->ip_epilogue = ctx->ro_image + ctx->idx;
-		emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+		/* for the first pass, assume the worst case */
+		if (!ctx->image)
+			ctx->idx += 4;
+		else
+			emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
 		emit_call((const u64)__bpf_tramp_exit, ctx);
 	}

@@ -26,6 +26,10 @@ struct loongson_board_info {

 #define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG)

+/*
+ * The "core" of cores_per_node and cores_per_package stands for a
+ * logical core, which means in a SMT system it stands for a thread.
+ */
 struct loongson_system_configuration {
 	int nr_cpus;
 	int nr_nodes;
@@ -16,7 +16,7 @@
 #define XRANGE_SHIFT (48)

 /* Valid address length */
-#define XRANGE_SHADOW_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
+#define XRANGE_SHADOW_SHIFT	min(cpu_vabits, VA_BITS)
 /* Used for taking out the valid address */
 #define XRANGE_SHADOW_MASK	GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0)
 /* One segment whole address space size */
@@ -250,7 +250,7 @@
 #define  CSR_ESTAT_IS_WIDTH		15
 #define  CSR_ESTAT_IS			(_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT)

-#define LOONGARCH_CSR_ERA		0x6	/* ERA */
+#define LOONGARCH_CSR_ERA		0x6	/* Exception return address */

 #define LOONGARCH_CSR_BADV		0x7	/* Bad virtual address */

@@ -10,6 +10,7 @@

 #define __HAVE_ARCH_PMD_ALLOC_ONE
 #define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
 #include <asm-generic/pgalloc.h>

 static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -44,6 +45,16 @@ extern void pagetable_init(void);

 extern pgd_t *pgd_alloc(struct mm_struct *mm);

+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+	pte_t *pte = __pte_alloc_one_kernel(mm);
+
+	if (pte)
+		kernel_pte_init(pte);
+
+	return pte;
+}
+
 #define __pte_free_tlb(tlb, pte, address)			\
 do {								\
 	pagetable_pte_dtor(page_ptdesc(pte));			\
@@ -269,6 +269,7 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm
 extern void pgd_init(void *addr);
 extern void pud_init(void *addr);
 extern void pmd_init(void *addr);
+extern void kernel_pte_init(void *addr);

 /*
 * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
@@ -325,39 +326,17 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
 	WRITE_ONCE(*ptep, pteval);

-	if (pte_val(pteval) & _PAGE_GLOBAL) {
-		pte_t *buddy = ptep_buddy(ptep);
-		/*
-		 * Make sure the buddy is global too (if it's !none,
-		 * it better already be global)
-		 */
-		if (pte_none(ptep_get(buddy))) {
 #ifdef CONFIG_SMP
-			/*
-			 * For SMP, multiple CPUs can race, so we need
-			 * to do this atomically.
-			 */
-			__asm__ __volatile__(
-			__AMOR "$zero, %[global], %[buddy] \n"
-			: [buddy] "+ZB" (buddy->pte)
-			: [global] "r" (_PAGE_GLOBAL)
-			: "memory");
-
-			DBAR(0b11000); /* o_wrw = 0b11000 */
-#else /* !CONFIG_SMP */
-			WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
-#endif /* CONFIG_SMP */
-		}
-	}
+	if (pte_val(pteval) & _PAGE_GLOBAL)
+		DBAR(0b11000); /* o_wrw = 0b11000 */
+#endif
 }

 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	/* Preserve global status for the pair */
-	if (pte_val(ptep_get(ptep_buddy(ptep))) & _PAGE_GLOBAL)
-		set_pte(ptep, __pte(_PAGE_GLOBAL));
-	else
-		set_pte(ptep, __pte(0));
+	pte_t pte = ptep_get(ptep);
+	pte_val(pte) &= _PAGE_GLOBAL;
+	set_pte(ptep, pte);
 }

 #define PGD_T_LOG2	(__builtin_ffs(sizeof(pgd_t)) - 1)
@@ -293,13 +293,15 @@ unsigned long stack_top(void)
 {
 	unsigned long top = TASK_SIZE & PAGE_MASK;

-	/* Space for the VDSO & data page */
-	top -= PAGE_ALIGN(current->thread.vdso->size);
-	top -= VVAR_SIZE;
+	if (current->thread.vdso) {
+		/* Space for the VDSO & data page */
+		top -= PAGE_ALIGN(current->thread.vdso->size);
+		top -= VVAR_SIZE;

-	/* Space to randomize the VDSO base */
-	if (current->flags & PF_RANDOMIZE)
-		top -= VDSO_RANDOMIZE_SIZE;
+		/* Space to randomize the VDSO base */
+		if (current->flags & PF_RANDOMIZE)
+			top -= VDSO_RANDOMIZE_SIZE;
+	}

 	return top;
 }
@@ -55,6 +55,7 @@
 #define SMBIOS_FREQHIGH_OFFSET		0x17
 #define SMBIOS_FREQLOW_MASK		0xFF
 #define SMBIOS_CORE_PACKAGE_OFFSET	0x23
+#define SMBIOS_THREAD_PACKAGE_OFFSET	0x25
 #define LOONGSON_EFI_ENABLE		(1 << 3)

 unsigned long fw_arg0, fw_arg1, fw_arg2;
@@ -125,7 +126,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm)
 	cpu_clock_freq = freq_temp * 1000000;

 	loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]);
-	loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET);
+	loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET);

 	pr_info("CpuClock = %llu\n", cpu_clock_freq);
 }
@@ -555,6 +555,9 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
 #else
 	unsigned int *pc;

+	if (regs->csr_prmd & CSR_PRMD_PIE)
+		local_irq_enable();
+
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);

 	/*
@@ -579,6 +582,8 @@ sigbus:
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 out:
+	if (regs->csr_prmd & CSR_PRMD_PIE)
+		local_irq_disable();
 #endif
 	irqentry_exit(regs, state);
 }
@@ -34,7 +34,6 @@ static union {
 	struct loongarch_vdso_data vdata;
 } loongarch_vdso_data __page_aligned_data;

-static struct page *vdso_pages[] = { NULL };
 struct vdso_data *vdso_data = generic_vdso_data.data;
 struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata;
 struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data;
@@ -85,10 +84,8 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,

 struct loongarch_vdso_info vdso_info = {
 	.vdso = vdso_start,
-	.size = PAGE_SIZE,
 	.code_mapping = {
 		.name = "[vdso]",
-		.pages = vdso_pages,
 		.mremap = vdso_mremap,
 	},
 	.data_mapping = {
@@ -103,11 +100,14 @@ static int __init init_vdso(void)
 	unsigned long i, cpu, pfn;

 	BUG_ON(!PAGE_ALIGNED(vdso_info.vdso));
-	BUG_ON(!PAGE_ALIGNED(vdso_info.size));

 	for_each_possible_cpu(cpu)
 		vdso_pdata[cpu].node = cpu_to_node(cpu);

+	vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start);
+	vdso_info.code_mapping.pages =
+		kcalloc(vdso_info.size / PAGE_SIZE, sizeof(struct page *), GFP_KERNEL);
+
 	pfn = __phys_to_pfn(__pa_symbol(vdso_info.vdso));
 	for (i = 0; i < vdso_info.size / PAGE_SIZE; i++)
 		vdso_info.code_mapping.pages[i] = pfn_to_page(pfn + i);
@@ -161,10 +161,11 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_is_blocking(vcpu)) {

 		/*
-		 * HRTIMER_MODE_PINNED is suggested since vcpu may run in
-		 * the same physical cpu in next time
+		 * HRTIMER_MODE_PINNED_HARD is suggested since vcpu may run in
+		 * the same physical cpu in next time, and the timer should run
+		 * in hardirq context even in the PREEMPT_RT case.
 		 */
-		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
+		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED_HARD);
 	}
 }

@@ -1457,7 +1457,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.vpid = 0;
 	vcpu->arch.flush_gpa = INVALID_GPA;

-	hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
 	vcpu->arch.swtimer.function = kvm_swtimer_wakeup;

 	vcpu->arch.handle_exit = kvm_handle_exit;
@@ -201,7 +201,9 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pte)
 			panic("%s: Failed to allocate memory\n", __func__);
+
 		pmd_populate_kernel(&init_mm, pmd, pte);
+		kernel_pte_init(pte);
 	}

 	return pte_offset_kernel(pmd, addr);
@@ -116,6 +116,26 @@ void pud_init(void *addr)
 EXPORT_SYMBOL_GPL(pud_init);
 #endif

+void kernel_pte_init(void *addr)
+{
+	unsigned long *p, *end;
+
+	p = (unsigned long *)addr;
+	end = p + PTRS_PER_PTE;
+
+	do {
+		p[0] = _PAGE_GLOBAL;
+		p[1] = _PAGE_GLOBAL;
+		p[2] = _PAGE_GLOBAL;
+		p[3] = _PAGE_GLOBAL;
+		p[4] = _PAGE_GLOBAL;
+		p += 8;
+		p[-3] = _PAGE_GLOBAL;
+		p[-2] = _PAGE_GLOBAL;
+		p[-1] = _PAGE_GLOBAL;
+	} while (p != end);
+}
+
 pmd_t mk_pmd(struct page *page, pgprot_t prot)
 {
 	pmd_t pmd;
@@ -55,7 +55,7 @@ struct imsic {
 	/* IMSIC SW-file */
 	struct imsic_mrif *swfile;
 	phys_addr_t swfile_pa;
-	spinlock_t swfile_extirq_lock;
+	raw_spinlock_t swfile_extirq_lock;
 };

 #define imsic_vs_csr_read(__c)			\
@@ -622,7 +622,7 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
 	 * interruptions between reading topei and updating pending status.
 	 */

-	spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
+	raw_spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);

 	if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) &&
 	    imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis))
@@ -630,7 +630,7 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
 	else
 		kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);

-	spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
+	raw_spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
 }

 static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear,
@@ -1051,7 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
 	}
 	imsic->swfile = page_to_virt(swfile_page);
 	imsic->swfile_pa = page_to_phys(swfile_page);
-	spin_lock_init(&imsic->swfile_extirq_lock);
+	raw_spin_lock_init(&imsic->swfile_extirq_lock);

 	/* Setup IO device */
 	kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);
@@ -2257,6 +2257,7 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING
 config ADDRESS_MASKING
 	bool "Linear Address Masking support"
 	depends on X86_64
+	depends on COMPILE_TEST || !CPU_MITIGATIONS # wait for LASS
 	help
 	  Linear Address Masking (LAM) modifies the checking that is applied
 	  to 64-bit linear addresses, allowing software to use of the
@@ -6,7 +6,7 @@
 	typeof(sym) __ret;					\
 	asm_inline("mov %1,%0\n1:\n"				\
 		".pushsection runtime_ptr_" #sym ",\"a\"\n\t"	\
-		".long 1b - %c2 - .\n\t"			\
+		".long 1b - %c2 - .\n"				\
 		".popsection"					\
 		:"=r" (__ret)					\
 		:"i" ((unsigned long)0x0123456789abcdefull),	\
@@ -20,7 +20,7 @@
 	typeof(0u+(val)) __ret = (val);				\
 	asm_inline("shrl $12,%k0\n1:\n"				\
 		".pushsection runtime_shift_" #sym ",\"a\"\n\t"	\
-		".long 1b - 1 - .\n\t"				\
+		".long 1b - 1 - .\n"				\
 		".popsection"					\
 		:"+r" (__ret));					\
 	__ret; })
@@ -12,6 +12,13 @@
 #include <asm/cpufeatures.h>
 #include <asm/page.h>
 #include <asm/percpu.h>
+#include <asm/runtime-const.h>
+
+/*
+ * Virtual variable: there's no actual backing store for this,
+ * it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)'
+ */
+extern unsigned long USER_PTR_MAX;

 #ifdef CONFIG_ADDRESS_MASKING
 /*
@@ -46,19 +53,24 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,

 #endif

-/*
- * The virtual address space space is logically divided into a kernel
- * half and a user half.  When cast to a signed type, user pointers
- * are positive and kernel pointers are negative.
- */
-#define valid_user_address(x) ((__force long)(x) >= 0)
+#define valid_user_address(x) \
+	((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))

 /*
 * Masking the user address is an alternative to a conditional
 * user_access_begin that can avoid the fencing. This only works
 * for dense accesses starting at the address.
 */
-#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63)))
+static inline void __user *mask_user_address(const void __user *ptr)
+{
+	unsigned long mask;
+	asm("cmp %1,%0\n\t"
+	    "sbb %0,%0"
+		:"=r" (mask)
+		:"r" (ptr),
+		 "0" (runtime_const_ptr(USER_PTR_MAX)));
+	return (__force void __user *)(mask | (__force unsigned long)ptr);
+}
 #define masked_user_access_begin(x) ({				\
 	__auto_type __masked_ptr = (x);				\
 	__masked_ptr = mask_user_address(__masked_ptr);		\
@@ -69,23 +81,16 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
 * arbitrary values in those bits rather then masking them off.
 *
 * Enforce two rules:
- * 1. 'ptr' must be in the user half of the address space
+ * 1. 'ptr' must be in the user part of the address space
 * 2. 'ptr+size' must not overflow into kernel addresses
 *
- * Note that addresses around the sign change are not valid addresses,
- * and will GP-fault even with LAM enabled if the sign bit is set (see
- * "CR3.LAM_SUP" that can narrow the canonicality check if we ever
- * enable it, but not remove it entirely).
- *
- * So the "overflow into kernel addresses" does not imply some sudden
- * exact boundary at the sign bit, and we can allow a lot of slop on the
- * size check.
+ * Note that we always have at least one guard page between the
+ * max user address and the non-canonical gap, allowing us to
+ * ignore small sizes entirely.
 *
 * In fact, we could probably remove the size check entirely, since
 * any kernel accesses will be in increasing address order starting
- * at 'ptr', and even if the end might be in kernel space, we'll
- * hit the GP faults for non-canonical accesses before we ever get
- * there.
+ * at 'ptr'.
 *
 * That's a separate optimization, for now just handle the small
 * constant case.
@@ -69,6 +69,7 @@
 #include <asm/sev.h>
 #include <asm/tdx.h>
 #include <asm/posted_intr.h>
+#include <asm/runtime-const.h>

 #include "cpu.h"

@@ -2389,6 +2390,15 @@ void __init arch_cpu_finalize_init(void)
 	alternative_instructions();

 	if (IS_ENABLED(CONFIG_X86_64)) {
+		unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1;
+
+		/*
+		 * Enable this when LAM is gated on LASS support
+		if (cpu_feature_enabled(X86_FEATURE_LAM))
+			USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1;
+		 */
+		runtime_const_init(ptr, USER_PTR_MAX);
+
 		/*
 		 * Make sure the first 2MB area is not mapped by huge pages
 		 * There are typically fixed size MTRRs in there and overlapping
@@ -584,7 +584,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }

-static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
+static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);

 static int __init save_microcode_in_initrd(void)
 {
@@ -605,7 +605,7 @@ static int __init save_microcode_in_initrd(void)
 	if (!desc.mc)
 		return -EINVAL;

-	ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
 	if (ret > UCODE_UPDATED)
 		return -EINVAL;

@@ -613,16 +613,19 @@ static int __init save_microcode_in_initrd(void)
 }
 early_initcall(save_microcode_in_initrd);

-static inline bool patch_cpus_equivalent(struct ucode_patch *p, struct ucode_patch *n)
+static inline bool patch_cpus_equivalent(struct ucode_patch *p,
+					 struct ucode_patch *n,
+					 bool ignore_stepping)
 {
 	/* Zen and newer hardcode the f/m/s in the patch ID */
        if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
 		union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id);
 		union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id);

-		/* Zap stepping */
-		p_cid.stepping = 0;
-		n_cid.stepping = 0;
+		if (ignore_stepping) {
+			p_cid.stepping = 0;
+			n_cid.stepping = 0;
+		}

 		return p_cid.full == n_cid.full;
 	} else {
@@ -644,13 +647,13 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi
 	WARN_ON_ONCE(!n.patch_id);

 	list_for_each_entry(p, &microcode_cache, plist)
-		if (patch_cpus_equivalent(p, &n))
+		if (patch_cpus_equivalent(p, &n, false))
 			return p;

 	return NULL;
 }

-static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
+static inline int patch_newer(struct ucode_patch *p, struct ucode_patch *n)
 {
 	/* Zen and newer hardcode the f/m/s in the patch ID */
        if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
@@ -659,6 +662,9 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
 		zp.ucode_rev = p->patch_id;
 		zn.ucode_rev = n->patch_id;

+		if (zn.stepping != zp.stepping)
+			return -1;
+
 		return zn.rev > zp.rev;
 	} else {
 		return n->patch_id > p->patch_id;
@@ -668,10 +674,14 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
 static void update_cache(struct ucode_patch *new_patch)
 {
 	struct ucode_patch *p;
+	int ret;

 	list_for_each_entry(p, &microcode_cache, plist) {
-		if (patch_cpus_equivalent(p, new_patch)) {
-			if (!patch_newer(p, new_patch)) {
+		if (patch_cpus_equivalent(p, new_patch, true)) {
+			ret = patch_newer(p, new_patch);
+			if (ret < 0)
+				continue;
+			else if (!ret) {
 				/* we already have the latest patch */
 				kfree(new_patch->data);
 				kfree(new_patch);
@@ -944,6 +954,20 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 	return UCODE_OK;
 }

+static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size)
+{
+	enum ucode_state ret;
+
+	/* free old equiv table */
+	free_equiv_cpu_table();
+
+	ret = __load_microcode_amd(family, data, size);
+	if (ret != UCODE_OK)
+		cleanup();
+
+	return ret;
+}
+
 static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
 	struct cpuinfo_x86 *c;
@@ -951,14 +975,9 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	struct ucode_patch *p;
 	enum ucode_state ret;

-	/* free old equiv table */
-	free_equiv_cpu_table();
-
-	ret = __load_microcode_amd(family, data, size);
-	if (ret != UCODE_OK) {
-		cleanup();
+	ret = _load_microcode_amd(family, data, size);
+	if (ret != UCODE_OK)
 		return ret;
-	}

 	for_each_node(nid) {
 		cpu = cpumask_first(cpumask_of_node(nid));
@@ -37,6 +37,7 @@
 #include <asm/apic.h>
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
+#include <asm/mtrr.h>
 #include <asm/tlb.h>
 #include <asm/cpuidle_haltpoll.h>
 #include <asm/ptrace.h>
@@ -980,6 +981,9 @@ static void __init kvm_init_platform(void)
 	}
 	kvmclock_init();
 	x86_platform.apic_post_init = kvm_apic_init;
+
+	/* Set WB as the default cache mode for SEV-SNP and TDX */
+	mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
 }

 #if defined(CONFIG_AMD_MEM_ENCRYPT)
@@ -358,6 +358,7 @@ SECTIONS
 #endif

 	RUNTIME_CONST_VARIABLES
+	RUNTIME_CONST(ptr, USER_PTR_MAX)

 	. = ALIGN(PAGE_SIZE);

@@ -1556,6 +1556,17 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	bool flush = false;

+	/*
+	 * To prevent races with vCPUs faulting in a gfn using stale data,
+	 * zapping a gfn range must be protected by mmu_invalidate_in_progress
+	 * (and mmu_invalidate_seq).  The only exception is memslot deletion;
+	 * in that case, SRCU synchronization ensures that SPTEs are zapped
+	 * after all vCPUs have unlocked SRCU, guaranteeing that vCPUs see the
+	 * invalid slot.
+	 */
+	lockdep_assert_once(kvm->mmu_invalidate_in_progress ||
+			    lockdep_is_held(&kvm->slots_lock));
+
 	if (kvm_memslots_have_rmaps(kvm))
 		flush = __kvm_rmap_zap_gfn_range(kvm, range->slot,
 						 range->start, range->end,
@@ -1884,14 +1895,10 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp)
 		if (is_obsolete_sp((_kvm), (_sp))) {			\
 		} else

-#define for_each_gfn_valid_sp(_kvm, _sp, _gfn)				\
+#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn)		\
 	for_each_valid_sp(_kvm, _sp,					\
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)])	\
-		if ((_sp)->gfn != (_gfn)) {} else
-
-#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn)		\
-	for_each_gfn_valid_sp(_kvm, _sp, _gfn)				\
-		if (!sp_has_gptes(_sp)) {} else
+		if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else

 static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -7063,15 +7070,15 @@ static void kvm_mmu_zap_memslot_pages_and_flush(struct kvm *kvm,

 	/*
 	 * Since accounting information is stored in struct kvm_arch_memory_slot,
-	 * shadow pages deletion (e.g. unaccount_shadowed()) requires that all
-	 * gfns with a shadow page have a corresponding memslot.  Do so before
-	 * the memslot goes away.
+	 * all MMU pages that are shadowing guest PTEs must be zapped before the
+	 * memslot is deleted, as freeing such pages after the memslot is freed
+	 * will result in use-after-free, e.g. in unaccount_shadowed().
 	 */
 	for (i = 0; i < slot->npages; i++) {
 		struct kvm_mmu_page *sp;
 		gfn_t gfn = slot->base_gfn + i;

-		for_each_gfn_valid_sp(kvm, sp, gfn)
+		for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn)
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);

 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
@@ -63,8 +63,12 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
 	u64 pdpte;
 	int ret;

+	/*
+	 * Note, nCR3 is "assumed" to be 32-byte aligned, i.e. the CPU ignores
+	 * nCR3[4:0] when loading PDPTEs from memory.
+	 */
 	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
-				       offset_in_page(cr3) + index * 8, 8);
+				       (cr3 & GENMASK(11, 5)) + index * 8, 8);
 	if (ret)
 		return 0;
 	return pdpte;
@@ -4888,9 +4888,6 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx->hv_deadline_tsc = -1;
 	kvm_set_cr8(vcpu, 0);

-	vmx_segment_cache_clear(vmx);
-	kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS);
-
 	seg_setup(VCPU_SREG_CS);
 	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
 	vmcs_writel(GUEST_CS_BASE, 0xffff0000ul);
@@ -4917,6 +4914,9 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmcs_writel(GUEST_IDTR_BASE, 0);
 	vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);

+	vmx_segment_cache_clear(vmx);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS);
+
 	vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
 	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
 	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0);
@@ -39,8 +39,13 @@

 .macro check_range size:req
 .if IS_ENABLED(CONFIG_X86_64)
-	mov %rax, %rdx
-	sar $63, %rdx
+	movq $0x0123456789abcdef,%rdx
+  1:
+  .pushsection runtime_ptr_USER_PTR_MAX,"a"
+	.long 1b - 8 - .
+  .popsection
+	cmp %rax, %rdx
+	sbb %rdx, %rdx
 	or %rdx, %rax
 .else
 	cmp $TASK_SIZE_MAX-\size+1, %eax
@@ -173,6 +173,8 @@ static void __init __snp_fixup_e820_tables(u64 pa)
 		e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		if (!memblock_is_region_reserved(pa, PMD_SIZE))
+			memblock_reserve(pa, PMD_SIZE);
 	}
 }

@@ -600,9 +600,7 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
 		if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len)
 			goto put_bio;
 		if (bytes + bv->bv_len > nr_iter)
-			goto put_bio;
-		if (bv->bv_offset + bv->bv_len > PAGE_SIZE)
-			goto put_bio;
+			break;

 		nsegs++;
 		bytes += bv->bv_len;
@@ -130,6 +130,17 @@ static const struct dmi_system_id dmi_lid_quirks[] = {
 		},
 		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
 	},
+	{
+		/*
+		 * Samsung galaxybook2 ,initial _LID device notification returns
+		 * lid closed.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "750XED"),
+		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+	},
 	{}
 };

@@ -1916,9 +1916,15 @@ unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf)
 	u64 mul, div;

 	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_freq - caps->lowest_freq;
+		/* Avoid special case when nominal_freq is equal to lowest_freq */
+		if (caps->lowest_freq == caps->nominal_freq) {
+			mul = caps->nominal_freq;
+			div = caps->nominal_perf;
+		} else {
+			mul = caps->nominal_freq - caps->lowest_freq;
+			div = caps->nominal_perf - caps->lowest_perf;
+		}
 		mul *= KHZ_PER_MHZ;
-		div = caps->nominal_perf - caps->lowest_perf;
 		offset = caps->nominal_freq * KHZ_PER_MHZ -
 			 div64_u64(caps->nominal_perf * mul, div);
 	} else {
@@ -1939,11 +1945,17 @@ unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq)
 {
 	s64 retval, offset = 0;
 	static u64 max_khz;
-	u64  mul, div;
+	u64 mul, div;

 	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_perf - caps->lowest_perf;
-		div = caps->nominal_freq - caps->lowest_freq;
+		/* Avoid special case when nominal_freq is equal to lowest_freq */
+		if (caps->lowest_freq == caps->nominal_freq) {
+			mul = caps->nominal_perf;
+			div = caps->nominal_freq;
+		} else {
+			mul = caps->nominal_perf - caps->lowest_perf;
+			div = caps->nominal_freq - caps->lowest_freq;
+		}
 		/*
 		 * We don't need to convert to kHz for computing offset and can
 		 * directly use nominal_freq and lowest_freq as the div64_u64
@@ -52,7 +52,7 @@ struct prm_context_buffer {
 static LIST_HEAD(prm_module_list);

 struct prm_handler_info {
-	guid_t guid;
+	efi_guid_t guid;
 	efi_status_t (__efiapi *handler_addr)(u64, void *);
 	u64 static_data_buffer_addr;
 	u64 acpi_param_buffer_addr;
@@ -72,17 +72,21 @@ struct prm_module_info {
 	struct prm_handler_info handlers[] __counted_by(handler_count);
 };

-static u64 efi_pa_va_lookup(u64 pa)
+static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa)
 {
 	efi_memory_desc_t *md;
 	u64 pa_offset = pa & ~PAGE_MASK;
 	u64 page = pa & PAGE_MASK;

 	for_each_efi_memory_desc(md) {
-		if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)
+		if ((md->attribute & EFI_MEMORY_RUNTIME) &&
+		    (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)) {
 			return pa_offset + md->virt_addr + page - md->phys_addr;
+		}
 	}

+	pr_warn("Failed to find VA for GUID: %pUL, PA: 0x%llx", guid, pa);
+
 	return 0;
 }

@@ -148,9 +152,15 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end)
 		th = &tm->handlers[cur_handler];

 		guid_copy(&th->guid, (guid_t *)handler_info->handler_guid);
-		th->handler_addr = (void *)efi_pa_va_lookup(handler_info->handler_address);
-		th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address);
-		th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address);
+		th->handler_addr =
+			(void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address);
+
+		th->static_data_buffer_addr =
+			efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address);
+
+		th->acpi_param_buffer_addr =
+			efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address);
+
 	} while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info)));

 	return 0;
@@ -277,6 +287,13 @@ static acpi_status acpi_platformrt_space_handler(u32 function,
 		if (!handler || !module)
 			goto invalid_guid;

+		if (!handler->handler_addr ||
+		    !handler->static_data_buffer_addr ||
+		    !handler->acpi_param_buffer_addr) {
+			buffer->prm_status = PRM_HANDLER_ERROR;
+			return AE_OK;
+		}
+
 		ACPI_COPY_NAMESEG(context.signature, "PRMC");
 		context.revision = 0x0;
 		context.reserved = 0x0;
@@ -503,6 +503,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "17U70P"),
 		},
 	},
+	{
+		/* LG Electronics 16T90SP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+			DMI_MATCH(DMI_BOARD_NAME, "16T90SP"),
+		},
+	},
 	{ }
 };

@@ -651,6 +651,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 			/* the scmd has an associated qc */
 			if (!(qc->flags & ATA_QCFLAG_EH)) {
 				/* which hasn't failed yet, timeout */
+				set_host_byte(scmd, DID_TIME_OUT);
 				qc->err_mask |= AC_ERR_TIMEOUT;
 				qc->flags |= ATA_QCFLAG_EH;
 				nr_timedout++;
@@ -204,7 +204,7 @@ static struct fw_node *build_tree(struct fw_card *card, const u32 *sid, int self
 				// the node->ports array where the parent node should be.  Later,
 				// when we handle the parent node, we fix up the reference.
 				++parent_count;
-				node->color = i;
+				node->color = port_index;
 				break;

 			case PHY_PACKET_SELF_ID_PORT_STATUS_CHILD:
@@ -147,6 +147,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
 					   struct acpi_buffer *params)
 {
 	acpi_status status;
+	union acpi_object *obj;
 	union acpi_object atif_arg_elements[2];
 	struct acpi_object_list atif_arg;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -169,16 +170,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,

 	status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
 				      &buffer);
+	obj = (union acpi_object *)buffer.pointer;

-	/* Fail only if calling the method fails and ATIF is supported */
+	/* Fail if calling the method fails and ATIF is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
 		DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
 				 acpi_format_exception(status));
-		kfree(buffer.pointer);
+		kfree(obj);
 		return NULL;
 	}

-	return buffer.pointer;
+	if (obj->type != ACPI_TYPE_BUFFER) {
+		DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n",
+				 obj->type);
+		kfree(obj);
+		return NULL;
+	}
+
+	return obj;
 }

 /**
@@ -51,6 +51,12 @@ MODULE_FIRMWARE("amdgpu/sdma_7_0_1.bin");
 #define SDMA0_HYP_DEC_REG_END 0x589a
 #define SDMA1_HYP_DEC_REG_OFFSET 0x20

+/*define for compression field for sdma7*/
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_offset 0
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask   0x00000001
+#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift  16
+#define SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(x) (((x) & SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask) << SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift)
+
 static const struct amdgpu_hwip_reg_entry sdma_reg_list_7_0[] = {
 	SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS_REG),
 	SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS1_REG),
@@ -1724,7 +1730,8 @@ static void sdma_v7_0_emit_fill_buffer(struct amdgpu_ib *ib,
 				       uint64_t dst_offset,
 				       uint32_t byte_count)
 {
-	ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_CONST_FILL);
+	ib->ptr[ib->length_dw++] = SDMA_PKT_CONSTANT_FILL_HEADER_OP(SDMA_OP_CONST_FILL) |
+		SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(1);
 	ib->ptr[ib->length_dw++] = lower_32_bits(dst_offset);
 	ib->ptr[ib->length_dw++] = upper_32_bits(dst_offset);
 	ib->ptr[ib->length_dw++] = src_data;
@@ -8374,7 +8374,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
 		if (amdgpu_ip_version(adev, DCE_HWIP, 0) <
 		    IP_VERSION(3, 5, 0) ||
 		    acrtc_state->stream->link->psr_settings.psr_version <
-		    DC_PSR_VERSION_UNSUPPORTED) {
+		    DC_PSR_VERSION_UNSUPPORTED ||
+		    !(adev->flags & AMD_IS_APU)) {
 			timing = &acrtc_state->stream->timing;

 			/* at least 2 frames */
@@ -44,6 +44,7 @@

 #include "dm_helpers.h"
 #include "ddc_service_types.h"
+#include "clk_mgr.h"

 static u32 edid_extract_panel_id(struct edid *edid)
 {
@@ -1121,6 +1122,8 @@ bool dm_helpers_dp_handle_test_pattern_request(
 	struct pipe_ctx *pipe_ctx = NULL;
 	struct amdgpu_dm_connector *aconnector = link->priv;
 	struct drm_device *dev = aconnector->base.dev;
+	struct dc_state *dc_state = ctx->dc->current_state;
+	struct clk_mgr *clk_mgr = ctx->dc->clk_mgr;
 	int i;

 	for (i = 0; i < MAX_PIPES; i++) {
@@ -1221,6 +1224,16 @@ bool dm_helpers_dp_handle_test_pattern_request(
 	pipe_ctx->stream->test_pattern.type = test_pattern;
 	pipe_ctx->stream->test_pattern.color_space = test_pattern_color_space;

+	/* Temp W/A for compliance test failure */
+	dc_state->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+	dc_state->bw_ctx.bw.dcn.clk.dramclk_khz = clk_mgr->dc_mode_softmax_enabled ?
+		clk_mgr->bw_params->dc_mode_softmax_memclk : clk_mgr->bw_params->max_memclk_mhz;
+	dc_state->bw_ctx.bw.dcn.clk.idle_dramclk_khz = dc_state->bw_ctx.bw.dcn.clk.dramclk_khz;
+	ctx->dc->clk_mgr->funcs->update_clocks(
+			ctx->dc->clk_mgr,
+			dc_state,
+			false);
+
 	dc_link_dp_set_test_pattern(
 		(struct dc_link *) link,
 		test_pattern,
@@ -841,6 +841,8 @@ bool is_psr_su_specific_panel(struct dc_link *link)
 				isPSRSUSupported = false;
 			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
 				isPSRSUSupported = false;
+			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01)
+				isPSRSUSupported = false;
 			else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
 				isPSRSUSupported = true;
 		}
@@ -1234,6 +1234,14 @@ static void smu_init_xgmi_plpd_mode(struct smu_context *smu)
 	}
 }

+static bool smu_is_workload_profile_available(struct smu_context *smu,
+					      u32 profile)
+{
+	if (profile >= PP_SMC_POWER_PROFILE_COUNT)
+		return false;
+	return smu->workload_map && smu->workload_map[profile].valid_mapping;
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1265,7 +1273,8 @@ static int smu_sw_init(void *handle)
 	smu->workload_prority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
 	smu->workload_prority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;

-	if (smu->is_apu)
+	if (smu->is_apu ||
+	    !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D))
 		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
 	else
 		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
@@ -25,7 +25,7 @@
 #define SMU14_DRIVER_IF_V14_0_H

 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x18
+#define PPTABLE_VERSION 0x1B

 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
@@ -145,7 +145,7 @@ typedef enum {
 } FEATURE_BTC_e;

 // Debug Overrides Bitmask
-#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_FCLK      0x00000001
+#define DEBUG_OVERRIDE_NOT_USE      				   0x00000001
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_DCN_FCLK      0x00000002
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_MP0_FCLK      0x00000004
 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCFCLK    0x00000008
@@ -161,6 +161,7 @@ typedef enum {
 #define DEBUG_OVERRIDE_ENABLE_SOC_VF_BRINGUP_MODE      0x00002000
 #define DEBUG_OVERRIDE_ENABLE_PER_WGP_RESIENCY         0x00004000
 #define DEBUG_OVERRIDE_DISABLE_MEMORY_VOLTAGE_SCALING  0x00008000
+#define DEBUG_OVERRIDE_DFLL_BTC_FCW_LOG                0x00010000

 // VR Mapping Bit Defines
 #define VR_MAPPING_VR_SELECT_MASK  0x01
@@ -391,6 +392,21 @@ typedef struct {
  EccInfo_t  EccInfo[24];
 } EccInfoTable_t;

+#define EPCS_HIGH_POWER                  600
+#define EPCS_NORMAL_POWER                450
+#define EPCS_LOW_POWER                   300
+#define EPCS_SHORTED_POWER               150
+#define EPCS_NO_BOOTUP                   0
+
+typedef enum{
+  EPCS_SHORTED_LIMIT,
+  EPCS_LOW_POWER_LIMIT,
+  EPCS_NORMAL_POWER_LIMIT,
+  EPCS_HIGH_POWER_LIMIT,
+  EPCS_NOT_CONFIGURED,
+  EPCS_STATUS_COUNT,
+} EPCS_STATUS_e;
+
 //D3HOT sequences
 typedef enum {
  BACO_SEQUENCE,
@@ -662,7 +678,7 @@ typedef enum {
 } PP_GRTAVFS_FW_SEP_FUSE_e;

 #define PP_NUM_RTAVFS_PWL_ZONES 5
-
+#define PP_NUM_PSM_DIDT_PWL_ZONES 3

 // VBIOS or PPLIB configures telemetry slope and offset. Only slope expected to be set for SVI3
 // Slope Q1.7, Offset Q1.2
@@ -746,10 +762,10 @@ typedef struct {
  uint16_t               Padding;

  //Frequency changes
-  int16_t                GfxclkFmin;           // MHz
-  int16_t                GfxclkFmax;           // MHz
-  uint16_t               UclkFmin;             // MHz
-  uint16_t               UclkFmax;             // MHz
+  int16_t                GfxclkFoffset;
+  uint16_t               Padding1;
+  uint16_t               UclkFmin;
+  uint16_t               UclkFmax;
  uint16_t               FclkFmin;
  uint16_t               FclkFmax;

@@ -770,19 +786,23 @@ typedef struct {
  uint8_t                MaxOpTemp;

  uint8_t                AdvancedOdModeEnabled;
-  uint8_t                Padding1[3];
+  uint8_t                Padding2[3];

  uint16_t               GfxVoltageFullCtrlMode;
  uint16_t               SocVoltageFullCtrlMode;
  uint16_t               GfxclkFullCtrlMode;
  uint16_t               UclkFullCtrlMode;
  uint16_t               FclkFullCtrlMode;
-  uint16_t               Padding2;
+  uint16_t               Padding3;

  int16_t                GfxEdc;
  int16_t                GfxPccLimitControl;

-  uint32_t               Spare[10];
+  uint16_t               GfxclkFmaxVmax;
+  uint8_t                GfxclkFmaxVmaxTemperature;
+  uint8_t                Padding4[1];
+
+  uint32_t               Spare[9];
  uint32_t               MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround
 } OverDriveTable_t;

@@ -802,8 +822,8 @@ typedef struct {
  uint16_t               VddSocVmax;

  //gfxclk
-  int16_t                GfxclkFmin;           // MHz
-  int16_t                GfxclkFmax;           // MHz
+  int16_t                GfxclkFoffset;
+  uint16_t               Padding;
  //uclk
  uint16_t               UclkFmin;             // MHz
  uint16_t               UclkFmax;             // MHz
@@ -828,7 +848,7 @@ typedef struct {
  uint8_t                FanZeroRpmEnable;
  //temperature
  uint8_t                MaxOpTemp;
-  uint8_t                Padding[2];
+  uint8_t                Padding1[2];

  //Full Ctrl
  uint16_t               GfxVoltageFullCtrlMode;
@@ -839,7 +859,7 @@ typedef struct {
  //EDC
  int16_t                GfxEdc;
  int16_t                GfxPccLimitControl;
-  int16_t                Padding1;
+  int16_t                Padding2;

  uint32_t               Spare[5];
 } OverDriveLimits_t;
@@ -987,8 +1007,9 @@ typedef struct {
  uint16_t BaseClockDc;
  uint16_t GameClockDc;
  uint16_t BoostClockDc;
-
-  uint32_t Reserved[4];
+  uint16_t MaxReportedClock;
+  uint16_t Padding;
+  uint32_t Reserved[3];
 } DriverReportedClocks_t;

 typedef struct {
@@ -1132,7 +1153,7 @@ typedef struct {
  uint32_t      DcModeMaxFreq     [PPCLK_COUNT            ];     // In MHz

  uint16_t      GfxclkAibFmax;
-  uint16_t      GfxclkFreqCap;
+  uint16_t      GfxDpmPadding;

  //GFX Idle Power Settings
  uint16_t      GfxclkFgfxoffEntry;   // Entry in RLC stage (PLL), in Mhz
@@ -1172,8 +1193,7 @@ typedef struct {
  uint32_t        DvoFmaxLowScaler; //Unitless float

  // GFX DCS
-  uint16_t      DcsGfxOffVoltage;     //Voltage in mV(Q2) applied to VDDGFX when entering DCS GFXOFF phase
-  uint16_t      PaddingDcs;
+  uint32_t      PaddingDcs;

  uint16_t      DcsMinGfxOffTime;     //Minimum amount of time PMFW shuts GFX OFF as part of GFX DCS phase
  uint16_t      DcsMaxGfxOffTime;      //Maximum amount of time PMFW can shut GFX OFF as part of GFX DCS phase at a stretch.
@@ -1205,8 +1225,7 @@ typedef struct {
  uint16_t      DalDcModeMaxUclkFreq;
  uint8_t       PaddingsMem[2];
  //FCLK Section
-  uint16_t      FclkDpmDisallowPstateFreq;  //Frequency which FW will target when indicated that display config cannot support P-state. Set to 0 use FW calculated value
-  uint16_t      PaddingFclk;
+  uint32_t      PaddingFclk;

  // Link DPM Settings
  uint8_t       PcieGenSpeed[NUM_LINK_LEVELS];           ///< 0:PciE-gen1 1:PciE-gen2 2:PciE-gen3 3:PciE-gen4 4:PciE-gen5
@@ -1215,12 +1234,19 @@ typedef struct {

  // SECTION: VDD_GFX AVFS
  uint8_t       OverrideGfxAvfsFuses;
-  uint8_t       GfxAvfsPadding[3];
+  uint8_t       GfxAvfsPadding[1];
+  uint16_t      DroopGBStDev;

  uint32_t      SocHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];   //new added for Soc domain
  uint32_t      GfxL2HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //see fusedoc for encoding
  //uint32_t      GfxSeHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
-  uint32_t      spare_HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT];
+
+  uint16_t      PsmDidt_Vcross[PP_NUM_PSM_DIDT_PWL_ZONES-1];
+  uint32_t      PsmDidt_StaticDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_StaticDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_DynDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      PsmDidt_DynDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES];
+  uint32_t      spare_HwRtAvfsFuses[19];

  uint32_t      SocCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
  uint32_t      GfxCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT];
@@ -1246,11 +1272,7 @@ typedef struct {
  uint32_t      dGbV_dT_vmin;
  uint32_t      dGbV_dT_vmax;

-  //Unused: PMFW-9370
-  uint32_t      V2F_vmin_range_low;
-  uint32_t      V2F_vmin_range_high;
-  uint32_t      V2F_vmax_range_low;
-  uint32_t      V2F_vmax_range_high;
+  uint32_t      PaddingV2F[4];

  AvfsDcBtcParams_t DcBtcGfxParams;
  QuadraticInt_t    SSCurve_GFX;
@@ -1327,18 +1349,18 @@ typedef struct {
  uint16_t        PsmDidtReleaseTimer;
  uint32_t        PsmDidtStallPattern; //Will be written to both pattern 1 and didt_static_level_prog
  // CAC EDC
-  uint32_t        Leakage_C0; // in IEEE float
-  uint32_t        Leakage_C1; // in IEEE float
-  uint32_t        Leakage_C2; // in IEEE float
-  uint32_t        Leakage_C3; // in IEEE float
-  uint32_t        Leakage_C4; // in IEEE float
-  uint32_t        Leakage_C5; // in IEEE float
-  uint32_t        GFX_CLK_SCALAR; // in IEEE float
-  uint32_t        GFX_CLK_INTERCEPT; // in IEEE float
-  uint32_t        GFX_CAC_M; // in IEEE float
-  uint32_t        GFX_CAC_B; // in IEEE float
-  uint32_t        VDD_GFX_CurrentLimitGuardband; // in IEEE float
-  uint32_t        DynToTotalCacScalar; // in IEEE
+  uint32_t        CacEdcCacLeakageC0;
+  uint32_t        CacEdcCacLeakageC1;
+  uint32_t        CacEdcCacLeakageC2;
+  uint32_t        CacEdcCacLeakageC3;
+  uint32_t        CacEdcCacLeakageC4;
+  uint32_t        CacEdcCacLeakageC5;
+  uint32_t        CacEdcGfxClkScalar;
+  uint32_t        CacEdcGfxClkIntercept;
+  uint32_t        CacEdcCac_m;
+  uint32_t        CacEdcCac_b;
+  uint32_t        CacEdcCurrLimitGuardband;
+  uint32_t        CacEdcDynToTotalCacRatio;
  // GFX EDC XVMIN
  uint32_t        XVmin_Gfx_EdcThreshScalar;
  uint32_t        XVmin_Gfx_EdcEnableFreq;
@@ -1467,7 +1489,7 @@ typedef struct {
  uint8_t      VddqOffEnabled;
  uint8_t      PaddingUmcFlags[2];

-  uint32_t    PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued
+  uint32_t    Paddign1;
  uint32_t    BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS

  uint8_t     FuseWritePowerMuxPresent;
@@ -1530,7 +1552,7 @@ typedef struct {
  int16_t     FuzzyFan_ErrorSetDelta;
  int16_t     FuzzyFan_ErrorRateSetDelta;
  int16_t     FuzzyFan_PwmSetDelta;
-  uint16_t    FuzzyFan_Reserved;
+  uint16_t    FanPadding2;

  uint16_t    FwCtfLimit[TEMP_COUNT];

@@ -1547,9 +1569,10 @@ typedef struct {
  uint16_t    FanSpare[1];
  uint8_t     FanIntakeSensorSupport;
  uint8_t     FanIntakePadding;
-  uint32_t    FanAmbientPerfBoostThreshold;
  uint32_t    FanSpare2[12];

+  uint32_t ODFeatureCtrlMask;
+
  uint16_t TemperatureLimit_Hynix; // In degrees Celsius. Memory temperature limit associated with Hynix
  uint16_t TemperatureLimit_Micron; // In degrees Celsius. Memory temperature limit associated with Micron
  uint16_t TemperatureFwCtfLimit_Hynix;
@@ -1637,7 +1660,7 @@ typedef struct {
  uint16_t AverageDclk0Frequency  ;
  uint16_t AverageVclk1Frequency  ;
  uint16_t AverageDclk1Frequency  ;
-  uint16_t PCIeBusy               ;
+  uint16_t AveragePCIeBusy        ;
  uint16_t dGPU_W_MAX             ;
  uint16_t padding                ;

@@ -1665,12 +1688,12 @@ typedef struct {

  uint16_t AverageGfxActivity    ;
  uint16_t AverageUclkActivity   ;
-  uint16_t Vcn0ActivityPercentage  ;
+  uint16_t AverageVcn0ActivityPercentage;
  uint16_t Vcn1ActivityPercentage  ;

  uint32_t EnergyAccumulator;
  uint16_t AverageSocketPower;
-  uint16_t MovingAverageTotalBoardPower;
+  uint16_t AverageTotalBoardPower;

  uint16_t AvgTemperature[TEMP_COUNT];
  uint16_t AvgTemperatureFanIntake;
@@ -1684,7 +1707,8 @@ typedef struct {


  uint8_t  ThrottlingPercentage[THROTTLER_COUNT];
-  uint8_t  padding1[3];
+  uint8_t  VmaxThrottlingPercentage;
+  uint8_t  padding1[2];

  //metrics for D3hot entry/exit and driver ARM msgs
  uint32_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT];
@@ -1693,7 +1717,7 @@ typedef struct {

  uint16_t ApuSTAPMSmartShiftLimit;
  uint16_t ApuSTAPMLimit;
-  uint16_t MovingAvgApuSocketPower;
+  uint16_t AvgApuSocketPower;

  uint16_t AverageUclkActivity_MAX;

@@ -1823,6 +1847,17 @@ typedef struct {
 #define TABLE_TRANSFER_FAILED     0xFF
 #define TABLE_TRANSFER_PENDING    0xAB

+#define TABLE_PPT_FAILED                          0x100
+#define TABLE_TDC_FAILED                          0x200
+#define TABLE_TEMP_FAILED                         0x400
+#define TABLE_FAN_TARGET_TEMP_FAILED              0x800
+#define TABLE_FAN_STOP_TEMP_FAILED               0x1000
+#define TABLE_FAN_START_TEMP_FAILED              0x2000
+#define TABLE_FAN_PWM_MIN_FAILED                 0x4000
+#define TABLE_ACOUSTIC_TARGET_RPM_FAILED         0x8000
+#define TABLE_ACOUSTIC_LIMIT_RPM_FAILED         0x10000
+#define TABLE_MGPU_ACOUSTIC_TARGET_RPM_FAILED   0x20000
+
 // Table types
 #define TABLE_PPTABLE            0
 #define TABLE_COMBO_PPTABLE           1
@@ -1849,5 +1884,6 @@ typedef struct {
 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING  0x7
 #define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
 #define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9
+#define IH_INTERRUPT_CONTEXT_ID_DYNAMIC_TABLE       0xA

 #endif
@@ -28,7 +28,7 @@
 #define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6
-#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x26
+#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x2E

 #define FEATURE_MASK(feature) (1ULL << feature)

@@ -1077,12 +1077,9 @@ static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,

 	switch (od_feature_bit) {
 	case PP_OD_FEATURE_GFXCLK_FMIN:
-		od_min_setting = overdrive_lowerlimits->GfxclkFmin;
-		od_max_setting = overdrive_upperlimits->GfxclkFmin;
-		break;
 	case PP_OD_FEATURE_GFXCLK_FMAX:
-		od_min_setting = overdrive_lowerlimits->GfxclkFmax;
-		od_max_setting = overdrive_upperlimits->GfxclkFmax;
+		od_min_setting = overdrive_lowerlimits->GfxclkFoffset;
+		od_max_setting = overdrive_upperlimits->GfxclkFoffset;
 		break;
 	case PP_OD_FEATURE_UCLK_FMIN:
 		od_min_setting = overdrive_lowerlimits->UclkFmin;
@@ -1269,10 +1266,16 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							 PP_OD_FEATURE_GFXCLK_BIT))
 			break;

-		size += sysfs_emit_at(buf, size, "OD_SCLK:\n");
-		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
-					od_table->OverDriveTable.GfxclkFmin,
-					od_table->OverDriveTable.GfxclkFmax);
+		PPTable_t *pptable = smu->smu_table.driver_pptable;
+		const OverDriveLimits_t * const overdrive_upperlimits =
+					&pptable->SkuTable.OverDriveLimitsBasicMax;
+		const OverDriveLimits_t * const overdrive_lowerlimits =
+					&pptable->SkuTable.OverDriveLimitsBasicMin;
+
+		size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n");
+		size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n",
+					overdrive_lowerlimits->GfxclkFoffset,
+					overdrive_upperlimits->GfxclkFoffset);
 		break;

 	case SMU_OD_MCLK:
@@ -1414,7 +1417,7 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							  PP_OD_FEATURE_GFXCLK_FMAX,
 							  NULL,
 							  &max_value);
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+			size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n",
 					      min_value, max_value);
 		}

@@ -1796,7 +1799,7 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 	DpmActivityMonitorCoeffInt_t *activity_monitor =
 		&(activity_monitor_external.DpmActivityMonitorCoeffInt);
 	int workload_type, ret = 0;
-
+	uint32_t current_profile_mode = smu->power_profile_mode;
 	smu->power_profile_mode = input[size];

 	if (smu->power_profile_mode >= PP_SMC_POWER_PROFILE_COUNT) {
@@ -1854,6 +1857,11 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 		}
 	}

+	if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+		smu_v14_0_deep_sleep_control(smu, false);
+	else if (current_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE)
+		smu_v14_0_deep_sleep_control(smu, true);
+
 	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
 	workload_type = smu_cmn_to_asic_specific_index(smu,
 						       CMN2ASIC_MAPPING_WORKLOAD,
@@ -2158,7 +2166,7 @@ static ssize_t smu_v14_0_2_get_gpu_metrics(struct smu_context *smu,

 	gpu_metrics->average_gfx_activity = metrics->AverageGfxActivity;
 	gpu_metrics->average_umc_activity = metrics->AverageUclkActivity;
-	gpu_metrics->average_mm_activity = max(metrics->Vcn0ActivityPercentage,
+	gpu_metrics->average_mm_activity = max(metrics->AverageVcn0ActivityPercentage,
 					       metrics->Vcn1ActivityPercentage);

 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
@@ -2217,8 +2225,7 @@ static void smu_v14_0_2_dump_od_table(struct smu_context *smu,
 {
 	struct amdgpu_device *adev = smu->adev;

-	dev_dbg(adev->dev, "OD: Gfxclk: (%d, %d)\n", od_table->OverDriveTable.GfxclkFmin,
-						     od_table->OverDriveTable.GfxclkFmax);
+	dev_dbg(adev->dev, "OD: Gfxclk offset: (%d)\n", od_table->OverDriveTable.GfxclkFoffset);
 	dev_dbg(adev->dev, "OD: Uclk: (%d, %d)\n", od_table->OverDriveTable.UclkFmin,
 						   od_table->OverDriveTable.UclkFmax);
 }
@@ -2309,10 +2316,8 @@ static int smu_v14_0_2_set_default_od_settings(struct smu_context *smu)
 		memcpy(user_od_table,
 		       boot_od_table,
 		       sizeof(OverDriveTableExternal_t));
-		user_od_table->OverDriveTable.GfxclkFmin =
-				user_od_table_bak.OverDriveTable.GfxclkFmin;
-		user_od_table->OverDriveTable.GfxclkFmax =
-				user_od_table_bak.OverDriveTable.GfxclkFmax;
+		user_od_table->OverDriveTable.GfxclkFoffset =
+				user_od_table_bak.OverDriveTable.GfxclkFoffset;
 		user_od_table->OverDriveTable.UclkFmin =
 				user_od_table_bak.OverDriveTable.UclkFmin;
 		user_od_table->OverDriveTable.UclkFmax =
@@ -2441,22 +2446,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			}

 			switch (input[i]) {
-			case 0:
-				smu_v14_0_2_get_od_setting_limits(smu,
-								  PP_OD_FEATURE_GFXCLK_FMIN,
-								  &minimum,
-								  &maximum);
-				if (input[i + 1] < minimum ||
-				    input[i + 1] > maximum) {
-					dev_info(adev->dev, "GfxclkFmin (%ld) must be within [%u, %u]!\n",
-						input[i + 1], minimum, maximum);
-					return -EINVAL;
-				}
-
-				od_table->OverDriveTable.GfxclkFmin = input[i + 1];
-				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
-				break;
-
 			case 1:
 				smu_v14_0_2_get_od_setting_limits(smu,
 								  PP_OD_FEATURE_GFXCLK_FMAX,
@@ -2469,7 +2458,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 					return -EINVAL;
 				}

-				od_table->OverDriveTable.GfxclkFmax = input[i + 1];
+				od_table->OverDriveTable.GfxclkFoffset = input[i + 1];
 				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
 				break;

@@ -2480,13 +2469,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			}
 		}

-		if (od_table->OverDriveTable.GfxclkFmin > od_table->OverDriveTable.GfxclkFmax) {
-			dev_err(adev->dev,
-				"Invalid setting: GfxclkFmin(%u) is bigger than GfxclkFmax(%u)\n",
-				(uint32_t)od_table->OverDriveTable.GfxclkFmin,
-				(uint32_t)od_table->OverDriveTable.GfxclkFmax);
-			return -EINVAL;
-		}
 		break;

 	case PP_OD_EDIT_MCLK_VDDC_TABLE:
@@ -58,9 +58,10 @@ int drm_aux_bridge_register(struct device *parent)
 	adev->id = ret;
 	adev->name = "aux_bridge";
 	adev->dev.parent = parent;
-	adev->dev.of_node = of_node_get(parent->of_node);
 	adev->dev.release = drm_aux_bridge_release;

+	device_set_of_node_from_dev(&adev->dev, parent);
+
 	ret = auxiliary_device_init(adev);
 	if (ret) {
 		ida_free(&drm_aux_bridge_ida, adev->id);
@@ -2391,6 +2391,7 @@ static int tc_probe_bridge_endpoint(struct tc_data *tc)
 			if (tc->pre_emphasis[0] < 0 || tc->pre_emphasis[0] > 2 ||
 			    tc->pre_emphasis[1] < 0 || tc->pre_emphasis[1] > 2) {
 				dev_err(dev, "Incorrect Pre-Emphasis setting, use either 0=0dB 1=3.5dB 2=6dB\n");
+				of_node_put(node);
 				return -EINVAL;
 			}
 		}
@@ -123,9 +123,8 @@ config DRM_I915_USERPTR
 config DRM_I915_GVT_KVMGT
 	tristate "Enable KVM host support Intel GVT-g graphics virtualization"
 	depends on DRM_I915
-	depends on X86
+	depends on KVM_X86
 	depends on 64BIT
-	depends on KVM
 	depends on VFIO
 	select DRM_I915_GVT
 	select KVM_EXTERNAL_WRITE_TRACKING
@@ -890,7 +890,7 @@ void xe_device_l2_flush(struct xe_device *xe)
 	spin_lock(&gt->global_invl_lock);
 	xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);

-	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true))
 		xe_gt_err_once(gt, "Global invalidation timeout\n");
 	spin_unlock(&gt->global_invl_lock);

@@ -115,9 +115,15 @@ static int __domain_wait(struct xe_gt *gt, struct xe_force_wake_domain *domain,
 			     XE_FORCE_WAKE_ACK_TIMEOUT_MS * USEC_PER_MSEC,
 			     &value, true);
 	if (ret)
-		xe_gt_notice(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
-			     domain->id, str_wake_sleep(wake), ERR_PTR(ret),
-			     domain->reg_ack.addr, value);
+		xe_gt_err(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n",
+			  domain->id, str_wake_sleep(wake), ERR_PTR(ret),
+			  domain->reg_ack.addr, value);
+	if (value == ~0) {
+		xe_gt_err(gt,
+			  "Force wake domain %d: %s. MMIO unreliable (forcewake register returns 0xFFFFFFFF)!\n",
+			  domain->id, str_wake_sleep(wake));
+		ret = -EIO;
+	}

 	return ret;
 }
@@ -897,6 +897,24 @@ retry_same_fence:

 	ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ);

+	/*
+	 * Occasionally it is seen that the G2H worker starts running after a delay of more than
+	 * a second even after being queued and activated by the Linux workqueue subsystem. This
+	 * leads to G2H timeout error. The root cause of issue lies with scheduling latency of
+	 * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS
+	 * and this is beyond xe kmd.
+	 *
+	 * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU.
+	 */
+	if (!ret) {
+		flush_work(&ct->g2h_worker);
+		if (g2h_fence.done) {
+			xe_gt_warn(gt, "G2H fence %u, action %04x, done\n",
+				   g2h_fence.seqno, action[0]);
+			ret = 1;
+		}
+	}
+
 	/*
 	 * Ensure we serialize with completion side to prevent UAF with fence going out of scope on
 	 * the stack, since we have no clue if it will fire after the timeout before we can erase
@@ -1726,8 +1726,13 @@ void xe_guc_submit_stop(struct xe_guc *guc)

 	mutex_lock(&guc->submission_state.lock);

-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to stop parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_stop(guc, q);
+	}

 	mutex_unlock(&guc->submission_state.lock);

@@ -1765,8 +1770,13 @@ int xe_guc_submit_start(struct xe_guc *guc)

 	mutex_lock(&guc->submission_state.lock);
 	atomic_dec(&guc->submission_state.stopped);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		/* Prevent redundant attempts to start parallel queues */
+		if (q->guc->id != index)
+			continue;
+
 		guc_exec_queue_start(q);
+	}
 	mutex_unlock(&guc->submission_state.lock);

 	wake_up_all(&guc->ct.wq);
@@ -54,8 +54,9 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 {
 	struct xe_user_fence *ufence;
 	u64 __user *ptr = u64_to_user_ptr(addr);
+	u64 __maybe_unused prefetch_val;

-	if (!access_ok(ptr, sizeof(*ptr)))
+	if (get_user(prefetch_val, ptr))
 		return ERR_PTR(-EFAULT);

 	ufence = kzalloc(sizeof(*ufence), GFP_KERNEL);
@@ -509,6 +509,7 @@
 #define I2C_DEVICE_ID_GOODIX_01E8	0x01e8
 #define I2C_DEVICE_ID_GOODIX_01E9	0x01e9
 #define I2C_DEVICE_ID_GOODIX_01F0	0x01f0
+#define I2C_DEVICE_ID_GOODIX_0D42	0x0d42

 #define USB_VENDOR_ID_GOODTOUCH		0x1aad
 #define USB_DEVICE_ID_GOODTOUCH_000f	0x000f
@@ -868,6 +869,7 @@
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1	0xc539
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1	0xc53f
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY	0xc53a
+#define USB_DEVICE_ID_LOGITECH_BOLT_RECEIVER	0xc548
 #define USB_DEVICE_ID_SPACETRAVELLER	0xc623
 #define USB_DEVICE_ID_SPACENAVIGATOR	0xc626
 #define USB_DEVICE_ID_DINOVO_DESKTOP	0xc704
@@ -473,6 +473,7 @@ static int lenovo_input_mapping(struct hid_device *hdev,
 		return lenovo_input_mapping_tp10_ultrabook_kbd(hdev, hi, field,
 							       usage, bit, max);
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max);
 	default:
 		return 0;
@@ -583,6 +584,7 @@ static ssize_t attr_fn_lock_store(struct device *dev,
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, value);
 		if (ret)
 			return ret;
@@ -776,6 +778,7 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field,
 		return lenovo_event_cptkbd(hdev, field, usage, value);
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		return lenovo_event_tp10ubkbd(hdev, field, usage, value);
 	default:
 		return 0;
@@ -1056,6 +1059,7 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev,
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_led_set_tp10ubkbd(hdev, tp10ubkbd_led[led_nr], value);
 		break;
 	}
@@ -1286,6 +1290,7 @@ static int lenovo_probe(struct hid_device *hdev,
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_probe_tp10ubkbd(hdev);
 		break;
 	default:
@@ -1372,6 +1377,7 @@ static void lenovo_remove(struct hid_device *hdev)
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		lenovo_remove_tp10ubkbd(hdev);
 		break;
 	}
@@ -1421,6 +1427,8 @@ static const struct hid_device_id lenovo_devices[] = {
 	 */
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) },
 	{ }
 };

@@ -2146,6 +2146,10 @@ static const struct hid_device_id mt_devices[] = {
 		HID_DEVICE(BUS_BLUETOOTH, HID_GROUP_MULTITOUCH_WIN_8,
 			USB_VENDOR_ID_LOGITECH,
 			USB_DEVICE_ID_LOGITECH_CASA_TOUCHPAD) },
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_LOGITECH,
+			USB_DEVICE_ID_LOGITECH_BOLT_RECEIVER) },

 	/* MosArt panels */
 	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
@@ -50,6 +50,7 @@
 #define I2C_HID_QUIRK_BAD_INPUT_SIZE		BIT(3)
 #define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET	BIT(4)
 #define I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND	BIT(5)
+#define I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME BIT(6)

 /* Command opcodes */
 #define I2C_HID_OPCODE_RESET			0x01
@@ -140,6 +141,8 @@ static const struct i2c_hid_quirks {
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
 		 I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET |
 		 I2C_HID_QUIRK_BOGUS_IRQ },
+	{ I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_0D42,
+		 I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME },
 	{ 0, 0 }
 };

@@ -981,6 +984,13 @@ static int i2c_hid_core_resume(struct i2c_hid *ihid)
 		return -ENXIO;
 	}

+	/* On Goodix 27c6:0d42 wait extra time before device wakeup.
+	 * It's not clear why but if we send wakeup too early, the device will
+	 * never trigger input interrupts.
+	 */
+	if (ihid->quirks & I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME)
+		msleep(1500);
+
 	/* Instead of resetting device, simply powers the device on. This
 	 * solves "incomplete reports" on Raydium devices 2386:3118 and
 	 * 2386:4B33 and fixes various SIS touchscreens no longer sending
@@ -546,6 +546,26 @@ static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_n
 	return 0;
 }

+/*
+ * The only difference from bio_chain_endio() is that the current
+ * bi_status of bio does not affect the bi_status of parent.
+ */
+static void md_end_flush(struct bio *bio)
+{
+	struct bio *parent = bio->bi_private;
+
+	/*
+	 * If any flush io error before the power failure,
+	 * disk data may be lost.
+	 */
+	if (bio->bi_status)
+		pr_err("md: %pg flush io error %d\n", bio->bi_bdev,
+			blk_status_to_errno(bio->bi_status));
+
+	bio_put(bio);
+	bio_endio(parent);
+}
+
 bool md_flush_request(struct mddev *mddev, struct bio *bio)
 {
 	struct md_rdev *rdev;
@@ -565,7 +585,9 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio)
 		new = bio_alloc_bioset(rdev->bdev, 0,
 				       REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO,
 				       &mddev->bio_set);
-		bio_chain(new, bio);
+		new->bi_private = bio;
+		new->bi_end_io = md_end_flush;
+		bio_inc_remaining(bio);
 		submit_bio(new);
 	}

@@ -4061,9 +4061,12 @@ static int raid10_run(struct mddev *mddev)
 	}

 	if (!mddev_is_dm(conf->mddev)) {
-		ret = raid10_set_queue_limits(mddev);
-		if (ret)
+		int err = raid10_set_queue_limits(mddev);
+
+		if (err) {
+			ret = err;
 			goto out_free_conf;
+		}
 	}

 	/* need to check that every block has at least one working mirror */
@@ -2733,26 +2733,27 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
 			return MICREL_KSZ8_P1_ERRATA;
 		break;
 	case KSZ8567_CHIP_ID:
+		/* KSZ8567R Errata DS80000752C Module 4 */
+	case KSZ8765_CHIP_ID:
+	case KSZ8794_CHIP_ID:
+	case KSZ8795_CHIP_ID:
+		/* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */
 	case KSZ9477_CHIP_ID:
+		/* KSZ9477S Errata DS80000754A Module 4 */
 	case KSZ9567_CHIP_ID:
+		/* KSZ9567S Errata DS80000756A Module 4 */
 	case KSZ9896_CHIP_ID:
+		/* KSZ9896C Errata DS80000757A Module 3 */
 	case KSZ9897_CHIP_ID:
-		/* KSZ9477 Errata DS80000754C
-		 *
-		 * Module 4: Energy Efficient Ethernet (EEE) feature select must
-		 * be manually disabled
+		/* KSZ9897R Errata DS80000758C Module 4 */
+		/* Energy Efficient Ethernet (EEE) feature select must be manually disabled
 		 *   The EEE feature is enabled by default, but it is not fully
 		 *   operational. It must be manually disabled through register
 		 *   controls. If not disabled, the PHY ports can auto-negotiate
 		 *   to enable EEE, and this feature can cause link drops when
 		 *   linked to another device supporting EEE.
 		 *
-		 * The same item appears in the errata for the KSZ9567, KSZ9896,
-		 * and KSZ9897.
-		 *
-		 * A similar item appears in the errata for the KSZ8567, but
-		 * provides an alternative workaround. For now, use the simple
-		 * workaround of disabling the EEE feature for this device too.
+		 * The same item appears in the errata for all switches above.
 		 */
 		return MICREL_NO_EEE;
 	}
@@ -206,6 +206,7 @@ struct mv88e6xxx_gpio_ops;
 struct mv88e6xxx_avb_ops;
 struct mv88e6xxx_ptp_ops;
 struct mv88e6xxx_pcs_ops;
+struct mv88e6xxx_cc_coeffs;

 struct mv88e6xxx_irq {
 	u16 masked;
@@ -408,6 +409,7 @@ struct mv88e6xxx_chip {
 	struct cyclecounter	tstamp_cc;
 	struct timecounter	tstamp_tc;
 	struct delayed_work	overflow_work;
+	const struct mv88e6xxx_cc_coeffs *cc_coeffs;

 	struct ptp_clock	*ptp_clock;
 	struct ptp_clock_info	ptp_clock_info;
@@ -731,10 +733,6 @@ struct mv88e6xxx_ptp_ops {
 	int arr1_sts_reg;
 	int dep_sts_reg;
 	u32 rx_filters;
-	u32 cc_shift;
-	u32 cc_mult;
-	u32 cc_mult_num;
-	u32 cc_mult_dem;
 };

 struct mv88e6xxx_pcs_ops {
@@ -1713,6 +1713,7 @@ int mv88e6393x_port_set_policy(struct mv88e6xxx_chip *chip, int port,
 	ptr = shift / 8;
 	shift %= 8;
 	mask >>= ptr * 8;
+	ptr <<= 8;

 	err = mv88e6393x_port_policy_read(chip, port, ptr, &reg);
 	if (err)
@@ -18,6 +18,13 @@

 #define MV88E6XXX_MAX_ADJ_PPB	1000000

+struct mv88e6xxx_cc_coeffs {
+	u32 cc_shift;
+	u32 cc_mult;
+	u32 cc_mult_num;
+	u32 cc_mult_dem;
+};
+
 /* Family MV88E6250:
 * Raw timestamps are in units of 10-ns clock periods.
 *
@@ -25,22 +32,43 @@
 * simplifies to
 * clkadj = scaled_ppm * 2^7 / 5^5
 */
-#define MV88E6250_CC_SHIFT	28
-#define MV88E6250_CC_MULT	(10 << MV88E6250_CC_SHIFT)
-#define MV88E6250_CC_MULT_NUM	(1 << 7)
-#define MV88E6250_CC_MULT_DEM	3125ULL
+#define MV88E6XXX_CC_10NS_SHIFT 28
+static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_10ns_coeffs = {
+	.cc_shift = MV88E6XXX_CC_10NS_SHIFT,
+	.cc_mult = 10 << MV88E6XXX_CC_10NS_SHIFT,
+	.cc_mult_num = 1 << 7,
+	.cc_mult_dem = 3125ULL,
+};

-/* Other families:
+/* Other families except MV88E6393X in internal clock mode:
 * Raw timestamps are in units of 8-ns clock periods.
 *
 * clkadj = scaled_ppm * 8*2^28 / (10^6 * 2^16)
 * simplifies to
 * clkadj = scaled_ppm * 2^9 / 5^6
 */
-#define MV88E6XXX_CC_SHIFT	28
-#define MV88E6XXX_CC_MULT	(8 << MV88E6XXX_CC_SHIFT)
-#define MV88E6XXX_CC_MULT_NUM	(1 << 9)
-#define MV88E6XXX_CC_MULT_DEM	15625ULL
+#define MV88E6XXX_CC_8NS_SHIFT 28
+static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_8ns_coeffs = {
+	.cc_shift = MV88E6XXX_CC_8NS_SHIFT,
+	.cc_mult = 8 << MV88E6XXX_CC_8NS_SHIFT,
+	.cc_mult_num = 1 << 9,
+	.cc_mult_dem = 15625ULL
+};
+
+/* Family MV88E6393X using internal clock:
+ * Raw timestamps are in units of 4-ns clock periods.
+ *
+ * clkadj = scaled_ppm * 4*2^28 / (10^6 * 2^16)
+ * simplifies to
+ * clkadj = scaled_ppm * 2^8 / 5^6
+ */
+#define MV88E6XXX_CC_4NS_SHIFT 28
+static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_4ns_coeffs = {
+	.cc_shift = MV88E6XXX_CC_4NS_SHIFT,
+	.cc_mult = 4 << MV88E6XXX_CC_4NS_SHIFT,
+	.cc_mult_num = 1 << 8,
+	.cc_mult_dem = 15625ULL
+};

 #define TAI_EVENT_WORK_INTERVAL msecs_to_jiffies(100)

@@ -83,6 +111,33 @@ static int mv88e6352_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
 	return chip->info->ops->gpio_ops->set_pctl(chip, pin, func);
 }

+static const struct mv88e6xxx_cc_coeffs *
+mv88e6xxx_cc_coeff_get(struct mv88e6xxx_chip *chip)
+{
+	u16 period_ps;
+	int err;
+
+	err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_CLOCK_PERIOD, &period_ps, 1);
+	if (err) {
+		dev_err(chip->dev, "failed to read cycle counter period: %d\n",
+			err);
+		return ERR_PTR(err);
+	}
+
+	switch (period_ps) {
+	case 4000:
+		return &mv88e6xxx_cc_4ns_coeffs;
+	case 8000:
+		return &mv88e6xxx_cc_8ns_coeffs;
+	case 10000:
+		return &mv88e6xxx_cc_10ns_coeffs;
+	default:
+		dev_err(chip->dev, "unexpected cycle counter period of %u ps\n",
+			period_ps);
+		return ERR_PTR(-ENODEV);
+	}
+}
+
 static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
@@ -204,7 +259,6 @@ out:
 static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 {
 	struct mv88e6xxx_chip *chip = ptp_to_chip(ptp);
-	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	int neg_adj = 0;
 	u32 diff, mult;
 	u64 adj;
@@ -214,10 +268,10 @@ static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 		scaled_ppm = -scaled_ppm;
 	}

-	mult = ptp_ops->cc_mult;
-	adj = ptp_ops->cc_mult_num;
+	mult = chip->cc_coeffs->cc_mult;
+	adj = chip->cc_coeffs->cc_mult_num;
 	adj *= scaled_ppm;
-	diff = div_u64(adj, ptp_ops->cc_mult_dem);
+	diff = div_u64(adj, chip->cc_coeffs->cc_mult_dem);

 	mv88e6xxx_reg_lock(chip);

@@ -364,10 +418,6 @@ const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
-	.cc_shift = MV88E6XXX_CC_SHIFT,
-	.cc_mult = MV88E6XXX_CC_MULT,
-	.cc_mult_num = MV88E6XXX_CC_MULT_NUM,
-	.cc_mult_dem = MV88E6XXX_CC_MULT_DEM,
 };

 const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {
@@ -391,10 +441,6 @@ const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
-	.cc_shift = MV88E6250_CC_SHIFT,
-	.cc_mult = MV88E6250_CC_MULT,
-	.cc_mult_num = MV88E6250_CC_MULT_NUM,
-	.cc_mult_dem = MV88E6250_CC_MULT_DEM,
 };

 const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
@@ -418,10 +464,6 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
-	.cc_shift = MV88E6XXX_CC_SHIFT,
-	.cc_mult = MV88E6XXX_CC_MULT,
-	.cc_mult_num = MV88E6XXX_CC_MULT_NUM,
-	.cc_mult_dem = MV88E6XXX_CC_MULT_DEM,
 };

 const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {
@@ -446,10 +488,6 @@ const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
-	.cc_shift = MV88E6XXX_CC_SHIFT,
-	.cc_mult = MV88E6XXX_CC_MULT,
-	.cc_mult_num = MV88E6XXX_CC_MULT_NUM,
-	.cc_mult_dem = MV88E6XXX_CC_MULT_DEM,
 };

 static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
@@ -462,10 +500,10 @@ static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
 	return 0;
 }

-/* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3
+/* With a 250MHz input clock, the 32-bit timestamp counter overflows in ~17.2
 * seconds; this task forces periodic reads so that we don't miss any.
 */
-#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 16)
+#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 8)
 static void mv88e6xxx_ptp_overflow_check(struct work_struct *work)
 {
 	struct delayed_work *dw = to_delayed_work(work);
@@ -484,11 +522,15 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 	int i;

 	/* Set up the cycle counter */
+	chip->cc_coeffs = mv88e6xxx_cc_coeff_get(chip);
+	if (IS_ERR(chip->cc_coeffs))
+		return PTR_ERR(chip->cc_coeffs);
+
 	memset(&chip->tstamp_cc, 0, sizeof(chip->tstamp_cc));
 	chip->tstamp_cc.read	= mv88e6xxx_ptp_clock_read;
 	chip->tstamp_cc.mask	= CYCLECOUNTER_MASK(32);
-	chip->tstamp_cc.mult	= ptp_ops->cc_mult;
-	chip->tstamp_cc.shift	= ptp_ops->cc_shift;
+	chip->tstamp_cc.mult	= chip->cc_coeffs->cc_mult;
+	chip->tstamp_cc.shift	= chip->cc_coeffs->cc_shift;

 	timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc,
 			 ktime_to_ns(ktime_get_real()));
@@ -2254,10 +2254,11 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,

 			if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
 				struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+				unsigned long flags;

-				spin_lock_bh(&ptp->ptp_lock);
+				spin_lock_irqsave(&ptp->ptp_lock, flags);
 				ns = timecounter_cyc2time(&ptp->tc, ts);
-				spin_unlock_bh(&ptp->ptp_lock);
+				spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 				memset(skb_hwtstamps(skb), 0,
 				       sizeof(*skb_hwtstamps(skb)));
 				skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns);
@@ -2757,17 +2758,18 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE:
 			if (BNXT_PTP_USE_RTC(bp)) {
 				struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+				unsigned long flags;
 				u64 ns;

 				if (!ptp)
 					goto async_event_process_exit;

-				spin_lock_bh(&ptp->ptp_lock);
+				spin_lock_irqsave(&ptp->ptp_lock, flags);
 				bnxt_ptp_update_current_time(bp);
 				ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) <<
 				       BNXT_PHC_BITS) | ptp->current_time);
 				bnxt_ptp_rtc_timecounter_init(ptp, ns);
-				spin_unlock_bh(&ptp->ptp_lock);
+				spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 			}
 			break;
 		}
@@ -13494,9 +13496,11 @@ static void bnxt_force_fw_reset(struct bnxt *bp)
 		return;

 	if (ptp) {
-		spin_lock_bh(&ptp->ptp_lock);
+		unsigned long flags;
+
+		spin_lock_irqsave(&ptp->ptp_lock, flags);
 		set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 	} else {
 		set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	}
@@ -13561,9 +13565,11 @@ void bnxt_fw_reset(struct bnxt *bp)
 		int n = 0, tmo;

 		if (ptp) {
-			spin_lock_bh(&ptp->ptp_lock);
+			unsigned long flags;
+
+			spin_lock_irqsave(&ptp->ptp_lock, flags);
 			set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-			spin_unlock_bh(&ptp->ptp_lock);
+			spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 		} else {
 			set_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 		}
@@ -62,13 +62,14 @@ static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info,
 	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
 						ptp_info);
 	u64 ns = timespec64_to_ns(ts);
+	unsigned long flags;

 	if (BNXT_PTP_USE_RTC(ptp->bp))
 		return bnxt_ptp_cfg_settime(ptp->bp, ns);

-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	timecounter_init(&ptp->tc, &ptp->cc, ns);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 	return 0;
 }

@@ -100,13 +101,14 @@ static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts,
 static void bnxt_ptp_get_current_time(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+	unsigned long flags;

 	if (!ptp)
 		return;
-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	WRITE_ONCE(ptp->old_time, ptp->current_time);
 	bnxt_refclk_read(bp, NULL, &ptp->current_time);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 }

 static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts,
@@ -149,17 +151,18 @@ static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info,
 {
 	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
 						ptp_info);
+	unsigned long flags;
 	u64 ns, cycles;
 	int rc;

-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	rc = bnxt_refclk_read(ptp->bp, sts, &cycles);
 	if (rc) {
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 		return rc;
 	}
 	ns = timecounter_cyc2time(&ptp->tc, cycles);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 	*ts = ns_to_timespec64(ns);

 	return 0;
@@ -177,6 +180,7 @@ void bnxt_ptp_update_current_time(struct bnxt *bp)
 static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta)
 {
 	struct hwrm_port_mac_cfg_input *req;
+	unsigned long flags;
 	int rc;

 	rc = hwrm_req_init(ptp->bp, req, HWRM_PORT_MAC_CFG);
@@ -190,9 +194,9 @@ static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta)
 	if (rc) {
 		netdev_err(ptp->bp->dev, "ptp adjphc failed. rc = %x\n", rc);
 	} else {
-		spin_lock_bh(&ptp->ptp_lock);
+		spin_lock_irqsave(&ptp->ptp_lock, flags);
 		bnxt_ptp_update_current_time(ptp->bp);
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 	}

 	return rc;
@@ -202,13 +206,14 @@ static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
 {
 	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
 						ptp_info);
+	unsigned long flags;

 	if (BNXT_PTP_USE_RTC(ptp->bp))
 		return bnxt_ptp_adjphc(ptp, delta);

-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	timecounter_adjtime(&ptp->tc, delta);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 	return 0;
 }

@@ -236,14 +241,15 @@ static int bnxt_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm)
 	struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
 						ptp_info);
 	struct bnxt *bp = ptp->bp;
+	unsigned long flags;

 	if (!BNXT_MH(bp))
 		return bnxt_ptp_adjfine_rtc(bp, scaled_ppm);

-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	timecounter_read(&ptp->tc);
 	ptp->cc.mult = adjust_by_scaled_ppm(ptp->cmult, scaled_ppm);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 	return 0;
 }

@@ -251,12 +257,13 @@ void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	struct ptp_clock_event event;
+	unsigned long flags;
 	u64 ns, pps_ts;

 	pps_ts = EVENT_PPS_TS(data2, data1);
-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	ns = timecounter_cyc2time(&ptp->tc, pps_ts);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);

 	switch (EVENT_DATA2_PPS_EVENT_TYPE(data2)) {
 	case ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL:
@@ -393,16 +400,17 @@ static int bnxt_get_target_cycles(struct bnxt_ptp_cfg *ptp, u64 target_ns,
 {
 	u64 cycles_now;
 	u64 nsec_now, nsec_delta;
+	unsigned long flags;
 	int rc;

-	spin_lock_bh(&ptp->ptp_lock);
+	spin_lock_irqsave(&ptp->ptp_lock, flags);
 	rc = bnxt_refclk_read(ptp->bp, NULL, &cycles_now);
 	if (rc) {
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 		return rc;
 	}
 	nsec_now = timecounter_cyc2time(&ptp->tc, cycles_now);
-	spin_unlock_bh(&ptp->ptp_lock);
+	spin_unlock_irqrestore(&ptp->ptp_lock, flags);

 	nsec_delta = target_ns - nsec_now;
 	*cycles_delta = div64_u64(nsec_delta << ptp->cc.shift, ptp->cc.mult);
@@ -689,6 +697,7 @@ static int bnxt_stamp_tx_skb(struct bnxt *bp, int slot)
 	struct skb_shared_hwtstamps timestamp;
 	struct bnxt_ptp_tx_req *txts_req;
 	unsigned long now = jiffies;
+	unsigned long flags;
 	u64 ts = 0, ns = 0;
 	u32 tmo = 0;
 	int rc;
@@ -702,9 +711,9 @@ static int bnxt_stamp_tx_skb(struct bnxt *bp, int slot)
 				     tmo, slot);
 	if (!rc) {
 		memset(&timestamp, 0, sizeof(timestamp));
-		spin_lock_bh(&ptp->ptp_lock);
+		spin_lock_irqsave(&ptp->ptp_lock, flags);
 		ns = timecounter_cyc2time(&ptp->tc, ts);
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(txts_req->tx_skb, &timestamp);
 		ptp->stats.ts_pkts++;
@@ -730,6 +739,7 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
 	unsigned long now = jiffies;
 	struct bnxt *bp = ptp->bp;
 	u16 cons = ptp->txts_cons;
+	unsigned long flags;
 	u32 num_requests;
 	int rc = 0;

@@ -757,9 +767,9 @@ next_slot:
 	bnxt_ptp_get_current_time(bp);
 	ptp->next_period = now + HZ;
 	if (time_after_eq(now, ptp->next_overflow_check)) {
-		spin_lock_bh(&ptp->ptp_lock);
+		spin_lock_irqsave(&ptp->ptp_lock, flags);
 		timecounter_read(&ptp->tc);
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 		ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD;
 	}
 	if (rc == -EAGAIN)
@@ -819,6 +829,7 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi,
 	u32 opaque = tscmp->tx_ts_cmp_opaque;
 	struct bnxt_tx_ring_info *txr;
 	struct bnxt_sw_tx_bd *tx_buf;
+	unsigned long flags;
 	u64 ts, ns;
 	u16 cons;

@@ -833,9 +844,9 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi,
 				   le32_to_cpu(tscmp->tx_ts_cmp_flags_type),
 				   le32_to_cpu(tscmp->tx_ts_cmp_errors_v));
 		} else {
-			spin_lock_bh(&ptp->ptp_lock);
+			spin_lock_irqsave(&ptp->ptp_lock, flags);
 			ns = timecounter_cyc2time(&ptp->tc, ts);
-			spin_unlock_bh(&ptp->ptp_lock);
+			spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 			timestamp.hwtstamp = ns_to_ktime(ns);
 			skb_tstamp_tx(tx_buf->skb, &timestamp);
 		}
@@ -975,6 +986,7 @@ void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns)
 int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
 {
 	struct timespec64 tsp;
+	unsigned long flags;
 	u64 ns;
 	int rc;

@@ -993,9 +1005,9 @@ int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
 		if (rc)
 			return rc;
 	}
-	spin_lock_bh(&bp->ptp_cfg->ptp_lock);
+	spin_lock_irqsave(&bp->ptp_cfg->ptp_lock, flags);
 	bnxt_ptp_rtc_timecounter_init(bp->ptp_cfg, ns);
-	spin_unlock_bh(&bp->ptp_cfg->ptp_lock);
+	spin_unlock_irqrestore(&bp->ptp_cfg->ptp_lock, flags);

 	return 0;
 }
@@ -1063,10 +1075,12 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 	atomic64_set(&ptp->stats.ts_err, 0);

 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-		spin_lock_bh(&ptp->ptp_lock);
+		unsigned long flags;
+
+		spin_lock_irqsave(&ptp->ptp_lock, flags);
 		bnxt_refclk_read(bp, NULL, &ptp->current_time);
 		WRITE_ONCE(ptp->old_time, ptp->current_time);
-		spin_unlock_bh(&ptp->ptp_lock);
+		spin_unlock_irqrestore(&ptp->ptp_lock, flags);
 		ptp_schedule_worker(ptp->ptp_clock, 0);
 	}
 	ptp->txts_tmo = BNXT_PTP_DFLT_TX_TMO;
@@ -146,11 +146,13 @@ struct bnxt_ptp_cfg {
 };

 #if BITS_PER_LONG == 32
-#define BNXT_READ_TIME64(ptp, dst, src)		\
-do {						\
-	spin_lock_bh(&(ptp)->ptp_lock);		\
-	(dst) = (src);				\
-	spin_unlock_bh(&(ptp)->ptp_lock);	\
+#define BNXT_READ_TIME64(ptp, dst, src)				\
+do {								\
+	unsigned long flags;					\
+								\
+	spin_lock_irqsave(&(ptp)->ptp_lock, flags);		\
+	(dst) = (src);						\
+	spin_unlock_irqrestore(&(ptp)->ptp_lock, flags);	\
 } while (0)
 #else
 #define BNXT_READ_TIME64(ptp, dst, src)		\
@@ -1381,10 +1381,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 	be_get_wrb_params_from_skb(adapter, skb, &wrb_params);

 	wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
-	if (unlikely(!wrb_cnt)) {
-		dev_kfree_skb_any(skb);
-		goto drop;
-	}
+	if (unlikely(!wrb_cnt))
+		goto drop_skb;

 	/* if os2bmc is enabled and if the pkt is destined to bmc,
 	 * enqueue the pkt a 2nd time with mgmt bit set.
@@ -1393,7 +1391,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 		BE_WRB_F_SET(wrb_params.features, OS2BMC, 1);
 		wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
 		if (unlikely(!wrb_cnt))
-			goto drop;
+			goto drop_skb;
 		else
 			skb_get(skb);
 	}
@@ -1407,6 +1405,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 		be_xmit_flush(adapter, txo);

 	return NETDEV_TX_OK;
+drop_skb:
+	dev_kfree_skb_any(skb);
 drop:
 	tx_stats(txo)->tx_drv_drops++;
 	/* Flush the already enqueued tx requests */
@@ -197,55 +197,67 @@ static int mac_probe(struct platform_device *_of_dev)
 		err = -EINVAL;
 		goto _return_of_node_put;
 	}
+	mac_dev->fman_dev = &of_dev->dev;

 	/* Get the FMan cell-index */
 	err = of_property_read_u32(dev_node, "cell-index", &val);
 	if (err) {
 		dev_err(dev, "failed to read cell-index for %pOF\n", dev_node);
 		err = -EINVAL;
-		goto _return_of_node_put;
+		goto _return_dev_put;
 	}
 	/* cell-index 0 => FMan id 1 */
 	fman_id = (u8)(val + 1);

-	priv->fman = fman_bind(&of_dev->dev);
+	priv->fman = fman_bind(mac_dev->fman_dev);
 	if (!priv->fman) {
 		dev_err(dev, "fman_bind(%pOF) failed\n", dev_node);
 		err = -ENODEV;
-		goto _return_of_node_put;
+		goto _return_dev_put;
 	}

+	/* Two references have been taken in of_find_device_by_node()
+	 * and fman_bind(). Release one of them here. The second one
+	 * will be released in mac_remove().
+	 */
+	put_device(mac_dev->fman_dev);
 	of_node_put(dev_node);
+	dev_node = NULL;

 	/* Get the address of the memory mapped registers */
 	mac_dev->res = platform_get_mem_or_io(_of_dev, 0);
 	if (!mac_dev->res) {
 		dev_err(dev, "could not get registers\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto _return_dev_put;
 	}

 	err = devm_request_resource(dev, fman_get_mem_region(priv->fman),
 				    mac_dev->res);
 	if (err) {
 		dev_err_probe(dev, err, "could not request resource\n");
-		return err;
+		goto _return_dev_put;
 	}

 	mac_dev->vaddr = devm_ioremap(dev, mac_dev->res->start,
 				      resource_size(mac_dev->res));
 	if (!mac_dev->vaddr) {
 		dev_err(dev, "devm_ioremap() failed\n");
-		return -EIO;
+		err = -EIO;
+		goto _return_dev_put;
 	}

-	if (!of_device_is_available(mac_node))
-		return -ENODEV;
+	if (!of_device_is_available(mac_node)) {
+		err = -ENODEV;
+		goto _return_dev_put;
+	}

 	/* Get the cell-index */
 	err = of_property_read_u32(mac_node, "cell-index", &val);
 	if (err) {
 		dev_err(dev, "failed to read cell-index for %pOF\n", mac_node);
-		return -EINVAL;
+		err = -EINVAL;
+		goto _return_dev_put;
 	}
 	priv->cell_index = (u8)val;

@@ -259,22 +271,26 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (unlikely(nph < 0)) {
 		dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n",
 			mac_node);
-		return nph;
+		err = nph;
+		goto _return_dev_put;
 	}

 	if (nph != ARRAY_SIZE(mac_dev->port)) {
 		dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n",
 			mac_node);
-		return -EINVAL;
+		err = -EINVAL;
+		goto _return_dev_put;
 	}

-	for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
+	/* PORT_NUM determines the size of the port array */
+	for (i = 0; i < PORT_NUM; i++) {
 		/* Find the port node */
 		dev_node = of_parse_phandle(mac_node, "fsl,fman-ports", i);
 		if (!dev_node) {
 			dev_err(dev, "of_parse_phandle(%pOF, fsl,fman-ports) failed\n",
 				mac_node);
-			return -EINVAL;
+			err = -EINVAL;
+			goto _return_dev_arr_put;
 		}

 		of_dev = of_find_device_by_node(dev_node);
@@ -282,17 +298,24 @@ static int mac_probe(struct platform_device *_of_dev)
 			dev_err(dev, "of_find_device_by_node(%pOF) failed\n",
 				dev_node);
 			err = -EINVAL;
-			goto _return_of_node_put;
+			goto _return_dev_arr_put;
 		}
+		mac_dev->fman_port_devs[i] = &of_dev->dev;

-		mac_dev->port[i] = fman_port_bind(&of_dev->dev);
+		mac_dev->port[i] = fman_port_bind(mac_dev->fman_port_devs[i]);
 		if (!mac_dev->port[i]) {
 			dev_err(dev, "dev_get_drvdata(%pOF) failed\n",
 				dev_node);
 			err = -EINVAL;
-			goto _return_of_node_put;
+			goto _return_dev_arr_put;
 		}
+		/* Two references have been taken in of_find_device_by_node()
+		 * and fman_port_bind(). Release one of them here. The second
+		 * one will be released in mac_remove().
+		 */
+		put_device(mac_dev->fman_port_devs[i]);
 		of_node_put(dev_node);
+		dev_node = NULL;
 	}

 	/* Get the PHY connection type */
@@ -312,7 +335,7 @@ static int mac_probe(struct platform_device *_of_dev)

 	err = init(mac_dev, mac_node, &params);
 	if (err < 0)
-		return err;
+		goto _return_dev_arr_put;

 	if (!is_zero_ether_addr(mac_dev->addr))
 		dev_info(dev, "FMan MAC address: %pM\n", mac_dev->addr);
@@ -327,6 +350,12 @@ static int mac_probe(struct platform_device *_of_dev)

 	return err;

+_return_dev_arr_put:
+	/* mac_dev is kzalloc'ed */
+	for (i = 0; i < PORT_NUM; i++)
+		put_device(mac_dev->fman_port_devs[i]);
+_return_dev_put:
+	put_device(mac_dev->fman_dev);
 _return_of_node_put:
 	of_node_put(dev_node);
 	return err;
@@ -335,6 +364,11 @@ _return_of_node_put:
 static void mac_remove(struct platform_device *pdev)
 {
 	struct mac_device *mac_dev = platform_get_drvdata(pdev);
+	int		   i;
+
+	for (i = 0; i < PORT_NUM; i++)
+		put_device(mac_dev->fman_port_devs[i]);
+	put_device(mac_dev->fman_dev);

 	platform_device_unregister(mac_dev->priv->eth_dev);
 }
@@ -19,12 +19,13 @@
 struct fman_mac;
 struct mac_priv_s;

+#define PORT_NUM 2
 struct mac_device {
 	void __iomem		*vaddr;
 	struct device		*dev;
 	struct resource		*res;
 	u8			 addr[ETH_ALEN];
-	struct fman_port	*port[2];
+	struct fman_port	*port[PORT_NUM];
 	struct phylink		*phylink;
 	struct phylink_config	phylink_config;
 	phy_interface_t		phy_if;
@@ -52,6 +53,9 @@ struct mac_device {

 	struct fman_mac		*fman_mac;
 	struct mac_priv_s	*priv;
+
+	struct device		*fman_dev;
+	struct device		*fman_port_devs[PORT_NUM];
 };

 static inline struct mac_device
@@ -1012,6 +1012,7 @@ sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev)
 	if(skb->len > XMIT_BUFF_SIZE)
 	{
 		printk("%s: Sorry, max. framelength is %d bytes. The length of your frame is %d bytes.\n",dev->name,XMIT_BUFF_SIZE,skb->len);
+		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}

@@ -336,6 +336,51 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 	return new_pkts;
 }

+/**
+ * octep_oq_next_pkt() - Move to the next packet in Rx queue.
+ *
+ * @oq: Octeon Rx queue data structure.
+ * @buff_info: Current packet buffer info.
+ * @read_idx: Current packet index in the ring.
+ * @desc_used: Current packet descriptor number.
+ *
+ * Free the resources associated with a packet.
+ * Increment packet index in the ring and packet descriptor number.
+ */
+static void octep_oq_next_pkt(struct octep_oq *oq,
+			      struct octep_rx_buffer *buff_info,
+			      u32 *read_idx, u32 *desc_used)
+{
+	dma_unmap_page(oq->dev, oq->desc_ring[*read_idx].buffer_ptr,
+		       PAGE_SIZE, DMA_FROM_DEVICE);
+	buff_info->page = NULL;
+	(*read_idx)++;
+	(*desc_used)++;
+	if (*read_idx == oq->max_count)
+		*read_idx = 0;
+}
+
+/**
+ * octep_oq_drop_rx() - Free the resources associated with a packet.
+ *
+ * @oq: Octeon Rx queue data structure.
+ * @buff_info: Current packet buffer info.
+ * @read_idx: Current packet index in the ring.
+ * @desc_used: Current packet descriptor number.
+ *
+ */
+static void octep_oq_drop_rx(struct octep_oq *oq,
+			     struct octep_rx_buffer *buff_info,
+			     u32 *read_idx, u32 *desc_used)
+{
+	int data_len = buff_info->len - oq->max_single_buffer_size;
+
+	while (data_len > 0) {
+		octep_oq_next_pkt(oq, buff_info, read_idx, desc_used);
+		data_len -= oq->buffer_size;
+	};
+}
+
 /**
 * __octep_oq_process_rx() - Process hardware Rx queue and push to stack.
 *
@@ -367,10 +412,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
 		buff_info = (struct octep_rx_buffer *)&oq->buff_info[read_idx];
-		dma_unmap_page(oq->dev, oq->desc_ring[read_idx].buffer_ptr,
-			       PAGE_SIZE, DMA_FROM_DEVICE);
 		resp_hw = page_address(buff_info->page);
-		buff_info->page = NULL;

 		/* Swap the length field that is in Big-Endian to CPU */
 		buff_info->len = be64_to_cpu(resp_hw->length);
@@ -394,36 +436,33 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 			data_offset = OCTEP_OQ_RESP_HW_SIZE;
 			rx_ol_flags = 0;
 		}
+
+		octep_oq_next_pkt(oq, buff_info, &read_idx, &desc_used);
+
+		skb = build_skb((void *)resp_hw, PAGE_SIZE);
+		if (!skb) {
+			octep_oq_drop_rx(oq, buff_info,
+					 &read_idx, &desc_used);
+			oq->stats.alloc_failures++;
+			continue;
+		}
+		skb_reserve(skb, data_offset);
+
 		rx_bytes += buff_info->len;

 		if (buff_info->len <= oq->max_single_buffer_size) {
-			skb = build_skb((void *)resp_hw, PAGE_SIZE);
-			skb_reserve(skb, data_offset);
 			skb_put(skb, buff_info->len);
-			read_idx++;
-			desc_used++;
-			if (read_idx == oq->max_count)
-				read_idx = 0;
 		} else {
 			struct skb_shared_info *shinfo;
 			u16 data_len;

-			skb = build_skb((void *)resp_hw, PAGE_SIZE);
-			skb_reserve(skb, data_offset);
 			/* Head fragment includes response header(s);
 			 * subsequent fragments contains only data.
 			 */
 			skb_put(skb, oq->max_single_buffer_size);
-			read_idx++;
-			desc_used++;
-			if (read_idx == oq->max_count)
-				read_idx = 0;
-
 			shinfo = skb_shinfo(skb);
 			data_len = buff_info->len - oq->max_single_buffer_size;
 			while (data_len) {
-				dma_unmap_page(oq->dev, oq->desc_ring[read_idx].buffer_ptr,
-					       PAGE_SIZE, DMA_FROM_DEVICE);
 				buff_info = (struct octep_rx_buffer *)
 					    &oq->buff_info[read_idx];
 				if (data_len < oq->buffer_size) {
@@ -438,11 +477,8 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 						buff_info->page, 0,
 						buff_info->len,
 						buff_info->len);
-				buff_info->page = NULL;
-				read_idx++;
-				desc_used++;
-				if (read_idx == oq->max_count)
-					read_idx = 0;
+
+				octep_oq_next_pkt(oq, buff_info, &read_idx, &desc_used);
 			}
 		}

@@ -3197,7 +3197,6 @@ mlxsw_sp_nexthop_sh_counter_get(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_nexthop_group *nh_grp = nh->nhgi->nh_grp;
 	struct mlxsw_sp_nexthop_counter *nhct;
-	void *ptr;
 	int err;

 	nhct = xa_load(&nh_grp->nhgi->nexthop_counters, nh->id);
@@ -3210,12 +3209,10 @@ mlxsw_sp_nexthop_sh_counter_get(struct mlxsw_sp *mlxsw_sp,
 	if (IS_ERR(nhct))
 		return nhct;

-	ptr = xa_store(&nh_grp->nhgi->nexthop_counters, nh->id, nhct,
-		       GFP_KERNEL);
-	if (IS_ERR(ptr)) {
-		err = PTR_ERR(ptr);
+	err = xa_err(xa_store(&nh_grp->nhgi->nexthop_counters, nh->id, nhct,
+			      GFP_KERNEL));
+	if (err)
 		goto err_store;
-	}

 	return nhct;

@@ -4682,7 +4682,9 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 	if ((status & 0xffff) == 0xffff || !(status & tp->irq_mask))
 		return IRQ_NONE;

-	if (unlikely(status & SYSErr)) {
+	/* At least RTL8168fp may unexpectedly set the SYSErr bit */
+	if (unlikely(status & SYSErr &&
+	    tp->mac_version <= RTL_GIGA_MAC_VER_06)) {
 		rtl8169_pcierr_interrupt(tp->dev);
 		goto out;
 	}
@@ -2798,6 +2798,31 @@ static struct  hv_driver netvsc_drv = {
 	},
 };

+/* Set VF's namespace same as the synthetic NIC */
+static void netvsc_event_set_vf_ns(struct net_device *ndev)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct net_device *vf_netdev;
+	int ret;
+
+	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
+	if (!vf_netdev)
+		return;
+
+	if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
+		ret = dev_change_net_namespace(vf_netdev, dev_net(ndev),
+					       "eth%d");
+		if (ret)
+			netdev_err(vf_netdev,
+				   "Cannot move to same namespace as %s: %d\n",
+				   ndev->name, ret);
+		else
+			netdev_info(vf_netdev,
+				    "Moved VF to namespace with: %s\n",
+				    ndev->name);
+	}
+}
+
 /*
 * On Hyper-V, every VF interface is matched with a corresponding
 * synthetic interface. The synthetic interface is presented first
@@ -2810,6 +2835,11 @@ static int netvsc_netdev_event(struct notifier_block *this,
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;

+	if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) {
+		netvsc_event_set_vf_ns(event_dev);
+		return NOTIFY_DONE;
+	}
+
 	ret = check_dev_is_matching_vf(event_dev);
 	if (ret != 0)
 		return NOTIFY_DONE;
@@ -45,8 +45,8 @@
 /* Control Register 2 bits */
 #define DP83822_FX_ENABLE	BIT(14)

-#define DP83822_HW_RESET	BIT(15)
-#define DP83822_SW_RESET	BIT(14)
+#define DP83822_SW_RESET	BIT(15)
+#define DP83822_DIG_RESTART	BIT(14)

 /* PHY STS bits */
 #define DP83822_PHYSTS_DUPLEX			BIT(2)
@@ -815,7 +815,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl,
 				return HS_TIMEOUT;
 			}
 		}
-		break;
+		fallthrough;

 	case PLIP_PK_LENGTH_LSB:
 		if (plip_send(nibble_timeout, dev,
@@ -113,7 +113,7 @@ static void pse_release_pis(struct pse_controller_dev *pcdev)
 {
 	int i;

-	for (i = 0; i <= pcdev->nr_lines; i++) {
+	for (i = 0; i < pcdev->nr_lines; i++) {
 		of_node_put(pcdev->pi[i].pairset[0].np);
 		of_node_put(pcdev->pi[i].pairset[1].np);
 		of_node_put(pcdev->pi[i].np);
@@ -647,7 +647,7 @@ static int of_pse_match_pi(struct pse_controller_dev *pcdev,
 {
 	int i;

-	for (i = 0; i <= pcdev->nr_lines; i++) {
+	for (i = 0; i < pcdev->nr_lines; i++) {
 		if (pcdev->pi[i].np == np)
 			return i;
 	}
@@ -1426,6 +1426,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)},	/* Quectel EM05GV2 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
+	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)},	/* Fibocom FG132 */
 	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
 	{QMI_FIXED_INTF(0x0489, 0xe0b5, 0)},	/* Foxconn T77W968 LTE with eSIM support*/
 	{QMI_FIXED_INTF(0x2692, 0x9025, 4)},    /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */
@@ -1767,7 +1767,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 		// can rename the link if it knows better.
 		if ((dev->driver_info->flags & FLAG_ETHER) != 0 &&
 		    ((dev->driver_info->flags & FLAG_POINTTOPOINT) == 0 ||
-		     (net->dev_addr [0] & 0x02) == 0))
+		     /* somebody touched it*/
+		     !is_zero_ether_addr(net->dev_addr)))
 			strscpy(net->name, "eth%d", sizeof(net->name));
 		/* WLAN devices should always be named "wlan%d" */
 		if ((dev->driver_info->flags & FLAG_WLAN) != 0)
@@ -4155,7 +4155,7 @@ struct virtnet_stats_ctx {
 	u32 desc_num[3];

 	/* The actual supported stat types. */
-	u32 bitmap[3];
+	u64 bitmap[3];

 	/* Used to calculate the reply buffer size. */
 	u32 size[3];
@@ -1038,7 +1038,7 @@ static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = {

 static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = {
 	.kind = "wwan",
-	.maxtype = __IFLA_WWAN_MAX,
+	.maxtype = IFLA_WWAN_MAX,
 	.alloc = wwan_rtnl_alloc,
 	.validate = wwan_rtnl_validate,
 	.newlink = wwan_rtnl_newlink,
--- a/Show More
+++ b/Show More