diff --git a/.mailmap b/.mailmap
index 369cfe4..c8f5f36 100644
--- a/.mailmap
+++ b/.mailmap
@@ -605,7 +605,8 @@
 Oleksij Rempel <o.rempel@pengutronix.de> <ore@pengutronix.de>
 Oliver Hartkopp <socketcan@hartkopp.net> <oliver.hartkopp@volkswagen.de>
 Oliver Hartkopp <socketcan@hartkopp.net> <oliver@hartkopp.net>
-Oliver Upton <oliver.upton@linux.dev> <oupton@google.com>
+Oliver Upton <oupton@kernel.org> <oupton@google.com>
+Oliver Upton <oupton@kernel.org> <oliver.upton@linux.dev>
 Ondřej Jirman <megi@xff.cz> <megous@megous.com>
 Oza Pawandeep <quic_poza@quicinc.com> <poza@codeaurora.org>
 Pali Rohár <pali@kernel.org> <pali.rohar@gmail.com>
diff --git a/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml b/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml
index 5e3e199f..96d50d1 100644
--- a/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml
+++ b/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/ti,twl4030-gpio.yaml#
+$id: http://devicetree.org/schemas/gpio/ti,twl4030-gpio.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: TI TWL4030 GPIO controller
diff --git a/MAINTAINERS b/MAINTAINERS
index ca428cd..f568b59 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13659,7 +13659,7 @@
 
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
 M:	Marc Zyngier <maz@kernel.org>
-M:	Oliver Upton <oliver.upton@linux.dev>
+M:	Oliver Upton <oupton@kernel.org>
 R:	Joey Gouly <joey.gouly@arm.com>
 R:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Zenghui Yu <yuzenghui@huawei.com>
@@ -20163,6 +20163,7 @@
 R:	Jiri Olsa <jolsa@kernel.org>
 R:	Ian Rogers <irogers@google.com>
 R:	Adrian Hunter <adrian.hunter@intel.com>
+R:	James Clark <james.clark@linaro.org>
 L:	linux-perf-users@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
 S:	Supported
diff --git a/Makefile b/Makefile
index 088565e..fb4389a 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index 4e16f9b..58b7d0c 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -479,7 +479,7 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 	struct ffa_mem_region_attributes *ep_mem_access;
 	struct ffa_composite_mem_region *reg;
 	struct ffa_mem_region *buf;
-	u32 offset, nr_ranges;
+	u32 offset, nr_ranges, checked_offset;
 	int ret = 0;
 
 	if (addr_mbz || npages_mbz || fraglen > len ||
@@ -516,7 +516,12 @@ static void __do_ffa_mem_xfer(const u64 func_id,
 		goto out_unlock;
 	}
 
-	if (fraglen < offset + sizeof(struct ffa_composite_mem_region)) {
+	if (check_add_overflow(offset, sizeof(struct ffa_composite_mem_region), &checked_offset)) {
+		ret = FFA_RET_INVALID_PARAMETERS;
+		goto out_unlock;
+	}
+
+	if (fraglen < checked_offset) {
 		ret = FFA_RET_INVALID_PARAMETERS;
 		goto out_unlock;
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index ddc8beb..49db32f 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -367,6 +367,19 @@ static int host_stage2_unmap_dev_all(void)
 	return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr);
 }
 
+/*
+ * Ensure the PFN range is contained within PA-range.
+ *
+ * This check is also robust to overflows and is therefore a requirement before
+ * using a pfn/nr_pages pair from an untrusted source.
+ */
+static bool pfn_range_is_valid(u64 pfn, u64 nr_pages)
+{
+	u64 limit = BIT(kvm_phys_shift(&host_mmu.arch.mmu) - PAGE_SHIFT);
+
+	return pfn < limit && ((limit - pfn) >= nr_pages);
+}
+
 struct kvm_mem_range {
 	u64 start;
 	u64 end;
@@ -776,6 +789,9 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
 	void *virt = __hyp_va(phys);
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	hyp_lock_component();
 
@@ -804,6 +820,9 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
 	u64 virt = (u64)__hyp_va(phys);
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	hyp_lock_component();
 
@@ -887,6 +906,9 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages)
 	u64 size = PAGE_SIZE * nr_pages;
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
 	if (!ret)
@@ -902,6 +924,9 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
 	u64 size = PAGE_SIZE * nr_pages;
 	int ret;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	host_lock_component();
 	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
 	if (!ret)
@@ -945,6 +970,9 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu
 	if (prot & ~KVM_PGTABLE_PROT_RWX)
 		return -EINVAL;
 
+	if (!pfn_range_is_valid(pfn, nr_pages))
+		return -EINVAL;
+
 	ret = __guest_check_transition_size(phys, ipa, nr_pages, &size);
 	if (ret)
 		return ret;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e67eb39..8ae2bca 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2595,19 +2595,23 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
 	.val = 0,				\
 }
 
-/* sys_reg_desc initialiser for known cpufeature ID registers */
-#define AA32_ID_SANITISED(name) {		\
-	ID_DESC(name),				\
-	.visibility = aa32_id_visibility,	\
-	.val = 0,				\
-}
-
 /* sys_reg_desc initialiser for writable ID registers */
 #define ID_WRITABLE(name, mask) {		\
 	ID_DESC(name),				\
 	.val = mask,				\
 }
 
+/*
+ * 32bit ID regs are fully writable when the guest is 32bit
+ * capable. Nothing in the KVM code should rely on 32bit features
+ * anyway, only 64bit, so let the VMM do its worse.
+ */
+#define AA32_ID_WRITABLE(name) {		\
+	ID_DESC(name),				\
+	.visibility = aa32_id_visibility,	\
+	.val = GENMASK(31, 0),			\
+}
+
 /* sys_reg_desc initialiser for cpufeature ID registers that need filtering */
 #define ID_FILTERED(sysreg, name, mask) {	\
 	ID_DESC(sysreg),				\
@@ -3128,40 +3132,39 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
-	AA32_ID_SANITISED(ID_PFR0_EL1),
-	AA32_ID_SANITISED(ID_PFR1_EL1),
+	AA32_ID_WRITABLE(ID_PFR0_EL1),
+	AA32_ID_WRITABLE(ID_PFR1_EL1),
 	{ SYS_DESC(SYS_ID_DFR0_EL1),
 	  .access = access_id_reg,
 	  .get_user = get_id_reg,
 	  .set_user = set_id_dfr0_el1,
 	  .visibility = aa32_id_visibility,
 	  .reset = read_sanitised_id_dfr0_el1,
-	  .val = ID_DFR0_EL1_PerfMon_MASK |
-		 ID_DFR0_EL1_CopDbg_MASK, },
+	  .val = GENMASK(31, 0) },
 	ID_HIDDEN(ID_AFR0_EL1),
-	AA32_ID_SANITISED(ID_MMFR0_EL1),
-	AA32_ID_SANITISED(ID_MMFR1_EL1),
-	AA32_ID_SANITISED(ID_MMFR2_EL1),
-	AA32_ID_SANITISED(ID_MMFR3_EL1),
+	AA32_ID_WRITABLE(ID_MMFR0_EL1),
+	AA32_ID_WRITABLE(ID_MMFR1_EL1),
+	AA32_ID_WRITABLE(ID_MMFR2_EL1),
+	AA32_ID_WRITABLE(ID_MMFR3_EL1),
 
 	/* CRm=2 */
-	AA32_ID_SANITISED(ID_ISAR0_EL1),
-	AA32_ID_SANITISED(ID_ISAR1_EL1),
-	AA32_ID_SANITISED(ID_ISAR2_EL1),
-	AA32_ID_SANITISED(ID_ISAR3_EL1),
-	AA32_ID_SANITISED(ID_ISAR4_EL1),
-	AA32_ID_SANITISED(ID_ISAR5_EL1),
-	AA32_ID_SANITISED(ID_MMFR4_EL1),
-	AA32_ID_SANITISED(ID_ISAR6_EL1),
+	AA32_ID_WRITABLE(ID_ISAR0_EL1),
+	AA32_ID_WRITABLE(ID_ISAR1_EL1),
+	AA32_ID_WRITABLE(ID_ISAR2_EL1),
+	AA32_ID_WRITABLE(ID_ISAR3_EL1),
+	AA32_ID_WRITABLE(ID_ISAR4_EL1),
+	AA32_ID_WRITABLE(ID_ISAR5_EL1),
+	AA32_ID_WRITABLE(ID_MMFR4_EL1),
+	AA32_ID_WRITABLE(ID_ISAR6_EL1),
 
 	/* CRm=3 */
-	AA32_ID_SANITISED(MVFR0_EL1),
-	AA32_ID_SANITISED(MVFR1_EL1),
-	AA32_ID_SANITISED(MVFR2_EL1),
+	AA32_ID_WRITABLE(MVFR0_EL1),
+	AA32_ID_WRITABLE(MVFR1_EL1),
+	AA32_ID_WRITABLE(MVFR2_EL1),
 	ID_UNALLOCATED(3,3),
-	AA32_ID_SANITISED(ID_PFR2_EL1),
+	AA32_ID_WRITABLE(ID_PFR2_EL1),
 	ID_HIDDEN(ID_DFR1_EL1),
-	AA32_ID_SANITISED(ID_MMFR5_EL1),
+	AA32_ID_WRITABLE(ID_MMFR5_EL1),
 	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */
@@ -5606,11 +5609,13 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu)
 
 	guard(mutex)(&kvm->arch.config_lock);
 
-	if (!(static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) &&
-	      irqchip_in_kernel(kvm) &&
-	      kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)) {
-		kvm->arch.id_regs[IDREG_IDX(SYS_ID_AA64PFR0_EL1)] &= ~ID_AA64PFR0_EL1_GIC_MASK;
-		kvm->arch.id_regs[IDREG_IDX(SYS_ID_PFR1_EL1)] &= ~ID_PFR1_EL1_GIC_MASK;
+	if (!irqchip_in_kernel(kvm)) {
+		u64 val;
+
+		val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
+		kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val);
+		val = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;
+		kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, val);
 	}
 
 	if (vcpu_has_nv(vcpu)) {
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index 4c12092..bb92853 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -64,29 +64,37 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter)
 static int iter_mark_lpis(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long intid, flags;
 	struct vgic_irq *irq;
-	unsigned long intid;
 	int nr_lpis = 0;
 
+	xa_lock_irqsave(&dist->lpi_xa, flags);
+
 	xa_for_each(&dist->lpi_xa, intid, irq) {
 		if (!vgic_try_get_irq_ref(irq))
 			continue;
 
-		xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+		__xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
 		nr_lpis++;
 	}
 
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
 	return nr_lpis;
 }
 
 static void iter_unmark_lpis(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long intid, flags;
 	struct vgic_irq *irq;
-	unsigned long intid;
 
 	xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
-		xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+		xa_lock_irqsave(&dist->lpi_xa, flags);
+		__xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+		xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
+		/* vgic_put_irq() expects to be called outside of the xa_lock */
 		vgic_put_irq(kvm, irq);
 	}
 }
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 1796b1a..da62edb 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -53,7 +53,7 @@ void kvm_vgic_early_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	xa_init(&dist->lpi_xa);
+	xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ);
 }
 
 /* CREATION */
@@ -71,6 +71,7 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type);
 int kvm_vgic_create(struct kvm *kvm, u32 type)
 {
 	struct kvm_vcpu *vcpu;
+	u64 aa64pfr0, pfr1;
 	unsigned long i;
 	int ret;
 
@@ -161,10 +162,19 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 
-	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
+	aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
+	pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;
+
+	if (type == KVM_DEV_TYPE_ARM_VGIC_V2) {
 		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
-	else
+	} else {
 		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
+		aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
+		pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3);
+	}
+
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0);
+	kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1);
 
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V3)
 		kvm->arch.vgic.nassgicap = system_supports_direct_sgis();
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index ce3e3ed..3f1c4b1 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -78,6 +78,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq;
+	unsigned long flags;
 	int ret;
 
 	/* In this case there is no put, since we keep the reference. */
@@ -88,7 +89,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	if (!irq)
 		return ERR_PTR(-ENOMEM);
 
-	ret = xa_reserve(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT);
+	ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT);
 	if (ret) {
 		kfree(irq);
 		return ERR_PTR(ret);
@@ -103,7 +104,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 	irq->target_vcpu = vcpu;
 	irq->group = 1;
 
-	xa_lock(&dist->lpi_xa);
+	xa_lock_irqsave(&dist->lpi_xa, flags);
 
 	/*
 	 * There could be a race with another vgic_add_lpi(), so we need to
@@ -114,21 +115,18 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
 		/* Someone was faster with adding this LPI, lets use that. */
 		kfree(irq);
 		irq = oldirq;
-
-		goto out_unlock;
+	} else {
+		ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0));
 	}
 
-	ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0));
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
+
 	if (ret) {
 		xa_release(&dist->lpi_xa, intid);
 		kfree(irq);
-	}
 
-out_unlock:
-	xa_unlock(&dist->lpi_xa);
-
-	if (ret)
 		return ERR_PTR(ret);
+	}
 
 	/*
 	 * We "cache" the configuration table entries in our struct vgic_irq's.
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 6fbb4b0..2f75ef1 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -301,7 +301,8 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
 		return;
 
 	/* Hide GICv3 sysreg if necessary */
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2 ||
+	    !irqchip_in_kernel(vcpu->kvm)) {
 		vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
 				      ICH_HCR_EL2_TC);
 		return;
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 6dd5a10..8d20c53 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -28,7 +28,7 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
  *     kvm->arch.config_lock (mutex)
  *       its->cmd_lock (mutex)
  *         its->its_lock (mutex)
- *           vgic_dist->lpi_xa.xa_lock
+ *           vgic_dist->lpi_xa.xa_lock		must be taken with IRQs disabled
  *             vgic_cpu->ap_list_lock		must be taken with IRQs disabled
  *               vgic_irq->irq_lock		must be taken with IRQs disabled
  *
@@ -141,32 +141,39 @@ static __must_check bool vgic_put_irq_norelease(struct kvm *kvm, struct vgic_irq
 void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned long flags;
 
-	if (irq->intid >= VGIC_MIN_LPI)
-		might_lock(&dist->lpi_xa.xa_lock);
+	/*
+	 * Normally the lock is only taken when the refcount drops to 0.
+	 * Acquire/release it early on lockdep kernels to make locking issues
+	 * in rare release paths a bit more obvious.
+	 */
+	if (IS_ENABLED(CONFIG_LOCKDEP) && irq->intid >= VGIC_MIN_LPI) {
+		guard(spinlock_irqsave)(&dist->lpi_xa.xa_lock);
+	}
 
 	if (!__vgic_put_irq(kvm, irq))
 		return;
 
-	xa_lock(&dist->lpi_xa);
+	xa_lock_irqsave(&dist->lpi_xa, flags);
 	vgic_release_lpi_locked(dist, irq);
-	xa_unlock(&dist->lpi_xa);
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
 }
 
 static void vgic_release_deleted_lpis(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
-	unsigned long intid;
+	unsigned long flags, intid;
 	struct vgic_irq *irq;
 
-	xa_lock(&dist->lpi_xa);
+	xa_lock_irqsave(&dist->lpi_xa, flags);
 
 	xa_for_each(&dist->lpi_xa, intid, irq) {
 		if (irq->pending_release)
 			vgic_release_lpi_locked(dist, irq);
 	}
 
-	xa_unlock(&dist->lpi_xa);
+	xa_unlock_irqrestore(&dist->lpi_xa, flags);
 }
 
 void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index f7e0fee..7ac88ff 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -35,6 +35,8 @@
 
 #define KERNEL_START (KERNEL_BINARY_TEXT_START)
 
+#define ALIGNMENT_OK(ptr, type) (((ptr) & (sizeof(type) - 1)) == 0)
+
 extern struct unwind_table_entry __start___unwind[];
 extern struct unwind_table_entry __stop___unwind[];
 
@@ -257,12 +259,15 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 	if (pc_is_kernel_fn(pc, _switch_to) ||
 	    pc == (unsigned long)&_switch_to_ret) {
 		info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
-		info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
+		if (ALIGNMENT_OK(info->prev_sp, long))
+			info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
+		else
+			info->prev_ip = info->prev_sp = 0;
 		return 1;
 	}
 
 #ifdef CONFIG_IRQSTACKS
-	if (pc == (unsigned long)&_call_on_stack) {
+	if (pc == (unsigned long)&_call_on_stack && ALIGNMENT_OK(info->sp, long)) {
 		info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
 		info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
 		return 1;
@@ -370,8 +375,10 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 			info->prev_sp = info->sp - frame_size;
 			if (e->Millicode)
 				info->rp = info->r31;
-			else if (rpoffset)
+			else if (rpoffset && ALIGNMENT_OK(info->prev_sp, long))
 				info->rp = *(unsigned long *)(info->prev_sp - rpoffset);
+			else
+				info->rp = 0;
 			info->prev_ip = info->rp;
 			info->rp = 0;
 		}
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index fda0346..11422cb 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -689,8 +689,20 @@ bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu)
 	 */
 
 	read_lock_irqsave(&imsic->vsfile_lock, flags);
-	if (imsic->vsfile_cpu > -1)
-		ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	if (imsic->vsfile_cpu > -1) {
+		/*
+		 * This function is typically called from kvm_vcpu_block() via
+		 * kvm_arch_vcpu_runnable() upon WFI trap. The kvm_vcpu_block()
+		 * can be preempted and the blocking VCPU might resume on a
+		 * different CPU. This means it is possible that current CPU
+		 * does not match the imsic->vsfile_cpu hence this function
+		 * must check imsic->vsfile_cpu before accessing HGEIP CSR.
+		 */
+		if (imsic->vsfile_cpu != vcpu->cpu)
+			ret = true;
+		else
+			ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	}
 	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
 
 	return ret;
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 525fb5a..58f5f35 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -171,7 +171,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				enum kvm_mr_change change)
 {
 	hva_t hva, reg_end, size;
-	gpa_t base_gpa;
 	bool writable;
 	int ret = 0;
 
@@ -190,15 +189,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	hva = new->userspace_addr;
 	size = new->npages << PAGE_SHIFT;
 	reg_end = hva + size;
-	base_gpa = new->base_gfn << PAGE_SHIFT;
 	writable = !(new->flags & KVM_MEM_READONLY);
 
 	mmap_read_lock(current->mm);
 
 	/*
 	 * A memory region could potentially cover multiple VMAs, and
-	 * any holes between them, so iterate over all of them to find
-	 * out if we can map any of them right now.
+	 * any holes between them, so iterate over all of them.
 	 *
 	 *     +--------------------------------------------+
 	 * +---------------+----------------+   +----------------+
@@ -209,7 +206,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 */
 	do {
 		struct vm_area_struct *vma;
-		hva_t vm_start, vm_end;
+		hva_t vm_end;
 
 		vma = find_vma_intersection(current->mm, hva, reg_end);
 		if (!vma)
@@ -225,36 +222,18 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		}
 
 		/* Take the intersection of this VMA with the memory region */
-		vm_start = max(hva, vma->vm_start);
 		vm_end = min(reg_end, vma->vm_end);
 
 		if (vma->vm_flags & VM_PFNMAP) {
-			gpa_t gpa = base_gpa + (vm_start - hva);
-			phys_addr_t pa;
-
-			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
-			pa += vm_start - vma->vm_start;
-
 			/* IO region dirty page logging not allowed */
 			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
 				ret = -EINVAL;
 				goto out;
 			}
-
-			ret = kvm_riscv_mmu_ioremap(kvm, gpa, pa, vm_end - vm_start,
-						    writable, false);
-			if (ret)
-				break;
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
 
-	if (change == KVM_MR_FLAGS_ONLY)
-		goto out;
-
-	if (ret)
-		kvm_riscv_mmu_iounmap(kvm, base_gpa, size);
-
 out:
 	mmap_read_unlock(current->mm);
 	return ret;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index bccb919..5ce35ab 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -212,7 +212,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
+	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1ULL) &&
 		!kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause);
 }
 
diff --git a/arch/x86/include/asm/amd/node.h b/arch/x86/include/asm/amd/node.h
index 23fe617..a672b87 100644
--- a/arch/x86/include/asm/amd/node.h
+++ b/arch/x86/include/asm/amd/node.h
@@ -23,7 +23,6 @@
 #define AMD_NODE0_PCI_SLOT	0x18
 
 struct pci_dev *amd_node_get_func(u16 node, u8 func);
-struct pci_dev *amd_node_get_root(u16 node);
 
 static inline u16 amd_num_nodes(void)
 {
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 9792e32..1baa86d 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -93,6 +93,7 @@
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
 #define EXIT_REASON_NOTIFY              75
+#define EXIT_REASON_SEAMCALL            76
 #define EXIT_REASON_TDCALL              77
 #define EXIT_REASON_MSR_READ_IMM        84
 #define EXIT_REASON_MSR_WRITE_IMM       85
diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index a40176b..3d0a476 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -34,62 +34,6 @@ struct pci_dev *amd_node_get_func(u16 node, u8 func)
 	return pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(AMD_NODE0_PCI_SLOT + node, func));
 }
 
-#define DF_BLK_INST_CNT		0x040
-#define	DF_CFG_ADDR_CNTL_LEGACY	0x084
-#define	DF_CFG_ADDR_CNTL_DF4	0xC04
-
-#define DF_MAJOR_REVISION	GENMASK(27, 24)
-
-static u16 get_cfg_addr_cntl_offset(struct pci_dev *df_f0)
-{
-	u32 reg;
-
-	/*
-	 * Revision fields added for DF4 and later.
-	 *
-	 * Major revision of '0' is found pre-DF4. Field is Read-as-Zero.
-	 */
-	if (pci_read_config_dword(df_f0, DF_BLK_INST_CNT, &reg))
-		return 0;
-
-	if (reg & DF_MAJOR_REVISION)
-		return DF_CFG_ADDR_CNTL_DF4;
-
-	return DF_CFG_ADDR_CNTL_LEGACY;
-}
-
-struct pci_dev *amd_node_get_root(u16 node)
-{
-	struct pci_dev *root;
-	u16 cntl_off;
-	u8 bus;
-
-	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
-		return NULL;
-
-	/*
-	 * D18F0xXXX [Config Address Control] (DF::CfgAddressCntl)
-	 * Bits [7:0] (SecBusNum) holds the bus number of the root device for
-	 * this Data Fabric instance. The segment, device, and function will be 0.
-	 */
-	struct pci_dev *df_f0 __free(pci_dev_put) = amd_node_get_func(node, 0);
-	if (!df_f0)
-		return NULL;
-
-	cntl_off = get_cfg_addr_cntl_offset(df_f0);
-	if (!cntl_off)
-		return NULL;
-
-	if (pci_read_config_byte(df_f0, cntl_off, &bus))
-		return NULL;
-
-	/* Grab the pointer for the actual root device instance. */
-	root = pci_get_domain_bus_and_slot(0, bus, 0);
-
-	pci_dbg(root, "is root for AMD node %u\n", node);
-	return root;
-}
-
 static struct pci_dev **amd_roots;
 
 /* Protect the PCI config register pairs used for SMN. */
@@ -274,51 +218,21 @@ DEFINE_SHOW_STORE_ATTRIBUTE(smn_node);
 DEFINE_SHOW_STORE_ATTRIBUTE(smn_address);
 DEFINE_SHOW_STORE_ATTRIBUTE(smn_value);
 
-static int amd_cache_roots(void)
+static struct pci_dev *get_next_root(struct pci_dev *root)
 {
-	u16 node, num_nodes = amd_num_nodes();
-
-	amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL);
-	if (!amd_roots)
-		return -ENOMEM;
-
-	for (node = 0; node < num_nodes; node++)
-		amd_roots[node] = amd_node_get_root(node);
-
-	return 0;
-}
-
-static int reserve_root_config_spaces(void)
-{
-	struct pci_dev *root = NULL;
-	struct pci_bus *bus = NULL;
-
-	while ((bus = pci_find_next_bus(bus))) {
-		/* Root device is Device 0 Function 0 on each Primary Bus. */
-		root = pci_get_slot(bus, 0);
-		if (!root)
+	while ((root = pci_get_class(PCI_CLASS_BRIDGE_HOST << 8, root))) {
+		/* Root device is Device 0 Function 0. */
+		if (root->devfn)
 			continue;
 
 		if (root->vendor != PCI_VENDOR_ID_AMD &&
 		    root->vendor != PCI_VENDOR_ID_HYGON)
 			continue;
 
-		pci_dbg(root, "Reserving PCI config space\n");
-
-		/*
-		 * There are a few SMN index/data pairs and other registers
-		 * that shouldn't be accessed by user space.
-		 * So reserve the entire PCI config space for simplicity rather
-		 * than covering specific registers piecemeal.
-		 */
-		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
-			pci_err(root, "Failed to reserve config space\n");
-			return -EEXIST;
-		}
+		break;
 	}
 
-	smn_exclusive = true;
-	return 0;
+	return root;
 }
 
 static bool enable_dfs;
@@ -332,7 +246,8 @@ __setup("amd_smn_debugfs_enable", amd_smn_enable_dfs);
 
 static int __init amd_smn_init(void)
 {
-	int err;
+	u16 count, num_roots, roots_per_node, node, num_nodes;
+	struct pci_dev *root;
 
 	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
 		return 0;
@@ -342,13 +257,48 @@ static int __init amd_smn_init(void)
 	if (amd_roots)
 		return 0;
 
-	err = amd_cache_roots();
-	if (err)
-		return err;
+	num_roots = 0;
+	root = NULL;
+	while ((root = get_next_root(root))) {
+		pci_dbg(root, "Reserving PCI config space\n");
 
-	err = reserve_root_config_spaces();
-	if (err)
-		return err;
+		/*
+		 * There are a few SMN index/data pairs and other registers
+		 * that shouldn't be accessed by user space. So reserve the
+		 * entire PCI config space for simplicity rather than covering
+		 * specific registers piecemeal.
+		 */
+		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
+			pci_err(root, "Failed to reserve config space\n");
+			return -EEXIST;
+		}
+
+		num_roots++;
+	}
+
+	pr_debug("Found %d AMD root devices\n", num_roots);
+
+	if (!num_roots)
+		return -ENODEV;
+
+	num_nodes = amd_num_nodes();
+	amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL);
+	if (!amd_roots)
+		return -ENOMEM;
+
+	roots_per_node = num_roots / num_nodes;
+
+	count = 0;
+	node = 0;
+	root = NULL;
+	while (node < num_nodes && (root = get_next_root(root))) {
+		/* Use one root for each node and skip the rest. */
+		if (count++ % roots_per_node)
+			continue;
+
+		pci_dbg(root, "is root for AMD node %u\n", node);
+		amd_roots[node++] = root;
+	}
 
 	if (enable_dfs) {
 		debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir);
@@ -358,6 +308,8 @@ static int __init amd_smn_init(void)
 		debugfs_create_file("value",	0600, debugfs_dir, NULL, &smn_value_fops);
 	}
 
+	smn_exclusive = true;
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8e36964..2ba9f2d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1038,6 +1038,7 @@ static void init_amd_zen4(struct cpuinfo_x86 *c)
 static const struct x86_cpu_id zen5_rdseed_microcode[] = {
 	ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a),
 	ZEN_MODEL_STEP_UCODE(0x1a, 0x11, 0x0, 0x0b101054),
+	{},
 };
 
 static void init_amd_zen5(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b7c797d..dc82153 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -220,10 +220,12 @@ static bool need_sha_check(u32 cur_rev)
 	case 0xaa001: return cur_rev <= 0xaa00116; break;
 	case 0xaa002: return cur_rev <= 0xaa00218; break;
 	case 0xb0021: return cur_rev <= 0xb002146; break;
+	case 0xb0081: return cur_rev <= 0xb008111; break;
 	case 0xb1010: return cur_rev <= 0xb101046; break;
 	case 0xb2040: return cur_rev <= 0xb204031; break;
 	case 0xb4040: return cur_rev <= 0xb404031; break;
 	case 0xb6000: return cur_rev <= 0xb600031; break;
+	case 0xb6080: return cur_rev <= 0xb608031; break;
 	case 0xb7000: return cur_rev <= 0xb700031; break;
 	default: break;
 	}
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index f286b57..fef0054 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -216,7 +216,7 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm)
  * This function is called from IOMMU driver to notify
  * SVM to schedule in a particular vCPU of a particular VM.
  */
-int avic_ga_log_notifier(u32 ga_tag)
+static int avic_ga_log_notifier(u32 ga_tag)
 {
 	unsigned long flags;
 	struct kvm_svm *kvm_svm;
@@ -788,7 +788,7 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	INIT_LIST_HEAD(&svm->ir_list);
-	spin_lock_init(&svm->ir_list_lock);
+	raw_spin_lock_init(&svm->ir_list_lock);
 
 	if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm))
 		return 0;
@@ -816,9 +816,9 @@ static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd)
 	if (!vcpu)
 		return;
 
-	spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
+	raw_spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
 	list_del(&irqfd->vcpu_list);
-	spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
+	raw_spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
 }
 
 int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
@@ -855,7 +855,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		 * list of IRQs being posted to the vCPU, to ensure the IRTE
 		 * isn't programmed with stale pCPU/IsRunning information.
 		 */
-		guard(spinlock_irqsave)(&svm->ir_list_lock);
+		guard(raw_spinlock_irqsave)(&svm->ir_list_lock);
 
 		/*
 		 * Update the target pCPU for IOMMU doorbells if the vCPU is
@@ -972,7 +972,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
 	 * up-to-date entry information, or that this task will wait until
 	 * svm_ir_list_add() completes to set the new target pCPU.
 	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
+	raw_spin_lock_irqsave(&svm->ir_list_lock, flags);
 
 	entry = svm->avic_physical_id_entry;
 	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
@@ -997,7 +997,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
 
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action);
 
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -1035,7 +1035,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
 	 * or that this task will wait until svm_ir_list_add() completes to
 	 * mark the vCPU as not running.
 	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
+	raw_spin_lock_irqsave(&svm->ir_list_lock, flags);
 
 	avic_update_iommu_vcpu_affinity(vcpu, -1, action);
 
@@ -1059,7 +1059,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
 
 	svm->avic_physical_id_entry = entry;
 
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
 void avic_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1243,3 +1243,9 @@ bool __init avic_hardware_setup(void)
 
 	return true;
 }
+
+void avic_hardware_unsetup(void)
+{
+	if (avic)
+		amd_iommu_register_ga_log_notifier(NULL);
+}
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index a6443fe..da6e80b 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -677,11 +677,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 		 */
 		svm_copy_lbrs(vmcb02, vmcb12);
 		vmcb02->save.dbgctl &= ~DEBUGCTL_RESERVED_BITS;
-		svm_update_lbrv(&svm->vcpu);
-
-	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
+	} else {
 		svm_copy_lbrs(vmcb02, vmcb01);
 	}
+	svm_update_lbrv(&svm->vcpu);
 }
 
 static inline bool is_evtinj_soft(u32 evtinj)
@@ -833,11 +832,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 			svm->soft_int_next_rip = vmcb12_rip;
 	}
 
-	vmcb02->control.virt_ext            = vmcb01->control.virt_ext &
-					      LBR_CTL_ENABLE_MASK;
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV))
-		vmcb02->control.virt_ext  |=
-			(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK);
+	/* LBR_CTL_ENABLE_MASK is controlled by svm_update_lbrv() */
 
 	if (!nested_vmcb_needs_vls_intercept(svm))
 		vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
@@ -1189,13 +1184,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
 	if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
-		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
+		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)))
 		svm_copy_lbrs(vmcb12, vmcb02);
-		svm_update_lbrv(vcpu);
-	} else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) {
+	else
 		svm_copy_lbrs(vmcb01, vmcb02);
-		svm_update_lbrv(vcpu);
-	}
+
+	svm_update_lbrv(vcpu);
 
 	if (vnmi) {
 		if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 153c12d..10c21e4 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -806,60 +806,43 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
 }
 
+static void __svm_enable_lbrv(struct kvm_vcpu *vcpu)
+{
+	to_svm(vcpu)->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
+}
+
 void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
+	__svm_enable_lbrv(vcpu);
 	svm_recalc_lbr_msr_intercepts(vcpu);
-
-	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
-	if (is_guest_mode(vcpu))
-		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
 }
 
-static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
+static void __svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-
 	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
-	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
-	svm_recalc_lbr_msr_intercepts(vcpu);
-
-	/*
-	 * Move the LBR msrs back to the vmcb01 to avoid copying them
-	 * on nested guest entries.
-	 */
-	if (is_guest_mode(vcpu))
-		svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb);
-}
-
-static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm)
-{
-	/*
-	 * If LBR virtualization is disabled, the LBR MSRs are always kept in
-	 * vmcb01.  If LBR virtualization is enabled and L1 is running VMs of
-	 * its own, the MSRs are moved between vmcb01 and vmcb02 as needed.
-	 */
-	return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb :
-								   svm->vmcb01.ptr;
+	to_svm(vcpu)->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
 }
 
 void svm_update_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK;
-	bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) ||
+	bool enable_lbrv = (svm->vmcb->save.dbgctl & DEBUGCTLMSR_LBR) ||
 			    (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
 			    (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK));
 
-	if (enable_lbrv == current_enable_lbrv)
-		return;
+	if (enable_lbrv && !current_enable_lbrv)
+		__svm_enable_lbrv(vcpu);
+	else if (!enable_lbrv && current_enable_lbrv)
+		__svm_disable_lbrv(vcpu);
 
-	if (enable_lbrv)
-		svm_enable_lbrv(vcpu);
-	else
-		svm_disable_lbrv(vcpu);
+	/*
+	 * During nested transitions, it is possible that the current VMCB has
+	 * LBR_CTL set, but the previous LBR_CTL had it cleared (or vice versa).
+	 * In this case, even though LBR_CTL does not need an update, intercepts
+	 * do, so always recalculate the intercepts here.
+	 */
+	svm_recalc_lbr_msr_intercepts(vcpu);
 }
 
 void disable_nmi_singlestep(struct vcpu_svm *svm)
@@ -921,6 +904,8 @@ static void svm_hardware_unsetup(void)
 {
 	int cpu;
 
+	avic_hardware_unsetup();
+
 	sev_hardware_unsetup();
 
 	for_each_possible_cpu(cpu)
@@ -2722,19 +2707,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = svm->tsc_aux;
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl;
+		msr_info->data = svm->vmcb->save.dbgctl;
 		break;
 	case MSR_IA32_LASTBRANCHFROMIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from;
+		msr_info->data = svm->vmcb->save.br_from;
 		break;
 	case MSR_IA32_LASTBRANCHTOIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to;
+		msr_info->data = svm->vmcb->save.br_to;
 		break;
 	case MSR_IA32_LASTINTFROMIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from;
+		msr_info->data = svm->vmcb->save.last_excp_from;
 		break;
 	case MSR_IA32_LASTINTTOIP:
-		msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to;
+		msr_info->data = svm->vmcb->save.last_excp_to;
 		break;
 	case MSR_VM_HSAVE_PA:
 		msr_info->data = svm->nested.hsave_msr;
@@ -3002,7 +2987,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
-		svm_get_lbr_vmcb(svm)->save.dbgctl = data;
+		if (svm->vmcb->save.dbgctl == data)
+			break;
+
+		svm->vmcb->save.dbgctl = data;
+		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
 		svm_update_lbrv(vcpu);
 		break;
 	case MSR_VM_HSAVE_PA:
@@ -5386,12 +5375,6 @@ static __init int svm_hardware_setup(void)
 
 	svm_hv_hardware_setup();
 
-	for_each_possible_cpu(cpu) {
-		r = svm_cpu_init(cpu);
-		if (r)
-			goto err;
-	}
-
 	enable_apicv = avic_hardware_setup();
 	if (!enable_apicv) {
 		enable_ipiv = false;
@@ -5435,6 +5418,13 @@ static __init int svm_hardware_setup(void)
 	svm_set_cpu_caps();
 
 	kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED;
+
+	for_each_possible_cpu(cpu) {
+		r = svm_cpu_init(cpu);
+		if (r)
+			goto err;
+	}
+
 	return 0;
 
 err:
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e4b04f4..c856d8e 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -329,7 +329,7 @@ struct vcpu_svm {
 	 * back into remapped mode).
 	 */
 	struct list_head ir_list;
-	spinlock_t ir_list_lock;
+	raw_spinlock_t ir_list_lock;
 
 	struct vcpu_sev_es_state sev_es;
 
@@ -805,7 +805,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 )
 
 bool __init avic_hardware_setup(void);
-int avic_ga_log_notifier(u32 ga_tag);
+void avic_hardware_unsetup(void);
 void avic_vm_destroy(struct kvm *kvm);
 int avic_vm_init(struct kvm *kvm);
 void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb);
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index bc5ece7..412d082 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -98,7 +98,7 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa,
 	error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK)
 		      ? PFERR_PRESENT_MASK : 0;
 
-	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
+	if (exit_qualification & EPT_VIOLATION_GVA_IS_VALID)
 		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
 			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7627196..bcea087 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6728,6 +6728,14 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_NOTIFY:
 		/* Notify VM exit is not exposed to L1 */
 		return false;
+	case EXIT_REASON_SEAMCALL:
+	case EXIT_REASON_TDCALL:
+		/*
+		 * SEAMCALL and TDCALL unconditionally VM-Exit, but aren't
+		 * virtualized by KVM for L1 hypervisors, i.e. L1 should
+		 * never want or expect such an exit.
+		 */
+		return false;
 	default:
 		return true;
 	}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f87c216..91b6f2f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6032,6 +6032,12 @@ static int handle_vmx_instruction(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_tdx_instruction(struct kvm_vcpu *vcpu)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
 #ifndef CONFIG_X86_SGX_KVM
 static int handle_encls(struct kvm_vcpu *vcpu)
 {
@@ -6157,6 +6163,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_ENCLS]		      = handle_encls,
 	[EXIT_REASON_BUS_LOCK]                = handle_bus_lock_vmexit,
 	[EXIT_REASON_NOTIFY]		      = handle_notify,
+	[EXIT_REASON_SEAMCALL]		      = handle_tdx_instruction,
+	[EXIT_REASON_TDCALL]		      = handle_tdx_instruction,
 	[EXIT_REASON_MSR_READ_IMM]            = handle_rdmsr_imm,
 	[EXIT_REASON_MSR_WRITE_IMM]           = handle_wrmsr_imm,
 };
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b4b5d2d..c9c2aa6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3874,15 +3874,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 
 /*
  * Returns true if the MSR in question is managed via XSTATE, i.e. is context
- * switched with the rest of guest FPU state.  Note!  S_CET is _not_ context
- * switched via XSTATE even though it _is_ saved/restored via XSAVES/XRSTORS.
- * Because S_CET is loaded on VM-Enter and VM-Exit via dedicated VMCS fields,
- * the value saved/restored via XSTATE is always the host's value.  That detail
- * is _extremely_ important, as the guest's S_CET must _never_ be resident in
- * hardware while executing in the host.  Loading guest values for U_CET and
- * PL[0-3]_SSP while executing in the kernel is safe, as U_CET is specific to
- * userspace, and PL[0-3]_SSP are only consumed when transitioning to lower
- * privilege levels, i.e. are effectively only consumed by userspace as well.
+ * switched with the rest of guest FPU state.
+ *
+ * Note, S_CET is _not_ saved/restored via XSAVES/XRSTORS.
  */
 static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
@@ -3905,6 +3899,11 @@ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr)
  * MSR that is managed via XSTATE.  Note, the caller is responsible for doing
  * the initial FPU load, this helper only ensures that guest state is resident
  * in hardware (the kernel can load its FPU state in IRQ context).
+ *
+ * Note, loading guest values for U_CET and PL[0-3]_SSP while executing in the
+ * kernel is safe, as U_CET is specific to userspace, and PL[0-3]_SSP are only
+ * consumed when transitioning to lower privilege levels, i.e. are effectively
+ * only consumed by userspace as well.
  */
 static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu,
 						  struct msr_data *msr_info,
@@ -11807,6 +11806,9 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
+	if (KVM_BUG_ON(vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm))
+		return;
+
 	/* Exclude PKRU, it's restored separately immediately after VM-Exit. */
 	fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true);
 	trace_kvm_fpu(1);
@@ -11815,6 +11817,9 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 /* When vcpu_run ends, restore user space FPU context. */
 static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
+	if (KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm))
+		return;
+
 	fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false);
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
@@ -12137,9 +12142,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 	int r;
 
 	vcpu_load(vcpu);
-	if (kvm_mpx_supported())
-		kvm_load_guest_fpu(vcpu);
-
 	kvm_vcpu_srcu_read_lock(vcpu);
 
 	r = kvm_apic_accept_events(vcpu);
@@ -12156,9 +12158,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 
 out:
 	kvm_vcpu_srcu_read_unlock(vcpu);
-
-	if (kvm_mpx_supported())
-		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
 	return r;
 }
@@ -12788,6 +12787,7 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
 	u64 xfeatures_mask;
+	bool fpu_in_use;
 	int i;
 
 	/*
@@ -12811,13 +12811,23 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event)
 	BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX);
 
 	/*
-	 * All paths that lead to INIT are required to load the guest's FPU
-	 * state (because most paths are buried in KVM_RUN).
+	 * Unload guest FPU state (if necessary) before zeroing XSTATE fields
+	 * as the kernel can only modify the state when its resident in memory,
+	 * i.e. when it's not loaded into hardware.
+	 *
+	 * WARN if the vCPU's desire to run, i.e. whether or not its in KVM_RUN,
+	 * doesn't match the loaded/in-use state of the FPU, as KVM_RUN is the
+	 * only path that can trigger INIT emulation _and_ loads FPU state, and
+	 * KVM_RUN should _always_ load FPU state.
 	 */
-	kvm_put_guest_fpu(vcpu);
+	WARN_ON_ONCE(vcpu->wants_to_run != fpstate->in_use);
+	fpu_in_use = fpstate->in_use;
+	if (fpu_in_use)
+		kvm_put_guest_fpu(vcpu);
 	for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX)
 		fpstate_clear_xstate_component(fpstate, i);
-	kvm_load_guest_fpu(vcpu);
+	if (fpu_in_use)
+		kvm_load_guest_fpu(vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c
index 37600fa..416f265 100644
--- a/drivers/gpio/gpio-aggregator.c
+++ b/drivers/gpio/gpio-aggregator.c
@@ -723,6 +723,7 @@ struct gpiochip_fwd *devm_gpiochip_fwd_alloc(struct device *dev,
 	chip->get_multiple = gpio_fwd_get_multiple_locked;
 	chip->set = gpio_fwd_set;
 	chip->set_multiple = gpio_fwd_set_multiple_locked;
+	chip->set_config = gpio_fwd_set_config;
 	chip->to_irq = gpio_fwd_to_irq;
 	chip->base = -1;
 	chip->ngpio = ngpios;
diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c
index 09a448c..3c8fd32 100644
--- a/drivers/gpio/gpio-tb10x.c
+++ b/drivers/gpio/gpio-tb10x.c
@@ -50,25 +50,6 @@ static inline u32 tb10x_reg_read(struct tb10x_gpio *gpio, unsigned int offs)
 	return ioread32(gpio->base + offs);
 }
 
-static inline void tb10x_reg_write(struct tb10x_gpio *gpio, unsigned int offs,
-				u32 val)
-{
-	iowrite32(val, gpio->base + offs);
-}
-
-static inline void tb10x_set_bits(struct tb10x_gpio *gpio, unsigned int offs,
-				u32 mask, u32 val)
-{
-	u32 r;
-
-	guard(gpio_generic_lock_irqsave)(&gpio->chip);
-
-	r = tb10x_reg_read(gpio, offs);
-	r = (r & ~mask) | (val & mask);
-
-	tb10x_reg_write(gpio, offs, r);
-}
-
 static int tb10x_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
 {
 	struct tb10x_gpio *tb10x_gpio = gpiochip_get_data(chip);
diff --git a/drivers/gpio/gpiolib-swnode.c b/drivers/gpio/gpiolib-swnode.c
index f21dbc2..e3806db 100644
--- a/drivers/gpio/gpiolib-swnode.c
+++ b/drivers/gpio/gpiolib-swnode.c
@@ -41,7 +41,7 @@ static struct gpio_device *swnode_get_gpio_device(struct fwnode_handle *fwnode)
 	    !strcmp(gdev_node->name, GPIOLIB_SWNODE_UNDEFINED_NAME))
 		return ERR_PTR(-ENOENT);
 
-	gdev = gpio_device_find_by_label(gdev_node->name);
+	gdev = gpio_device_find_by_fwnode(fwnode);
 	return gdev ?: ERR_PTR(-EPROBE_DEFER);
 }
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 9952e41..cd8800b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -5296,6 +5296,8 @@ static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos)
 	struct gpio_device *gdev;
 	loff_t index = *pos;
 
+	s->private = NULL;
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return NULL;
@@ -5329,7 +5331,11 @@ static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos)
 
 static void gpiolib_seq_stop(struct seq_file *s, void *v)
 {
-	struct gpiolib_seq_priv *priv = s->private;
+	struct gpiolib_seq_priv *priv;
+
+	priv = s->private;
+	if (!priv)
+		return;
 
 	srcu_read_unlock(&gpio_devices_srcu, priv->idx);
 	kfree(priv);
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 4b2f7d7..da2565e 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -245,7 +245,7 @@
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
       cmd_hdrtest = \
 		$(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \
-		 PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
+		 PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
 		touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a2ca9ac..923f0fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1267,6 +1267,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
 
+	/* VM entity stopped if process killed, don't clear freed pt bo */
+	if (!amdgpu_vm_ready(vm))
+		return 0;
+
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3d032c4..2819ace 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5243,10 +5243,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
-	r = amdgpu_dpm_notify_rlc_state(adev, false);
-	if (r)
-		return r;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 61268aa..7333e19 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2632,9 +2632,14 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 8c0e5d0..aa7987d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2355,8 +2355,11 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	if (!ret && !psp->securedisplay_context.context.resp_status) {
 		psp->securedisplay_context.context.initialized = true;
 		mutex_init(&psp->securedisplay_context.mutex);
-	} else
+	} else {
+		/* don't try again */
+		psp->securedisplay_context.context.bin_desc.size_bytes = 0;
 		return ret;
+	}
 
 	mutex_lock(&psp->securedisplay_context.mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 811124f..f9e2edf 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -407,7 +407,8 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr,
 		return -EINVAL;
 	}
 
-	if (adev->kfd.init_complete && !amdgpu_in_reset(adev))
+	if (adev->kfd.init_complete && !amdgpu_in_reset(adev) &&
+		!adev->in_suspend)
 		flags |= AMDGPU_XCP_OPS_KFD;
 
 	if (flags & AMDGPU_XCP_OPS_KFD) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 7693b79..8056539 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -3102,6 +3102,11 @@ static int gfx_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 5976ed5..2b7aba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4399,6 +4399,11 @@ static int gfx_v7_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	gfx_v7_0_gpu_early_init(adev);
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 0856ff6..8a81713 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2023,6 +2023,11 @@ static int gfx_v8_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 77f9d5b..c90cbe0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -2292,7 +2292,9 @@ static int gfx_v9_4_3_cp_resume(struct amdgpu_device *adev)
 		r = amdgpu_xcp_init(adev->xcp_mgr, num_xcp, mode);
 
 	} else {
-		if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
+		if (adev->in_suspend)
+			amdgpu_xcp_restore_partition_mode(adev->xcp_mgr);
+		else if (amdgpu_xcp_query_partition_mode(adev->xcp_mgr,
 						    AMDGPU_XCP_FL_NONE) ==
 		    AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE)
 			r = amdgpu_xcp_switch_partition_mode(
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 64b240b..a9be7a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -142,13 +142,37 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	return err;
 }
 
+static int psp_v11_wait_for_tos_unload(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+	uint32_t sol_reg1, sol_reg2;
+	int retry_loop;
+
+	/* Wait for the TOS to be unloaded */
+	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
+		sol_reg1 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+		usleep_range(1000, 2000);
+		sol_reg2 = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+		if (sol_reg1 == sol_reg2)
+			return 0;
+	}
+	dev_err(adev->dev, "TOS unload failed, C2PMSG_33: %x C2PMSG_81: %x",
+		RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_33),
+		RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81));
+
+	return -ETIME;
+}
+
 static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
-
 	int ret;
 	int retry_loop;
 
+	/* For a reset done at the end of S3, only wait for TOS to be unloaded */
+	if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev))
+		return psp_v11_wait_for_tos_unload(psp);
+
 	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
 		/* Wait for bootloader to signify that is
 		    ready having bit 31 of C2PMSG_35 set to 1 */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index bfa3199..91c0188 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3563,6 +3563,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 	/* Do mst topology probing after resuming cached state*/
 	drm_connector_list_iter_begin(ddev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
+		bool init = false;
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
 			continue;
@@ -3572,7 +3573,14 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 		    aconnector->mst_root)
 			continue;
 
-		drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
+		scoped_guard(mutex, &aconnector->mst_mgr.lock) {
+			init = !aconnector->mst_mgr.mst_primary;
+		}
+		if (init)
+			dm_helpers_dp_mst_start_top_mgr(aconnector->dc_link->ctx,
+				aconnector->dc_link, false);
+		else
+			drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
 	}
 	drm_connector_list_iter_end(&iter);
 
@@ -8030,7 +8038,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 				       "mode %dx%d@%dHz is not native, enabling scaling\n",
 				       adjusted_mode->hdisplay, adjusted_mode->vdisplay,
 				       drm_mode_vrefresh(adjusted_mode));
-			dm_new_connector_state->scaling = RMX_FULL;
+			dm_new_connector_state->scaling = RMX_ASPECT;
 		}
 		return 0;
 	}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f263e1a..00dac86 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1302,7 +1302,8 @@ static int odm_combine_segments_show(struct seq_file *m, void *unused)
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
 
-	if (pipe_ctx != NULL && pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments)
+	if (pipe_ctx && pipe_ctx->stream_res.tg &&
+	    pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments)
 		pipe_ctx->stream_res.tg->funcs->get_odm_combine_segments(pipe_ctx->stream_res.tg, &segments);
 
 	seq_printf(m, "%d\n", segments);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index 8530316..1173c53 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -1141,6 +1141,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 		    !sink->edid_caps.edid_hdmi)
 			sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
 		else if (dc_is_dvi_signal(sink->sink_signal) &&
+			 dc_is_dvi_signal(link->connector_signal) &&
 			 aud_support->hdmi_audio_native &&
 			 sink->edid_caps.edid_hdmi)
 			sink->sink_signal = SIGNAL_TYPE_HDMI_TYPE_A;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 518d07a..bc29a92 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -195,24 +195,6 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
-int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
-{
-	int ret = 0;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (pp_funcs && pp_funcs->notify_rlc_state) {
-		mutex_lock(&adev->pm.mutex);
-
-		ret = pp_funcs->notify_rlc_state(
-				adev->powerplay.pp_handle,
-				en);
-
-		mutex_unlock(&adev->pm.mutex);
-	}
-
-	return ret;
-}
-
 int amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index b5fbb0f..a7e6d78 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4724,14 +4724,14 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 		ret = devm_device_add_group(adev->dev,
 					    &amdgpu_pm_policy_attr_group);
 		if (ret)
-			goto err_out0;
+			goto err_out1;
 	}
 
 	if (amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_GPUBOARD)) {
 		ret = devm_device_add_group(adev->dev,
 					    &amdgpu_board_attr_group);
 		if (ret)
-			goto err_out0;
+			goto err_out1;
 		if (amdgpu_pm_get_sensor_generic(adev, AMDGPU_PP_SENSOR_MAXNODEPOWERLIMIT,
 						 (void *)&tmp) != -EOPNOTSUPP) {
 			sysfs_add_file_to_group(&adev->dev->kobj,
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 65c1d98..af48aea 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -424,8 +424,6 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
-int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
-
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index fb80868..244b8c3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2040,6 +2040,12 @@ static int smu_disable_dpms(struct smu_context *smu)
 	    smu->is_apu && (amdgpu_in_reset(adev) || adev->in_s0ix))
 		return 0;
 
+	/* vangogh s0ix */
+	if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 0) ||
+	     amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(11, 5, 2)) &&
+	    adev->in_s0ix)
+		return 0;
+
 	/*
 	 * For gpu reset, runpm and hibernation through BACO,
 	 * BACO feature has to be kept enabled.
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 2c9869f..0708d0f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2217,6 +2217,9 @@ static int vangogh_post_smu_init(struct smu_context *smu)
 	uint32_t total_cu = adev->gfx.config.max_cu_per_sh *
 		adev->gfx.config.max_sh_per_se * adev->gfx.config.max_shader_engines;
 
+	if (adev->in_s0ix)
+		return 0;
+
 	/* allow message will be sent after enable message on Vangogh*/
 	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_GFXCLK_BIT) &&
 			(adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e58c0c1..b915753 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -413,7 +413,7 @@
 #
 # Enable locally for CONFIG_DRM_I915_WERROR=y. See also scripts/Makefile.build
 ifdef CONFIG_DRM_I915_WERROR
-    cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none -Werror $<
+    cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none -Werror $<
 endif
 
 # header test
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 88b147f..c90b358 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -205,7 +205,7 @@ static u64 div_u64_roundup(u64 nom, u32 den)
 
 u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count)
 {
-	return div_u64_roundup(count * NSEC_PER_SEC, gt->clock_frequency);
+	return mul_u64_u32_div(count, NSEC_PER_SEC, gt->clock_frequency);
 }
 
 u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
@@ -215,7 +215,7 @@ u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
 
 u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns)
 {
-	return div_u64_roundup(gt->clock_frequency * ns, NSEC_PER_SEC);
+	return mul_u64_u32_div(ns, gt->clock_frequency, NSEC_PER_SEC);
 }
 
 u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 25e9703..30d5889 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1595,8 +1595,20 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 err_vma_res:
 	i915_vma_resource_free(vma_res);
 err_fence:
-	if (work)
-		dma_fence_work_commit_imm(&work->base);
+	if (work) {
+		/*
+		 * When pinning VMA to GGTT on CHV or BXT with VTD enabled,
+		 * commit VMA binding asynchronously to avoid risk of lock
+		 * inversion among reservation_ww locks held here and
+		 * cpu_hotplug_lock acquired from stop_machine(), which we
+		 * wrap around GGTT updates when running in those environments.
+		 */
+		if (i915_vma_is_ggtt(vma) &&
+		    intel_vm_no_concurrent_access_wa(vma->vm->i915))
+			dma_fence_work_commit(&work->base);
+		else
+			dma_fence_work_commit_imm(&work->base);
+	}
 err_rpm:
 	intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
 
diff --git a/drivers/gpu/drm/imagination/Kconfig b/drivers/gpu/drm/imagination/Kconfig
index 682dd26..0482bfc 100644
--- a/drivers/gpu/drm/imagination/Kconfig
+++ b/drivers/gpu/drm/imagination/Kconfig
@@ -7,6 +7,7 @@
 	depends on DRM
 	depends on MMU
 	depends on PM
+	depends on POWER_SEQUENCING || !POWER_SEQUENCING
 	select DRM_EXEC
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_SCHED
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
index bc75275..c4c6d02 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
@@ -283,6 +283,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
 	unsigned int i;
 	unsigned long flags;
 
+	/* release GCE HW usage and start autosuspend */
+	pm_runtime_mark_last_busy(cmdq_cl->chan->mbox->dev);
+	pm_runtime_put_autosuspend(cmdq_cl->chan->mbox->dev);
+
 	if (data->sta < 0)
 		return;
 
@@ -618,6 +622,9 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank)
 		mtk_crtc->config_updating = false;
 		spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
 
+		if (pm_runtime_resume_and_get(mtk_crtc->cmdq_client.chan->mbox->dev) < 0)
+			goto update_config_out;
+
 		mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle);
 		mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0);
 		goto update_config_out;
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index 02349bd..788b52c 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -21,9 +21,6 @@
 
 static const u64 modifiers[] = {
 	DRM_FORMAT_MOD_LINEAR,
-	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
-				AFBC_FORMAT_MOD_SPLIT |
-				AFBC_FORMAT_MOD_SPARSE),
 	DRM_FORMAT_MOD_INVALID,
 };
 
@@ -71,26 +68,7 @@ static bool mtk_plane_format_mod_supported(struct drm_plane *plane,
 					   uint32_t format,
 					   uint64_t modifier)
 {
-	if (modifier == DRM_FORMAT_MOD_LINEAR)
-		return true;
-
-	if (modifier != DRM_FORMAT_MOD_ARM_AFBC(
-				AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
-				AFBC_FORMAT_MOD_SPLIT |
-				AFBC_FORMAT_MOD_SPARSE))
-		return false;
-
-	if (format != DRM_FORMAT_XRGB8888 &&
-	    format != DRM_FORMAT_ARGB8888 &&
-	    format != DRM_FORMAT_BGRX8888 &&
-	    format != DRM_FORMAT_BGRA8888 &&
-	    format != DRM_FORMAT_ABGR8888 &&
-	    format != DRM_FORMAT_XBGR8888 &&
-	    format != DRM_FORMAT_RGB888 &&
-	    format != DRM_FORMAT_BGR888)
-		return false;
-
-	return true;
+	return modifier == DRM_FORMAT_MOD_LINEAR;
 }
 
 static void mtk_plane_destroy_state(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index e97e39a..12b1dba 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2867,7 +2867,9 @@ nv50_display_create(struct drm_device *dev)
 	}
 
 	/* Assign the correct format modifiers */
-	if (disp->disp->object.oclass >= TU102_DISP)
+	if (disp->disp->object.oclass >= GB202_DISP)
+		nouveau_display(dev)->format_modifiers = wndwca7e_modifiers;
+	else if (disp->disp->object.oclass >= TU102_DISP)
 		nouveau_display(dev)->format_modifiers = wndwc57e_modifiers;
 	else
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 15f9242..5d998f0 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -104,4 +104,5 @@ struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder);
 extern const u64 disp50xx_modifiers[];
 extern const u64 disp90xx_modifiers[];
 extern const u64 wndwc57e_modifiers[];
+extern const u64 wndwca7e_modifiers[];
 #endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index e2c55f4..ef9e410 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -786,13 +786,14 @@ nv50_wndw_destroy(struct drm_plane *plane)
 }
 
 /* This function assumes the format has already been validated against the plane
- * and the modifier was validated against the device-wides modifier list at FB
+ * and the modifier was validated against the device-wide modifier list at FB
  * creation time.
  */
 static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 					    u32 format, u64 modifier)
 {
 	struct nouveau_drm *drm = nouveau_drm(plane->dev);
+	const struct drm_format_info *info = drm_format_info(format);
 	uint8_t i;
 
 	/* All chipsets can display all formats in linear layout */
@@ -800,13 +801,32 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 		return true;
 
 	if (drm->client.device.info.chipset < 0xc0) {
-		const struct drm_format_info *info = drm_format_info(format);
 		const uint8_t kind = (modifier >> 12) & 0xff;
 
 		if (!format) return false;
 
 		for (i = 0; i < info->num_planes; i++)
 			if ((info->cpp[i] != 4) && kind != 0x70) return false;
+	} else if (drm->client.device.info.chipset >= 0x1b2) {
+		const uint8_t slayout = ((modifier >> 22) & 0x1) |
+			((modifier >> 25) & 0x6);
+
+		if (!format)
+			return false;
+
+		/*
+		 * Note in practice this implies only formats where cpp is equal
+		 * for each plane, or >= 4 for all planes, are supported.
+		 */
+		for (i = 0; i < info->num_planes; i++) {
+			if (((info->cpp[i] == 2) && slayout != 3) ||
+			    ((info->cpp[i] == 1) && slayout != 2) ||
+			    ((info->cpp[i] >= 4) && slayout != 1))
+				return false;
+
+			/* 24-bit not supported. It has yet another layout */
+			WARN_ON(info->cpp[i] == 3);
+		}
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
index 0d8e9a9..2cec8cf 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
@@ -179,6 +179,39 @@ wndwca7e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
+/****************************************************************
+ *            Log2(block height) ----------------------------+  *
+ *            Page Kind ----------------------------------+  |  *
+ *            Gob Height/Page Kind Generation ------+     |  |  *
+ *                          Sector layout -------+  |     |  |  *
+ *                          Compression ------+  |  |     |  |  */
+const u64 wndwca7e_modifiers[] = { /*         |  |  |     |  |  */
+	/* 4cpp+ modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 5),
+	/* 1cpp/8bpp modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 5),
+	/* 2cpp/16bpp modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 5),
+	/* All formats support linear */
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 static const struct nv50_wndw_func
 wndwca7e = {
 	.acquire = wndwc37e_acquire,
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index c8e949f..fe174a4 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -173,26 +173,15 @@ int drm_sched_entity_error(struct drm_sched_entity *entity)
 }
 EXPORT_SYMBOL(drm_sched_entity_error);
 
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb);
+
 static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
 {
 	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
-
-	drm_sched_fence_scheduled(job->s_fence, NULL);
-	drm_sched_fence_finished(job->s_fence, -ESRCH);
-	WARN_ON(job->s_fence->parent);
-	job->sched->ops->free_job(job);
-}
-
-/* Signal the scheduler finished fence when the entity in question is killed. */
-static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
-					  struct dma_fence_cb *cb)
-{
-	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
-						 finish_cb);
+	struct dma_fence *f;
 	unsigned long index;
 
-	dma_fence_put(f);
-
 	/* Wait for all dependencies to avoid data corruptions */
 	xa_for_each(&job->dependencies, index, f) {
 		struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
@@ -220,6 +209,21 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 		dma_fence_put(f);
 	}
 
+	drm_sched_fence_scheduled(job->s_fence, NULL);
+	drm_sched_fence_finished(job->s_fence, -ESRCH);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
+/* Signal the scheduler finished fence when the entity in question is killed. */
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
+						 finish_cb);
+
+	dma_fence_put(f);
+
 	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
 	schedule_work(&job->work);
 }
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 7d9e85e..f0e72d4 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -85,6 +85,7 @@
 config DRM_PIXPAPER
         tristate "DRM support for PIXPAPER display panels"
         depends on DRM && SPI
+        depends on MMU
         select DRM_CLIENT_SELECTION
         select DRM_GEM_SHMEM_HELPER
         select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 34d3396..4568992 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -988,16 +988,16 @@ void xe_device_shutdown(struct xe_device *xe)
 
 	drm_dbg(&xe->drm, "Shutting down device\n");
 
-	if (xe_driver_flr_disabled(xe)) {
-		xe_display_pm_shutdown(xe);
+	xe_display_pm_shutdown(xe);
 
-		xe_irq_suspend(xe);
+	xe_irq_suspend(xe);
 
-		for_each_gt(gt, xe, id)
-			xe_gt_shutdown(gt);
+	for_each_gt(gt, xe, id)
+		xe_gt_shutdown(gt);
 
-		xe_display_pm_shutdown_late(xe);
-	} else {
+	xe_display_pm_shutdown_late(xe);
+
+	if (!xe_driver_flr_disabled(xe)) {
 		/* BOOM! */
 		__xe_driver_flr(xe);
 	}
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 7715e74b..a8ab363 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -165,7 +165,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) {
 		err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs],
-					  &syncs_user[num_syncs], SYNC_PARSE_FLAG_EXEC |
+					  &syncs_user[num_syncs], NULL, 0,
+					  SYNC_PARSE_FLAG_EXEC |
 					  (xe_vm_in_lr_mode(vm) ?
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 37b2b93..cb5f204 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -10,6 +10,7 @@
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
+#include <drm/drm_syncobj.h>
 #include <uapi/drm/xe_drm.h>
 
 #include "xe_dep_scheduler.h"
@@ -324,6 +325,16 @@ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe,
 	}
 	xe_vm_put(migrate_vm);
 
+	if (!IS_ERR(q)) {
+		int err = drm_syncobj_create(&q->ufence_syncobj,
+					     DRM_SYNCOBJ_CREATE_SIGNALED,
+					     NULL);
+		if (err) {
+			xe_exec_queue_put(q);
+			return ERR_PTR(err);
+		}
+	}
+
 	return q;
 }
 ALLOW_ERROR_INJECTION(xe_exec_queue_create_bind, ERRNO);
@@ -333,6 +344,9 @@ void xe_exec_queue_destroy(struct kref *ref)
 	struct xe_exec_queue *q = container_of(ref, struct xe_exec_queue, refcount);
 	struct xe_exec_queue *eq, *next;
 
+	if (q->ufence_syncobj)
+		drm_syncobj_put(q->ufence_syncobj);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 27b76cf..df1c69d 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -15,6 +15,7 @@
 #include "xe_hw_fence_types.h"
 #include "xe_lrc_types.h"
 
+struct drm_syncobj;
 struct xe_execlist_exec_queue;
 struct xe_gt;
 struct xe_guc_exec_queue;
@@ -155,6 +156,12 @@ struct xe_exec_queue {
 		struct list_head link;
 	} pxp;
 
+	/** @ufence_syncobj: User fence syncobj */
+	struct drm_syncobj *ufence_syncobj;
+
+	/** @ufence_timeline_value: User fence timeline value */
+	u64 ufence_timeline_value;
+
 	/** @ops: submission backend exec queue operations */
 	const struct xe_exec_queue_ops *ops;
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 18f6327..283d846c 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -200,6 +200,9 @@ static void guc_ct_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc_ct *ct = arg;
 
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+	cancel_work_sync(&ct->dead.worker);
+#endif
 	ct_exit_safe_mode(ct);
 	destroy_workqueue(ct->g2h_wq);
 	xa_destroy(&ct->fence_lookup);
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index a4894eb..125698a 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -10,6 +10,7 @@
 
 #include <drm/drm_drv.h>
 #include <drm/drm_managed.h>
+#include <drm/drm_syncobj.h>
 #include <uapi/drm/xe_drm.h>
 
 #include <generated/xe_wa_oob.h>
@@ -1389,7 +1390,9 @@ static int xe_oa_user_extensions(struct xe_oa *oa, enum xe_oa_user_extn_from fro
 	return 0;
 }
 
-static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param)
+static int xe_oa_parse_syncs(struct xe_oa *oa,
+			     struct xe_oa_stream *stream,
+			     struct xe_oa_open_param *param)
 {
 	int ret, num_syncs, num_ufence = 0;
 
@@ -1409,7 +1412,9 @@ static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param)
 
 	for (num_syncs = 0; num_syncs < param->num_syncs; num_syncs++) {
 		ret = xe_sync_entry_parse(oa->xe, param->xef, &param->syncs[num_syncs],
-					  &param->syncs_user[num_syncs], 0);
+					  &param->syncs_user[num_syncs],
+					  stream->ufence_syncobj,
+					  ++stream->ufence_timeline_value, 0);
 		if (ret)
 			goto err_syncs;
 
@@ -1539,7 +1544,7 @@ static long xe_oa_config_locked(struct xe_oa_stream *stream, u64 arg)
 		return -ENODEV;
 
 	param.xef = stream->xef;
-	err = xe_oa_parse_syncs(stream->oa, &param);
+	err = xe_oa_parse_syncs(stream->oa, stream, &param);
 	if (err)
 		goto err_config_put;
 
@@ -1635,6 +1640,7 @@ static void xe_oa_destroy_locked(struct xe_oa_stream *stream)
 	if (stream->exec_q)
 		xe_exec_queue_put(stream->exec_q);
 
+	drm_syncobj_put(stream->ufence_syncobj);
 	kfree(stream);
 }
 
@@ -1826,6 +1832,7 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa,
 					  struct xe_oa_open_param *param)
 {
 	struct xe_oa_stream *stream;
+	struct drm_syncobj *ufence_syncobj;
 	int stream_fd;
 	int ret;
 
@@ -1836,17 +1843,31 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa,
 		goto exit;
 	}
 
+	ret = drm_syncobj_create(&ufence_syncobj, DRM_SYNCOBJ_CREATE_SIGNALED,
+				 NULL);
+	if (ret)
+		goto exit;
+
 	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
 	if (!stream) {
 		ret = -ENOMEM;
-		goto exit;
+		goto err_syncobj;
 	}
-
+	stream->ufence_syncobj = ufence_syncobj;
 	stream->oa = oa;
-	ret = xe_oa_stream_init(stream, param);
+
+	ret = xe_oa_parse_syncs(oa, stream, param);
 	if (ret)
 		goto err_free;
 
+	ret = xe_oa_stream_init(stream, param);
+	if (ret) {
+		while (param->num_syncs--)
+			xe_sync_entry_cleanup(&param->syncs[param->num_syncs]);
+		kfree(param->syncs);
+		goto err_free;
+	}
+
 	if (!param->disabled) {
 		ret = xe_oa_enable_locked(stream);
 		if (ret)
@@ -1870,6 +1891,8 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa,
 	xe_oa_stream_destroy(stream);
 err_free:
 	kfree(stream);
+err_syncobj:
+	drm_syncobj_put(ufence_syncobj);
 exit:
 	return ret;
 }
@@ -2083,22 +2106,14 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		goto err_exec_q;
 	}
 
-	ret = xe_oa_parse_syncs(oa, &param);
-	if (ret)
-		goto err_exec_q;
-
 	mutex_lock(&param.hwe->gt->oa.gt_lock);
 	ret = xe_oa_stream_open_ioctl_locked(oa, &param);
 	mutex_unlock(&param.hwe->gt->oa.gt_lock);
 	if (ret < 0)
-		goto err_sync_cleanup;
+		goto err_exec_q;
 
 	return ret;
 
-err_sync_cleanup:
-	while (param.num_syncs--)
-		xe_sync_entry_cleanup(&param.syncs[param.num_syncs]);
-	kfree(param.syncs);
 err_exec_q:
 	if (param.exec_q)
 		xe_exec_queue_put(param.exec_q);
diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
index 2628f78..daf701b 100644
--- a/drivers/gpu/drm/xe/xe_oa_types.h
+++ b/drivers/gpu/drm/xe/xe_oa_types.h
@@ -15,6 +15,8 @@
 #include "regs/xe_reg_defs.h"
 #include "xe_hw_engine_types.h"
 
+struct drm_syncobj;
+
 #define DEFAULT_XE_OA_BUFFER_SIZE SZ_16M
 
 enum xe_oa_report_header {
@@ -248,6 +250,12 @@ struct xe_oa_stream {
 	/** @xef: xe_file with which the stream was opened */
 	struct xe_file *xef;
 
+	/** @ufence_syncobj: User fence syncobj */
+	struct drm_syncobj *ufence_syncobj;
+
+	/** @ufence_timeline_value: User fence timeline value */
+	u64 ufence_timeline_value;
+
 	/** @last_fence: fence to use in stream destroy when needed */
 	struct dma_fence *last_fence;
 
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index 82872a5..d48ab7b 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -113,6 +113,8 @@ static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 			struct xe_sync_entry *sync,
 			struct drm_xe_sync __user *sync_user,
+			struct drm_syncobj *ufence_syncobj,
+			u64 ufence_timeline_value,
 			unsigned int flags)
 {
 	struct drm_xe_sync sync_in;
@@ -192,10 +194,15 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 		if (exec) {
 			sync->addr = sync_in.addr;
 		} else {
+			sync->ufence_timeline_value = ufence_timeline_value;
 			sync->ufence = user_fence_create(xe, sync_in.addr,
 							 sync_in.timeline_value);
 			if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence)))
 				return PTR_ERR(sync->ufence);
+			sync->ufence_chain_fence = dma_fence_chain_alloc();
+			if (!sync->ufence_chain_fence)
+				return -ENOMEM;
+			sync->ufence_syncobj = ufence_syncobj;
 		}
 
 		break;
@@ -239,7 +246,12 @@ void xe_sync_entry_signal(struct xe_sync_entry *sync, struct dma_fence *fence)
 	} else if (sync->ufence) {
 		int err;
 
-		dma_fence_get(fence);
+		drm_syncobj_add_point(sync->ufence_syncobj,
+				      sync->ufence_chain_fence,
+				      fence, sync->ufence_timeline_value);
+		sync->ufence_chain_fence = NULL;
+
+		fence = drm_syncobj_fence_get(sync->ufence_syncobj);
 		user_fence_get(sync->ufence);
 		err = dma_fence_add_callback(fence, &sync->ufence->cb,
 					     user_fence_cb);
@@ -259,7 +271,8 @@ void xe_sync_entry_cleanup(struct xe_sync_entry *sync)
 		drm_syncobj_put(sync->syncobj);
 	dma_fence_put(sync->fence);
 	dma_fence_chain_free(sync->chain_fence);
-	if (sync->ufence)
+	dma_fence_chain_free(sync->ufence_chain_fence);
+	if (!IS_ERR_OR_NULL(sync->ufence))
 		user_fence_put(sync->ufence);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index 256ffc1..51f2d80 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -8,6 +8,7 @@
 
 #include "xe_sync_types.h"
 
+struct drm_syncobj;
 struct xe_device;
 struct xe_exec_queue;
 struct xe_file;
@@ -21,6 +22,8 @@ struct xe_vm;
 int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 			struct xe_sync_entry *sync,
 			struct drm_xe_sync __user *sync_user,
+			struct drm_syncobj *ufence_syncobj,
+			u64 ufence_timeline_value,
 			unsigned int flags);
 int xe_sync_entry_add_deps(struct xe_sync_entry *sync,
 			   struct xe_sched_job *job);
diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h
index 30ac3f5..b88f183 100644
--- a/drivers/gpu/drm/xe/xe_sync_types.h
+++ b/drivers/gpu/drm/xe/xe_sync_types.h
@@ -18,9 +18,12 @@ struct xe_sync_entry {
 	struct drm_syncobj *syncobj;
 	struct dma_fence *fence;
 	struct dma_fence_chain *chain_fence;
+	struct dma_fence_chain *ufence_chain_fence;
+	struct drm_syncobj *ufence_syncobj;
 	struct xe_user_fence *ufence;
 	u64 addr;
 	u64 timeline_value;
+	u64 ufence_timeline_value;
 	u32 type;
 	u32 flags;
 };
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 63c65e3..ccb09ef 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3606,8 +3606,12 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	syncs_user = u64_to_user_ptr(args->syncs);
 	for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) {
+		struct xe_exec_queue *__q = q ?: vm->q[0];
+
 		err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs],
 					  &syncs_user[num_syncs],
+					  __q->ufence_syncobj,
+					  ++__q->ufence_timeline_value,
 					  (xe_vm_in_lr_mode(vm) ?
 					   SYNC_PARSE_FLAG_LR_MODE : 0) |
 					  (!args->num_binds ?
diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c
index 75c8d08..b9f370c 100644
--- a/drivers/i2c/muxes/i2c-mux-pca954x.c
+++ b/drivers/i2c/muxes/i2c-mux-pca954x.c
@@ -118,6 +118,7 @@ struct pca954x {
 	raw_spinlock_t lock;
 	struct regulator *supply;
 
+	struct gpio_desc *reset_gpio;
 	struct reset_control *reset_cont;
 };
 
@@ -315,25 +316,6 @@ static u8 pca954x_regval(struct pca954x *data, u8 chan)
 		return 1 << chan;
 }
 
-static void pca954x_reset_assert(struct pca954x *data)
-{
-	if (data->reset_cont)
-		reset_control_assert(data->reset_cont);
-}
-
-static void pca954x_reset_deassert(struct pca954x *data)
-{
-	if (data->reset_cont)
-		reset_control_deassert(data->reset_cont);
-}
-
-static void pca954x_reset_mux(struct pca954x *data)
-{
-	pca954x_reset_assert(data);
-	udelay(1);
-	pca954x_reset_deassert(data);
-}
-
 static int pca954x_select_chan(struct i2c_mux_core *muxc, u32 chan)
 {
 	struct pca954x *data = i2c_mux_priv(muxc);
@@ -347,8 +329,6 @@ static int pca954x_select_chan(struct i2c_mux_core *muxc, u32 chan)
 		ret = pca954x_reg_write(muxc->parent, client, regval);
 		data->last_chan = ret < 0 ? 0 : regval;
 	}
-	if (ret == -ETIMEDOUT && data->reset_cont)
-		pca954x_reset_mux(data);
 
 	return ret;
 }
@@ -358,7 +338,6 @@ static int pca954x_deselect_mux(struct i2c_mux_core *muxc, u32 chan)
 	struct pca954x *data = i2c_mux_priv(muxc);
 	struct i2c_client *client = data->client;
 	s32 idle_state;
-	int ret = 0;
 
 	idle_state = READ_ONCE(data->idle_state);
 	if (idle_state >= 0)
@@ -368,10 +347,8 @@ static int pca954x_deselect_mux(struct i2c_mux_core *muxc, u32 chan)
 	if (idle_state == MUX_IDLE_DISCONNECT) {
 		/* Deselect active channel */
 		data->last_chan = 0;
-		ret = pca954x_reg_write(muxc->parent, client,
-					data->last_chan);
-		if (ret == -ETIMEDOUT && data->reset_cont)
-			pca954x_reset_mux(data);
+		return pca954x_reg_write(muxc->parent, client,
+					 data->last_chan);
 	}
 
 	/* otherwise leave as-is */
@@ -550,10 +527,29 @@ static int pca954x_get_reset(struct device *dev, struct pca954x *data)
 	if (IS_ERR(data->reset_cont))
 		return dev_err_probe(dev, PTR_ERR(data->reset_cont),
 				     "Failed to get reset\n");
+	else if (data->reset_cont)
+		return 0;
+
+	/*
+	 * fallback to legacy reset-gpios
+	 */
+	data->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(data->reset_gpio)) {
+		return dev_err_probe(dev, PTR_ERR(data->reset_gpio),
+				     "Failed to get reset gpio");
+	}
 
 	return 0;
 }
 
+static void pca954x_reset_deassert(struct pca954x *data)
+{
+	if (data->reset_cont)
+		reset_control_deassert(data->reset_cont);
+	else
+		gpiod_set_value_cansleep(data->reset_gpio, 0);
+}
+
 /*
  * I2C init/probing/exit functions
  */
@@ -593,7 +589,7 @@ static int pca954x_probe(struct i2c_client *client)
 	if (ret)
 		goto fail_cleanup;
 
-	if (data->reset_cont) {
+	if (data->reset_cont || data->reset_gpio) {
 		udelay(1);
 		pca954x_reset_deassert(data);
 		/* Give the chip some time to recover. */
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index c0360c4..75d60f2 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -707,7 +707,8 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start,
 	struct iopt_area *area;
 	unsigned long unmapped_bytes = 0;
 	unsigned int tries = 0;
-	int rc = -ENOENT;
+	/* If there are no mapped entries then success */
+	int rc = 0;
 
 	/*
 	 * The domains_rwsem must be held in read mode any time any area->pages
@@ -777,8 +778,6 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start,
 
 		down_write(&iopt->iova_rwsem);
 	}
-	if (unmapped_bytes)
-		rc = 0;
 
 out_unlock_iova:
 	up_write(&iopt->iova_rwsem);
@@ -815,13 +814,8 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova,
 
 int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped)
 {
-	int rc;
-
-	rc = iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped);
 	/* If the IOVAs are empty then unmap all succeeds */
-	if (rc == -ENOENT)
-		return 0;
-	return rc;
+	return iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped);
 }
 
 /* The caller must always free all the nodes in the allowed_iova rb_root. */
diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
index 1542c5f..459a7c5 100644
--- a/drivers/iommu/iommufd/ioas.c
+++ b/drivers/iommu/iommufd/ioas.c
@@ -367,6 +367,10 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd)
 				     &unmapped);
 		if (rc)
 			goto out_put;
+		if (!unmapped) {
+			rc = -ENOENT;
+			goto out_put;
+		}
 	}
 
 	cmd->length = unmapped;
diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
index 4514575..b5b67a9 100644
--- a/drivers/iommu/iommufd/iova_bitmap.c
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -130,9 +130,8 @@ struct iova_bitmap {
 static unsigned long iova_bitmap_offset_to_index(struct iova_bitmap *bitmap,
 						 unsigned long iova)
 {
-	unsigned long pgsize = 1UL << bitmap->mapped.pgshift;
-
-	return iova / (BITS_PER_TYPE(*bitmap->bitmap) * pgsize);
+	return (iova >> bitmap->mapped.pgshift) /
+	       BITS_PER_TYPE(*bitmap->bitmap);
 }
 
 /*
diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index 8b6b357..c170345 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -268,7 +268,6 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 		return err;
 
 	rtc->alarm_irq = platform_get_irq(pdev, 0);
-	rtc->alarm_enabled = true;
 	err = devm_request_threaded_irq(dev, rtc->alarm_irq, NULL,
 					cpcap_rtc_alarm_irq,
 					IRQF_TRIGGER_NONE | IRQF_ONESHOT,
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index aabe62c..7e9f7cb 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -316,7 +316,7 @@ static int rx8025_init_client(struct i2c_client *client)
 			return hour_reg;
 		rx8025->is_24 = (hour_reg & RX8035_BIT_HOUR_1224);
 	} else {
-		rx8025->is_24 = (ctrl[1] & RX8025_BIT_CTRL1_1224);
+		rx8025->is_24 = (ctrl[0] & RX8025_BIT_CTRL1_1224);
 	}
 out:
 	return err;
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index 76ecf7b..54c8429 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -258,7 +258,6 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 
 	irq_set_status_flags(rtc->irq, IRQ_NOAUTOEN);
 
-	rtc->irq_en = true;
 	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
 				tps6586x_rtc_irq,
 				IRQF_ONESHOT,
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index c040afc..0086816 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -1949,7 +1949,7 @@ static umode_t ufs_sysfs_hid_is_visible(struct kobject *kobj,
 	return	hba->dev_info.hid_sup ? attr->mode : 0;
 }
 
-const struct attribute_group ufs_sysfs_hid_group = {
+static const struct attribute_group ufs_sysfs_hid_group = {
 	.name = "hid",
 	.attrs = ufs_sysfs_hid,
 	.is_visible = ufs_sysfs_hid_is_visible,
diff --git a/drivers/ufs/core/ufs-sysfs.h b/drivers/ufs/core/ufs-sysfs.h
index 6efb82a..8d94af3 100644
--- a/drivers/ufs/core/ufs-sysfs.h
+++ b/drivers/ufs/core/ufs-sysfs.h
@@ -14,6 +14,5 @@ void ufs_sysfs_remove_nodes(struct device *dev);
 
 extern const struct attribute_group ufs_sysfs_unit_descriptor_group;
 extern const struct attribute_group ufs_sysfs_lun_attributes_group;
-extern const struct attribute_group ufs_sysfs_hid_group;
 
 #endif
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 9ca27de..d6a060a 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5066,7 +5066,8 @@ static int ufshcd_link_startup(struct ufs_hba *hba)
 	 * If UFS device isn't active then we will have to issue link startup
 	 * 2 times to make sure the device state move to active.
 	 */
-	if (!ufshcd_is_ufs_dev_active(hba))
+	if (!(hba->quirks & UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE) &&
+	    !ufshcd_is_ufs_dev_active(hba))
 		link_startup_again = true;
 
 link_startup:
@@ -5131,12 +5132,8 @@ static int ufshcd_link_startup(struct ufs_hba *hba)
 	ufshcd_readl(hba, REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER);
 	ret = ufshcd_make_hba_operational(hba);
 out:
-	if (ret) {
+	if (ret)
 		dev_err(hba->dev, "link startup failed %d\n", ret);
-		ufshcd_print_host_state(hba);
-		ufshcd_print_pwr_info(hba);
-		ufshcd_print_evt_hist(hba);
-	}
 	return ret;
 }
 
@@ -8503,8 +8500,6 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 				DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP) &
 				UFS_DEV_HID_SUPPORT;
 
-	sysfs_update_group(&hba->dev->kobj, &ufs_sysfs_hid_group);
-
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
 
 	err = ufshcd_read_string_desc(hba, model_index,
@@ -10661,7 +10656,7 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba)
  * @mmio_base: base register address
  * @irq: Interrupt line of device
  *
- * Return: 0 on success, non-zero value on failure.
+ * Return: 0 on success; < 0 on failure.
  */
 int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 {
@@ -10891,8 +10886,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	if (err)
 		goto out_disable;
 
-	async_schedule(ufshcd_async_scan, hba);
 	ufs_sysfs_add_nodes(hba->dev);
+	async_schedule(ufshcd_async_scan, hba);
 
 	device_enable_async_suspend(dev);
 	ufshcd_pm_qos_init(hba);
@@ -10902,7 +10897,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	hba->is_irq_enabled = false;
 	ufshcd_hba_exit(hba);
 out_error:
-	return err;
+	return err > 0 ? -EIO : err;
 }
 EXPORT_SYMBOL_GPL(ufshcd_init);
 
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 3e83dc5..eba0e66 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -740,8 +740,21 @@ static int ufs_qcom_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
 
 
 	/* reset the connected UFS device during power down */
-	if (ufs_qcom_is_link_off(hba) && host->device_reset)
+	if (ufs_qcom_is_link_off(hba) && host->device_reset) {
 		ufs_qcom_device_reset_ctrl(hba, true);
+		/*
+		 * After sending the SSU command, asserting the rst_n
+		 * line causes the device firmware to wake up and
+		 * execute its reset routine.
+		 *
+		 * During this process, the device may draw current
+		 * beyond the permissible limit for low-power mode (LPM).
+		 * A 10ms delay, based on experimental observations,
+		 * allows the UFS device to complete its hardware reset
+		 * before transitioning the power rail to LPM.
+		 */
+		usleep_range(10000, 11000);
+	}
 
 	return ufs_qcom_ice_suspend(host);
 }
diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c
index b87e037..5f65dfa 100644
--- a/drivers/ufs/host/ufshcd-pci.c
+++ b/drivers/ufs/host/ufshcd-pci.c
@@ -15,6 +15,7 @@
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_qos.h>
+#include <linux/suspend.h>
 #include <linux/debugfs.h>
 #include <linux/uuid.h>
 #include <linux/acpi.h>
@@ -31,6 +32,7 @@ struct intel_host {
 	u32		dsm_fns;
 	u32		active_ltr;
 	u32		idle_ltr;
+	int		saved_spm_lvl;
 	struct dentry	*debugfs_root;
 	struct gpio_desc *reset_gpio;
 };
@@ -347,6 +349,7 @@ static int ufs_intel_common_init(struct ufs_hba *hba)
 	host = devm_kzalloc(hba->dev, sizeof(*host), GFP_KERNEL);
 	if (!host)
 		return -ENOMEM;
+	host->saved_spm_lvl = -1;
 	ufshcd_set_variant(hba, host);
 	intel_dsm_init(host, hba->dev);
 	if (INTEL_DSM_SUPPORTED(host, RESET)) {
@@ -425,7 +428,8 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba)
 static int ufs_intel_adl_init(struct ufs_hba *hba)
 {
 	hba->nop_out_timeout = 200;
-	hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8;
+	hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 |
+		       UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE;
 	hba->caps |= UFSHCD_CAP_WB_EN;
 	return ufs_intel_common_init(hba);
 }
@@ -538,6 +542,66 @@ static int ufshcd_pci_restore(struct device *dev)
 
 	return ufshcd_system_resume(dev);
 }
+
+static int ufs_intel_suspend_prepare(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	struct intel_host *host = ufshcd_get_variant(hba);
+	int err;
+
+	/*
+	 * Only s2idle (S0ix) retains link state.  Force power-off
+	 * (UFS_PM_LVL_5) for any other case.
+	 */
+	if (pm_suspend_target_state != PM_SUSPEND_TO_IDLE && hba->spm_lvl < UFS_PM_LVL_5) {
+		host->saved_spm_lvl = hba->spm_lvl;
+		hba->spm_lvl = UFS_PM_LVL_5;
+	}
+
+	err = ufshcd_suspend_prepare(dev);
+
+	if (err < 0 && host->saved_spm_lvl != -1) {
+		hba->spm_lvl = host->saved_spm_lvl;
+		host->saved_spm_lvl = -1;
+	}
+
+	return err;
+}
+
+static void ufs_intel_resume_complete(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	struct intel_host *host = ufshcd_get_variant(hba);
+
+	ufshcd_resume_complete(dev);
+
+	if (host->saved_spm_lvl != -1) {
+		hba->spm_lvl = host->saved_spm_lvl;
+		host->saved_spm_lvl = -1;
+	}
+}
+
+static int ufshcd_pci_suspend_prepare(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	if (!strcmp(hba->vops->name, "intel-pci"))
+		return ufs_intel_suspend_prepare(dev);
+
+	return ufshcd_suspend_prepare(dev);
+}
+
+static void ufshcd_pci_resume_complete(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	if (!strcmp(hba->vops->name, "intel-pci")) {
+		ufs_intel_resume_complete(dev);
+		return;
+	}
+
+	ufshcd_resume_complete(dev);
+}
 #endif
 
 /**
@@ -611,8 +675,8 @@ static const struct dev_pm_ops ufshcd_pci_pm_ops = {
 	.thaw		= ufshcd_system_resume,
 	.poweroff	= ufshcd_system_suspend,
 	.restore	= ufshcd_pci_restore,
-	.prepare	= ufshcd_suspend_prepare,
-	.complete	= ufshcd_resume_complete,
+	.prepare	= ufshcd_pci_suspend_prepare,
+	.complete	= ufshcd_pci_resume_complete,
 #endif
 };
 
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index b8ac7b7..018055f 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -388,11 +388,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 			 * lease. Release one here, and the second below.
 			 */
 			cfid->has_lease = false;
-			kref_put(&cfid->refcount, smb2_close_cached_fid);
+			close_cached_dir(cfid);
 		}
 		spin_unlock(&cfids->cfid_list_lock);
 
-		kref_put(&cfid->refcount, smb2_close_cached_fid);
+		close_cached_dir(cfid);
 	} else {
 		*ret_cfid = cfid;
 		atomic_inc(&tcon->num_remote_opens);
@@ -438,12 +438,14 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon,
 
 static void
 smb2_close_cached_fid(struct kref *ref)
+__releases(&cfid->cfids->cfid_list_lock)
 {
 	struct cached_fid *cfid = container_of(ref, struct cached_fid,
 					       refcount);
 	int rc;
 
-	spin_lock(&cfid->cfids->cfid_list_lock);
+	lockdep_assert_held(&cfid->cfids->cfid_list_lock);
+
 	if (cfid->on_list) {
 		list_del(&cfid->entry);
 		cfid->on_list = false;
@@ -478,7 +480,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon,
 	spin_lock(&cfid->cfids->cfid_list_lock);
 	if (cfid->has_lease) {
 		cfid->has_lease = false;
-		kref_put(&cfid->refcount, smb2_close_cached_fid);
+		close_cached_dir(cfid);
 	}
 	spin_unlock(&cfid->cfids->cfid_list_lock);
 	close_cached_dir(cfid);
@@ -487,7 +489,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon,
 
 void close_cached_dir(struct cached_fid *cfid)
 {
-	kref_put(&cfid->refcount, smb2_close_cached_fid);
+	kref_put_lock(&cfid->refcount, smb2_close_cached_fid, &cfid->cfids->cfid_list_lock);
 }
 
 /*
@@ -596,7 +598,7 @@ cached_dir_offload_close(struct work_struct *work)
 
 	WARN_ON(cfid->on_list);
 
-	kref_put(&cfid->refcount, smb2_close_cached_fid);
+	close_cached_dir(cfid);
 	cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cached_close);
 }
 
@@ -762,7 +764,7 @@ static void cfids_laundromat_worker(struct work_struct *work)
 			 * Drop the ref-count from above, either the lease-ref (if there
 			 * was one) or the extra one acquired.
 			 */
-			kref_put(&cfid->refcount, smb2_close_cached_fid);
+			close_cached_dir(cfid);
 	}
 	queue_delayed_work(cfid_put_wq, &cfids->laundromat_work,
 			   dir_cache_timeout * HZ);
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 09e3fc8..69cb81f 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1294,6 +1294,8 @@ static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	smb2_to_name = cifs_convert_path_to_utf16(to_name, cifs_sb);
 	if (smb2_to_name == NULL) {
 		rc = -ENOMEM;
+		if (cfile)
+			cifsFileInfo_put(cfile);
 		goto smb2_rename_path;
 	}
 	in_iov.iov_base = smb2_to_name;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index b0739a2..8b4a457 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4054,9 +4054,12 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
 
 		smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base;
 
-		smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset),
-				le32_to_cpu(smb_rsp->OutputBufferLength), &rsp_iov,
+		rc = smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset),
+				le32_to_cpu(smb_rsp->OutputBufferLength),
+				&rsp_iov,
 				sizeof(struct file_notify_information));
+		if (rc)
+			goto cnotify_exit;
 
 		*out_data = kmemdup((char *)smb_rsp + le16_to_cpu(smb_rsp->OutputBufferOffset),
 				le32_to_cpu(smb_rsp->OutputBufferLength), GFP_KERNEL);
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 7d86553..5d3b48e 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2606,7 +2606,7 @@ void ksmbd_rdma_destroy(void)
 	}
 }
 
-bool ksmbd_rdma_capable_netdev(struct net_device *netdev)
+static bool ksmbd_find_rdma_capable_netdev(struct net_device *netdev)
 {
 	struct smb_direct_device *smb_dev;
 	int i;
@@ -2648,6 +2648,28 @@ bool ksmbd_rdma_capable_netdev(struct net_device *netdev)
 	return rdma_capable;
 }
 
+bool ksmbd_rdma_capable_netdev(struct net_device *netdev)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	if (ksmbd_find_rdma_capable_netdev(netdev))
+		return true;
+
+	/* check if netdev is bridge or VLAN */
+	if (netif_is_bridge_master(netdev) ||
+	    netdev->priv_flags & IFF_802_1Q_VLAN)
+		netdev_for_each_lower_dev(netdev, lower_dev, iter)
+			if (ksmbd_find_rdma_capable_netdev(lower_dev))
+				return true;
+
+	/* check if netdev is IPoIB safely without layer violation */
+	if (netdev->type == ARPHRD_INFINIBAND)
+		return true;
+
+	return false;
+}
+
 static const struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = {
 	.prepare	= smb_direct_prepare,
 	.disconnect	= smb_direct_disconnect,
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index ee49f208..6917de83 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -726,8 +726,10 @@ xfs_trim_rtgroup_extents(
 			break;
 		}
 
-		if (!tr.queued)
+		if (!tr.queued) {
+			kfree(tr.extents);
 			break;
+		}
 
 		/*
 		 * We hand the extent list to the discard function here so the
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d3f6e3e..490e12c 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1091,6 +1091,29 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = {
 };
 #endif /* CONFIG_XFS_RT */
 
+#ifdef DEBUG
+static void
+xfs_check_atomic_cow_conversion(
+	struct xfs_inode		*ip,
+	xfs_fileoff_t			offset_fsb,
+	xfs_filblks_t			count_fsb,
+	const struct xfs_bmbt_irec	*cmap)
+{
+	struct xfs_iext_cursor		icur;
+	struct xfs_bmbt_irec		cmap2 = { };
+
+	if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2))
+		xfs_trim_extent(&cmap2, offset_fsb, count_fsb);
+
+	ASSERT(cmap2.br_startoff == cmap->br_startoff);
+	ASSERT(cmap2.br_blockcount == cmap->br_blockcount);
+	ASSERT(cmap2.br_startblock == cmap->br_startblock);
+	ASSERT(cmap2.br_state == cmap->br_state);
+}
+#else
+# define xfs_check_atomic_cow_conversion(...)	((void)0)
+#endif
+
 static int
 xfs_atomic_write_cow_iomap_begin(
 	struct inode		*inode,
@@ -1102,9 +1125,10 @@ xfs_atomic_write_cow_iomap_begin(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	const xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
-	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
+	const xfs_fileoff_t	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	const xfs_fileoff_t	end_fsb = XFS_B_TO_FSB(mp, offset + length);
+	const xfs_filblks_t	count_fsb = end_fsb - offset_fsb;
+	xfs_filblks_t		hole_count_fsb;
 	int			nmaps = 1;
 	xfs_filblks_t		resaligned;
 	struct xfs_bmbt_irec	cmap;
@@ -1130,7 +1154,7 @@ xfs_atomic_write_cow_iomap_begin(
 		return -EAGAIN;
 
 	trace_xfs_iomap_atomic_write_cow(ip, offset, length);
-
+retry:
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
 	if (!ip->i_cowfp) {
@@ -1141,14 +1165,22 @@ xfs_atomic_write_cow_iomap_begin(
 	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
 		cmap.br_startoff = end_fsb;
 	if (cmap.br_startoff <= offset_fsb) {
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+
+		/*
+		 * cmap could extend outside the write range due to previous
+		 * speculative preallocations.  We must trim cmap to the write
+		 * range because the cow fork treats written mappings to mean
+		 * "write in progress".
+		 */
 		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		goto found;
 	}
 
-	end_fsb = cmap.br_startoff;
-	count_fsb = end_fsb - offset_fsb;
+	hole_count_fsb = cmap.br_startoff - offset_fsb;
 
-	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb,
+	resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb,
 			xfs_get_cowextsz_hint(ip));
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
@@ -1169,8 +1201,10 @@ xfs_atomic_write_cow_iomap_begin(
 	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
 		cmap.br_startoff = end_fsb;
 	if (cmap.br_startoff <= offset_fsb) {
-		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		xfs_trans_cancel(tp);
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		goto found;
 	}
 
@@ -1182,7 +1216,7 @@ xfs_atomic_write_cow_iomap_begin(
 	 * atomic writes to that same range will be aligned (and don't require
 	 * this COW-based method).
 	 */
-	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
+	error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC |
 			XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps);
 	if (error) {
@@ -1195,21 +1229,43 @@ xfs_atomic_write_cow_iomap_begin(
 	if (error)
 		goto out_unlock;
 
+	/*
+	 * cmap could map more blocks than the range we passed into bmapi_write
+	 * because of EXTSZALIGN or adjacent pre-existing unwritten mappings
+	 * that were merged.  Trim cmap to the original write range so that we
+	 * don't convert more than we were asked to do for this write.
+	 */
+	xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+
 found:
 	if (cmap.br_state != XFS_EXT_NORM) {
-		error = xfs_reflink_convert_cow_locked(ip, offset_fsb,
-				count_fsb);
+		error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff,
+				cmap.br_blockcount);
 		if (error)
 			goto out_unlock;
 		cmap.br_state = XFS_EXT_NORM;
+		xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb,
+				&cmap);
 	}
 
-	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
-	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
+	trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap);
 	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);
 
+convert_delay:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_convert_delalloc(ip, XFS_COW_FORK, offset, iomap,
+			NULL);
+	if (error)
+		return error;
+
+	/*
+	 * Try the lookup again, because the delalloc conversion might have
+	 * turned the COW mapping into unwritten, but we need it to be in
+	 * written state.
+	 */
+	goto retry;
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 0404022..ef7a931 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -615,7 +615,7 @@ xfs_select_open_zone_mru(
 	lockdep_assert_held(&zi->zi_open_zones_lock);
 
 	list_for_each_entry_reverse(oz, &zi->zi_open_zones, oz_entry)
-		if (xfs_try_use_zone(zi, file_hint, oz, false))
+		if (xfs_try_use_zone(zi, file_hint, oz, XFS_ZONE_ALLOC_OK))
 			return oz;
 
 	cond_resched_lock(&zi->zi_open_zones_lock);
@@ -1249,8 +1249,10 @@ xfs_mount_zones(
 
 		while ((rtg = xfs_rtgroup_next(mp, rtg))) {
 			error = xfs_init_zone(&iz, rtg, NULL);
-			if (error)
+			if (error) {
+				xfs_rtgroup_rele(rtg);
 				goto out_free_zone_info;
+			}
 		}
 	}
 
diff --git a/include/drm/Makefile b/include/drm/Makefile
index 1df6962..48fae3f 100644
--- a/include/drm/Makefile
+++ b/include/drm/Makefile
@@ -11,7 +11,7 @@
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
       cmd_hdrtest = \
 		$(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \
-		PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
+		PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
 		touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 1414be4..0a1b959 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -250,10 +250,9 @@ struct ftrace_likely_data {
 /*
  * GCC does not warn about unused static inline functions for -Wunused-function.
  * Suppress the warning in clang as well by using __maybe_unused, but enable it
- * for W=1 build. This will allow clang to find unused functions. Remove the
- * __inline_maybe_unused entirely after fixing most of -Wunused-function warnings.
+ * for W=2 build. This will allow clang to find unused functions.
  */
-#ifdef KBUILD_EXTRA_WARN1
+#ifdef KBUILD_EXTRA_WARN2
 #define __inline_maybe_unused
 #else
 #define __inline_maybe_unused __maybe_unused
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index ea91aa8..e527b24 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -979,14 +979,20 @@ extern "C" {
  *               2 = Gob Height 8, Turing+ Page Kind mapping
  *               3 = Reserved for future use.
  *
- * 22:22 s     Sector layout.  On Tegra GPUs prior to Xavier, there is a further
- *             bit remapping step that occurs at an even lower level than the
- *             page kind and block linear swizzles.  This causes the layout of
- *             surfaces mapped in those SOC's GPUs to be incompatible with the
- *             equivalent mapping on other GPUs in the same system.
+ * 22:22 s     Sector layout.  There is a further bit remapping step that occurs
+ * 26:27       at an even lower level than the page kind and block linear
+ *             swizzles.  This causes the bit arrangement of surfaces in memory
+ *             to differ subtly, and prevents direct sharing of surfaces between
+ *             GPUs with different layouts.
  *
- *               0 = Tegra K1 - Tegra Parker/TX2 Layout.
- *               1 = Desktop GPU and Tegra Xavier+ Layout
+ *               0 = Tegra K1 - Tegra Parker/TX2 Layout
+ *               1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout
+ *               2 = GB20x(Blackwell 2)+ 8 bpp surface layout
+ *               3 = GB20x(Blackwell 2)+ 16 bpp surface layout
+ *               4 = Reserved for future use.
+ *               5 = Reserved for future use.
+ *               6 = Reserved for future use.
+ *               7 = Reserved for future use.
  *
  * 25:23 c     Lossless Framebuffer Compression type.
  *
@@ -1001,7 +1007,7 @@ extern "C" {
  *               6 = Reserved for future use
  *               7 = Reserved for future use
  *
- * 55:25 -     Reserved for future use.  Must be zero.
+ * 55:28 -     Reserved for future use.  Must be zero.
  */
 #define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \
 	fourcc_mod_code(NVIDIA, (0x10 | \
@@ -1009,6 +1015,7 @@ extern "C" {
 				 (((k) & 0xff) << 12) | \
 				 (((g) & 0x3) << 20) | \
 				 (((s) & 0x1) << 22) | \
+				 (((s) & 0x6) << 25) | \
 				 (((c) & 0x7) << 23)))
 
 /* To grandfather in prior block linear format modifiers to the above layout,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 263bed1..b7c8dad 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -689,9 +689,6 @@ enum io_uring_register_op {
 	/* query various aspects of io_uring, see linux/io_uring/query.h */
 	IORING_REGISTER_QUERY			= 35,
 
-	/* return zcrx buffers back into circulation */
-	IORING_REGISTER_ZCRX_REFILL		= 36,
-
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -1073,15 +1070,6 @@ struct io_uring_zcrx_ifq_reg {
 	__u64	__resv[3];
 };
 
-struct io_uring_zcrx_sync_refill {
-	__u32		zcrx_id;
-	/* the number of entries to return */
-	__u32		nr_entries;
-	/* pointer to an array of struct io_uring_zcrx_rqe */
-	__u64		rqes;
-	__u64		__resv[2];
-};
-
 #ifdef __cplusplus
 }
 #endif
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 9425cfd..0f95576 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -688,6 +688,13 @@ enum ufshcd_quirks {
 	 * single doorbell mode.
 	 */
 	UFSHCD_QUIRK_BROKEN_LSDBS_CAP			= 1 << 25,
+
+	/*
+	 * This quirk indicates that DME_LINKSTARTUP should not be issued a 2nd
+	 * time (refer link_startup_again) after the 1st time was successful,
+	 * because it causes link startup to become unreliable.
+	 */
+	UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE		= 1 << 26,
 };
 
 enum ufshcd_caps {
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 2e99dffd..add03ca 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -135,7 +135,7 @@ static int io_region_pin_pages(struct io_ring_ctx *ctx,
 				struct io_mapped_region *mr,
 				struct io_uring_region_desc *reg)
 {
-	unsigned long size = mr->nr_pages << PAGE_SHIFT;
+	unsigned long size = (size_t) mr->nr_pages << PAGE_SHIFT;
 	struct page **pages;
 	int nr_pages;
 
diff --git a/io_uring/register.c b/io_uring/register.c
index 2e4717f..d189b26 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -827,9 +827,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	case IORING_REGISTER_QUERY:
 		ret = io_query(ctx, arg, nr_args);
 		break;
-	case IORING_REGISTER_ZCRX_REFILL:
-		ret = io_zcrx_return_bufs(ctx, arg, nr_args);
-		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index d787c16..2602d76 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1403,8 +1403,11 @@ static int io_estimate_bvec_size(struct iovec *iov, unsigned nr_iovs,
 	size_t max_segs = 0;
 	unsigned i;
 
-	for (i = 0; i < nr_iovs; i++)
+	for (i = 0; i < nr_iovs; i++) {
 		max_segs += (iov[i].iov_len >> shift) + 2;
+		if (max_segs > INT_MAX)
+			return -EOVERFLOW;
+	}
 	return max_segs;
 }
 
@@ -1510,7 +1513,11 @@ int io_import_reg_vec(int ddir, struct iov_iter *iter,
 		if (unlikely(ret))
 			return ret;
 	} else {
-		nr_segs = io_estimate_bvec_size(iov, nr_iovs, imu);
+		int ret = io_estimate_bvec_size(iov, nr_iovs, imu);
+
+		if (ret < 0)
+			return ret;
+		nr_segs = ret;
 	}
 
 	if (sizeof(struct bio_vec) > sizeof(struct iovec)) {
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index a816f59..b1b7232 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -928,74 +928,6 @@ static const struct memory_provider_ops io_uring_pp_zc_ops = {
 	.uninstall		= io_pp_uninstall,
 };
 
-#define IO_ZCRX_MAX_SYS_REFILL_BUFS		(1 << 16)
-#define IO_ZCRX_SYS_REFILL_BATCH		32
-
-static void io_return_buffers(struct io_zcrx_ifq *ifq,
-			      struct io_uring_zcrx_rqe *rqes, unsigned nr)
-{
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		struct net_iov *niov;
-		netmem_ref netmem;
-
-		if (!io_parse_rqe(&rqes[i], ifq, &niov))
-			continue;
-
-		scoped_guard(spinlock_bh, &ifq->rq_lock) {
-			if (!io_zcrx_put_niov_uref(niov))
-				continue;
-		}
-
-		netmem = net_iov_to_netmem(niov);
-		if (!page_pool_unref_and_test(netmem))
-			continue;
-		io_zcrx_return_niov(niov);
-	}
-}
-
-int io_zcrx_return_bufs(struct io_ring_ctx *ctx,
-			void __user *arg, unsigned nr_arg)
-{
-	struct io_uring_zcrx_rqe rqes[IO_ZCRX_SYS_REFILL_BATCH];
-	struct io_uring_zcrx_rqe __user *user_rqes;
-	struct io_uring_zcrx_sync_refill zr;
-	struct io_zcrx_ifq *ifq;
-	unsigned nr, i;
-
-	if (nr_arg)
-		return -EINVAL;
-	if (copy_from_user(&zr, arg, sizeof(zr)))
-		return -EFAULT;
-	if (!zr.nr_entries || zr.nr_entries > IO_ZCRX_MAX_SYS_REFILL_BUFS)
-		return -EINVAL;
-	if (!mem_is_zero(&zr.__resv, sizeof(zr.__resv)))
-		return -EINVAL;
-
-	ifq = xa_load(&ctx->zcrx_ctxs, zr.zcrx_id);
-	if (!ifq)
-		return -EINVAL;
-	nr = zr.nr_entries;
-	user_rqes = u64_to_user_ptr(zr.rqes);
-
-	for (i = 0; i < nr;) {
-		unsigned batch = min(nr - i, IO_ZCRX_SYS_REFILL_BATCH);
-		size_t size = batch * sizeof(rqes[0]);
-
-		if (copy_from_user(rqes, user_rqes + i, size))
-			return i ? i : -EFAULT;
-		io_return_buffers(ifq, rqes, batch);
-
-		i += batch;
-
-		if (fatal_signal_pending(current))
-			return i;
-		cond_resched();
-	}
-	return nr;
-}
-
 static bool io_zcrx_queue_cqe(struct io_kiocb *req, struct net_iov *niov,
 			      struct io_zcrx_ifq *ifq, int off, int len)
 {
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 33ef615..a48871b 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -63,8 +63,6 @@ struct io_zcrx_ifq {
 };
 
 #if defined(CONFIG_IO_URING_ZCRX)
-int io_zcrx_return_bufs(struct io_ring_ctx *ctx,
-			void __user *arg, unsigned nr_arg);
 int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 			 struct io_uring_zcrx_ifq_reg __user *arg);
 void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx);
@@ -97,11 +95,6 @@ static inline struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ct
 {
 	return NULL;
 }
-static inline int io_zcrx_return_bufs(struct io_ring_ctx *ctx,
-				      void __user *arg, unsigned nr_arg)
-{
-	return -EOPNOTSUPP;
-}
 #endif
 
 int io_recvzc(struct io_kiocb *req, unsigned int issue_flags);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 177e57c..1fd347d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11773,7 +11773,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
 	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
 
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state != PERF_EVENT_STATE_ACTIVE ||
+	    event->hw.state & PERF_HES_STOPPED)
 		return HRTIMER_NORESTART;
 
 	event->pmu->read(event);
@@ -11819,15 +11820,20 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 
 	/*
-	 * The throttle can be triggered in the hrtimer handler.
-	 * The HRTIMER_NORESTART should be used to stop the timer,
-	 * rather than hrtimer_cancel(). See perf_swevent_hrtimer()
+	 * Careful: this function can be triggered in the hrtimer handler,
+	 * for cpu-clock events, so hrtimer_cancel() would cause a
+	 * deadlock.
+	 *
+	 * So use hrtimer_try_to_cancel() to try to stop the hrtimer,
+	 * and the cpu-clock handler also sets the PERF_HES_STOPPED flag,
+	 * which guarantees that perf_swevent_hrtimer() will stop the
+	 * hrtimer once it sees the PERF_HES_STOPPED flag.
 	 */
 	if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) {
 		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
 		local64_set(&hwc->period_left, ktime_to_ns(remaining));
 
-		hrtimer_cancel(&hwc->hrtimer);
+		hrtimer_try_to_cancel(&hwc->hrtimer);
 	}
 }
 
@@ -11871,12 +11877,14 @@ static void cpu_clock_event_update(struct perf_event *event)
 
 static void cpu_clock_event_start(struct perf_event *event, int flags)
 {
+	event->hw.state = 0;
 	local64_set(&event->hw.prev_count, local_clock());
 	perf_swevent_start_hrtimer(event);
 }
 
 static void cpu_clock_event_stop(struct perf_event *event, int flags)
 {
+	event->hw.state = PERF_HES_STOPPED;
 	perf_swevent_cancel_hrtimer(event);
 	if (flags & PERF_EF_UPDATE)
 		cpu_clock_event_update(event);
@@ -11950,12 +11958,14 @@ static void task_clock_event_update(struct perf_event *event, u64 now)
 
 static void task_clock_event_start(struct perf_event *event, int flags)
 {
+	event->hw.state = 0;
 	local64_set(&event->hw.prev_count, event->ctx->time);
 	perf_swevent_start_hrtimer(event);
 }
 
 static void task_clock_event_stop(struct perf_event *event, int flags)
 {
+	event->hw.state = PERF_HES_STOPPED;
 	perf_swevent_cancel_hrtimer(event);
 	if (flags & PERF_EF_UPDATE)
 		task_clock_event_update(event, event->ctx->time);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 125804f..2e77a6e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1680,10 +1680,10 @@ static bool futex_ref_get(struct futex_private_hash *fph)
 {
 	struct mm_struct *mm = fph->mm;
 
-	guard(rcu)();
+	guard(preempt)();
 
-	if (smp_load_acquire(&fph->state) == FR_PERCPU) {
-		this_cpu_inc(*mm->futex_ref);
+	if (READ_ONCE(fph->state) == FR_PERCPU) {
+		__this_cpu_inc(*mm->futex_ref);
 		return true;
 	}
 
@@ -1694,10 +1694,10 @@ static bool futex_ref_put(struct futex_private_hash *fph)
 {
 	struct mm_struct *mm = fph->mm;
 
-	guard(rcu)();
+	guard(preempt)();
 
-	if (smp_load_acquire(&fph->state) == FR_PERCPU) {
-		this_cpu_dec(*mm->futex_ref);
+	if (READ_ONCE(fph->state) == FR_PERCPU) {
+		__this_cpu_dec(*mm->futex_ref);
 		return false;
 	}
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f1ebf67..f754a60 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9606,7 +9606,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg,
 
 		guard(rq_lock_irq)(rq);
 		cfs_rq->runtime_enabled = runtime_enabled;
-		cfs_rq->runtime_remaining = 0;
+		cfs_rq->runtime_remaining = 1;
 
 		if (cfs_rq->throttled)
 			unthrottle_cfs_rq(cfs_rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 25970db..5b752324 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6024,20 +6024,17 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
 
 	/*
-	 * It's possible we are called with !runtime_remaining due to things
-	 * like user changed quota setting(see tg_set_cfs_bandwidth()) or async
-	 * unthrottled us with a positive runtime_remaining but other still
-	 * running entities consumed those runtime before we reached here.
+	 * It's possible we are called with runtime_remaining < 0 due to things
+	 * like async unthrottled us with a positive runtime_remaining but other
+	 * still running entities consumed those runtime before we reached here.
 	 *
-	 * Anyway, we can't unthrottle this cfs_rq without any runtime remaining
-	 * because any enqueue in tg_unthrottle_up() will immediately trigger a
-	 * throttle, which is not supposed to happen on unthrottle path.
+	 * We can't unthrottle this cfs_rq without any runtime remaining because
+	 * any enqueue in tg_unthrottle_up() will immediately trigger a throttle,
+	 * which is not supposed to happen on unthrottle path.
 	 */
 	if (cfs_rq->runtime_enabled && cfs_rq->runtime_remaining <= 0)
 		return;
 
-	se = cfs_rq->tg->se[cpu_of(rq)];
-
 	cfs_rq->throttled = 0;
 
 	update_rq_clock(rq);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1244d2c..afcd374 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7344,6 +7344,10 @@ int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu)
 		goto out;
 	}
 
+	/* Did the reader catch up with the writer? */
+	if (cpu_buffer->reader_page == cpu_buffer->commit_page)
+		goto out;
+
 	reader = rb_get_reader_page(cpu_buffer);
 	if (WARN_ON(!reader))
 		goto out;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1d53621..6bfaf12 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3272,14 +3272,16 @@ static struct field_var *create_field_var(struct hist_trigger_data *hist_data,
 	var = create_var(hist_data, file, field_name, val->size, val->type);
 	if (IS_ERR(var)) {
 		hist_err(tr, HIST_ERR_VAR_CREATE_FIND_FAIL, errpos(field_name));
-		kfree(val);
+		destroy_hist_field(val, 0);
 		ret = PTR_ERR(var);
 		goto err;
 	}
 
 	field_var = kzalloc(sizeof(struct field_var), GFP_KERNEL);
 	if (!field_var) {
-		kfree(val);
+		destroy_hist_field(val, 0);
+		kfree_const(var->type);
+		kfree(var->var.name);
 		kfree(var);
 		ret =  -ENOMEM;
 		goto err;
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index ad9d634..8001dbf1 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -106,13 +106,14 @@ static struct tracepoint_user *__tracepoint_user_init(const char *name, struct t
 	if (!tuser->name)
 		return NULL;
 
+	/* Register tracepoint if it is loaded. */
 	if (tpoint) {
+		tuser->tpoint = tpoint;
 		ret = tracepoint_user_register(tuser);
 		if (ret)
 			return ERR_PTR(ret);
 	}
 
-	tuser->tpoint = tpoint;
 	tuser->refcount = 1;
 	INIT_LIST_HEAD(&tuser->list);
 	list_add(&tuser->list, &tracepoint_user_list);
@@ -1513,6 +1514,10 @@ static int disable_trace_fprobe(struct trace_event_call *call,
 	if (!trace_probe_is_enabled(tp)) {
 		list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
 			unregister_fprobe(&tf->fp);
+			if (tf->tuser) {
+				tracepoint_user_put(tf->tuser);
+				tf->tuser = NULL;
+			}
 		}
 	}
 
diff --git a/mm/slub.c b/mm/slub.c
index d4367f2..f1a5373 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4666,8 +4666,12 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (kmem_cache_debug(s)) {
 		freelist = alloc_single_from_new_slab(s, slab, orig_size, gfpflags);
 
-		if (unlikely(!freelist))
+		if (unlikely(!freelist)) {
+			/* This could cause an endless loop. Fail instead. */
+			if (!allow_spin)
+				return NULL;
 			goto new_objects;
+		}
 
 		if (s->flags & SLAB_STORE_USER)
 			set_track(s, freelist, TRACK_ALLOC, addr,
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d0ee33a..52c08c4 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -167,7 +167,7 @@
 endif
 
 ifneq ($(KBUILD_EXTRA_WARN),)
-  cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(KDOCFLAGS) \
+  cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(KDOCFLAGS) \
         $(if $(findstring 2, $(KBUILD_EXTRA_WARN)), -Wall) \
         $<
 endif
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index ced4379..cd788ca 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -102,11 +102,24 @@
 # modules.builtin.modinfo
 # ---------------------------------------------------------------------------
 
+# .modinfo in vmlinux.unstripped is aligned to 8 bytes for compatibility with
+# tools that expect vmlinux to have sufficiently aligned sections but the
+# additional bytes used for padding .modinfo to satisfy this requirement break
+# certain versions of kmod with
+#
+#   depmod: ERROR: kmod_builtin_iter_next: unexpected string without modname prefix
+#
+# Strip the trailing padding bytes after extracting .modinfo to comply with
+# what kmod expects to parse.
+quiet_cmd_modules_builtin_modinfo = GEN     $@
+      cmd_modules_builtin_modinfo = $(cmd_objcopy); \
+                                    sed -i 's/\x00\+$$/\x00/g' $@
+
 OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary
 
 targets += modules.builtin.modinfo
 modules.builtin.modinfo: vmlinux.unstripped FORCE
-	$(call if_changed,objcopy)
+	$(call if_changed,modules_builtin_modinfo)
 
 # modules.builtin
 # ---------------------------------------------------------------------------
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 06fc047..4091a77 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -444,6 +444,7 @@
 #define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* VM Page Flush MSR is supported */
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */
 #define X86_FEATURE_SEV_SNP		(19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */
+#define X86_FEATURE_SNP_SECURE_TSC	(19*32+ 8) /* SEV-SNP Secure TSC */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* hardware-enforced cache coherency */
 #define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
@@ -495,6 +496,9 @@
 #define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
 #define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
 #define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
+#define X86_FEATURE_IBPB_EXIT_TO_USER	(21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */
+#define X86_FEATURE_ABMC		(21*32+15) /* Assignable Bandwidth Monitoring Counters */
+#define X86_FEATURE_MSR_IMM		(21*32+16) /* MSR immediate form instructions */
 
 /*
  * BUG word(s)
@@ -551,4 +555,5 @@
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
 #define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
+#define X86_BUG_VMSCAPE			X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index f627196..9e1720d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -315,9 +315,12 @@
 #define PERF_CAP_PT_IDX			16
 
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+
+#define PERF_CAP_LBR_FMT		0x3f
 #define PERF_CAP_PEBS_TRAP		BIT_ULL(6)
 #define PERF_CAP_ARCH_REG		BIT_ULL(7)
 #define PERF_CAP_PEBS_FORMAT		0xf00
+#define PERF_CAP_FW_WRITES		BIT_ULL(13)
 #define PERF_CAP_PEBS_BASELINE		BIT_ULL(14)
 #define PERF_CAP_PEBS_TIMING_INFO	BIT_ULL(17)
 #define PERF_CAP_PEBS_MASK		(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
@@ -633,6 +636,11 @@
 #define MSR_AMD_PPIN			0xc00102f1
 #define MSR_AMD64_CPUID_FN_7		0xc0011002
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
+
+#define MSR_AMD64_CPUID_EXT_FEAT	0xc0011005
+#define MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT_BIT	54
+#define MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT	BIT_ULL(MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT_BIT)
+
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_TW_CFG		0xc0011023
@@ -701,8 +709,15 @@
 #define MSR_AMD64_SNP_VMSA_REG_PROT	BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT)
 #define MSR_AMD64_SNP_SMT_PROT_BIT	17
 #define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
-#define MSR_AMD64_SNP_RESV_BIT		18
+#define MSR_AMD64_SNP_SECURE_AVIC_BIT	18
+#define MSR_AMD64_SNP_SECURE_AVIC	BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT)
+#define MSR_AMD64_SNP_RESV_BIT		19
 #define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
+#define MSR_AMD64_SAVIC_CONTROL		0xc0010138
+#define MSR_AMD64_SAVIC_EN_BIT		0
+#define MSR_AMD64_SAVIC_EN		BIT_ULL(MSR_AMD64_SAVIC_EN_BIT)
+#define MSR_AMD64_SAVIC_ALLOWEDNMI_BIT	1
+#define MSR_AMD64_SAVIC_ALLOWEDNMI	BIT_ULL(MSR_AMD64_SAVIC_ALLOWEDNMI_BIT)
 #define MSR_AMD64_RMP_BASE		0xc0010132
 #define MSR_AMD64_RMP_END		0xc0010133
 #define MSR_AMD64_RMP_CFG		0xc0010136
@@ -735,6 +750,7 @@
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
+#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET	0xc0000303
 
 /* AMD Hardware Feedback Support MSRs */
 #define MSR_AMD_WORKLOAD_CLASS_CONFIG		0xc0000500
@@ -1225,6 +1241,8 @@
 /* - AMD: */
 #define MSR_IA32_MBA_BW_BASE		0xc0000200
 #define MSR_IA32_SMBA_BW_BASE		0xc0000280
+#define MSR_IA32_L3_QOS_ABMC_CFG	0xc00003fd
+#define MSR_IA32_L3_QOS_EXT_CFG		0xc00003ff
 #define MSR_IA32_EVT_CFG_BASE		0xc0000400
 
 /* AMD-V MSRs */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 0f15d68..d420c9c 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -35,6 +35,11 @@
 #define MC_VECTOR 18
 #define XM_VECTOR 19
 #define VE_VECTOR 20
+#define CP_VECTOR 21
+
+#define HV_VECTOR 28
+#define VC_VECTOR 29
+#define SX_VECTOR 30
 
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_PIT
@@ -411,6 +416,35 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
+#define KVM_X86_REG_TYPE_MSR		2
+#define KVM_X86_REG_TYPE_KVM		3
+
+#define KVM_X86_KVM_REG_SIZE(reg)						\
+({										\
+	reg == KVM_REG_GUEST_SSP ? KVM_REG_SIZE_U64 : 0;			\
+})
+
+#define KVM_X86_REG_TYPE_SIZE(type, reg)					\
+({										\
+	__u64 type_size = (__u64)type << 32;					\
+										\
+	type_size |= type == KVM_X86_REG_TYPE_MSR ? KVM_REG_SIZE_U64 :		\
+		     type == KVM_X86_REG_TYPE_KVM ? KVM_X86_KVM_REG_SIZE(reg) :	\
+		     0;								\
+	type_size;								\
+})
+
+#define KVM_X86_REG_ID(type, index)				\
+	(KVM_REG_X86 | KVM_X86_REG_TYPE_SIZE(type, index) | index)
+
+#define KVM_X86_REG_MSR(index)					\
+	KVM_X86_REG_ID(KVM_X86_REG_TYPE_MSR, index)
+#define KVM_X86_REG_KVM(index)					\
+	KVM_X86_REG_ID(KVM_X86_REG_TYPE_KVM, index)
+
+/* KVM-defined registers starting from 0 */
+#define KVM_REG_GUEST_SSP	0
+
 #define KVM_SYNC_X86_REGS      (1UL << 0)
 #define KVM_SYNC_X86_SREGS     (1UL << 1)
 #define KVM_SYNC_X86_EVENTS    (1UL << 2)
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 9c640a5..650e325 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -118,6 +118,10 @@
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
 #define SVM_VMGEXIT_SNP_RUN_VMPL		0x80000018
+#define SVM_VMGEXIT_SAVIC			0x8000001a
+#define SVM_VMGEXIT_SAVIC_REGISTER_GPA		0
+#define SVM_VMGEXIT_SAVIC_UNREGISTER_GPA	1
+#define SVM_VMGEXIT_SAVIC_SELF_GPA		~0ULL
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
 #define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
 #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0f4a4c..9792e32 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -94,6 +94,8 @@
 #define EXIT_REASON_BUS_LOCK            74
 #define EXIT_REASON_NOTIFY              75
 #define EXIT_REASON_TDCALL              77
+#define EXIT_REASON_MSR_READ_IMM        84
+#define EXIT_REASON_MSR_WRITE_IMM       85
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -158,7 +160,9 @@
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
 	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }, \
 	{ EXIT_REASON_NOTIFY,                "NOTIFY" }, \
-	{ EXIT_REASON_TDCALL,                "TDCALL" }
+	{ EXIT_REASON_TDCALL,                "TDCALL" }, \
+	{ EXIT_REASON_MSR_READ_IMM,          "MSR_READ_IMM" }, \
+	{ EXIT_REASON_MSR_WRITE_IMM,         "MSR_WRITE_IMM" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index e974ec9..35f3378 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -10,7 +10,7 @@
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static __always_inline unsigned int generic___fls(unsigned long word)
+static __always_inline __attribute_const__ unsigned int generic___fls(unsigned long word)
 {
 	unsigned int num = BITS_PER_LONG - 1;
 
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index 26f3ce1..8eed343 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -10,7 +10,7 @@
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
 
-static __always_inline int generic_fls(unsigned int x)
+static __always_inline __attribute_const__ int generic_fls(unsigned int x)
 {
 	int r = 32;
 
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index 866f2b2..b5f58dd 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -16,7 +16,7 @@
  * at position 64.
  */
 #if BITS_PER_LONG == 32
-static __always_inline int fls64(__u64 x)
+static __always_inline __attribute_const__ int fls64(__u64 x)
 {
 	__u32 h = x >> 32;
 	if (h)
@@ -24,7 +24,7 @@ static __always_inline int fls64(__u64 x)
 	return fls(x);
 }
 #elif BITS_PER_LONG == 64
-static __always_inline int fls64(__u64 x)
+static __always_inline __attribute_const__ int fls64(__u64 x)
 {
 	if (x == 0)
 		return 0;
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index e63a71d..3cd5cf1 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -597,35 +597,66 @@ struct drm_set_version {
 	int drm_dd_minor;
 };
 
-/* DRM_IOCTL_GEM_CLOSE ioctl argument type */
+/**
+ * struct drm_gem_close - Argument for &DRM_IOCTL_GEM_CLOSE ioctl.
+ * @handle: Handle of the object to be closed.
+ * @pad: Padding.
+ *
+ * Releases the handle to an mm object.
+ */
 struct drm_gem_close {
-	/** Handle of the object to be closed. */
 	__u32 handle;
 	__u32 pad;
 };
 
-/* DRM_IOCTL_GEM_FLINK ioctl argument type */
+/**
+ * struct drm_gem_flink - Argument for &DRM_IOCTL_GEM_FLINK ioctl.
+ * @handle: Handle for the object being named.
+ * @name: Returned global name.
+ *
+ * Create a global name for an object, returning the name.
+ *
+ * Note that the name does not hold a reference; when the object
+ * is freed, the name goes away.
+ */
 struct drm_gem_flink {
-	/** Handle for the object being named */
 	__u32 handle;
-
-	/** Returned global name */
 	__u32 name;
 };
 
-/* DRM_IOCTL_GEM_OPEN ioctl argument type */
+/**
+ * struct drm_gem_open - Argument for &DRM_IOCTL_GEM_OPEN ioctl.
+ * @name: Name of object being opened.
+ * @handle: Returned handle for the object.
+ * @size: Returned size of the object
+ *
+ * Open an object using the global name, returning a handle and the size.
+ *
+ * This handle (of course) holds a reference to the object, so the object
+ * will not go away until the handle is deleted.
+ */
 struct drm_gem_open {
-	/** Name of object being opened */
 	__u32 name;
-
-	/** Returned handle for the object */
 	__u32 handle;
-
-	/** Returned size of the object */
 	__u64 size;
 };
 
 /**
+ * struct drm_gem_change_handle - Argument for &DRM_IOCTL_GEM_CHANGE_HANDLE ioctl.
+ * @handle: The handle of a gem object.
+ * @new_handle: An available gem handle.
+ *
+ * This ioctl changes the handle of a GEM object to the specified one.
+ * The new handle must be unused. On success the old handle is closed
+ * and all further IOCTL should refer to the new handle only.
+ * Calls to DRM_IOCTL_PRIME_FD_TO_HANDLE will return the new handle.
+ */
+struct drm_gem_change_handle {
+	__u32 handle;
+	__u32 new_handle;
+};
+
+/**
  * DRM_CAP_DUMB_BUFFER
  *
  * If set to 1, the driver supports creating dumb buffers via the
@@ -1309,6 +1340,14 @@ extern "C" {
  */
 #define DRM_IOCTL_SET_CLIENT_NAME	DRM_IOWR(0xD1, struct drm_set_client_name)
 
+/**
+ * DRM_IOCTL_GEM_CHANGE_HANDLE - Move an object to a different handle
+ *
+ * Some applications (notably CRIU) need objects to have specific gem handles.
+ * This ioctl changes the object at one gem handle to use a new gem handle.
+ */
+#define DRM_IOCTL_GEM_CHANGE_HANDLE    DRM_IOWR(0xD2, struct drm_gem_change_handle)
+
 /*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f0f0d49..52f6000 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -962,6 +962,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_ARM_EL2_E2H0 241
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
+#define KVM_CAP_GUEST_MEMFD_FLAGS 244
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1598,6 +1599,8 @@ struct kvm_memory_attributes {
 #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
 
 #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+#define GUEST_MEMFD_FLAG_MMAP		(1ULL << 0)
+#define GUEST_MEMFD_FLAG_INIT_SHARED	(1ULL << 1)
 
 struct kvm_create_guest_memfd {
 	__u64 size;
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 92cf0fe..ced2a1d 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,7 @@
 333	common	io_pgetevents		sys_io_pgetevents
 334	common	rseq			sys_rseq
 335	common	uretprobe		sys_uretprobe
+336	common	uprobe			sys_uprobe
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	sys_pidfd_send_signal
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index f291ab4..3741ea1 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -111,6 +111,7 @@
 #define PIDFD_SELF_THREAD_GROUP		-10001 /* Current thread group leader. */
 
 #define FD_PIDFS_ROOT			-10002 /* Root of the pidfs filesystem */
+#define FD_NSFS_ROOT			-10003 /* Root of the nsfs filesystem */
 #define FD_INVALID			-10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */
 
 /* Generic flags for the *at(2) family of syscalls. */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 0bd678a..beb4c2d 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -430,10 +430,13 @@ typedef int __bitwise __kernel_rwf_t;
 /* buffered IO that drops the cache after reading or writing data */
 #define RWF_DONTCACHE	((__force __kernel_rwf_t)0x00000080)
 
+/* prevent pipe and socket writes from raising SIGPIPE */
+#define RWF_NOSIGNAL	((__force __kernel_rwf_t)0x00000100)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
 			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
-			 RWF_DONTCACHE)
+			 RWF_DONTCACHE | RWF_NOSIGNAL)
 
 #define PROCFS_IOCTL_MAGIC 'f'
 
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index ed3aed2..51c4e8c 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -177,7 +177,17 @@ struct prctl_mm_map {
 
 #define PR_GET_TID_ADDRESS	40
 
+/*
+ * Flags for PR_SET_THP_DISABLE are only applicable when disabling. Bit 0
+ * is reserved, so PR_GET_THP_DISABLE can return "1 | flags", to effectively
+ * return "1" when no flags were specified for PR_SET_THP_DISABLE.
+ */
 #define PR_SET_THP_DISABLE	41
+/*
+ * Don't disable THPs when explicitly advised (e.g., MADV_HUGEPAGE /
+ * VM_HUGEPAGE, MADV_COLLAPSE).
+ */
+# define PR_THP_DISABLE_EXCEPT_ADVISED	(1 << 1)
 #define PR_GET_THP_DISABLE	42
 
 /*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cc26b7b..948d3e8 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -112,9 +112,13 @@ static bool symbol_type__filter(char __symbol_type)
 	// 'N' first seen in:
 	// ffffffff9b35d130 N __pfx__RNCINvNtNtNtCsbDUBuN8AbD4_4core4iter8adapters3map12map_try_foldjNtCs6vVzKs5jPr6_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_
 	// a seemingly Rust mangled name
+	// Ditto for '1':
+	// root@x1:~# grep ' 1 ' /proc/kallsyms
+	// ffffffffb098bc00 1 __pfx__RNCINvNtNtNtCsfwaGRd4cjqE_4core4iter8adapters3map12map_try_foldjNtCskFudTml27HW_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_
+	// ffffffffb098bc10 1 _RNCINvNtNtNtCsfwaGRd4cjqE_4core4iter8adapters3map12map_try_foldjNtCskFudTml27HW_12drm_panic_qr7VersionuINtNtNtBa_3ops12control_flow11ControlFlowB10_ENcB10_0NCINvNvNtNtNtB8_6traits8iterator8Iterator4find5checkB10_NCNvMB12_B10_13from_segments0E0E0B12_
 	char symbol_type = toupper(__symbol_type);
 	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B' ||
-	       __symbol_type == 'u' || __symbol_type == 'l' || __symbol_type == 'N';
+	       __symbol_type == 'u' || __symbol_type == 'l' || __symbol_type == 'N' || __symbol_type == '1';
 }
 
 static int prefix_underscores_count(const char *str)
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 3eebf5e..bb4d33d 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -2638,6 +2638,8 @@ TEST_F(vfio_compat_mock_domain, map)
 	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_MAP_DMA, &map_cmd));
 	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_UNMAP_DMA, &unmap_cmd));
 	ASSERT_EQ(BUFFER_SIZE, unmap_cmd.size);
+	/* Unmap of empty is success */
+	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_UNMAP_DMA, &unmap_cmd));
 
 	/* UNMAP_FLAG_ALL requires 0 iova/size */
 	ASSERT_EQ(0, ioctl(self->fd, VFIO_IOMMU_MAP_DMA, &map_cmd));
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index 772ca1d..9f472c2 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -1044,8 +1044,8 @@ static int _test_cmd_trigger_vevents(int fd, __u32 dev_id, __u32 nvevents)
 	};
 
 	while (nvevents--) {
-		if (!ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT),
-			    &trigger_vevent_cmd))
+		if (ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT),
+			  &trigger_vevent_cmd))
 			return -1;
 	}
 	return 0;
diff --git a/tools/testing/selftests/kvm/arm64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c
index c9b84ee..0a3a94c 100644
--- a/tools/testing/selftests/kvm/arm64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/arm64/get-reg-list.c
@@ -63,11 +63,13 @@ static struct feature_id_reg feat_id_regs[] = {
 	REG_FEAT(HDFGWTR2_EL2,	ID_AA64MMFR0_EL1, FGT, FGT2),
 	REG_FEAT(ZCR_EL2,	ID_AA64PFR0_EL1, SVE, IMP),
 	REG_FEAT(SCTLR2_EL1,	ID_AA64MMFR3_EL1, SCTLRX, IMP),
+	REG_FEAT(SCTLR2_EL2,	ID_AA64MMFR3_EL1, SCTLRX, IMP),
 	REG_FEAT(VDISR_EL2,	ID_AA64PFR0_EL1, RAS, IMP),
 	REG_FEAT(VSESR_EL2,	ID_AA64PFR0_EL1, RAS, IMP),
 	REG_FEAT(VNCR_EL2,	ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY),
 	REG_FEAT(CNTHV_CTL_EL2, ID_AA64MMFR1_EL1, VH, IMP),
 	REG_FEAT(CNTHV_CVAL_EL2,ID_AA64MMFR1_EL1, VH, IMP),
+	REG_FEAT(ZCR_EL2,	ID_AA64PFR0_EL1, SVE, IMP),
 };
 
 bool filter_reg(__u64 reg)
@@ -718,6 +720,7 @@ static __u64 el2_regs[] = {
 	SYS_REG(VMPIDR_EL2),
 	SYS_REG(SCTLR_EL2),
 	SYS_REG(ACTLR_EL2),
+	SYS_REG(SCTLR2_EL2),
 	SYS_REG(HCR_EL2),
 	SYS_REG(MDCR_EL2),
 	SYS_REG(CPTR_EL2),
diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
index 09f2705..0e2f8ed 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
@@ -15,6 +15,8 @@
 #include "gic_v3.h"
 #include "processor.h"
 
+#define GITS_COLLECTION_TARGET_SHIFT 16
+
 static u64 its_read_u64(unsigned long offset)
 {
 	return readq_relaxed(GITS_BASE_GVA + offset);
@@ -163,6 +165,11 @@ static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
 	its_mask_encode(&cmd->raw_cmd[2], col, 15, 0);
 }
 
+static u64 procnum_to_rdbase(u32 vcpu_id)
+{
+	return vcpu_id << GITS_COLLECTION_TARGET_SHIFT;
+}
+
 #define GITS_CMDQ_POLL_ITERATIONS	0
 
 static void its_send_cmd(void *cmdq_base, struct its_cmd_block *cmd)
@@ -217,7 +224,7 @@ void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool val
 
 	its_encode_cmd(&cmd, GITS_CMD_MAPC);
 	its_encode_collection(&cmd, collection_id);
-	its_encode_target(&cmd, vcpu_id);
+	its_encode_target(&cmd, procnum_to_rdbase(vcpu_id));
 	its_encode_valid(&cmd, valid);
 
 	its_send_cmd(cmdq_base, &cmd);
diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c
index cf263fe..ef97916 100644
--- a/tools/tracing/latency/latency-collector.c
+++ b/tools/tracing/latency/latency-collector.c
@@ -1725,7 +1725,7 @@ static void show_usage(void)
 "-n, --notrace\t\tIf latency is detected, do not print out the content of\n"
 "\t\t\tthe trace file to standard output\n\n"
 
-"-t, --threads NRTHR\tRun NRTHR threads for printing. Default is %d.\n\n"
+"-e, --threads NRTHR\tRun NRTHR threads for printing. Default is %d.\n\n"
 
 "-r, --random\t\tArbitrarily sleep a certain amount of time, default\n"
 "\t\t\t%ld ms, before reading the trace file. The\n"
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index fbca8c0..ffadc5e 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -623,24 +623,11 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 	return r;
 }
 
-void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct kvm_gmem *gmem)
 {
 	unsigned long start = slot->gmem.pgoff;
 	unsigned long end = start + slot->npages;
-	struct kvm_gmem *gmem;
-	struct file *file;
 
-	/*
-	 * Nothing to do if the underlying file was already closed (or is being
-	 * closed right now), kvm_gmem_release() invalidates all bindings.
-	 */
-	file = kvm_gmem_get_file(slot);
-	if (!file)
-		return;
-
-	gmem = file->private_data;
-
-	filemap_invalidate_lock(file->f_mapping);
 	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
 
 	/*
@@ -648,6 +635,38 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 	 * cannot see this memslot.
 	 */
 	WRITE_ONCE(slot->gmem.file, NULL);
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	struct file *file;
+
+	/*
+	 * Nothing to do if the underlying file was _already_ closed, as
+	 * kvm_gmem_release() invalidates and nullifies all bindings.
+	 */
+	if (!slot->gmem.file)
+		return;
+
+	file = kvm_gmem_get_file(slot);
+
+	/*
+	 * However, if the file is _being_ closed, then the bindings need to be
+	 * removed as kvm_gmem_release() might not run until after the memslot
+	 * is freed.  Note, modifying the bindings is safe even though the file
+	 * is dying as kvm_gmem_release() nullifies slot->gmem.file under
+	 * slots_lock, and only puts its reference to KVM after destroying all
+	 * bindings.  I.e. reaching this point means kvm_gmem_release() hasn't
+	 * yet destroyed the bindings or freed the gmem_file, and can't do so
+	 * until the caller drops slots_lock.
+	 */
+	if (!file) {
+		__kvm_gmem_unbind(slot, slot->gmem.file->private_data);
+		return;
+	}
+
+	filemap_invalidate_lock(file->f_mapping);
+	__kvm_gmem_unbind(slot, file->private_data);
 	filemap_invalidate_unlock(file->f_mapping);
 
 	fput(file);