diff --git a/Makefile b/Makefile
index 658ec2b8aa749..22e392649b025 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
@@ -555,11 +555,23 @@ LINUXINCLUDE    := \
 		$(USERINCLUDE)
 
 KBUILD_AFLAGS   := -D__ASSEMBLY__ -fno-PIE
-KBUILD_CFLAGS   := -Wall -Wundef -Werror=strict-prototypes -Wno-trigraphs \
-		   -fno-strict-aliasing -fno-common -fshort-wchar -fno-PIE \
-		   -Werror=implicit-function-declaration -Werror=implicit-int \
-		   -Werror=return-type -Wno-format-security -funsigned-char \
-		   -std=gnu11
+
+KBUILD_CFLAGS :=
+KBUILD_CFLAGS += -std=gnu11
+KBUILD_CFLAGS += -fshort-wchar
+KBUILD_CFLAGS += -funsigned-char
+KBUILD_CFLAGS += -fno-common
+KBUILD_CFLAGS += -fno-PIE
+KBUILD_CFLAGS += -fno-strict-aliasing
+KBUILD_CFLAGS += -Wall
+KBUILD_CFLAGS += -Wundef
+KBUILD_CFLAGS += -Werror=implicit-function-declaration
+KBUILD_CFLAGS += -Werror=implicit-int
+KBUILD_CFLAGS += -Werror=return-type
+KBUILD_CFLAGS += -Werror=strict-prototypes
+KBUILD_CFLAGS += -Wno-format-security
+KBUILD_CFLAGS += -Wno-trigraphs
+
 KBUILD_CPPFLAGS := -D__KERNEL__
 KBUILD_RUSTFLAGS := $(rust_common_flags) \
 		    --target=$(objtree)/scripts/target.json \
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8b6096753740c..d3dd05bbfe23f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -727,6 +727,8 @@ struct kvm_vcpu_arch {
 #define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
 /* PMUSERENR for the guest EL0 is on physical CPU */
 #define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
+/* WFI instruction trapped */
+#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 8294a9a7e566d..929d355eae0ac 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -608,22 +608,26 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
 kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
 
 /**
- * kvm_pgtable_stage2_mkold() - Clear the access flag in a page-table entry.
+ * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access
+ *					   flag in a page-table entry.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Intermediate physical address to identify the page-table entry.
+ * @size:	Size of the address range to visit.
+ * @mkold:	True if the access flag should be cleared.
  *
  * The offset of @addr within a page is ignored.
  *
- * If there is a valid, leaf page-table entry used to translate @addr, then
- * clear the access flag in that entry.
+ * Tests and conditionally clears the access flag for every valid, leaf
+ * page-table entry used to translate the range [@addr, @addr + @size).
  *
  * Note that it is the caller's responsibility to invalidate the TLB after
  * calling this function to ensure that the updated permissions are visible
  * to the CPUs.
  *
- * Return: The old page-table entry prior to clearing the flag, 0 on failure.
+ * Return: True if any of the visited PTEs had the access flag set.
  */
-kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
+bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
+					 u64 size, bool mkold);
 
 /**
  * kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a
@@ -645,18 +649,6 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				   enum kvm_pgtable_prot prot);
 
-/**
- * kvm_pgtable_stage2_is_young() - Test whether a page-table entry has the
- *				   access flag set.
- * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
- * @addr:	Intermediate physical address to identify the page-table entry.
- *
- * The offset of @addr within a page is ignored.
- *
- * Return: True if the page-table entry has the access flag set, false otherwise.
- */
-bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
-
 /**
  * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
  * 				      of Coherency for guest stage-2 address
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 5227db7640c8d..261d6e9df2e10 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -78,6 +78,7 @@ extern u32 __boot_cpu_mode[2];
 
 void __hyp_set_vectors(phys_addr_t phys_vector_base);
 void __hyp_reset_vectors(void);
+bool is_kvm_arm_initialised(void);
 
 DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
 
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 0696732fa38cd..6dcdae4d38cb5 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -827,8 +827,8 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 	assign_clear_set_bit(tpt, CNTHCTL_EL1PCEN << 10, set, clr);
 	assign_clear_set_bit(tpc, CNTHCTL_EL1PCTEN << 10, set, clr);
 
-	/* This only happens on VHE, so use the CNTKCTL_EL1 accessor */
-	sysreg_clear_set(cntkctl_el1, clr, set);
+	/* This only happens on VHE, so use the CNTHCTL_EL2 accessor. */
+	sysreg_clear_set(cnthctl_el2, clr, set);
 }
 
 void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
@@ -1563,7 +1563,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 void kvm_timer_init_vhe(void)
 {
 	if (cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF))
-		sysreg_clear_set(cntkctl_el1, 0, CNTHCTL_ECV);
+		sysreg_clear_set(cnthctl_el2, 0, CNTHCTL_ECV);
 }
 
 int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c2c14059f6a8c..72dc53a75d1c8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -53,11 +53,16 @@ DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 
-static bool vgic_present;
+static bool vgic_present, kvm_arm_initialised;
 
 static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
 DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
+bool is_kvm_arm_initialised(void)
+{
+	return kvm_arm_initialised;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
@@ -713,13 +718,15 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 	 */
 	preempt_disable();
 	kvm_vgic_vmcr_sync(vcpu);
-	vgic_v4_put(vcpu, true);
+	vcpu_set_flag(vcpu, IN_WFI);
+	vgic_v4_put(vcpu);
 	preempt_enable();
 
 	kvm_vcpu_halt(vcpu);
 	vcpu_clear_flag(vcpu, IN_WFIT);
 
 	preempt_disable();
+	vcpu_clear_flag(vcpu, IN_WFI);
 	vgic_v4_load(vcpu);
 	preempt_enable();
 }
@@ -787,7 +794,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) {
 			/* The distributor enable bits were changed */
 			preempt_disable();
-			vgic_v4_put(vcpu, false);
+			vgic_v4_put(vcpu);
 			vgic_v4_load(vcpu);
 			preempt_enable();
 		}
@@ -1867,8 +1874,17 @@ static void _kvm_arch_hardware_enable(void *discard)
 
 int kvm_arch_hardware_enable(void)
 {
-	int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled);
+	int was_enabled;
+
+	/*
+	 * Most calls to this function are made with migration
+	 * disabled, but not with preemption disabled. The former is
+	 * enough to ensure correctness, but most of the helpers
+	 * expect the later and will throw a tantrum otherwise.
+	 */
+	preempt_disable();
 
+	was_enabled = __this_cpu_read(kvm_arm_hardware_enabled);
 	_kvm_arch_hardware_enable(NULL);
 
 	if (!was_enabled) {
@@ -1876,6 +1892,8 @@ int kvm_arch_hardware_enable(void)
 		kvm_timer_cpu_up();
 	}
 
+	preempt_enable();
+
 	return 0;
 }
 
@@ -2482,6 +2500,8 @@ static __init int kvm_arm_init(void)
 	if (err)
 		goto out_subs;
 
+	kvm_arm_initialised = true;
+
 	return 0;
 
 out_subs:
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 8f3f93fa119ed..03f97d71984c4 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -154,6 +154,12 @@ SYM_CODE_END(\label)
 	esb
 	stp	x0, x1, [sp, #-16]!
 662:
+	/*
+	 * spectre vectors __bp_harden_hyp_vecs generate br instructions at runtime
+	 * that jump at offset 8 at __kvm_hyp_vector.
+	 * As hyp .text is guarded section, it needs bti j.
+	 */
+	bti j
 	b	\target
 
 check_preamble_length 661b, 662b
@@ -165,6 +171,8 @@ check_preamble_length 661b, 662b
 	nop
 	stp	x0, x1, [sp, #-16]!
 662:
+	/* Check valid_vect */
+	bti j
 	b	\target
 
 check_preamble_length 661b, 662b
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index c87c63133e10c..7693a6757cd76 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -297,3 +297,13 @@ SYM_CODE_START(__kvm_hyp_host_forward_smc)
 
 	ret
 SYM_CODE_END(__kvm_hyp_host_forward_smc)
+
+/*
+ * kvm_host_psci_cpu_entry is called through br instruction, which requires
+ * bti j instruction as compilers (gcc and llvm) doesn't insert bti j for external
+ * functions, but bti c instead.
+ */
+SYM_CODE_START(kvm_host_psci_cpu_entry)
+       bti j
+       b __kvm_host_psci_cpu_entry
+SYM_CODE_END(kvm_host_psci_cpu_entry)
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 08508783ec3d7..24543d2a34905 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -200,7 +200,7 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 			 __hyp_pa(init_params), 0);
 }
 
-asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on)
+asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 {
 	struct psci_boot_args *boot_args;
 	struct kvm_cpu_context *host_ctxt;
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index aa740a974e024..f7a93ef292506 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1195,25 +1195,54 @@ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 	return pte;
 }
 
-kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
+struct stage2_age_data {
+	bool	mkold;
+	bool	young;
+};
+
+static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			     enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL, 0);
+	kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data *data = ctx->arg;
+
+	if (!kvm_pte_valid(ctx->old) || new == ctx->old)
+		return 0;
+
+	data->young = true;
+
+	/*
+	 * stage2_age_walker() is always called while holding the MMU lock for
+	 * write, so this will always succeed. Nonetheless, this deliberately
+	 * follows the race detection pattern of the other stage-2 walkers in
+	 * case the locking mechanics of the MMU notifiers is ever changed.
+	 */
+	if (data->mkold && !stage2_try_set_pte(ctx, new))
+		return -EAGAIN;
+
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
 	 *
 	 * See the '->clear_flush_young()' callback on the KVM mmu notifier.
 	 */
-	return pte;
+	return 0;
 }
 
-bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
+bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
+					 u64 size, bool mkold)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0);
-	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data data = {
+		.mkold		= mkold,
+	};
+	struct kvm_pgtable_walker walker = {
+		.cb		= stage2_age_walker,
+		.arg		= &data,
+		.flags		= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+	return data.young;
 }
 
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6db9ef288ec38..d3b4feed460c0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1756,27 +1756,25 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	u64 size = (range->end - range->start) << PAGE_SHIFT;
-	kvm_pte_t kpte;
-	pte_t pte;
 
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-
-	kpte = kvm_pgtable_stage2_mkold(kvm->arch.mmu.pgt,
-					range->start << PAGE_SHIFT);
-	pte = __pte(kpte);
-	return pte_valid(pte) && pte_young(pte);
+	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+						   range->start << PAGE_SHIFT,
+						   size, true);
 }
 
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
+	u64 size = (range->end - range->start) << PAGE_SHIFT;
+
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt,
-					   range->start << PAGE_SHIFT);
+	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+						   range->start << PAGE_SHIFT,
+						   size, false);
 }
 
 phys_addr_t kvm_mmu_get_httbr(void)
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 994a494703c3c..6ff3ec18c9258 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -244,7 +244,7 @@ static int __init finalize_pkvm(void)
 {
 	int ret;
 
-	if (!is_protected_kvm_enabled())
+	if (!is_protected_kvm_enabled() || !is_kvm_arm_initialised())
 		return 0;
 
 	/*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index bd3431823ec54..2ca2973abe66f 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -986,7 +986,6 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 	if (p->is_write) {
 		kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
-		__vcpu_sys_reg(vcpu, reg) = p->regval & ARMV8_PMU_EVTYPE_MASK;
 		kvm_vcpu_pmu_restore_guest(vcpu);
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
@@ -1115,18 +1114,19 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_DBGWCRn_EL1(n)),					\
 	  trap_wcr, reset_wcr, 0, 0,  get_wcr, set_wcr }
 
-#define PMU_SYS_REG(r)						\
-	SYS_DESC(r), .reset = reset_pmu_reg, .visibility = pmu_visibility
+#define PMU_SYS_REG(name)						\
+	SYS_DESC(SYS_##name), .reset = reset_pmu_reg,			\
+	.visibility = pmu_visibility
 
 /* Macro to expand the PMEVCNTRn_EL0 register */
 #define PMU_PMEVCNTR_EL0(n)						\
-	{ PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)),				\
+	{ PMU_SYS_REG(PMEVCNTRn_EL0(n)),				\
 	  .reset = reset_pmevcntr, .get_user = get_pmu_evcntr,		\
 	  .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
 #define PMU_PMEVTYPER_EL0(n)						\
-	{ PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)),				\
+	{ PMU_SYS_REG(PMEVTYPERn_EL0(n)),				\
 	  .reset = reset_pmevtyper,					\
 	  .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), }
 
@@ -2115,9 +2115,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_PMBSR_EL1), undef_access },
 	/* PMBIDR_EL1 is not trapped */
 
-	{ PMU_SYS_REG(SYS_PMINTENSET_EL1),
+	{ PMU_SYS_REG(PMINTENSET_EL1),
 	  .access = access_pminten, .reg = PMINTENSET_EL1 },
-	{ PMU_SYS_REG(SYS_PMINTENCLR_EL1),
+	{ PMU_SYS_REG(PMINTENCLR_EL1),
 	  .access = access_pminten, .reg = PMINTENSET_EL1 },
 	{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },
 
@@ -2164,41 +2164,41 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
 	{ SYS_DESC(SYS_SVCR), undef_access },
 
-	{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,
+	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr,
 	  .reset = reset_pmcr, .reg = PMCR_EL0 },
-	{ PMU_SYS_REG(SYS_PMCNTENSET_EL0),
+	{ PMU_SYS_REG(PMCNTENSET_EL0),
 	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
-	{ PMU_SYS_REG(SYS_PMCNTENCLR_EL0),
+	{ PMU_SYS_REG(PMCNTENCLR_EL0),
 	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
-	{ PMU_SYS_REG(SYS_PMOVSCLR_EL0),
+	{ PMU_SYS_REG(PMOVSCLR_EL0),
 	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
 	/*
 	 * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was
 	 * previously (and pointlessly) advertised in the past...
 	 */
-	{ PMU_SYS_REG(SYS_PMSWINC_EL0),
+	{ PMU_SYS_REG(PMSWINC_EL0),
 	  .get_user = get_raz_reg, .set_user = set_wi_reg,
 	  .access = access_pmswinc, .reset = NULL },
-	{ PMU_SYS_REG(SYS_PMSELR_EL0),
+	{ PMU_SYS_REG(PMSELR_EL0),
 	  .access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 },
-	{ PMU_SYS_REG(SYS_PMCEID0_EL0),
+	{ PMU_SYS_REG(PMCEID0_EL0),
 	  .access = access_pmceid, .reset = NULL },
-	{ PMU_SYS_REG(SYS_PMCEID1_EL0),
+	{ PMU_SYS_REG(PMCEID1_EL0),
 	  .access = access_pmceid, .reset = NULL },
-	{ PMU_SYS_REG(SYS_PMCCNTR_EL0),
+	{ PMU_SYS_REG(PMCCNTR_EL0),
 	  .access = access_pmu_evcntr, .reset = reset_unknown,
 	  .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr},
-	{ PMU_SYS_REG(SYS_PMXEVTYPER_EL0),
+	{ PMU_SYS_REG(PMXEVTYPER_EL0),
 	  .access = access_pmu_evtyper, .reset = NULL },
-	{ PMU_SYS_REG(SYS_PMXEVCNTR_EL0),
+	{ PMU_SYS_REG(PMXEVCNTR_EL0),
 	  .access = access_pmu_evcntr, .reset = NULL },
 	/*
 	 * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ PMU_SYS_REG(SYS_PMUSERENR_EL0), .access = access_pmuserenr,
+	{ PMU_SYS_REG(PMUSERENR_EL0), .access = access_pmuserenr,
 	  .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 },
-	{ PMU_SYS_REG(SYS_PMOVSSET_EL0),
+	{ PMU_SYS_REG(PMOVSSET_EL0),
 	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
 
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
@@ -2354,7 +2354,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	 * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper,
+	{ PMU_SYS_REG(PMCCFILTR_EL0), .access = access_pmu_evtyper,
 	  .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
 
 	EL2_REG(VPIDR_EL2, access_rw, reset_unknown, 0),
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index c3b8e132d5992..3dfc8b84e03e6 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -749,7 +749,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	WARN_ON(vgic_v4_put(vcpu, false));
+	WARN_ON(vgic_v4_put(vcpu));
 
 	vgic_v3_vmcr_sync(vcpu);
 
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index c1c28fe680ba3..339a55194b2c6 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -336,14 +336,14 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
-int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
+int vgic_v4_put(struct kvm_vcpu *vcpu)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
 
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_make_vpe_non_resident(vpe, need_db);
+	return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI));
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -354,6 +354,9 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident)
 		return 0;
 
+	if (vcpu_get_flag(vcpu, IN_WFI))
+		return 0;
+
 	/*
 	 * Before making the VPE resident, make sure the redistributor
 	 * corresponding to our current CPU expects us here. See the
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 2f34c7c3c5abf..bf1fdc7bf89e0 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -411,8 +411,12 @@ int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc)
 	u16 _rc, _rrc;
 	int cc = 0;
 
-	/* Make sure the counter does not reach 0 before calling s390_uv_destroy_range */
-	atomic_inc(&kvm->mm->context.protected_count);
+	/*
+	 * Nothing to do if the counter was already 0. Otherwise make sure
+	 * the counter does not reach 0 before calling s390_uv_destroy_range.
+	 */
+	if (!atomic_inc_not_zero(&kvm->mm->context.protected_count))
+		return 0;
 
 	*rc = 1;
 	/* If the current VM is protected, destroy it */
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 989ebd0912b48..9c8af31be9705 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2853,6 +2853,7 @@ int s390_replace_asce(struct gmap *gmap)
 	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		return -ENOMEM;
+	page->index = 0;
 	table = page_to_virt(page);
 	memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a2475b8c9fb5f..21b903fe546e8 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1006,14 +1006,11 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context
 	 * fls() instead since we need to know the actual length while modifying
 	 * goal length.
 	 */
-	order = fls(ac->ac_g_ex.fe_len);
+	order = fls(ac->ac_g_ex.fe_len) - 1;
 	min_order = order - sbi->s_mb_best_avail_max_trim_order;
 	if (min_order < 0)
 		min_order = 0;
 
-	if (1 << min_order < ac->ac_o_ex.fe_len)
-		min_order = fls(ac->ac_o_ex.fe_len) + 1;
-
 	if (sbi->s_stripe > 0) {
 		/*
 		 * We are assuming that stripe size is always a multiple of
@@ -1021,9 +1018,16 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context
 		 */
 		num_stripe_clusters = EXT4_NUM_B2C(sbi, sbi->s_stripe);
 		if (1 << min_order < num_stripe_clusters)
-			min_order = fls(num_stripe_clusters);
+			/*
+			 * We consider 1 order less because later we round
+			 * up the goal len to num_stripe_clusters
+			 */
+			min_order = fls(num_stripe_clusters) - 1;
 	}
 
+	if (1 << min_order < ac->ac_o_ex.fe_len)
+		min_order = fls(ac->ac_o_ex.fe_len);
+
 	for (i = order; i >= min_order; i--) {
 		int frag_order;
 		/*
@@ -4761,8 +4765,8 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 	int order, i;
 	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
 	struct ext4_locality_group *lg;
-	struct ext4_prealloc_space *tmp_pa, *cpa = NULL;
-	ext4_lblk_t tmp_pa_start, tmp_pa_end;
+	struct ext4_prealloc_space *tmp_pa = NULL, *cpa = NULL;
+	loff_t tmp_pa_end;
 	struct rb_node *iter;
 	ext4_fsblk_t goal_block;
 
@@ -4770,47 +4774,151 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
 		return false;
 
-	/* first, try per-file preallocation */
+	/*
+	 * first, try per-file preallocation by searching the inode pa rbtree.
+	 *
+	 * Here, we can't do a direct traversal of the tree because
+	 * ext4_mb_discard_group_preallocation() can paralelly mark the pa
+	 * deleted and that can cause direct traversal to skip some entries.
+	 */
 	read_lock(&ei->i_prealloc_lock);
+
+	if (RB_EMPTY_ROOT(&ei->i_prealloc_node)) {
+		goto try_group_pa;
+	}
+
+	/*
+	 * Step 1: Find a pa with logical start immediately adjacent to the
+	 * original logical start. This could be on the left or right.
+	 *
+	 * (tmp_pa->pa_lstart never changes so we can skip locking for it).
+	 */
 	for (iter = ei->i_prealloc_node.rb_node; iter;
 	     iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical,
-					    tmp_pa_start, iter)) {
+					    tmp_pa->pa_lstart, iter)) {
 		tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
 				  pa_node.inode_node);
+	}
 
-		/* all fields in this condition don't change,
-		 * so we can skip locking for them */
-		tmp_pa_start = tmp_pa->pa_lstart;
-		tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
-
-		/* original request start doesn't lie in this PA */
-		if (ac->ac_o_ex.fe_logical < tmp_pa_start ||
-		    ac->ac_o_ex.fe_logical >= tmp_pa_end)
-			continue;
+	/*
+	 * Step 2: The adjacent pa might be to the right of logical start, find
+	 * the left adjacent pa. After this step we'd have a valid tmp_pa whose
+	 * logical start is towards the left of original request's logical start
+	 */
+	if (tmp_pa->pa_lstart > ac->ac_o_ex.fe_logical) {
+		struct rb_node *tmp;
+		tmp = rb_prev(&tmp_pa->pa_node.inode_node);
 
-		/* non-extent files can't have physical blocks past 2^32 */
-		if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
-		    (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) >
-		     EXT4_MAX_BLOCK_FILE_PHYS)) {
+		if (tmp) {
+			tmp_pa = rb_entry(tmp, struct ext4_prealloc_space,
+					    pa_node.inode_node);
+		} else {
 			/*
-			 * Since PAs don't overlap, we won't find any
-			 * other PA to satisfy this.
+			 * If there is no adjacent pa to the left then finding
+			 * an overlapping pa is not possible hence stop searching
+			 * inode pa tree
 			 */
-			break;
+			goto try_group_pa;
 		}
+	}
+
+	BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical));
 
-		/* found preallocated blocks, use them */
+	/*
+	 * Step 3: If the left adjacent pa is deleted, keep moving left to find
+	 * the first non deleted adjacent pa. After this step we should have a
+	 * valid tmp_pa which is guaranteed to be non deleted.
+	 */
+	for (iter = &tmp_pa->pa_node.inode_node;; iter = rb_prev(iter)) {
+		if (!iter) {
+			/*
+			 * no non deleted left adjacent pa, so stop searching
+			 * inode pa tree
+			 */
+			goto try_group_pa;
+		}
+		tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+				  pa_node.inode_node);
 		spin_lock(&tmp_pa->pa_lock);
-		if (tmp_pa->pa_deleted == 0 && tmp_pa->pa_free &&
-		    likely(ext4_mb_pa_goal_check(ac, tmp_pa))) {
-			atomic_inc(&tmp_pa->pa_count);
-			ext4_mb_use_inode_pa(ac, tmp_pa);
+		if (tmp_pa->pa_deleted == 0) {
+			/*
+			 * We will keep holding the pa_lock from
+			 * this point on because we don't want group discard
+			 * to delete this pa underneath us. Since group
+			 * discard is anyways an ENOSPC operation it
+			 * should be okay for it to wait a few more cycles.
+			 */
+			break;
+		} else {
 			spin_unlock(&tmp_pa->pa_lock);
-			read_unlock(&ei->i_prealloc_lock);
-			return true;
 		}
+	}
+
+	BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical));
+	BUG_ON(tmp_pa->pa_deleted == 1);
+
+	/*
+	 * Step 4: We now have the non deleted left adjacent pa. Only this
+	 * pa can possibly satisfy the request hence check if it overlaps
+	 * original logical start and stop searching if it doesn't.
+	 */
+	tmp_pa_end = (loff_t)tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
+
+	if (ac->ac_o_ex.fe_logical >= tmp_pa_end) {
 		spin_unlock(&tmp_pa->pa_lock);
+		goto try_group_pa;
+	}
+
+	/* non-extent files can't have physical blocks past 2^32 */
+	if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
+	    (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) >
+	     EXT4_MAX_BLOCK_FILE_PHYS)) {
+		/*
+		 * Since PAs don't overlap, we won't find any other PA to
+		 * satisfy this.
+		 */
+		spin_unlock(&tmp_pa->pa_lock);
+		goto try_group_pa;
+	}
+
+	if (tmp_pa->pa_free && likely(ext4_mb_pa_goal_check(ac, tmp_pa))) {
+		atomic_inc(&tmp_pa->pa_count);
+		ext4_mb_use_inode_pa(ac, tmp_pa);
+		spin_unlock(&tmp_pa->pa_lock);
+		read_unlock(&ei->i_prealloc_lock);
+		return true;
+	} else {
+		/*
+		 * We found a valid overlapping pa but couldn't use it because
+		 * it had no free blocks. This should ideally never happen
+		 * because:
+		 *
+		 * 1. When a new inode pa is added to rbtree it must have
+		 *    pa_free > 0 since otherwise we won't actually need
+		 *    preallocation.
+		 *
+		 * 2. An inode pa that is in the rbtree can only have it's
+		 *    pa_free become zero when another thread calls:
+		 *      ext4_mb_new_blocks
+		 *       ext4_mb_use_preallocated
+		 *        ext4_mb_use_inode_pa
+		 *
+		 * 3. Further, after the above calls make pa_free == 0, we will
+		 *    immediately remove it from the rbtree in:
+		 *      ext4_mb_new_blocks
+		 *       ext4_mb_release_context
+		 *        ext4_mb_put_pa
+		 *
+		 * 4. Since the pa_free becoming 0 and pa_free getting removed
+		 * from tree both happen in ext4_mb_new_blocks, which is always
+		 * called with i_data_sem held for data allocations, we can be
+		 * sure that another process will never see a pa in rbtree with
+		 * pa_free == 0.
+		 */
+		WARN_ON_ONCE(tmp_pa->pa_free == 0);
 	}
+	spin_unlock(&tmp_pa->pa_lock);
+try_group_pa:
 	read_unlock(&ei->i_prealloc_lock);
 
 	/* can we use group allocation? */
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 321e3a888c20b..05151d61b00b3 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1782,6 +1782,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 		memmove(here, (void *)here + size,
 			(void *)last - (void *)here + sizeof(__u32));
 		memset(last, 0, size);
+
+		/*
+		 * Update i_inline_off - moved ibody region might contain
+		 * system.data attribute.  Handling a failure here won't
+		 * cause other complications for setting an xattr.
+		 */
+		if (!is_block && ext4_has_inline_data(inode)) {
+			ret = ext4_find_inline_data_nolock(inode);
+			if (ret) {
+				ext4_warning_inode(inode,
+					"unable to update i_inline_off");
+				goto out;
+			}
+		}
 	} else if (s->not_found) {
 		/* Insert new name. */
 		size_t size = EXT4_XATTR_LEN(name_len);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 51bd38da21cdd..9ec91017a7f3c 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -27,7 +27,7 @@
  *
  * Called with j_list_lock held.
  */
-static inline void __buffer_unlink_first(struct journal_head *jh)
+static inline void __buffer_unlink(struct journal_head *jh)
 {
 	transaction_t *transaction = jh->b_cp_transaction;
 
@@ -40,45 +40,6 @@ static inline void __buffer_unlink_first(struct journal_head *jh)
 	}
 }
 
-/*
- * Unlink a buffer from a transaction checkpoint(io) list.
- *
- * Called with j_list_lock held.
- */
-static inline void __buffer_unlink(struct journal_head *jh)
-{
-	transaction_t *transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-	if (transaction->t_checkpoint_io_list == jh) {
-		transaction->t_checkpoint_io_list = jh->b_cpnext;
-		if (transaction->t_checkpoint_io_list == jh)
-			transaction->t_checkpoint_io_list = NULL;
-	}
-}
-
-/*
- * Move a buffer from the checkpoint list to the checkpoint io list
- *
- * Called with j_list_lock held
- */
-static inline void __buffer_relink_io(struct journal_head *jh)
-{
-	transaction_t *transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-
-	if (!transaction->t_checkpoint_io_list) {
-		jh->b_cpnext = jh->b_cpprev = jh;
-	} else {
-		jh->b_cpnext = transaction->t_checkpoint_io_list;
-		jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev;
-		jh->b_cpprev->b_cpnext = jh;
-		jh->b_cpnext->b_cpprev = jh;
-	}
-	transaction->t_checkpoint_io_list = jh;
-}
-
 /*
  * Check a checkpoint buffer could be release or not.
  *
@@ -183,6 +144,7 @@ __flush_batch(journal_t *journal, int *batch_count)
 		struct buffer_head *bh = journal->j_chkpt_bhs[i];
 		BUFFER_TRACE(bh, "brelse");
 		__brelse(bh);
+		journal->j_chkpt_bhs[i] = NULL;
 	}
 	*batch_count = 0;
 }
@@ -242,15 +204,6 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 		jh = transaction->t_checkpoint_list;
 		bh = jh2bh(jh);
 
-		if (buffer_locked(bh)) {
-			get_bh(bh);
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			goto retry;
-		}
 		if (jh->b_transaction != NULL) {
 			transaction_t *t = jh->b_transaction;
 			tid_t tid = t->t_tid;
@@ -285,30 +238,50 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 		}
-		if (!buffer_dirty(bh)) {
+		if (!trylock_buffer(bh)) {
+			/*
+			 * The buffer is locked, it may be writing back, or
+			 * flushing out in the last couple of cycles, or
+			 * re-adding into a new transaction, need to check
+			 * it again until it's unlocked.
+			 */
+			get_bh(bh);
+			spin_unlock(&journal->j_list_lock);
+			wait_on_buffer(bh);
+			/* the journal_head may have gone by now */
+			BUFFER_TRACE(bh, "brelse");
+			__brelse(bh);
+			goto retry;
+		} else if (!buffer_dirty(bh)) {
+			unlock_buffer(bh);
 			BUFFER_TRACE(bh, "remove from checkpoint");
-			if (__jbd2_journal_remove_checkpoint(jh))
-				/* The transaction was released; we're done */
+			/*
+			 * If the transaction was released or the checkpoint
+			 * list was empty, we're done.
+			 */
+			if (__jbd2_journal_remove_checkpoint(jh) ||
+			    !transaction->t_checkpoint_list)
 				goto out;
-			continue;
+		} else {
+			unlock_buffer(bh);
+			/*
+			 * We are about to write the buffer, it could be
+			 * raced by some other transaction shrink or buffer
+			 * re-log logic once we release the j_list_lock,
+			 * leave it on the checkpoint list and check status
+			 * again to make sure it's clean.
+			 */
+			BUFFER_TRACE(bh, "queue");
+			get_bh(bh);
+			J_ASSERT_BH(bh, !buffer_jwrite(bh));
+			journal->j_chkpt_bhs[batch_count++] = bh;
+			transaction->t_chp_stats.cs_written++;
+			transaction->t_checkpoint_list = jh->b_cpnext;
 		}
-		/*
-		 * Important: we are about to write the buffer, and
-		 * possibly block, while still holding the journal
-		 * lock.  We cannot afford to let the transaction
-		 * logic start messing around with this buffer before
-		 * we write it to disk, as that would break
-		 * recoverability.
-		 */
-		BUFFER_TRACE(bh, "queue");
-		get_bh(bh);
-		J_ASSERT_BH(bh, !buffer_jwrite(bh));
-		journal->j_chkpt_bhs[batch_count++] = bh;
-		__buffer_relink_io(jh);
-		transaction->t_chp_stats.cs_written++;
+
 		if ((batch_count == JBD2_NR_BATCH) ||
-		    need_resched() ||
-		    spin_needbreak(&journal->j_list_lock))
+		    need_resched() || spin_needbreak(&journal->j_list_lock) ||
+		    jh2bh(transaction->t_checkpoint_list) == journal->j_chkpt_bhs[0])
 			goto unlock_and_flush;
 	}
 
@@ -322,38 +295,6 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 			goto restart;
 	}
 
-	/*
-	 * Now we issued all of the transaction's buffers, let's deal
-	 * with the buffers that are out for I/O.
-	 */
-restart2:
-	/* Did somebody clean up the transaction in the meanwhile? */
-	if (journal->j_checkpoint_transactions != transaction ||
-	    transaction->t_tid != this_tid)
-		goto out;
-
-	while (transaction->t_checkpoint_io_list) {
-		jh = transaction->t_checkpoint_io_list;
-		bh = jh2bh(jh);
-		if (buffer_locked(bh)) {
-			get_bh(bh);
-			spin_unlock(&journal->j_list_lock);
-			wait_on_buffer(bh);
-			/* the journal_head may have gone by now */
-			BUFFER_TRACE(bh, "brelse");
-			__brelse(bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart2;
-		}
-
-		/*
-		 * Now in whatever state the buffer currently is, we
-		 * know that it has been written out and so we can
-		 * drop it from the list
-		 */
-		if (__jbd2_journal_remove_checkpoint(jh))
-			break;
-	}
 out:
 	spin_unlock(&journal->j_list_lock);
 	result = jbd2_cleanup_journal_tail(journal);
@@ -408,50 +349,10 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 
 /* Checkpoint list management */
 
-/*
- * journal_clean_one_cp_list
- *
- * Find all the written-back checkpoint buffers in the given list and
- * release them. If 'destroy' is set, clean all buffers unconditionally.
- *
- * Called with j_list_lock held.
- * Returns 1 if we freed the transaction, 0 otherwise.
- */
-static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy)
-{
-	struct journal_head *last_jh;
-	struct journal_head *next_jh = jh;
-
-	if (!jh)
-		return 0;
-
-	last_jh = jh->b_cpprev;
-	do {
-		jh = next_jh;
-		next_jh = jh->b_cpnext;
-
-		if (!destroy && __cp_buffer_busy(jh))
-			return 0;
-
-		if (__jbd2_journal_remove_checkpoint(jh))
-			return 1;
-		/*
-		 * This function only frees up some memory
-		 * if possible so we dont have an obligation
-		 * to finish processing. Bail out if preemption
-		 * requested:
-		 */
-		if (need_resched())
-			return 0;
-	} while (jh != last_jh);
-
-	return 0;
-}
-
 /*
  * journal_shrink_one_cp_list
  *
- * Find 'nr_to_scan' written-back checkpoint buffers in the given list
+ * Find all the written-back checkpoint buffers in the given list
  * and try to release them. If the whole transaction is released, set
  * the 'released' parameter. Return the number of released checkpointed
  * buffers.
@@ -459,15 +360,15 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy)
  * Called with j_list_lock held.
  */
 static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
-						unsigned long *nr_to_scan,
-						bool *released)
+						bool destroy, bool *released)
 {
 	struct journal_head *last_jh;
 	struct journal_head *next_jh = jh;
 	unsigned long nr_freed = 0;
 	int ret;
 
-	if (!jh || *nr_to_scan == 0)
+	*released = false;
+	if (!jh)
 		return 0;
 
 	last_jh = jh->b_cpprev;
@@ -475,12 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
 
-		(*nr_to_scan)--;
-		if (__cp_buffer_busy(jh))
-			continue;
+		if (destroy) {
+			ret = __jbd2_journal_remove_checkpoint(jh);
+		} else {
+			ret = jbd2_journal_try_remove_checkpoint(jh);
+			if (ret < 0)
+				continue;
+		}
 
 		nr_freed++;
-		ret = __jbd2_journal_remove_checkpoint(jh);
 		if (ret) {
 			*released = true;
 			break;
@@ -488,7 +392,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 
 		if (need_resched())
 			break;
-	} while (jh != last_jh && *nr_to_scan);
+	} while (jh != last_jh);
 
 	return nr_freed;
 }
@@ -506,11 +410,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 						  unsigned long *nr_to_scan)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	bool released;
+	bool __maybe_unused released;
 	tid_t first_tid = 0, last_tid = 0, next_tid = 0;
 	tid_t tid = 0;
 	unsigned long nr_freed = 0;
-	unsigned long nr_scanned = *nr_to_scan;
+	unsigned long freed;
 
 again:
 	spin_lock(&journal->j_list_lock);
@@ -539,19 +443,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
 		tid = transaction->t_tid;
-		released = false;
-
-		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list,
-						       nr_to_scan, &released);
-		if (*nr_to_scan == 0)
-			break;
-		if (need_resched() || spin_needbreak(&journal->j_list_lock))
-			break;
-		if (released)
-			continue;
 
-		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list,
-						       nr_to_scan, &released);
+		freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list,
+						   false, &released);
+		nr_freed += freed;
+		(*nr_to_scan) -= min(*nr_to_scan, freed);
 		if (*nr_to_scan == 0)
 			break;
 		if (need_resched() || spin_needbreak(&journal->j_list_lock))
@@ -572,9 +468,8 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 	if (*nr_to_scan && next_tid)
 		goto again;
 out:
-	nr_scanned -= *nr_to_scan;
 	trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid,
-					  nr_freed, nr_scanned, next_tid);
+					  nr_freed, next_tid);
 
 	return nr_freed;
 }
@@ -590,7 +485,7 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	int ret;
+	bool released;
 
 	transaction = journal->j_checkpoint_transactions;
 	if (!transaction)
@@ -601,8 +496,8 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 	do {
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
-		ret = journal_clean_one_cp_list(transaction->t_checkpoint_list,
-						destroy);
+		journal_shrink_one_cp_list(transaction->t_checkpoint_list,
+					   destroy, &released);
 		/*
 		 * This function only frees up some memory if possible so we
 		 * dont have an obligation to finish processing. Bail out if
@@ -610,23 +505,12 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 		 */
 		if (need_resched())
 			return;
-		if (ret)
-			continue;
-		/*
-		 * It is essential that we are as careful as in the case of
-		 * t_checkpoint_list with removing the buffer from the list as
-		 * we can possibly see not yet submitted buffers on io_list
-		 */
-		ret = journal_clean_one_cp_list(transaction->
-				t_checkpoint_io_list, destroy);
-		if (need_resched())
-			return;
 		/*
 		 * Stop scanning if we couldn't free the transaction. This
 		 * avoids pointless scanning of transactions which still
 		 * weren't checkpointed.
 		 */
-		if (!ret)
+		if (!released)
 			return;
 	} while (transaction != last_transaction);
 }
@@ -705,7 +589,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	jbd2_journal_put_journal_head(jh);
 
 	/* Is this transaction empty? */
-	if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list)
+	if (transaction->t_checkpoint_list)
 		return 0;
 
 	/*
@@ -736,6 +620,34 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	return 1;
 }
 
+/*
+ * Check the checkpoint buffer and try to remove it from the checkpoint
+ * list if it's clean. Returns -EBUSY if it is not clean, returns 1 if
+ * it frees the transaction, 0 otherwise.
+ *
+ * This function is called with j_list_lock held.
+ */
+int jbd2_journal_try_remove_checkpoint(struct journal_head *jh)
+{
+	struct buffer_head *bh = jh2bh(jh);
+
+	if (!trylock_buffer(bh))
+		return -EBUSY;
+	if (buffer_dirty(bh)) {
+		unlock_buffer(bh);
+		return -EBUSY;
+	}
+	unlock_buffer(bh);
+
+	/*
+	 * Buffer is clean and the IO has finished (we held the buffer
+	 * lock) so the checkpoint is done. We can safely remove the
+	 * buffer from this transaction.
+	 */
+	JBUFFER_TRACE(jh, "remove from checkpoint list");
+	return __jbd2_journal_remove_checkpoint(jh);
+}
+
 /*
  * journal_insert_checkpoint: put a committed buffer onto a checkpoint
  * list so that we know when it is safe to clean the transaction out of
@@ -797,7 +709,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
 	J_ASSERT(transaction->t_forget == NULL);
 	J_ASSERT(transaction->t_shadow_list == NULL);
 	J_ASSERT(transaction->t_checkpoint_list == NULL);
-	J_ASSERT(transaction->t_checkpoint_io_list == NULL);
 	J_ASSERT(atomic_read(&transaction->t_updates) == 0);
 	J_ASSERT(journal->j_committing_transaction != transaction);
 	J_ASSERT(journal->j_running_transaction != transaction);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index b33155dd70017..1073259902a60 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -1141,8 +1141,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
+	if (commit_transaction->t_checkpoint_list == NULL) {
 		__jbd2_journal_drop_transaction(journal, commit_transaction);
 		jbd2_journal_free_transaction(commit_transaction);
 	}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 18611241f4513..4d1fda1f71439 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1784,8 +1784,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
 		 * Otherwise, if the buffer has been written to disk,
 		 * it is safe to remove the checkpoint and drop it.
 		 */
-		if (!buffer_dirty(bh)) {
-			__jbd2_journal_remove_checkpoint(jh);
+		if (jbd2_journal_try_remove_checkpoint(jh) >= 0) {
 			spin_unlock(&journal->j_list_lock);
 			goto drop;
 		}
@@ -2100,35 +2099,6 @@ void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
 	__brelse(bh);
 }
 
-/*
- * Called from jbd2_journal_try_to_free_buffers().
- *
- * Called under jh->b_state_lock
- */
-static void
-__journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
-{
-	struct journal_head *jh;
-
-	jh = bh2jh(bh);
-
-	if (buffer_locked(bh) || buffer_dirty(bh))
-		goto out;
-
-	if (jh->b_next_transaction != NULL || jh->b_transaction != NULL)
-		goto out;
-
-	spin_lock(&journal->j_list_lock);
-	if (jh->b_cp_transaction != NULL) {
-		/* written-back checkpointed metadata buffer */
-		JBUFFER_TRACE(jh, "remove from checkpoint list");
-		__jbd2_journal_remove_checkpoint(jh);
-	}
-	spin_unlock(&journal->j_list_lock);
-out:
-	return;
-}
-
 /**
  * jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
@@ -2186,7 +2156,13 @@ bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio)
 			continue;
 
 		spin_lock(&jh->b_state_lock);
-		__journal_try_to_free_buffer(journal, bh);
+		if (!jh->b_transaction && !jh->b_next_transaction) {
+			spin_lock(&journal->j_list_lock);
+			/* Remove written-back checkpointed metadata buffer */
+			if (jh->b_cp_transaction != NULL)
+				jbd2_journal_try_remove_checkpoint(jh);
+			spin_unlock(&journal->j_list_lock);
+		}
 		spin_unlock(&jh->b_state_lock);
 		jbd2_journal_put_journal_head(jh);
 		if (buffer_jbd(bh))
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index d7274eefc666a..15c8cc4b66809 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -159,6 +159,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 43
-#define CIFS_VERSION   "2.43"
+#define SMB3_PRODUCT_BUILD 44
+#define CIFS_VERSION   "2.44"
 #endif				/* _CIFSFS_H */
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index fff092bbc7a37..e1904b86ed967 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -433,16 +433,21 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 			 * Dump encryption keys. This is an old ioctl that only
 			 * handles AES-128-{CCM,GCM}.
 			 */
-			if (pSMBFile == NULL)
-				break;
 			if (!capable(CAP_SYS_ADMIN)) {
 				rc = -EACCES;
 				break;
 			}
 
-			tcon = tlink_tcon(pSMBFile->tlink);
+			cifs_sb = CIFS_SB(inode->i_sb);
+			tlink = cifs_sb_tlink(cifs_sb);
+			if (IS_ERR(tlink)) {
+				rc = PTR_ERR(tlink);
+				break;
+			}
+			tcon = tlink_tcon(tlink);
 			if (!smb3_encryption_required(tcon)) {
 				rc = -EOPNOTSUPP;
+				cifs_put_tlink(tlink);
 				break;
 			}
 			pkey_inf.cipher_type =
@@ -459,6 +464,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				rc = -EFAULT;
 			else
 				rc = 0;
+			cifs_put_tlink(tlink);
 			break;
 		case CIFS_DUMP_FULL_KEY:
 			/*
@@ -470,8 +476,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				rc = -EACCES;
 				break;
 			}
-			tcon = tlink_tcon(pSMBFile->tlink);
+			cifs_sb = CIFS_SB(inode->i_sb);
+			tlink = cifs_sb_tlink(cifs_sb);
+			tcon = tlink_tcon(tlink);
 			rc = cifs_dump_full_key(tcon, (void __user *)arg);
+			cifs_put_tlink(tlink);
 			break;
 		case CIFS_IOC_NOTIFY:
 			if (!S_ISDIR(inode->i_mode)) {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 402b545959af7..5b27f94d4fad6 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -431,7 +431,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 
 int vgic_v4_load(struct kvm_vcpu *vcpu);
 void vgic_v4_commit(struct kvm_vcpu *vcpu);
-int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
+int vgic_v4_put(struct kvm_vcpu *vcpu);
 
 /* CPU HP callbacks */
 void kvm_vgic_cpu_up(void);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d860499e15e45..44c298aa58d44 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -613,12 +613,6 @@ struct transaction_s
 	 */
 	struct journal_head	*t_checkpoint_list;
 
-	/*
-	 * Doubly-linked circular list of all buffers submitted for IO while
-	 * checkpointing. [j_list_lock]
-	 */
-	struct journal_head	*t_checkpoint_io_list;
-
 	/*
 	 * Doubly-linked circular list of metadata buffers being
 	 * shadowed by log IO.  The IO buffers on the iobuf list and
@@ -1449,6 +1443,7 @@ extern void jbd2_journal_commit_transaction(journal_t *);
 void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy);
 unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan);
 int __jbd2_journal_remove_checkpoint(struct journal_head *);
+int jbd2_journal_try_remove_checkpoint(struct journal_head *jh);
 void jbd2_journal_destroy_checkpoint(journal_t *journal);
 void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
 
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 8f5ee380d3093..5646ae15a957a 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -462,11 +462,9 @@ TRACE_EVENT(jbd2_shrink_scan_exit,
 TRACE_EVENT(jbd2_shrink_checkpoint_list,
 
 	TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid,
-		 unsigned long nr_freed, unsigned long nr_scanned,
-		 tid_t next_tid),
+		 unsigned long nr_freed, tid_t next_tid),
 
-	TP_ARGS(journal, first_tid, tid, last_tid, nr_freed,
-		nr_scanned, next_tid),
+	TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, next_tid),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -474,7 +472,6 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list,
 		__field(tid_t, tid)
 		__field(tid_t, last_tid)
 		__field(unsigned long, nr_freed)
-		__field(unsigned long, nr_scanned)
 		__field(tid_t, next_tid)
 	),
 
@@ -484,15 +481,14 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list,
 		__entry->tid		= tid;
 		__entry->last_tid	= last_tid;
 		__entry->nr_freed	= nr_freed;
-		__entry->nr_scanned	= nr_scanned;
 		__entry->next_tid	= next_tid;
 	),
 
 	TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu "
-		  "scanned %lu next transaction %u",
+		  "next transaction %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->first_tid, __entry->tid, __entry->last_tid,
-		  __entry->nr_freed, __entry->nr_scanned, __entry->next_tid)
+		  __entry->nr_freed, __entry->next_tid)
 );
 
 #endif /* _TRACE_JBD2_H */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 14d8001140c82..de061dd473132 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -536,6 +536,7 @@ struct trace_buffer {
 	unsigned			flags;
 	int				cpus;
 	atomic_t			record_disabled;
+	atomic_t			resizing;
 	cpumask_var_t			cpumask;
 
 	struct lock_class_key		*reader_lock_key;
@@ -2167,7 +2168,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 
 	/* prevent another thread from changing buffer sizes */
 	mutex_lock(&buffer->mutex);
-
+	atomic_inc(&buffer->resizing);
 
 	if (cpu_id == RING_BUFFER_ALL_CPUS) {
 		/*
@@ -2322,6 +2323,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		atomic_dec(&buffer->record_disabled);
 	}
 
+	atomic_dec(&buffer->resizing);
 	mutex_unlock(&buffer->mutex);
 	return 0;
 
@@ -2342,6 +2344,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		}
 	}
  out_err_unlock:
+	atomic_dec(&buffer->resizing);
 	mutex_unlock(&buffer->mutex);
 	return err;
 }
@@ -5541,6 +5544,15 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 	if (local_read(&cpu_buffer_b->committing))
 		goto out_dec;
 
+	/*
+	 * When resize is in progress, we cannot swap it because
+	 * it will mess the state of the cpu buffer.
+	 */
+	if (atomic_read(&buffer_a->resizing))
+		goto out_dec;
+	if (atomic_read(&buffer_b->resizing))
+		goto out_dec;
+
 	buffer_a->buffers[cpu] = cpu_buffer_b;
 	buffer_b->buffers[cpu] = cpu_buffer_a;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index be847d45d81cf..b8870078ef58d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1928,9 +1928,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		 * place on this CPU. We fail to record, but we reset
 		 * the max trace buffer (no one writes directly to it)
 		 * and flag that it failed.
+		 * Another reason is resize is in progress.
 		 */
 		trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_,
-			"Failed to swap buffers due to commit in progress\n");
+			"Failed to swap buffers due to commit or resize in progress\n");
 	}
 
 	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index c8c61381eba48..d06938ae07174 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6668,7 +6668,8 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		goto out_unreg;
 
 	if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
-		if (save_hist_vars(hist_data))
+		ret = save_hist_vars(hist_data);
+		if (ret)
 			goto out_unreg;
 	}
 
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
index 2c765ee2a4d4e..99c37eeebc161 100644
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -272,10 +272,6 @@ extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
 extern u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i);
 extern u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i);
 
-extern void tracing_map_set_field_descr(struct tracing_map *map,
-					unsigned int i,
-					unsigned int key_offset,
-					tracing_map_cmp_fn_t cmp_fn);
 extern int
 tracing_map_sort_entries(struct tracing_map *map,
 			 struct tracing_map_sort_key *sort_keys,
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 6413342a03f4c..82e3fb19fdafc 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -264,6 +264,9 @@ $(obj)/%.lst: $(src)/%.c FORCE
 
 rust_allowed_features := new_uninit
 
+# `--out-dir` is required to avoid temporaries being created by `rustc` in the
+# current working directory, which may be not accessible in the out-of-tree
+# modules case.
 rust_common_cmd = \
 	RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \
 	-Zallow-features=$(rust_allowed_features) \
@@ -272,7 +275,7 @@ rust_common_cmd = \
 	--extern alloc --extern kernel \
 	--crate-type rlib -L $(objtree)/rust/ \
 	--crate-name $(basename $(notdir $@)) \
-	--emit=dep-info=$(depfile)
+	--out-dir $(dir $@) --emit=dep-info=$(depfile)
 
 # `--emit=obj`, `--emit=asm` and `--emit=llvm-ir` imply a single codegen unit
 # will be used. We explicitly request `-Ccodegen-units=1` in any case, and
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 7aea9005e4970..8f7f842b54f9e 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -86,7 +86,11 @@ hostc_flags    = -Wp,-MMD,$(depfile) \
 hostcxx_flags  = -Wp,-MMD,$(depfile) \
                  $(KBUILD_HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \
                  $(HOSTCXXFLAGS_$(target-stem).o)
-hostrust_flags = --emit=dep-info=$(depfile) \
+
+# `--out-dir` is required to avoid temporaries being created by `rustc` in the
+# current working directory, which may be not accessible in the out-of-tree
+# modules case.
+hostrust_flags = --out-dir $(dir $@) --emit=dep-info=$(depfile) \
                  $(KBUILD_HOSTRUSTFLAGS) $(HOST_EXTRARUSTFLAGS) \
                  $(HOSTRUSTFLAGS_$(target-stem))
 
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py
index 15ba56527acd8..a84cc5737c2c6 100755
--- a/scripts/clang-tools/gen_compile_commands.py
+++ b/scripts/clang-tools/gen_compile_commands.py
@@ -19,7 +19,7 @@
 _DEFAULT_LOG_LEVEL = 'WARNING'
 
 _FILENAME_PATTERN = r'^\..*\.cmd$'
-_LINE_PATTERN = r'^savedcmd_[^ ]*\.o := (.* )([^ ]*\.c) *(;|$)'
+_LINE_PATTERN = r'^savedcmd_[^ ]*\.o := (.* )([^ ]*\.[cS]) *(;|$)'
 _VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
 # The tools/ directory adopts a different build system, and produces .cmd
 # files in a different format. Do not support it.
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index 17adabfd6e6bf..9709aca3a30fe 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -636,7 +636,7 @@ void on_introduction1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *dialog;
 	const gchar *intro_text =
-	    "Welcome to gkc, the GTK+ graphical configuration tool\n"
+	    "Welcome to gconfig, the GTK+ graphical configuration tool.\n"
 	    "For each option, a blank box indicates the feature is disabled, a\n"
 	    "check indicates it is enabled, and a dot indicates that it is to\n"
 	    "be compiled as a module.  Clicking on the box will cycle through the three states.\n"
@@ -647,10 +647,7 @@ void on_introduction1_activate(GtkMenuItem * menuitem, gpointer user_data)
 	    "Although there is no cross reference yet to help you figure out\n"
 	    "what other options must be enabled to support the option you\n"
 	    "are interested in, you can still view the help of a grayed-out\n"
-	    "option.\n"
-	    "\n"
-	    "Toggling Show Debug Info under the Options menu will show \n"
-	    "the dependencies, which you can then match by examining other options.";
+	    "option.";
 
 	dialog = gtk_message_dialog_new(GTK_WINDOW(main_wnd),
 					GTK_DIALOG_DESTROY_WITH_PARENT,
@@ -667,7 +664,7 @@ void on_about1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *dialog;
 	const gchar *about_text =
-	    "gkc is copyright (c) 2002 Romain Lievin <roms@lpg.ticalc.org>.\n"
+	    "gconfig is copyright (c) 2002 Romain Lievin <roms@lpg.ticalc.org>.\n"
 	      "Based on the source code from Roman Zippel.\n";
 
 	dialog = gtk_message_dialog_new(GTK_WINDOW(main_wnd),
@@ -685,7 +682,7 @@ void on_license1_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	GtkWidget *dialog;
 	const gchar *license_text =
-	    "gkc is released under the terms of the GNU GPL v2.\n"
+	    "gconfig is released under the terms of the GNU GPL v2.\n"
 	      "For more information, please see the source code or\n"
 	      "visit http://www.fsf.org/licenses/licenses.html\n";