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

Cross-merge networking fixes after downstream PR.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

53 files changed, 295 insertions, 203 deletions

diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h
index 78d3d4b82c6c..f4db3e75d75f 100644
--- a/arch/arm/include/asm/arm_pmuv3.h
+++ b/arch/arm/include/asm/arm_pmuv3.h
@@ -92,7 +92,7 @@
 
 #define RETURN_READ_PMEVCNTRN(n) \
 	return read_sysreg(PMEVCNTR##n)
-static unsigned long read_pmevcntrn(int n)
+static inline unsigned long read_pmevcntrn(int n)
 {
 	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
 	return 0;
@@ -100,14 +100,14 @@ static unsigned long read_pmevcntrn(int n)
 
 #define WRITE_PMEVCNTRN(n) \
 	write_sysreg(val, PMEVCNTR##n)
-static void write_pmevcntrn(int n, unsigned long val)
+static inline void write_pmevcntrn(int n, unsigned long val)
 {
 	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
 }
 
 #define WRITE_PMEVTYPERN(n) \
 	write_sysreg(val, PMEVTYPER##n)
-static void write_pmevtypern(int n, unsigned long val)
+static inline void write_pmevtypern(int n, unsigned long val)
 {
 	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
 }
diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h
index d6b51deb7bf0..18dc2fb3d7b7 100644
--- a/arch/arm64/include/asm/arm_pmuv3.h
+++ b/arch/arm64/include/asm/arm_pmuv3.h
@@ -13,7 +13,7 @@
 
 #define RETURN_READ_PMEVCNTRN(n) \
 	return read_sysreg(pmevcntr##n##_el0)
-static unsigned long read_pmevcntrn(int n)
+static inline unsigned long read_pmevcntrn(int n)
 {
 	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
 	return 0;
@@ -21,14 +21,14 @@ static unsigned long read_pmevcntrn(int n)
 
 #define WRITE_PMEVCNTRN(n) \
 	write_sysreg(val, pmevcntr##n##_el0)
-static void write_pmevcntrn(int n, unsigned long val)
+static inline void write_pmevcntrn(int n, unsigned long val)
 {
 	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
 }
 
 #define WRITE_PMEVTYPERN(n) \
 	write_sysreg(val, pmevtyper##n##_el0)
-static void write_pmevtypern(int n, unsigned long val)
+static inline void write_pmevtypern(int n, unsigned long val)
 {
 	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
 }
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 683ca3af4084..5f6f84837a49 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -126,6 +126,10 @@
 #define APPLE_CPU_PART_M1_FIRESTORM_MAX	0x029
 #define APPLE_CPU_PART_M2_BLIZZARD	0x032
 #define APPLE_CPU_PART_M2_AVALANCHE	0x033
+#define APPLE_CPU_PART_M2_BLIZZARD_PRO	0x034
+#define APPLE_CPU_PART_M2_AVALANCHE_PRO	0x035
+#define APPLE_CPU_PART_M2_BLIZZARD_MAX	0x038
+#define APPLE_CPU_PART_M2_AVALANCHE_MAX	0x039
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
@@ -181,6 +185,10 @@
 #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
 #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
 #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
+#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO)
+#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO)
+#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
+#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 4cd6762bda80..dc3c072e862f 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -209,6 +209,7 @@ struct kvm_pgtable_visit_ctx {
 	kvm_pte_t				old;
 	void					*arg;
 	struct kvm_pgtable_mm_ops		*mm_ops;
+	u64					start;
 	u64					addr;
 	u64					end;
 	u32					level;
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index f5bcb0dc6267..7e89968bd282 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte)
 		return;
 
 	/* if PG_mte_tagged is set, tags have already been initialised */
-	for (i = 0; i < nr_pages; i++, page++) {
-		if (!page_mte_tagged(page)) {
+	for (i = 0; i < nr_pages; i++, page++)
+		if (!page_mte_tagged(page))
 			mte_sync_page_tags(page, old_pte, check_swap,
 					   pte_is_tagged);
-			set_page_mte_tagged(page);
-		}
-	}
 
 	/* ensure the tags are visible before the PTE is set */
 	smp_wmb();
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 0119dc91abb5..d9e1355730ef 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void)
 
 	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
 	       kuser_sz);
-	aarch32_vectors_page = virt_to_page(vdso_page);
+	aarch32_vectors_page = virt_to_page((void *)vdso_page);
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 1279949599b5..4c9dcd8fc939 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -81,26 +81,34 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 
 	fpsimd_kvm_prepare();
 
+	/*
+	 * We will check TIF_FOREIGN_FPSTATE just before entering the
+	 * guest in kvm_arch_vcpu_ctxflush_fp() and override this to
+	 * FP_STATE_FREE if the flag set.
+	 */
 	vcpu->arch.fp_state = FP_STATE_HOST_OWNED;
 
 	vcpu_clear_flag(vcpu, HOST_SVE_ENABLED);
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
 		vcpu_set_flag(vcpu, HOST_SVE_ENABLED);
 
-	/*
-	 * We don't currently support SME guests but if we leave
-	 * things in streaming mode then when the guest starts running
-	 * FPSIMD or SVE code it may generate SME traps so as a
-	 * special case if we are in streaming mode we force the host
-	 * state to be saved now and exit streaming mode so that we
-	 * don't have to handle any SME traps for valid guest
-	 * operations. Do this for ZA as well for now for simplicity.
-	 */
 	if (system_supports_sme()) {
 		vcpu_clear_flag(vcpu, HOST_SME_ENABLED);
 		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
 			vcpu_set_flag(vcpu, HOST_SME_ENABLED);
 
+		/*
+		 * If PSTATE.SM is enabled then save any pending FP
+		 * state and disable PSTATE.SM. If we leave PSTATE.SM
+		 * enabled and the guest does not enable SME via
+		 * CPACR_EL1.SMEN then operations that should be valid
+		 * may generate SME traps from EL1 to EL1 which we
+		 * can't intercept and which would confuse the guest.
+		 *
+		 * Do the same for PSTATE.ZA in the case where there
+		 * is state in the registers which has not already
+		 * been saved, this is very unlikely to happen.
+		 */
 		if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) {
 			vcpu->arch.fp_state = FP_STATE_FREE;
 			fpsimd_save_and_flush_cpu_state();
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index c41166f1a1dd..e78a08a72a3c 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -177,9 +177,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	sve_guest = vcpu_has_sve(vcpu);
 	esr_ec = kvm_vcpu_trap_get_class(vcpu);
 
-	/* Don't handle SVE traps for non-SVE vcpus here: */
-	if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD)
+	/* Only handle traps the vCPU can support here: */
+	switch (esr_ec) {
+	case ESR_ELx_EC_FP_ASIMD:
+		break;
+	case ESR_ELx_EC_SVE:
+		if (!sve_guest)
+			return false;
+		break;
+	default:
 		return false;
+	}
 
 	/* Valid trap.  Switch the context: */
 
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 3d61bd3e591d..5282cb9ca4cf 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -58,8 +58,9 @@
 struct kvm_pgtable_walk_data {
 	struct kvm_pgtable_walker	*walker;
 
+	const u64			start;
 	u64				addr;
-	u64				end;
+	const u64			end;
 };
 
 static bool kvm_phys_is_valid(u64 phys)
@@ -201,6 +202,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		.old	= READ_ONCE(*ptep),
 		.arg	= data->walker->arg,
 		.mm_ops	= mm_ops,
+		.start	= data->start,
 		.addr	= data->addr,
 		.end	= data->end,
 		.level	= level,
@@ -293,6 +295,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		     struct kvm_pgtable_walker *walker)
 {
 	struct kvm_pgtable_walk_data walk_data = {
+		.start	= ALIGN_DOWN(addr, PAGE_SIZE),
 		.addr	= ALIGN_DOWN(addr, PAGE_SIZE),
 		.end	= PAGE_ALIGN(walk_data.addr + size),
 		.walker	= walker,
@@ -349,7 +352,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
 }
 
 struct hyp_map_data {
-	u64				phys;
+	const u64			phys;
 	kvm_pte_t			attr;
 };
 
@@ -407,13 +410,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte)
 static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 				    struct hyp_map_data *data)
 {
+	u64 phys = data->phys + (ctx->addr - ctx->start);
 	kvm_pte_t new;
-	u64 granule = kvm_granule_size(ctx->level), phys = data->phys;
 
 	if (!kvm_block_mapping_supported(ctx, phys))
 		return false;
 
-	data->phys += granule;
 	new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
 	if (ctx->old == new)
 		return true;
@@ -576,7 +578,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
 }
 
 struct stage2_map_data {
-	u64				phys;
+	const u64			phys;
 	kvm_pte_t			attr;
 	u8				owner_id;
 
@@ -794,20 +796,43 @@ static bool stage2_pte_executable(kvm_pte_t pte)
 	return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
 }
 
+static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx,
+				       const struct stage2_map_data *data)
+{
+	u64 phys = data->phys;
+
+	/*
+	 * Stage-2 walks to update ownership data are communicated to the map
+	 * walker using an invalid PA. Avoid offsetting an already invalid PA,
+	 * which could overflow and make the address valid again.
+	 */
+	if (!kvm_phys_is_valid(phys))
+		return phys;
+
+	/*
+	 * Otherwise, work out the correct PA based on how far the walk has
+	 * gotten.
+	 */
+	return phys + (ctx->addr - ctx->start);
+}
+
 static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 					struct stage2_map_data *data)
 {
+	u64 phys = stage2_map_walker_phys_addr(ctx, data);
+
 	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
 		return false;
 
-	return kvm_block_mapping_supported(ctx, data->phys);
+	return kvm_block_mapping_supported(ctx, phys);
 }
 
 static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 				      struct stage2_map_data *data)
 {
 	kvm_pte_t new;
-	u64 granule = kvm_granule_size(ctx->level), phys = data->phys;
+	u64 phys = stage2_map_walker_phys_addr(ctx, data);
+	u64 granule = kvm_granule_size(ctx->level);
 	struct kvm_pgtable *pgt = data->mmu->pgt;
 	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
@@ -841,8 +866,6 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 
 	stage2_make_pte(ctx, new);
 
-	if (kvm_phys_is_valid(phys))
-		data->phys += granule;
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 64c3aec0d937..0bd93a5f21ce 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu)
 	 * Size Fault at level 0, as if exceeding PARange.
 	 *
 	 * Non-LPAE guests will only get the external abort, as there
-	 * is no way to to describe the ASF.
+	 * is no way to describe the ASF.
 	 */
 	if (vcpu_el1_is_32bit(vcpu) &&
 	    !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE))
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 469d816f356f..93a47a515c13 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -616,6 +616,10 @@ static const struct midr_range broken_seis[] = {
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX),
 	{},
 };
 
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 08978d0672e7..7fe8ba1a2851 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -47,7 +47,7 @@ static void flush_context(void)
 	int cpu;
 	u64 vmid;
 
-	bitmap_clear(vmid_map, 0, NUM_USER_VMIDS);
+	bitmap_zero(vmid_map, NUM_USER_VMIDS);
 
 	for_each_possible_cpu(cpu) {
 		vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0);
@@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void)
 	 */
 	WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus());
 	atomic64_set(&vmid_generation, VMID_FIRST_VERSION);
-	vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS),
-			   sizeof(*vmid_map), GFP_KERNEL);
+	vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL);
 	if (!vmid_map)
 		return -ENOMEM;
 
@@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void)
 
 void __init kvm_arm_vmid_alloc_free(void)
 {
-	kfree(vmid_map);
+	bitmap_free(vmid_map);
 }
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 4aadcfb01754..a7bb20055ce0 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -21,9 +21,10 @@ void copy_highpage(struct page *to, struct page *from)
 
 	copy_page(kto, kfrom);
 
+	if (kasan_hw_tags_enabled())
+		page_kasan_tag_reset(to);
+
 	if (system_supports_mte() && page_mte_tagged(from)) {
-		if (kasan_hw_tags_enabled())
-			page_kasan_tag_reset(to);
 		/* It's a new page, shouldn't have been tagged yet */
 		WARN_ON_ONCE(!try_page_mte_tagging(to));
 		mte_copy_page_tags(kto, kfrom);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 9e0db5c387e3..cb21ccd7940d 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -480,8 +480,8 @@ static void do_bad_area(unsigned long far, unsigned long esr,
 	}
 }
 
-#define VM_FAULT_BADMAP		0x010000
-#define VM_FAULT_BADACCESS	0x020000
+#define VM_FAULT_BADMAP		((__force vm_fault_t)0x010000)
+#define VM_FAULT_BADACCESS	((__force vm_fault_t)0x020000)
 
 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 				  unsigned int mm_flags, unsigned long vm_flags,
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index b9f6908a31bc..ba468b5f3f0b 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -858,11 +858,17 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *
 }
 
 static inline void __user *
-get_sigframe(struct ksignal *ksig, size_t frame_size)
+get_sigframe(struct ksignal *ksig, struct pt_regs *tregs, size_t frame_size)
 {
 	unsigned long usp = sigsp(rdusp(), ksig);
+	unsigned long gap = 0;
 
-	return (void __user *)((usp - frame_size) & -8UL);
+	if (CPU_IS_020_OR_030 && tregs->format == 0xb) {
+		/* USP is unreliable so use worst-case value */
+		gap = 256;
+	}
+
+	return (void __user *)((usp - gap - frame_size) & -8UL);
 }
 
 static int setup_frame(struct ksignal *ksig, sigset_t *set,
@@ -880,7 +886,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 		return -EFAULT;
 	}
 
-	frame = get_sigframe(ksig, sizeof(*frame) + fsize);
+	frame = get_sigframe(ksig, tregs, sizeof(*frame) + fsize);
 
 	if (fsize)
 		err |= copy_to_user (frame + 1, regs + 1, fsize);
@@ -952,7 +958,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 		return -EFAULT;
 	}
 
-	frame = get_sigframe(ksig, sizeof(*frame));
+	frame = get_sigframe(ksig, tregs, sizeof(*frame));
 
 	if (fsize)
 		err |= copy_to_user (&frame->uc.uc_extra, regs + 1, fsize);
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 85cde5bf04b7..771b79423bbc 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -34,8 +34,6 @@ endif
 
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \
-		 $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \
-		 $(call cc-option,-mno-mma) \
 		 $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \
 		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
 		 $(LINUXINCLUDE)
@@ -71,6 +69,10 @@ BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc
 
 BOOTARFLAGS	:= -crD
 
+BOOTCFLAGS	+= $(call cc-option,-mno-prefixed) \
+		   $(call cc-option,-mno-pcrel) \
+		   $(call cc-option,-mno-mma)
+
 ifdef CONFIG_CC_IS_CLANG
 BOOTCFLAGS += $(CLANG_FLAGS)
 BOOTAFLAGS += $(CLANG_FLAGS)
diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
index 7113f9355165..ad1872518992 100644
--- a/arch/powerpc/crypto/Kconfig
+++ b/arch/powerpc/crypto/Kconfig
@@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE
 
 config CRYPTO_AES_GCM_P10
 	tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)"
-	depends on PPC64 && CPU_LITTLE_ENDIAN
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
 	select CRYPTO_LIB_AES
 	select CRYPTO_ALGAPI
 	select CRYPTO_AEAD
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 678b5bdc79b1..34e14dfd8e04 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group,
 				 int pci_domain_number, unsigned long pe_num);
 extern int iommu_add_device(struct iommu_table_group *table_group,
 		struct device *dev);
-extern void iommu_del_device(struct device *dev);
 extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction);
@@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group,
 {
 	return 0;
 }
-
-static inline void iommu_del_device(struct device *dev)
-{
-}
 #endif /* !CONFIG_IOMMU_API */
 
 u64 dma_iommu_get_required_mask(struct device *dev);
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 038ce8d9061d..8920862ffd79 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
 /* We support DMA to/from any memory page via the iommu */
 int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct iommu_table *tbl = get_iommu_table_base(dev);
+	struct iommu_table *tbl;
 
 	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
 		/*
@@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 1;
 	}
 
+	tbl = get_iommu_table_base(dev);
+
 	if (!tbl) {
 		dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
 		return 0;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0089dd49b4cb..67f0b01e6ff5 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		/* Convert entry to a dma_addr_t */
 		entry += tbl->it_offset;
 		dma_addr = entry << tbl->it_page_shift;
-		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));
+		dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl));
 
 		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
 			    npages, entry, dma_addr);
@@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	unsigned int order;
 	unsigned int nio_pages, io_order;
 	struct page *page;
+	int tcesize = (1 << tbl->it_page_shift);
 
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
@@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> tbl->it_page_shift;
+	nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
+
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
@@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}
-	*dma_handle = mapping;
+
+	*dma_handle = mapping | ((u64)ret & (tcesize - 1));
 	return ret;
 }
 
@@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		unsigned int nio_pages;
 
 		size = PAGE_ALIGN(size);
-		nio_pages = size >> tbl->it_page_shift;
+		nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
 		iommu_free(tbl, dma_handle, nio_pages);
 		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));
@@ -1168,23 +1171,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_add_device);
 
-void iommu_del_device(struct device *dev)
-{
-	/*
-	 * Some devices might not have IOMMU table and group
-	 * and we needn't detach them from the associated
-	 * IOMMU groups
-	 */
-	if (!device_iommu_mapped(dev)) {
-		pr_debug("iommu_tce: skipping device %s with no tbl\n",
-			 dev_name(dev));
-		return;
-	}
-
-	iommu_group_remove_device(dev);
-}
-EXPORT_SYMBOL_GPL(iommu_del_device);
-
 /*
  * A simple iommu_table_group_ops which only allows reusing the existing
  * iommu_table. This handles VFIO for POWER7 or the nested KVM.
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 85bdd7d3652f..48e0eaf1ad61 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node,
 	}
 
 inval_range:
-	if (!phb_io_base_phys) {
+	if (phb_io_base_phys) {
 		pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n");
 		remap_isa_base(phb_io_base_phys, 0x10000);
+		return 0;
 	}
-	return 0;
+	return -EINVAL;
 }
 
 
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 26245aaf12b8..2297aa764ecd 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 				  pte_t entry, unsigned long address, int psize)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
-					      _PAGE_RW | _PAGE_EXEC);
+	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY |
+					      _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
 
 	unsigned long change = pte_val(entry) ^ pte_val(*ptep);
 	/*
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index e93aefcfb83f..37043dfc1add 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		bpf_hdr = jit_data->header;
 		proglen = jit_data->proglen;
 		extra_pass = true;
+		/* During extra pass, ensure index is reset before repopulating extable entries */
+		cgctx.exentry_idx = 0;
 		goto skip_init_ctx;
 	}
 
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 0d9b7609c7d5..3e2e252016f7 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -265,6 +265,7 @@ config CPM2
 config FSL_ULI1575
 	bool "ULI1575 PCIe south bridge support"
 	depends on FSL_SOC_BOOKE || PPC_86xx
+	depends on PCI
 	select FSL_PCI
 	select GENERIC_ISA_DMA
 	help
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 233a50e65fce..7725492097b6 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -865,28 +865,3 @@ void __init pnv_pci_init(void)
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }
-
-static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block pnv_tce_iommu_bus_nb = {
-	.notifier_call = pnv_tce_iommu_bus_notifier,
-};
-
-static int __init pnv_tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb);
-	return 0;
-}
-machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 7464fa6e4145..918f511837db 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		const char *node_name)
 {
-	struct iommu_table *tbl;
-
 	if (!table_group)
 		return;
 
-	tbl = table_group->tables[0];
 #ifdef CONFIG_IOMMU_API
 	if (table_group->group) {
 		iommu_group_put(table_group->group);
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_tce_table_put(tbl);
+
+	/* Default DMA window table is at index 0, while DDW at 1. SR-IOV
+	 * adapters only have table on index 1.
+	 */
+	if (table_group->tables[0])
+		iommu_tce_table_put(table_group->tables[0]);
+
+	if (table_group->tables[1])
+		iommu_tce_table_put(table_group->tables[1]);
 
 	kfree(table_group);
 }
@@ -1695,31 +1700,6 @@ static int __init disable_multitce(char *str)
 
 __setup("multitce=", disable_multitce);
 
-static int tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block tce_iommu_bus_nb = {
-	.notifier_call = tce_iommu_bus_notifier,
-};
-
-static int __init tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
-	return 0;
-}
-machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init);
-
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose,
 					     struct pci_dev *pdev)
diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile
index c40139e9ca47..8265ff497977 100644
--- a/arch/riscv/kernel/probes/Makefile
+++ b/arch/riscv/kernel/probes/Makefile
@@ -4,3 +4,5 @@ obj-$(CONFIG_RETHOOK)		+= rethook.o rethook_trampoline.o
 obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o simulate-insn.o
 CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index db20c1589a98..6dab9c1be508 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -469,19 +469,11 @@ config SCHED_SMT
 config SCHED_MC
 	def_bool n
 
-config SCHED_BOOK
-	def_bool n
-
-config SCHED_DRAWER
-	def_bool n
-
 config SCHED_TOPOLOGY
 	def_bool y
 	prompt "Topology scheduler support"
 	select SCHED_SMT
 	select SCHED_MC
-	select SCHED_BOOK
-	select SCHED_DRAWER
 	help
 	  Topology scheduler support improves the CPU scheduler's decision
 	  making when dealing with machines that have multi-threading,
@@ -716,7 +708,6 @@ config EADM_SCH
 config VFIO_CCW
 	def_tristate n
 	prompt "Support for VFIO-CCW subchannels"
-	depends on S390_CCW_IOMMU
 	depends on VFIO
 	select VFIO_MDEV
 	help
@@ -728,7 +719,7 @@ config VFIO_CCW
 config VFIO_AP
 	def_tristate n
 	prompt "VFIO support for AP devices"
-	depends on S390_AP_IOMMU && KVM
+	depends on KVM
 	depends on VFIO
 	depends on ZCRYPT
 	select VFIO_MDEV
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 4ccf66d29fc2..be3bf03bf361 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -591,8 +591,6 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
-CONFIG_S390_CCW_IOMMU=y
-CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -703,6 +701,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
+CONFIG_INIT_STACK_NONE=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
 CONFIG_CRYPTO_PCRYPT=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 693297a2e897..769c7eed8b6a 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -580,8 +580,6 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
-CONFIG_S390_CCW_IOMMU=y
-CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -686,6 +684,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
+CONFIG_INIT_STACK_NONE=y
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 33a232bb68af..6f68b39817ef 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -67,6 +67,7 @@ CONFIG_ZFCP=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
+CONFIG_INIT_STACK_NONE=y
 # CONFIG_ZLIB_DFLTCC is not set
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_PRINTK_TIME=y
diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c
index 7752bd314558..5fae187f947a 100644
--- a/arch/s390/crypto/chacha-glue.c
+++ b/arch/s390/crypto/chacha-glue.c
@@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
 	 * it cannot handle a block of data or less, but otherwise
 	 * it can handle data of arbitrary size
 	 */
-	if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20)
+	if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX)
 		chacha_crypt_generic(state, dst, src, bytes, nrounds);
 	else
 		chacha20_crypt_s390(state, dst, src, bytes,
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index a386070f1d56..3cb9d813f022 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -112,7 +112,7 @@ struct compat_statfs64 {
 	u32		f_namelen;
 	u32		f_frsize;
 	u32		f_flags;
-	u32		f_spare[4];
+	u32		f_spare[5];
 };
 
 /*
diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h
index 72604f7792c3..f85b50723dd3 100644
--- a/arch/s390/include/uapi/asm/statfs.h
+++ b/arch/s390/include/uapi/asm/statfs.h
@@ -30,7 +30,7 @@ struct statfs {
 	unsigned int	f_namelen;
 	unsigned int	f_frsize;
 	unsigned int	f_flags;
-	unsigned int	f_spare[4];
+	unsigned int	f_spare[5];
 };
 
 struct statfs64 {
@@ -45,7 +45,7 @@ struct statfs64 {
 	unsigned int	f_namelen;
 	unsigned int	f_frsize;
 	unsigned int	f_flags;
-	unsigned int	f_spare[4];
+	unsigned int	f_spare[5];
 };
 
 #endif
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 8983837b3565..6b2a051e1f8a 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -10,6 +10,7 @@ CFLAGS_REMOVE_ftrace.o		= $(CC_FLAGS_FTRACE)
 
 # Do not trace early setup code
 CFLAGS_REMOVE_early.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rethook.o		= $(CC_FLAGS_FTRACE)
 
 endif
 
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 43de939b7af1..f44f70de9661 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1935,14 +1935,13 @@ static struct shutdown_action __refdata dump_action = {
 
 static void dump_reipl_run(struct shutdown_trigger *trigger)
 {
-	unsigned long ipib = (unsigned long) reipl_block_actual;
 	struct lowcore *abs_lc;
 	unsigned int csum;
 
 	csum = (__force unsigned int)
 	       csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
 	abs_lc = get_abs_lowcore();
-	abs_lc->ipib = ipib;
+	abs_lc->ipib = __pa(reipl_block_actual);
 	abs_lc->ipib_checksum = csum;
 	put_abs_lowcore(abs_lc);
 	dump_run(trigger);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 9fd19530c9a5..68adf1de8888 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -95,7 +95,7 @@ out:
 static void cpu_thread_map(cpumask_t *dst, unsigned int cpu)
 {
 	static cpumask_t mask;
-	int i;
+	unsigned int max_cpu;
 
 	cpumask_clear(&mask);
 	if (!cpumask_test_cpu(cpu, &cpu_setup_mask))
@@ -104,9 +104,10 @@ static void cpu_thread_map(cpumask_t *dst, unsigned int cpu)
 	if (topology_mode != TOPOLOGY_MODE_HW)
 		goto out;
 	cpu -= cpu % (smp_cpu_mtid + 1);
-	for (i = 0; i <= smp_cpu_mtid; i++) {
-		if (cpumask_test_cpu(cpu + i, &cpu_setup_mask))
-			cpumask_set_cpu(cpu + i, &mask);
+	max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1);
+	for (; cpu <= max_cpu; cpu++) {
+		if (cpumask_test_cpu(cpu, &cpu_setup_mask))
+			cpumask_set_cpu(cpu, &mask);
 	}
 out:
 	cpumask_copy(dst, &mask);
@@ -123,25 +124,26 @@ static void add_cpus_to_mask(struct topology_core *tl_core,
 	unsigned int core;
 
 	for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) {
-		unsigned int rcore;
-		int lcpu, i;
+		unsigned int max_cpu, rcore;
+		int cpu;
 
 		rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin;
-		lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift);
-		if (lcpu < 0)
+		cpu = smp_find_processor_id(rcore << smp_cpu_mt_shift);
+		if (cpu < 0)
 			continue;
-		for (i = 0; i <= smp_cpu_mtid; i++) {
-			topo = &cpu_topology[lcpu + i];
+		max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1);
+		for (; cpu <= max_cpu; cpu++) {
+			topo = &cpu_topology[cpu];
 			topo->drawer_id = drawer->id;
 			topo->book_id = book->id;
 			topo->socket_id = socket->id;
 			topo->core_id = rcore;
-			topo->thread_id = lcpu + i;
+			topo->thread_id = cpu;
 			topo->dedicated = tl_core->d;
-			cpumask_set_cpu(lcpu + i, &drawer->mask);
-			cpumask_set_cpu(lcpu + i, &book->mask);
-			cpumask_set_cpu(lcpu + i, &socket->mask);
-			smp_cpu_set_polarization(lcpu + i, tl_core->pp);
+			cpumask_set_cpu(cpu, &drawer->mask);
+			cpumask_set_cpu(cpu, &book->mask);
+			cpumask_set_cpu(cpu, &socket->mask);
+			smp_cpu_set_polarization(cpu, tl_core->pp);
 		}
 	}
 }
diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index dee6f66353b3..a461a950f051 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -16,7 +16,8 @@ mconsole-objs := mconsole_kern.o mconsole_user.o
 hostaudio-objs := hostaudio_kern.o
 ubd-objs := ubd_kern.o ubd_user.o
 port-objs := port_kern.o port_user.o
-harddog-objs := harddog_kern.o harddog_user.o
+harddog-objs := harddog_kern.o
+harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o
 rtc-objs := rtc_kern.o rtc_user.o
 
 LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a)
@@ -60,6 +61,7 @@ obj-$(CONFIG_PTY_CHAN) += pty.o
 obj-$(CONFIG_TTY_CHAN) += tty.o 
 obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o
 obj-$(CONFIG_UML_WATCHDOG) += harddog.o
+obj-y += $(harddog-builtin-y) $(harddog-builtin-m)
 obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o
 obj-$(CONFIG_UML_RANDOM) += random.o
 obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o
diff --git a/arch/um/drivers/harddog.h b/arch/um/drivers/harddog.h
new file mode 100644
index 000000000000..6d9ea60e7133
--- /dev/null
+++ b/arch/um/drivers/harddog.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef UM_WATCHDOG_H
+#define UM_WATCHDOG_H
+
+int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock);
+void stop_watchdog(int in_fd, int out_fd);
+int ping_watchdog(int fd);
+
+#endif /* UM_WATCHDOG_H */
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index e6d4f43deba8..60d1c6cab8a9 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -47,6 +47,7 @@
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include "mconsole.h"
+#include "harddog.h"
 
 MODULE_LICENSE("GPL");
 
@@ -60,8 +61,6 @@ static int harddog_out_fd = -1;
  *	Allow only one person to hold it open
  */
 
-extern int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock);
-
 static int harddog_open(struct inode *inode, struct file *file)
 {
 	int err = -EBUSY;
@@ -92,8 +91,6 @@ err:
 	return err;
 }
 
-extern void stop_watchdog(int in_fd, int out_fd);
-
 static int harddog_release(struct inode *inode, struct file *file)
 {
 	/*
@@ -112,8 +109,6 @@ static int harddog_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-extern int ping_watchdog(int fd);
-
 static ssize_t harddog_write(struct file *file, const char __user *data, size_t len,
 			     loff_t *ppos)
 {
diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c
index 070468d22e39..9ed89304975e 100644
--- a/arch/um/drivers/harddog_user.c
+++ b/arch/um/drivers/harddog_user.c
@@ -7,6 +7,7 @@
 #include <unistd.h>
 #include <errno.h>
 #include <os.h>
+#include "harddog.h"
 
 struct dog_data {
 	int stdin_fd;
diff --git a/arch/um/drivers/harddog_user_exp.c b/arch/um/drivers/harddog_user_exp.c
new file mode 100644
index 000000000000..c74d4b815d14
--- /dev/null
+++ b/arch/um/drivers/harddog_user_exp.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include "harddog.h"
+
+#if IS_MODULE(CONFIG_UML_WATCHDOG)
+EXPORT_SYMBOL(start_watchdog);
+EXPORT_SYMBOL(stop_watchdog);
+EXPORT_SYMBOL(ping_watchdog);
+#endif
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 498dc600bd5c..0d02c4aafa6f 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -13,7 +13,9 @@
 
 
 #include <linux/bitops.h>
+#include <linux/bug.h>
 #include <linux/types.h>
+
 #include <uapi/asm/vmx.h>
 #include <asm/vmxfeatures.h>
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index dd61752f4c96..4070a01c11b7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_head64.o = -pg
 CFLAGS_REMOVE_sev.o = -pg
+CFLAGS_REMOVE_rethook.o = -pg
 endif
 
 KASAN_SANITIZE_head$(BITS).o				:= n
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 123bf8b97a4b..0c9660a07b23 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -253,7 +253,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
 				       int nent)
 {
 	struct kvm_cpuid_entry2 *best;
-	u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent);
 
 	best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
 	if (best) {
@@ -292,21 +291,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
 					   vcpu->arch.ia32_misc_enable_msr &
 					   MSR_IA32_MISC_ENABLE_MWAIT);
 	}
-
-	/*
-	 * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate
-	 * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's
-	 * requested XCR0 value.  The enclave's XFRM must be a subset of XCRO
-	 * at the time of EENTER, thus adjust the allowed XFRM by the guest's
-	 * supported XCR0.  Similar to XCR0 handling, FP and SSE are forced to
-	 * '1' even on CPUs that don't support XSAVE.
-	 */
-	best = cpuid_entry2_find(entries, nent, 0x12, 0x1);
-	if (best) {
-		best->ecx &= guest_supported_xcr0 & 0xffffffff;
-		best->edx &= guest_supported_xcr0 >> 32;
-		best->ecx |= XFEATURE_MASK_FPSSE;
-	}
 }
 
 void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index 0574030b071f..2261b684a7d4 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -170,12 +170,19 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu,
 		return 1;
 	}
 
-	/* Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. */
+	/*
+	 * Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM.  Note
+	 * that the allowed XFRM (XFeature Request Mask) isn't strictly bound
+	 * by the supported XCR0.  FP+SSE *must* be set in XFRM, even if XSAVE
+	 * is unsupported, i.e. even if XCR0 itself is completely unsupported.
+	 */
 	if ((u32)miscselect & ~sgx_12_0->ebx ||
 	    (u32)attributes & ~sgx_12_1->eax ||
 	    (u32)(attributes >> 32) & ~sgx_12_1->ebx ||
 	    (u32)xfrm & ~sgx_12_1->ecx ||
-	    (u32)(xfrm >> 32) & ~sgx_12_1->edx) {
+	    (u32)(xfrm >> 32) & ~sgx_12_1->edx ||
+	    xfrm & ~(vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE) ||
+	    (xfrm & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ceb7c5e9cf9e..c0778ca39650 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1446,7 +1446,7 @@ static const u32 msrs_to_save_base[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
-	MSR_IA32_SPEC_CTRL,
+	MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL,
 	MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
 	MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
 	MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
@@ -7155,6 +7155,10 @@ static void kvm_probe_msr_to_save(u32 msr_index)
 		if (!kvm_cpu_cap_has(X86_FEATURE_XFD))
 			return;
 		break;
+	case MSR_IA32_TSX_CTRL:
+		if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR))
+			return;
+		break;
 	default:
 		break;
 	}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 3cdac0f0055d..8192452d1d2d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -9,6 +9,7 @@
 #include <linux/sched/task.h>
 
 #include <asm/set_memory.h>
+#include <asm/cpu_device_id.h>
 #include <asm/e820/api.h>
 #include <asm/init.h>
 #include <asm/page.h>
@@ -261,6 +262,24 @@ static void __init probe_page_size_mask(void)
 	}
 }
 
+#define INTEL_MATCH(_model) { .vendor  = X86_VENDOR_INTEL,	\
+			      .family  = 6,			\
+			      .model = _model,			\
+			    }
+/*
+ * INVLPG may not properly flush Global entries
+ * on these CPUs when PCIDs are enabled.
+ */
+static const struct x86_cpu_id invlpg_miss_ids[] = {
+	INTEL_MATCH(INTEL_FAM6_ALDERLAKE   ),
+	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
+	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ),
+	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE  ),
+	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
+	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+	{}
+};
+
 static void setup_pcid(void)
 {
 	if (!IS_ENABLED(CONFIG_X86_64))
@@ -269,6 +288,12 @@ static void setup_pcid(void)
 	if (!boot_cpu_has(X86_FEATURE_PCID))
 		return;
 
+	if (x86_match_cpu(invlpg_miss_ids)) {
+		pr_info("Incomplete global flushes, disabling PCID");
+		setup_clear_cpu_cap(X86_FEATURE_PCID);
+		return;
+	}
+
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		/*
 		 * This can't be cr4_set_bits_and_update_boot() -- the
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 876d5df157ed..5c01d7e70d90 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -343,7 +343,19 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	struct rt_sigframe *frame;
 	int err = 0, sig = ksig->sig;
 	unsigned long sp, ra, tp, ps;
+	unsigned long handler = (unsigned long)ksig->ka.sa.sa_handler;
+	unsigned long handler_fdpic_GOT = 0;
 	unsigned int base;
+	bool fdpic = IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC) &&
+		(current->personality & FDPIC_FUNCPTRS);
+
+	if (fdpic) {
+		unsigned long __user *fdpic_func_desc =
+			(unsigned long __user *)handler;
+		if (__get_user(handler, &fdpic_func_desc[0]) ||
+		    __get_user(handler_fdpic_GOT, &fdpic_func_desc[1]))
+			return -EFAULT;
+	}
 
 	sp = regs->areg[1];
 
@@ -373,20 +385,26 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		ra = (unsigned long)ksig->ka.sa.sa_restorer;
+		if (fdpic) {
+			unsigned long __user *fdpic_func_desc =
+				(unsigned long __user *)ksig->ka.sa.sa_restorer;
+
+			err |= __get_user(ra, fdpic_func_desc);
+		} else {
+			ra = (unsigned long)ksig->ka.sa.sa_restorer;
+		}
 	} else {
 
 		/* Create sys_rt_sigreturn syscall in stack frame */
 
 		err |= gen_return_code(frame->retcode);
-
-		if (err) {
-			return -EFAULT;
-		}
 		ra = (unsigned long) frame->retcode;
 	}
 
-	/* 
+	if (err)
+		return -EFAULT;
+
+	/*
 	 * Create signal handler execution context.
 	 * Return context not modified until this point.
 	 */
@@ -394,8 +412,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	/* Set up registers for signal handler; preserve the threadptr */
 	tp = regs->threadptr;
 	ps = regs->ps;
-	start_thread(regs, (unsigned long) ksig->ka.sa.sa_handler,
-		     (unsigned long) frame);
+	start_thread(regs, handler, (unsigned long)frame);
 
 	/* Set up a stack frame for a call4 if userspace uses windowed ABI */
 	if (ps & PS_WOE_MASK) {
@@ -413,6 +430,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	regs->areg[base + 4] = (unsigned long) &frame->uc;
 	regs->threadptr = tp;
 	regs->ps = ps;
+	if (fdpic)
+		regs->areg[base + 11] = handler_fdpic_GOT;
 
 	pr_debug("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08lx\n",
 		 current->comm, current->pid, sig, frame, regs->pc);
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 2a31b1ab0c9f..17a7ef86fd0d 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -56,6 +56,8 @@ EXPORT_SYMBOL(empty_zero_page);
  */
 extern long long __ashrdi3(long long, int);
 extern long long __ashldi3(long long, int);
+extern long long __bswapdi2(long long);
+extern int __bswapsi2(int);
 extern long long __lshrdi3(long long, int);
 extern int __divsi3(int, int);
 extern int __modsi3(int, int);
@@ -66,6 +68,8 @@ extern unsigned long long __umulsidi3(unsigned int, unsigned int);
 
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__bswapdi2);
+EXPORT_SYMBOL(__bswapsi2);
 EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(__divsi3);
 EXPORT_SYMBOL(__modsi3);
diff --git a/arch/xtensa/lib/Makefile b/arch/xtensa/lib/Makefile
index 7ecef0519a27..c9c2614188f7 100644
--- a/arch/xtensa/lib/Makefile
+++ b/arch/xtensa/lib/Makefile
@@ -4,7 +4,7 @@
 #
 
 lib-y	+= memcopy.o memset.o checksum.o \
-	   ashldi3.o ashrdi3.o lshrdi3.o \
+	   ashldi3.o ashrdi3.o bswapdi2.o bswapsi2.o lshrdi3.o \
 	   divsi3.o udivsi3.o modsi3.o umodsi3.o mulsi3.o umulsidi3.o \
 	   usercopy.o strncpy_user.o strnlen_user.o
 lib-$(CONFIG_PCI) += pci-auto.o
diff --git a/arch/xtensa/lib/bswapdi2.S b/arch/xtensa/lib/bswapdi2.S
new file mode 100644
index 000000000000..d8e52e05eba6
--- /dev/null
+++ b/arch/xtensa/lib/bswapdi2.S
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */
+#include <linux/linkage.h>
+#include <asm/asmmacro.h>
+#include <asm/core.h>
+
+ENTRY(__bswapdi2)
+
+	abi_entry_default
+	ssai	8
+	srli	a4, a2, 16
+	src	a4, a4, a2
+	src	a4, a4, a4
+	src	a4, a2, a4
+	srli	a2, a3, 16
+	src	a2, a2, a3
+	src	a2, a2, a2
+	src	a2, a3, a2
+	mov	a3, a4
+	abi_ret_default
+
+ENDPROC(__bswapdi2)
diff --git a/arch/xtensa/lib/bswapsi2.S b/arch/xtensa/lib/bswapsi2.S
new file mode 100644
index 000000000000..9c1de1344f79
--- /dev/null
+++ b/arch/xtensa/lib/bswapsi2.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */
+#include <linux/linkage.h>
+#include <asm/asmmacro.h>
+#include <asm/core.h>
+
+ENTRY(__bswapsi2)
+
+	abi_entry_default
+	ssai	8
+	srli	a3, a2, 16
+	src	a3, a3, a2
+	src	a3, a3, a3
+	src	a2, a2, a3
+	abi_ret_default
+
+ENDPROC(__bswapsi2)