Merge branch 'kvm-v6.2-rc4-fixes' into HEAD

ARM:

* Fix the PMCR_EL0 reset value after the PMU rework

* Correctly handle S2 fault triggered by a S1 page table walk
  by not always classifying it as a write, as this breaks on
  R/O memslots

* Document why we cannot exit with KVM_EXIT_MMIO when taking
  a write fault from a S1 PTW on a R/O memslot

* Put the Apple M2 on the naughty list for not being able to
  correctly implement the vgic SEIS feature, just like the M1
  before it

* Reviewer updates: Alex is stepping down, replaced by Zenghui

x86:

* Fix various rare locking issues in Xen emulation and teach lockdep
  to detect them

* Documentation improvements

* Do not return host topology information from KVM_GET_SUPPORTED_CPUID

16 files changed, 140 insertions, 134 deletions

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index cfd4c95b9f04..669d9e4f2901 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -386,8 +386,8 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
 {
 	unsigned long *reg, val, vaddr;
 	char buffer[MAX_INSN_SIZE];
+	enum insn_mmio_type mmio;
 	struct insn insn = {};
-	enum mmio_type mmio;
 	int size, extend_size;
 	u8 extend_val = 0;
 
@@ -402,10 +402,10 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
 		return -EINVAL;
 
 	mmio = insn_decode_mmio(&insn, &size);
-	if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+	if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED))
 		return -EINVAL;
 
-	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
 		reg = insn_get_modrm_reg_ptr(&insn, regs);
 		if (!reg)
 			return -EINVAL;
@@ -426,23 +426,23 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
 
 	/* Handle writes first */
 	switch (mmio) {
-	case MMIO_WRITE:
+	case INSN_MMIO_WRITE:
 		memcpy(&val, reg, size);
 		if (!mmio_write(size, ve->gpa, val))
 			return -EIO;
 		return insn.length;
-	case MMIO_WRITE_IMM:
+	case INSN_MMIO_WRITE_IMM:
 		val = insn.immediate.value;
 		if (!mmio_write(size, ve->gpa, val))
 			return -EIO;
 		return insn.length;
-	case MMIO_READ:
-	case MMIO_READ_ZERO_EXTEND:
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ:
+	case INSN_MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		/* Reads are handled below */
 		break;
-	case MMIO_MOVS:
-	case MMIO_DECODE_FAILED:
+	case INSN_MMIO_MOVS:
+	case INSN_MMIO_DECODE_FAILED:
 		/*
 		 * MMIO was accessed with an instruction that could not be
 		 * decoded or handled properly. It was likely not using io.h
@@ -459,15 +459,15 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
 		return -EIO;
 
 	switch (mmio) {
-	case MMIO_READ:
+	case INSN_MMIO_READ:
 		/* Zero-extend for 32-bit operation */
 		extend_size = size == 4 ? sizeof(*reg) : 0;
 		break;
-	case MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_ZERO_EXTEND:
 		/* Zero extend based on operand size */
 		extend_size = insn.opnd_bytes;
 		break;
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		/* Sign extend based on operand size */
 		extend_size = insn.opnd_bytes;
 		if (size == 1 && val & BIT(7))
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index d6f3703e4119..4386b10682ce 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -1387,7 +1387,7 @@ static int __init amd_core_pmu_init(void)
 		 * numbered counter following it.
 		 */
 		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
-			even_ctr_mask |= 1 << i;
+			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index a829492bca4c..52e6e7ed4f78 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -800,13 +800,18 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&model_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&model_skl),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index f07faa61c7f3..54368a43abf6 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -32,16 +32,16 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs,
 bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
 			   unsigned char buf[MAX_INSN_SIZE], int buf_size);
 
-enum mmio_type {
-	MMIO_DECODE_FAILED,
-	MMIO_WRITE,
-	MMIO_WRITE_IMM,
-	MMIO_READ,
-	MMIO_READ_ZERO_EXTEND,
-	MMIO_READ_SIGN_EXTEND,
-	MMIO_MOVS,
+enum insn_mmio_type {
+	INSN_MMIO_DECODE_FAILED,
+	INSN_MMIO_WRITE,
+	INSN_MMIO_WRITE_IMM,
+	INSN_MMIO_READ,
+	INSN_MMIO_READ_ZERO_EXTEND,
+	INSN_MMIO_READ_SIGN_EXTEND,
+	INSN_MMIO_MOVS,
 };
 
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
 
 #endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6a9d6f99d0d3..8d0a0a7c34fc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1112,6 +1112,7 @@ struct msr_bitmap_range {
 
 /* Xen emulation context */
 struct kvm_xen {
+	struct mutex xen_lock;
 	u32 xen_version;
 	bool long_mode;
 	bool runstate_update_flag;
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 7d2c75ec9a8c..ffea98f9064b 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -119,7 +119,7 @@ static bool is_coretext(const struct core_text *ct, void *addr)
 	return within_module_coretext(addr);
 }
 
-static __init_or_module bool skip_addr(void *dest)
+static bool skip_addr(void *dest)
 {
 	if (dest == error_entry)
 		return true;
@@ -181,7 +181,7 @@ static const u8 nops[] = {
 	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
 };
 
-static __init_or_module void *patch_dest(void *dest, bool direct)
+static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
 	u8 *pad = dest - tsize;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d970ddb0cc65..bca0bd8f4846 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1981,6 +1981,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
 		task_update_spec_tif(task);
+		if (task == current)
+			indirect_branch_prediction_barrier();
 		break;
 	default:
 		return -ERANGE;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 9730c88530fc..305514431f26 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -401,10 +401,8 @@ int crash_load_segments(struct kimage *image)
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
-	if (ret) {
-		vfree((void *)image->elf_headers);
+	if (ret)
 		return ret;
-	}
 	image->elf_load_addr = kbuf.mem;
 	pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
 		 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 66299682b6b7..b36f3c367cb2 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -37,6 +37,7 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
@@ -281,12 +282,15 @@ static int can_probe(unsigned long paddr)
 		if (ret < 0)
 			return 0;
 
+#ifdef CONFIG_KGDB
 		/*
-		 * Another debugging subsystem might insert this breakpoint.
-		 * In that case, we can't recover it.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
 			return 0;
+#endif
 		addr += insn.length;
 	}
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index e6b8c5362b94..e57e07b0edb6 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -15,6 +15,7 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/objtool.h>
 #include <linux/pgtable.h>
@@ -279,19 +280,6 @@ static int insn_is_indirect_jump(struct insn *insn)
 	return ret;
 }
 
-static bool is_padding_int3(unsigned long addr, unsigned long eaddr)
-{
-	unsigned char ops;
-
-	for (; addr < eaddr; addr++) {
-		if (get_kernel_nofault(ops, (void *)addr) < 0 ||
-		    ops != INT3_INSN_OPCODE)
-			return false;
-	}
-
-	return true;
-}
-
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
@@ -334,15 +322,15 @@ static int can_optimize(unsigned long paddr)
 		ret = insn_decode_kernel(&insn, (void *)recovered_insn);
 		if (ret < 0)
 			return 0;
-
+#ifdef CONFIG_KGDB
 		/*
-		 * In the case of detecting unknown breakpoint, this could be
-		 * a padding INT3 between functions. Let's check that all the
-		 * rest of the bytes are also INT3.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
-			return is_padding_int3(addr, paddr - offset + size) ? 1 : 0;
-
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
+			return 0;
+#endif
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a428c62330d3..679026a640ef 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1536,32 +1536,32 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
 static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
 	struct insn *insn = &ctxt->insn;
+	enum insn_mmio_type mmio;
 	unsigned int bytes = 0;
-	enum mmio_type mmio;
 	enum es_result ret;
 	u8 sign_byte;
 	long *reg_data;
 
 	mmio = insn_decode_mmio(insn, &bytes);
-	if (mmio == MMIO_DECODE_FAILED)
+	if (mmio == INSN_MMIO_DECODE_FAILED)
 		return ES_DECODE_FAILED;
 
-	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
 		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
 		if (!reg_data)
 			return ES_DECODE_FAILED;
 	}
 
 	switch (mmio) {
-	case MMIO_WRITE:
+	case INSN_MMIO_WRITE:
 		memcpy(ghcb->shared_buffer, reg_data, bytes);
 		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
 		break;
-	case MMIO_WRITE_IMM:
+	case INSN_MMIO_WRITE_IMM:
 		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
 		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
 		break;
-	case MMIO_READ:
+	case INSN_MMIO_READ:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
@@ -1572,7 +1572,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_ZERO_EXTEND:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
@@ -1581,7 +1581,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 		memset(reg_data, 0, insn->opnd_bytes);
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
@@ -1600,7 +1600,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 		memset(reg_data, sign_byte, insn->opnd_bytes);
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_MOVS:
+	case INSN_MMIO_MOVS:
 		ret = vc_handle_mmio_movs(ctxt, bytes);
 		break;
 	default:
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 4ca16b18a086..2a9f1e200dbc 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -775,16 +775,22 @@ struct kvm_cpuid_array {
 	int nent;
 };
 
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
+{
+	if (array->nent >= array->maxnent)
+		return NULL;
+
+	return &array->entries[array->nent++];
+}
+
 static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
 					      u32 function, u32 index)
 {
-	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
 
-	if (array->nent >= array->maxnent)
+	if (!entry)
 		return NULL;
 
-	entry = &array->entries[array->nent++];
-
 	memset(entry, 0, sizeof(*entry));
 	entry->function = function;
 	entry->index = index;
@@ -961,22 +967,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->edx = edx.full;
 		break;
 	}
-	/*
-	 * Per Intel's SDM, the 0x1f is a superset of 0xb,
-	 * thus they can be handled by common code.
-	 */
 	case 0x1f:
 	case 0xb:
 		/*
-		 * Populate entries until the level type (ECX[15:8]) of the
-		 * previous entry is zero.  Note, CPUID EAX.{0x1f,0xb}.0 is
-		 * the starting entry, filled by the primary do_host_cpuid().
+		 * No topology; a valid topology is indicated by the presence
+		 * of subleaf 1.
 		 */
-		for (i = 1; entry->ecx & 0xff00; ++i) {
-			entry = do_host_cpuid(array, function, i);
-			if (!entry)
-				goto out;
-		}
+		entry->eax = entry->ebx = entry->ecx = 0;
 		break;
 	case 0xd: {
 		u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
@@ -1207,6 +1204,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->ebx = entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001e:
+		/* Do not return host topology information.  */
+		entry->eax = entry->ebx = entry->ecx = 0;
+		entry->edx = 0; /* reserved */
 		break;
 	case 0x8000001F:
 		if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 3bfbcb607d80..500da957e590 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm)
 		c->intercepts[i] = h->intercepts[i];
 
 	if (g->int_ctl & V_INTR_MASKING_MASK) {
-		/* We only want the cr8 intercept bits of L1 */
-		vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
-		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-
 		/*
-		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
-		 * affect any interrupt we may want to inject; therefore,
-		 * interrupt window vmexits are irrelevant to L0.
+		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
+		 * does not affect any interrupt we may want to inject;
+		 * therefore, writes to CR8 are irrelevant to L0, as are
+		 * interrupt window vmexits.
 		 */
+		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
 		vmcb_clr_intercept(c, INTERCEPT_VINTR);
 	}
 
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 0bd5d171df57..2681e2007e39 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -272,7 +272,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
 	 * Attempt to obtain the GPC lock on *both* (if there are two)
 	 * gfn_to_pfn caches that cover the region.
 	 */
-	read_lock_irqsave(&gpc1->lock, flags);
+	if (atomic) {
+		local_irq_save(flags);
+		if (!read_trylock(&gpc1->lock)) {
+			local_irq_restore(flags);
+			return;
+		}
+	} else {
+		read_lock_irqsave(&gpc1->lock, flags);
+	}
 	while (!kvm_gpc_check(gpc1, user_len1)) {
 		read_unlock_irqrestore(&gpc1->lock, flags);
 
@@ -305,9 +313,18 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
 		 * The guest's runstate_info is split across two pages and we
 		 * need to hold and validate both GPCs simultaneously. We can
 		 * declare a lock ordering GPC1 > GPC2 because nothing else
-		 * takes them more than one at a time.
+		 * takes them more than one at a time. Set a subclass on the
+		 * gpc1 lock to make lockdep shut up about it.
 		 */
-		read_lock(&gpc2->lock);
+		lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
+		if (atomic) {
+			if (!read_trylock(&gpc2->lock)) {
+				read_unlock_irqrestore(&gpc1->lock, flags);
+				return;
+			}
+		} else {
+			read_lock(&gpc2->lock);
+		}
 
 		if (!kvm_gpc_check(gpc2, user_len2)) {
 			read_unlock(&gpc2->lock);
@@ -591,26 +608,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
 			r = -EINVAL;
 		} else {
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->arch.xen.xen_lock);
 			kvm->arch.xen.long_mode = !!data->u.long_mode;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.xen.xen_lock);
 			r = 0;
 		}
 		break;
 
 	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		break;
 
 	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
 		if (data->u.vector && data->u.vector < 0x10)
 			r = -EINVAL;
 		else {
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->arch.xen.xen_lock);
 			kvm->arch.xen.upcall_vector = data->u.vector;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.xen.xen_lock);
 			r = 0;
 		}
 		break;
@@ -620,9 +637,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 
 	case KVM_XEN_ATTR_TYPE_XEN_VERSION:
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		kvm->arch.xen.xen_version = data->u.xen_version;
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		r = 0;
 		break;
 
@@ -631,9 +648,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 			r = -EOPNOTSUPP;
 			break;
 		}
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		r = 0;
 		break;
 
@@ -648,7 +665,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 {
 	int r = -ENOENT;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	switch (data->type) {
 	case KVM_XEN_ATTR_TYPE_LONG_MODE:
@@ -687,7 +704,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 	}
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return r;
 }
 
@@ -695,7 +712,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 {
 	int idx, r = -ENOENT;
 
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	switch (data->type) {
@@ -923,7 +940,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 	}
 
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
 	return r;
 }
 
@@ -931,7 +948,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 {
 	int r = -ENOENT;
 
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
 
 	switch (data->type) {
 	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
@@ -1014,7 +1031,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 		break;
 	}
 
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
 	return r;
 }
 
@@ -1107,7 +1124,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	     xhc->blob_size_32 || xhc->blob_size_64))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
 		static_branch_inc(&kvm_xen_enabled.key);
@@ -1116,7 +1133,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 
 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return 0;
 }
 
@@ -1659,15 +1676,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 		mm_borrowed = true;
 	}
 
-	/*
-	 * For the irqfd workqueue, using the main kvm->lock mutex is
-	 * fine since this function is invoked from kvm_set_irq() with
-	 * no other lock held, no srcu. In future if it will be called
-	 * directly from a vCPU thread (e.g. on hypercall for an IPI)
-	 * then it may need to switch to using a leaf-node mutex for
-	 * serializing the shared_info mapping.
-	 */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	/*
 	 * It is theoretically possible for the page to be unmapped
@@ -1696,7 +1705,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 		srcu_read_unlock(&kvm->srcu, idx);
 	} while(!rc);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 
 	if (mm_borrowed)
 		kthread_unuse_mm(kvm->mm);
@@ -1812,7 +1821,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
 	int ret;
 
 	/* Protect writes to evtchnfd as well as the idr lookup.  */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
 
 	ret = -ENOENT;
@@ -1843,7 +1852,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
 	}
 	ret = 0;
 out_unlock:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return ret;
 }
 
@@ -1906,10 +1915,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
 		evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
 	}
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
 			GFP_KERNEL);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	if (ret >= 0)
 		return 0;
 
@@ -1927,9 +1936,9 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port)
 {
 	struct evtchnfd *evtchnfd;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 
 	if (!evtchnfd)
 		return -ENOENT;
@@ -1947,7 +1956,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 	int i;
 	int n = 0;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	/*
 	 * Because synchronize_srcu() cannot be called inside the
@@ -1959,7 +1968,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 
 	all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
 	if (!all_evtchnfds) {
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		return -ENOMEM;
 	}
 
@@ -1968,7 +1977,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 		all_evtchnfds[n++] = evtchnfd;
 		idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 
 	synchronize_srcu(&kvm->srcu);
 
@@ -2070,6 +2079,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
 
 void kvm_xen_init_vm(struct kvm *kvm)
 {
+	mutex_init(&kvm->arch.xen.xen_lock);
 	idr_init(&kvm->arch.xen.evtchn_ports);
 	kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
 }
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 21104c41cba0..558a605929db 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -1595,16 +1595,16 @@ bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
  * Returns:
  *
  * Type of the instruction. Size of the memory operand is stored in
- * @bytes. If decode failed, MMIO_DECODE_FAILED returned.
+ * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned.
  */
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 {
-	enum mmio_type type = MMIO_DECODE_FAILED;
+	enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED;
 
 	*bytes = 0;
 
 	if (insn_get_opcode(insn))
-		return MMIO_DECODE_FAILED;
+		return INSN_MMIO_DECODE_FAILED;
 
 	switch (insn->opcode.bytes[0]) {
 	case 0x88: /* MOV m8,r8 */
@@ -1613,7 +1613,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 	case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_WRITE;
+		type = INSN_MMIO_WRITE;
 		break;
 
 	case 0xc6: /* MOV m8, imm8 */
@@ -1622,7 +1622,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 	case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_WRITE_IMM;
+		type = INSN_MMIO_WRITE_IMM;
 		break;
 
 	case 0x8a: /* MOV r8, m8 */
@@ -1631,7 +1631,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 	case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_READ;
+		type = INSN_MMIO_READ;
 		break;
 
 	case 0xa4: /* MOVS m8, m8 */
@@ -1640,7 +1640,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 	case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_MOVS;
+		type = INSN_MMIO_MOVS;
 		break;
 
 	case 0x0f: /* Two-byte instruction */
@@ -1651,7 +1651,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 		case 0xb7: /* MOVZX r32/r64, m16 */
 			if (!*bytes)
 				*bytes = 2;
-			type = MMIO_READ_ZERO_EXTEND;
+			type = INSN_MMIO_READ_ZERO_EXTEND;
 			break;
 
 		case 0xbe: /* MOVSX r16/r32/r64, m8 */
@@ -1660,7 +1660,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 		case 0xbf: /* MOVSX r32/r64, m16 */
 			if (!*bytes)
 				*bytes = 2;
-			type = MMIO_READ_SIGN_EXTEND;
+			type = INSN_MMIO_READ_SIGN_EXTEND;
 			break;
 		}
 		break;
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index a1f9416bf67a..6ff2f56cb0f7 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -10,6 +10,6 @@
  */
 SYM_FUNC_START(__iowrite32_copy)
 	movl %edx,%ecx
-	rep movsd
+	rep movsl
 	RET
 SYM_FUNC_END(__iowrite32_copy)