21 files changed, 174 insertions, 62 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 00163e4a237c..bd9f095d69fa 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -855,14 +855,14 @@ config HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG
 	def_bool y
 	depends on $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers)
 	# With GCOV/KASAN we need this fix: https://github.com/llvm/llvm-project/pull/104826
-	depends on CLANG_VERSION >= 190000 || (!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS)
+	depends on CLANG_VERSION >= 190103 || (!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS)
 
 config HAVE_CFI_ICALL_NORMALIZE_INTEGERS_RUSTC
 	def_bool y
 	depends on HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG
 	depends on RUSTC_VERSION >= 107900
 	# With GCOV/KASAN we need this fix: https://github.com/rust-lang/rust/pull/129373
-	depends on (RUSTC_LLVM_VERSION >= 190000 && RUSTC_VERSION >= 108200) || \
+	depends on (RUSTC_LLVM_VERSION >= 190103 && RUSTC_VERSION >= 108200) || \
 		(!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS)
 
 config CFI_PERMISSIVE
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 561986947530..c7d311d8b92a 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -19,6 +19,7 @@
 #include <linux/ratelimit.h>
 #include <linux/rseq.h>
 #include <linux/syscalls.h>
+#include <linux/pkeys.h>
 
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
@@ -66,10 +67,63 @@ struct rt_sigframe_user_layout {
 	unsigned long end_offset;
 };
 
+/*
+ * Holds any EL0-controlled state that influences unprivileged memory accesses.
+ * This includes both accesses done in userspace and uaccess done in the kernel.
+ *
+ * This state needs to be carefully managed to ensure that it doesn't cause
+ * uaccess to fail when setting up the signal frame, and the signal handler
+ * itself also expects a well-defined state when entered.
+ */
+struct user_access_state {
+	u64 por_el0;
+};
+
 #define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
 #define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
 #define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
 
+/*
+ * Save the user access state into ua_state and reset it to disable any
+ * restrictions.
+ */
+static void save_reset_user_access_state(struct user_access_state *ua_state)
+{
+	if (system_supports_poe()) {
+		u64 por_enable_all = 0;
+
+		for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
+			por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
+
+		ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
+		write_sysreg_s(por_enable_all, SYS_POR_EL0);
+		/* Ensure that any subsequent uaccess observes the updated value */
+		isb();
+	}
+}
+
+/*
+ * Set the user access state for invoking the signal handler.
+ *
+ * No uaccess should be done after that function is called.
+ */
+static void set_handler_user_access_state(void)
+{
+	if (system_supports_poe())
+		write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
+}
+
+/*
+ * Restore the user access state to the values saved in ua_state.
+ *
+ * No uaccess should be done after that function is called.
+ */
+static void restore_user_access_state(const struct user_access_state *ua_state)
+{
+	if (system_supports_poe())
+		write_sysreg_s(ua_state->por_el0, SYS_POR_EL0);
+}
+
 static void init_user_layout(struct rt_sigframe_user_layout *user)
 {
 	const size_t reserved_size =
@@ -261,18 +315,20 @@ static int restore_fpmr_context(struct user_ctxs *user)
 	return err;
 }
 
-static int preserve_poe_context(struct poe_context __user *ctx)
+static int preserve_poe_context(struct poe_context __user *ctx,
+				const struct user_access_state *ua_state)
 {
 	int err = 0;
 
 	__put_user_error(POE_MAGIC, &ctx->head.magic, err);
 	__put_user_error(sizeof(*ctx), &ctx->head.size, err);
-	__put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err);
+	__put_user_error(ua_state->por_el0, &ctx->por_el0, err);
 
 	return err;
 }
 
-static int restore_poe_context(struct user_ctxs *user)
+static int restore_poe_context(struct user_ctxs *user,
+			       struct user_access_state *ua_state)
 {
 	u64 por_el0;
 	int err = 0;
@@ -282,7 +338,7 @@ static int restore_poe_context(struct user_ctxs *user)
 
 	__get_user_error(por_el0, &(user->poe->por_el0), err);
 	if (!err)
-		write_sysreg_s(por_el0, SYS_POR_EL0);
+		ua_state->por_el0 = por_el0;
 
 	return err;
 }
@@ -850,7 +906,8 @@ invalid:
 }
 
 static int restore_sigframe(struct pt_regs *regs,
-			    struct rt_sigframe __user *sf)
+			    struct rt_sigframe __user *sf,
+			    struct user_access_state *ua_state)
 {
 	sigset_t set;
 	int i, err;
@@ -899,7 +956,7 @@ static int restore_sigframe(struct pt_regs *regs,
 		err = restore_zt_context(&user);
 
 	if (err == 0 && system_supports_poe() && user.poe)
-		err = restore_poe_context(&user);
+		err = restore_poe_context(&user, ua_state);
 
 	return err;
 }
@@ -908,6 +965,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
+	struct user_access_state ua_state;
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current->restart_block.fn = do_no_restart_syscall;
@@ -924,12 +982,14 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	if (!access_ok(frame, sizeof (*frame)))
 		goto badframe;
 
-	if (restore_sigframe(regs, frame))
+	if (restore_sigframe(regs, frame, &ua_state))
 		goto badframe;
 
 	if (restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
 
+	restore_user_access_state(&ua_state);
+
 	return regs->regs[0];
 
 badframe:
@@ -1035,7 +1095,8 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 }
 
 static int setup_sigframe(struct rt_sigframe_user_layout *user,
-			  struct pt_regs *regs, sigset_t *set)
+			  struct pt_regs *regs, sigset_t *set,
+			  const struct user_access_state *ua_state)
 {
 	int i, err = 0;
 	struct rt_sigframe __user *sf = user->sigframe;
@@ -1097,10 +1158,9 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		struct poe_context __user *poe_ctx =
 			apply_user_offset(user, user->poe_offset);
 
-		err |= preserve_poe_context(poe_ctx);
+		err |= preserve_poe_context(poe_ctx, ua_state);
 	}
 
-
 	/* ZA state if present */
 	if (system_supports_sme() && err == 0 && user->za_offset) {
 		struct za_context __user *za_ctx =
@@ -1237,9 +1297,6 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		sme_smstop();
 	}
 
-	if (system_supports_poe())
-		write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
-
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
@@ -1253,6 +1310,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 {
 	struct rt_sigframe_user_layout user;
 	struct rt_sigframe __user *frame;
+	struct user_access_state ua_state;
 	int err = 0;
 
 	fpsimd_signal_preserve_current_state();
@@ -1260,13 +1318,14 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 	if (get_sigframe(&user, ksig, regs))
 		return 1;
 
+	save_reset_user_access_state(&ua_state);
 	frame = user.sigframe;
 
 	__put_user_error(0, &frame->uc.uc_flags, err);
 	__put_user_error(NULL, &frame->uc.uc_link, err);
 
 	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
-	err |= setup_sigframe(&user, regs, set);
+	err |= setup_sigframe(&user, regs, set, &ua_state);
 	if (err == 0) {
 		setup_return(regs, &ksig->ka, &user, usig);
 		if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
@@ -1276,6 +1335,11 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 		}
 	}
 
+	if (err == 0)
+		set_handler_user_access_state();
+	else
+		restore_user_access_state(&ua_state);
+
 	return err;
 }
 
diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c
index e974a4954df8..c371def2302d 100644
--- a/arch/mips/kernel/cmpxchg.c
+++ b/arch/mips/kernel/cmpxchg.c
@@ -102,3 +102,4 @@ unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
 			return old;
 	}
 }
+EXPORT_SYMBOL(__cmpxchg_small);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f14329989e9a..76446604332c 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -612,9 +612,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 				r = 8 | 4 | 2 | 1;
 		}
 		break;
-	case KVM_CAP_PPC_RMA:
-		r = 0;
-		break;
 	case KVM_CAP_PPC_HWRNG:
 		r = kvmppc_hwrng_present();
 		break;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 62545946ecf4..f4c570538d55 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -177,7 +177,7 @@ config RISCV
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK if !XIP_KERNEL
 	select HAVE_RSEQ
-	select HAVE_RUST if RUSTC_SUPPORTS_RISCV
+	select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_STACKPROTECTOR
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index 8a2739485123..f0da9d7b39c3 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -2,6 +2,12 @@ ifdef CONFIG_RELOCATABLE
 KBUILD_CFLAGS += -fno-pie
 endif
 
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+ifdef CONFIG_FORTIFY_SOURCE
+KBUILD_CFLAGS += -D__NO_FORTIFY
+endif
+endif
+
 obj-$(CONFIG_ERRATA_ANDES) += andes/
 obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
 obj-$(CONFIG_ERRATA_THEAD) += thead/
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 7f88cc4931f5..69dc8aaab3fb 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -36,6 +36,11 @@ KASAN_SANITIZE_alternative.o := n
 KASAN_SANITIZE_cpufeature.o := n
 KASAN_SANITIZE_sbi_ecall.o := n
 endif
+ifdef CONFIG_FORTIFY_SOURCE
+CFLAGS_alternative.o += -D__NO_FORTIFY
+CFLAGS_cpufeature.o += -D__NO_FORTIFY
+CFLAGS_sbi_ecall.o += -D__NO_FORTIFY
+endif
 endif
 
 extra-y += vmlinux.lds
diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c
index 6e0d333f57e5..2fd29695a788 100644
--- a/arch/riscv/kernel/acpi.c
+++ b/arch/riscv/kernel/acpi.c
@@ -210,7 +210,7 @@ void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size)
 	if (!size)
 		return NULL;
 
-	return early_ioremap(phys, size);
+	return early_memremap(phys, size);
 }
 
 void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
@@ -218,7 +218,7 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
 	if (!map || !size)
 		return;
 
-	early_iounmap(map, size);
+	early_memunmap(map, size);
 }
 
 void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index e94180ba432f..c2f3129a8e5c 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -4,8 +4,6 @@
  * Copyright (C) 2017 SiFive
  */
 
-#define GENERATING_ASM_OFFSETS
-
 #include <linux/kbuild.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index b320b1d9aa01..2d40736fc37c 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -80,8 +80,7 @@ int populate_cache_leaves(unsigned int cpu)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-	struct device_node *np = of_cpu_device_node_get(cpu);
-	struct device_node *prev = NULL;
+	struct device_node *np, *prev;
 	int levels = 1, level = 1;
 
 	if (!acpi_disabled) {
@@ -105,6 +104,10 @@ int populate_cache_leaves(unsigned int cpu)
 		return 0;
 	}
 
+	np = of_cpu_device_node_get(cpu);
+	if (!np)
+		return -ENOENT;
+
 	if (of_property_read_bool(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
 	if (of_property_read_bool(np, "i-cache-size"))
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index 28b58fc5ad19..a1e38ecfc8be 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -58,7 +58,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 	if (cpu_ops->cpu_is_stopped)
 		ret = cpu_ops->cpu_is_stopped(cpu);
 	if (ret)
-		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+		pr_warn("CPU%u may not have stopped: %d\n", cpu, ret);
 }
 
 /*
diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S
index 515b2dfbca75..c5f17c2710b5 100644
--- a/arch/riscv/kernel/efi-header.S
+++ b/arch/riscv/kernel/efi-header.S
@@ -64,7 +64,7 @@ extra_header_fields:
 	.long	efi_header_end - _start			// SizeOfHeaders
 	.long	0					// CheckSum
 	.short	IMAGE_SUBSYSTEM_EFI_APPLICATION		// Subsystem
-	.short	0					// DllCharacteristics
+	.short	IMAGE_DLL_CHARACTERISTICS_NX_COMPAT	// DllCharacteristics
 	.quad	0					// SizeOfStackReserve
 	.quad	0					// SizeOfStackCommit
 	.quad	0					// SizeOfHeapReserve
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index d5bf1bc7de62..81d69d45c06c 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -16,8 +16,12 @@ KBUILD_CFLAGS	:= $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS))
 KBUILD_CFLAGS	+= -mcmodel=medany
 
 CFLAGS_cmdline_early.o += -D__NO_FORTIFY
-CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
 CFLAGS_fdt_early.o += -D__NO_FORTIFY
+# lib/string.c already defines __NO_FORTIFY
+CFLAGS_ctype.o += -D__NO_FORTIFY
+CFLAGS_lib-fdt.o += -D__NO_FORTIFY
+CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
+CFLAGS_archrandom_early.o += -D__NO_FORTIFY
 
 $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \
 			       --remove-section=.note.gnu.property \
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index d4fd8af7aaf5..1b9867136b61 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -136,8 +136,6 @@
 #define REG_PTR(insn, pos, regs)	\
 	(ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
 
-#define GET_RM(insn)			(((insn) >> 12) & 7)
-
 #define GET_RS1(insn, regs)		(*REG_PTR(insn, SH_RS1, regs))
 #define GET_RS2(insn, regs)		(*REG_PTR(insn, SH_RS2, regs))
 #define GET_RS1S(insn, regs)		(*REG_PTR(RVC_RS1S(insn), 0, regs))
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 960feb1526ca..3f1c4b2d0b06 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -18,6 +18,7 @@ obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 ccflags-y := -fno-stack-protector
 ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -fno-builtin
 
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 6f3b6aef47ba..d0caac26533f 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -116,7 +116,10 @@ static inline bool amd_gart_present(void)
 
 #define amd_nb_num(x)		0
 #define amd_nb_has_feature(x)	false
-#define node_to_amd_nb(x)	NULL
+static inline struct amd_northbridge *node_to_amd_nb(int node)
+{
+	return NULL;
+}
 #define amd_gart_present(x)	false
 
 #endif
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d05392db5d0f..2dbadf347b5f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -261,12 +261,6 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	int ud_type;
 	u32 imm;
 
-	/*
-	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
-	 * is a rare case that uses @regs without passing them to
-	 * irqentry_enter().
-	 */
-	kmsan_unpoison_entry_regs(regs);
 	ud_type = decode_bug(regs->ip, &imm);
 	if (ud_type == BUG_NONE)
 		return handled;
@@ -276,6 +270,12 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	instrumentation_begin();
 	/*
+	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
+	 * is a rare case that uses @regs without passing them to
+	 * irqentry_enter().
+	 */
+	kmsan_unpoison_entry_regs(regs);
+	/*
 	 * Since we're emulating a CALL with exceptions, restore the interrupt
 	 * state to what it was at the exception site.
 	 */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 59a64b703aad..3c83951c619e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2654,19 +2654,26 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic->apicv_active) {
-		/* irr_pending is always true when apicv is activated. */
-		apic->irr_pending = true;
+	/*
+	 * When APICv is enabled, KVM must always search the IRR for a pending
+	 * IRQ, as other vCPUs and devices can set IRR bits even if the vCPU
+	 * isn't running.  If APICv is disabled, KVM _should_ search the IRR
+	 * for a pending IRQ.  But KVM currently doesn't ensure *all* hardware,
+	 * e.g. CPUs and IOMMUs, has seen the change in state, i.e. searching
+	 * the IRR at this time could race with IRQ delivery from hardware that
+	 * still sees APICv as being enabled.
+	 *
+	 * FIXME: Ensure other vCPUs and devices observe the change in APICv
+	 *        state prior to updating KVM's metadata caches, so that KVM
+	 *        can safely search the IRR and set irr_pending accordingly.
+	 */
+	apic->irr_pending = true;
+
+	if (apic->apicv_active)
 		apic->isr_count = 1;
-	} else {
-		/*
-		 * Don't clear irr_pending, searching the IRR can race with
-		 * updates from the CPU as APICv is still active from hardware's
-		 * perspective.  The flag will be cleared as appropriate when
-		 * KVM injects the interrupt.
-		 */
+	else
 		apic->isr_count = count_vectors(apic->regs + APIC_ISR);
-	}
+
 	apic->highest_isr_cache = -1;
 }
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c6c852485900..72674b8825c4 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -450,8 +450,11 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 		goto e_free;
 
 	/* This needs to happen after SEV/SNP firmware initialization. */
-	if (vm_type == KVM_X86_SNP_VM && snp_guest_req_init(kvm))
-		goto e_free;
+	if (vm_type == KVM_X86_SNP_VM) {
+		ret = snp_guest_req_init(kvm);
+		if (ret)
+			goto e_free;
+	}
 
 	INIT_LIST_HEAD(&sev->regions_list);
 	INIT_LIST_HEAD(&sev->mirror_vms);
@@ -2212,10 +2215,6 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (sev->snp_context)
 		return -EINVAL;
 
-	sev->snp_context = snp_context_create(kvm, argp);
-	if (!sev->snp_context)
-		return -ENOTTY;
-
 	if (params.flags)
 		return -EINVAL;
 
@@ -2230,6 +2229,10 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET)
 		return -EINVAL;
 
+	sev->snp_context = snp_context_create(kvm, argp);
+	if (!sev->snp_context)
+		return -ENOTTY;
+
 	start.gctx_paddr = __psp_pa(sev->snp_context);
 	start.policy = params.policy;
 	memcpy(start.gosvw, params.gosvw, sizeof(params.gosvw));
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 746cb41c5b98..aa78b6f38dfe 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1197,11 +1197,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept);
 
 	/*
-	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
-	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
-	 * full TLB flush from the guest's perspective.  This is required even
-	 * if VPID is disabled in the host as KVM may need to synchronize the
-	 * MMU in response to the guest TLB flush.
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host, and so architecturally, linear and combined
+	 * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit.  KVM
+	 * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2,
+	 * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01.  This
+	 * is required if VPID is disabled in KVM, as a TLB flush (there are no
+	 * VPIDs) still occurs from L1's perspective, and KVM may need to
+	 * synchronize the MMU in response to the guest TLB flush.
 	 *
 	 * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use.
 	 * EPT is a special snowflake, as guest-physical mappings aren't
@@ -2315,6 +2318,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
 
 	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);
 
+	/*
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host.  Emulate this behavior by using vpid01 for L2
+	 * if VPID is disabled in vmcs12.  Note, if VPID is disabled, VM-Enter
+	 * and VM-Exit are architecturally required to flush VPID=0, but *only*
+	 * VPID=0.  I.e. using vpid02 would be ok (so long as KVM emulates the
+	 * required flushes), but doing so would cause KVM to over-flush.  E.g.
+	 * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled,
+	 * and then runs L2 X again, then KVM can and should retain TLB entries
+	 * for VPID12=1.
+	 */
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
 			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
@@ -5957,6 +5971,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 
+	/*
+	 * Always flush the effective vpid02, i.e. never flush the current VPID
+	 * and never explicitly flush vpid01.  INVVPID targets a VPID, not a
+	 * VMCS, and so whether or not the current vmcs12 has VPID enabled is
+	 * irrelevant (and there may not be a loaded vmcs12).
+	 */
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6ed801ffe33f..0f008f5ef6f0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -217,9 +217,11 @@ module_param(ple_window_shrink, uint, 0444);
 static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
 module_param(ple_window_max, uint, 0444);
 
-/* Default is SYSTEM mode, 1 for host-guest mode */
+/* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */
 int __read_mostly pt_mode = PT_MODE_SYSTEM;
+#ifdef CONFIG_BROKEN
 module_param(pt_mode, int, S_IRUGO);
+#endif
 
 struct x86_pmu_lbr __ro_after_init vmx_lbr_caps;
 
@@ -3213,7 +3215,7 @@ void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 
 static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu))
+	if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu)))
 		return nested_get_vpid02(vcpu);
 	return to_vmx(vcpu)->vpid;
 }