Merge branch 'x86/urgent' into x86/apic, to resolve conflicts

 Conflicts:
	arch/x86/kernel/cpu/common.c
	arch/x86/kernel/cpu/intel.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

19 files changed, 221 insertions, 146 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2264db14a25d..da8f3caf2781 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -112,13 +112,13 @@ ifeq ($(CONFIG_X86_32),y)
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-        ifeq ($(CONFIG_STACKPROTECTOR),y)
-                ifeq ($(CONFIG_SMP),y)
+    ifeq ($(CONFIG_STACKPROTECTOR),y)
+        ifeq ($(CONFIG_SMP),y)
 			KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
-                else
+        else
 			KBUILD_CFLAGS += -mstack-protector-guard=global
-                endif
         endif
+    endif
 else
         BITS := 64
         UTS_MACHINE := x86_64
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 8c8d38f0cb1d..003379049924 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -6,6 +6,9 @@
 #include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/msr-index.h>
+#include <asm/unwind_hints.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
 
 .pushsection .noinstr.text, "ax"
 
@@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb)
 EXPORT_SYMBOL_GPL(entry_ibpb);
 
 .popsection
+
+/*
+ * Define the VERW operand that is disguised as entry code so that
+ * it can be referenced with KPTI enabled. This ensure VERW can be
+ * used late in exit-to-user path after page tables are switched.
+ */
+.pushsection .entry.text, "ax"
+
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_START_NOALIGN(mds_verw_sel)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	.word __KERNEL_DS
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_END(mds_verw_sel);
+/* For KVM */
+EXPORT_SYMBOL_GPL(mds_verw_sel);
+
+.popsection
+
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c73047bf9f4b..fba427646805 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -885,6 +885,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
 	popl	%eax
+	CLEAR_CPU_BUFFERS
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -954,6 +955,7 @@ restore_all_switch_stack:
 
 	/* Restore user state */
 	RESTORE_REGS pop=4			# skip orig_eax/error_code
+	CLEAR_CPU_BUFFERS
 .Lirq_return:
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -1146,6 +1148,7 @@ SYM_CODE_START(asm_exc_nmi)
 
 	/* Not on SYSENTER stack. */
 	call	exc_nmi
+	CLEAR_CPU_BUFFERS
 	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c40f89ab1b4c..9bb485977629 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -161,6 +161,7 @@ syscall_return_via_sysret:
 SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	swapgs
+	CLEAR_CPU_BUFFERS
 	sysretq
 SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -573,6 +574,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 
 .Lswapgs_and_iret:
 	swapgs
+	CLEAR_CPU_BUFFERS
 	/* Assert that the IRET frame indicates user mode. */
 	testb	$3, 8(%rsp)
 	jnz	.Lnative_iret
@@ -723,6 +725,8 @@ native_irq_return_ldt:
 	 */
 	popq	%rax				/* Restore user RAX */
 
+	CLEAR_CPU_BUFFERS
+
 	/*
 	 * RSP now points to an ordinary IRET frame, except that the page
 	 * is read-only and RSP[31:16] are preloaded with the userspace
@@ -1450,6 +1454,12 @@ nmi_restore:
 	movq	$0, 5*8(%rsp)		/* clear "NMI executing" */
 
 	/*
+	 * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like
+	 * NMI in kernel after user state is restored. For an unprivileged user
+	 * these conditions are hard to meet.
+	 */
+
+	/*
 	 * iretq reads the "iret" frame and exits the NMI stack in a
 	 * single instruction.  We are returning to kernel mode, so this
 	 * cannot result in a fault.  Similarly, we don't need to worry
@@ -1466,6 +1476,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore)
 	UNWIND_HINT_END_OF_STACK
 	ENDBR
 	mov	$-ENOSYS, %eax
+	CLEAR_CPU_BUFFERS
 	sysretl
 SYM_CODE_END(entry_SYSCALL32_ignore)
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index de94e2e84ecc..eabf48c4d4b4 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
 	xorl	%r9d, %r9d
 	xorl	%r10d, %r10d
 	swapgs
+	CLEAR_CPU_BUFFERS
 	sysretl
 SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index fdf723b6f6d0..2b62cdd8dd12 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -95,7 +95,7 @@
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-/* FREE, was #define X86_FEATURE_LFENCE_RDTSC		( 3*32+18) "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* "" Clear CPU buffers using VERW */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index ce8f50192ae3..7e523bb3d2d3 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 
 static __always_inline void arch_exit_to_user_mode(void)
 {
-	mds_user_clear_cpu_buffers();
 	amd_clear_divider();
 }
 #define arch_exit_to_user_mode arch_exit_to_user_mode
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 262e65539f83..ab19c7f1167b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -315,6 +315,17 @@
 #endif
 .endm
 
+/*
+ * Macro to execute VERW instruction that mitigate transient data sampling
+ * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ *
+ * Note: Only the memory operand variant of VERW clears the CPU buffers.
+ */
+.macro CLEAR_CPU_BUFFERS
+	ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF
+.endm
+
 #else /* __ASSEMBLY__ */
 
 #define ANNOTATE_RETPOLINE_SAFE					\
@@ -529,13 +540,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-DECLARE_STATIC_KEY_FALSE(mds_user_clear);
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
 DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
 
+extern u16 mds_verw_sel;
+
 #include <asm/segment.h>
 
 /**
@@ -562,17 +574,6 @@ static __always_inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
- *
- * Clear CPU buffers if the corresponding static key is enabled
- */
-static __always_inline void mds_user_clear_cpu_buffers(void)
-{
-	if (static_branch_likely(&mds_user_clear))
-		mds_clear_cpu_buffers();
-}
-
-/**
  * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bb0ab8466b91..48d049cd74e7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-/* Control MDS CPU buffer clear before returning to user space */
-DEFINE_STATIC_KEY_FALSE(mds_user_clear);
-EXPORT_SYMBOL_GPL(mds_user_clear);
 /* Control MDS CPU buffer clear before idling (halt, mwait) */
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void)
 		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
 			mds_mitigation = MDS_MITIGATION_VMWERV;
 
-		static_branch_enable(&mds_user_clear);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 
 		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
 		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
@@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void)
 	 * For guests that can't determine whether the correct microcode is
 	 * present on host, enable the mitigation for UCODE_NEEDED as well.
 	 */
-	static_branch_enable(&mds_user_clear);
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 
 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
@@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void)
 	 */
 	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
 					      boot_cpu_has(X86_FEATURE_RTM)))
-		static_branch_enable(&mds_user_clear);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 	else
 		static_branch_enable(&mmio_stale_data_clear);
 
@@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void)
 	if (cpu_mitigations_off())
 		return;
 
-	if (!static_key_enabled(&mds_user_clear))
+	if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
 		goto out;
 
 	/*
-	 * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
-	 * mitigation, if necessary.
+	 * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
+	 * Stale Data mitigation, if necessary.
 	 */
 	if (mds_mitigation == MDS_MITIGATION_OFF &&
 	    boot_cpu_has_bug(X86_BUG_MDS)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 05e0b31f75e9..087d21734286 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1543,6 +1543,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 		cpu_parse_early_param();
 
 		cpu_init_topology(c);
@@ -1557,11 +1558,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 			this_cpu->c_bsp_init(c);
 	} else {
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 		cpu_init_topology(c);
 	}
 
-	get_cpu_address_sizes(c);
-
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
 	cpu_set_bug_bits(c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1bb37a69d837..be30d7fa2e66 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	return false;
 }
 
+#define MSR_IA32_TME_ACTIVATE		0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
+#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128	0
+
+#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED			0
+#define MKTME_DISABLED			1
+#define MKTME_UNINITIALIZED		2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+	u64 tme_activate, tme_policy, tme_crypto_algs;
+	int keyid_bits = 0, nr_keyids = 0;
+	static u64 tme_activate_cpu0 = 0;
+
+	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+	if (mktme_status != MKTME_UNINITIALIZED) {
+		if (tme_activate != tme_activate_cpu0) {
+			/* Broken BIOS? */
+			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+			pr_err_once("x86/tme: MKTME is not usable\n");
+			mktme_status = MKTME_DISABLED;
+
+			/* Proceed. We may need to exclude bits from x86_phys_bits. */
+		}
+	} else {
+		tme_activate_cpu0 = tme_activate;
+	}
+
+	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+		pr_info_once("x86/tme: not enabled by BIOS\n");
+		mktme_status = MKTME_DISABLED;
+		return;
+	}
+
+	if (mktme_status != MKTME_UNINITIALIZED)
+		goto detect_keyid_bits;
+
+	pr_info("x86/tme: enabled by BIOS\n");
+
+	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+				tme_crypto_algs);
+		mktme_status = MKTME_DISABLED;
+	}
+detect_keyid_bits:
+	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+	nr_keyids = (1UL << keyid_bits) - 1;
+	if (nr_keyids) {
+		pr_info_once("x86/mktme: enabled by BIOS\n");
+		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+	} else {
+		pr_info_once("x86/mktme: disabled by BIOS\n");
+	}
+
+	if (mktme_status == MKTME_UNINITIALIZED) {
+		/* MKTME is usable */
+		mktme_status = MKTME_ENABLED;
+	}
+
+	/*
+	 * KeyID bits effectively lower the number of physical address
+	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
+	 */
+	c->x86_phys_bits -= keyid_bits;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -315,6 +399,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_memory_type_self_snoop_errata(c);
+
+	/*
+	 * Adjust the number of physical bits early because it affects the
+	 * valid bits of the MTRR mask registers.
+	 */
+	if (cpu_has(c, X86_FEATURE_TME))
+		detect_tme_early(c);
 }
 
 static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -475,90 +566,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define MSR_IA32_TME_ACTIVATE		0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
-#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128	0
-
-#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED			0
-#define MKTME_DISABLED			1
-#define MKTME_UNINITIALIZED		2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
-	u64 tme_activate, tme_policy, tme_crypto_algs;
-	int keyid_bits = 0, nr_keyids = 0;
-	static u64 tme_activate_cpu0 = 0;
-
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
-	if (mktme_status != MKTME_UNINITIALIZED) {
-		if (tme_activate != tme_activate_cpu0) {
-			/* Broken BIOS? */
-			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
-			pr_err_once("x86/tme: MKTME is not usable\n");
-			mktme_status = MKTME_DISABLED;
-
-			/* Proceed. We may need to exclude bits from x86_phys_bits. */
-		}
-	} else {
-		tme_activate_cpu0 = tme_activate;
-	}
-
-	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
-		pr_info_once("x86/tme: not enabled by BIOS\n");
-		mktme_status = MKTME_DISABLED;
-		return;
-	}
-
-	if (mktme_status != MKTME_UNINITIALIZED)
-		goto detect_keyid_bits;
-
-	pr_info("x86/tme: enabled by BIOS\n");
-
-	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
-	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
-		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
-	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
-	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
-		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
-				tme_crypto_algs);
-		mktme_status = MKTME_DISABLED;
-	}
-detect_keyid_bits:
-	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
-	nr_keyids = (1UL << keyid_bits) - 1;
-	if (nr_keyids) {
-		pr_info_once("x86/mktme: enabled by BIOS\n");
-		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
-	} else {
-		pr_info_once("x86/mktme: disabled by BIOS\n");
-	}
-
-	if (mktme_status == MKTME_UNINITIALIZED) {
-		/* MKTME is usable */
-		mktme_status = MKTME_ENABLED;
-	}
-
-	/*
-	 * KeyID bits effectively lower the number of physical address
-	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
-	 */
-	c->x86_phys_bits -= keyid_bits;
-}
-
 static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
@@ -677,9 +684,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_ia32_feat_ctl(c);
 
-	if (cpu_has(c, X86_FEATURE_TME))
-		detect_tme(c);
-
 	init_intel_misc_features(c);
 
 	split_lock_init();
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 17e955ab69fe..3082cf24b69e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -563,9 +563,6 @@ nmi_restart:
 	}
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
-
-	if (user_mode(regs))
-		mds_user_clear_cpu_buffers();
 }
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a6216c874729..315c7c2ba89b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -71,7 +71,7 @@ static int fixed_pmc_events[] = {
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
 	struct kvm_pmc *pmc;
-	u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
+	u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
 	int i;
 
 	pmu->fixed_ctr_ctrl = data;
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h
index edc3f16cc189..6a9bfdfbb6e5 100644
--- a/arch/x86/kvm/vmx/run_flags.h
+++ b/arch/x86/kvm/vmx/run_flags.h
@@ -2,7 +2,10 @@
 #ifndef __KVM_X86_VMX_RUN_FLAGS_H
 #define __KVM_X86_VMX_RUN_FLAGS_H
 
-#define VMX_RUN_VMRESUME	(1 << 0)
-#define VMX_RUN_SAVE_SPEC_CTRL	(1 << 1)
+#define VMX_RUN_VMRESUME_SHIFT		0
+#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT	1
+
+#define VMX_RUN_VMRESUME		BIT(VMX_RUN_VMRESUME_SHIFT)
+#define VMX_RUN_SAVE_SPEC_CTRL		BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
 
 #endif /* __KVM_X86_VMX_RUN_FLAGS_H */
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 906ecd001511..2bfbf758d061 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	mov (%_ASM_SP), %_ASM_AX
 
 	/* Check if vmlaunch or vmresume is needed */
-	test $VMX_RUN_VMRESUME, %ebx
+	bt   $VMX_RUN_VMRESUME_SHIFT, %ebx
 
 	/* Load guest registers.  Don't clobber flags. */
 	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
@@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	/* Load guest RAX.  This kills the @regs pointer! */
 	mov VCPU_RAX(%_ASM_AX), %_ASM_AX
 
-	/* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */
-	jz .Lvmlaunch
+	/* Clobbers EFLAGS.ZF */
+	CLEAR_CPU_BUFFERS
+
+	/* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */
+	jnc .Lvmlaunch
 
 	/*
 	 * After a successful VMRESUME/VMLAUNCH, control flow "magically"
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1111d9d08903..88a4ff200d04 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -388,7 +388,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 {
-	vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+	/*
+	 * Disable VERW's behavior of clearing CPU buffers for the guest if the
+	 * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled
+	 * the mitigation. Disabling the clearing behavior provides a
+	 * performance boost for guests that aren't aware that manually clearing
+	 * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry
+	 * and VM-Exit.
+	 */
+	vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) &&
+				(host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
 				!boot_cpu_has_bug(X86_BUG_MDS) &&
 				!boot_cpu_has_bug(X86_BUG_TAA);
 
@@ -7224,11 +7233,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	guest_state_enter_irqoff();
 
-	/* L1D Flush includes CPU buffer clear to mitigate MDS */
+	/*
+	 * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW
+	 * mitigation for MDS is done late in VMentry and is still
+	 * executed in spite of L1D Flush. This is because an extra VERW
+	 * should not matter much after the big hammer L1D Flush.
+	 */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
-	else if (static_branch_unlikely(&mds_user_clear))
-		mds_clear_cpu_buffers();
 	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
 		 kvm_arch_has_assigned_device(vcpu->kvm))
 		mds_clear_cpu_buffers();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bf10a9073a09..48a61d283406 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1704,22 +1704,17 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	struct kvm_msr_entry msr;
 	int r;
 
+	/* Unconditionally clear the output for simplicity */
+	msr.data = 0;
 	msr.index = index;
 	r = kvm_get_msr_feature(&msr);
 
-	if (r == KVM_MSR_RET_INVALID) {
-		/* Unconditionally clear the output for simplicity */
-		*data = 0;
-		if (kvm_msr_ignored_check(index, 0, false))
-			r = 0;
-	}
-
-	if (r)
-		return r;
+	if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false))
+		r = 0;
 
 	*data = msr.data;
 
-	return 0;
+	return r;
 }
 
 static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
@@ -2511,7 +2506,7 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 }
 
 #ifdef CONFIG_X86_64
-static inline int gtod_is_based_on_tsc(int mode)
+static inline bool gtod_is_based_on_tsc(int mode)
 {
 	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
 }
@@ -5458,7 +5453,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
 		vcpu->arch.nmi_pending = 0;
 		atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
-		kvm_make_request(KVM_REQ_NMI, vcpu);
+		if (events->nmi.pending)
+			kvm_make_request(KVM_REQ_NMI, vcpu);
 	}
 	static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
 
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..f50cc210a981 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		if (info->direct_gbpages) {
-			pud_t pudval;
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_large(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
 
-			if (pud_present(*pud))
-				continue;
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 114b362cb7af..935771726f9c 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu)
 	char *resched_name, *callfunc_name, *debug_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+	if (!resched_name)
+		goto fail_mem;
 	per_cpu(xen_resched_irq, cpu).name = resched_name;
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
 				    cpu,
@@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu)
 	per_cpu(xen_resched_irq, cpu).irq = rc;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+	if (!callfunc_name)
+		goto fail_mem;
 	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
 				    cpu,
@@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu)
 
 	if (!xen_fifo_events) {
 		debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+		if (!debug_name)
+			goto fail_mem;
+
 		per_cpu(xen_debug_irq, cpu).name = debug_name;
 		rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
 					     xen_debug_interrupt,
@@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu)
 	}
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+	if (!callfunc_name)
+		goto fail_mem;
+
 	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
 				    cpu,
@@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu)
 
 	return 0;
 
+ fail_mem:
+	rc = -ENOMEM;
  fail:
 	xen_smp_intr_free(cpu);
 	return rc;