19 files changed, 254 insertions, 105 deletions

diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 401e30ca0a75..8272a4492844 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -37,6 +37,14 @@ int memcmp(const void *s1, const void *s2, size_t len)
 	return diff;
 }
 
+/*
+ * Clang may lower `memcmp == 0` to `bcmp == 0`.
+ */
+int bcmp(const void *s1, const void *s2, size_t len)
+{
+	return memcmp(s1, s2, len);
+}
+
 int strcmp(const char *str1, const char *str2)
 {
 	const unsigned char *s1 = (const unsigned char *)str1;
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 830bd984182b..515c0ceeb4a3 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -314,6 +314,23 @@ For 32-bit we have the following conventions - kernel is built with
 
 #endif
 
+/*
+ * Mitigate Spectre v1 for conditional swapgs code paths.
+ *
+ * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to
+ * prevent a speculative swapgs when coming from kernel space.
+ *
+ * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path,
+ * to prevent the swapgs from getting speculatively skipped when coming from
+ * user space.
+ */
+.macro FENCE_SWAPGS_USER_ENTRY
+	ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER
+.endm
+.macro FENCE_SWAPGS_KERNEL_ENTRY
+	ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL
+.endm
+
 .macro STACKLEAK_ERASE_NOCLOBBER
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 	PUSH_AND_CLEAR_REGS
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 3f5a978a02a7..be9ca198c581 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -519,7 +519,7 @@ ENTRY(interrupt_entry)
 	testb	$3, CS-ORIG_RAX+8(%rsp)
 	jz	1f
 	SWAPGS
-
+	FENCE_SWAPGS_USER_ENTRY
 	/*
 	 * Switch to the thread stack. The IRET frame and orig_ax are
 	 * on the stack, as well as the return address. RDI..R12 are
@@ -549,8 +549,10 @@ ENTRY(interrupt_entry)
 	UNWIND_HINT_FUNC
 
 	movq	(%rdi), %rdi
+	jmp	2f
 1:
-
+	FENCE_SWAPGS_KERNEL_ENTRY
+2:
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 
@@ -1238,6 +1240,13 @@ ENTRY(paranoid_entry)
 	 */
 	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
 
+	/*
+	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
+	 * unconditional CR3 write, even in the PTI case.  So do an lfence
+	 * to prevent GS speculation, regardless of whether PTI is enabled.
+	 */
+	FENCE_SWAPGS_KERNEL_ENTRY
+
 	ret
 END(paranoid_entry)
 
@@ -1288,6 +1297,7 @@ ENTRY(error_entry)
 	 * from user mode due to an IRET fault.
 	 */
 	SWAPGS
+	FENCE_SWAPGS_USER_ENTRY
 	/* We have user CR3.  Change to kernel CR3. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
@@ -1301,6 +1311,8 @@ ENTRY(error_entry)
 	pushq	%r12
 	ret
 
+.Lerror_entry_done_lfence:
+	FENCE_SWAPGS_KERNEL_ENTRY
 .Lerror_entry_done:
 	ret
 
@@ -1318,7 +1330,7 @@ ENTRY(error_entry)
 	cmpq	%rax, RIP+8(%rsp)
 	je	.Lbstep_iret
 	cmpq	$.Lgs_change, RIP+8(%rsp)
-	jne	.Lerror_entry_done
+	jne	.Lerror_entry_done_lfence
 
 	/*
 	 * hack: .Lgs_change can fail with user gsbase.  If this happens, fix up
@@ -1326,6 +1338,7 @@ ENTRY(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
+	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	jmp .Lerror_entry_done
 
@@ -1340,6 +1353,7 @@ ENTRY(error_entry)
 	 * gsbase and CR3.  Switch to kernel gsbase and CR3:
 	 */
 	SWAPGS
+	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 	/*
@@ -1431,6 +1445,7 @@ ENTRY(nmi)
 
 	swapgs
 	cld
+	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 998c2cc08363..e880f2408e29 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -281,6 +281,8 @@
 #define X86_FEATURE_CQM_OCCUP_LLC	(11*32+ 1) /* LLC occupancy monitoring */
 #define X86_FEATURE_CQM_MBM_TOTAL	(11*32+ 2) /* LLC Total MBM monitoring */
 #define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
+#define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
+#define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -394,5 +396,6 @@
 #define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 #define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
 #define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
+#define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7b0a4ee77313..74e88e5edd9c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,6 +35,8 @@
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/hyperv-tlfs.h>
 
+#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
+
 #define KVM_MAX_VCPUS 288
 #define KVM_SOFT_MAX_VCPUS 240
 #define KVM_MAX_VCPU_ID 1023
@@ -1175,6 +1177,7 @@ struct kvm_x86_ops {
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
+	bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
 
 	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
 			    bool *expired);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 801ecd1c3fd5..c6fa3ef10b4e 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,6 +34,7 @@
 
 #include "cpu.h"
 
+static void __init spectre_v1_select_mitigation(void);
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
@@ -98,17 +99,11 @@ void __init check_bugs(void)
 	if (boot_cpu_has(X86_FEATURE_STIBP))
 		x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
 
-	/* Select the proper spectre mitigation before patching alternatives */
+	/* Select the proper CPU mitigations before patching alternatives: */
+	spectre_v1_select_mitigation();
 	spectre_v2_select_mitigation();
-
-	/*
-	 * Select proper mitigation for any exposure to the Speculative Store
-	 * Bypass vulnerability.
-	 */
 	ssb_select_mitigation();
-
 	l1tf_select_mitigation();
-
 	mds_select_mitigation();
 
 	arch_smt_update();
@@ -274,6 +269,98 @@ static int __init mds_cmdline(char *str)
 early_param("mds", mds_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V1 : " fmt
+
+enum spectre_v1_mitigation {
+	SPECTRE_V1_MITIGATION_NONE,
+	SPECTRE_V1_MITIGATION_AUTO,
+};
+
+static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init =
+	SPECTRE_V1_MITIGATION_AUTO;
+
+static const char * const spectre_v1_strings[] = {
+	[SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers",
+	[SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization",
+};
+
+/*
+ * Does SMAP provide full mitigation against speculative kernel access to
+ * userspace?
+ */
+static bool smap_works_speculatively(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_SMAP))
+		return false;
+
+	/*
+	 * On CPUs which are vulnerable to Meltdown, SMAP does not
+	 * prevent speculative access to user data in the L1 cache.
+	 * Consider SMAP to be non-functional as a mitigation on these
+	 * CPUs.
+	 */
+	if (boot_cpu_has(X86_BUG_CPU_MELTDOWN))
+		return false;
+
+	return true;
+}
+
+static void __init spectre_v1_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) {
+		spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+		return;
+	}
+
+	if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) {
+		/*
+		 * With Spectre v1, a user can speculatively control either
+		 * path of a conditional swapgs with a user-controlled GS
+		 * value.  The mitigation is to add lfences to both code paths.
+		 *
+		 * If FSGSBASE is enabled, the user can put a kernel address in
+		 * GS, in which case SMAP provides no protection.
+		 *
+		 * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the
+		 *	   FSGSBASE enablement patches have been merged. ]
+		 *
+		 * If FSGSBASE is disabled, the user can only put a user space
+		 * address in GS.  That makes an attack harder, but still
+		 * possible if there's no SMAP protection.
+		 */
+		if (!smap_works_speculatively()) {
+			/*
+			 * Mitigation can be provided from SWAPGS itself or
+			 * PTI as the CR3 write in the Meltdown mitigation
+			 * is serializing.
+			 *
+			 * If neither is there, mitigate with an LFENCE to
+			 * stop speculation through swapgs.
+			 */
+			if (boot_cpu_has_bug(X86_BUG_SWAPGS) &&
+			    !boot_cpu_has(X86_FEATURE_PTI))
+				setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER);
+
+			/*
+			 * Enable lfences in the kernel entry (non-swapgs)
+			 * paths, to prevent user entry from speculatively
+			 * skipping swapgs.
+			 */
+			setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL);
+		}
+	}
+
+	pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]);
+}
+
+static int __init nospectre_v1_cmdline(char *str)
+{
+	spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+	return 0;
+}
+early_param("nospectre_v1", nospectre_v1_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -1290,7 +1377,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		break;
 
 	case X86_BUG_SPECTRE_V1:
-		return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+		return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]);
 
 	case X86_BUG_SPECTRE_V2:
 		return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 11472178e17f..f125bf7ecb6f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1022,6 +1022,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_L1TF		BIT(3)
 #define NO_MDS		BIT(4)
 #define MSBDS_ONLY	BIT(5)
+#define NO_SWAPGS	BIT(6)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1048,30 +1049,38 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
 	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
 
-	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY),
-	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
 
 	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF),
-	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF | NO_SWAPGS),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS),
+
+	/*
+	 * Technically, swapgs isn't serializing on AMD (despite it previously
+	 * being documented as such in the APM).  But according to AMD, %gs is
+	 * updated non-speculatively, and the issuing of %gs-relative memory
+	 * operands will be blocked until the %gs update completes, which is
+	 * good enough for our purposes.
+	 */
 
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
 	{}
 };
 
@@ -1108,6 +1117,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
 	}
 
+	if (!cpu_matches(NO_SWAPGS))
+		setup_force_cpu_bug(X86_BUG_SWAPGS);
+
 	if (cpu_matches(NO_MELTDOWN))
 		return;
 
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 4296c702a3f7..72182809b333 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -98,6 +98,7 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 	case 7:
 		if (size < 0x40)
 			break;
+		/* Else, fall through */
 	case 6:
 	case 5:
 	case 4:
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b7f34fe2171e..4ab377c9fffe 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -308,9 +308,6 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 
 static void kvm_guest_cpu_init(void)
 {
-	if (!kvm_para_available())
-		return;
-
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
 		u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
 
@@ -625,9 +622,6 @@ static void __init kvm_guest_init(void)
 {
 	int i;
 
-	if (!kvm_para_available())
-		return;
-
 	paravirt_ops_setup();
 	register_reboot_notifier(&kvm_pv_reboot_nb);
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
@@ -848,8 +842,6 @@ asm(
  */
 void __init kvm_spinlock_init(void)
 {
-	if (!kvm_para_available())
-		return;
 	/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0fdbe89d0754..3c5bbe8e4120 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -201,6 +201,7 @@ static int set_segment_reg(struct task_struct *task,
 	case offsetof(struct user_regs_struct, ss):
 		if (unlikely(value == 0))
 			return -EIO;
+		/* Else, fall through */
 
 	default:
 		*pt_regs_access(task_pt_regs(task), offset) = value;
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index 329361b69d5e..018aebce33ff 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -8,11 +8,6 @@
 #include <linux/debugfs.h>
 #include "lapic.h"
 
-bool kvm_arch_has_vcpu_debugfs(void)
-{
-	return true;
-}
-
 static int vcpu_get_timer_advance_ns(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
@@ -48,37 +43,22 @@ static int vcpu_get_tsc_scaling_frac_bits(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bits, NULL, "%llu\n");
 
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 {
-	struct dentry *ret;
-
-	ret = debugfs_create_file("tsc-offset", 0444,
-							vcpu->debugfs_dentry,
-							vcpu, &vcpu_tsc_offset_fops);
-	if (!ret)
-		return -ENOMEM;
+	debugfs_create_file("tsc-offset", 0444, vcpu->debugfs_dentry, vcpu,
+			    &vcpu_tsc_offset_fops);
 
-	if (lapic_in_kernel(vcpu)) {
-		ret = debugfs_create_file("lapic_timer_advance_ns", 0444,
-								vcpu->debugfs_dentry,
-								vcpu, &vcpu_timer_advance_ns_fops);
-		if (!ret)
-			return -ENOMEM;
-	}
+	if (lapic_in_kernel(vcpu))
+		debugfs_create_file("lapic_timer_advance_ns", 0444,
+				    vcpu->debugfs_dentry, vcpu,
+				    &vcpu_timer_advance_ns_fops);
 
 	if (kvm_has_tsc_control) {
-		ret = debugfs_create_file("tsc-scaling-ratio", 0444,
-							vcpu->debugfs_dentry,
-							vcpu, &vcpu_tsc_scaling_fops);
-		if (!ret)
-			return -ENOMEM;
-		ret = debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
-							vcpu->debugfs_dentry,
-							vcpu, &vcpu_tsc_scaling_frac_fops);
-		if (!ret)
-			return -ENOMEM;
-
+		debugfs_create_file("tsc-scaling-ratio", 0444,
+				    vcpu->debugfs_dentry, vcpu,
+				    &vcpu_tsc_scaling_fops);
+		debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
+				    vcpu->debugfs_dentry, vcpu,
+				    &vcpu_tsc_scaling_frac_fops);
 	}
-
-	return 0;
 }
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0aa158657f20..685d17c11461 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1548,7 +1548,6 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
-	struct swait_queue_head *q = &vcpu->wq;
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	if (atomic_read(&apic->lapic_timer.pending))
@@ -1566,13 +1565,6 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 
 	atomic_inc(&apic->lapic_timer.pending);
 	kvm_set_pending_timer(vcpu);
-
-	/*
-	 * For x86, the atomic_inc() is serialized, thus
-	 * using swait_active() is safe.
-	 */
-	if (swait_active(q))
-		swake_up_one(q);
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7eafc6907861..d685491fce4d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -5190,6 +5190,11 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		kvm_vcpu_wake_up(vcpu);
 }
 
+static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 {
 	unsigned long flags;
@@ -7314,6 +7319,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.pmu_ops = &amd_pmu_ops,
 	.deliver_posted_interrupt = svm_deliver_avic_intr,
+	.dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
 	.update_pi_irte = svm_update_pi_irte,
 	.setup_mce = svm_setup_mce,
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 074385c86c09..42ed3faa6af8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6117,6 +6117,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	return max_irr;
 }
 
+static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	return pi_test_on(vcpu_to_pi_desc(vcpu));
+}
+
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -7726,6 +7731,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
 	.sync_pir_to_irr = vmx_sync_pir_to_irr,
 	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+	.dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.set_identity_map_addr = vmx_set_identity_map_addr,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c6d951cbd76c..93b0bd45ac73 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9698,6 +9698,22 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
+		return true;
+
+	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+		kvm_test_request(KVM_REQ_SMI, vcpu) ||
+		 kvm_test_request(KVM_REQ_EVENT, vcpu))
+		return true;
+
+	if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu))
+		return true;
+
+	return false;
+}
+
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.preempted_in_kernel;
diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c
index 04967cdce5d1..7ad68917a51e 100644
--- a/arch/x86/lib/cpu.c
+++ b/arch/x86/lib/cpu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/types.h>
 #include <linux/export.h>
+#include <asm/cpu.h>
 
 unsigned int x86_family(unsigned int sig)
 {
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 3cf302b26332..8901a1f89cf5 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -6,6 +6,9 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string
 targets += $(purgatory-y)
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
+$(obj)/string.o: $(srctree)/arch/x86/boot/compressed/string.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
 $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
@@ -17,11 +20,34 @@ KCOV_INSTRUMENT := n
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
-# sure how to relocate those. Like kexec-tools, use custom flags.
-
-KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -Os -mcmodel=large
-KBUILD_CFLAGS += -m$(BITS)
-KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+# sure how to relocate those.
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_sha256.o		+= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_purgatory.o	+= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_string.o		+= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_kexec-purgatory.o	+= $(CC_FLAGS_FTRACE)
+endif
+
+ifdef CONFIG_STACKPROTECTOR
+CFLAGS_REMOVE_sha256.o		+= -fstack-protector
+CFLAGS_REMOVE_purgatory.o	+= -fstack-protector
+CFLAGS_REMOVE_string.o		+= -fstack-protector
+CFLAGS_REMOVE_kexec-purgatory.o	+= -fstack-protector
+endif
+
+ifdef CONFIG_STACKPROTECTOR_STRONG
+CFLAGS_REMOVE_sha256.o		+= -fstack-protector-strong
+CFLAGS_REMOVE_purgatory.o	+= -fstack-protector-strong
+CFLAGS_REMOVE_string.o		+= -fstack-protector-strong
+CFLAGS_REMOVE_kexec-purgatory.o	+= -fstack-protector-strong
+endif
+
+ifdef CONFIG_RETPOLINE
+CFLAGS_REMOVE_sha256.o		+= $(RETPOLINE_CFLAGS)
+CFLAGS_REMOVE_purgatory.o	+= $(RETPOLINE_CFLAGS)
+CFLAGS_REMOVE_string.o		+= $(RETPOLINE_CFLAGS)
+CFLAGS_REMOVE_kexec-purgatory.o	+= $(RETPOLINE_CFLAGS)
+endif
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 6d8d5a34c377..b607bda786f6 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -68,3 +68,9 @@ void purgatory(void)
 	}
 	copy_backup_region();
 }
+
+/*
+ * Defined in order to reuse memcpy() and memset() from
+ * arch/x86/boot/compressed/string.c
+ */
+void warn(const char *msg) {}
diff --git a/arch/x86/purgatory/string.c b/arch/x86/purgatory/string.c
deleted file mode 100644
index 01ad43873ad9..000000000000
--- a/arch/x86/purgatory/string.c
+++ /dev/null
@@ -1,23 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Simple string functions.
- *
- * Copyright (C) 2014 Red Hat Inc.
- *
- * Author:
- *       Vivek Goyal <vgoyal@redhat.com>
- */
-
-#include <linux/types.h>
-
-#include "../boot/string.c"
-
-void *memcpy(void *dst, const void *src, size_t len)
-{
-	return __builtin_memcpy(dst, src, len);
-}
-
-void *memset(void *dst, int c, size_t len)
-{
-	return __builtin_memset(dst, c, len);
-}