Merging upstream version 4.19.282.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

40 files changed, 318 insertions, 175 deletions

diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index d401b4a26..a86039085 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -35,7 +35,7 @@ intcall:
 	movw	%dx, %si
 	movw	%sp, %di
 	movw	$11, %cx
-	rep; movsd
+	rep; movsl
 
 	/* Pop full state from the stack */
 	popal
@@ -70,7 +70,7 @@ intcall:
 	jz	4f
 	movw	%sp, %si
 	movw	$11, %cx
-	rep; movsd
+	rep; movsl
 4:	addw	$44, %sp
 
 	/* Restore state and return */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 78b308f2f..e6c258bf9 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1500,13 +1500,13 @@ ENTRY(async_page_fault)
 END(async_page_fault)
 #endif
 
-ENTRY(rewind_stack_do_exit)
+ENTRY(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
 	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
 
-	call	do_exit
+	call	make_task_dead
 1:	jmp 1b
-END(rewind_stack_do_exit)
+END(rewind_stack_and_make_dead)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 3f418aede..ef693d368 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1759,10 +1759,10 @@ END(nmi)
 ENTRY(ignore_sysret)
 	UNWIND_HINT_EMPTY
 	mov	$-ENOSYS, %eax
-	sysret
+	sysretl
 END(ignore_sysret)
 
-ENTRY(rewind_stack_do_exit)
+ENTRY(rewind_stack_and_make_dead)
 	UNWIND_HINT_FUNC
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
@@ -1771,5 +1771,5 @@ ENTRY(rewind_stack_do_exit)
 	leaq	-PTREGS_SIZE(%rax), %rsp
 	UNWIND_HINT_REGS
 
-	call	do_exit
-END(rewind_stack_do_exit)
+	call	make_task_dead
+END(rewind_stack_and_make_dead)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 2bf1170f7..34da6d27d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2699,6 +2699,7 @@ static bool hswep_has_limit_sbox(unsigned int device)
 		return false;
 
 	pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4);
+	pci_dev_put(dev);
 	if (!hswep_get_chop(capid4))
 		return true;
 
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 3ebd77770..4cfda3cfa 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -298,6 +298,7 @@ static int load_aout_binary(struct linux_binprm *bprm)
 	set_personality_ia32(false);
 
 	setup_new_exec(bprm);
+	install_exec_creds(bprm);
 
 	regs->cs = __USER32_CS;
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
@@ -314,8 +315,6 @@ static int load_aout_binary(struct linux_binprm *bprm)
 	if (retval < 0)
 		return retval;
 
-	install_exec_creds(bprm);
-
 	if (N_MAGIC(ex) == OMAGIC) {
 		unsigned long text_addr, map_size;
 
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 91a06cef5..8e915e381 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -130,7 +130,7 @@ static inline unsigned int x86_cpuid_family(void)
 int __init microcode_init(void);
 extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
-void reload_early_microcode(void);
+void reload_early_microcode(unsigned int cpu);
 extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
 extern bool initrd_gone;
 void microcode_bsp_resume(void);
@@ -138,7 +138,7 @@ void microcode_bsp_resume(void);
 static inline int __init microcode_init(void)			{ return 0; };
 static inline void __init load_ucode_bsp(void)			{ }
 static inline void load_ucode_ap(void)				{ }
-static inline void reload_early_microcode(void)			{ }
+static inline void reload_early_microcode(unsigned int cpu)	{ }
 static inline void microcode_bsp_resume(void)			{ }
 static inline bool
 get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 5c524d4f7..a645b25ee 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -47,12 +47,12 @@ struct microcode_amd {
 extern void __init load_ucode_amd_bsp(unsigned int family);
 extern void load_ucode_amd_ap(unsigned int family);
 extern int __init save_microcode_in_initrd_amd(unsigned int family);
-void reload_ucode_amd(void);
+void reload_ucode_amd(unsigned int cpu);
 #else
 static inline void __init load_ucode_amd_bsp(unsigned int family) {}
 static inline void load_ucode_amd_ap(unsigned int family) {}
 static inline int __init
 save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
-void reload_ucode_amd(void) {}
+static inline void reload_ucode_amd(unsigned int cpu) {}
 #endif
 #endif /* _ASM_X86_MICROCODE_AMD_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 0bd07699d..847f3f582 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -50,6 +50,10 @@
 #define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
 #define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
 
+/* A mask for bits which the kernel toggles when controlling mitigations */
+#define SPEC_CTRL_MITIGATIONS_MASK	(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
+							| SPEC_CTRL_RRSBA_DIS_S)
+
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
 
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index a671a1145..9177b4354 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
+void cpu_emergency_disable_virtualization(void);
+
 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
 void run_crash_ipi_callback(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 0116b2ee9..4699acd60 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -114,7 +114,21 @@ static inline void cpu_svm_disable(void)
 
 	wrmsrl(MSR_VM_HSAVE_PA, 0);
 	rdmsrl(MSR_EFER, efer);
-	wrmsrl(MSR_EFER, efer & ~EFER_SVME);
+	if (efer & EFER_SVME) {
+		/*
+		 * Force GIF=1 prior to disabling SVM to ensure INIT and NMI
+		 * aren't blocked, e.g. if a fatal error occurred between CLGI
+		 * and STGI.  Note, STGI may #UD if SVM is disabled from NMI
+		 * context between reading EFER and executing STGI.  In that
+		 * case, GIF must already be set, otherwise the NMI would have
+		 * been blocked, so just eat the fault.
+		 */
+		asm_volatile_goto("1: stgi\n\t"
+				  _ASM_EXTABLE(1b, %l[fault])
+				  ::: "memory" : fault);
+fault:
+		wrmsrl(MSR_EFER, efer & ~EFER_SVME);
+	}
 }
 
 /** Makes sure SVM is disabled, if it is supported on the CPU
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e017f64e0..c8979f8cb 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -199,6 +199,15 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		return;
 	}
 #endif
+	/*
+	 * Work around Erratum 1386.  The XSAVES instruction malfunctions in
+	 * certain circumstances on Zen1/2 uarch, and not all parts have had
+	 * updated microcode at the time of writing (March 2023).
+	 *
+	 * Affected parts all have no supervisor XSAVE states, meaning that
+	 * the XSAVEC instruction (which works fine) is equivalent.
+	 */
+	clear_cpu_cap(c, X86_FEATURE_XSAVES);
 }
 
 static void init_amd_k7(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index f1f57acca..680fa070e 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -135,9 +135,17 @@ void __init check_bugs(void)
 	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
 	 * init code as it is not enumerated and depends on the family.
 	 */
-	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+	if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) {
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
+		/*
+		 * Previously running kernel (kexec), may have some controls
+		 * turned ON. Clear them and let the mitigations setup below
+		 * rediscover them based on configuration.
+		 */
+		x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK;
+	}
+
 	/* Select the proper CPU mitigations before patching alternatives: */
 	spectre_v1_select_mitigation();
 	spectre_v2_select_mitigation();
@@ -975,14 +983,18 @@ spectre_v2_parse_user_cmdline(void)
 	return SPECTRE_V2_USER_CMD_AUTO;
 }
 
-static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
+static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode)
 {
-	return mode == SPECTRE_V2_IBRS ||
-	       mode == SPECTRE_V2_EIBRS ||
+	return mode == SPECTRE_V2_EIBRS ||
 	       mode == SPECTRE_V2_EIBRS_RETPOLINE ||
 	       mode == SPECTRE_V2_EIBRS_LFENCE;
 }
 
+static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
+{
+	return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS;
+}
+
 static void __init
 spectre_v2_user_select_mitigation(void)
 {
@@ -1045,12 +1057,19 @@ spectre_v2_user_select_mitigation(void)
 	}
 
 	/*
-	 * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible,
-	 * STIBP is not required.
+	 * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP
+	 * is not required.
+	 *
+	 * Enhanced IBRS also protects against cross-thread branch target
+	 * injection in user-mode as the IBRS bit remains always set which
+	 * implicitly enables cross-thread protections.  However, in legacy IBRS
+	 * mode, the IBRS bit is set only on kernel entry and cleared on return
+	 * to userspace. This disables the implicit cross-thread protection,
+	 * so allow for STIBP to be selected in that case.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
 	    !smt_possible ||
-	    spectre_v2_in_ibrs_mode(spectre_v2_enabled))
+	    spectre_v2_in_eibrs_mode(spectre_v2_enabled))
 		return;
 
 	/*
@@ -1778,6 +1797,8 @@ 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;
@@ -2100,7 +2121,7 @@ static ssize_t mmio_stale_data_show_state(char *buf)
 
 static char *stibp_state(void)
 {
-	if (spectre_v2_in_ibrs_mode(spectre_v2_enabled))
+	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled))
 		return "";
 
 	switch (spectre_v2_user_stibp) {
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index f406e3b85..1125f752f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -585,8 +585,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
+	 * This pairs with the full barrier between the rq->curr update and
+	 * resctrl_sched_in() during context switch.
 	 */
-	barrier();
+	smp_mb();
 
 	/*
 	 * By now, the task's closid and rmid are set. If the task is current
@@ -2140,19 +2142,23 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 			t->closid = to->closid;
 			t->rmid = to->mon.rmid;
 
-#ifdef CONFIG_SMP
 			/*
-			 * This is safe on x86 w/o barriers as the ordering
-			 * of writing to task_cpu() and t->on_cpu is
-			 * reverse to the reading here. The detection is
-			 * inaccurate as tasks might move or schedule
-			 * before the smp function call takes place. In
-			 * such a case the function call is pointless, but
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and resctrl_sched_in()
+			 * during context switch.
+			 */
+			smp_mb();
+
+			/*
+			 * If the task is on a CPU, set the CPU in the mask.
+			 * The detection is inaccurate as tasks might move or
+			 * schedule before the smp function call takes place.
+			 * In such a case the function call is pointless, but
 			 * there is no other side effect.
 			 */
-			if (mask && t->on_cpu)
+			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
 				cpumask_set_cpu(task_cpu(t), mask);
-#endif
 		}
 	}
 	read_unlock(&tasklist_lock);
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 8396c77e9..b33e4fe9d 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -54,7 +54,9 @@ struct cont_desc {
 };
 
 static u32 ucode_new_rev;
-static u8 amd_ucode_patch[PATCH_MAX_SIZE];
+
+/* One blob per node. */
+static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE];
 
 /*
  * Microcode patch container file is prepended to the initrd in cpio
@@ -210,7 +212,7 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p
 	patch	= (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
 #else
 	new_rev = &ucode_new_rev;
-	patch	= &amd_ucode_patch;
+	patch	= &amd_ucode_patch[0];
 #endif
 
 	desc.cpuid_1_eax = cpuid_1_eax;
@@ -329,8 +331,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 	apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false);
 }
 
-static enum ucode_state
-load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
+static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
 
 int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 {
@@ -348,19 +349,19 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 	if (!desc.mc)
 		return -EINVAL;
 
-	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
+	ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
 	if (ret > UCODE_UPDATED)
 		return -EINVAL;
 
 	return 0;
 }
 
-void reload_ucode_amd(void)
+void reload_ucode_amd(unsigned int cpu)
 {
-	struct microcode_amd *mc;
 	u32 rev, dummy;
+	struct microcode_amd *mc;
 
-	mc = (struct microcode_amd *)amd_ucode_patch;
+	mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)];
 
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
@@ -698,9 +699,10 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 	return UCODE_OK;
 }
 
-static enum ucode_state
-load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
+static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
+	struct cpuinfo_x86 *c;
+	unsigned int nid, cpu;
 	struct ucode_patch *p;
 	enum ucode_state ret;
 
@@ -713,22 +715,22 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 		return ret;
 	}
 
-	p = find_patch(0);
-	if (!p) {
-		return ret;
-	} else {
-		if (boot_cpu_data.microcode >= p->patch_id)
-			return ret;
+	for_each_node(nid) {
+		cpu = cpumask_first(cpumask_of_node(nid));
+		c = &cpu_data(cpu);
 
-		ret = UCODE_NEW;
-	}
+		p = find_patch(cpu);
+		if (!p)
+			continue;
 
-	/* save BSP's matching patch for early load */
-	if (!save)
-		return ret;
+		if (c->microcode >= p->patch_id)
+			continue;
 
-	memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
-	memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+		ret = UCODE_NEW;
+
+		memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE);
+		memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+	}
 
 	return ret;
 }
@@ -754,12 +756,11 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	enum ucode_state ret = UCODE_NFOUND;
 	const struct firmware *fw;
 
 	/* reload ucode container only on the boot cpu */
-	if (!refresh_fw || !bsp)
+	if (!refresh_fw)
 		return UCODE_OK;
 
 	if (c->x86 >= 0x15)
@@ -776,7 +777,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 985ef98c8..963b98971 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -326,7 +326,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
 #endif
 }
 
-void reload_early_microcode(void)
+void reload_early_microcode(unsigned int cpu)
 {
 	int vendor, family;
 
@@ -340,7 +340,7 @@ void reload_early_microcode(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (family >= 0x10)
-			reload_ucode_amd();
+			reload_ucode_amd(cpu);
 		break;
 	default:
 		break;
@@ -783,7 +783,7 @@ void microcode_bsp_resume(void)
 	if (uci->valid && uci->mc)
 		microcode_ops->apply_microcode(cpu);
 	else if (!uci->mc)
-		reload_early_microcode();
+		reload_early_microcode(cpu);
 }
 
 static struct syscore_ops mc_syscore_ops = {
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 3aa0e5a45..31ad79a0c 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -662,7 +662,6 @@ void load_ucode_intel_ap(void)
 	else
 		iup = &intel_ucode_patch;
 
-reget:
 	if (!*iup) {
 		patch = __load_ucode_intel(&uci);
 		if (!patch)
@@ -673,12 +672,7 @@ reget:
 
 	uci.mc = *iup;
 
-	if (apply_microcode_early(&uci, true)) {
-		/* Mixed-silicon system? Try to refetch the proper patch: */
-		*iup = NULL;
-
-		goto reget;
-	}
+	apply_microcode_early(&uci, true);
 }
 
 static struct microcode_intel *find_patch(struct ucode_cpu_info *uci)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 91b3483e5..e40bb50c5 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -35,7 +35,6 @@
 #include <linux/kdebug.h>
 #include <asm/cpu.h>
 #include <asm/reboot.h>
-#include <asm/virtext.h>
 #include <asm/intel_pt.h>
 
 /* Used while preparing memory map entries for second kernel */
@@ -86,15 +85,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 	 */
 	cpu_crash_vmclear_loaded_vmcss();
 
-	/* Disable VMX or SVM if needed.
-	 *
-	 * We need to disable virtualization on all CPUs.
-	 * Having VMX or SVM enabled on any CPU may break rebooting
-	 * after the kdump kernel has finished its task.
-	 */
-	cpu_emergency_vmxoff();
-	cpu_emergency_svm_disable();
-
 	/*
 	 * Disable Intel PT to stop its logging
 	 */
@@ -153,12 +143,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	 */
 	cpu_crash_vmclear_loaded_vmcss();
 
-	/* Booting kdump kernel with VMX or SVM enabled won't work,
-	 * because (among other limitations) we can't disable paging
-	 * with the virt flags.
-	 */
-	cpu_emergency_vmxoff();
-	cpu_emergency_svm_disable();
+	cpu_emergency_disable_virtualization();
 
 	/*
 	 * Disable Intel PT to stop its logging
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2b5886401..2b17a5cec 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -326,7 +326,7 @@ unsigned long oops_begin(void)
 }
 NOKPROBE_SYMBOL(oops_begin);
 
-void __noreturn rewind_stack_do_exit(int signr);
+void __noreturn rewind_stack_and_make_dead(int signr);
 
 void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 {
@@ -361,7 +361,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 	 * reuse the task stack and that existing poisons are invalid.
 	 */
 	kasan_unpoison_task_stack(current);
-	rewind_stack_do_exit(signr);
+	rewind_stack_and_make_dead(signr);
 }
 NOKPROBE_SYMBOL(oops_end);
 
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index fe522691a..8821d0ab0 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq)
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
 	irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+	irq_set_status_flags(irq, IRQ_LEVEL);
 	enable_irq(irq);
 	lapic_assign_legacy_vector(irq, true);
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a0693b71c..f2c215e1f 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -72,8 +72,10 @@ void __init init_ISA_irqs(void)
 
 	legacy_pic->init(0);
 
-	for (i = 0; i < nr_legacy_irqs(); i++)
+	for (i = 0; i < nr_legacy_irqs(); i++) {
 		irq_set_chip_and_handler(i, chip, handle_level_irq);
+		irq_set_status_flags(i, IRQ_LEVEL);
+	}
 }
 
 void __init init_IRQ(void)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 544bd41a5..36b5a493e 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -56,8 +56,8 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
 		/* This function only handles jump-optimized kprobe */
 		if (kp && kprobe_optimized(kp)) {
 			op = container_of(kp, struct optimized_kprobe, kp);
-			/* If op->list is not empty, op is under optimizing */
-			if (list_empty(&op->list))
+			/* If op is optimized or under unoptimizing */
+			if (list_empty(&op->list) || optprobe_queued_unopt(op))
 				goto found;
 		}
 	}
@@ -328,7 +328,7 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op)
 
 	for (i = 1; i < op->optinsn.size; i++) {
 		p = get_kprobe(op->kp.addr + i);
-		if (p && !kprobe_disabled(p))
+		if (p && !kprobe_disarmed(p))
 			return -EEXIST;
 	}
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index b0f3a996d..444b8a691 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -536,33 +536,29 @@ static inline void kb_wait(void)
 	}
 }
 
-static void vmxoff_nmi(int cpu, struct pt_regs *regs)
-{
-	cpu_emergency_vmxoff();
-}
+static inline void nmi_shootdown_cpus_on_restart(void);
 
-/* Use NMIs as IPIs to tell all CPUs to disable virtualization */
-static void emergency_vmx_disable_all(void)
+static void emergency_reboot_disable_virtualization(void)
 {
 	/* Just make sure we won't change CPUs while doing this */
 	local_irq_disable();
 
 	/*
-	 * Disable VMX on all CPUs before rebooting, otherwise we risk hanging
-	 * the machine, because the CPU blocks INIT when it's in VMX root.
+	 * Disable virtualization on all CPUs before rebooting to avoid hanging
+	 * the system, as VMX and SVM block INIT when running in the host.
 	 *
 	 * We can't take any locks and we may be on an inconsistent state, so
-	 * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt.
+	 * use NMIs as IPIs to tell the other CPUs to disable VMX/SVM and halt.
 	 *
-	 * Do the NMI shootdown even if VMX if off on _this_ CPU, as that
-	 * doesn't prevent a different CPU from being in VMX root operation.
+	 * Do the NMI shootdown even if virtualization is off on _this_ CPU, as
+	 * other CPUs may have virtualization enabled.
 	 */
-	if (cpu_has_vmx()) {
-		/* Safely force _this_ CPU out of VMX root operation. */
-		__cpu_emergency_vmxoff();
+	if (cpu_has_vmx() || cpu_has_svm(NULL)) {
+		/* Safely force _this_ CPU out of VMX/SVM operation. */
+		cpu_emergency_disable_virtualization();
 
-		/* Halt and exit VMX root operation on the other CPUs. */
-		nmi_shootdown_cpus(vmxoff_nmi);
+		/* Disable VMX/SVM and halt on other CPUs. */
+		nmi_shootdown_cpus_on_restart();
 
 	}
 }
@@ -599,7 +595,7 @@ static void native_machine_emergency_restart(void)
 	unsigned short mode;
 
 	if (reboot_emergency)
-		emergency_vmx_disable_all();
+		emergency_reboot_disable_virtualization();
 
 	tboot_shutdown(TB_SHUTDOWN_REBOOT);
 
@@ -804,6 +800,17 @@ void machine_crash_shutdown(struct pt_regs *regs)
 /* This is the CPU performing the emergency shutdown work. */
 int crashing_cpu = -1;
 
+/*
+ * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during
+ * reboot.  VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if
+ * GIF=0, i.e. if the crash occurred between CLGI and STGI.
+ */
+void cpu_emergency_disable_virtualization(void)
+{
+	cpu_emergency_vmxoff();
+	cpu_emergency_svm_disable();
+}
+
 #if defined(CONFIG_SMP)
 
 static nmi_shootdown_cb shootdown_callback;
@@ -826,7 +833,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 		return NMI_HANDLED;
 	local_irq_disable();
 
-	shootdown_callback(cpu, regs);
+	if (shootdown_callback)
+		shootdown_callback(cpu, regs);
+
+	/*
+	 * Prepare the CPU for reboot _after_ invoking the callback so that the
+	 * callback can safely use virtualization instructions, e.g. VMCLEAR.
+	 */
+	cpu_emergency_disable_virtualization();
 
 	atomic_dec(&waiting_for_crash_ipi);
 	/* Assume hlt works */
@@ -842,18 +856,32 @@ static void smp_send_nmi_allbutself(void)
 	apic->send_IPI_allbutself(NMI_VECTOR);
 }
 
-/*
- * Halt all other CPUs, calling the specified function on each of them
+/**
+ * nmi_shootdown_cpus - Stop other CPUs via NMI
+ * @callback:	Optional callback to be invoked from the NMI handler
+ *
+ * The NMI handler on the remote CPUs invokes @callback, if not
+ * NULL, first and then disables virtualization to ensure that
+ * INIT is recognized during reboot.
  *
- * This function can be used to halt all other CPUs on crash
- * or emergency reboot time. The function passed as parameter
- * will be called inside a NMI handler on all CPUs.
+ * nmi_shootdown_cpus() can only be invoked once. After the first
+ * invocation all other CPUs are stuck in crash_nmi_callback() and
+ * cannot respond to a second NMI.
  */
 void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 {
 	unsigned long msecs;
+
 	local_irq_disable();
 
+	/*
+	 * Avoid certain doom if a shootdown already occurred; re-registering
+	 * the NMI handler will cause list corruption, modifying the callback
+	 * will do who knows what, etc...
+	 */
+	if (WARN_ON_ONCE(crash_ipi_issued))
+		return;
+
 	/* Make a note of crashing cpu. Will be used in NMI callback. */
 	crashing_cpu = safe_smp_processor_id();
 
@@ -881,7 +909,17 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 		msecs--;
 	}
 
-	/* Leave the nmi callback set */
+	/*
+	 * Leave the nmi callback set, shootdown is a one-time thing.  Clearing
+	 * the callback could result in a NULL pointer dereference if a CPU
+	 * (finally) responds after the timeout expires.
+	 */
+}
+
+static inline void nmi_shootdown_cpus_on_restart(void)
+{
+	if (!crash_ipi_issued)
+		nmi_shootdown_cpus(NULL);
 }
 
 /*
@@ -911,6 +949,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 	/* No other CPUs to shoot down */
 }
 
+static inline void nmi_shootdown_cpus_on_restart(void) { }
+
 void run_crash_ipi_callback(struct pt_regs *regs)
 {
 }
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index b2b87b91f..c94ed0b37 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -33,7 +33,7 @@
 #include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 #include <asm/kexec.h>
-#include <asm/virtext.h>
+#include <asm/reboot.h>
 
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
@@ -163,7 +163,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
 		return NMI_HANDLED;
 
-	cpu_emergency_vmxoff();
+	cpu_emergency_disable_virtualization();
 	stop_this_cpu(NULL);
 
 	return NMI_HANDLED;
@@ -176,7 +176,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 asmlinkage __visible void smp_reboot_interrupt(void)
 {
 	ipi_entering_ack_irq();
-	cpu_emergency_vmxoff();
+	cpu_emergency_disable_virtualization();
 	stop_this_cpu(NULL);
 	irq_exit();
 }
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index 897da526e..5bc0fedb3 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -265,6 +265,22 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = {
 					"Lenovo ideapad D330-10IGM"),
 		},
 	},
+	{
+		/* Lenovo IdeaPad Duet 3 10IGL5 with 1200x1920 portrait screen */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"IdeaPad Duet 3 10IGL5"),
+		},
+	},
+	{
+		/* Lenovo Yoga Book X91F / X91L */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			/* Non exact match to match F + L versions */
+			DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"),
+		},
+	},
 	{},
 };
 
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index ae9e806a1..3b87bca02 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -735,8 +735,9 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 	switch (opc1) {
 	case 0xeb:	/* jmp 8 */
 	case 0xe9:	/* jmp 32 */
-	case 0x90:	/* prefix* + nop; same as jmp with .offs = 0 */
 		break;
+	case 0x90:	/* prefix* + nop; same as jmp with .offs = 0 */
+		goto setup;
 
 	case 0xe8:	/* call relative */
 		branch_clear_offset(auprobe, insn);
@@ -765,6 +766,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 			return -ENOTSUPP;
 	}
 
+setup:
 	auprobe->branch.opc1 = opc1;
 	auprobe->branch.ilen = insn->length;
 	auprobe->branch.offs = insn->immediate.value;
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index dc4f2fdf5..13fd54de5 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -16,7 +16,7 @@ kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
 			   hyperv.o page_track.o debugfs.o
 
-kvm-intel-y		+= vmx.o pmu_intel.o
+kvm-intel-y		+= vmx/vmx.o vmx/pmu_intel.o
 kvm-amd-y		+= svm.o pmu_amd.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 611f9e60f..611f9e60f 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9bb696d73..265e70b0e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2062,6 +2062,12 @@ static inline bool nested_cpu_has_shadow_vmcs(struct vmcs12 *vmcs12)
 	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS);
 }
 
+static inline bool nested_cpu_has_save_preemption_timer(struct vmcs12 *vmcs12)
+{
+	return vmcs12->vm_exit_controls &
+	    VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+}
+
 static inline bool is_nmi(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -4734,9 +4740,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		}
 	}
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, host_xss);
-
 	return 0;
 }
 
@@ -5518,18 +5521,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
 
-	if (var->unusable || !var->present)
-		ar = 1 << 16;
-	else {
-		ar = var->type & 15;
-		ar |= (var->s & 1) << 4;
-		ar |= (var->dpl & 3) << 5;
-		ar |= (var->present & 1) << 7;
-		ar |= (var->avl & 1) << 12;
-		ar |= (var->l & 1) << 13;
-		ar |= (var->db & 1) << 14;
-		ar |= (var->g & 1) << 15;
-	}
+	ar = var->type & 15;
+	ar |= (var->s & 1) << 4;
+	ar |= (var->dpl & 3) << 5;
+	ar |= (var->present & 1) << 7;
+	ar |= (var->avl & 1) << 12;
+	ar |= (var->l & 1) << 13;
+	ar |= (var->db & 1) << 14;
+	ar |= (var->g & 1) << 15;
+	ar |= (var->unusable || !var->present) << 16;
 
 	return ar;
 }
@@ -7951,6 +7951,9 @@ static __init int hardware_setup(void)
 		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
 	}
 
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		rdmsrl(MSR_IA32_XSS, host_xss);
+
 	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
 		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
@@ -12609,6 +12612,10 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (!nested_cpu_has_preemption_timer(vmcs12) &&
+	    nested_cpu_has_save_preemption_timer(vmcs12))
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_pml_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
@@ -12745,7 +12752,7 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				  u32 *exit_qual)
 {
-	bool ia32e;
+	bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);
 
 	*exit_qual = ENTRY_FAIL_DEFAULT;
 
@@ -12758,6 +12765,13 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		return 1;
 	}
 
+	if ((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG)
+		return 1;
+
+	if ((ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
+	    (ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
+		return 1;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -12769,7 +12783,6 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 */
 	if (to_vmx(vcpu)->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
-		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
 		if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) ||
 		    ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) ||
 		    ((vmcs12->guest_cr0 & X86_CR0_PG) &&
diff --git a/arch/x86/kvm/vmx_evmcs.h b/arch/x86/kvm/vmx/vmx_evmcs.h
index 210a88409..210a88409 100644
--- a/arch/x86/kvm/vmx_evmcs.h
+++ b/arch/x86/kvm/vmx/vmx_evmcs.h
diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx/vmx_shadow_fields.h
index cd0c75f6d..cd0c75f6d 100644
--- a/arch/x86/kvm/vmx_shadow_fields.h
+++ b/arch/x86/kvm/vmx/vmx_shadow_fields.h
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8fe615df8..ff7ec9b50 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3637,12 +3637,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
 {
 	unsigned long val;
 
+	memset(dbgregs, 0, sizeof(*dbgregs));
 	memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
 	kvm_get_dr(vcpu, 6, &val);
 	dbgregs->dr6 = val;
 	dbgregs->dr7 = vcpu->arch.dr7;
-	dbgregs->flags = 0;
-	memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
 }
 
 static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index 33147fef3..f1024b51c 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -22,6 +22,6 @@
  */
 ENTRY(__iowrite32_copy)
 	movl %edx,%ecx
-	rep movsd
+	rep movsl
 	ret
 ENDPROC(__iowrite32_copy)
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 650d5a6ca..832c899b7 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -563,7 +563,8 @@ void __init sme_enable(struct boot_params *bp)
 	cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
 				     ((u64)bp->ext_cmd_line_ptr << 32));
 
-	cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer));
+	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0)
+		return;
 
 	if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
 		sme_me_mask = me_mask;
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 76959a7d8..94291e0dd 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -7,6 +7,7 @@
 #include <linux/dmi.h>
 #include <linux/pci.h>
 #include <linux/vgaarb.h>
+#include <asm/amd_nb.h>
 #include <asm/hpet.h>
 #include <asm/pci_x86.h>
 
@@ -824,3 +825,23 @@ static void rs690_fix_64bit_dma(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma);
 
 #endif
+
+#ifdef CONFIG_AMD_NB
+
+#define AMD_15B8_RCC_DEV2_EPF0_STRAP2                                  0x10136008
+#define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK       0x00000080L
+
+static void quirk_clear_strap_no_soft_reset_dev2_f0(struct pci_dev *dev)
+{
+	u32 data;
+
+	if (!amd_smn_read(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, &data)) {
+		data &= ~AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK;
+		if (amd_smn_write(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, data))
+			pci_err(dev, "Failed to write data 0x%x\n", data);
+	} else {
+		pci_err(dev, "Failed to read data\n");
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b8, quirk_clear_strap_no_soft_reset_dev2_f0);
+#endif
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 2cfa0caef..002f7a01a 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -25,7 +25,7 @@ KCOV_INSTRUMENT := n
 # make up the standalone purgatory.ro
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
-PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
+PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0
 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
@@ -56,6 +56,9 @@ CFLAGS_sha256.o			+= $(PURGATORY_CFLAGS)
 CFLAGS_REMOVE_string.o		+= $(PURGATORY_CFLAGS_REMOVE)
 CFLAGS_string.o			+= $(PURGATORY_CFLAGS)
 
+AFLAGS_REMOVE_setup-x86_$(BITS).o	+= -g -Wa,-gdwarf-2
+AFLAGS_REMOVE_entry64.o			+= -g -Wa,-gdwarf-2
+
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
 
diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
index 7c441b59d..be99ff25c 100644
--- a/arch/x86/um/vdso/um_vdso.c
+++ b/arch/x86/um/vdso/um_vdso.c
@@ -20,8 +20,10 @@ int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
-		"0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+	asm("syscall"
+		: "=a" (ret)
+		: "0" (__NR_clock_gettime), "D" (clock), "S" (ts)
+		: "rcx", "r11", "memory");
 
 	return ret;
 }
@@ -32,8 +34,10 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
-		"0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	asm("syscall"
+		: "=a" (ret)
+		: "0" (__NR_gettimeofday), "D" (tv), "S" (tz)
+		: "rcx", "r11", "memory");
 
 	return ret;
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7a43b2ae1..a1cc855c5 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -32,30 +32,30 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 
 void xen_smp_intr_free(unsigned int cpu)
 {
+	kfree(per_cpu(xen_resched_irq, cpu).name);
+	per_cpu(xen_resched_irq, cpu).name = NULL;
 	if (per_cpu(xen_resched_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL);
 		per_cpu(xen_resched_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_resched_irq, cpu).name);
-		per_cpu(xen_resched_irq, cpu).name = NULL;
 	}
+	kfree(per_cpu(xen_callfunc_irq, cpu).name);
+	per_cpu(xen_callfunc_irq, cpu).name = NULL;
 	if (per_cpu(xen_callfunc_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu).irq, NULL);
 		per_cpu(xen_callfunc_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_callfunc_irq, cpu).name);
-		per_cpu(xen_callfunc_irq, cpu).name = NULL;
 	}
+	kfree(per_cpu(xen_debug_irq, cpu).name);
+	per_cpu(xen_debug_irq, cpu).name = NULL;
 	if (per_cpu(xen_debug_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu).irq, NULL);
 		per_cpu(xen_debug_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_debug_irq, cpu).name);
-		per_cpu(xen_debug_irq, cpu).name = NULL;
 	}
+	kfree(per_cpu(xen_callfuncsingle_irq, cpu).name);
+	per_cpu(xen_callfuncsingle_irq, cpu).name = NULL;
 	if (per_cpu(xen_callfuncsingle_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu).irq,
 				       NULL);
 		per_cpu(xen_callfuncsingle_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_callfuncsingle_irq, cpu).name);
-		per_cpu(xen_callfuncsingle_irq, cpu).name = NULL;
 	}
 }
 
@@ -65,6 +65,7 @@ int xen_smp_intr_init(unsigned int cpu)
 	char *resched_name, *callfunc_name, *debug_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+	per_cpu(xen_resched_irq, cpu).name = resched_name;
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
 				    cpu,
 				    xen_reschedule_interrupt,
@@ -74,9 +75,9 @@ int xen_smp_intr_init(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_resched_irq, cpu).irq = rc;
-	per_cpu(xen_resched_irq, cpu).name = resched_name;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
 				    cpu,
 				    xen_call_function_interrupt,
@@ -86,18 +87,21 @@ int xen_smp_intr_init(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_callfunc_irq, cpu).irq = rc;
-	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 
-	debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
-	rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
-				     IRQF_PERCPU | IRQF_NOBALANCING,
-				     debug_name, NULL);
-	if (rc < 0)
-		goto fail;
-	per_cpu(xen_debug_irq, cpu).irq = rc;
-	per_cpu(xen_debug_irq, cpu).name = debug_name;
+	if (!xen_fifo_events) {
+		debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+		per_cpu(xen_debug_irq, cpu).name = debug_name;
+		rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
+					     xen_debug_interrupt,
+					     IRQF_PERCPU | IRQF_NOBALANCING,
+					     debug_name, NULL);
+		if (rc < 0)
+			goto fail;
+		per_cpu(xen_debug_irq, cpu).irq = rc;
+	}
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
 				    cpu,
 				    xen_call_function_single_interrupt,
@@ -107,7 +111,6 @@ int xen_smp_intr_init(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_callfuncsingle_irq, cpu).irq = rc;
-	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 
 	return 0;
 
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index e8248e8a0..75807c2a1 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -94,18 +94,18 @@ asmlinkage __visible void cpu_bringup_and_idle(void)
 
 void xen_smp_intr_free_pv(unsigned int cpu)
 {
+	kfree(per_cpu(xen_irq_work, cpu).name);
+	per_cpu(xen_irq_work, cpu).name = NULL;
 	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
 		per_cpu(xen_irq_work, cpu).irq = -1;
-		kfree(per_cpu(xen_irq_work, cpu).name);
-		per_cpu(xen_irq_work, cpu).name = NULL;
 	}
 
+	kfree(per_cpu(xen_pmu_irq, cpu).name);
+	per_cpu(xen_pmu_irq, cpu).name = NULL;
 	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
 		per_cpu(xen_pmu_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_pmu_irq, cpu).name);
-		per_cpu(xen_pmu_irq, cpu).name = NULL;
 	}
 }
 
@@ -115,6 +115,7 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	char *callfunc_name, *pmu_name;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
+	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
 				    cpu,
 				    xen_irq_work_interrupt,
@@ -124,10 +125,10 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_irq_work, cpu).irq = rc;
-	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 
 	if (is_xen_pmu) {
 		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
+		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
 		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
 					     xen_pmu_irq_handler,
 					     IRQF_PERCPU|IRQF_NOBALANCING,
@@ -135,7 +136,6 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 		if (rc < 0)
 			goto fail;
 		per_cpu(xen_pmu_irq, cpu).irq = rc;
-		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
 	}
 
 	return 0;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 6fffb86a3..e6cf1b430 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -83,6 +83,7 @@ void xen_init_lock_cpu(int cpu)
 	     cpu, per_cpu(lock_kicker_irq, cpu));
 
 	name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
+	per_cpu(irq_name, cpu) = name;
 	irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
 				     cpu,
 				     dummy_handler,
@@ -93,7 +94,6 @@ void xen_init_lock_cpu(int cpu)
 	if (irq >= 0) {
 		disable_irq(irq); /* make sure it's never delivered */
 		per_cpu(lock_kicker_irq, cpu) = irq;
-		per_cpu(irq_name, cpu) = name;
 	}
 
 	printk("cpu %d spinlock event irq %d\n", cpu, irq);
@@ -106,6 +106,8 @@ void xen_uninit_lock_cpu(int cpu)
 	if (!xen_pvspin)
 		return;
 
+	kfree(per_cpu(irq_name, cpu));
+	per_cpu(irq_name, cpu) = NULL;
 	/*
 	 * When booting the kernel with 'mitigations=auto,nosmt', the secondary
 	 * CPUs are not activated, and lock_kicker_irq is not initialized.
@@ -116,8 +118,6 @@ void xen_uninit_lock_cpu(int cpu)
 
 	unbind_from_irqhandler(irq, NULL);
 	per_cpu(lock_kicker_irq, cpu) = -1;
-	kfree(per_cpu(irq_name, cpu));
-	per_cpu(irq_name, cpu) = NULL;
 }
 
 PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 2f111f47b..9faec8543 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -30,6 +30,8 @@ extern struct start_info *xen_start_info;
 extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
+extern bool xen_fifo_events;
+
 void xen_setup_mfn_list_list(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);