Merging upstream version 4.19.289.

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

16 files changed, 229 insertions, 97 deletions

diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index ef5a9cc66..a4c5fb92b 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -114,66 +114,78 @@ typedef unsigned int addr_t;
 
 static inline u8 rdfs8(addr_t addr)
 {
+	u8 *ptr = (u8 *)absolute_pointer(addr);
 	u8 v;
-	asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+	asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*ptr));
 	return v;
 }
 static inline u16 rdfs16(addr_t addr)
 {
+	u16 *ptr = (u16 *)absolute_pointer(addr);
 	u16 v;
-	asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr));
+	asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*ptr));
 	return v;
 }
 static inline u32 rdfs32(addr_t addr)
 {
+	u32 *ptr = (u32 *)absolute_pointer(addr);
 	u32 v;
-	asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr));
+	asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*ptr));
 	return v;
 }
 
 static inline void wrfs8(u8 v, addr_t addr)
 {
-	asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
+	u8 *ptr = (u8 *)absolute_pointer(addr);
+	asm volatile("movb %1,%%fs:%0" : "+m" (*ptr) : "qi" (v));
 }
 static inline void wrfs16(u16 v, addr_t addr)
 {
-	asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
+	u16 *ptr = (u16 *)absolute_pointer(addr);
+	asm volatile("movw %1,%%fs:%0" : "+m" (*ptr) : "ri" (v));
 }
 static inline void wrfs32(u32 v, addr_t addr)
 {
-	asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
+	u32 *ptr = (u32 *)absolute_pointer(addr);
+	asm volatile("movl %1,%%fs:%0" : "+m" (*ptr) : "ri" (v));
 }
 
 static inline u8 rdgs8(addr_t addr)
 {
+	u8 *ptr = (u8 *)absolute_pointer(addr);
 	u8 v;
-	asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+	asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*ptr));
 	return v;
 }
 static inline u16 rdgs16(addr_t addr)
 {
+	u16 *ptr = (u16 *)absolute_pointer(addr);
 	u16 v;
-	asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr));
+	asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*ptr));
 	return v;
 }
 static inline u32 rdgs32(addr_t addr)
 {
+	u32 *ptr = (u32 *)absolute_pointer(addr);
 	u32 v;
-	asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr));
+	asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*ptr));
 	return v;
 }
 
 static inline void wrgs8(u8 v, addr_t addr)
 {
-	asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
+	u8 *ptr = (u8 *)absolute_pointer(addr);
+	asm volatile("movb %1,%%gs:%0" : "+m" (*ptr) : "qi" (v));
 }
 static inline void wrgs16(u16 v, addr_t addr)
 {
-	asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
+	u16 *ptr = (u16 *)absolute_pointer(addr);
+	asm volatile("movw %1,%%gs:%0" : "+m" (*ptr) : "ri" (v));
 }
 static inline void wrgs32(u32 v, addr_t addr)
 {
-	asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
+	u32 *ptr = (u32 *)absolute_pointer(addr);
+	asm volatile("movl %1,%%gs:%0" : "+m" (*ptr) : "ri" (v));
 }
 
 /* Note: these only return true/false, not a signed return value! */
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index 9bcea386d..98b4ff1c5 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -34,7 +34,7 @@ static void copy_boot_params(void)
 		u16 cl_offset;
 	};
 	const struct old_cmdline * const oldcmd =
-		(const struct old_cmdline *)OLD_CL_ADDRESS;
+		absolute_pointer(OLD_CL_ADDRESS);
 
 	BUILD_BUG_ON(sizeof boot_params != 4096);
 	memcpy(&boot_params.hdr, &hdr, sizeof hdr);
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 1f2f52a34..ccf07426a 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -74,6 +74,11 @@
 #define	INTEL_FAM6_LAKEFIELD		0x8A
 #define INTEL_FAM6_ALDERLAKE		0x97
 #define INTEL_FAM6_ALDERLAKE_L		0x9A
+#define INTEL_FAM6_ALDERLAKE_N		0xBE
+
+#define INTEL_FAM6_RAPTORLAKE		0xB7
+#define INTEL_FAM6_RAPTORLAKE_P		0xBA
+#define INTEL_FAM6_RAPTORLAKE_S		0xBF
 
 /* "Small Core" Processors (Atom) */
 
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 8e915e381..b675db12a 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 #include <linux/earlycpio.h>
 #include <linux/initrd.h>
+#include <asm/microcode_amd.h>
 
 struct ucode_patch {
 	struct list_head plist;
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index a645b25ee..403a8e76b 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -48,11 +48,13 @@ 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(unsigned int cpu);
+extern void amd_check_microcode(void);
 #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; }
 static inline void reload_ucode_amd(unsigned int cpu) {}
+static inline void amd_check_microcode(void) {}
 #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 847f3f582..d9c6603dc 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -407,6 +407,7 @@
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE	BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT)
+#define MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT 9
 
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 926939978..9318fe7d8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -403,10 +403,9 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 		if (vector && !eilvt_entry_is_changeable(vector, new))
 			/* may not change if vectors are different */
 			return rsvd;
-		rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
-	} while (rsvd != new);
+	} while (!atomic_try_cmpxchg(&eilvt_offsets[offset], &rsvd, new));
 
-	rsvd &= ~APIC_EILVT_MASKED;
+	rsvd = new & ~APIC_EILVT_MASKED;
 	if (rsvd && rsvd != vector)
 		pr_info("LVT offset %d assigned for vector 0x%02x\n",
 			offset, rsvd);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 677508baf..af59aa9c5 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2449,17 +2449,21 @@ static int io_apic_get_redir_entries(int ioapic)
 
 unsigned int arch_dynirq_lower_bound(unsigned int from)
 {
+	unsigned int ret;
+
 	/*
 	 * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use
 	 * gsi_top if ioapic_dynirq_base hasn't been initialized yet.
 	 */
-	if (!ioapic_initialized)
-		return gsi_top;
+	ret = ioapic_dynirq_base ? : gsi_top;
+
 	/*
-	 * For DT enabled machines ioapic_dynirq_base is irrelevant and not
-	 * updated. So simply return @from if ioapic_dynirq_base == 0.
+	 * For DT enabled machines ioapic_dynirq_base is irrelevant and
+	 * always 0. gsi_top can be 0 if there is no IO/APIC registered.
+	 * 0 is an invalid interrupt number for dynamic allocations. Return
+	 * @from instead.
 	 */
-	return ioapic_dynirq_base ? : from;
+	return ret ? : from;
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8e70c2ba2..fb1776755 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -102,7 +102,10 @@ static void init_x2apic_ldr(void)
 
 static int x2apic_phys_probe(void)
 {
-	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
+	if (!x2apic_mode)
+		return 0;
+
+	if (x2apic_phys || x2apic_fadt_phys())
 		return 1;
 
 	return apic == &apic_x2apic_phys;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c8979f8cb..256f2c612 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -23,11 +23,6 @@
 
 #include "cpu.h"
 
-static const int amd_erratum_383[];
-static const int amd_erratum_400[];
-static const int amd_erratum_1054[];
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
-
 /*
  * nodes_per_socket: Stores the number of nodes per socket.
  * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
@@ -35,6 +30,78 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
  */
 static u32 nodes_per_socket = 1;
 
+/*
+ * AMD errata checking
+ *
+ * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
+ * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
+ * have an OSVW id assigned, which it takes as first argument. Both take a
+ * variable number of family-specific model-stepping ranges created by
+ * AMD_MODEL_RANGE().
+ *
+ * Example:
+ *
+ * const int amd_erratum_319[] =
+ *	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
+ *			   AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
+ *			   AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
+ */
+
+#define AMD_LEGACY_ERRATUM(...)		{ -1, __VA_ARGS__, 0 }
+#define AMD_OSVW_ERRATUM(osvw_id, ...)	{ osvw_id, __VA_ARGS__, 0 }
+#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
+	((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
+#define AMD_MODEL_RANGE_FAMILY(range)	(((range) >> 24) & 0xff)
+#define AMD_MODEL_RANGE_START(range)	(((range) >> 12) & 0xfff)
+#define AMD_MODEL_RANGE_END(range)	((range) & 0xfff)
+
+static const int amd_erratum_400[] =
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
+
+static const int amd_erratum_383[] =
+	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
+
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+
+static const int amd_zenbleed[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf),
+			   AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf),
+			   AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
+
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
+{
+	int osvw_id = *erratum++;
+	u32 range;
+	u32 ms;
+
+	if (osvw_id >= 0 && osvw_id < 65536 &&
+	    cpu_has(cpu, X86_FEATURE_OSVW)) {
+		u64 osvw_len;
+
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
+		if (osvw_id < osvw_len) {
+			u64 osvw_bits;
+
+			rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
+			    osvw_bits);
+			return osvw_bits & (1ULL << (osvw_id & 0x3f));
+		}
+	}
+
+	/* OSVW unavailable or ID unknown, match family-model-stepping range */
+	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
+	while ((range = *erratum++))
+		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
+		    (ms >= AMD_MODEL_RANGE_START(range)) &&
+		    (ms <= AMD_MODEL_RANGE_END(range)))
+			return true;
+
+	return false;
+}
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -909,6 +976,47 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 	}
 }
 
+static bool cpu_has_zenbleed_microcode(void)
+{
+	u32 good_rev = 0;
+
+	switch (boot_cpu_data.x86_model) {
+	case 0x30 ... 0x3f: good_rev = 0x0830107a; break;
+	case 0x60 ... 0x67: good_rev = 0x0860010b; break;
+	case 0x68 ... 0x6f: good_rev = 0x08608105; break;
+	case 0x70 ... 0x7f: good_rev = 0x08701032; break;
+	case 0xa0 ... 0xaf: good_rev = 0x08a00008; break;
+
+	default:
+		return false;
+		break;
+	}
+
+	if (boot_cpu_data.microcode < good_rev)
+		return false;
+
+	return true;
+}
+
+static void zenbleed_check(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has_amd_erratum(c, amd_zenbleed))
+		return;
+
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (!cpu_has(c, X86_FEATURE_AVX))
+		return;
+
+	if (!cpu_has_zenbleed_microcode()) {
+		pr_notice_once("Zenbleed: please update your microcode for the most optimal fix\n");
+		msr_set_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT);
+	} else {
+		msr_clear_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT);
+	}
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd(c);
@@ -1011,6 +1119,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 
 	check_null_seg_clears_base(c);
+
+	zenbleed_check(c);
 }
 
 #ifdef CONFIG_X86_32
@@ -1106,73 +1216,6 @@ static const struct cpu_dev amd_cpu_dev = {
 
 cpu_dev_register(amd_cpu_dev);
 
-/*
- * AMD errata checking
- *
- * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
- * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
- * have an OSVW id assigned, which it takes as first argument. Both take a
- * variable number of family-specific model-stepping ranges created by
- * AMD_MODEL_RANGE().
- *
- * Example:
- *
- * const int amd_erratum_319[] =
- *	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
- *			   AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
- *			   AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
- */
-
-#define AMD_LEGACY_ERRATUM(...)		{ -1, __VA_ARGS__, 0 }
-#define AMD_OSVW_ERRATUM(osvw_id, ...)	{ osvw_id, __VA_ARGS__, 0 }
-#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
-	((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
-#define AMD_MODEL_RANGE_FAMILY(range)	(((range) >> 24) & 0xff)
-#define AMD_MODEL_RANGE_START(range)	(((range) >> 12) & 0xfff)
-#define AMD_MODEL_RANGE_END(range)	((range) & 0xfff)
-
-static const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
-			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
-
-static const int amd_erratum_383[] =
-	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
-
-/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
-static const int amd_erratum_1054[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
-
-static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
-{
-	int osvw_id = *erratum++;
-	u32 range;
-	u32 ms;
-
-	if (osvw_id >= 0 && osvw_id < 65536 &&
-	    cpu_has(cpu, X86_FEATURE_OSVW)) {
-		u64 osvw_len;
-
-		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
-		if (osvw_id < osvw_len) {
-			u64 osvw_bits;
-
-			rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
-			    osvw_bits);
-			return osvw_bits & (1ULL << (osvw_id & 0x3f));
-		}
-	}
-
-	/* OSVW unavailable or ID unknown, match family-model-stepping range */
-	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
-	while ((range = *erratum++))
-		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
-		    (ms >= AMD_MODEL_RANGE_START(range)) &&
-		    (ms <= AMD_MODEL_RANGE_END(range)))
-			return true;
-
-	return false;
-}
-
 void set_dr_addr_mask(unsigned long mask, int dr)
 {
 	if (!boot_cpu_has(X86_FEATURE_BPEXT))
@@ -1191,3 +1234,15 @@ void set_dr_addr_mask(unsigned long mask, int dr)
 		break;
 	}
 }
+
+static void zenbleed_check_cpu(void *unused)
+{
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+
+	zenbleed_check(c);
+}
+
+void amd_check_microcode(void)
+{
+	on_each_cpu(zenbleed_check_cpu, NULL, 1);
+}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 55293e5dc..ec324be00 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2077,6 +2077,8 @@ void microcode_check(void)
 
 	perf_check_microcode();
 
+	amd_check_microcode();
+
 	/* Reload CPUID max function as it might've changed. */
 	info.cpuid_level = cpuid_eax(0);
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b33e4fe9d..5698e0480 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -532,7 +532,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
 	/* need to apply patch? */
-	if (rev >= mc_amd->hdr.patch_id) {
+	if (rev > mc_amd->hdr.patch_id) {
 		ret = UCODE_OK;
 		goto out;
 	}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2b17a5cec..7e698c457 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -171,7 +171,6 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	printk("%sCall Trace:\n", log_lvl);
 
 	unwind_start(&state, task, regs, stack);
-	stack = stack ? : get_stack_pointer(task, regs);
 	regs = unwind_get_entry_regs(&state, &partial);
 
 	/*
@@ -190,9 +189,13 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - hardirq stack
 	 * - entry stack
 	 */
-	for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+	for (stack = stack ?: get_stack_pointer(task, regs);
+	     stack;
+	     stack = stack_info.next_sp) {
 		const char *stack_name;
 
+		stack = PTR_ALIGN(stack, sizeof(long));
+
 		if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
 			/*
 			 * We weren't on a valid stack.  It's possible that
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 265e70b0e..55e52064c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -13878,6 +13878,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
 		break;
 
+	case x86_intercept_pause:
+		/*
+		 * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides
+		 * with vanilla NOPs in the emulator.  Apply the interception
+		 * check only to actual PAUSE instructions.  Don't check
+		 * PAUSE-loop-exiting, software can't expect a given PAUSE to
+		 * exit, i.e. KVM is within its rights to allow L2 to execute
+		 * the PAUSE.
+		 */
+		if ((info->rep_prefix != REPE_PREFIX) ||
+		    !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING))
+			return X86EMUL_CONTINUE;
+
+		break;
+
 	/* TODO: check more intercepts... */
 	default:
 		break;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index b1dba0987..2c84c5595 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -9,6 +9,7 @@
 #include <linux/kmemleak.h>
 
 #include <asm/set_memory.h>
+#include <asm/cpu_device_id.h>
 #include <asm/e820/api.h>
 #include <asm/init.h>
 #include <asm/page.h>
@@ -207,6 +208,24 @@ static void __init probe_page_size_mask(void)
 	}
 }
 
+#define INTEL_MATCH(_model) { .vendor  = X86_VENDOR_INTEL,	\
+			      .family  = 6,			\
+			      .model = _model,			\
+			    }
+/*
+ * INVLPG may not properly flush Global entries
+ * on these CPUs when PCIDs are enabled.
+ */
+static const struct x86_cpu_id invlpg_miss_ids[] = {
+	INTEL_MATCH(INTEL_FAM6_ALDERLAKE   ),
+	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
+	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ),
+	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE  ),
+	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
+	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+	{}
+};
+
 static void setup_pcid(void)
 {
 	if (!IS_ENABLED(CONFIG_X86_64))
@@ -215,6 +234,12 @@ static void setup_pcid(void)
 	if (!boot_cpu_has(X86_FEATURE_PCID))
 		return;
 
+	if (x86_match_cpu(invlpg_miss_ids)) {
+		pr_info("Incomplete global flushes, disabling PCID");
+		setup_clear_cpu_cap(X86_FEATURE_PCID);
+		return;
+	}
+
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		/*
 		 * This can't be cr4_set_bits_and_update_boot() -- the
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 002f7a01a..00f104e34 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -12,6 +12,11 @@ $(obj)/string.o: $(srctree)/arch/x86/boot/compressed/string.c FORCE
 $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
+# When profile-guided optimization is enabled, llvm emits two different
+# overlapping text sections, which is not supported by kexec. Remove profile
+# optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
 targets += purgatory.ro