Merge tag 'x86_cpu_for_v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu feature updates from Borislav Petkov:

 - Add synthetic X86_FEATURE flags for the different AMD Zen generations
   and use them everywhere instead of ad-hoc family/model checks. Drop
   an ancient AMD errata checking facility as a result

 - Fix a fragile initcall ordering in intel_epb

 - Do not issue the MFENCE+LFENCE barrier for the TSC deadline and
   X2APIC MSRs on AMD as it is not needed there

* tag 'x86_cpu_for_v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/CPU/AMD: Add X86_FEATURE_ZEN1
  x86/CPU/AMD: Drop now unused CPU erratum checking function
  x86/CPU/AMD: Get rid of amd_erratum_1485[]
  x86/CPU/AMD: Get rid of amd_erratum_400[]
  x86/CPU/AMD: Get rid of amd_erratum_383[]
  x86/CPU/AMD: Get rid of amd_erratum_1054[]
  x86/CPU/AMD: Move the DIV0 bug detection to the Zen1 init function
  x86/CPU/AMD: Move Zenbleed check to the Zen2 init function
  x86/CPU/AMD: Rename init_amd_zn() to init_amd_zen_common()
  x86/CPU/AMD: Call the spectral chicken in the Zen2 init function
  x86/CPU/AMD: Move erratum 1076 fix into the Zen1 init function
  x86/CPU/AMD: Move the Zen3 BTC_NO detection to the Zen3 init function
  x86/CPU/AMD: Carve out the erratum 1386 fix
  x86/CPU/AMD: Add ZenX generations flags
  x86/cpu/intel_epb: Don't rely on link order
  x86/barrier: Do not serialize MSR accesses on AMD

7 files changed, 169 insertions, 155 deletions

diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 35389b2af88e..0216f63a366b 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -81,22 +81,4 @@ do {									\
 
 #include <asm-generic/barrier.h>
 
-/*
- * Make previous memory operations globally visible before
- * a WRMSR.
- *
- * MFENCE makes writes visible, but only affects load/store
- * instructions.  WRMSR is unfortunately not a load/store
- * instruction and is unaffected by MFENCE.  The LFENCE ensures
- * that the WRMSR is not reordered.
- *
- * Most WRMSRs are full serializing instructions themselves and
- * do not require this barrier.  This is only required for the
- * IA32_TSC_DEADLINE and X2APIC MSRs.
- */
-static inline void weak_wrmsr_fence(void)
-{
-	asm volatile("mfence; lfence" : : : "memory");
-}
-
 #endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4af140cf5719..632c26cdeeda 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -218,7 +218,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" Generic flag for all Zen and newer */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -308,10 +308,14 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2		(11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3		(11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4		(11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1		(11*32+31) /* "" CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ae81a7191c1c..26620d7642a9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -749,4 +749,22 @@ enum mds_mitigations {
 
 extern bool gds_ucode_mitigated(void);
 
+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions.  WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE.  The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier.  This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+	alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE));
+}
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f322ebd053a9..9f42d1c59e09 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -34,87 +34,6 @@
  */
 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, 0x90, 0x0, 0x91, 0xf),
-			   AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
-
-static const int amd_div0[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf),
-			   AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf));
-
-static const int amd_erratum_1485[] =
-	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
-			   AMD_MODEL_RANGE(0x19, 0x60, 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 };
@@ -616,6 +535,49 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	}
 
 	resctrl_cpu_detect(c);
+
+	/* Figure out Zen generations: */
+	switch (c->x86) {
+	case 0x17: {
+		switch (c->x86_model) {
+		case 0x00 ... 0x2f:
+		case 0x50 ... 0x5f:
+			setup_force_cpu_cap(X86_FEATURE_ZEN1);
+			break;
+		case 0x30 ... 0x4f:
+		case 0x60 ... 0x7f:
+		case 0x90 ... 0x91:
+		case 0xa0 ... 0xaf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN2);
+			break;
+		default:
+			goto warn;
+		}
+		break;
+	}
+	case 0x19: {
+		switch (c->x86_model) {
+		case 0x00 ... 0x0f:
+		case 0x20 ... 0x5f:
+			setup_force_cpu_cap(X86_FEATURE_ZEN3);
+			break;
+		case 0x10 ... 0x1f:
+		case 0x60 ... 0xaf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN4);
+			break;
+		default:
+			goto warn;
+		}
+		break;
+	}
+	default:
+		break;
+	}
+
+	return;
+
+warn:
+	WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model);
 }
 
 static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -739,15 +701,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x16 && c->x86_model <= 0xf)
 		msr_set_bit(MSR_AMD64_LS_CFG, 15);
 
-	/*
-	 * Check whether the machine is affected by erratum 400. This is
-	 * used to select the proper idle routine and to enable the check
-	 * whether the machine is affected in arch_post_acpi_init(), which
-	 * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
-	 */
-	if (cpu_has_amd_erratum(c, amd_erratum_400))
-		set_cpu_bug(c, X86_BUG_AMD_E400);
-
 	early_detect_mem_encrypt(c);
 
 	/* Re-enable TopologyExtensions if switched off by BIOS */
@@ -814,6 +767,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	msr_set_bit(MSR_K7_HWCR, 6);
 #endif
 	set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
+
+	/*
+	 * Check models and steppings affected by erratum 400. This is
+	 * used to select the proper idle routine and to enable the
+	 * check whether the machine is affected in arch_post_acpi_subsys_init()
+	 * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+	 */
+	if (c->x86_model > 0x41 ||
+	    (c->x86_model == 0x41 && c->x86_stepping >= 0x2))
+		setup_force_cpu_bug(X86_BUG_AMD_E400);
 }
 
 static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -847,8 +810,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
 	 */
 	msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
-	if (cpu_has_amd_erratum(c, amd_erratum_383))
-		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+	set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+
+	/*
+	 * Check models and steppings affected by erratum 400. This is
+	 * used to select the proper idle routine and to enable the
+	 * check whether the machine is affected in arch_post_acpi_subsys_init()
+	 * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check.
+	 */
+	if (c->x86_model > 0x2 ||
+	    (c->x86_model == 0x2 && c->x86_stepping >= 0x1))
+		setup_force_cpu_bug(X86_BUG_AMD_E400);
 }
 
 static void init_amd_ln(struct cpuinfo_x86 *c)
@@ -941,6 +913,19 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	clear_rdrand_cpuid_bit(c);
 }
 
+static void fix_erratum_1386(struct cpuinfo_x86 *c)
+{
+	/*
+	 * 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);
+}
+
 void init_spectral_chicken(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_CPU_UNRET_ENTRY
@@ -951,34 +936,28 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
 	 *
 	 * This suppresses speculation from the middle of a basic block, i.e. it
 	 * suppresses non-branch predictions.
-	 *
-	 * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
 	 */
-	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
 			value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
 			wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
 		}
 	}
 #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_zn(struct cpuinfo_x86 *c)
+static void init_amd_zen_common(void)
 {
-	set_cpu_cap(c, X86_FEATURE_ZEN);
-
+	setup_force_cpu_cap(X86_FEATURE_ZEN);
 #ifdef CONFIG_NUMA
 	node_reclaim_distance = 32;
 #endif
+}
+
+static void init_amd_zen1(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+	fix_erratum_1386(c);
 
 	/* Fix up CPUID bits, but only if not virtualised. */
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
@@ -986,15 +965,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 		/* Erratum 1076: CPB feature bit not being set in CPUID. */
 		if (!cpu_has(c, X86_FEATURE_CPB))
 			set_cpu_cap(c, X86_FEATURE_CPB);
-
-		/*
-		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
-		 * Branch Type Confusion, but predate the allocation of the
-		 * BTC_NO bit.
-		 */
-		if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO))
-			set_cpu_cap(c, X86_FEATURE_BTC_NO);
 	}
+
+	pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
+	setup_force_cpu_bug(X86_BUG_DIV0);
 }
 
 static bool cpu_has_zenbleed_microcode(void)
@@ -1018,11 +992,8 @@ static bool cpu_has_zenbleed_microcode(void)
 	return true;
 }
 
-static void zenbleed_check(struct cpuinfo_x86 *c)
+static void zen2_zenbleed_check(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has_amd_erratum(c, amd_zenbleed))
-		return;
-
 	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
 		return;
 
@@ -1037,6 +1008,37 @@ static void zenbleed_check(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_amd_zen2(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+	init_spectral_chicken(c);
+	fix_erratum_1386(c);
+	zen2_zenbleed_check(c);
+}
+
+static void init_amd_zen3(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
+		/*
+		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
+		 * Branch Type Confusion, but predate the allocation of the
+		 * BTC_NO bit.
+		 */
+		if (!cpu_has(c, X86_FEATURE_BTC_NO))
+			set_cpu_cap(c, X86_FEATURE_BTC_NO);
+	}
+}
+
+static void init_amd_zen4(struct cpuinfo_x86 *c)
+{
+	init_amd_zen_common();
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
 	u64 vm_cr;
@@ -1072,11 +1074,17 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	case 0x16: init_amd_jg(c); break;
-	case 0x17: init_spectral_chicken(c);
-		   fallthrough;
-	case 0x19: init_amd_zn(c); break;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_ZEN1))
+		init_amd_zen1(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN2))
+		init_amd_zen2(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN3))
+		init_amd_zen3(c);
+	else if (boot_cpu_has(X86_FEATURE_ZEN4))
+		init_amd_zen4(c);
+
 	/*
 	 * Enable workaround for FXSAVE leak on CPUs
 	 * without a XSaveErPtr feature
@@ -1136,7 +1144,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 * Counter May Be Inaccurate".
 	 */
 	if (cpu_has(c, X86_FEATURE_IRPERF) &&
-	    !cpu_has_amd_erratum(c, amd_erratum_1054))
+	    (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
 		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 
 	check_null_seg_clears_base(c);
@@ -1152,16 +1160,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	    cpu_has(c, X86_FEATURE_AUTOIBRS))
 		WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS));
 
-	zenbleed_check(c);
-
-	if (cpu_has_amd_erratum(c, amd_div0)) {
-		pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
-		setup_force_cpu_bug(X86_BUG_DIV0);
-	}
-
-	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
-	     cpu_has_amd_erratum(c, amd_erratum_1485))
-		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
 }
 
 #ifdef CONFIG_X86_32
@@ -1315,7 +1315,7 @@ static void zenbleed_check_cpu(void *unused)
 {
 	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
-	zenbleed_check(c);
+	zen2_zenbleed_check(c);
 }
 
 void amd_check_microcode(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b14fc8c1c953..98f7ea6b931c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1856,6 +1856,13 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
 #endif
 
+
+	/*
+	 * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+	 * Hygon will clear it in ->c_init() below.
+	 */
+	set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
 	/*
 	 * Vendor-specific initialization.  In this section we
 	 * canonicalize the feature flags, meaning if there are
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 6f247d66758d..f0cd95502faa 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -354,6 +354,9 @@ static void init_hygon(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
 
 	check_null_seg_clears_base(c);
+
+	/* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
 }
 
 static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index e4c3ba91321c..f18d35fe27a9 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -237,4 +237,4 @@ err_out_online:
 	cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
 	return ret;
 }
-subsys_initcall(intel_epb_init);
+late_initcall(intel_epb_init);