Merge branch 'x86/urgent' into x86/cpu, to pick up dependent commits

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

14 files changed, 156 insertions, 44 deletions

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 94941c5a10ac..14db5b85114c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -190,6 +190,7 @@ static __always_inline bool int80_is_external(void)
 
 /**
  * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445..2092d615333d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -628,7 +628,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
+	if (!event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 397c545b8610..40a62bf6ef0a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
 
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x012a, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x012b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
 
 	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
 	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
-	/*
-	 * Generally event codes < 0x90 are restricted to counters 0-3.
-	 * The 0x2E and 0x3C are exception, which has no restriction.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
 
-	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc),
 	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
-	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
 
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
-	/*
-	 * Generally event codes >= 0x90 are likely to have no restrictions.
-	 * The exception are defined as above.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf),
 
 	EVENT_CONSTRAINT_END
 };
@@ -3958,6 +3952,85 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3969,6 +4042,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c2e2eae7309c..f122882ef278 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 4952faf03e82..6941f4811bec 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -879,6 +879,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index e6fa03ed9172..a6c6bccfa8b8 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -808,7 +808,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
+			for (j = 0 ; j < 4 ; j++)
 				if (regs[j] & (1 << 31))
 					regs[j] = 0;
 
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 8bd84114c2d9..df838e3bdbe0 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -45,6 +45,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AES,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_SHA_NI,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_GFNI,			X86_FEATURE_XMM2      },
+	{ X86_FEATURE_AVX_VNNI,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_FMA,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VAES,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VPCLMULQDQ,		X86_FEATURE_AVX       },
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1..dfec2c61e354 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
 	u8 ccr3;
 	local_irq_save(flags);
 
-	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	/* Suspend on halt power saving */
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 045b439c653a..c5d833f5bffb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -635,26 +635,37 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
+#define TLB_INST_4K		0x01
+#define TLB_INST_4M		0x02
+#define TLB_INST_2M_4M		0x03
 
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
+#define TLB_INST_ALL		0x05
+#define TLB_INST_1G		0x06
 
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
+#define TLB_DATA_4K		0x11
+#define TLB_DATA_4M		0x12
+#define TLB_DATA_2M_4M		0x13
+#define TLB_DATA_4K_4M		0x14
 
-#define TLB_DATA_1G	0x16
+#define TLB_DATA_1G		0x16
+#define TLB_DATA_1G_2M_4M	0x17
 
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
+#define TLB_DATA0_4K		0x21
+#define TLB_DATA0_4M		0x22
+#define TLB_DATA0_2M_4M		0x23
 
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
+#define STLB_4K			0x41
+#define STLB_4K_2M		0x42
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of
+ * entries for their respective TLB types.  The 0x63 descriptor is an
+ * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
+ * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
+ * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
+ * intel_tlb_table[] mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES	32
 
 static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
@@ -676,7 +687,8 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x63, TLB_DATA_1G_2M_4M,	4,	" TLB_DATA 1 GByte pages, 4-way set associative"
+						" (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here)" },
 	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
 	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
 	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
@@ -776,6 +788,12 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case TLB_DATA_1G_2M_4M:
+		if (tlb_lld_2m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_2m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		if (tlb_lld_4m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_4m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		fallthrough;
 	case TLB_DATA_1G:
 		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
@@ -799,7 +817,7 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c)
 		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
+		for (j = 0 ; j < 4 ; j++)
 			if (regs[j] & (1 << 31))
 				regs[j] = 0;
 
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 59d23cdf4ed0..dd8748c45529 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,6 +2,7 @@
 /*
  * Architecture specific OF callbacks.
  */
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -313,6 +314,6 @@ void __init x86_flattree_get_config(void)
 	if (initial_dtb)
 		early_memunmap(dt, map_len);
 #endif
-	if (of_have_populated_dt())
+	if (acpi_disabled && of_have_populated_dt())
 		x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 385e3a5fc304..feca4f20b06a 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -25,8 +25,10 @@
 #include <asm/posted_intr.h>
 #include <asm/irq_remapping.h>
 
+#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
+#endif
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d4ac4a1f8b81..8160870398b9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7460,7 +7460,7 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-static void kvm_mmu_start_lpage_recovery(struct once *once)
+static int kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
@@ -7471,13 +7471,14 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm_nx_huge_page_recovery_worker_kill,
 				      kvm, "kvm-nx-lpage-recovery");
 
-	if (!nx_thread)
-		return;
+	if (IS_ERR(nx_thread))
+		return PTR_ERR(nx_thread);
 
 	vhost_task_start(nx_thread);
 
 	/* Make the task visible only once it is fully started. */
 	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+	return 0;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
@@ -7485,10 +7486,7 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
-	if (!kvm->arch.nx_huge_page_recovery_thread)
-		return -ENOMEM;
-	return 0;
+	return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e..ed8a3cb53961 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5084,6 +5084,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29..6fc4ddc606bd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12877,11 +12877,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	kvm_unload_vcpu_mmus(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_x86_call(vm_destroy)(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);