summary refs log tree commit diff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/compressed/eboot.c134
-rw-r--r--arch/x86/events/amd/core.c4
-rw-r--r--arch/x86/events/amd/uncore.c22
-rw-r--r--arch/x86/events/intel/bts.c126
-rw-r--r--arch/x86/events/intel/core.c15
-rw-r--r--arch/x86/events/intel/cqm.c9
-rw-r--r--arch/x86/events/intel/ds.c19
-rw-r--r--arch/x86/events/intel/pt.c18
-rw-r--r--arch/x86/include/asm/uaccess.h6
-rw-r--r--arch/x86/kernel/apic/apic.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c13
-rw-r--r--arch/x86/kernel/kvmclock.c1
-rw-r--r--arch/x86/kvm/ioapic.c8
-rw-r--r--arch/x86/kvm/pmu_amd.c4
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/mm/pageattr.c21
-rw-r--r--arch/x86/pci/fixup.c20
-rw-r--r--arch/x86/platform/efi/efi_64.c2
18 files changed, 282 insertions, 152 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff574dad95cc..94dd4a31f5b3 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1004,79 +1004,87 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 	return status;
 }
 
-static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle, bool is64)
-{
-	struct efi_info *efi = &boot_params->efi_info;
-	unsigned long map_sz, key, desc_size;
-	efi_memory_desc_t *mem_map;
+struct exit_boot_struct {
+	struct boot_params *boot_params;
+	struct efi_info *efi;
 	struct setup_data *e820ext;
-	const char *signature;
 	__u32 e820ext_size;
-	__u32 nr_desc, prev_nr_desc;
-	efi_status_t status;
-	__u32 desc_version;
-	bool called_exit = false;
-	u8 nr_entries;
-	int i;
-
-	nr_desc = 0;
-	e820ext = NULL;
-	e820ext_size = 0;
-
-get_map:
-	status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
-				    &desc_version, &key);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	prev_nr_desc = nr_desc;
-	nr_desc = map_sz / desc_size;
-	if (nr_desc > prev_nr_desc &&
-	    nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
-		u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
-		status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
-		if (status != EFI_SUCCESS)
-			goto free_mem_map;
+	bool is64;
+};
 
-		efi_call_early(free_pool, mem_map);
-		goto get_map; /* Allocated memory, get map again */
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+				   struct efi_boot_memmap *map,
+				   void *priv)
+{
+	static bool first = true;
+	const char *signature;
+	__u32 nr_desc;
+	efi_status_t status;
+	struct exit_boot_struct *p = priv;
+
+	if (first) {
+		nr_desc = *map->buff_size / *map->desc_size;
+		if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+			u32 nr_e820ext = nr_desc -
+					ARRAY_SIZE(p->boot_params->e820_map);
+
+			status = alloc_e820ext(nr_e820ext, &p->e820ext,
+					       &p->e820ext_size);
+			if (status != EFI_SUCCESS)
+				return status;
+		}
+		first = false;
 	}
 
-	signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
-	memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	efi->efi_systab = (unsigned long)sys_table;
-	efi->efi_memdesc_size = desc_size;
-	efi->efi_memdesc_version = desc_version;
-	efi->efi_memmap = (unsigned long)mem_map;
-	efi->efi_memmap_size = map_sz;
+	p->efi->efi_systab = (unsigned long)sys_table_arg;
+	p->efi->efi_memdesc_size = *map->desc_size;
+	p->efi->efi_memdesc_version = *map->desc_ver;
+	p->efi->efi_memmap = (unsigned long)*map->map;
+	p->efi->efi_memmap_size = *map->map_size;
 
 #ifdef CONFIG_X86_64
-	efi->efi_systab_hi = (unsigned long)sys_table >> 32;
-	efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+	p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+	p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
 #endif
 
+	return EFI_SUCCESS;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+			      void *handle, bool is64)
+{
+	unsigned long map_sz, key, desc_size, buff_size;
+	efi_memory_desc_t *mem_map;
+	struct setup_data *e820ext;
+	__u32 e820ext_size;
+	efi_status_t status;
+	__u32 desc_version;
+	struct efi_boot_memmap map;
+	struct exit_boot_struct priv;
+
+	map.map =		&mem_map;
+	map.map_size =		&map_sz;
+	map.desc_size =		&desc_size;
+	map.desc_ver =		&desc_version;
+	map.key_ptr =		&key;
+	map.buff_size =		&buff_size;
+	priv.boot_params =	boot_params;
+	priv.efi =		&boot_params->efi_info;
+	priv.e820ext =		NULL;
+	priv.e820ext_size =	0;
+	priv.is64 =		is64;
+
 	/* Might as well exit boot services now */
-	status = efi_call_early(exit_boot_services, handle, key);
-	if (status != EFI_SUCCESS) {
-		/*
-		 * ExitBootServices() will fail if any of the event
-		 * handlers change the memory map. In which case, we
-		 * must be prepared to retry, but only once so that
-		 * we're guaranteed to exit on repeated failures instead
-		 * of spinning forever.
-		 */
-		if (called_exit)
-			goto free_mem_map;
-
-		called_exit = true;
-		efi_call_early(free_pool, mem_map);
-		goto get_map;
-	}
+	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+					exit_boot_func);
+	if (status != EFI_SUCCESS)
+		return status;
 
+	e820ext = priv.e820ext;
+	e820ext_size = priv.e820ext_size;
 	/* Historic? */
 	boot_params->alt_mem_k = 32 * 1024;
 
@@ -1085,10 +1093,6 @@ get_map:
 		return status;
 
 	return EFI_SUCCESS;
-
-free_mem_map:
-	efi_call_early(free_pool, mem_map);
-	return status;
 }
 
 /*
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e07a22bb9308..f5f4b3fbbbc2 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -119,8 +119,8 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
   [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
   [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x0080,
-  [PERF_COUNT_HW_CACHE_MISSES]			= 0x0081,
+  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x077d,
+  [PERF_COUNT_HW_CACHE_MISSES]			= 0x077e,
   [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
   [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
   [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index e6131d4454e6..65577f081d07 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -29,6 +29,8 @@
 
 #define COUNTER_SHIFT		16
 
+static HLIST_HEAD(uncore_unused_list);
+
 struct amd_uncore {
 	int id;
 	int refcnt;
@@ -39,7 +41,7 @@ struct amd_uncore {
 	cpumask_t *active_mask;
 	struct pmu *pmu;
 	struct perf_event *events[MAX_COUNTERS];
-	struct amd_uncore *free_when_cpu_online;
+	struct hlist_node node;
 };
 
 static struct amd_uncore * __percpu *amd_uncore_nb;
@@ -306,6 +308,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
 		uncore_nb->active_mask = &amd_nb_active_mask;
 		uncore_nb->pmu = &amd_nb_pmu;
+		uncore_nb->id = -1;
 		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
@@ -319,6 +322,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
 		uncore_l2->active_mask = &amd_l2_active_mask;
 		uncore_l2->pmu = &amd_l2_pmu;
+		uncore_l2->id = -1;
 		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
 	}
 
@@ -348,7 +352,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
 			continue;
 
 		if (this->id == that->id) {
-			that->free_when_cpu_online = this;
+			hlist_add_head(&this->node, &uncore_unused_list);
 			this = that;
 			break;
 		}
@@ -388,13 +392,23 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
 	return 0;
 }
 
+static void uncore_clean_online(void)
+{
+	struct amd_uncore *uncore;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+		hlist_del(&uncore->node);
+		kfree(uncore);
+	}
+}
+
 static void uncore_online(unsigned int cpu,
 			  struct amd_uncore * __percpu *uncores)
 {
 	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
 
-	kfree(uncore->free_when_cpu_online);
-	uncore->free_when_cpu_online = NULL;
+	uncore_clean_online();
 
 	if (cpu == uncore->cpu)
 		cpumask_set_cpu(cpu, uncore->active_mask);
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 0a6e393a2e62..982c9e31daca 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -31,7 +31,17 @@
 struct bts_ctx {
 	struct perf_output_handle	handle;
 	struct debug_store		ds_back;
-	int				started;
+	int				state;
+};
+
+/* BTS context states: */
+enum {
+	/* no ongoing AUX transactions */
+	BTS_STATE_STOPPED = 0,
+	/* AUX transaction is on, BTS tracing is disabled */
+	BTS_STATE_INACTIVE,
+	/* AUX transaction is on, BTS tracing is running */
+	BTS_STATE_ACTIVE,
 };
 
 static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
@@ -204,6 +214,15 @@ static void bts_update(struct bts_ctx *bts)
 static int
 bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ *  - is set when bts::handle::event is valid, that is, between
+ *    perf_aux_output_begin() and perf_aux_output_end();
+ *  - is zero otherwise;
+ *  - is ordered against bts::handle::event with a compiler barrier.
+ */
+
 static void __bts_event_start(struct perf_event *event)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
@@ -221,10 +240,13 @@ static void __bts_event_start(struct perf_event *event)
 
 	/*
 	 * local barrier to make sure that ds configuration made it
-	 * before we enable BTS
+	 * before we enable BTS and bts::state goes ACTIVE
 	 */
 	wmb();
 
+	/* INACTIVE/STOPPED -> ACTIVE */
+	WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
 	intel_pmu_enable_bts(config);
 
 }
@@ -251,9 +273,6 @@ static void bts_event_start(struct perf_event *event, int flags)
 
 	__bts_event_start(event);
 
-	/* PMI handler: this counter is running and likely generating PMIs */
-	ACCESS_ONCE(bts->started) = 1;
-
 	return;
 
 fail_end_stop:
@@ -263,30 +282,34 @@ fail_stop:
 	event->hw.state = PERF_HES_STOPPED;
 }
 
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
 {
+	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+	/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+	WRITE_ONCE(bts->state, state);
+
 	/*
 	 * No extra synchronization is mandated by the documentation to have
 	 * BTS data stores globally visible.
 	 */
 	intel_pmu_disable_bts();
-
-	if (event->hw.state & PERF_HES_STOPPED)
-		return;
-
-	ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
 }
 
 static void bts_event_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_buffer *buf = NULL;
+	int state = READ_ONCE(bts->state);
 
-	/* PMI handler: don't restart this counter */
-	ACCESS_ONCE(bts->started) = 0;
+	if (state == BTS_STATE_ACTIVE)
+		__bts_event_stop(event, BTS_STATE_STOPPED);
 
-	__bts_event_stop(event);
+	if (state != BTS_STATE_STOPPED)
+		buf = perf_get_aux(&bts->handle);
+
+	event->hw.state |= PERF_HES_STOPPED;
 
 	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
@@ -296,6 +319,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
 				bts->handle.head =
 					local_xchg(&buf->data_size,
 						   buf->nr_pages << PAGE_SHIFT);
+
 			perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
 					    !!local_xchg(&buf->lost, 0));
 		}
@@ -310,8 +334,20 @@ static void bts_event_stop(struct perf_event *event, int flags)
 void intel_bts_enable_local(void)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	int state = READ_ONCE(bts->state);
+
+	/*
+	 * Here we transition from INACTIVE to ACTIVE;
+	 * if we instead are STOPPED from the interrupt handler,
+	 * stay that way. Can't be ACTIVE here though.
+	 */
+	if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+		return;
+
+	if (state == BTS_STATE_STOPPED)
+		return;
 
-	if (bts->handle.event && bts->started)
+	if (bts->handle.event)
 		__bts_event_start(bts->handle.event);
 }
 
@@ -319,8 +355,15 @@ void intel_bts_disable_local(void)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 
+	/*
+	 * Here we transition from ACTIVE to INACTIVE;
+	 * do nothing for STOPPED or INACTIVE.
+	 */
+	if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+		return;
+
 	if (bts->handle.event)
-		__bts_event_stop(bts->handle.event);
+		__bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
 }
 
 static int
@@ -335,8 +378,6 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 		return 0;
 
 	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
-	if (WARN_ON_ONCE(head != local_read(&buf->head)))
-		return -EINVAL;
 
 	phys = &buf->buf[buf->cur_buf];
 	space = phys->offset + phys->displacement + phys->size - head;
@@ -403,22 +444,37 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 
 int intel_bts_interrupt(void)
 {
+	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct perf_event *event = bts->handle.event;
 	struct bts_buffer *buf;
 	s64 old_head;
-	int err;
+	int err = -ENOSPC, handled = 0;
 
-	if (!event || !bts->started)
-		return 0;
+	/*
+	 * The only surefire way of knowing if this NMI is ours is by checking
+	 * the write ptr against the PMI threshold.
+	 */
+	if (ds && (ds->bts_index >= ds->bts_interrupt_threshold))
+		handled = 1;
+
+	/*
+	 * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+	 * so we can only be INACTIVE or STOPPED
+	 */
+	if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+		return handled;
 
 	buf = perf_get_aux(&bts->handle);
+	if (!buf)
+		return handled;
+
 	/*
 	 * Skip snapshot counters: they don't use the interrupt, but
 	 * there's no other way of telling, because the pointer will
 	 * keep moving
 	 */
-	if (!buf || buf->snapshot)
+	if (buf->snapshot)
 		return 0;
 
 	old_head = local_read(&buf->head);
@@ -426,18 +482,27 @@ int intel_bts_interrupt(void)
 
 	/* no new data */
 	if (old_head == local_read(&buf->head))
-		return 0;
+		return handled;
 
 	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
 			    !!local_xchg(&buf->lost, 0));
 
 	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
-		return 1;
+	if (buf)
+		err = bts_buffer_reset(buf, &bts->handle);
+
+	if (err) {
+		WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
 
-	err = bts_buffer_reset(buf, &bts->handle);
-	if (err)
-		perf_aux_output_end(&bts->handle, 0, false);
+		if (buf) {
+			/*
+			 * BTS_STATE_STOPPED should be visible before
+			 * cleared handle::event
+			 */
+			barrier();
+			perf_aux_output_end(&bts->handle, 0, false);
+		}
+	}
 
 	return 1;
 }
@@ -519,7 +584,8 @@ static __init int bts_init(void)
 	if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
 		return -ENODEV;
 
-	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE;
+	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
+				  PERF_PMU_CAP_EXCLUSIVE;
 	bts_pmu.task_ctx_nr	= perf_sw_context;
 	bts_pmu.event_init	= bts_event_init;
 	bts_pmu.add		= bts_event_add;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2cbde2f449aa..4c9a79b9cd69 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1730,9 +1730,11 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * disabled state if called consecutively.
  *
  * During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
  */
 static void __intel_pmu_disable_all(void)
 {
@@ -1742,8 +1744,6 @@ static void __intel_pmu_disable_all(void)
 
 	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
-	else
-		intel_bts_disable_local();
 
 	intel_pmu_pebs_disable_all();
 }
@@ -1771,8 +1771,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 			return;
 
 		intel_pmu_enable_bts(event->hw.config);
-	} else
-		intel_bts_enable_local();
+	}
 }
 
 static void intel_pmu_enable_all(int added)
@@ -2073,6 +2072,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	 */
 	if (!x86_pmu.late_ack)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
+	intel_bts_disable_local();
 	__intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
@@ -2172,6 +2172,7 @@ done:
 	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
 	if (cpuc->enabled)
 		__intel_pmu_enable_all(0, true);
+	intel_bts_enable_local();
 
 	/*
 	 * Only unmask the NMI after the overflow counters
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 783c49ddef29..8f82b02934fa 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -458,6 +458,11 @@ static void __intel_cqm_event_count(void *info);
 static void init_mbm_sample(u32 rmid, u32 evt_type);
 static void __intel_mbm_event_count(void *info);
 
+static bool is_cqm_event(int e)
+{
+	return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
 static bool is_mbm_event(int e)
 {
 	return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
@@ -1366,6 +1371,10 @@ static int intel_cqm_event_init(struct perf_event *event)
 	     (event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
 		return -EINVAL;
 
+	if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+	    (is_mbm_event(event->attr.config) && !mbm_enabled))
+		return -EINVAL;
+
 	/* unsupported modes and filters */
 	if (event->attr.exclude_user   ||
 	    event->attr.exclude_kernel ||
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f669e6..9b983a474253 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1274,18 +1274,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		struct pebs_record_nhm *p = at;
 		u64 pebs_status;
 
-		/* PEBS v3 has accurate status bits */
+		pebs_status = p->status & cpuc->pebs_enabled;
+		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
-			for_each_set_bit(bit, (unsigned long *)&p->status,
-					 MAX_PEBS_EVENTS)
+			for_each_set_bit(bit, (unsigned long *)&pebs_status,
+					 x86_pmu.max_pebs_events)
 				counts[bit]++;
 
 			continue;
 		}
 
-		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
 		/*
 		 * On some CPUs the PEBS status can be zero when PEBS is
 		 * racing with clearing of GLOBAL_STATUS.
@@ -1333,8 +1333,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		event = cpuc->events[bit];
-		WARN_ON_ONCE(!event);
-		WARN_ON_ONCE(!event->attr.precise_ip);
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		if (WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
 
 		/* log dropped samples number */
 		if (error[bit])
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 04bb5fb5a8d7..861a7d9cb60f 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1074,6 +1074,11 @@ static void pt_addr_filters_fini(struct perf_event *event)
 	event->hw.addr_filters = NULL;
 }
 
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+	return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
 static int pt_event_addr_filters_validate(struct list_head *filters)
 {
 	struct perf_addr_filter *filter;
@@ -1081,11 +1086,16 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 
 	list_for_each_entry(filter, filters, entry) {
 		/* PT doesn't support single address triggers */
-		if (!filter->range)
+		if (!filter->range || !filter->size)
 			return -EOPNOTSUPP;
 
-		if (!filter->inode && !kernel_ip(filter->offset))
-			return -EINVAL;
+		if (!filter->inode) {
+			if (!valid_kernel_ip(filter->offset))
+				return -EINVAL;
+
+			if (!valid_kernel_ip(filter->offset + filter->size))
+				return -EINVAL;
+		}
 
 		if (++range > pt_cap_get(PT_CAP_num_address_ranges))
 			return -EOPNOTSUPP;
@@ -1111,7 +1121,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		} else {
 			/* apply the offset */
 			msr_a = filter->offset + offs[range];
-			msr_b = filter->size + msr_a;
+			msr_b = filter->size + msr_a - 1;
 		}
 
 		filters->filter[range].msr_a  = msr_a;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index e3af86f58eaf..2131c4ce7d8a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -433,7 +433,11 @@ do {									\
 #define __get_user_asm_ex(x, addr, itype, rtype, ltype)			\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
-		     _ASM_EXTABLE_EX(1b, 2b)				\
+		     ".section .fixup,\"ax\"\n"				\
+                     "3:xor"itype" %"rtype"0,%"rtype"0\n"		\
+		     "  jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE_EX(1b, 3b)				\
 		     : ltype(x) : "m" (__m(addr)))
 
 #define __put_user_nocheck(x, ptr, size)			\
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 50c95af0f017..f3e9b2df4b16 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2093,7 +2093,6 @@ int generic_processor_info(int apicid, int version)
 		return -EINVAL;
 	}
 
-	num_processors++;
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
 		 * x86_bios_cpu_apicid is required to have processors listed
@@ -2116,10 +2115,13 @@ int generic_processor_info(int apicid, int version)
 
 		pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
 			   thiscpu, apicid);
+
 		disabled_cpus++;
 		return -ENOSPC;
 	}
 
+	num_processors++;
+
 	/*
 	 * Validate version
 	 */
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b816971f5da4..620ab06bcf45 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -54,6 +54,7 @@ static LIST_HEAD(pcache);
  */
 static u8 *container;
 static size_t container_size;
+static bool ucode_builtin;
 
 static u32 ucode_new_rev;
 static u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -281,18 +282,22 @@ static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
 void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct cpio_data cp;
+	bool *builtin;
 	void **data;
 	size_t *size;
 
 #ifdef CONFIG_X86_32
 	data =  (void **)__pa_nodebug(&ucode_cpio.data);
 	size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+	builtin = (bool *)__pa_nodebug(&ucode_builtin);
 #else
 	data = &ucode_cpio.data;
 	size = &ucode_cpio.size;
+	builtin = &ucode_builtin;
 #endif
 
-	if (!load_builtin_amd_microcode(&cp, family))
+	*builtin = load_builtin_amd_microcode(&cp, family);
+	if (!*builtin)
 		cp = find_ucode_in_initrd();
 
 	if (!(cp.data && cp.size))
@@ -373,7 +378,8 @@ void load_ucode_amd_ap(void)
 		return;
 
 	/* Add CONFIG_RANDOMIZE_MEMORY offset. */
-	cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+	if (!ucode_builtin)
+		cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
 
 	eax = cpuid_eax(0x00000001);
 	eq  = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
@@ -439,7 +445,8 @@ int __init save_microcode_in_initrd_amd(void)
 		container = cont_va;
 
 	/* Add CONFIG_RANDOMIZE_MEMORY offset. */
-	container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+	if (!ucode_builtin)
+		container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
 
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1d39bfbd26bb..3692249a70f1 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -289,6 +289,7 @@ void __init kvmclock_init(void)
 	put_cpu();
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 5f42d038fcb4..c7220ba94aa7 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -109,6 +109,7 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 {
 	bool new_val, old_val;
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
 	union kvm_ioapic_redirect_entry *e;
 
 	e = &ioapic->redirtbl[RTC_GSI];
@@ -117,16 +118,17 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 		return;
 
 	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
-	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+	old_val = test_bit(vcpu->vcpu_id, dest_map->map);
 
 	if (new_val == old_val)
 		return;
 
 	if (new_val) {
-		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+		__set_bit(vcpu->vcpu_id, dest_map->map);
+		dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
 		ioapic->rtc_status.pending_eoi++;
 	} else {
-		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+		__clear_bit(vcpu->vcpu_id, dest_map->map);
 		ioapic->rtc_status.pending_eoi--;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 39b91127ef07..cd944435dfbd 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -23,8 +23,8 @@
 static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
 	[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
 	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
-	[2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
-	[3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+	[2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+	[3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
 	[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
 	[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 19f9f9e05c2a..699f8726539a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2743,16 +2743,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 
-		if (kvm_lapic_hv_timer_in_use(vcpu) &&
-				kvm_x86_ops->set_hv_timer(vcpu,
-					kvm_get_lapic_tscdeadline_msr(vcpu)))
-			kvm_lapic_switch_to_sw_timer(vcpu);
 		if (check_tsc_unstable()) {
 			u64 offset = kvm_compute_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
 			kvm_x86_ops->write_tsc_offset(vcpu, offset);
 			vcpu->arch.tsc_catchup = 1;
 		}
+		if (kvm_lapic_hv_timer_in_use(vcpu) &&
+				kvm_x86_ops->set_hv_timer(vcpu,
+					kvm_get_lapic_tscdeadline_msr(vcpu)))
+			kvm_lapic_switch_to_sw_timer(vcpu);
 		/*
 		 * On a host with synchronized TSC, there is no need to update
 		 * kvmclock on vcpu->cpu migration
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 849dc09fa4f0..e3353c97d086 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -917,11 +917,11 @@ static void populate_pte(struct cpa_data *cpa,
 	}
 }
 
-static int populate_pmd(struct cpa_data *cpa,
-			unsigned long start, unsigned long end,
-			unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+static long populate_pmd(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pud_t *pud, pgprot_t pgprot)
 {
-	unsigned int cur_pages = 0;
+	long cur_pages = 0;
 	pmd_t *pmd;
 	pgprot_t pmd_pgprot;
 
@@ -991,12 +991,12 @@ static int populate_pmd(struct cpa_data *cpa,
 	return num_pages;
 }
 
-static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
-			pgprot_t pgprot)
+static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+			 pgprot_t pgprot)
 {
 	pud_t *pud;
 	unsigned long end;
-	int cur_pages = 0;
+	long cur_pages = 0;
 	pgprot_t pud_pgprot;
 
 	end = start + (cpa->numpages << PAGE_SHIFT);
@@ -1052,7 +1052,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 
 	/* Map trailing leftover */
 	if (start < end) {
-		int tmp;
+		long tmp;
 
 		pud = pud_offset(pgd, start);
 		if (pud_none(*pud))
@@ -1078,7 +1078,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
 	pud_t *pud = NULL;	/* shut up gcc */
 	pgd_t *pgd_entry;
-	int ret;
+	long ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
 
@@ -1327,7 +1327,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
 
 static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 {
-	int ret, numpages = cpa->numpages;
+	unsigned long numpages = cpa->numpages;
+	int ret;
 
 	while (numpages) {
 		/*
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 837ea36a837d..6d52b94f4bb9 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -553,15 +553,21 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
 
 /*
- * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
  *
- * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
- * entry BDF2.
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
  */
-static void pci_bdwep_bar(struct pci_dev *dev)
+static void pci_invalid_bar(struct pci_dev *dev)
 {
 	dev->non_compliant_bars = 1;
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 677e29e29473..8dd3784eb075 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -245,7 +245,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	 * text and allocate a new stack because we can't rely on the
 	 * stack pointer being < 4GB.
 	 */
-	if (!IS_ENABLED(CONFIG_EFI_MIXED))
+	if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native())
 		return 0;
 
 	/*
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-08 23:18:55 +0000