Merge branch into tip/master: 'perf/core'

# New commits in perf/core:
    b709eb872e19 ("perf: map pages in advance")
    6d642735cdb6 ("perf/x86/intel/uncore: Support more units on Granite Rapids")
    3f710be02ea6 ("perf/x86/intel/uncore: Clean up func_id")
    0e45818ec189 ("perf/x86/intel: Support RDPMC metrics clear mode")
    02c56362a7d3 ("uprobes: Guard against kmemdup() failing in dup_return_instance()")
    d29e744c7167 ("perf/x86: Relax privilege filter restriction on AMD IBS")
    6057b90ecc84 ("perf/core: Export perf_exclude_event()")
    8622e45b5da1 ("uprobes: Reuse return_instances between multiple uretprobes within task")
    0cf981de7687 ("uprobes: Ensure return_instance is detached from the list before freeing")
    636666a1c733 ("uprobes: Decouple return_instance list traversal and freeing")
    2ff913ab3f47 ("uprobes: Simplify session consumer tracking")
    e0925f2dc4de ("uprobes: add speculative lockless VMA-to-inode-to-uprobe resolution")
    83e3dc9a5d4d ("uprobes: simplify find_active_uprobe_rcu() VMA checks")
    03a001b156d2 ("mm: introduce mmap_lock_speculate_{try_begin|retry}")
    eb449bd96954 ("mm: convert mm_lock_seq to a proper seqcount")
    7528585290a1 ("mm/gup: Use raw_seqcount_try_begin()")
    96450ead1652 ("seqlock: add raw_seqcount_try_begin")
    b4943b8bfc41 ("perf/x86/rapl: Add core energy counter support for AMD CPUs")
    54d2759778c1 ("perf/x86/rapl: Move the cntr_mask to rapl_pmus struct")
    bdc57ec70548 ("perf/x86/rapl: Remove the global variable rapl_msrs")
    abf03d9bd20c ("perf/x86/rapl: Modify the generic variable names to *_pkg*")
    eeca4c6b2529 ("perf/x86/rapl: Add arguments to the init and cleanup functions")
    cd29d83a6d81 ("perf/x86/rapl: Make rapl_model struct global")
    8bf1c86e5ac8 ("perf/x86/rapl: Rename rapl_pmu variables")
    1d5e2f637a94 ("perf/x86/rapl: Remove the cpu_to_rapl_pmu() function")
    e4b444347795 ("x86/topology: Introduce topology_logical_core_id()")
    2f2db347071a ("perf/x86/rapl: Remove the unused get_rapl_pmu_cpumask() function")
    ae55e308bde2 ("perf/x86/intel/ds: Simplify the PEBS records processing for adaptive PEBS")
    3c00ed344cef ("perf/x86/intel/ds: Factor out functions for PEBS records processing")
    7087bfb0adc9 ("perf/x86/intel/ds: Clarify adaptive PEBS processing")
    faac6f105ef1 ("perf/core: Check sample_type in perf_sample_save_brstack")
    f226805bc5f6 ("perf/core: Check sample_type in perf_sample_save_callchain")
    b9c44b91476b ("perf/core: Save raw sample data conditionally based on sample type")

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

Documentation/arch/x86/topology.rst

@@ -135,6 +135,10 @@ Thread-related topology information in the kernel:
     The ID of the core to which a thread belongs. It is also printed in /proc/cpuinfo
     "core_id."
 
+  - topology_logical_core_id();
+
+    The logical core ID to which a thread belongs.
+
 
 
 System topology examples

arch/s390/kernel/perf_cpum_cf.c

@@ -981,7 +981,7 @@ static int cfdiag_push_sample(struct perf_event *event,
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
 		raw.frag.size = cpuhw->usedss;
 		raw.frag.data = cpuhw->stop;
-		perf_sample_save_raw_data(&data, &raw);
+		perf_sample_save_raw_data(&data, event, &raw);
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);

arch/s390/kernel/perf_cpum_sf.c

@@ -981,7 +981,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 	cpuhw->flags &= ~PMU_F_ENABLED;
 }
 
-/* perf_exclude_event() - Filter event
+/* perf_event_exclude() - Filter event
  * @event:	The perf event
  * @regs:	pt_regs structure
  * @sde_regs:	Sample-data-entry (sde) regs structure
@@ -990,7 +990,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
  *
  * Return non-zero if the event shall be excluded.
  */
-static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs,
+static int perf_event_exclude(struct perf_event *event, struct pt_regs *regs,
 			      struct perf_sf_sde_regs *sde_regs)
 {
 	if (event->attr.exclude_user && user_mode(regs))
@@ -1073,7 +1073,7 @@ static int perf_push_sample(struct perf_event *event,
 	data.tid_entry.pid = basic->hpp & LPP_PID_MASK;
 
 	overflow = 0;
-	if (perf_exclude_event(event, &regs, sde_regs))
+	if (perf_event_exclude(event, &regs, sde_regs))
 		goto out;
 	if (perf_event_overflow(event, &data, &regs)) {
 		overflow = 1;

arch/s390/kernel/perf_pai_crypto.c

@@ -478,7 +478,7 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump,
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
 		raw.frag.size = rawsize;
 		raw.frag.data = cpump->save;
-		perf_sample_save_raw_data(&data, &raw);
+		perf_sample_save_raw_data(&data, event, &raw);
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);

arch/s390/kernel/perf_pai_ext.c

@@ -503,7 +503,7 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump,
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
 		raw.frag.size = rawsize;
 		raw.frag.data = cpump->save;
-		perf_sample_save_raw_data(&data, &raw);
+		perf_sample_save_raw_data(&data, event, &raw);
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);

arch/x86/events/amd/core.c

@@ -1001,8 +1001,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (has_branch_stack(event))
+		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);

arch/x86/events/amd/ibs.c

@@ -31,6 +31,8 @@ static u32 ibs_caps;
 #define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
 #define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
 
+/* attr.config2 */
+#define IBS_SW_FILTER_MASK	1
 
 /*
  * IBS states:
@@ -290,6 +292,16 @@ static int perf_ibs_init(struct perf_event *event)
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
 
+	/* handle exclude_{user,kernel} in the IRQ handler */
+	if (event->attr.exclude_host || event->attr.exclude_guest ||
+	    event->attr.exclude_idle)
+		return -EINVAL;
+
+	if (!(event->attr.config2 & IBS_SW_FILTER_MASK) &&
+	    (event->attr.exclude_kernel || event->attr.exclude_user ||
+	     event->attr.exclude_hv))
+		return -EINVAL;
+
 	ret = validate_group(event);
 	if (ret)
 		return ret;
@@ -550,24 +562,14 @@ static struct attribute *attrs_empty[] = {
 	NULL,
 };
 
-static struct attribute_group empty_format_group = {
-	.name = "format",
-	.attrs = attrs_empty,
-};
-
 static struct attribute_group empty_caps_group = {
 	.name = "caps",
 	.attrs = attrs_empty,
 };
 
-static const struct attribute_group *empty_attr_groups[] = {
-	&empty_format_group,
-	&empty_caps_group,
-	NULL,
-};
-
 PMU_FORMAT_ATTR(rand_en,	"config:57");
 PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
+PMU_FORMAT_ATTR(swfilt,		"config2:0");
 PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59");
 PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
 PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
@@ -578,8 +580,9 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int
 	return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0;
 }
 
-static struct attribute *rand_en_attrs[] = {
+static struct attribute *fetch_attrs[] = {
 	&format_attr_rand_en.attr,
+	&format_attr_swfilt.attr,
 	NULL,
 };
 
@@ -593,9 +596,9 @@ static struct attribute *zen4_ibs_extensions_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group group_rand_en = {
+static struct attribute_group group_fetch_formats = {
 	.name = "format",
-	.attrs = rand_en_attrs,
+	.attrs = fetch_attrs,
 };
 
 static struct attribute_group group_fetch_l3missonly = {
@@ -611,7 +614,7 @@ static struct attribute_group group_zen4_ibs_extensions = {
 };
 
 static const struct attribute_group *fetch_attr_groups[] = {
-	&group_rand_en,
+	&group_fetch_formats,
 	&empty_caps_group,
 	NULL,
 };
@@ -628,6 +631,11 @@ cnt_ctl_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return ibs_caps & IBS_CAPS_OPCNT ? attr->mode : 0;
 }
 
+static struct attribute *op_attrs[] = {
+	&format_attr_swfilt.attr,
+	NULL,
+};
+
 static struct attribute *cnt_ctl_attrs[] = {
 	&format_attr_cnt_ctl.attr,
 	NULL,
@@ -638,6 +646,11 @@ static struct attribute *op_l3missonly_attrs[] = {
 	NULL,
 };
 
+static struct attribute_group group_op_formats = {
+	.name = "format",
+	.attrs = op_attrs,
+};
+
 static struct attribute_group group_cnt_ctl = {
 	.name = "format",
 	.attrs = cnt_ctl_attrs,
@@ -650,6 +663,12 @@ static struct attribute_group group_op_l3missonly = {
 	.is_visible = zen4_ibs_extensions_is_visible,
 };
 
+static const struct attribute_group *op_attr_groups[] = {
+	&group_op_formats,
+	&empty_caps_group,
+	NULL,
+};
+
 static const struct attribute_group *op_attr_update[] = {
 	&group_cnt_ctl,
 	&group_op_l3missonly,
@@ -667,7 +686,6 @@ static struct perf_ibs perf_ibs_fetch = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
-		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	},
 	.msr			= MSR_AMD64_IBSFETCHCTL,
 	.config_mask		= IBS_FETCH_CONFIG_MASK,
@@ -691,7 +709,6 @@ static struct perf_ibs perf_ibs_op = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
-		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
@@ -1111,6 +1128,12 @@ fail:
 		regs.flags |= PERF_EFLAGS_EXACT;
 	}
 
+	if ((event->attr.config2 & IBS_SW_FILTER_MASK) &&
+	    perf_exclude_event(event, &regs)) {
+		throttle = perf_event_account_interrupt(event);
+		goto out;
+	}
+
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
 		raw = (struct perf_raw_record){
 			.frag = {
@@ -1118,7 +1141,7 @@ fail:
 				.data = ibs_data.data,
 			},
 		};
-		perf_sample_save_raw_data(&data, &raw);
+		perf_sample_save_raw_data(&data, event, &raw);
 	}
 
 	if (perf_ibs == &perf_ibs_op)
@@ -1129,8 +1152,7 @@ fail:
 	 * recorded as part of interrupt regs. Thus we need to use rip from
 	 * interrupt regs while unwinding call stack.
 	 */
-	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+	perf_sample_save_callchain(&data, event, iregs);
-		perf_sample_save_callchain(&data, event, iregs);
 
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
@@ -1228,7 +1250,7 @@ static __init int perf_ibs_op_init(void)
 	if (ibs_caps & IBS_CAPS_ZEN4)
 		perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY;
 
-	perf_ibs_op.pmu.attr_groups = empty_attr_groups;
+	perf_ibs_op.pmu.attr_groups = op_attr_groups;
 	perf_ibs_op.pmu.attr_update = op_attr_update;
 
 	return perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");

arch/x86/events/core.c

@@ -1707,8 +1707,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event))
+		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);

arch/x86/events/intel/core.c

@@ -2826,6 +2826,9 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 			return;
 
 		idx = INTEL_PMC_IDX_FIXED_SLOTS;
+
+		if (event->attr.config1 & INTEL_TD_CFG_METRIC_CLEAR)
+			bits |= INTEL_FIXED_3_METRICS_CLEAR;
 	}
 
 	intel_set_masks(event, idx);
@@ -4081,7 +4084,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	 * is used in a metrics group, it too cannot support sampling.
 	 */
 	if (intel_pmu_has_cap(event, PERF_CAP_METRICS_IDX) && is_topdown_event(event)) {
-		if (event->attr.config1 || event->attr.config2)
+		/* The metrics_clear can only be set for the slots event */
+		if (event->attr.config1 &&
+		    (!is_slots_event(event) || (event->attr.config1 & ~INTEL_TD_CFG_METRIC_CLEAR)))
+			return -EINVAL;
+
+		if (event->attr.config2)
 			return -EINVAL;
 
 		/*
@@ -4690,6 +4698,8 @@ PMU_FORMAT_ATTR(in_tx,  "config:32"	);
 PMU_FORMAT_ATTR(in_tx_cp, "config:33"	);
 PMU_FORMAT_ATTR(eq,	"config:36"	); /* v6 + */
 
+PMU_FORMAT_ATTR(metrics_clear,	"config1:0"); /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */
+
 static ssize_t umask2_show(struct device *dev,
 			   struct device_attribute *attr,
 			   char *page)
@@ -4709,6 +4719,7 @@ static struct device_attribute format_attr_umask2  =
 static struct attribute *format_evtsel_ext_attrs[] = {
 	&format_attr_umask2.attr,
 	&format_attr_eq.attr,
+	&format_attr_metrics_clear.attr,
 	NULL
 };
 
@@ -4733,6 +4744,13 @@ evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	if (i == 1)
 		return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0;
 
+	/* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */
+	if (i == 2) {
+		union perf_capabilities intel_cap = hybrid(dev_get_drvdata(dev), intel_cap);
+
+		return intel_cap.rdpmc_metrics_clear ? attr->mode : 0;
+	}
+
 	return 0;
 }
 

arch/x86/events/intel/ds.c

@@ -1789,8 +1789,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	 * previous PMI context or an (I)RET happened between the record and
 	 * PMI.
 	 */
-	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+	perf_sample_save_callchain(data, event, iregs);
-		perf_sample_save_callchain(data, event, iregs);
 
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
@@ -1889,8 +1888,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	if (x86_pmu.intel_cap.pebs_format >= 3)
 		setup_pebs_time(event, data, pebs->tsc);
 
-	if (has_branch_stack(event))
+	perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
-		perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1917,8 +1915,6 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
 }
 
 #define PEBS_LATENCY_MASK			0xffff
-#define PEBS_CACHE_LATENCY_OFFSET		32
-#define PEBS_RETIRE_LATENCY_OFFSET		32
 
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
@@ -1932,8 +1928,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_basic *basic = __pebs;
 	void *next_record = basic + 1;
-	u64 sample_type;
+	u64 sample_type, format_group;
-	u64 format_size;
 	struct pebs_meminfo *meminfo = NULL;
 	struct pebs_gprs *gprs = NULL;
 	struct x86_perf_regs *perf_regs;
@@ -1945,7 +1940,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	perf_regs->xmm_regs = NULL;
 
 	sample_type = event->attr.sample_type;
-	format_size = basic->format_size;
+	format_group = basic->format_group;
 	perf_sample_data_init(data, 0, event->hw.last_period);
 	data->period = event->hw.last_period;
 
@@ -1957,8 +1952,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	 * previous PMI context or an (I)RET happened between the record and
 	 * PMI.
 	 */
-	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+	perf_sample_save_callchain(data, event, iregs);
-		perf_sample_save_callchain(data, event, iregs);
 
 	*regs = *iregs;
 	/* The ip in basic is EventingIP */
@@ -1967,7 +1961,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 	if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
 		if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
-			data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+			data->weight.var3_w = basic->retire_latency;
 		else
 			data->weight.var3_w = 0;
 	}
@@ -1977,12 +1971,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
 	 * Save the pointer here but process later.
 	 */
-	if (format_size & PEBS_DATACFG_MEMINFO) {
+	if (format_group & PEBS_DATACFG_MEMINFO) {
 		meminfo = next_record;
 		next_record = meminfo + 1;
 	}
 
-	if (format_size & PEBS_DATACFG_GP) {
+	if (format_group & PEBS_DATACFG_GP) {
 		gprs = next_record;
 		next_record = gprs + 1;
 
@@ -1995,14 +1989,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			adaptive_pebs_save_regs(regs, gprs);
 	}
 
-	if (format_size & PEBS_DATACFG_MEMINFO) {
+	if (format_group & PEBS_DATACFG_MEMINFO) {
 		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
-			u64 weight = meminfo->latency;
+			u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
+					meminfo->cache_latency : meminfo->mem_latency;
 
-			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) {
+			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY)
-				data->weight.var2_w = weight & PEBS_LATENCY_MASK;
+				data->weight.var2_w = meminfo->instr_latency;
-				weight >>= PEBS_CACHE_LATENCY_OFFSET;
-			}
 
 			/*
 			 * Although meminfo::latency is defined as a u64,
@@ -2010,12 +2003,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			 * in practice on Ice Lake and earlier platforms.
 			 */
 			if (sample_type & PERF_SAMPLE_WEIGHT) {
-				data->weight.full = weight ?:
+				data->weight.full = latency ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			} else {
-				data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
+				data->weight.var1_dw = (u32)latency ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			}
+
 			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
 
@@ -2036,16 +2030,16 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
-	if (format_size & PEBS_DATACFG_XMMS) {
+	if (format_group & PEBS_DATACFG_XMMS) {
 		struct pebs_xmm *xmm = next_record;
 
 		next_record = xmm + 1;
 		perf_regs->xmm_regs = xmm->xmm;
 	}
 
-	if (format_size & PEBS_DATACFG_LBRS) {
+	if (format_group & PEBS_DATACFG_LBRS) {
 		struct lbr_entry *lbr = next_record;
-		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+		int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT)
 					& 0xff) + 1;
 		next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
@@ -2055,11 +2049,11 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
-	WARN_ONCE(next_record != __pebs + (format_size >> 48),
+	WARN_ONCE(next_record != __pebs + basic->format_size,
-			"PEBS record size %llu, expected %llu, config %llx\n",
+			"PEBS record size %u, expected %llu, config %llx\n",
-			format_size >> 48,
+			basic->format_size,
 			(u64)(next_record - __pebs),
-			basic->format_size);
+			format_group);
 }
 
 static inline void *
@@ -2170,46 +2164,33 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	return 0;
 }
 
+typedef void (*setup_fn)(struct perf_event *, struct pt_regs *, void *,
+			 struct perf_sample_data *, struct pt_regs *);
+
+static struct pt_regs dummy_iregs;
+
 static __always_inline void
 __intel_pmu_pebs_event(struct perf_event *event,
 		       struct pt_regs *iregs,
+		       struct pt_regs *regs,
 		       struct perf_sample_data *data,
-		       void *base, void *top,
+		       void *at,
-		       int bit, int count,
+		       setup_fn setup_sample)
-		       void (*setup_sample)(struct perf_event *,
+{
-					    struct pt_regs *,
+	setup_sample(event, iregs, at, data, regs);
-					    void *,
+	perf_event_output(event, data, regs);
-					    struct perf_sample_data *,
+}
-					    struct pt_regs *))
+
+static __always_inline void
+__intel_pmu_pebs_last_event(struct perf_event *event,
+			    struct pt_regs *iregs,
+			    struct pt_regs *regs,
+			    struct perf_sample_data *data,
+			    void *at,
+			    int count,
+			    setup_fn setup_sample)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	struct x86_perf_regs perf_regs;
-	struct pt_regs *regs = &perf_regs.regs;
-	void *at = get_next_pebs_record_by_bit(base, top, bit);
-	static struct pt_regs dummy_iregs;
-
-	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		/*
-		 * Now, auto-reload is only enabled in fixed period mode.
-		 * The reload value is always hwc->sample_period.
-		 * May need to change it, if auto-reload is enabled in
-		 * freq mode later.
-		 */
-		intel_pmu_save_and_restart_reload(event, count);
-	} else if (!intel_pmu_save_and_restart(event))
-		return;
-
-	if (!iregs)
-		iregs = &dummy_iregs;
-
-	while (count > 1) {
-		setup_sample(event, iregs, at, data, regs);
-		perf_event_output(event, data, regs);
-		at += cpuc->pebs_record_size;
-		at = get_next_pebs_record_by_bit(at, top, bit);
-		count--;
-	}
 
 	setup_sample(event, iregs, at, data, regs);
 	if (iregs == &dummy_iregs) {
@@ -2228,6 +2209,44 @@ __intel_pmu_pebs_event(struct perf_event *event,
 		if (perf_event_overflow(event, data, regs))
 			x86_pmu_stop(event, 0);
 	}
+
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		/*
+		 * Now, auto-reload is only enabled in fixed period mode.
+		 * The reload value is always hwc->sample_period.
+		 * May need to change it, if auto-reload is enabled in
+		 * freq mode later.
+		 */
+		intel_pmu_save_and_restart_reload(event, count);
+	} else
+		intel_pmu_save_and_restart(event);
+}
+
+static __always_inline void
+__intel_pmu_pebs_events(struct perf_event *event,
+			struct pt_regs *iregs,
+			struct perf_sample_data *data,
+			void *base, void *top,
+			int bit, int count,
+			setup_fn setup_sample)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+	int cnt = count;
+
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	while (cnt > 1) {
+		__intel_pmu_pebs_event(event, iregs, regs, data, at, setup_sample);
+		at += cpuc->pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		cnt--;
+	}
+
+	__intel_pmu_pebs_last_event(event, iregs, regs, data, at, count, setup_sample);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
@@ -2264,8 +2283,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
+	__intel_pmu_pebs_events(event, iregs, data, at, top, 0, n,
-			       setup_pebs_fixed_sample_data);
+				setup_pebs_fixed_sample_data);
 }
 
 static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
@@ -2396,9 +2415,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		}
 
 		if (counts[bit]) {
-			__intel_pmu_pebs_event(event, iregs, data, base,
+			__intel_pmu_pebs_events(event, iregs, data, base,
-					       top, bit, counts[bit],
+						top, bit, counts[bit],
-					       setup_pebs_fixed_sample_data);
+						setup_pebs_fixed_sample_data);
 		}
 	}
 }
@@ -2406,8 +2425,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS];
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	struct pebs_basic *basic;
 	struct perf_event *event;
 	void *base, *at, *top;
 	int bit;
@@ -2429,30 +2452,41 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 		return;
 	}
 
-	for (at = base; at < top; at += cpuc->pebs_record_size) {
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	/* Process all but the last event for each counter. */
+	for (at = base; at < top; at += basic->format_size) {
 		u64 pebs_status;
 
-		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+		basic = at;
-		pebs_status &= mask;
+		if (basic->format_size != cpuc->pebs_record_size)
+			continue;
 
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
+		pebs_status = basic->applicable_counters & cpuc->pebs_enabled & mask;
-			counts[bit]++;
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) {
+			event = cpuc->events[bit];
+
+			if (WARN_ON_ONCE(!event) ||
+			    WARN_ON_ONCE(!event->attr.precise_ip))
+				continue;
+
+			if (counts[bit]++) {
+				__intel_pmu_pebs_event(event, iregs, regs, data, last[bit],
+						       setup_pebs_adaptive_sample_data);
+			}
+			last[bit] = at;
+		}
 	}
 
 	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
-		if (counts[bit] == 0)
+		if (!counts[bit])
 			continue;
 
 		event = cpuc->events[bit];
-		if (WARN_ON_ONCE(!event))
-			continue;
 
-		if (WARN_ON_ONCE(!event->attr.precise_ip))
+		__intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit],
-			continue;
+					    counts[bit], setup_pebs_adaptive_sample_data);
-
-		__intel_pmu_pebs_event(event, iregs, data, base,
-				       top, bit, counts[bit],
-				       setup_pebs_adaptive_sample_data);
 	}
 }
 

arch/x86/events/intel/uncore.c

@@ -745,7 +745,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (pmu->func_id < 0)
+	if (!pmu->registered)
 		return -ENOENT;
 
 	/* Sampling not supported yet */
@@ -992,7 +992,7 @@ static void uncore_types_exit(struct intel_uncore_type **types)
 		uncore_type_exit(*types);
 }
 
-static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
+static int __init uncore_type_init(struct intel_uncore_type *type)
 {
 	struct intel_uncore_pmu *pmus;
 	size_t size;
@@ -1005,7 +1005,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	size = uncore_max_dies() * sizeof(struct intel_uncore_box *);
 
 	for (i = 0; i < type->num_boxes; i++) {
-		pmus[i].func_id	= setid ? i : -1;
 		pmus[i].pmu_idx	= i;
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
@@ -1055,12 +1054,12 @@ err:
 }
 
 static int __init
-uncore_types_init(struct intel_uncore_type **types, bool setid)
+uncore_types_init(struct intel_uncore_type **types)
 {
 	int ret;
 
 	for (; *types; types++) {
-		ret = uncore_type_init(*types, setid);
+		ret = uncore_type_init(*types);
 		if (ret)
 			return ret;
 	}
@@ -1160,11 +1159,6 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev,
 	if (!box)
 		return -ENOMEM;
 
-	if (pmu->func_id < 0)
-		pmu->func_id = pdev->devfn;
-	else
-		WARN_ON_ONCE(pmu->func_id != pdev->devfn);
-
 	atomic_inc(&box->refcnt);
 	box->dieid = die;
 	box->pci_dev = pdev;
@@ -1410,7 +1404,7 @@ static int __init uncore_pci_init(void)
 		goto err;
 	}
 
-	ret = uncore_types_init(uncore_pci_uncores, false);
+	ret = uncore_types_init(uncore_pci_uncores);
 	if (ret)
 		goto errtype;
 
@@ -1678,7 +1672,7 @@ static int __init uncore_cpu_init(void)
 {
 	int ret;
 
-	ret = uncore_types_init(uncore_msr_uncores, true);
+	ret = uncore_types_init(uncore_msr_uncores);
 	if (ret)
 		goto err;
 
@@ -1697,7 +1691,7 @@ static int __init uncore_mmio_init(void)
 	struct intel_uncore_type **types = uncore_mmio_uncores;
 	int ret;
 
-	ret = uncore_types_init(types, true);
+	ret = uncore_types_init(types);
 	if (ret)
 		goto err;
 

arch/x86/events/intel/uncore.h

@@ -125,7 +125,6 @@ struct intel_uncore_pmu {
 	struct pmu			pmu;
 	char				name[UNCORE_PMU_NAME_LEN];
 	int				pmu_idx;
-	int				func_id;
 	bool				registered;
 	atomic_t			activeboxes;
 	cpumask_t			cpu_mask;

arch/x86/events/intel/uncore_snb.c

@@ -910,7 +910,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (pmu->func_id < 0)
+	if (!pmu->registered)
 		return -ENOENT;
 
 	/* Sampling not supported yet */

arch/x86/events/intel/uncore_snbep.c

@@ -6684,17 +6684,8 @@ void spr_uncore_mmio_init(void)
 /* GNR uncore support */
 
 #define UNCORE_GNR_NUM_UNCORE_TYPES	23
-#define UNCORE_GNR_TYPE_15		15
-#define UNCORE_GNR_B2UPI		18
-#define UNCORE_GNR_TYPE_21		21
-#define UNCORE_GNR_TYPE_22		22
 
 int gnr_uncore_units_ignore[] = {
-	UNCORE_SPR_UPI,
-	UNCORE_GNR_TYPE_15,
-	UNCORE_GNR_B2UPI,
-	UNCORE_GNR_TYPE_21,
-	UNCORE_GNR_TYPE_22,
 	UNCORE_IGNORE_END
 };
 
@@ -6703,6 +6694,31 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct intel_uncore_type gnr_uncore_pciex8 = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "pciex8",
+};
+
+static struct intel_uncore_type gnr_uncore_pciex16 = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "pciex16",
+};
+
+static struct intel_uncore_type gnr_uncore_upi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "upi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2upi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "b2upi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2hot = {
+	.name			= "b2hot",
+	.attr_update		= uncore_alias_groups,
+};
+
 static struct intel_uncore_type gnr_uncore_b2cmi = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "b2cmi",
@@ -6727,21 +6743,21 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	&gnr_uncore_ubox,
 	&spr_uncore_imc,
 	NULL,
+	&gnr_uncore_upi,
 	NULL,
 	NULL,
 	NULL,
+	&spr_uncore_cxlcm,
+	&spr_uncore_cxldp,
 	NULL,
-	NULL,
+	&gnr_uncore_b2hot,
-	NULL,
-	NULL,
-	NULL,
 	&gnr_uncore_b2cmi,
 	&gnr_uncore_b2cxl,
-	NULL,
+	&gnr_uncore_b2upi,
 	NULL,
 	&gnr_uncore_mdf_sbo,
-	NULL,
+	&gnr_uncore_pciex16,
-	NULL,
+	&gnr_uncore_pciex8,
 };
 
 static struct freerunning_counters gnr_iio_freerunning[] = {

arch/x86/events/perf_event.h

@@ -624,6 +624,7 @@ union perf_capabilities {
 		u64	pebs_output_pt_available:1;
 		u64	pebs_timing_info:1;
 		u64	anythread_deprecated:1;
+		u64	rdpmc_metrics_clear:1;
 	};
 	u64	capabilities;
 };

arch/x86/events/rapl.c

@@ -39,6 +39,10 @@
  *	  event: rapl_energy_psys
  *    perf code: 0x5
  *
+ *  core counter: consumption of a single physical core
+ *	  event: rapl_energy_core (power_core PMU)
+ *    perf code: 0x1
+ *
  * We manage those counters as free running (read-only). They may be
  * use simultaneously by other tools, such as turbostat.
  *
@@ -70,18 +74,22 @@ MODULE_LICENSE("GPL");
 /*
  * RAPL energy status counters
  */
-enum perf_rapl_events {
+enum perf_rapl_pkg_events {
 	PERF_RAPL_PP0 = 0,		/* all cores */
 	PERF_RAPL_PKG,			/* entire package */
 	PERF_RAPL_RAM,			/* DRAM */
 	PERF_RAPL_PP1,			/* gpu */
 	PERF_RAPL_PSYS,			/* psys */
 
-	PERF_RAPL_MAX,
+	PERF_RAPL_PKG_EVENTS_MAX,
-	NR_RAPL_DOMAINS = PERF_RAPL_MAX,
+	NR_RAPL_PKG_DOMAINS = PERF_RAPL_PKG_EVENTS_MAX,
 };
 
-static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
+#define PERF_RAPL_CORE			0		/* single core */
+#define PERF_RAPL_CORE_EVENTS_MAX	1
+#define NR_RAPL_CORE_DOMAINS		PERF_RAPL_CORE_EVENTS_MAX
+
+static const char *const rapl_pkg_domain_names[NR_RAPL_PKG_DOMAINS] __initconst = {
 	"pp0-core",
 	"package",
 	"dram",
@@ -89,6 +97,8 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
 	"psys",
 };
 
+static const char *const rapl_core_domain_name __initconst = "core";
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -112,7 +122,7 @@ static struct perf_pmu_events_attr event_attr_##v = {				\
  *	     considered as either pkg-scope or die-scope, and we are considering
  *	     them as die-scope.
  */
-#define rapl_pmu_is_pkg_scope()				\
+#define rapl_pkg_pmu_is_pkg_scope()				\
 	(boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||	\
 	 boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
 
@@ -129,7 +139,8 @@ struct rapl_pmu {
 struct rapl_pmus {
 	struct pmu		pmu;
 	unsigned int		nr_rapl_pmu;
-	struct rapl_pmu		*pmus[] __counted_by(nr_rapl_pmu);
+	unsigned int		cntr_mask;
+	struct rapl_pmu		*rapl_pmu[] __counted_by(nr_rapl_pmu);
 };
 
 enum rapl_unit_quirk {
@@ -139,44 +150,43 @@ enum rapl_unit_quirk {
 };
 
 struct rapl_model {
-	struct perf_msr *rapl_msrs;
+	struct perf_msr *rapl_pkg_msrs;
-	unsigned long	events;
+	struct perf_msr *rapl_core_msrs;
+	unsigned long	pkg_events;
+	unsigned long	core_events;
 	unsigned int	msr_power_unit;
 	enum rapl_unit_quirk	unit_quirk;
 };
 
  /* 1/2^hw_unit Joule */
-static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
+static int rapl_pkg_hw_unit[NR_RAPL_PKG_DOMAINS] __read_mostly;
-static struct rapl_pmus *rapl_pmus;
+static int rapl_core_hw_unit __read_mostly;
-static unsigned int rapl_cntr_mask;
+static struct rapl_pmus *rapl_pmus_pkg;
+static struct rapl_pmus *rapl_pmus_core;
 static u64 rapl_timer_ms;
-static struct perf_msr *rapl_msrs;
+static struct rapl_model *rapl_model;
 
 /*
- * Helper functions to get the correct topology macros according to the
+ * Helper function to get the correct topology id according to the
  * RAPL PMU scope.
  */
-static inline unsigned int get_rapl_pmu_idx(int cpu)
+static inline unsigned int get_rapl_pmu_idx(int cpu, int scope)
 {
-	return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) :
-					 topology_logical_die_id(cpu);
-}
-
-static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu)
-{
-	return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) :
-					 topology_die_cpumask(cpu);
-}
-
-static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
-{
-	unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu);
-
 	/*
-	 * The unsigned check also catches the '-1' return value for non
+	 * Returns unsigned int, which converts the '-1' return value
-	 * existent mappings in the topology map.
+	 * (for non-existent mappings in topology map) to UINT_MAX, so
+	 * the error check in the caller is simplified.
 	 */
-	return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL;
+	switch (scope) {
+	case PERF_PMU_SCOPE_PKG:
+		return topology_logical_package_id(cpu);
+	case PERF_PMU_SCOPE_DIE:
+		return topology_logical_die_id(cpu);
+	case PERF_PMU_SCOPE_CORE:
+		return topology_logical_core_id(cpu);
+	default:
+		return -EINVAL;
+	}
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -186,19 +196,20 @@ static inline u64 rapl_read_counter(struct perf_event *event)
 	return raw;
 }
 
-static inline u64 rapl_scale(u64 v, int cfg)
+static inline u64 rapl_scale(u64 v, struct perf_event *event)
 {
-	if (cfg > NR_RAPL_DOMAINS) {
+	int hw_unit = rapl_pkg_hw_unit[event->hw.config - 1];
-		pr_warn("Invalid domain %d, failed to scale data\n", cfg);
+
-		return v;
+	if (event->pmu->scope == PERF_PMU_SCOPE_CORE)
-	}
+		hw_unit = rapl_core_hw_unit;
+
 	/*
 	 * scale delta to smallest unit (1/2^32)
 	 * users must then scale back: count * 1/(1e9*2^32) to get Joules
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - rapl_hw_unit[cfg - 1]);
+	return v << (32 - hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -225,7 +236,7 @@ static u64 rapl_event_update(struct perf_event *event)
 	delta = (new_raw_count << shift) - (prev_raw_count << shift);
 	delta >>= shift;
 
-	sdelta = rapl_scale(delta, event->hw.config);
+	sdelta = rapl_scale(delta, event);
 
 	local64_add(sdelta, &event->count);
 
@@ -240,34 +251,34 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 
 static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 {
-	struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
+	struct rapl_pmu *rapl_pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
 	struct perf_event *event;
 	unsigned long flags;
 
-	if (!pmu->n_active)
+	if (!rapl_pmu->n_active)
 		return HRTIMER_NORESTART;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
 
-	list_for_each_entry(event, &pmu->active_list, active_entry)
+	list_for_each_entry(event, &rapl_pmu->active_list, active_entry)
 		rapl_event_update(event);
 
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 
-	hrtimer_forward_now(hrtimer, pmu->timer_interval);
+	hrtimer_forward_now(hrtimer, rapl_pmu->timer_interval);
 
 	return HRTIMER_RESTART;
 }
 
-static void rapl_hrtimer_init(struct rapl_pmu *pmu)
+static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu)
 {
-	struct hrtimer *hr = &pmu->hrtimer;
+	struct hrtimer *hr = &rapl_pmu->hrtimer;
 
 	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hr->function = rapl_hrtimer_handle;
 }
 
-static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
+static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu,
 				   struct perf_event *event)
 {
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -275,39 +286,39 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 
 	event->hw.state = 0;
 
-	list_add_tail(&event->active_entry, &pmu->active_list);
+	list_add_tail(&event->active_entry, &rapl_pmu->active_list);
 
 	local64_set(&event->hw.prev_count, rapl_read_counter(event));
 
-	pmu->n_active++;
+	rapl_pmu->n_active++;
-	if (pmu->n_active == 1)
+	if (rapl_pmu->n_active == 1)
-		rapl_start_hrtimer(pmu);
+		rapl_start_hrtimer(rapl_pmu);
 }
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = event->pmu_private;
+	struct rapl_pmu *rapl_pmu = event->pmu_private;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
-	__rapl_pmu_event_start(pmu, event);
+	__rapl_pmu_event_start(rapl_pmu, event);
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 }
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = event->pmu_private;
+	struct rapl_pmu *rapl_pmu = event->pmu_private;
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
 
 	/* mark event as deactivated and stopped */
 	if (!(hwc->state & PERF_HES_STOPPED)) {
-		WARN_ON_ONCE(pmu->n_active <= 0);
+		WARN_ON_ONCE(rapl_pmu->n_active <= 0);
-		pmu->n_active--;
+		rapl_pmu->n_active--;
-		if (pmu->n_active == 0)
+		if (rapl_pmu->n_active == 0)
-			hrtimer_cancel(&pmu->hrtimer);
+			hrtimer_cancel(&rapl_pmu->hrtimer);
 
 		list_del(&event->active_entry);
 
@@ -325,23 +336,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 }
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = event->pmu_private;
+	struct rapl_pmu *rapl_pmu = event->pmu_private;
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
 
 	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_START)
-		__rapl_pmu_event_start(pmu, event);
+		__rapl_pmu_event_start(rapl_pmu, event);
 
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 
 	return 0;
 }
@@ -354,12 +365,14 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags)
 static int rapl_pmu_event_init(struct perf_event *event)
 {
 	u64 cfg = event->attr.config & RAPL_EVENT_MASK;
-	int bit, ret = 0;
+	int bit, rapl_pmus_scope, ret = 0;
-	struct rapl_pmu *pmu;
+	struct rapl_pmu *rapl_pmu;
+	unsigned int rapl_pmu_idx;
+	struct rapl_pmus *rapl_pmus;
 
-	/* only look at RAPL events */
+	/* unsupported modes and filters */
-	if (event->attr.type != rapl_pmus->pmu.type)
+	if (event->attr.sample_period) /* no sampling */
-		return -ENOENT;
+		return -EINVAL;
 
 	/* check only supported bits are set */
 	if (event->attr.config & ~RAPL_EVENT_MASK)
@@ -368,26 +381,49 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	if (event->cpu < 0)
 		return -EINVAL;
 
-	if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
+	rapl_pmus = container_of(event->pmu, struct rapl_pmus, pmu);
+	if (!rapl_pmus)
 		return -EINVAL;
+	rapl_pmus_scope = rapl_pmus->pmu.scope;
 
-	cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
+	if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) {
-	bit = cfg - 1;
+		/* only look at RAPL package events */
+		if (event->attr.type != rapl_pmus_pkg->pmu.type)
+			return -ENOENT;
+
+		cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1);
+		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
+			return -EINVAL;
+
+		bit = cfg - 1;
+		event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr;
+	} else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) {
+		/* only look at RAPL core events */
+		if (event->attr.type != rapl_pmus_core->pmu.type)
+			return -ENOENT;
+
+		cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1);
+		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
+			return -EINVAL;
+
+		bit = cfg - 1;
+		event->hw.event_base = rapl_model->rapl_core_msrs[bit].msr;
+	} else
+		return -EINVAL;
 
 	/* check event supported */
-	if (!(rapl_cntr_mask & (1 << bit)))
+	if (!(rapl_pmus->cntr_mask & (1 << bit)))
 		return -EINVAL;
 
-	/* unsupported modes and filters */
+	rapl_pmu_idx = get_rapl_pmu_idx(event->cpu, rapl_pmus_scope);
-	if (event->attr.sample_period) /* no sampling */
+	if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu)
 		return -EINVAL;
-
 	/* must be done before validate_group */
-	pmu = cpu_to_rapl_pmu(event->cpu);
+	rapl_pmu = rapl_pmus->rapl_pmu[rapl_pmu_idx];
-	if (!pmu)
+	if (!rapl_pmu)
 		return -EINVAL;
-	event->pmu_private = pmu;
+
-	event->hw.event_base = rapl_msrs[bit].msr;
+	event->pmu_private = rapl_pmu;
 	event->hw.config = cfg;
 	event->hw.idx = bit;
 
@@ -404,12 +440,14 @@ RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
 RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
 RAPL_EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
 RAPL_EVENT_ATTR_STR(energy-psys,   rapl_psys, "event=0x05");
+RAPL_EVENT_ATTR_STR(energy-core,   rapl_core, "event=0x01");
 
 RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-psys.unit,   rapl_psys_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-core.unit,   rapl_core_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
@@ -419,6 +457,7 @@ RAPL_EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890
 RAPL_EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
 RAPL_EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
 RAPL_EVENT_ATTR_STR(energy-psys.scale,   rapl_psys_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-core.scale,   rapl_core_scale, "2.3283064365386962890625e-10");
 
 /*
  * There are no default events, but we need to create
@@ -451,6 +490,12 @@ static const struct attribute_group *rapl_attr_groups[] = {
 	NULL,
 };
 
+static const struct attribute_group *rapl_core_attr_groups[] = {
+	&rapl_pmu_format_group,
+	&rapl_pmu_events_group,
+	NULL,
+};
+
 static struct attribute *rapl_events_cores[] = {
 	EVENT_PTR(rapl_cores),
 	EVENT_PTR(rapl_cores_unit),
@@ -511,6 +556,18 @@ static struct attribute_group rapl_events_psys_group = {
 	.attrs = rapl_events_psys,
 };
 
+static struct attribute *rapl_events_core[] = {
+	EVENT_PTR(rapl_core),
+	EVENT_PTR(rapl_core_unit),
+	EVENT_PTR(rapl_core_scale),
+	NULL,
+};
+
+static struct attribute_group rapl_events_core_group = {
+	.name  = "events",
+	.attrs = rapl_events_core,
+};
+
 static bool test_msr(int idx, void *data)
 {
 	return test_bit(idx, (unsigned long *) data);
@@ -536,11 +593,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = {
 };
 
 /*
- * Force to PERF_RAPL_MAX size due to:
+ * Force to PERF_RAPL_PKG_EVENTS_MAX size due to:
- * - perf_msr_probe(PERF_RAPL_MAX)
+ * - perf_msr_probe(PERF_RAPL_PKG_EVENTS_MAX)
  * - want to use same event codes across both architectures
  */
-static struct perf_msr amd_rapl_msrs[] = {
+static struct perf_msr amd_rapl_pkg_msrs[] = {
 	[PERF_RAPL_PP0]  = { 0, &rapl_events_cores_group, NULL, false, 0 },
 	[PERF_RAPL_PKG]  = { MSR_AMD_PKG_ENERGY_STATUS,  &rapl_events_pkg_group,   test_msr, false, RAPL_MSR_MASK },
 	[PERF_RAPL_RAM]  = { 0, &rapl_events_ram_group,   NULL, false, 0 },
@@ -548,18 +605,25 @@ static struct perf_msr amd_rapl_msrs[] = {
 	[PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group,  NULL, false, 0 },
 };
 
-static int rapl_check_hw_unit(struct rapl_model *rm)
+static struct perf_msr amd_rapl_core_msrs[] = {
+	[PERF_RAPL_CORE] = { MSR_AMD_CORE_ENERGY_STATUS, &rapl_events_core_group,
+				 test_msr, false, RAPL_MSR_MASK },
+};
+
+static int rapl_check_hw_unit(void)
 {
 	u64 msr_rapl_power_unit_bits;
 	int i;
 
 	/* protect rdmsrl() to handle virtualization */
-	if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits))
+	if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits))
 		return -1;
-	for (i = 0; i < NR_RAPL_DOMAINS; i++)
+	for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++)
-		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
+		rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 
-	switch (rm->unit_quirk) {
+	rapl_core_hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
+
+	switch (rapl_model->unit_quirk) {
 	/*
 	 * DRAM domain on HSW server and KNL has fixed energy unit which can be
 	 * different than the unit from power unit MSR. See
@@ -567,17 +631,16 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
 	case RAPL_UNIT_QUIRK_INTEL_HSW:
-		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		rapl_pkg_hw_unit[PERF_RAPL_RAM] = 16;
 		break;
 	/* SPR uses a fixed energy unit for Psys domain. */
 	case RAPL_UNIT_QUIRK_INTEL_SPR:
-		rapl_hw_unit[PERF_RAPL_PSYS] = 0;
+		rapl_pkg_hw_unit[PERF_RAPL_PSYS] = 0;
 		break;
 	default:
 		break;
 	}
 
-
 	/*
 	 * Calculate the timer rate:
 	 * Use reference of 200W for scaling the timeout to avoid counter
@@ -586,9 +649,9 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	 * if hw unit is 32, then we use 2 ms 1/200/2
 	 */
 	rapl_timer_ms = 2;
-	if (rapl_hw_unit[0] < 32) {
+	if (rapl_pkg_hw_unit[0] < 32) {
 		rapl_timer_ms = (1000 / (2 * 100));
-		rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1));
+		rapl_timer_ms *= (1ULL << (32 - rapl_pkg_hw_unit[0] - 1));
 	}
 	return 0;
 }
@@ -596,24 +659,32 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 static void __init rapl_advertise(void)
 {
 	int i;
+	int num_counters = hweight32(rapl_pmus_pkg->cntr_mask);
+
+	if (rapl_pmus_core)
+		num_counters += hweight32(rapl_pmus_core->cntr_mask);
 
 	pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n",
-		hweight32(rapl_cntr_mask), rapl_timer_ms);
+		num_counters, rapl_timer_ms);
 
-	for (i = 0; i < NR_RAPL_DOMAINS; i++) {
+	for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) {
-		if (rapl_cntr_mask & (1 << i)) {
+		if (rapl_pmus_pkg->cntr_mask & (1 << i)) {
 			pr_info("hw unit of domain %s 2^-%d Joules\n",
-				rapl_domain_names[i], rapl_hw_unit[i]);
+				rapl_pkg_domain_names[i], rapl_pkg_hw_unit[i]);
 		}
 	}
+
+	if (rapl_pmus_core && (rapl_pmus_core->cntr_mask & (1 << PERF_RAPL_CORE)))
+		pr_info("hw unit of domain %s 2^-%d Joules\n",
+			rapl_core_domain_name, rapl_core_hw_unit);
 }
 
-static void cleanup_rapl_pmus(void)
+static void cleanup_rapl_pmus(struct rapl_pmus *rapl_pmus)
 {
 	int i;
 
 	for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++)
-		kfree(rapl_pmus->pmus[i]);
+		kfree(rapl_pmus->rapl_pmu[i]);
 	kfree(rapl_pmus);
 }
 
@@ -626,46 +697,60 @@ static const struct attribute_group *rapl_attr_update[] = {
 	NULL,
 };
 
-static int __init init_rapl_pmu(void)
+static const struct attribute_group *rapl_core_attr_update[] = {
+	&rapl_events_core_group,
+	NULL,
+};
+
+static int __init init_rapl_pmu(struct rapl_pmus *rapl_pmus)
 {
-	struct rapl_pmu *pmu;
+	struct rapl_pmu *rapl_pmu;
 	int idx;
 
 	for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) {
-		pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
+		rapl_pmu = kzalloc(sizeof(*rapl_pmu), GFP_KERNEL);
-		if (!pmu)
+		if (!rapl_pmu)
 			goto free;
 
-		raw_spin_lock_init(&pmu->lock);
+		raw_spin_lock_init(&rapl_pmu->lock);
-		INIT_LIST_HEAD(&pmu->active_list);
+		INIT_LIST_HEAD(&rapl_pmu->active_list);
-		pmu->pmu = &rapl_pmus->pmu;
+		rapl_pmu->pmu = &rapl_pmus->pmu;
-		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-		rapl_hrtimer_init(pmu);
+		rapl_hrtimer_init(rapl_pmu);
 
-		rapl_pmus->pmus[idx] = pmu;
+		rapl_pmus->rapl_pmu[idx] = rapl_pmu;
 	}
 
 	return 0;
 free:
 	for (; idx > 0; idx--)
-		kfree(rapl_pmus->pmus[idx - 1]);
+		kfree(rapl_pmus->rapl_pmu[idx - 1]);
 	return -ENOMEM;
 }
 
-static int __init init_rapl_pmus(void)
+static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_scope,
+				 const struct attribute_group **rapl_attr_groups,
+				 const struct attribute_group **rapl_attr_update)
 {
 	int nr_rapl_pmu = topology_max_packages();
-	int rapl_pmu_scope = PERF_PMU_SCOPE_PKG;
+	struct rapl_pmus *rapl_pmus;
 
-	if (!rapl_pmu_is_pkg_scope()) {
+	/*
-		nr_rapl_pmu *= topology_max_dies_per_package();
+	 * rapl_pmu_scope must be either PKG, DIE or CORE
-		rapl_pmu_scope = PERF_PMU_SCOPE_DIE;
+	 */
-	}
+	if (rapl_pmu_scope == PERF_PMU_SCOPE_DIE)
+		nr_rapl_pmu	*= topology_max_dies_per_package();
+	else if (rapl_pmu_scope == PERF_PMU_SCOPE_CORE)
+		nr_rapl_pmu	*= topology_num_cores_per_package();
+	else if (rapl_pmu_scope != PERF_PMU_SCOPE_PKG)
+		return -EINVAL;
 
-	rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL);
+	rapl_pmus = kzalloc(struct_size(rapl_pmus, rapl_pmu, nr_rapl_pmu), GFP_KERNEL);
 	if (!rapl_pmus)
 		return -ENOMEM;
 
+	*rapl_pmus_ptr = rapl_pmus;
+
 	rapl_pmus->nr_rapl_pmu		= nr_rapl_pmu;
 	rapl_pmus->pmu.attr_groups	= rapl_attr_groups;
 	rapl_pmus->pmu.attr_update	= rapl_attr_update;
@@ -680,75 +765,77 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.module		= THIS_MODULE;
 	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
 
-	return init_rapl_pmu();
+	return init_rapl_pmu(rapl_pmus);
 }
 
 static struct rapl_model model_snb = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_snbep = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsw = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsx = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_knl = {
-	.events		= BIT(PERF_RAPL_PKG) |
+	.pkg_events	= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_skl = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_spr = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PSYS),
 	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_SPR,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_spr_msrs,
+	.rapl_pkg_msrs	= intel_rapl_spr_msrs,
 };
 
 static struct rapl_model model_amd_hygon = {
-	.events		= BIT(PERF_RAPL_PKG),
+	.pkg_events	= BIT(PERF_RAPL_PKG),
+	.core_events	= BIT(PERF_RAPL_CORE),
 	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
-	.rapl_msrs      = amd_rapl_msrs,
+	.rapl_pkg_msrs	= amd_rapl_pkg_msrs,
+	.rapl_core_msrs	= amd_rapl_core_msrs,
 };
 
 static const struct x86_cpu_id rapl_model_match[] __initconst = {
@@ -804,45 +891,73 @@ MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
 static int __init rapl_pmu_init(void)
 {
 	const struct x86_cpu_id *id;
-	struct rapl_model *rm;
+	int rapl_pkg_pmu_scope = PERF_PMU_SCOPE_DIE;
 	int ret;
 
+	if (rapl_pkg_pmu_is_pkg_scope())
+		rapl_pkg_pmu_scope = PERF_PMU_SCOPE_PKG;
+
 	id = x86_match_cpu(rapl_model_match);
 	if (!id)
 		return -ENODEV;
 
-	rm = (struct rapl_model *) id->driver_data;
+	rapl_model = (struct rapl_model *) id->driver_data;
 
-	rapl_msrs = rm->rapl_msrs;
+	ret = rapl_check_hw_unit();
-
-	rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
-					false, (void *) &rm->events);
-
-	ret = rapl_check_hw_unit(rm);
 	if (ret)
 		return ret;
 
-	ret = init_rapl_pmus();
+	ret = init_rapl_pmus(&rapl_pmus_pkg, rapl_pkg_pmu_scope, rapl_attr_groups,
+			     rapl_attr_update);
 	if (ret)
 		return ret;
 
-	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
+	rapl_pmus_pkg->cntr_mask = perf_msr_probe(rapl_model->rapl_pkg_msrs,
+						  PERF_RAPL_PKG_EVENTS_MAX, false,
+						  (void *) &rapl_model->pkg_events);
+
+	ret = perf_pmu_register(&rapl_pmus_pkg->pmu, "power", -1);
 	if (ret)
 		goto out;
 
+	if (rapl_model->core_events) {
+		ret = init_rapl_pmus(&rapl_pmus_core, PERF_PMU_SCOPE_CORE,
+				     rapl_core_attr_groups,
+				     rapl_core_attr_update);
+		if (ret) {
+			pr_warn("power-core PMU initialization failed (%d)\n", ret);
+			goto core_init_failed;
+		}
+
+		rapl_pmus_core->cntr_mask = perf_msr_probe(rapl_model->rapl_core_msrs,
+						     PERF_RAPL_CORE_EVENTS_MAX, false,
+						     (void *) &rapl_model->core_events);
+
+		ret = perf_pmu_register(&rapl_pmus_core->pmu, "power_core", -1);
+		if (ret) {
+			pr_warn("power-core PMU registration failed (%d)\n", ret);
+			cleanup_rapl_pmus(rapl_pmus_core);
+		}
+	}
+
+core_init_failed:
 	rapl_advertise();
 	return 0;
 
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
-	cleanup_rapl_pmus();
+	cleanup_rapl_pmus(rapl_pmus_pkg);
 	return ret;
 }
 module_init(rapl_pmu_init);
 
 static void __exit intel_rapl_exit(void)
 {
-	perf_pmu_unregister(&rapl_pmus->pmu);
+	if (rapl_pmus_core) {
-	cleanup_rapl_pmus();
+		perf_pmu_unregister(&rapl_pmus_core->pmu);
+		cleanup_rapl_pmus(rapl_pmus_core);
+	}
+	perf_pmu_unregister(&rapl_pmus_pkg->pmu);
+	cleanup_rapl_pmus(rapl_pmus_pkg);
 }
 module_exit(intel_rapl_exit);

arch/x86/include/asm/perf_event.h

@@ -41,6 +41,7 @@
 #define INTEL_FIXED_0_USER				(1ULL << 1)
 #define INTEL_FIXED_0_ANYTHREAD			(1ULL << 2)
 #define INTEL_FIXED_0_ENABLE_PMI			(1ULL << 3)
+#define INTEL_FIXED_3_METRICS_CLEAR			(1ULL << 2)
 
 #define HSW_IN_TX					(1ULL << 32)
 #define HSW_IN_TX_CHECKPOINTED				(1ULL << 33)
@@ -372,6 +373,9 @@ static inline bool use_fixed_pseudo_encoding(u64 code)
 #define INTEL_TD_METRIC_MAX			INTEL_TD_METRIC_MEM_BOUND
 #define INTEL_TD_METRIC_NUM			8
 
+#define INTEL_TD_CFG_METRIC_CLEAR_BIT		0
+#define INTEL_TD_CFG_METRIC_CLEAR		BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT)
+
 static inline bool is_metric_idx(int idx)
 {
 	return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM;
@@ -422,7 +426,9 @@ static inline bool is_topdown_idx(int idx)
  */
 
 struct pebs_basic {
-	u64 format_size;
+	u64 format_group:32,
+	    retire_latency:16,
+	    format_size:16;
 	u64 ip;
 	u64 applicable_counters;
 	u64 tsc;
@@ -431,7 +437,17 @@ struct pebs_basic {
 struct pebs_meminfo {
 	u64 address;
 	u64 aux;
-	u64 latency;
+	union {
+		/* pre Alder Lake */
+		u64 mem_latency;
+		/* Alder Lake and later */
+		struct {
+			u64 instr_latency:16;
+			u64 pad2:16;
+			u64 cache_latency:16;
+			u64 pad3:16;
+		};
+	};
 	u64 tsx_tuning;
 };
 

arch/x86/include/asm/processor.h

@@ -98,6 +98,7 @@ struct cpuinfo_topology {
 	// Logical ID mappings
 	u32			logical_pkg_id;
 	u32			logical_die_id;
+	u32			logical_core_id;
 
 	// AMD Node ID and Nodes per Package info
 	u32			amd_node_id;

arch/x86/include/asm/topology.h

@@ -143,6 +143,7 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu);
 #define topology_logical_package_id(cpu)	(cpu_data(cpu).topo.logical_pkg_id)
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).topo.pkg_id)
 #define topology_logical_die_id(cpu)		(cpu_data(cpu).topo.logical_die_id)
+#define topology_logical_core_id(cpu)		(cpu_data(cpu).topo.logical_core_id)
 #define topology_die_id(cpu)			(cpu_data(cpu).topo.die_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).topo.core_id)
 #define topology_ppin(cpu)			(cpu_data(cpu).ppin)

arch/x86/kernel/cpu/debugfs.c

@@ -25,6 +25,7 @@ static int cpu_debug_show(struct seq_file *m, void *p)
 	seq_printf(m, "cpu_type:            %s\n", get_topology_cpu_type_name(c));
 	seq_printf(m, "logical_pkg_id:      %u\n", c->topo.logical_pkg_id);
 	seq_printf(m, "logical_die_id:      %u\n", c->topo.logical_die_id);
+	seq_printf(m, "logical_core_id:     %u\n", c->topo.logical_core_id);
 	seq_printf(m, "llc_id:              %u\n", c->topo.llc_id);
 	seq_printf(m, "l2c_id:              %u\n", c->topo.l2c_id);
 	seq_printf(m, "amd_node_id:         %u\n", c->topo.amd_node_id);

arch/x86/kernel/cpu/topology_common.c

@@ -185,6 +185,7 @@ static void topo_set_ids(struct topo_scan *tscan, bool early)
 	if (!early) {
 		c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
 		c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+		c->topo.logical_core_id = topology_get_logical_id(apicid, TOPO_CORE_DOMAIN);
 	}
 
 	/* Package relative core ID */

include/linux/mm.h

@@ -711,7 +711,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
 	 * we don't rely on for anything - the mm_lock_seq read against which we
 	 * need ordering is below.
 	 */
-	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq))
+	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence))
 		return false;
 
 	if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
@@ -728,7 +728,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
 	 * after it has been unlocked.
 	 * This pairs with RELEASE semantics in vma_end_write_all().
 	 */
-	if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) {
+	if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) {
 		up_read(&vma->vm_lock->lock);
 		return false;
 	}
@@ -743,7 +743,7 @@ static inline void vma_end_read(struct vm_area_struct *vma)
 }
 
 /* WARNING! Can only be used if mmap_lock is expected to be write-locked */
-static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
+static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq)
 {
 	mmap_assert_write_locked(vma->vm_mm);
 
@@ -751,7 +751,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
 	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
 	 * mm->mm_lock_seq can't be concurrently modified.
 	 */
-	*mm_lock_seq = vma->vm_mm->mm_lock_seq;
+	*mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence;
 	return (vma->vm_lock_seq == *mm_lock_seq);
 }
 
@@ -762,7 +762,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
  */
 static inline void vma_start_write(struct vm_area_struct *vma)
 {
-	int mm_lock_seq;
+	unsigned int mm_lock_seq;
 
 	if (__is_vma_write_locked(vma, &mm_lock_seq))
 		return;
@@ -780,7 +780,7 @@ static inline void vma_start_write(struct vm_area_struct *vma)
 
 static inline void vma_assert_write_locked(struct vm_area_struct *vma)
 {
-	int mm_lock_seq;
+	unsigned int mm_lock_seq;
 
 	VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
 }

include/linux/mm_types.h

@@ -727,7 +727,7 @@ struct vm_area_struct {
 	 * counter reuse can only lead to occasional unnecessary use of the
 	 * slowpath.
 	 */
-	int vm_lock_seq;
+	unsigned int vm_lock_seq;
 	/* Unstable RCU readers are allowed to read this. */
 	struct vma_lock *vm_lock;
 #endif
@@ -921,6 +921,9 @@ struct mm_struct {
 		 * Roughly speaking, incrementing the sequence number is
 		 * equivalent to releasing locks on VMAs; reading the sequence
 		 * number can be part of taking a read lock on a VMA.
+		 * Incremented every time mmap_lock is write-locked/unlocked.
+		 * Initialized to 0, therefore odd values indicate mmap_lock
+		 * is write-locked and even values that it's released.
 		 *
 		 * Can be modified under write mmap_lock using RELEASE
 		 * semantics.
@@ -929,7 +932,7 @@ struct mm_struct {
 		 * Can be read with ACQUIRE semantics if not holding write
 		 * mmap_lock.
 		 */
-		int mm_lock_seq;
+		seqcount_t mm_lock_seq;
 #endif
 
 

include/linux/mmap_lock.h

@@ -71,6 +71,91 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm)
 }
 
 #ifdef CONFIG_PER_VMA_LOCK
+
+static inline void mm_lock_seqcount_init(struct mm_struct *mm)
+{
+	seqcount_init(&mm->mm_lock_seq);
+}
+
+static inline void mm_lock_seqcount_begin(struct mm_struct *mm)
+{
+	do_raw_write_seqcount_begin(&mm->mm_lock_seq);
+}
+
+static inline void mm_lock_seqcount_end(struct mm_struct *mm)
+{
+	ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq);
+	do_raw_write_seqcount_end(&mm->mm_lock_seq);
+}
+
+static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq)
+{
+	/*
+	 * Since mmap_lock is a sleeping lock, and waiting for it to become
+	 * unlocked is more or less equivalent with taking it ourselves, don't
+	 * bother with the speculative path if mmap_lock is already write-locked
+	 * and take the slow path, which takes the lock.
+	 */
+	return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq);
+}
+
+static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq)
+{
+	return read_seqcount_retry(&mm->mm_lock_seq, seq);
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline void mm_lock_seqcount_init(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_end(struct mm_struct *mm) {}
+
+static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq)
+{
+	return false;
+}
+
+static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq)
+{
+	return true;
+}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
+static inline void mmap_init_lock(struct mm_struct *mm)
+{
+	init_rwsem(&mm->mmap_lock);
+	mm_lock_seqcount_init(mm);
+}
+
+static inline void mmap_write_lock(struct mm_struct *mm)
+{
+	__mmap_lock_trace_start_locking(mm, true);
+	down_write(&mm->mmap_lock);
+	mm_lock_seqcount_begin(mm);
+	__mmap_lock_trace_acquire_returned(mm, true, true);
+}
+
+static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
+{
+	__mmap_lock_trace_start_locking(mm, true);
+	down_write_nested(&mm->mmap_lock, subclass);
+	mm_lock_seqcount_begin(mm);
+	__mmap_lock_trace_acquire_returned(mm, true, true);
+}
+
+static inline int mmap_write_lock_killable(struct mm_struct *mm)
+{
+	int ret;
+
+	__mmap_lock_trace_start_locking(mm, true);
+	ret = down_write_killable(&mm->mmap_lock);
+	if (!ret)
+		mm_lock_seqcount_begin(mm);
+	__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
+	return ret;
+}
+
 /*
  * Drop all currently-held per-VMA locks.
  * This is called from the mmap_lock implementation directly before releasing
@@ -82,46 +167,7 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm)
 static inline void vma_end_write_all(struct mm_struct *mm)
 {
 	mmap_assert_write_locked(mm);
-	/*
+	mm_lock_seqcount_end(mm);
-	 * Nobody can concurrently modify mm->mm_lock_seq due to exclusive
-	 * mmap_lock being held.
-	 * We need RELEASE semantics here to ensure that preceding stores into
-	 * the VMA take effect before we unlock it with this store.
-	 * Pairs with ACQUIRE semantics in vma_start_read().
-	 */
-	smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
-}
-#else
-static inline void vma_end_write_all(struct mm_struct *mm) {}
-#endif
-
-static inline void mmap_init_lock(struct mm_struct *mm)
-{
-	init_rwsem(&mm->mmap_lock);
-}
-
-static inline void mmap_write_lock(struct mm_struct *mm)
-{
-	__mmap_lock_trace_start_locking(mm, true);
-	down_write(&mm->mmap_lock);
-	__mmap_lock_trace_acquire_returned(mm, true, true);
-}
-
-static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
-{
-	__mmap_lock_trace_start_locking(mm, true);
-	down_write_nested(&mm->mmap_lock, subclass);
-	__mmap_lock_trace_acquire_returned(mm, true, true);
-}
-
-static inline int mmap_write_lock_killable(struct mm_struct *mm)
-{
-	int ret;
-
-	__mmap_lock_trace_start_locking(mm, true);
-	ret = down_write_killable(&mm->mmap_lock);
-	__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
-	return ret;
 }
 
 static inline void mmap_write_unlock(struct mm_struct *mm)

include/linux/perf_event.h

@@ -1279,6 +1279,11 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data,
 {
 	int size = 1;
 
+	if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
+		return;
+	if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN))
+		return;
+
 	data->callchain = perf_callchain(event, regs);
 	size += data->callchain->nr;
 
@@ -1287,12 +1292,18 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data,
 }
 
 static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
+					     struct perf_event *event,
 					     struct perf_raw_record *raw)
 {
 	struct perf_raw_frag *frag = &raw->frag;
 	u32 sum = 0;
 	int size;
 
+	if (!(event->attr.sample_type & PERF_SAMPLE_RAW))
+		return;
+	if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW))
+		return;
+
 	do {
 		sum += frag->size;
 		if (perf_raw_frag_last(frag))
@@ -1309,6 +1320,11 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
 	data->sample_flags |= PERF_SAMPLE_RAW;
 }
 
+static inline bool has_branch_stack(struct perf_event *event)
+{
+	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
 static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 					    struct perf_event *event,
 					    struct perf_branch_stack *brs,
@@ -1316,6 +1332,11 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 {
 	int size = sizeof(u64); /* nr */
 
+	if (!has_branch_stack(event))
+		return;
+	if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK))
+		return;
+
 	if (branch_sample_hw_index(event))
 		size += sizeof(u64);
 	size += brs->nr * sizeof(struct perf_branch_entry);
@@ -1669,6 +1690,8 @@ static inline int perf_allow_tracepoint(struct perf_event_attr *attr)
 	return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT);
 }
 
+extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs);
+
 extern void perf_event_init(void);
 extern void perf_tp_event(u16 event_type, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
@@ -1705,11 +1728,6 @@ static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
 # define perf_arch_guest_misc_flags(regs)	perf_arch_guest_misc_flags(regs)
 #endif
 
-static inline bool has_branch_stack(struct perf_event *event)
-{
-	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
-}
-
 static inline bool needs_branch_stack(struct perf_event *event)
 {
 	return event->attr.branch_sample_type != 0;
@@ -1879,6 +1897,10 @@ static inline u64 perf_event_pause(struct perf_event *event, bool reset)
 {
 	return 0;
 }
+static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs)
+{
+	return 0;
+}
 #endif
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)

include/linux/seqlock.h

@@ -318,6 +318,28 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
 	__seq;								\
 })
 
+/**
+ * raw_seqcount_try_begin() - begin a seqcount_t read critical section
+ *                            w/o lockdep and w/o counter stabilization
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
+ *
+ * Similar to raw_seqcount_begin(), except it enables eliding the critical
+ * section entirely if odd, instead of doing the speculation knowing it will
+ * fail.
+ *
+ * Useful when counter stabilization is more or less equivalent to taking
+ * the lock and there is a slowpath that does that.
+ *
+ * If true, start will be set to the (even) sequence count read.
+ *
+ * Return: true when a read critical section is started.
+ */
+#define raw_seqcount_try_begin(s, start)				\
+({									\
+	start = raw_read_seqcount(s);					\
+	!(start & 1);							\
+})
+
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
  *                        lockdep and w/o counter stabilization

include/linux/uprobes.h

@@ -16,6 +16,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 #include <linux/timer.h>
+#include <linux/seqlock.h>
 
 struct uprobe;
 struct vm_area_struct;
@@ -124,6 +125,10 @@ struct uprobe_task {
 	unsigned int			depth;
 	struct return_instance		*return_instances;
 
+	struct return_instance		*ri_pool;
+	struct timer_list		ri_timer;
+	seqcount_t			ri_seqcount;
+
 	union {
 		struct {
 			struct arch_uprobe_task	autask;
@@ -137,7 +142,6 @@ struct uprobe_task {
 	};
 
 	struct uprobe			*active_uprobe;
-	struct timer_list		ri_timer;
 	unsigned long			xol_vaddr;
 
 	struct arch_uprobe              *auprobe;
@@ -154,12 +158,18 @@ struct return_instance {
 	unsigned long		stack;		/* stack pointer */
 	unsigned long		orig_ret_vaddr; /* original return address */
 	bool			chained;	/* true, if instance is nested */
-	int			consumers_cnt;
+	int			cons_cnt;	/* total number of session consumers */
 
 	struct return_instance	*next;		/* keep as stack */
 	struct rcu_head		rcu;
 
-	struct return_consumer	consumers[] __counted_by(consumers_cnt);
+	/* singular pre-allocated return_consumer instance for common case */
+	struct return_consumer	consumer;
+	/*
+	 * extra return_consumer instances for rare cases of multiple session consumers,
+	 * contains (cons_cnt - 1) elements
+	 */
+	struct return_consumer	*extra_consumers;
 } ____cacheline_aligned;
 
 enum rp_check {

kernel/events/core.c

@@ -6277,41 +6277,6 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
-static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
-{
-	struct perf_event *event = vmf->vma->vm_file->private_data;
-	struct perf_buffer *rb;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-
-	if (vmf->flags & FAULT_FLAG_MKWRITE) {
-		if (vmf->pgoff == 0)
-			ret = 0;
-		return ret;
-	}
-
-	rcu_read_lock();
-	rb = rcu_dereference(event->rb);
-	if (!rb)
-		goto unlock;
-
-	if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
-		goto unlock;
-
-	vmf->page = perf_mmap_to_page(rb, vmf->pgoff);
-	if (!vmf->page)
-		goto unlock;
-
-	get_page(vmf->page);
-	vmf->page->mapping = vmf->vma->vm_file->f_mapping;
-	vmf->page->index   = vmf->pgoff;
-
-	ret = 0;
-unlock:
-	rcu_read_unlock();
-
-	return ret;
-}
-
 static void ring_buffer_attach(struct perf_event *event,
 			       struct perf_buffer *rb)
 {
@@ -6551,13 +6516,87 @@ out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
+static vm_fault_t perf_mmap_pfn_mkwrite(struct vm_fault *vmf)
+{
+	/* The first page is the user control page, others are read-only. */
+	return vmf->pgoff == 0 ? 0 : VM_FAULT_SIGBUS;
+}
+
 static const struct vm_operations_struct perf_mmap_vmops = {
 	.open		= perf_mmap_open,
 	.close		= perf_mmap_close, /* non mergeable */
-	.fault		= perf_mmap_fault,
+	.pfn_mkwrite	= perf_mmap_pfn_mkwrite,
-	.page_mkwrite	= perf_mmap_fault,
 };
 
+static int map_range(struct perf_buffer *rb, struct vm_area_struct *vma)
+{
+	unsigned long nr_pages = vma_pages(vma);
+	int err = 0;
+	unsigned long pagenum;
+
+	/*
+	 * We map this as a VM_PFNMAP VMA.
+	 *
+	 * This is not ideal as this is designed broadly for mappings of PFNs
+	 * referencing memory-mapped I/O ranges or non-system RAM i.e. for which
+	 * !pfn_valid(pfn).
+	 *
+	 * We are mapping kernel-allocated memory (memory we manage ourselves)
+	 * which would more ideally be mapped using vm_insert_page() or a
+	 * similar mechanism, that is as a VM_MIXEDMAP mapping.
+	 *
+	 * However this won't work here, because:
+	 *
+	 * 1. It uses vma->vm_page_prot, but this field has not been completely
+	 *    setup at the point of the f_op->mmp() hook, so we are unable to
+	 *    indicate that this should be mapped CoW in order that the
+	 *    mkwrite() hook can be invoked to make the first page R/W and the
+	 *    rest R/O as desired.
+	 *
+	 * 2. Anything other than a VM_PFNMAP of valid PFNs will result in
+	 *    vm_normal_page() returning a struct page * pointer, which means
+	 *    vm_ops->page_mkwrite() will be invoked rather than
+	 *    vm_ops->pfn_mkwrite(), and this means we have to set page->mapping
+	 *    to work around retry logic in the fault handler, however this
+	 *    field is no longer allowed to be used within struct page.
+	 *
+	 * 3. Having a struct page * made available in the fault logic also
+	 *    means that the page gets put on the rmap and becomes
+	 *    inappropriately accessible and subject to map and ref counting.
+	 *
+	 * Ideally we would have a mechanism that could explicitly express our
+	 * desires, but this is not currently the case, so we instead use
+	 * VM_PFNMAP.
+	 *
+	 * We manage the lifetime of these mappings with internal refcounts (see
+	 * perf_mmap_open() and perf_mmap_close()) so we ensure the lifetime of
+	 * this mapping is maintained correctly.
+	 */
+	for (pagenum = 0; pagenum < nr_pages; pagenum++) {
+		unsigned long va = vma->vm_start + PAGE_SIZE * pagenum;
+		struct page *page = perf_mmap_to_page(rb, vma->vm_pgoff + pagenum);
+
+		if (page == NULL) {
+			err = -EINVAL;
+			break;
+		}
+
+		/* Map readonly, perf_mmap_pfn_mkwrite() called on write fault. */
+		err = remap_pfn_range(vma, va, page_to_pfn(page), PAGE_SIZE,
+				      vm_get_page_prot(vma->vm_flags & ~VM_SHARED));
+		if (err)
+			break;
+	}
+
+#ifdef CONFIG_MMU
+	/* Clear any partial mappings on error. */
+	if (err)
+		zap_page_range_single(vma, vma->vm_start, nr_pages * PAGE_SIZE, NULL);
+#endif
+
+	return err;
+}
+
 static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct perf_event *event = file->private_data;
@@ -6682,6 +6721,8 @@ again:
 			goto again;
 		}
 
+		/* We need the rb to map pages. */
+		rb = event->rb;
 		goto unlock;
 	}
 
@@ -6776,6 +6817,9 @@ aux_unlock:
 	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
 	vma->vm_ops = &perf_mmap_vmops;
 
+	if (!ret)
+		ret = map_range(rb, vma);
+
 	if (event->pmu->event_mapped)
 		event->pmu->event_mapped(event, vma->vm_mm);
 
@@ -10039,8 +10083,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 	perf_swevent_overflow(event, 0, data, regs);
 }
 
-static int perf_exclude_event(struct perf_event *event,
+int perf_exclude_event(struct perf_event *event, struct pt_regs *regs)
-			      struct pt_regs *regs)
 {
 	if (event->hw.state & PERF_HES_STOPPED)
 		return 1;
@@ -10425,9 +10468,9 @@ static struct pmu perf_tracepoint = {
 };
 
 static int perf_tp_filter_match(struct perf_event *event,
-				struct perf_sample_data *data)
+				struct perf_raw_record *raw)
 {
-	void *record = data->raw->frag.data;
+	void *record = raw->frag.data;
 
 	/* only top level events have filters set */
 	if (event->parent)
@@ -10439,7 +10482,7 @@ static int perf_tp_filter_match(struct perf_event *event,
 }
 
 static int perf_tp_event_match(struct perf_event *event,
-				struct perf_sample_data *data,
+				struct perf_raw_record *raw,
 				struct pt_regs *regs)
 {
 	if (event->hw.state & PERF_HES_STOPPED)
@@ -10450,7 +10493,7 @@ static int perf_tp_event_match(struct perf_event *event,
 	if (event->attr.exclude_kernel && !user_mode(regs))
 		return 0;
 
-	if (!perf_tp_filter_match(event, data))
+	if (!perf_tp_filter_match(event, raw))
 		return 0;
 
 	return 1;
@@ -10476,6 +10519,7 @@ EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit);
 static void __perf_tp_event_target_task(u64 count, void *record,
 					struct pt_regs *regs,
 					struct perf_sample_data *data,
+					struct perf_raw_record *raw,
 					struct perf_event *event)
 {
 	struct trace_entry *entry = record;
@@ -10485,13 +10529,17 @@ static void __perf_tp_event_target_task(u64 count, void *record,
 	/* Cannot deliver synchronous signal to other task. */
 	if (event->attr.sigtrap)
 		return;
-	if (perf_tp_event_match(event, data, regs))
+	if (perf_tp_event_match(event, raw, regs)) {
+		perf_sample_data_init(data, 0, 0);
+		perf_sample_save_raw_data(data, event, raw);
 		perf_swevent_event(event, count, data, regs);
+	}
 }
 
 static void perf_tp_event_target_task(u64 count, void *record,
 				      struct pt_regs *regs,
 				      struct perf_sample_data *data,
+				      struct perf_raw_record *raw,
 				      struct perf_event_context *ctx)
 {
 	unsigned int cpu = smp_processor_id();
@@ -10499,15 +10547,15 @@ static void perf_tp_event_target_task(u64 count, void *record,
 	struct perf_event *event, *sibling;
 
 	perf_event_groups_for_cpu_pmu(event, &ctx->pinned_groups, cpu, pmu) {
-		__perf_tp_event_target_task(count, record, regs, data, event);
+		__perf_tp_event_target_task(count, record, regs, data, raw, event);
 		for_each_sibling_event(sibling, event)
-			__perf_tp_event_target_task(count, record, regs, data, sibling);
+			__perf_tp_event_target_task(count, record, regs, data, raw, sibling);
 	}
 
 	perf_event_groups_for_cpu_pmu(event, &ctx->flexible_groups, cpu, pmu) {
-		__perf_tp_event_target_task(count, record, regs, data, event);
+		__perf_tp_event_target_task(count, record, regs, data, raw, event);
 		for_each_sibling_event(sibling, event)
-			__perf_tp_event_target_task(count, record, regs, data, sibling);
+			__perf_tp_event_target_task(count, record, regs, data, raw, sibling);
 	}
 }
 
@@ -10525,15 +10573,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 		},
 	};
 
-	perf_sample_data_init(&data, 0, 0);
-	perf_sample_save_raw_data(&data, &raw);
-
 	perf_trace_buf_update(record, event_type);
 
 	hlist_for_each_entry_rcu(event, head, hlist_entry) {
-		if (perf_tp_event_match(event, &data, regs)) {
+		if (perf_tp_event_match(event, &raw, regs)) {
-			perf_swevent_event(event, count, &data, regs);
-
 			/*
 			 * Here use the same on-stack perf_sample_data,
 			 * some members in data are event-specific and
@@ -10543,7 +10586,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			 * because data->sample_flags is set.
 			 */
 			perf_sample_data_init(&data, 0, 0);
-			perf_sample_save_raw_data(&data, &raw);
+			perf_sample_save_raw_data(&data, event, &raw);
+			perf_swevent_event(event, count, &data, regs);
 		}
 	}
 
@@ -10560,7 +10604,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		raw_spin_lock(&ctx->lock);
-		perf_tp_event_target_task(count, record, regs, &data, ctx);
+		perf_tp_event_target_task(count, record, regs, &data, &raw, ctx);
 		raw_spin_unlock(&ctx->lock);
 unlock:
 		rcu_read_unlock();

kernel/events/ring_buffer.c

@@ -643,7 +643,6 @@ static void rb_free_aux_page(struct perf_buffer *rb, int idx)
 	struct page *page = virt_to_page(rb->aux_pages[idx]);
 
 	ClearPagePrivate(page);
-	page->mapping = NULL;
 	__free_page(page);
 }
 
@@ -819,7 +818,6 @@ static void perf_mmap_free_page(void *addr)
 {
 	struct page *page = virt_to_page(addr);
 
-	page->mapping = NULL;
 	__free_page(page);
 }
 
@@ -890,28 +888,13 @@ __perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff)
 	return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE);
 }
 
-static void perf_mmap_unmark_page(void *addr)
-{
-	struct page *page = vmalloc_to_page(addr);
-
-	page->mapping = NULL;
-}
-
 static void rb_free_work(struct work_struct *work)
 {
 	struct perf_buffer *rb;
-	void *base;
-	int i, nr;
 
 	rb = container_of(work, struct perf_buffer, work);
-	nr = data_page_nr(rb);
 
-	base = rb->user_page;
+	vfree(rb->user_page);
-	/* The '<=' counts in the user page. */
-	for (i = 0; i <= nr; i++)
-		perf_mmap_unmark_page(base + (i * PAGE_SIZE));
-
-	vfree(base);
 	kfree(rb);
 }
 

kernel/events/uprobes.c

@@ -1888,9 +1888,33 @@ unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
 	return instruction_pointer(regs);
 }
 
-static struct return_instance *free_ret_instance(struct return_instance *ri, bool cleanup_hprobe)
+static void ri_pool_push(struct uprobe_task *utask, struct return_instance *ri)
 {
-	struct return_instance *next = ri->next;
+	ri->cons_cnt = 0;
+	ri->next = utask->ri_pool;
+	utask->ri_pool = ri;
+}
+
+static struct return_instance *ri_pool_pop(struct uprobe_task *utask)
+{
+	struct return_instance *ri = utask->ri_pool;
+
+	if (likely(ri))
+		utask->ri_pool = ri->next;
+
+	return ri;
+}
+
+static void ri_free(struct return_instance *ri)
+{
+	kfree(ri->extra_consumers);
+	kfree_rcu(ri, rcu);
+}
+
+static void free_ret_instance(struct uprobe_task *utask,
+			      struct return_instance *ri, bool cleanup_hprobe)
+{
+	unsigned seq;
 
 	if (cleanup_hprobe) {
 		enum hprobe_state hstate;
@@ -1899,8 +1923,22 @@ static struct return_instance *free_ret_instance(struct return_instance *ri, boo
 		hprobe_finalize(&ri->hprobe, hstate);
 	}
 
-	kfree_rcu(ri, rcu);
+	/*
-	return next;
+	 * At this point return_instance is unlinked from utask's
+	 * return_instances list and this has become visible to ri_timer().
+	 * If seqcount now indicates that ri_timer's return instance
+	 * processing loop isn't active, we can return ri into the pool of
+	 * to-be-reused return instances for future uretprobes. If ri_timer()
+	 * happens to be running right now, though, we fallback to safety and
+	 * just perform RCU-delated freeing of ri.
+	 */
+	if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) {
+		/* immediate reuse of ri without RCU GP is OK */
+		ri_pool_push(utask, ri);
+	} else {
+		/* we might be racing with ri_timer(), so play it safe */
+		ri_free(ri);
+	}
 }
 
 /*
@@ -1910,7 +1948,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri, boo
 void uprobe_free_utask(struct task_struct *t)
 {
 	struct uprobe_task *utask = t->utask;
-	struct return_instance *ri;
+	struct return_instance *ri, *ri_next;
 
 	if (!utask)
 		return;
@@ -1921,8 +1959,19 @@ void uprobe_free_utask(struct task_struct *t)
 	timer_delete_sync(&utask->ri_timer);
 
 	ri = utask->return_instances;
-	while (ri)
+	while (ri) {
-		ri = free_ret_instance(ri, true /* cleanup_hprobe */);
+		ri_next = ri->next;
+		free_ret_instance(utask, ri, true /* cleanup_hprobe */);
+		ri = ri_next;
+	}
+
+	/* free_ret_instance() above might add to ri_pool, so this loop should come last */
+	ri = utask->ri_pool;
+	while (ri) {
+		ri_next = ri->next;
+		ri_free(ri);
+		ri = ri_next;
+	}
 
 	kfree(utask);
 }
@@ -1942,8 +1991,12 @@ static void ri_timer(struct timer_list *timer)
 	/* RCU protects return_instance from freeing. */
 	guard(rcu)();
 
+	write_seqcount_begin(&utask->ri_seqcount);
+
 	for_each_ret_instance_rcu(ri, utask->return_instances)
 		hprobe_expire(&ri->hprobe, false);
+
+	write_seqcount_end(&utask->ri_seqcount);
 }
 
 static struct uprobe_task *alloc_utask(void)
@@ -1955,6 +2008,7 @@ static struct uprobe_task *alloc_utask(void)
 		return NULL;
 
 	timer_setup(&utask->ri_timer, ri_timer, 0);
+	seqcount_init(&utask->ri_seqcount);
 
 	return utask;
 }
@@ -1974,32 +2028,40 @@ static struct uprobe_task *get_utask(void)
 	return current->utask;
 }
 
-static size_t ri_size(int consumers_cnt)
+static struct return_instance *alloc_return_instance(struct uprobe_task *utask)
 {
 	struct return_instance *ri;
 
-	return sizeof(*ri) + sizeof(ri->consumers[0]) * consumers_cnt;
+	ri = ri_pool_pop(utask);
-}
+	if (ri)
+		return ri;
 
-#define DEF_CNT 4
+	ri = kzalloc(sizeof(*ri), GFP_KERNEL);
-
-static struct return_instance *alloc_return_instance(void)
-{
-	struct return_instance *ri;
-
-	ri = kzalloc(ri_size(DEF_CNT), GFP_KERNEL);
 	if (!ri)
 		return ZERO_SIZE_PTR;
 
-	ri->consumers_cnt = DEF_CNT;
 	return ri;
 }
 
 static struct return_instance *dup_return_instance(struct return_instance *old)
 {
-	size_t size = ri_size(old->consumers_cnt);
+	struct return_instance *ri;
 
-	return kmemdup(old, size, GFP_KERNEL);
+	ri = kmemdup(old, sizeof(*ri), GFP_KERNEL);
+	if (!ri)
+		return NULL;
+
+	if (unlikely(old->cons_cnt > 1)) {
+		ri->extra_consumers = kmemdup(old->extra_consumers,
+					      sizeof(ri->extra_consumers[0]) * (old->cons_cnt - 1),
+					      GFP_KERNEL);
+		if (!ri->extra_consumers) {
+			kfree(ri);
+			return NULL;
+		}
+	}
+
+	return ri;
 }
 
 static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask)
@@ -2108,14 +2170,17 @@ unsigned long uprobe_get_trampoline_vaddr(void)
 static void cleanup_return_instances(struct uprobe_task *utask, bool chained,
 					struct pt_regs *regs)
 {
-	struct return_instance *ri = utask->return_instances;
+	struct return_instance *ri = utask->return_instances, *ri_next;
 	enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL;
 
 	while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) {
-		ri = free_ret_instance(ri, true /* cleanup_hprobe */);
+		ri_next = ri->next;
+		rcu_assign_pointer(utask->return_instances, ri_next);
 		utask->depth--;
+
+		free_ret_instance(utask, ri, true /* cleanup_hprobe */);
+		ri = ri_next;
 	}
-	rcu_assign_pointer(utask->return_instances, ri);
 }
 
 static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs,
@@ -2180,7 +2245,7 @@ static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs,
 
 	return;
 free:
-	kfree(ri);
+	ri_free(ri);
 }
 
 /* Prepare to single-step probed instruction out of line. */
@@ -2294,6 +2359,47 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	return is_trap_insn(&opcode);
 }
 
+static struct uprobe *find_active_uprobe_speculative(unsigned long bp_vaddr)
+{
+	struct mm_struct *mm = current->mm;
+	struct uprobe *uprobe = NULL;
+	struct vm_area_struct *vma;
+	struct file *vm_file;
+	loff_t offset;
+	unsigned int seq;
+
+	guard(rcu)();
+
+	if (!mmap_lock_speculate_try_begin(mm, &seq))
+		return NULL;
+
+	vma = vma_lookup(mm, bp_vaddr);
+	if (!vma)
+		return NULL;
+
+	/*
+	 * vm_file memory can be reused for another instance of struct file,
+	 * but can't be freed from under us, so it's safe to read fields from
+	 * it, even if the values are some garbage values; ultimately
+	 * find_uprobe_rcu() + mmap_lock_speculation_end() check will ensure
+	 * that whatever we speculatively found is correct
+	 */
+	vm_file = READ_ONCE(vma->vm_file);
+	if (!vm_file)
+		return NULL;
+
+	offset = (loff_t)(vma->vm_pgoff << PAGE_SHIFT) + (bp_vaddr - vma->vm_start);
+	uprobe = find_uprobe_rcu(vm_file->f_inode, offset);
+	if (!uprobe)
+		return NULL;
+
+	/* now double check that nothing about MM changed */
+	if (mmap_lock_speculate_retry(mm, seq))
+		return NULL;
+
+	return uprobe;
+}
+
 /* assumes being inside RCU protected region */
 static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swbp)
 {
@@ -2301,10 +2407,14 @@ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swb
 	struct uprobe *uprobe = NULL;
 	struct vm_area_struct *vma;
 
+	uprobe = find_active_uprobe_speculative(bp_vaddr);
+	if (uprobe)
+		return uprobe;
+
 	mmap_read_lock(mm);
 	vma = vma_lookup(mm, bp_vaddr);
 	if (vma) {
-		if (valid_vma(vma, false)) {
+		if (vma->vm_file) {
 			struct inode *inode = file_inode(vma->vm_file);
 			loff_t offset = vaddr_to_offset(vma, bp_vaddr);
 
@@ -2324,25 +2434,27 @@ static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swb
 	return uprobe;
 }
 
-static struct return_instance*
+static struct return_instance *push_consumer(struct return_instance *ri, __u64 id, __u64 cookie)
-push_consumer(struct return_instance *ri, int idx, __u64 id, __u64 cookie)
 {
+	struct return_consumer *ric;
+
 	if (unlikely(ri == ZERO_SIZE_PTR))
 		return ri;
 
-	if (unlikely(idx >= ri->consumers_cnt)) {
+	if (unlikely(ri->cons_cnt > 0)) {
-		struct return_instance *old_ri = ri;
+		ric = krealloc(ri->extra_consumers, sizeof(*ric) * ri->cons_cnt, GFP_KERNEL);
-
+		if (!ric) {
-		ri->consumers_cnt += DEF_CNT;
+			ri_free(ri);
-		ri = krealloc(old_ri, ri_size(old_ri->consumers_cnt), GFP_KERNEL);
-		if (!ri) {
-			kfree(old_ri);
 			return ZERO_SIZE_PTR;
 		}
+		ri->extra_consumers = ric;
 	}
 
-	ri->consumers[idx].id = id;
+	ric = likely(ri->cons_cnt == 0) ? &ri->consumer : &ri->extra_consumers[ri->cons_cnt - 1];
-	ri->consumers[idx].cookie = cookie;
+	ric->id = id;
+	ric->cookie = cookie;
+
+	ri->cons_cnt++;
 	return ri;
 }
 
@@ -2350,14 +2462,17 @@ static struct return_consumer *
 return_consumer_find(struct return_instance *ri, int *iter, int id)
 {
 	struct return_consumer *ric;
-	int idx = *iter;
+	int idx;
 
-	for (ric = &ri->consumers[idx]; idx < ri->consumers_cnt; idx++, ric++) {
+	for (idx = *iter; idx < ri->cons_cnt; idx++)
+	{
+		ric = likely(idx == 0) ? &ri->consumer : &ri->extra_consumers[idx - 1];
 		if (ric->id == id) {
 			*iter = idx + 1;
 			return ric;
 		}
 	}
+
 	return NULL;
 }
 
@@ -2371,9 +2486,9 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 	struct uprobe_consumer *uc;
 	bool has_consumers = false, remove = true;
 	struct return_instance *ri = NULL;
-	int push_idx = 0;
+	struct uprobe_task *utask = current->utask;
 
-	current->utask->auprobe = &uprobe->arch;
+	utask->auprobe = &uprobe->arch;
 
 	list_for_each_entry_rcu(uc, &uprobe->consumers, cons_node, rcu_read_lock_trace_held()) {
 		bool session = uc->handler && uc->ret_handler;
@@ -2393,21 +2508,15 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 			continue;
 
 		if (!ri)
-			ri = alloc_return_instance();
+			ri = alloc_return_instance(utask);
 
 		if (session)
-			ri = push_consumer(ri, push_idx++, uc->id, cookie);
+			ri = push_consumer(ri, uc->id, cookie);
 	}
-	current->utask->auprobe = NULL;
+	utask->auprobe = NULL;
 
-	if (!ZERO_OR_NULL_PTR(ri)) {
+	if (!ZERO_OR_NULL_PTR(ri))
-		/*
-		 * The push_idx value has the final number of return consumers,
-		 * and ri->consumers_cnt has number of allocated consumers.
-		 */
-		ri->consumers_cnt = push_idx;
 		prepare_uretprobe(uprobe, regs, ri);
-	}
 
 	if (remove && has_consumers) {
 		down_read(&uprobe->register_rwsem);
@@ -2461,7 +2570,7 @@ static struct return_instance *find_next_ret_chain(struct return_instance *ri)
 void uprobe_handle_trampoline(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
-	struct return_instance *ri, *next;
+	struct return_instance *ri, *ri_next, *next_chain;
 	struct uprobe *uprobe;
 	enum hprobe_state hstate;
 	bool valid;
@@ -2481,8 +2590,8 @@ void uprobe_handle_trampoline(struct pt_regs *regs)
 		 * or NULL; the latter case means that nobody but ri->func
 		 * could hit this trampoline on return. TODO: sigaltstack().
 		 */
-		next = find_next_ret_chain(ri);
+		next_chain = find_next_ret_chain(ri);
-		valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs);
+		valid = !next_chain || arch_uretprobe_is_alive(next_chain, RP_CHECK_RET, regs);
 
 		instruction_pointer_set(regs, ri->orig_ret_vaddr);
 		do {
@@ -2494,7 +2603,9 @@ void uprobe_handle_trampoline(struct pt_regs *regs)
 			 * trampoline addresses on the stack are replaced with correct
 			 * original return addresses
 			 */
-			rcu_assign_pointer(utask->return_instances, ri->next);
+			ri_next = ri->next;
+			rcu_assign_pointer(utask->return_instances, ri_next);
+			utask->depth--;
 
 			uprobe = hprobe_consume(&ri->hprobe, &hstate);
 			if (valid)
@@ -2502,9 +2613,9 @@ void uprobe_handle_trampoline(struct pt_regs *regs)
 			hprobe_finalize(&ri->hprobe, hstate);
 
 			/* We already took care of hprobe, no need to waste more time on that. */
-			ri = free_ret_instance(ri, false /* !cleanup_hprobe */);
+			free_ret_instance(utask, ri, false /* !cleanup_hprobe */);
-			utask->depth--;
+			ri = ri_next;
-		} while (ri != next);
+		} while (ri != next_chain);
 	} while (!valid);
 
 	return;

kernel/fork.c

@@ -448,7 +448,7 @@ static bool vma_lock_alloc(struct vm_area_struct *vma)
 		return false;
 
 	init_rwsem(&vma->vm_lock->lock);
-	vma->vm_lock_seq = -1;
+	vma->vm_lock_seq = UINT_MAX;
 
 	return true;
 }
@@ -1262,9 +1262,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
-#ifdef CONFIG_PER_VMA_LOCK
-	mm->mm_lock_seq = 0;
-#endif
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;

kernel/trace/bpf_trace.c

@@ -619,7 +619,8 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
-			u64 flags, struct perf_sample_data *sd)
+			u64 flags, struct perf_raw_record *raw,
+			struct perf_sample_data *sd)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	unsigned int cpu = smp_processor_id();
@@ -644,6 +645,8 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
+	perf_sample_save_raw_data(sd, event, raw);
+
 	return perf_event_output(event, sd, regs);
 }
 
@@ -687,9 +690,8 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	}
 
 	perf_sample_data_init(sd, 0, 0);
-	perf_sample_save_raw_data(sd, &raw);
 
-	err = __bpf_perf_event_output(regs, map, flags, sd);
+	err = __bpf_perf_event_output(regs, map, flags, &raw, sd);
 out:
 	this_cpu_dec(bpf_trace_nest_level);
 	preempt_enable();
@@ -748,9 +750,8 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 
 	perf_fetch_caller_regs(regs);
 	perf_sample_data_init(sd, 0, 0);
-	perf_sample_save_raw_data(sd, &raw);
 
-	ret = __bpf_perf_event_output(regs, map, flags, sd);
+	ret = __bpf_perf_event_output(regs, map, flags, &raw, sd);
 out:
 	this_cpu_dec(bpf_event_output_nest_level);
 	preempt_enable();

mm/gup.c

@@ -3360,8 +3360,7 @@ static unsigned long gup_fast(unsigned long start, unsigned long end,
 		return 0;
 
 	if (gup_flags & FOLL_PIN) {
-		seq = raw_read_seqcount(&current->mm->write_protect_seq);
+		if (!raw_seqcount_try_begin(&current->mm->write_protect_seq, seq))
-		if (seq & 1)
 			return 0;
 	}
 

mm/init-mm.c

@@ -40,7 +40,7 @@ struct mm_struct init_mm = {
 	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
 #ifdef CONFIG_PER_VMA_LOCK
-	.mm_lock_seq	= 0,
+	.mm_lock_seq	= SEQCNT_ZERO(init_mm.mm_lock_seq),
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,

tools/testing/vma/vma.c

@@ -89,7 +89,7 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
 	 * begun. Linking to the tree will have caused this to be incremented,
 	 * which means we will get a false positive otherwise.
 	 */
-	vma->vm_lock_seq = -1;
+	vma->vm_lock_seq = UINT_MAX;
 
 	return vma;
 }
@@ -214,7 +214,7 @@ static bool vma_write_started(struct vm_area_struct *vma)
 	int seq = vma->vm_lock_seq;
 
 	/* We reset after each check. */
-	vma->vm_lock_seq = -1;
+	vma->vm_lock_seq = UINT_MAX;
 
 	/* The vma_start_write() stub simply increments this value. */
 	return seq > -1;

tools/testing/vma/vma_internal.h

@@ -241,7 +241,7 @@ struct vm_area_struct {
 	 * counter reuse can only lead to occasional unnecessary use of the
 	 * slowpath.
 	 */
-	int vm_lock_seq;
+	unsigned int vm_lock_seq;
 	struct vma_lock *vm_lock;
 #endif
 
@@ -416,7 +416,7 @@ static inline bool vma_lock_alloc(struct vm_area_struct *vma)
 		return false;
 
 	init_rwsem(&vma->vm_lock->lock);
-	vma->vm_lock_seq = -1;
+	vma->vm_lock_seq = UINT_MAX;
 
 	return true;
 }