Merge tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:
 "HW support updates:

   - Add uncore support for Intel Comet Lake

   - Add RAPL support for Hygon Fam18h

   - Add Intel "IIO stack to PMON mapping" support on Skylake-SP CPUs,
     which enumerates per device performance counters via sysfs and
     enables the perf stat --iiostat functionality

   - Add support for Intel "Architectural LBRs", which generalized the
     model specific LBR hardware tracing feature into a
     model-independent, architected performance monitoring feature.

     Usage is mostly seamless to tooling, as the pre-existing LBR
     features are kept, but there's a couple of advantages under the
     hood, such as faster context-switching, faster LBR reads, cleaner
     exposure of LBR features to guest kernels, etc.

     ( Since architectural LBRs are supported via XSAVE, there's related
       changes to the x86 FPU code as well. )

  ftrace/perf updates:

   - Add support to add a text poke event to record changes to kernel
     text (i.e. self-modifying code) in order to support tracers like
     Intel PT decoding through jump labels, kprobes and ftrace
     trampolines.

  Misc cleanups, smaller fixes..."

* tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  perf/x86/rapl: Add Hygon Fam18h RAPL support
  kprobes: Remove unnecessary module_mutex locking from kprobe_optimizer()
  x86/perf: Fix a typo
  perf: <linux/perf_event.h>: drop a duplicated word
  perf/x86/intel/lbr: Support XSAVES for arch LBR read
  perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch
  x86/fpu/xstate: Add helpers for LBR dynamic supervisor feature
  x86/fpu/xstate: Support dynamic supervisor feature for LBR
  x86/fpu: Use proper mask to replace full instruction mask
  perf/x86: Remove task_ctx_size
  perf/x86/intel/lbr: Create kmem_cache for the LBR context data
  perf/core: Use kmem_cache to allocate the PMU specific data
  perf/core: Factor out functions to allocate/free the task_ctx_data
  perf/x86/intel/lbr: Support Architectural LBR
  perf/x86/intel/lbr: Factor out intel_pmu_store_lbr
  perf/x86/intel/lbr: Factor out rdlbr_all() and wrlbr_all()
  perf/x86/intel/lbr: Mark the {rd,wr}lbr_{to,from} wrappers __always_inline
  perf/x86/intel/lbr: Unify the stored format of LBR information
  perf/x86/intel/lbr: Support LBR_CTL
  perf/x86: Expose CPUID enumeration bits for arch LBR
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-devices-mapping

@@ -0,0 +1,33 @@
+What:           /sys/devices/uncore_iio_x/dieX
+Date:           February 2020
+Contact:        Roman Sudarikov <[email protected]>
+Description:
+                Each IIO stack (PCIe root port) has its own IIO PMON block, so
+                each dieX file (where X is die number) holds "Segment:Root Bus"
+                for PCIe root port, which can be monitored by that IIO PMON
+                block.
+                For example, on 4-die Xeon platform with up to 6 IIO stacks per
+                die and, therefore, 6 IIO PMON blocks per die, the mapping of
+                IIO PMON block 0 exposes as the following:
+
+                $ ls /sys/devices/uncore_iio_0/die*
+                -r--r--r-- /sys/devices/uncore_iio_0/die0
+                -r--r--r-- /sys/devices/uncore_iio_0/die1
+                -r--r--r-- /sys/devices/uncore_iio_0/die2
+                -r--r--r-- /sys/devices/uncore_iio_0/die3
+
+                $ tail /sys/devices/uncore_iio_0/die*
+                ==> /sys/devices/uncore_iio_0/die0 <==
+                0000:00
+                ==> /sys/devices/uncore_iio_0/die1 <==
+                0000:40
+                ==> /sys/devices/uncore_iio_0/die2 <==
+                0000:80
+                ==> /sys/devices/uncore_iio_0/die3 <==
+                0000:c0
+
+                Which means:
+                IIO PMU 0 on die 0 belongs to PCI RP on bus 0x00, domain 0x0000
+                IIO PMU 0 on die 1 belongs to PCI RP on bus 0x40, domain 0x0000
+                IIO PMU 0 on die 2 belongs to PCI RP on bus 0x80, domain 0x0000
+                IIO PMU 0 on die 3 belongs to PCI RP on bus 0xc0, domain 0x0000

arch/x86/events/core.c

@@ -71,10 +71,9 @@ u64 x86_perf_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
-	int idx = hwc->idx;
 	u64 delta;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -359,6 +358,7 @@ void x86_release_hardware(void)
 	if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
 		release_pmc_hardware();
 		release_ds_buffers();
+		release_lbr_buffers();
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 }
@@ -1097,22 +1097,31 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 				struct cpu_hw_events *cpuc, int i)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	int idx;
 
-	hwc->idx = cpuc->assign[i];
+	idx = hwc->idx = cpuc->assign[i];
 	hwc->last_cpu = smp_processor_id();
 	hwc->last_tag = ++cpuc->tags[i];
 
-	if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
+	switch (hwc->idx) {
+	case INTEL_PMC_IDX_FIXED_BTS:
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		hwc->config_base = 0;
 		hwc->event_base	= 0;
-	} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+		break;
+
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
-		hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
-	} else {
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+		break;
+
+	default:
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
 		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
+		break;
 	}
 }
 
@@ -1233,7 +1242,7 @@ int x86_perf_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0, idx = hwc->idx;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -2363,7 +2372,6 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
-	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 

arch/x86/events/intel/core.c

@@ -2136,8 +2136,35 @@ static inline void intel_pmu_ack_status(u64 ack)
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
 {
+	return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (event->attr.exclude_host)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	if (event->attr.exclude_guest)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	if (event_is_checkpointed(event))
+		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
@@ -2148,30 +2175,22 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
-	return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx = hwc->idx;
 
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_clear_masks(event, idx);
+		x86_pmu_disable_event(event);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_clear_masks(event, idx);
+		intel_pmu_disable_fixed(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-		return;
-	}
-
-	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
-		intel_pmu_disable_fixed(hwc);
-	else
-		x86_pmu_disable_event(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_clear_masks(event, idx);
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
@@ -2238,33 +2257,23 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
-		if (!__this_cpu_read(cpu_hw_events.enabled))
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		return;
-	}
-
-	if (event->attr.exclude_host)
-		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
-	if (event->attr.exclude_guest)
-		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
-	if (unlikely(event_is_checkpointed(event)))
-		cpuc->intel_cp_status |= (1ull << hwc->idx);
+	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_set_masks(event, idx);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_set_masks(event, idx);
 		intel_pmu_enable_fixed(event);
-		return;
-	}
-
-	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		if (!__this_cpu_read(cpu_hw_events.enabled))
+			return;
+		intel_pmu_enable_bts(hwc->config);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_set_masks(event, idx);
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
@@ -2614,6 +2623,20 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
+/*
+ * Note: matches a fake event, like Fixed2.
+ */
+static struct event_constraint *
+intel_vlbr_constraints(struct perf_event *event)
+{
+	struct event_constraint *c = &vlbr_constraint;
+
+	if (unlikely(constraint_match(c, event->hw.config)))
+		return c;
+
+	return NULL;
+}
+
 static int intel_alt_er(int idx, u64 config)
 {
 	int alt_idx = idx;
@@ -2804,6 +2827,10 @@ __intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
+	c = intel_vlbr_constraints(event);
+	if (c)
+		return c;
+
 	c = intel_bts_constraints(event);
 	if (c)
 		return c;
@@ -3951,6 +3978,11 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_dead		= intel_pmu_cpu_dead,
 
 	.check_period		= intel_pmu_check_period,
+
+	.lbr_reset		= intel_pmu_lbr_reset_64,
+	.lbr_read		= intel_pmu_lbr_read_64,
+	.lbr_save		= intel_pmu_lbr_save,
+	.lbr_restore		= intel_pmu_lbr_restore,
 };
 
 static __initconst const struct x86_pmu intel_pmu = {
@@ -3996,6 +4028,11 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.check_period		= intel_pmu_check_period,
 
 	.aux_output_match	= intel_pmu_aux_output_match,
+
+	.lbr_reset		= intel_pmu_lbr_reset_64,
+	.lbr_read		= intel_pmu_lbr_read_64,
+	.lbr_save		= intel_pmu_lbr_save,
+	.lbr_restore		= intel_pmu_lbr_restore,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -4622,6 +4659,14 @@ __init int intel_pmu_init(void)
 		x86_pmu.intel_cap.capabilities = capabilities;
 	}
 
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) {
+		x86_pmu.lbr_reset = intel_pmu_lbr_reset_32;
+		x86_pmu.lbr_read = intel_pmu_lbr_read_32;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
+		intel_pmu_arch_lbr_init();
+
 	intel_ds_init();
 
 	x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */

arch/x86/events/intel/ds.c

@@ -954,7 +954,7 @@ static void adaptive_pebs_record_size_update(void)
 	if (pebs_data_cfg & PEBS_DATACFG_XMMS)
 		sz += sizeof(struct pebs_xmm);
 	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
-		sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+		sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
 
 	cpuc->pebs_record_size = sz;
 }
@@ -1595,10 +1595,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	}
 
 	if (format_size & PEBS_DATACFG_LBRS) {
-		struct pebs_lbr *lbr = next_record;
+		struct lbr_entry *lbr = next_record;
 		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
 					& 0xff) + 1;
-		next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+		next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);