Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Lots of tooling updates - too many to list, here's a few highlights:

   - Various subcommand updates to 'perf trace', 'perf report', 'perf
     record', 'perf annotate', 'perf script', 'perf test', etc.

   - CPU and NUMA topology and affinity handling improvements,

   - HW tracing and HW support updates:
      - Intel PT updates
      - ARM CoreSight updates
      - vendor HW event updates

   - BPF updates

   - Tons of infrastructure updates, both on the build system and the
     library support side

   - Documentation updates.

   - ... and lots of other changes, see the changelog for details.

  Kernel side updates:

   - Tighten up kprobes blacklist handling, reduce the number of places
     where developers can install a kprobe and hang/crash the system.

   - Fix/enhance vma address filter handling.

   - Various PMU driver updates, small fixes and additions.

   - refcount_t conversions

   - BPF updates

   - error code propagation enhancements

   - misc other changes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (238 commits)
  perf script python: Add Python3 support to syscall-counts-by-pid.py
  perf script python: Add Python3 support to syscall-counts.py
  perf script python: Add Python3 support to stat-cpi.py
  perf script python: Add Python3 support to stackcollapse.py
  perf script python: Add Python3 support to sctop.py
  perf script python: Add Python3 support to powerpc-hcalls.py
  perf script python: Add Python3 support to net_dropmonitor.py
  perf script python: Add Python3 support to mem-phys-addr.py
  perf script python: Add Python3 support to failed-syscalls-by-pid.py
  perf script python: Add Python3 support to netdev-times.py
  perf tools: Add perf_exe() helper to find perf binary
  perf script: Handle missing fields with -F +..
  perf data: Add perf_data__open_dir_data function
  perf data: Add perf_data__(create_dir|close_dir) functions
  perf data: Fail check_backup in case of error
  perf data: Make check_backup work over directories
  perf tools: Add rm_rf_perf_data function
  perf tools: Add pattern name checking to rm_rf
  perf tools: Add depth checking to rm_rf
  perf data: Add global path holder
  ...

arch/alpha/kernel/perf_event.c

@@ -630,12 +630,6 @@ static int __hw_perf_event_init(struct perf_event *event)
 		return ev;
 	}
 
-	/* The EV67 does not support mode exclusion */
-	if (attr->exclude_kernel || attr->exclude_user
-			|| attr->exclude_hv || attr->exclude_idle) {
-		return -EPERM;
-	}
-
 	/*
 	 * We place the event type in event_base here and leave calculation
 	 * of the codes to programme the PMU for alpha_pmu_enable() because
@@ -771,6 +765,7 @@ static struct pmu pmu = {
 	.start		= alpha_pmu_start,
 	.stop		= alpha_pmu_stop,
 	.read		= alpha_pmu_read,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 

arch/arm/mach-imx/mmdc.c

@@ -294,13 +294,7 @@ static int mmdc_pmu_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 	}
 
-	if (event->attr.exclude_user		||
+	if (event->attr.sample_period)
-			event->attr.exclude_kernel	||
-			event->attr.exclude_hv		||
-			event->attr.exclude_idle	||
-			event->attr.exclude_host	||
-			event->attr.exclude_guest	||
-			event->attr.sample_period)
 		return -EINVAL;
 
 	if (cfg < 0 || cfg >= MMDC_NUM_COUNTERS)
@@ -456,6 +450,7 @@ static int mmdc_pmu_init(struct mmdc_pmu *pmu_mmdc,
 			.start          = mmdc_pmu_event_start,
 			.stop           = mmdc_pmu_event_stop,
 			.read           = mmdc_pmu_event_update,
+			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 		},
 		.mmdc_base = mmdc_base,
 		.dev = dev,

arch/arm/mm/cache-l2x0-pmu.c

@@ -314,14 +314,6 @@ static int l2x0_pmu_event_init(struct perf_event *event)
 	    event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -544,6 +536,7 @@ static __init int l2x0_pmu_init(void)
 		.del = l2x0_pmu_event_del,
 		.event_init = l2x0_pmu_event_init,
 		.attr_groups = l2x0_pmu_attr_groups,
+		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	l2x0_pmu_reset();

arch/powerpc/perf/hv-24x7.c

@@ -1306,15 +1306,6 @@ static int h_24x7_event_init(struct perf_event *event)
 		return -EINVAL;
 	}
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	/* no branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -1577,6 +1568,7 @@ static struct pmu h_24x7_pmu = {
 	.start_txn   = h_24x7_event_start_txn,
 	.commit_txn  = h_24x7_event_commit_txn,
 	.cancel_txn  = h_24x7_event_cancel_txn,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static int hv_24x7_init(void)

arch/powerpc/perf/hv-gpci.c

@@ -232,15 +232,6 @@ static int h_gpci_event_init(struct perf_event *event)
 		return -EINVAL;
 	}
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	/* no branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -285,6 +276,7 @@ static struct pmu h_gpci_pmu = {
 	.start       = h_gpci_event_start,
 	.stop        = h_gpci_event_stop,
 	.read        = h_gpci_event_update,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static int hv_gpci_init(void)

arch/powerpc/perf/imc-pmu.c

@@ -473,15 +473,6 @@ static int nest_imc_event_init(struct perf_event *event)
 	if (event->hw.sample_period)
 		return -EINVAL;
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -748,15 +739,6 @@ static int core_imc_event_init(struct perf_event *event)
 	if (event->hw.sample_period)
 		return -EINVAL;
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -1069,6 +1051,7 @@ static int update_pmu_ops(struct imc_pmu *pmu)
 	pmu->pmu.stop = imc_event_stop;
 	pmu->pmu.read = imc_event_update;
 	pmu->pmu.attr_groups = pmu->attr_groups;
+	pmu->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE;
 	pmu->attr_groups[IMC_FORMAT_ATTR] = &imc_format_group;
 
 	switch (pmu->domain) {

arch/s390/kernel/perf_cpum_sf.c

@@ -1600,7 +1600,7 @@ static void aux_sdb_init(unsigned long sdb)
 
 /*
  * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
- * @cpu:	On which to allocate, -1 means current
+ * @event:	Event the buffer is setup for, event->cpu == -1 means current
  * @pages:	Array of pointers to buffer pages passed from perf core
  * @nr_pages:	Total pages
  * @snapshot:	Flag for snapshot mode
@@ -1612,8 +1612,8 @@ static void aux_sdb_init(unsigned long sdb)
  *
  * Return the private AUX buffer structure if success or NULL if fails.
  */
-static void *aux_buffer_setup(int cpu, void **pages, int nr_pages,
+static void *aux_buffer_setup(struct perf_event *event, void **pages,
-			      bool snapshot)
+			      int nr_pages, bool snapshot)
 {
 	struct sf_buffer *sfb;
 	struct aux_buffer *aux;

arch/x86/events/amd/ibs.c

@@ -253,15 +253,6 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
 	return -EOPNOTSUPP;
 }
 
-static const struct perf_event_attr ibs_notsupp = {
-	.exclude_user	= 1,
-	.exclude_kernel	= 1,
-	.exclude_hv	= 1,
-	.exclude_idle	= 1,
-	.exclude_host	= 1,
-	.exclude_guest	= 1,
-};
-
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -282,9 +273,6 @@ static int perf_ibs_init(struct perf_event *event)
 	if (event->pmu != &perf_ibs->pmu)
 		return -ENOENT;
 
-	if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
-		return -EINVAL;
-
 	if (config & ~perf_ibs->config_mask)
 		return -EINVAL;
 
@@ -537,6 +525,7 @@ 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,

arch/x86/events/amd/iommu.c

@@ -223,11 +223,6 @@ static int perf_iommu_event_init(struct perf_event *event)
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	/* IOMMU counters do not have usr/os/guest/host bits */
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-	    event->attr.exclude_host || event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -414,6 +409,7 @@ static const struct pmu iommu_pmu __initconst = {
 	.read		= perf_iommu_read,
 	.task_ctx_nr	= perf_invalid_context,
 	.attr_groups	= amd_iommu_attr_groups,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static __init int init_one_iommu(unsigned int idx)

arch/x86/events/amd/power.c

@@ -136,14 +136,7 @@ static int pmu_event_init(struct perf_event *event)
 		return -ENOENT;
 
 	/* Unsupported modes and filters. */
-	if (event->attr.exclude_user   ||
+	if (event->attr.sample_period)
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    /* no sampling */
-	    event->attr.sample_period)
 		return -EINVAL;
 
 	if (cfg != AMD_POWER_EVENTSEL_PKG)
@@ -226,6 +219,7 @@ static struct pmu pmu_class = {
 	.start		= pmu_event_start,
 	.stop		= pmu_event_stop,
 	.read		= pmu_event_read,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static int power_cpu_exit(unsigned int cpu)

arch/x86/events/amd/uncore.c

@@ -201,11 +201,6 @@ static int amd_uncore_event_init(struct perf_event *event)
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	/* NB and Last level cache counters do not have usr/os/guest/host bits */
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-	    event->attr.exclude_host || event->attr.exclude_guest)
-		return -EINVAL;
-
 	/* and we do not enable counter overflow interrupts */
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
@@ -307,6 +302,7 @@ static struct pmu amd_nb_pmu = {
 	.start		= amd_uncore_start,
 	.stop		= amd_uncore_stop,
 	.read		= amd_uncore_read,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static struct pmu amd_llc_pmu = {
@@ -317,6 +313,7 @@ static struct pmu amd_llc_pmu = {
 	.start		= amd_uncore_start,
 	.stop		= amd_uncore_stop,
 	.read		= amd_uncore_read,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)

arch/x86/events/intel/bts.c

@@ -77,10 +77,12 @@ static size_t buf_size(struct page *page)
 }
 
 static void *
-bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite)
+bts_buffer_setup_aux(struct perf_event *event, void **pages,
+		     int nr_pages, bool overwrite)
 {
 	struct bts_buffer *buf;
 	struct page *page;
+	int cpu = event->cpu;
 	int node = (cpu == -1) ? cpu : cpu_to_node(cpu);
 	unsigned long offset;
 	size_t size = nr_pages << PAGE_SHIFT;

arch/x86/events/intel/core.c

@@ -18,6 +18,7 @@
 #include <asm/hardirq.h>
 #include <asm/intel-family.h>
 #include <asm/apic.h>
+#include <asm/cpu_device_id.h>
 
 #include "../perf_event.h"
 
@@ -3206,16 +3207,27 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
 	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
 	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
-	/*
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
-	 * If PMU counter has PEBS enabled it is not enough to disable counter
+		arr[0].guest &= ~cpuc->pebs_enabled;
-	 * on a guest entry since PEBS memory write can overshoot guest entry
+	else
-	 * and corrupt guest memory. Disabling PEBS solves the problem.
+		arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
-	 */
+	*nr = 1;
-	arr[1].msr = MSR_IA32_PEBS_ENABLE;
+
-	arr[1].host = cpuc->pebs_enabled;
+	if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
-	arr[1].guest = 0;
+		/*
+		 * If PMU counter has PEBS enabled it is not enough to
+		 * disable counter on a guest entry since PEBS memory
+		 * write can overshoot guest entry and corrupt guest
+		 * memory. Disabling PEBS solves the problem.
+		 *
+		 * Don't do this if the CPU already enforces it.
+		 */
+		arr[1].msr = MSR_IA32_PEBS_ENABLE;
+		arr[1].host = cpuc->pebs_enabled;
+		arr[1].guest = 0;
+		*nr = 2;
+	}
 
-	*nr = 2;
 	return arr;
 }
 
@@ -3748,36 +3760,62 @@ static __init void intel_clovertown_quirk(void)
 	x86_pmu.pebs_constraints = NULL;
 }
 
-static int intel_snb_pebs_broken(int cpu)
+static const struct x86_cpu_desc isolation_ucodes[] = {
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_CORE,		 3, 0x0000001f),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_ULT,		 1, 0x0000001e),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_GT3E,		 1, 0x00000015),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X,		 2, 0x00000037),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X,		 4, 0x0000000a),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_CORE,	 4, 0x00000023),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_GT3E,	 1, 0x00000014),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 2, 0x00000010),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 3, 0x07000009),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 4, 0x0f000009),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 5, 0x0e000002),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X,		 2, 0x0b000014),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 3, 0x00000021),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 4, 0x00000000),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_MOBILE,	 3, 0x0000007c),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_DESKTOP,	 3, 0x0000007c),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	 9, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	 9, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	10, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	11, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	12, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	10, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	11, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	12, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	13, 0x0000004e),
+	{}
+};
+
+static void intel_check_pebs_isolation(void)
 {
-	u32 rev = UINT_MAX; /* default to broken for unknown models */
+	x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes);
+}
 
-	switch (cpu_data(cpu).x86_model) {
+static __init void intel_pebs_isolation_quirk(void)
-	case INTEL_FAM6_SANDYBRIDGE:
+{
-		rev = 0x28;
+	WARN_ON_ONCE(x86_pmu.check_microcode);
-		break;
+	x86_pmu.check_microcode = intel_check_pebs_isolation;
+	intel_check_pebs_isolation();
+}
 
-	case INTEL_FAM6_SANDYBRIDGE_X:
+static const struct x86_cpu_desc pebs_ucodes[] = {
-		switch (cpu_data(cpu).x86_stepping) {
+	INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE,		7, 0x00000028),
-		case 6: rev = 0x618; break;
+	INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X,	6, 0x00000618),
-		case 7: rev = 0x70c; break;
+	INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X,	7, 0x0000070c),
-		}
+	{}
-	}
+};
 
-	return (cpu_data(cpu).microcode < rev);
+static bool intel_snb_pebs_broken(void)
+{
+	return !x86_cpu_has_min_microcode_rev(pebs_ucodes);
 }
 
 static void intel_snb_check_microcode(void)
 {
-	int pebs_broken = 0;
+	if (intel_snb_pebs_broken() == x86_pmu.pebs_broken)
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if ((pebs_broken = intel_snb_pebs_broken(cpu)))
-			break;
-	}
-
-	if (pebs_broken == x86_pmu.pebs_broken)
 		return;
 
 	/*
@@ -3894,23 +3932,22 @@ static __init void intel_nehalem_quirk(void)
 	}
 }
 
-static bool intel_glp_counter_freezing_broken(int cpu)
+static const struct x86_cpu_desc counter_freezing_ucodes[] = {
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT,	 2, 0x0000000e),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT,	 9, 0x0000002e),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT,	10, 0x00000008),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_X,	 1, 0x00000028),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	 1, 0x00000028),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	 8, 0x00000006),
+	{}
+};
+
+static bool intel_counter_freezing_broken(void)
 {
-	u32 rev = UINT_MAX; /* default to broken for unknown stepping */
+	return !x86_cpu_has_min_microcode_rev(counter_freezing_ucodes);
-
-	switch (cpu_data(cpu).x86_stepping) {
-	case 1:
-		rev = 0x28;
-		break;
-	case 8:
-		rev = 0x6;
-		break;
-	}
-
-	return (cpu_data(cpu).microcode < rev);
 }
 
-static __init void intel_glp_counter_freezing_quirk(void)
+static __init void intel_counter_freezing_quirk(void)
 {
 	/* Check if it's already disabled */
 	if (disable_counter_freezing)
@@ -3920,7 +3957,7 @@ static __init void intel_glp_counter_freezing_quirk(void)
 	 * If the system starts with the wrong ucode, leave the
 	 * counter-freezing feature permanently disabled.
 	 */
-	if (intel_glp_counter_freezing_broken(raw_smp_processor_id())) {
+	if (intel_counter_freezing_broken()) {
 		pr_info("PMU counter freezing disabled due to CPU errata,"
 			"please upgrade microcode\n");
 		x86_pmu.counter_freezing = false;
@@ -4271,6 +4308,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_ATOM_GOLDMONT_X:
+		x86_add_quirk(intel_counter_freezing_quirk);
 		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -4297,7 +4335,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-		x86_add_quirk(intel_glp_counter_freezing_quirk);
+		x86_add_quirk(intel_counter_freezing_quirk);
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -4440,6 +4478,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_HASWELL_ULT:
 	case INTEL_FAM6_HASWELL_GT3E:
 		x86_add_quirk(intel_ht_bug);
+		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4471,6 +4510,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_BROADWELL_XEON_D:
 	case INTEL_FAM6_BROADWELL_GT3E:
 	case INTEL_FAM6_BROADWELL_X:
+		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4533,6 +4573,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
+		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));

arch/x86/events/intel/cstate.c

@@ -280,13 +280,7 @@ static int cstate_pmu_event_init(struct perf_event *event)
 		return -ENOENT;
 
 	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
+	if (event->attr.sample_period) /* no sampling */
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    event->attr.sample_period) /* no sampling */
 		return -EINVAL;
 
 	if (event->cpu < 0)
@@ -437,7 +431,7 @@ static struct pmu cstate_core_pmu = {
 	.start		= cstate_pmu_event_start,
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
-	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
 	.module		= THIS_MODULE,
 };
 
@@ -451,7 +445,7 @@ static struct pmu cstate_pkg_pmu = {
 	.start		= cstate_pmu_event_start,
 	.stop		= cstate_pmu_event_stop,
 	.read		= cstate_pmu_event_update,
-	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
 	.module		= THIS_MODULE,
 };
 

arch/x86/events/intel/ds.c

@@ -1628,6 +1628,8 @@ void __init intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
+	if (x86_pmu.version <= 4)
+		x86_pmu.pebs_no_isolation = 1;
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;

arch/x86/events/intel/pt.c

@@ -1114,10 +1114,11 @@ static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages,
  * Return:	Our private PT buffer structure.
  */
 static void *
-pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot)
+pt_buffer_setup_aux(struct perf_event *event, void **pages,
+		    int nr_pages, bool snapshot)
 {
 	struct pt_buffer *buf;
-	int node, ret;
+	int node, ret, cpu = event->cpu;
 
 	if (!nr_pages)
 		return NULL;
@@ -1222,7 +1223,8 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 static void pt_event_addr_filters_sync(struct perf_event *event)
 {
 	struct perf_addr_filters_head *head = perf_event_addr_filters(event);
-	unsigned long msr_a, msr_b, *offs = event->addr_filters_offs;
+	unsigned long msr_a, msr_b;
+	struct perf_addr_filter_range *fr = event->addr_filter_ranges;
 	struct pt_filters *filters = event->hw.addr_filters;
 	struct perf_addr_filter *filter;
 	int range = 0;
@@ -1231,12 +1233,12 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		return;
 
 	list_for_each_entry(filter, &head->list, entry) {
-		if (filter->path.dentry && !offs[range]) {
+		if (filter->path.dentry && !fr[range].start) {
 			msr_a = msr_b = 0;
 		} else {
 			/* apply the offset */
-			msr_a = filter->offset + offs[range];
+			msr_a = fr[range].start;
-			msr_b = filter->size + msr_a - 1;
+			msr_b = msr_a + fr[range].size - 1;
 		}
 
 		filters->filter[range].msr_a  = msr_a;

arch/x86/events/intel/rapl.c

@@ -397,13 +397,7 @@ static int rapl_pmu_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
+	if (event->attr.sample_period) /* no sampling */
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    event->attr.sample_period) /* no sampling */
 		return -EINVAL;
 
 	/* must be done before validate_group */
@@ -699,6 +693,7 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
 	rapl_pmus->pmu.module		= THIS_MODULE;
+	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
 	return 0;
 }
 

arch/x86/events/intel/uncore.c

@@ -695,14 +695,6 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	if (pmu->func_id < 0)
 		return -ENOENT;
 
-	/*
-	 * Uncore PMU does measure at all privilege level all the time.
-	 * So it doesn't make sense to specify any exclude bits.
-	 */
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-			event->attr.exclude_hv || event->attr.exclude_idle)
-		return -EINVAL;
-
 	/* Sampling not supported yet */
 	if (hwc->sample_period)
 		return -EINVAL;
@@ -800,6 +792,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 			.stop		= uncore_pmu_event_stop,
 			.read		= uncore_pmu_event_read,
 			.module		= THIS_MODULE,
+			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 		};
 	} else {
 		pmu->pmu = *pmu->type->pmu;

arch/x86/events/intel/uncore_snb.c

@@ -397,13 +397,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
+	if (event->attr.sample_period) /* no sampling */
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    event->attr.sample_period) /* no sampling */
 		return -EINVAL;
 
 	/*
@@ -497,6 +491,7 @@ static struct pmu snb_uncore_imc_pmu = {
 	.start		= uncore_pmu_event_start,
 	.stop		= uncore_pmu_event_stop,
 	.read		= uncore_pmu_event_read,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static struct intel_uncore_ops snb_uncore_imc_ops = {

arch/x86/events/msr.c

@@ -160,13 +160,7 @@ static int msr_event_init(struct perf_event *event)
 		return -ENOENT;
 
 	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
+	if (event->attr.sample_period) /* no sampling */
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    event->attr.sample_period) /* no sampling */
 		return -EINVAL;
 
 	if (cfg >= PERF_MSR_EVENT_MAX)
@@ -256,7 +250,7 @@ static struct pmu pmu_msr = {
 	.start		= msr_event_start,
 	.stop		= msr_event_stop,
 	.read		= msr_event_update,
-	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
+	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static int __init msr_init(void)

arch/x86/events/perf_event.h

@@ -601,13 +601,14 @@ struct x86_pmu {
 	/*
 	 * Intel DebugStore bits
 	 */
-	unsigned int	bts		:1,
+	unsigned int	bts			:1,
-			bts_active	:1,
+			bts_active		:1,
-			pebs		:1,
+			pebs			:1,
-			pebs_active	:1,
+			pebs_active		:1,
-			pebs_broken	:1,
+			pebs_broken		:1,
-			pebs_prec_dist	:1,
+			pebs_prec_dist		:1,
-			pebs_no_tlb	:1;
+			pebs_no_tlb		:1,
+			pebs_no_isolation	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	void		(*drain_pebs)(struct pt_regs *regs);

arch/x86/include/asm/cpu_device_id.h

@@ -11,4 +11,32 @@
 
 extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 
+/*
+ * Match specific microcode revisions.
+ *
+ * vendor/family/model/stepping must be all set.
+ *
+ * Only checks against the boot CPU.  When mixed-stepping configs are
+ * valid for a CPU model, add a quirk for every valid stepping and
+ * do the fine-tuning in the quirk handler.
+ */
+
+struct x86_cpu_desc {
+	__u8	x86_family;
+	__u8	x86_vendor;
+	__u8	x86_model;
+	__u8	x86_stepping;
+	__u32	x86_microcode_rev;
+};
+
+#define INTEL_CPU_DESC(mod, step, rev) {			\
+	.x86_family = 6,					\
+	.x86_vendor = X86_VENDOR_INTEL,				\
+	.x86_model = mod,					\
+	.x86_stepping = step,					\
+	.x86_microcode_rev = rev,				\
+}
+
+extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table);
+
 #endif

arch/x86/kernel/alternative.c

@@ -11,6 +11,7 @@
 #include <linux/stop_machine.h>
 #include <linux/slab.h>
 #include <linux/kdebug.h>
+#include <linux/kprobes.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -764,8 +765,8 @@ int poke_int3_handler(struct pt_regs *regs)
 	regs->ip = (unsigned long) bp_int3_handler;
 
 	return 1;
-
 }
+NOKPROBE_SYMBOL(poke_int3_handler);
 
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP

arch/x86/kernel/cpu/amd.c

@@ -819,11 +819,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
-	/*
+
-	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
+	/* Fix erratum 1076: CPB feature bit not being set in CPUID. */
-	 * all up to and including B1.
+	if (!cpu_has(c, X86_FEATURE_CPB))
-	 */
-	if (c->x86_model <= 1 && c->x86_stepping <= 1)
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 

arch/x86/kernel/cpu/match.c

@@ -48,3 +48,34 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	return NULL;
 }
 EXPORT_SYMBOL(x86_match_cpu);
+
+static const struct x86_cpu_desc *
+x86_match_cpu_with_stepping(const struct x86_cpu_desc *match)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	const struct x86_cpu_desc *m;
+
+	for (m = match; m->x86_family | m->x86_model; m++) {
+		if (c->x86_vendor != m->x86_vendor)
+			continue;
+		if (c->x86 != m->x86_family)
+			continue;
+		if (c->x86_model != m->x86_model)
+			continue;
+		if (c->x86_stepping != m->x86_stepping)
+			continue;
+		return m;
+	}
+	return NULL;
+}
+
+bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table)
+{
+	const struct x86_cpu_desc *res = x86_match_cpu_with_stepping(table);
+
+	if (!res || res->x86_microcode_rev > boot_cpu_data.microcode)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(x86_cpu_has_min_microcode_rev);

arch/x86/kernel/ftrace.c

@@ -269,7 +269,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
-static int is_ftrace_caller(unsigned long ip)
+static nokprobe_inline int is_ftrace_caller(unsigned long ip)
 {
 	if (ip == ftrace_update_func)
 		return 1;
@@ -299,6 +299,7 @@ int ftrace_int3_handler(struct pt_regs *regs)
 
 	return 1;
 }
+NOKPROBE_SYMBOL(ftrace_int3_handler);
 
 static int ftrace_write(unsigned long ip, const char *val, int size)
 {

arch/x86/kernel/kprobes/core.c

@@ -1028,6 +1028,13 @@ NOKPROBE_SYMBOL(kprobe_fault_handler);
 
 int __init arch_populate_kprobe_blacklist(void)
 {
+	int ret;
+
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					 (unsigned long)__irqentry_text_end);
+	if (ret)
+		return ret;
+
 	return kprobe_add_area_blacklist((unsigned long)__entry_text_start,
 					 (unsigned long)__entry_text_end);
 }

arch/x86/kernel/kprobes/opt.c

@@ -97,6 +97,7 @@ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
 }
 
 asm (
+			".pushsection .rodata\n"
 			"optprobe_template_func:\n"
 			".global optprobe_template_entry\n"
 			"optprobe_template_entry:\n"
@@ -136,8 +137,7 @@ asm (
 #endif
 			".global optprobe_template_end\n"
 			"optprobe_template_end:\n"
-			".type optprobe_template_func, @function\n"
+			".popsection\n");
-			".size optprobe_template_func, .-optprobe_template_func\n");
 
 void optprobe_template_func(void);
 STACK_FRAME_NON_STANDARD(optprobe_template_func);

arch/x86/kernel/traps.c

@@ -111,6 +111,7 @@ void ist_enter(struct pt_regs *regs)
 	/* This code is a bit fragile.  Test it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
 }
+NOKPROBE_SYMBOL(ist_enter);
 
 void ist_exit(struct pt_regs *regs)
 {

drivers/hwtracing/coresight/coresight-etm-perf.c

@@ -14,6 +14,7 @@
 #include <linux/perf_event.h>
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
+#include <linux/stringhash.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
@@ -30,11 +31,14 @@ static DEFINE_PER_CPU(struct coresight_device *, csdev_src);
 PMU_FORMAT_ATTR(cycacc,		"config:" __stringify(ETM_OPT_CYCACC));
 PMU_FORMAT_ATTR(timestamp,	"config:" __stringify(ETM_OPT_TS));
 PMU_FORMAT_ATTR(retstack,	"config:" __stringify(ETM_OPT_RETSTK));
+/* Sink ID - same for all ETMs */
+PMU_FORMAT_ATTR(sinkid,		"config2:0-31");
 
 static struct attribute *etm_config_formats_attr[] = {
 	&format_attr_cycacc.attr,
 	&format_attr_timestamp.attr,
 	&format_attr_retstack.attr,
+	&format_attr_sinkid.attr,
 	NULL,
 };
 
@@ -43,8 +47,18 @@ static const struct attribute_group etm_pmu_format_group = {
 	.attrs  = etm_config_formats_attr,
 };
 
+static struct attribute *etm_config_sinks_attr[] = {
+	NULL,
+};
+
+static const struct attribute_group etm_pmu_sinks_group = {
+	.name   = "sinks",
+	.attrs  = etm_config_sinks_attr,
+};
+
 static const struct attribute_group *etm_pmu_attr_groups[] = {
 	&etm_pmu_format_group,
+	&etm_pmu_sinks_group,
 	NULL,
 };
 
@@ -177,31 +191,28 @@ static void etm_free_aux(void *data)
 	schedule_work(&event_data->work);
 }
 
-static void *etm_setup_aux(int event_cpu, void **pages,
+static void *etm_setup_aux(struct perf_event *event, void **pages,
 			   int nr_pages, bool overwrite)
 {
-	int cpu;
+	u32 id;
+	int cpu = event->cpu;
 	cpumask_t *mask;
 	struct coresight_device *sink;
 	struct etm_event_data *event_data = NULL;
 
-	event_data = alloc_event_data(event_cpu);
+	event_data = alloc_event_data(cpu);
 	if (!event_data)
 		return NULL;
 	INIT_WORK(&event_data->work, free_event_data);
 
-	/*
+	/* First get the selected sink from user space. */
-	 * In theory nothing prevent tracers in a trace session from being
+	if (event->attr.config2) {
-	 * associated with different sinks, nor having a sink per tracer.  But
+		id = (u32)event->attr.config2;
-	 * until we have HW with this kind of topology we need to assume tracers
+		sink = coresight_get_sink_by_id(id);
-	 * in a trace session are using the same sink.  Therefore go through
+	} else {
-	 * the coresight bus and pick the first enabled sink.
+		sink = coresight_get_enabled_sink(true);
-	 *
+	}
-	 * When operated from sysFS users are responsible to enable the sink
+
-	 * while from perf, the perf tools will do it based on the choice made
-	 * on the cmd line.  As such the "enable_sink" flag in sysFS is reset.
-	 */
-	sink = coresight_get_enabled_sink(true);
 	if (!sink || !sink_ops(sink)->alloc_buffer)
 		goto err;
 
@@ -422,15 +433,16 @@ static int etm_addr_filters_validate(struct list_head *filters)
 static void etm_addr_filters_sync(struct perf_event *event)
 {
 	struct perf_addr_filters_head *head = perf_event_addr_filters(event);
-	unsigned long start, stop, *offs = event->addr_filters_offs;
+	unsigned long start, stop;
+	struct perf_addr_filter_range *fr = event->addr_filter_ranges;
 	struct etm_filters *filters = event->hw.addr_filters;
 	struct etm_filter *etm_filter;
 	struct perf_addr_filter *filter;
 	int i = 0;
 
 	list_for_each_entry(filter, &head->list, entry) {
-		start = filter->offset + offs[i];
+		start = fr[i].start;
-		stop = start + filter->size;
+		stop = start + fr[i].size;
 		etm_filter = &filters->etm_filter[i];
 
 		switch (filter->action) {
@@ -479,6 +491,77 @@ int etm_perf_symlink(struct coresight_device *csdev, bool link)
 	return 0;
 }
 
+static ssize_t etm_perf_sink_name_show(struct device *dev,
+				       struct device_attribute *dattr,
+				       char *buf)
+{
+	struct dev_ext_attribute *ea;
+
+	ea = container_of(dattr, struct dev_ext_attribute, attr);
+	return scnprintf(buf, PAGE_SIZE, "0x%lx\n", (unsigned long)(ea->var));
+}
+
+int etm_perf_add_symlink_sink(struct coresight_device *csdev)
+{
+	int ret;
+	unsigned long hash;
+	const char *name;
+	struct device *pmu_dev = etm_pmu.dev;
+	struct device *pdev = csdev->dev.parent;
+	struct dev_ext_attribute *ea;
+
+	if (csdev->type != CORESIGHT_DEV_TYPE_SINK &&
+	    csdev->type != CORESIGHT_DEV_TYPE_LINKSINK)
+		return -EINVAL;
+
+	if (csdev->ea != NULL)
+		return -EINVAL;
+
+	if (!etm_perf_up)
+		return -EPROBE_DEFER;
+
+	ea = devm_kzalloc(pdev, sizeof(*ea), GFP_KERNEL);
+	if (!ea)
+		return -ENOMEM;
+
+	name = dev_name(pdev);
+	/* See function coresight_get_sink_by_id() to know where this is used */
+	hash = hashlen_hash(hashlen_string(NULL, name));
+
+	ea->attr.attr.name = devm_kstrdup(pdev, name, GFP_KERNEL);
+	if (!ea->attr.attr.name)
+		return -ENOMEM;
+
+	ea->attr.attr.mode = 0444;
+	ea->attr.show = etm_perf_sink_name_show;
+	ea->var = (unsigned long *)hash;
+
+	ret = sysfs_add_file_to_group(&pmu_dev->kobj,
+				      &ea->attr.attr, "sinks");
+
+	if (!ret)
+		csdev->ea = ea;
+
+	return ret;
+}
+
+void etm_perf_del_symlink_sink(struct coresight_device *csdev)
+{
+	struct device *pmu_dev = etm_pmu.dev;
+	struct dev_ext_attribute *ea = csdev->ea;
+
+	if (csdev->type != CORESIGHT_DEV_TYPE_SINK &&
+	    csdev->type != CORESIGHT_DEV_TYPE_LINKSINK)
+		return;
+
+	if (!ea)
+		return;
+
+	sysfs_remove_file_from_group(&pmu_dev->kobj,
+				     &ea->attr.attr, "sinks");
+	csdev->ea = NULL;
+}
+
 static int __init etm_perf_init(void)
 {
 	int ret;

drivers/hwtracing/coresight/coresight-etm-perf.h

@@ -59,6 +59,8 @@ struct etm_event_data {
 
 #ifdef CONFIG_CORESIGHT
 int etm_perf_symlink(struct coresight_device *csdev, bool link);
+int etm_perf_add_symlink_sink(struct coresight_device *csdev);
+void etm_perf_del_symlink_sink(struct coresight_device *csdev);
 static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
 {
 	struct etm_event_data *data = perf_get_aux(handle);
@@ -70,7 +72,9 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
 #else
 static inline int etm_perf_symlink(struct coresight_device *csdev, bool link)
 { return -EINVAL; }
-
+int etm_perf_add_symlink_sink(struct coresight_device *csdev)
+{ return -EINVAL; }
+void etm_perf_del_symlink_sink(struct coresight_device *csdev) {}
 static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
 {
 	return NULL;

drivers/hwtracing/coresight/coresight-priv.h

@@ -147,6 +147,7 @@ void coresight_disable_path(struct list_head *path);
 int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data);
 struct coresight_device *coresight_get_sink(struct list_head *path);
 struct coresight_device *coresight_get_enabled_sink(bool reset);
+struct coresight_device *coresight_get_sink_by_id(u32 id);
 struct list_head *coresight_build_path(struct coresight_device *csdev,
 				       struct coresight_device *sink);
 void coresight_release_path(struct list_head *path);

drivers/hwtracing/coresight/coresight.c

@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/stringhash.h>
 #include <linux/mutex.h>
 #include <linux/clk.h>
 #include <linux/coresight.h>
@@ -18,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
 
+#include "coresight-etm-perf.h"
 #include "coresight-priv.h"
 
 static DEFINE_MUTEX(coresight_mutex);
@@ -540,6 +542,47 @@ struct coresight_device *coresight_get_enabled_sink(bool deactivate)
 	return dev ? to_coresight_device(dev) : NULL;
 }
 
+static int coresight_sink_by_id(struct device *dev, void *data)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+	unsigned long hash;
+
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	     csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+
+		if (!csdev->ea)
+			return 0;
+		/*
+		 * See function etm_perf_add_symlink_sink() to know where
+		 * this comes from.
+		 */
+		hash = (unsigned long)csdev->ea->var;
+
+		if ((u32)hash == *(u32 *)data)
+			return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * coresight_get_sink_by_id - returns the sink that matches the id
+ * @id: Id of the sink to match
+ *
+ * The name of a sink is unique, whether it is found on the AMBA bus or
+ * otherwise.  As such the hash of that name can easily be used to identify
+ * a sink.
+ */
+struct coresight_device *coresight_get_sink_by_id(u32 id)
+{
+	struct device *dev = NULL;
+
+	dev = bus_find_device(&coresight_bustype, NULL, &id,
+			      coresight_sink_by_id);
+
+	return dev ? to_coresight_device(dev) : NULL;
+}
+
 /*
  * coresight_grab_device - Power up this device and any of the helper
  * devices connected to it for trace operation. Since the helper devices
@@ -1167,6 +1210,22 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 		goto err_out;
 	}
 
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	    csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		ret = etm_perf_add_symlink_sink(csdev);
+
+		if (ret) {
+			device_unregister(&csdev->dev);
+			/*
+			 * As with the above, all resources are free'd
+			 * explicitly via coresight_device_release() triggered
+			 * from put_device(), which is in turn called from
+			 * function device_unregister().
+			 */
+			goto err_out;
+		}
+	}
+
 	mutex_lock(&coresight_mutex);
 
 	coresight_fixup_device_conns(csdev);
@@ -1185,6 +1244,7 @@ EXPORT_SYMBOL_GPL(coresight_register);
 
 void coresight_unregister(struct coresight_device *csdev)
 {
+	etm_perf_del_symlink_sink(csdev);
 	/* Remove references of that device in the topology */
 	coresight_remove_conns(csdev);
 	device_unregister(&csdev->dev);

drivers/perf/arm-cci.c

@@ -1327,15 +1327,6 @@ static int cci_pmu_event_init(struct perf_event *event)
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EOPNOTSUPP;
 
-	/* We have no filtering of any kind */
-	if (event->attr.exclude_user	||
-	    event->attr.exclude_kernel	||
-	    event->attr.exclude_hv	||
-	    event->attr.exclude_idle	||
-	    event->attr.exclude_host	||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	/*
 	 * Following the example set by other "uncore" PMUs, we accept any CPU
 	 * and rewrite its affinity dynamically rather than having perf core
@@ -1433,6 +1424,7 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 		.stop		= cci_pmu_stop,
 		.read		= pmu_read,
 		.attr_groups	= pmu_attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	cci_pmu->plat_device = pdev;

drivers/perf/arm-ccn.c

@@ -741,10 +741,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 	}
 
-	if (has_branch_stack(event) || event->attr.exclude_user ||
+	if (has_branch_stack(event)) {
-			event->attr.exclude_kernel || event->attr.exclude_hv ||
-			event->attr.exclude_idle || event->attr.exclude_host ||
-			event->attr.exclude_guest) {
 		dev_dbg(ccn->dev, "Can't exclude execution levels!\n");
 		return -EINVAL;
 	}
@@ -1290,6 +1287,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 		.read = arm_ccn_pmu_event_read,
 		.pmu_enable = arm_ccn_pmu_enable,
 		.pmu_disable = arm_ccn_pmu_disable,
+		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	/* No overflow interrupt? Have to use a timer instead. */

drivers/perf/arm_dsu_pmu.c

@@ -562,13 +562,7 @@ static int dsu_pmu_event_init(struct perf_event *event)
 		return -EINVAL;
 	}
 
-	if (has_branch_stack(event) ||
+	if (has_branch_stack(event)) {
-	    event->attr.exclude_user ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv ||
-	    event->attr.exclude_idle ||
-	    event->attr.exclude_host ||
-	    event->attr.exclude_guest) {
 		dev_dbg(dsu_pmu->pmu.dev, "Can't support filtering\n");
 		return -EINVAL;
 	}
@@ -735,6 +729,7 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 		.read		= dsu_pmu_read,
 
 		.attr_groups	= dsu_pmu_attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	rc = perf_pmu_register(&dsu_pmu->pmu, name, -1);

drivers/perf/arm_pmu.c

@@ -356,13 +356,6 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 	return ret;
 }
 
-static int
-event_requires_mode_exclusion(struct perf_event_attr *attr)
-{
-	return attr->exclude_idle || attr->exclude_user ||
-	       attr->exclude_kernel || attr->exclude_hv;
-}
-
 static int
 __hw_perf_event_init(struct perf_event *event)
 {
@@ -393,9 +386,8 @@ __hw_perf_event_init(struct perf_event *event)
 	/*
 	 * Check whether we need to exclude the counter from certain modes.
 	 */
-	if ((!armpmu->set_event_filter ||
+	if (armpmu->set_event_filter &&
-	     armpmu->set_event_filter(hwc, &event->attr)) &&
+	    armpmu->set_event_filter(hwc, &event->attr)) {
-	     event_requires_mode_exclusion(&event->attr)) {
 		pr_debug("ARM performance counters do not support "
 			 "mode exclusion\n");
 		return -EOPNOTSUPP;
@@ -867,6 +859,9 @@ int armpmu_register(struct arm_pmu *pmu)
 	if (ret)
 		return ret;
 
+	if (!pmu->set_event_filter)
+		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
+
 	ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
 	if (ret)
 		goto out_destroy;

drivers/perf/arm_spe_pmu.c

@@ -824,10 +824,10 @@ static void arm_spe_pmu_read(struct perf_event *event)
 {
 }
 
-static void *arm_spe_pmu_setup_aux(int cpu, void **pages, int nr_pages,
+static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages,
-				   bool snapshot)
+				   int nr_pages, bool snapshot)
 {
-	int i;
+	int i, cpu = event->cpu;
 	struct page **pglist;
 	struct arm_spe_pmu_buf *buf;
 

drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c

@@ -396,6 +396,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
 		.attr_groups	= hisi_ddrc_pmu_attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);

drivers/perf/hisilicon/hisi_uncore_hha_pmu.c

@@ -407,6 +407,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
 		.attr_groups	= hisi_hha_pmu_attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	ret = perf_pmu_register(&hha_pmu->pmu, name, -1);

drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c

@@ -397,6 +397,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
 		.attr_groups	= hisi_l3c_pmu_attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);

drivers/perf/hisilicon/hisi_uncore_pmu.c

@@ -142,15 +142,6 @@ int hisi_uncore_pmu_event_init(struct perf_event *event)
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EOPNOTSUPP;
 
-	/* counters do not have these bits */
-	if (event->attr.exclude_user	||
-	    event->attr.exclude_kernel	||
-	    event->attr.exclude_host	||
-	    event->attr.exclude_guest	||
-	    event->attr.exclude_hv	||
-	    event->attr.exclude_idle)
-		return -EINVAL;
-
 	/*
 	 *  The uncore counters not specific to any CPU, so cannot
 	 *  support per-task

drivers/perf/qcom_l2_pmu.c

@@ -509,14 +509,6 @@ static int l2_cache_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 	}
 
-	/* We cannot filter accurately so we just don't allow it. */
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-	    event->attr.exclude_hv || event->attr.exclude_idle) {
-		dev_dbg_ratelimited(&l2cache_pmu->pdev->dev,
-				    "Can't exclude execution levels\n");
-		return -EOPNOTSUPP;
-	}
-
 	if (((L2_EVT_GROUP(event->attr.config) > L2_EVT_GROUP_MAX) ||
 	     ((event->attr.config & ~L2_EVT_MASK) != 0)) &&
 	    (event->attr.config != L2CYCLE_CTR_RAW_CODE)) {
@@ -982,6 +974,7 @@ static int l2_cache_pmu_probe(struct platform_device *pdev)
 		.stop		= l2_cache_event_stop,
 		.read		= l2_cache_event_read,
 		.attr_groups	= l2_cache_pmu_attr_grps,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	l2cache_pmu->num_counters = get_num_counters();

drivers/perf/qcom_l3_pmu.c

@@ -494,13 +494,6 @@ static int qcom_l3_cache__event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	/*
-	 * There are no per-counter mode filters in the PMU.
-	 */
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-	    event->attr.exclude_hv || event->attr.exclude_idle)
-		return -EINVAL;
-
 	/*
 	 * Sampling not supported since these events are not core-attributable.
 	 */
@@ -777,6 +770,7 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 		.read		= qcom_l3_cache__event_read,
 
 		.attr_groups	= qcom_l3_cache_pmu_attr_grps,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	memrc = platform_get_resource(pdev, IORESOURCE_MEM, 0);

drivers/perf/thunderx2_pmu.c

@@ -424,15 +424,6 @@ static int tx2_uncore_event_init(struct perf_event *event)
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	/* We have no filtering of any kind */
-	if (event->attr.exclude_user	||
-	    event->attr.exclude_kernel	||
-	    event->attr.exclude_hv	||
-	    event->attr.exclude_idle	||
-	    event->attr.exclude_host	||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -572,6 +563,7 @@ static int tx2_uncore_pmu_register(
 		.start		= tx2_uncore_event_start,
 		.stop		= tx2_uncore_event_stop,
 		.read		= tx2_uncore_event_read,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	tx2_pmu->pmu.name = devm_kasprintf(dev, GFP_KERNEL,

drivers/perf/xgene_pmu.c

@@ -917,11 +917,6 @@ static int xgene_perf_event_init(struct perf_event *event)
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	/* SOC counters do not have usr/os/guest/host bits */
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-	    event->attr.exclude_host || event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 	/*
@@ -1136,6 +1131,7 @@ static int xgene_init_perf(struct xgene_pmu_dev *pmu_dev, char *name)
 		.start		= xgene_perf_start,
 		.stop		= xgene_perf_stop,
 		.read		= xgene_perf_read,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	/* Hardware counter init */

include/linux/coresight.h

@@ -154,8 +154,9 @@ struct coresight_connection {
  * @orphan:	true if the component has connections that haven't been linked.
  * @enable:	'true' if component is currently part of an active path.
  * @activated:	'true' only if a _sink_ has been activated.  A sink can be
-		activated but not yet enabled.  Enabling for a _sink_
+ *		activated but not yet enabled.  Enabling for a _sink_
-		happens when a source has been selected for that it.
+ *		appens when a source has been selected for that it.
+ * @ea:		Device attribute for sink representation under PMU directory.
  */
 struct coresight_device {
 	struct coresight_connection *conns;
@@ -168,7 +169,9 @@ struct coresight_device {
 	atomic_t *refcnt;
 	bool orphan;
 	bool enable;	/* true only if configured as part of a path */
+	/* sink specific fields */
 	bool activated;	/* true only if a sink is part of a path */
+	struct dev_ext_attribute *ea;
 };
 
 #define to_coresight_device(d) container_of(d, struct coresight_device, dev)

include/linux/filter.h

@@ -1007,6 +1007,7 @@ bpf_address_lookup(unsigned long addr, unsigned long *size,
 
 void bpf_prog_kallsyms_add(struct bpf_prog *fp);
 void bpf_prog_kallsyms_del(struct bpf_prog *fp);
+void bpf_get_prog_name(const struct bpf_prog *prog, char *sym);
 
 #else /* CONFIG_BPF_JIT */
 
@@ -1062,6 +1063,12 @@ static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 {
 }
+
+static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+{
+	sym[0] = '\0';
+}
+
 #endif /* CONFIG_BPF_JIT */
 
 void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);

include/linux/perf_event.h

@@ -53,8 +53,8 @@ struct perf_guest_info_callbacks {
 #include <linux/atomic.h>
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
-#include <linux/workqueue.h>
 #include <linux/cgroup.h>
+#include <linux/refcount.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -244,6 +244,7 @@ struct perf_event;
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
+#define PERF_PMU_CAP_NO_EXCLUDE			0x80
 
 /**
  * struct pmu - generic performance monitoring unit
@@ -409,7 +410,7 @@ struct pmu {
 	/*
 	 * Set up pmu-private data structures for an AUX area
 	 */
-	void *(*setup_aux)		(int cpu, void **pages,
+	void *(*setup_aux)		(struct perf_event *event, void **pages,
 					 int nr_pages, bool overwrite);
 					/* optional */
 
@@ -494,6 +495,11 @@ struct perf_addr_filters_head {
 	unsigned int		nr_file_filters;
 };
 
+struct perf_addr_filter_range {
+	unsigned long		start;
+	unsigned long		size;
+};
+
 /**
  * enum perf_event_state - the states of an event:
  */
@@ -670,7 +676,7 @@ struct perf_event {
 	/* address range filters */
 	struct perf_addr_filters_head	addr_filters;
 	/* vma address array for file-based filders */
-	unsigned long			*addr_filters_offs;
+	struct perf_addr_filter_range	*addr_filter_ranges;
 	unsigned long			addr_filters_gen;
 
 	void (*destroy)(struct perf_event *);
@@ -742,7 +748,7 @@ struct perf_event_context {
 	int				nr_stat;
 	int				nr_freq;
 	int				rotate_disable;
-	atomic_t			refcount;
+	refcount_t			refcount;
 	struct task_struct		*task;
 
 	/*
@@ -983,9 +989,9 @@ extern void perf_event_output_forward(struct perf_event *event,
 extern void perf_event_output_backward(struct perf_event *event,
 				       struct perf_sample_data *data,
 				       struct pt_regs *regs);
-extern void perf_event_output(struct perf_event *event,
+extern int perf_event_output(struct perf_event *event,
-			      struct perf_sample_data *data,
+			     struct perf_sample_data *data,
-			      struct pt_regs *regs);
+			     struct pt_regs *regs);
 
 static inline bool
 is_default_overflow_handler(struct perf_event *event)
@@ -1009,6 +1015,15 @@ perf_event__output_id_sample(struct perf_event *event,
 extern void
 perf_log_lost_samples(struct perf_event *event, u64 lost);
 
+static inline bool event_has_any_exclude_flag(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	return attr->exclude_idle || attr->exclude_user ||
+	       attr->exclude_kernel || attr->exclude_hv ||
+	       attr->exclude_guest || attr->exclude_host;
+}
+
 static inline bool is_sampling_event(struct perf_event *event)
 {
 	return event->attr.sample_period != 0;
@@ -1118,6 +1133,13 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
+
+extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
+			       bool unregister, const char *sym);
+extern void perf_event_bpf_event(struct bpf_prog *prog,
+				 enum perf_bpf_event_type type,
+				 u16 flags);
+
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -1338,6 +1360,13 @@ static inline int perf_unregister_guest_info_callbacks
 (struct perf_guest_info_callbacks *callbacks)				{ return 0; }
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
+
+typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);
+static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
+				      bool unregister, const char *sym)	{ }
+static inline void perf_event_bpf_event(struct bpf_prog *prog,
+					enum perf_bpf_event_type type,
+					u16 flags)			{ }
 static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_namespaces(struct task_struct *tsk)	{ }

include/uapi/linux/perf_event.h

@@ -372,7 +372,9 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				ksymbol        :  1, /* include ksymbol events */
+				bpf_event      :  1, /* include bpf events */
+				__reserved_1   : 33;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -445,8 +447,6 @@ struct perf_event_query_bpf {
 	__u32	ids[0];
 };
 
-#define perf_flags(attr)	(*(&(attr)->read_format + 1))
-
 /*
  * Ioctls that can be done on a perf event fd:
  */
@@ -965,9 +965,58 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_NAMESPACES			= 16,
 
+	/*
+	 * Record ksymbol register/unregister events:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				addr;
+	 *	u32				len;
+	 *	u16				ksym_type;
+	 *	u16				flags;
+	 *	char				name[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_KSYMBOL			= 17,
+
+	/*
+	 * Record bpf events:
+	 *  enum perf_bpf_event_type {
+	 *	PERF_BPF_EVENT_UNKNOWN		= 0,
+	 *	PERF_BPF_EVENT_PROG_LOAD	= 1,
+	 *	PERF_BPF_EVENT_PROG_UNLOAD	= 2,
+	 *  };
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u16				type;
+	 *	u16				flags;
+	 *	u32				id;
+	 *	u8				tag[BPF_TAG_SIZE];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_BPF_EVENT			= 18,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
+enum perf_record_ksymbol_type {
+	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
+	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
+};
+
+#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER	(1 << 0)
+
+enum perf_bpf_event_type {
+	PERF_BPF_EVENT_UNKNOWN		= 0,
+	PERF_BPF_EVENT_PROG_LOAD	= 1,
+	PERF_BPF_EVENT_PROG_UNLOAD	= 2,
+	PERF_BPF_EVENT_MAX,		/* non-ABI */
+};
+
 #define PERF_MAX_STACK_DEPTH		127
 #define PERF_MAX_CONTEXTS_PER_STACK	  8
 

kernel/bpf/core.c

@@ -539,7 +539,7 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog,
 	*symbol_end   = addr + hdr->pages * PAGE_SIZE;
 }
 
-static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 {
 	const char *end = sym + KSYM_NAME_LEN;
 	const struct btf_type *type;

kernel/bpf/syscall.c

@@ -1258,6 +1258,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
 		bpf_prog_kallsyms_del_all(prog);
@@ -1631,6 +1632,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	}
 
 	bpf_prog_kallsyms_add(prog);
+	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
 	return err;
 
 free_used_maps:

kernel/events/callchain.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Performance events callchain code, extracted from core.c:
  *
@@ -5,8 +6,6 @@
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- * For licensing details see kernel-base/COPYING
  */
 
 #include <linux/perf_event.h>

kernel/events/core.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Performance events core code:
  *
@@ -5,8 +6,6 @@
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- * For licensing details see kernel-base/COPYING
  */
 
 #include <linux/fs.h>
@@ -385,6 +384,8 @@ static atomic_t nr_namespaces_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
+static atomic_t nr_ksymbol_events __read_mostly;
+static atomic_t nr_bpf_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1171,7 +1172,7 @@ static void perf_event_ctx_deactivate(struct perf_event_context *ctx)
 
 static void get_ctx(struct perf_event_context *ctx)
 {
-	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
+	refcount_inc(&ctx->refcount);
 }
 
 static void free_ctx(struct rcu_head *head)
@@ -1185,7 +1186,7 @@ static void free_ctx(struct rcu_head *head)
 
 static void put_ctx(struct perf_event_context *ctx)
 {
-	if (atomic_dec_and_test(&ctx->refcount)) {
+	if (refcount_dec_and_test(&ctx->refcount)) {
 		if (ctx->parent_ctx)
 			put_ctx(ctx->parent_ctx);
 		if (ctx->task && ctx->task != TASK_TOMBSTONE)
@@ -1254,6 +1255,7 @@ static void put_ctx(struct perf_event_context *ctx)
  *	      perf_event_context::lock
  *	    perf_event::mmap_mutex
  *	    mmap_sem
+ *	      perf_addr_filters_head::lock
  *
  *    cpu_hotplug_lock
  *      pmus_lock
@@ -1267,7 +1269,7 @@ perf_event_ctx_lock_nested(struct perf_event *event, int nesting)
 again:
 	rcu_read_lock();
 	ctx = READ_ONCE(event->ctx);
-	if (!atomic_inc_not_zero(&ctx->refcount)) {
+	if (!refcount_inc_not_zero(&ctx->refcount)) {
 		rcu_read_unlock();
 		goto again;
 	}
@@ -1400,7 +1402,7 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 		}
 
 		if (ctx->task == TASK_TOMBSTONE ||
-		    !atomic_inc_not_zero(&ctx->refcount)) {
+		    !refcount_inc_not_zero(&ctx->refcount)) {
 			raw_spin_unlock(&ctx->lock);
 			ctx = NULL;
 		} else {
@@ -2797,7 +2799,7 @@ static int perf_event_stop(struct perf_event *event, int restart)
  *
  * (p1) when userspace mappings change as a result of (1) or (2) or (3) below,
  *      we update the addresses of corresponding vmas in
- *	event::addr_filters_offs array and bump the event::addr_filters_gen;
+ *	event::addr_filter_ranges array and bump the event::addr_filters_gen;
  * (p2) when an event is scheduled in (pmu::add), it calls
  *      perf_event_addr_filters_sync() which calls pmu::addr_filters_sync()
  *      if the generation has changed since the previous call.
@@ -4056,7 +4058,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 	INIT_LIST_HEAD(&ctx->event_list);
 	INIT_LIST_HEAD(&ctx->pinned_active);
 	INIT_LIST_HEAD(&ctx->flexible_active);
-	atomic_set(&ctx->refcount, 1);
+	refcount_set(&ctx->refcount, 1);
 }
 
 static struct perf_event_context *
@@ -4235,7 +4237,7 @@ static bool is_sb_event(struct perf_event *event)
 
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
-	    attr->task ||
+	    attr->task || attr->ksymbol ||
 	    attr->context_switch)
 		return true;
 	return false;
@@ -4305,6 +4307,10 @@ static void unaccount_event(struct perf_event *event)
 		dec = true;
 	if (has_branch_stack(event))
 		dec = true;
+	if (event->attr.ksymbol)
+		atomic_dec(&nr_ksymbol_events);
+	if (event->attr.bpf_event)
+		atomic_dec(&nr_bpf_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -4440,7 +4446,7 @@ static void _free_event(struct perf_event *event)
 
 	perf_event_free_bpf_prog(event);
 	perf_addr_filters_splice(event, NULL);
-	kfree(event->addr_filters_offs);
+	kfree(event->addr_filter_ranges);
 
 	if (event->destroy)
 		event->destroy(event);
@@ -5396,7 +5402,7 @@ struct ring_buffer *ring_buffer_get(struct perf_event *event)
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
 	if (rb) {
-		if (!atomic_inc_not_zero(&rb->refcount))
+		if (!refcount_inc_not_zero(&rb->refcount))
 			rb = NULL;
 	}
 	rcu_read_unlock();
@@ -5406,7 +5412,7 @@ struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 void ring_buffer_put(struct ring_buffer *rb)
 {
-	if (!atomic_dec_and_test(&rb->refcount))
+	if (!refcount_dec_and_test(&rb->refcount))
 		return;
 
 	WARN_ON_ONCE(!list_empty(&rb->event_list));
@@ -5471,7 +5477,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 
 		/* this has to be the last one */
 		rb_free_aux(rb);
-		WARN_ON_ONCE(atomic_read(&rb->aux_refcount));
+		WARN_ON_ONCE(refcount_read(&rb->aux_refcount));
 
 		mutex_unlock(&event->mmap_mutex);
 	}
@@ -6497,7 +6503,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
-static __always_inline void
+static __always_inline int
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
@@ -6507,13 +6513,15 @@ __perf_event_output(struct perf_event *event,
 {
 	struct perf_output_handle handle;
 	struct perf_event_header header;
+	int err;
 
 	/* protect the callchain buffers */
 	rcu_read_lock();
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	if (output_begin(&handle, event, header.size))
+	err = output_begin(&handle, event, header.size);
+	if (err)
 		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
@@ -6522,6 +6530,7 @@ __perf_event_output(struct perf_event *event,
 
 exit:
 	rcu_read_unlock();
+	return err;
 }
 
 void
@@ -6540,12 +6549,12 @@ perf_event_output_backward(struct perf_event *event,
 	__perf_event_output(event, data, regs, perf_output_begin_backward);
 }
 
-void
+int
 perf_event_output(struct perf_event *event,
 		  struct perf_sample_data *data,
 		  struct pt_regs *regs)
 {
-	__perf_event_output(event, data, regs, perf_output_begin);
+	return __perf_event_output(event, data, regs, perf_output_begin);
 }
 
 /*
@@ -6686,7 +6695,8 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
 		if (filter->path.dentry) {
-			event->addr_filters_offs[count] = 0;
+			event->addr_filter_ranges[count].start = 0;
+			event->addr_filter_ranges[count].size = 0;
 			restart++;
 		}
 
@@ -7366,28 +7376,47 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 	return true;
 }
 
+static bool perf_addr_filter_vma_adjust(struct perf_addr_filter *filter,
+					struct vm_area_struct *vma,
+					struct perf_addr_filter_range *fr)
+{
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
+	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+	struct file *file = vma->vm_file;
+
+	if (!perf_addr_filter_match(filter, file, off, vma_size))
+		return false;
+
+	if (filter->offset < off) {
+		fr->start = vma->vm_start;
+		fr->size = min(vma_size, filter->size - (off - filter->offset));
+	} else {
+		fr->start = vma->vm_start + filter->offset - off;
+		fr->size = min(vma->vm_end - fr->start, filter->size);
+	}
+
+	return true;
+}
+
 static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
 {
 	struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
 	struct vm_area_struct *vma = data;
-	unsigned long off = vma->vm_pgoff << PAGE_SHIFT, flags;
-	struct file *file = vma->vm_file;
 	struct perf_addr_filter *filter;
 	unsigned int restart = 0, count = 0;
+	unsigned long flags;
 
 	if (!has_addr_filter(event))
 		return;
 
-	if (!file)
+	if (!vma->vm_file)
 		return;
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		if (perf_addr_filter_match(filter, file, off,
+		if (perf_addr_filter_vma_adjust(filter, vma,
-					     vma->vm_end - vma->vm_start)) {
+						&event->addr_filter_ranges[count]))
-			event->addr_filters_offs[count] = vma->vm_start;
 			restart++;
-		}
 
 		count++;
 	}
@@ -7658,6 +7687,207 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 	perf_output_end(&handle);
 }
 
+/*
+ * ksymbol register/unregister tracking
+ */
+
+struct perf_ksymbol_event {
+	const char	*name;
+	int		name_len;
+	struct {
+		struct perf_event_header        header;
+		u64				addr;
+		u32				len;
+		u16				ksym_type;
+		u16				flags;
+	} event_id;
+};
+
+static int perf_event_ksymbol_match(struct perf_event *event)
+{
+	return event->attr.ksymbol;
+}
+
+static void perf_event_ksymbol_output(struct perf_event *event, void *data)
+{
+	struct perf_ksymbol_event *ksymbol_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_ksymbol_match(event))
+		return;
+
+	perf_event_header__init_id(&ksymbol_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				ksymbol_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, ksymbol_event->event_id);
+	__output_copy(&handle, ksymbol_event->name, ksymbol_event->name_len);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
+			const char *sym)
+{
+	struct perf_ksymbol_event ksymbol_event;
+	char name[KSYM_NAME_LEN];
+	u16 flags = 0;
+	int name_len;
+
+	if (!atomic_read(&nr_ksymbol_events))
+		return;
+
+	if (ksym_type >= PERF_RECORD_KSYMBOL_TYPE_MAX ||
+	    ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
+		goto err;
+
+	strlcpy(name, sym, KSYM_NAME_LEN);
+	name_len = strlen(name) + 1;
+	while (!IS_ALIGNED(name_len, sizeof(u64)))
+		name[name_len++] = '\0';
+	BUILD_BUG_ON(KSYM_NAME_LEN % sizeof(u64));
+
+	if (unregister)
+		flags |= PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER;
+
+	ksymbol_event = (struct perf_ksymbol_event){
+		.name = name,
+		.name_len = name_len,
+		.event_id = {
+			.header = {
+				.type = PERF_RECORD_KSYMBOL,
+				.size = sizeof(ksymbol_event.event_id) +
+					name_len,
+			},
+			.addr = addr,
+			.len = len,
+			.ksym_type = ksym_type,
+			.flags = flags,
+		},
+	};
+
+	perf_iterate_sb(perf_event_ksymbol_output, &ksymbol_event, NULL);
+	return;
+err:
+	WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type);
+}
+
+/*
+ * bpf program load/unload tracking
+ */
+
+struct perf_bpf_event {
+	struct bpf_prog	*prog;
+	struct {
+		struct perf_event_header        header;
+		u16				type;
+		u16				flags;
+		u32				id;
+		u8				tag[BPF_TAG_SIZE];
+	} event_id;
+};
+
+static int perf_event_bpf_match(struct perf_event *event)
+{
+	return event->attr.bpf_event;
+}
+
+static void perf_event_bpf_output(struct perf_event *event, void *data)
+{
+	struct perf_bpf_event *bpf_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_bpf_match(event))
+		return;
+
+	perf_event_header__init_id(&bpf_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				bpf_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, bpf_event->event_id);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
+					 enum perf_bpf_event_type type)
+{
+	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
+	char sym[KSYM_NAME_LEN];
+	int i;
+
+	if (prog->aux->func_cnt == 0) {
+		bpf_get_prog_name(prog, sym);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+				   (u64)(unsigned long)prog->bpf_func,
+				   prog->jited_len, unregister, sym);
+	} else {
+		for (i = 0; i < prog->aux->func_cnt; i++) {
+			struct bpf_prog *subprog = prog->aux->func[i];
+
+			bpf_get_prog_name(subprog, sym);
+			perf_event_ksymbol(
+				PERF_RECORD_KSYMBOL_TYPE_BPF,
+				(u64)(unsigned long)subprog->bpf_func,
+				subprog->jited_len, unregister, sym);
+		}
+	}
+}
+
+void perf_event_bpf_event(struct bpf_prog *prog,
+			  enum perf_bpf_event_type type,
+			  u16 flags)
+{
+	struct perf_bpf_event bpf_event;
+
+	if (type <= PERF_BPF_EVENT_UNKNOWN ||
+	    type >= PERF_BPF_EVENT_MAX)
+		return;
+
+	switch (type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		if (atomic_read(&nr_ksymbol_events))
+			perf_event_bpf_emit_ksymbols(prog, type);
+		break;
+	default:
+		break;
+	}
+
+	if (!atomic_read(&nr_bpf_events))
+		return;
+
+	bpf_event = (struct perf_bpf_event){
+		.prog = prog,
+		.event_id = {
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(bpf_event.event_id),
+			},
+			.type = type,
+			.flags = flags,
+			.id = prog->aux->id,
+		},
+	};
+
+	BUILD_BUG_ON(BPF_TAG_SIZE % sizeof(u64));
+
+	memcpy(bpf_event.event_id.tag, prog->tag, BPF_TAG_SIZE);
+	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -8776,26 +9006,19 @@ static void perf_addr_filters_splice(struct perf_event *event,
  * @filter; if so, adjust filter's address range.
  * Called with mm::mmap_sem down for reading.
  */
-static unsigned long perf_addr_filter_apply(struct perf_addr_filter *filter,
+static void perf_addr_filter_apply(struct perf_addr_filter *filter,
-					    struct mm_struct *mm)
+				   struct mm_struct *mm,
+				   struct perf_addr_filter_range *fr)
 {
 	struct vm_area_struct *vma;
 
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		struct file *file = vma->vm_file;
+		if (!vma->vm_file)
-		unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
-		unsigned long vma_size = vma->vm_end - vma->vm_start;
-
-		if (!file)
 			continue;
 
-		if (!perf_addr_filter_match(filter, file, off, vma_size))
+		if (perf_addr_filter_vma_adjust(filter, vma, fr))
-			continue;
+			return;
-
-		return vma->vm_start;
 	}
-
-	return 0;
 }
 
 /*
@@ -8829,15 +9052,15 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		event->addr_filters_offs[count] = 0;
+		event->addr_filter_ranges[count].start = 0;
+		event->addr_filter_ranges[count].size = 0;
 
 		/*
 		 * Adjust base offset if the filter is associated to a binary
 		 * that needs to be mapped:
 		 */
 		if (filter->path.dentry)
-			event->addr_filters_offs[count] =
+			perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]);
-				perf_addr_filter_apply(filter, mm);
 
 		count++;
 	}
@@ -9788,6 +10011,15 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 	if (ctx)
 		perf_event_ctx_unlock(event->group_leader, ctx);
 
+	if (!ret) {
+		if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE &&
+				event_has_any_exclude_flag(event)) {
+			if (event->destroy)
+				event->destroy(event);
+			ret = -EINVAL;
+		}
+	}
+
 	if (ret)
 		module_put(pmu->module);
 
@@ -9916,6 +10148,10 @@ static void account_event(struct perf_event *event)
 		inc = true;
 	if (is_cgroup_event(event))
 		inc = true;
+	if (event->attr.ksymbol)
+		atomic_inc(&nr_ksymbol_events);
+	if (event->attr.bpf_event)
+		atomic_inc(&nr_bpf_events);
 
 	if (inc) {
 		/*
@@ -10098,14 +10334,28 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_pmu;
 
 	if (has_addr_filter(event)) {
-		event->addr_filters_offs = kcalloc(pmu->nr_addr_filters,
+		event->addr_filter_ranges = kcalloc(pmu->nr_addr_filters,
-						   sizeof(unsigned long),
+						    sizeof(struct perf_addr_filter_range),
-						   GFP_KERNEL);
+						    GFP_KERNEL);
-		if (!event->addr_filters_offs) {
+		if (!event->addr_filter_ranges) {
 			err = -ENOMEM;
 			goto err_per_task;
 		}
 
+		/*
+		 * Clone the parent's vma offsets: they are valid until exec()
+		 * even if the mm is not shared with the parent.
+		 */
+		if (event->parent) {
+			struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+
+			raw_spin_lock_irq(&ifh->lock);
+			memcpy(event->addr_filter_ranges,
+			       event->parent->addr_filter_ranges,
+			       pmu->nr_addr_filters * sizeof(struct perf_addr_filter_range));
+			raw_spin_unlock_irq(&ifh->lock);
+		}
+
 		/* force hw sync on the address filters */
 		event->addr_filters_gen = 1;
 	}
@@ -10124,7 +10374,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	return event;
 
 err_addr_filters:
-	kfree(event->addr_filters_offs);
+	kfree(event->addr_filter_ranges);
 
 err_per_task:
 	exclusive_event_destroy(event);
@@ -10407,7 +10657,7 @@ __perf_event_ctx_lock_double(struct perf_event *group_leader,
 again:
 	rcu_read_lock();
 	gctx = READ_ONCE(group_leader->ctx);
-	if (!atomic_inc_not_zero(&gctx->refcount)) {
+	if (!refcount_inc_not_zero(&gctx->refcount)) {
 		rcu_read_unlock();
 		goto again;
 	}

kernel/events/hw_breakpoint.c

@@ -1,18 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright (C) 2007 Alan Stern
  * Copyright (C) IBM Corporation, 2009
  * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>

kernel/events/internal.h

@@ -4,13 +4,14 @@
 
 #include <linux/hardirq.h>
 #include <linux/uaccess.h>
+#include <linux/refcount.h>
 
 /* Buffer handling */
 
 #define RING_BUFFER_WRITABLE		0x01
 
 struct ring_buffer {
-	atomic_t			refcount;
+	refcount_t			refcount;
 	struct rcu_head			rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
@@ -48,7 +49,7 @@ struct ring_buffer {
 	atomic_t			aux_mmap_count;
 	unsigned long			aux_mmap_locked;
 	void				(*free_aux)(void *);
-	atomic_t			aux_refcount;
+	refcount_t			aux_refcount;
 	void				**aux_pages;
 	void				*aux_priv;
 

kernel/events/ring_buffer.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Performance events ring-buffer code:
  *
@@ -5,8 +6,6 @@
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- * For licensing details see kernel-base/COPYING
  */
 
 #include <linux/perf_event.h>
@@ -285,7 +284,7 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 	else
 		rb->overwrite = 1;
 
-	atomic_set(&rb->refcount, 1);
+	refcount_set(&rb->refcount, 1);
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
@@ -358,7 +357,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	if (!atomic_read(&rb->aux_mmap_count))
 		goto err;
 
-	if (!atomic_inc_not_zero(&rb->aux_refcount))
+	if (!refcount_inc_not_zero(&rb->aux_refcount))
 		goto err;
 
 	/*
@@ -658,7 +657,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 			goto out;
 	}
 
-	rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
+	rb->aux_priv = event->pmu->setup_aux(event, rb->aux_pages, nr_pages,
 					     overwrite);
 	if (!rb->aux_priv)
 		goto out;
@@ -671,7 +670,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 	 * we keep a refcount here to make sure either of the two can
 	 * reference them safely.
 	 */
-	atomic_set(&rb->aux_refcount, 1);
+	refcount_set(&rb->aux_refcount, 1);
 
 	rb->aux_overwrite = overwrite;
 	rb->aux_watermark = watermark;
@@ -690,7 +689,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 
 void rb_free_aux(struct ring_buffer *rb)
 {
-	if (atomic_dec_and_test(&rb->aux_refcount))
+	if (refcount_dec_and_test(&rb->aux_refcount))
 		__rb_free_aux(rb);
 }
 

kernel/events/uprobes.c

@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * User-space Probes (UProbes)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright (C) IBM Corporation, 2008-2012
  * Authors:
  *	Srikar Dronamraju

kernel/kallsyms.c

@@ -494,7 +494,7 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
-	iter->module_name[0] = '\0';
+	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
 	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
 			       &iter->value, &iter->type,

kernel/kprobes.c

@@ -1396,7 +1396,7 @@ bool __weak arch_within_kprobe_blacklist(unsigned long addr)
 	       addr < (unsigned long)__kprobes_text_end;
 }
 
-bool within_kprobe_blacklist(unsigned long addr)
+static bool __within_kprobe_blacklist(unsigned long addr)
 {
 	struct kprobe_blacklist_entry *ent;
 
@@ -1410,7 +1410,26 @@ bool within_kprobe_blacklist(unsigned long addr)
 		if (addr >= ent->start_addr && addr < ent->end_addr)
 			return true;
 	}
+	return false;
+}
 
+bool within_kprobe_blacklist(unsigned long addr)
+{
+	char symname[KSYM_NAME_LEN], *p;
+
+	if (__within_kprobe_blacklist(addr))
+		return true;
+
+	/* Check if the address is on a suffixed-symbol */
+	if (!lookup_symbol_name(addr, symname)) {
+		p = strchr(symname, '.');
+		if (!p)
+			return false;
+		*p = '\0';
+		addr = (unsigned long)kprobe_lookup_name(symname, 0);
+		if (addr)
+			return __within_kprobe_blacklist(addr);
+	}
 	return false;
 }
 

kernel/locking/lockdep.c

@@ -52,6 +52,7 @@
 #include <linux/jhash.h>
 #include <linux/nmi.h>
 #include <linux/rcupdate.h>
+#include <linux/kprobes.h>
 
 #include <asm/sections.h>
 
@@ -3161,6 +3162,7 @@ void lockdep_hardirqs_on(unsigned long ip)
 	__trace_hardirqs_on_caller(ip);
 	current->lockdep_recursion = 0;
 }
+NOKPROBE_SYMBOL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
@@ -3190,6 +3192,7 @@ void lockdep_hardirqs_off(unsigned long ip)
 	} else
 		debug_atomic_inc(redundant_hardirqs_off);
 }
+NOKPROBE_SYMBOL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
@@ -4007,7 +4010,8 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 	return 0;
 }
 
-static int __lock_is_held(const struct lockdep_map *lock, int read)
+static nokprobe_inline
+int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
 	int i;
@@ -4240,6 +4244,7 @@ int lock_is_held_type(const struct lockdep_map *lock, int read)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lock_is_held_type);
+NOKPROBE_SYMBOL(lock_is_held_type);
 
 struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 {

kernel/rcu/tree.c

@@ -50,6 +50,7 @@
 #include <linux/ftrace.h>
 #include <linux/tick.h>
 #include <linux/sysrq.h>
+#include <linux/kprobes.h>
 
 #include "tree.h"
 #include "rcu.h"
@@ -882,6 +883,7 @@ void rcu_nmi_enter(void)
 {
 	rcu_nmi_enter_common(false);
 }
+NOKPROBE_SYMBOL(rcu_nmi_enter);
 
 /**
  * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle

kernel/rcu/update.c

@@ -39,6 +39,7 @@
 #include <linux/tick.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched/isolation.h>
+#include <linux/kprobes.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -236,6 +237,7 @@ int notrace debug_lockdep_rcu_enabled(void)
 	       current->lockdep_recursion == 0;
 }
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
+NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
 
 /**
  * rcu_read_lock_held() - might we be in RCU read-side critical section?

kernel/trace/bpf_trace.c

@@ -431,8 +431,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
-	perf_event_output(event, sd, regs);
+	return perf_event_output(event, sd, regs);
-	return 0;
 }
 
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,

kernel/trace/trace_irqsoff.c

@@ -14,6 +14,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 
 #include "trace.h"
 
@@ -365,7 +366,7 @@ check_critical_timing(struct trace_array *tr,
 	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
-static inline void
+static nokprobe_inline void
 start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
 {
 	int cpu;
@@ -401,7 +402,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
 	atomic_dec(&data->disabled);
 }
 
-static inline void
+static nokprobe_inline void
 stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
 {
 	int cpu;
@@ -443,6 +444,7 @@ void start_critical_timings(void)
 		start_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc);
 }
 EXPORT_SYMBOL_GPL(start_critical_timings);
+NOKPROBE_SYMBOL(start_critical_timings);
 
 void stop_critical_timings(void)
 {
@@ -452,6 +454,7 @@ void stop_critical_timings(void)
 		stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc);
 }
 EXPORT_SYMBOL_GPL(stop_critical_timings);
+NOKPROBE_SYMBOL(stop_critical_timings);
 
 #ifdef CONFIG_FUNCTION_TRACER
 static bool function_enabled;
@@ -611,6 +614,7 @@ void tracer_hardirqs_on(unsigned long a0, unsigned long a1)
 	if (!preempt_trace(pc) && irq_trace())
 		stop_critical_timing(a0, a1, pc);
 }
+NOKPROBE_SYMBOL(tracer_hardirqs_on);
 
 void tracer_hardirqs_off(unsigned long a0, unsigned long a1)
 {
@@ -619,6 +623,7 @@ void tracer_hardirqs_off(unsigned long a0, unsigned long a1)
 	if (!preempt_trace(pc) && irq_trace())
 		start_critical_timing(a0, a1, pc);
 }
+NOKPROBE_SYMBOL(tracer_hardirqs_off);
 
 static int irqsoff_tracer_init(struct trace_array *tr)
 {

kernel/trace/trace_preemptirq.c

@@ -9,6 +9,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include "trace.h"
 
 #define CREATE_TRACE_POINTS
@@ -30,6 +31,7 @@ void trace_hardirqs_on(void)
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
+NOKPROBE_SYMBOL(trace_hardirqs_on);
 
 void trace_hardirqs_off(void)
 {
@@ -43,6 +45,7 @@ void trace_hardirqs_off(void)
 	lockdep_hardirqs_off(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
+NOKPROBE_SYMBOL(trace_hardirqs_off);
 
 __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 {
@@ -56,6 +59,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
+NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
@@ -69,6 +73,7 @@ __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 	lockdep_hardirqs_off(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
+NOKPROBE_SYMBOL(trace_hardirqs_off_caller);
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
 #ifdef CONFIG_TRACE_PREEMPT_TOGGLE

lib/bsearch.c

@@ -11,6 +11,7 @@
 
 #include <linux/export.h>
 #include <linux/bsearch.h>
+#include <linux/kprobes.h>
 
 /*
  * bsearch - binary search an array of elements
@@ -53,3 +54,4 @@ void *bsearch(const void *key, const void *base, size_t num, size_t size,
 	return NULL;
 }
 EXPORT_SYMBOL(bsearch);
+NOKPROBE_SYMBOL(bsearch);

lib/smp_processor_id.c

@@ -5,10 +5,11 @@
  * DEBUG_PREEMPT variant of smp_processor_id().
  */
 #include <linux/export.h>
+#include <linux/kprobes.h>
 #include <linux/sched.h>
 
-notrace static unsigned int check_preemption_disabled(const char *what1,
+notrace static nokprobe_inline
-							const char *what2)
+unsigned int check_preemption_disabled(const char *what1, const char *what2)
 {
 	int this_cpu = raw_smp_processor_id();
 
@@ -56,9 +57,11 @@ notrace unsigned int debug_smp_processor_id(void)
 	return check_preemption_disabled("smp_processor_id", "");
 }
 EXPORT_SYMBOL(debug_smp_processor_id);
+NOKPROBE_SYMBOL(debug_smp_processor_id);
 
 notrace void __this_cpu_preempt_check(const char *op)
 {
 	check_preemption_disabled("__this_cpu_", op);
 }
 EXPORT_SYMBOL(__this_cpu_preempt_check);
+NOKPROBE_SYMBOL(__this_cpu_preempt_check);

tools/build/Makefile.feature

@@ -53,10 +53,6 @@ FEATURE_TESTS_BASIC :=                  \
         libslang                        \
         libcrypto                       \
         libunwind                       \
-        libunwind-x86                   \
-        libunwind-x86_64                \
-        libunwind-arm                   \
-        libunwind-aarch64               \
         pthread-attr-setaffinity-np     \
         pthread-barrier     		\
         reallocarray                    \
@@ -70,7 +66,6 @@ FEATURE_TESTS_BASIC :=                  \
         sched_getcpu			\
         sdt				\
         setns				\
-        libopencsd			\
         libaio
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
@@ -84,6 +79,11 @@ FEATURE_TESTS_EXTRA :=                  \
          libbabeltrace                  \
          libbfd-liberty                 \
          libbfd-liberty-z               \
+         libopencsd                     \
+         libunwind-x86                  \
+         libunwind-x86_64               \
+         libunwind-arm                  \
+         libunwind-aarch64              \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
          libunwind-debug-frame-aarch64  \

tools/build/feature/test-all.c

@@ -170,14 +170,14 @@
 # include "test-setns.c"
 #undef main
 
-#define main main_test_libopencsd
-# include "test-libopencsd.c"
-#undef main
-
 #define main main_test_libaio
 # include "test-libaio.c"
 #undef main
 
+#define main main_test_reallocarray
+# include "test-reallocarray.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -217,8 +217,8 @@ int main(int argc, char *argv[])
 	main_test_sched_getcpu();
 	main_test_sdt();
 	main_test_setns();
-	main_test_libopencsd();
 	main_test_libaio();
+	main_test_reallocarray();
 
 	return 0;
 }

tools/build/feature/test-get_current_dir_name.c

@@ -8,3 +8,4 @@ int main(void)
 	free(get_current_dir_name());
 	return 0;
 }
+#undef _GNU_SOURCE

tools/build/feature/test-libpython.c

@@ -7,3 +7,4 @@ int main(void)
 
 	return 0;
 }
+#undef _GNU_SOURCE

tools/build/feature/test-reallocarray.c

@@ -6,3 +6,5 @@ int main(void)
 {
 	return !!reallocarray(NULL, 1, 1);
 }
+
+#undef _GNU_SOURCE

tools/build/feature/test-sched_getcpu.c

@@ -8,3 +8,5 @@ int main(void)
 {
 	return sched_getcpu();
 }
+
+#undef _GNU_SOURCE

tools/build/feature/test-setns.c

@@ -5,3 +5,4 @@ int main(void)
 {
 	return setns(0, 0);
 }
+#undef _GNU_SOURCE

tools/include/linux/rbtree.h

@@ -43,13 +43,28 @@ struct rb_root {
 	struct rb_node *rb_node;
 };
 
+/*
+ * Leftmost-cached rbtrees.
+ *
+ * We do not cache the rightmost node based on footprint
+ * size vs number of potential users that could benefit
+ * from O(1) rb_last(). Just not worth it, users that want
+ * this feature can always implement the logic explicitly.
+ * Furthermore, users that want to cache both pointers may
+ * find it a bit asymmetric, but that's ok.
+ */
+struct rb_root_cached {
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+};
 
 #define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
 
 #define RB_ROOT	(struct rb_root) { NULL, }
+#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
-#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+#define RB_EMPTY_ROOT(root)  (READ_ONCE((root)->rb_node) == NULL)
 
 /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
 #define RB_EMPTY_NODE(node)  \
@@ -68,6 +83,12 @@ extern struct rb_node *rb_prev(const struct rb_node *);
 extern struct rb_node *rb_first(const struct rb_root *);
 extern struct rb_node *rb_last(const struct rb_root *);
 
+extern void rb_insert_color_cached(struct rb_node *,
+				   struct rb_root_cached *, bool);
+extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *);
+/* Same as rb_first(), but O(1) */
+#define rb_first_cached(root) (root)->rb_leftmost
+
 /* Postorder iteration - always visit the parent after its children */
 extern struct rb_node *rb_first_postorder(const struct rb_root *);
 extern struct rb_node *rb_next_postorder(const struct rb_node *);
@@ -75,6 +96,8 @@ extern struct rb_node *rb_next_postorder(const struct rb_node *);
 /* Fast replacement of a single node without remove/rebalance/add/rebalance */
 extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 			    struct rb_root *root);
+extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
+				   struct rb_root_cached *root);
 
 static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
 				struct rb_node **rb_link)
@@ -90,12 +113,29 @@ static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
 	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
 	})
 
-
+/**
-/*
+ * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of
- * Handy for checking that we are not deleting an entry that is
+ * given type allowing the backing memory of @pos to be invalidated
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ *
- * probably should be moved to lib/rbtree.c...
+ * @pos:	the 'type *' to use as a loop cursor.
+ * @n:		another 'type *' to use as temporary storage
+ * @root:	'rb_root *' of the rbtree.
+ * @field:	the name of the rb_node field within 'type'.
+ *
+ * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as
+ * list_for_each_entry_safe() and allows the iteration to continue independent
+ * of changes to @pos by the body of the loop.
+ *
+ * Note, however, that it cannot handle other modifications that re-order the
+ * rbtree it is iterating over. This includes calling rb_erase() on @pos, as
+ * rb_erase() may rebalance the tree, causing us to miss some nodes.
  */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+	for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
+	     pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \
+			typeof(*pos), field); 1; }); \
+	     pos = n)
+
 static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
 {
 	rb_erase(n, root);

tools/include/linux/rbtree_augmented.h

@@ -44,7 +44,9 @@ struct rb_augment_callbacks {
 	void (*rotate)(struct rb_node *old, struct rb_node *new);
 };
 
-extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+extern void __rb_insert_augmented(struct rb_node *node,
+				  struct rb_root *root,
+				  bool newleft, struct rb_node **leftmost,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
 /*
  * Fixup the rbtree and update the augmented information when rebalancing.
@@ -60,7 +62,16 @@ static inline void
 rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 		    const struct rb_augment_callbacks *augment)
 {
-	__rb_insert_augmented(node, root, augment->rotate);
+	__rb_insert_augmented(node, root, false, NULL, augment->rotate);
+}
+
+static inline void
+rb_insert_augmented_cached(struct rb_node *node,
+			   struct rb_root_cached *root, bool newleft,
+			   const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, &root->rb_root,
+			      newleft, &root->rb_leftmost, augment->rotate);
 }
 
 #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
@@ -93,7 +104,9 @@ rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
 	old->rbaugmented = rbcompute(old);				\
 }									\
 rbstatic const struct rb_augment_callbacks rbname = {			\
-	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+	.propagate = rbname ## _propagate,				\
+	.copy = rbname ## _copy,					\
+	.rotate = rbname ## _rotate					\
 };
 
 
@@ -126,11 +139,11 @@ __rb_change_child(struct rb_node *old, struct rb_node *new,
 {
 	if (parent) {
 		if (parent->rb_left == old)
-			parent->rb_left = new;
+			WRITE_ONCE(parent->rb_left, new);
 		else
-			parent->rb_right = new;
+			WRITE_ONCE(parent->rb_right, new);
 	} else
-		root->rb_node = new;
+		WRITE_ONCE(root->rb_node, new);
 }
 
 extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
@@ -138,12 +151,17 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 
 static __always_inline struct rb_node *
 __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     struct rb_node **leftmost,
 		     const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *child = node->rb_right;
+	struct rb_node *tmp = node->rb_left;
 	struct rb_node *parent, *rebalance;
 	unsigned long pc;
 
+	if (leftmost && node == *leftmost)
+		*leftmost = rb_next(node);
+
 	if (!tmp) {
 		/*
 		 * Case 1: node to erase has no more than 1 child (easy!)
@@ -170,6 +188,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		tmp = parent;
 	} else {
 		struct rb_node *successor = child, *child2;
+
 		tmp = child->rb_left;
 		if (!tmp) {
 			/*
@@ -183,6 +202,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 			 */
 			parent = successor;
 			child2 = successor->rb_right;
+
 			augment->copy(node, successor);
 		} else {
 			/*
@@ -204,19 +224,23 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 				successor = tmp;
 				tmp = tmp->rb_left;
 			} while (tmp);
-			parent->rb_left = child2 = successor->rb_right;
+			child2 = successor->rb_right;
-			successor->rb_right = child;
+			WRITE_ONCE(parent->rb_left, child2);
+			WRITE_ONCE(successor->rb_right, child);
 			rb_set_parent(child, successor);
+
 			augment->copy(node, successor);
 			augment->propagate(parent, successor);
 		}
 
-		successor->rb_left = tmp = node->rb_left;
+		tmp = node->rb_left;
+		WRITE_ONCE(successor->rb_left, tmp);
 		rb_set_parent(tmp, successor);
 
 		pc = node->__rb_parent_color;
 		tmp = __rb_parent(pc);
 		__rb_change_child(node, successor, tmp, root);
+
 		if (child2) {
 			successor->__rb_parent_color = pc;
 			rb_set_parent_color(child2, parent, RB_BLACK);
@@ -237,9 +261,21 @@ static __always_inline void
 rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		   const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	struct rb_node *rebalance = __rb_erase_augmented(node, root,
+							 NULL, augment);
 	if (rebalance)
 		__rb_erase_color(rebalance, root, augment->rotate);
 }
 
-#endif	/* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
+static __always_inline void
+rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root,
+			  const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root,
+							 &root->rb_leftmost,
+							 augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, &root->rb_root, augment->rotate);
+}
+
+#endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */

tools/include/uapi/linux/perf_event.h

@@ -372,7 +372,9 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				ksymbol        :  1, /* include ksymbol events */
+				bpf_event      :  1, /* include bpf events */
+				__reserved_1   : 33;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -445,8 +447,6 @@ struct perf_event_query_bpf {
 	__u32	ids[0];
 };
 
-#define perf_flags(attr)	(*(&(attr)->read_format + 1))
-
 /*
  * Ioctls that can be done on a perf event fd:
  */
@@ -965,9 +965,58 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_NAMESPACES			= 16,
 
+	/*
+	 * Record ksymbol register/unregister events:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				addr;
+	 *	u32				len;
+	 *	u16				ksym_type;
+	 *	u16				flags;
+	 *	char				name[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_KSYMBOL			= 17,
+
+	/*
+	 * Record bpf events:
+	 *  enum perf_bpf_event_type {
+	 *	PERF_BPF_EVENT_UNKNOWN		= 0,
+	 *	PERF_BPF_EVENT_PROG_LOAD	= 1,
+	 *	PERF_BPF_EVENT_PROG_UNLOAD	= 2,
+	 *  };
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u16				type;
+	 *	u16				flags;
+	 *	u32				id;
+	 *	u8				tag[BPF_TAG_SIZE];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_BPF_EVENT			= 18,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
+enum perf_record_ksymbol_type {
+	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
+	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
+};
+
+#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER	(1 << 0)
+
+enum perf_bpf_event_type {
+	PERF_BPF_EVENT_UNKNOWN		= 0,
+	PERF_BPF_EVENT_PROG_LOAD	= 1,
+	PERF_BPF_EVENT_PROG_UNLOAD	= 2,
+	PERF_BPF_EVENT_MAX,		/* non-ABI */
+};
+
 #define PERF_MAX_STACK_DEPTH		127
 #define PERF_MAX_CONTEXTS_PER_STACK	  8
 

tools/lib/rbtree.c

@@ -22,6 +22,7 @@
 */
 
 #include <linux/rbtree_augmented.h>
+#include <linux/export.h>
 
 /*
  * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
@@ -43,6 +44,30 @@
  *  parentheses and have some accompanying text comment.
  */
 
+/*
+ * Notes on lockless lookups:
+ *
+ * All stores to the tree structure (rb_left and rb_right) must be done using
+ * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the
+ * tree structure as seen in program order.
+ *
+ * These two requirements will allow lockless iteration of the tree -- not
+ * correct iteration mind you, tree rotations are not atomic so a lookup might
+ * miss entire subtrees.
+ *
+ * But they do guarantee that any such traversal will only see valid elements
+ * and that it will indeed complete -- does not get stuck in a loop.
+ *
+ * It also guarantees that if the lookup returns an element it is the 'correct'
+ * one. But not returning an element does _NOT_ mean it's not present.
+ *
+ * NOTE:
+ *
+ * Stores to __rb_parent_color are not important for simple lookups so those
+ * are left undone as of now. Nor did I check for loops involving parent
+ * pointers.
+ */
+
 static inline void rb_set_black(struct rb_node *rb)
 {
 	rb->__rb_parent_color |= RB_BLACK;
@@ -70,22 +95,35 @@ __rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
 
 static __always_inline void
 __rb_insert(struct rb_node *node, struct rb_root *root,
+	    bool newleft, struct rb_node **leftmost,
 	    void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
 	struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
 
+	if (newleft)
+		*leftmost = node;
+
 	while (true) {
 		/*
-		 * Loop invariant: node is red
+		 * Loop invariant: node is red.
-		 *
-		 * If there is a black parent, we are done.
-		 * Otherwise, take some corrective action as we don't
-		 * want a red root or two consecutive red nodes.
 		 */
-		if (!parent) {
+		if (unlikely(!parent)) {
+			/*
+			 * The inserted node is root. Either this is the
+			 * first node, or we recursed at Case 1 below and
+			 * are no longer violating 4).
+			 */
 			rb_set_parent_color(node, NULL, RB_BLACK);
 			break;
-		} else if (rb_is_black(parent))
+		}
+
+		/*
+		 * If there is a black parent, we are done.
+		 * Otherwise, take some corrective action as,
+		 * per 4), we don't want a red root or two
+		 * consecutive red nodes.
+		 */
+		if(rb_is_black(parent))
 			break;
 
 		gparent = rb_red_parent(parent);
@@ -94,7 +132,7 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 		if (parent != tmp) {	/* parent == gparent->rb_left */
 			if (tmp && rb_is_red(tmp)) {
 				/*
-				 * Case 1 - color flips
+				 * Case 1 - node's uncle is red (color flips).
 				 *
 				 *       G            g
 				 *      / \          / \
@@ -117,7 +155,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			tmp = parent->rb_right;
 			if (node == tmp) {
 				/*
-				 * Case 2 - left rotate at parent
+				 * Case 2 - node's uncle is black and node is
+				 * the parent's right child (left rotate at parent).
 				 *
 				 *      G             G
 				 *     / \           / \
@@ -128,8 +167,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 				 * This still leaves us in violation of 4), the
 				 * continuation into Case 3 will fix that.
 				 */
-				parent->rb_right = tmp = node->rb_left;
+				tmp = node->rb_left;
-				node->rb_left = parent;
+				WRITE_ONCE(parent->rb_right, tmp);
+				WRITE_ONCE(node->rb_left, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
@@ -140,7 +180,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			}
 
 			/*
-			 * Case 3 - right rotate at gparent
+			 * Case 3 - node's uncle is black and node is
+			 * the parent's left child (right rotate at gparent).
 			 *
 			 *        G           P
 			 *       / \         / \
@@ -148,8 +189,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			 *     /                 \
 			 *    n                   U
 			 */
-			gparent->rb_left = tmp;  /* == parent->rb_right */
+			WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */
-			parent->rb_right = gparent;
+			WRITE_ONCE(parent->rb_right, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -170,8 +211,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			tmp = parent->rb_left;
 			if (node == tmp) {
 				/* Case 2 - right rotate at parent */
-				parent->rb_left = tmp = node->rb_right;
+				tmp = node->rb_right;
-				node->rb_right = parent;
+				WRITE_ONCE(parent->rb_left, tmp);
+				WRITE_ONCE(node->rb_right, parent);
 				if (tmp)
 					rb_set_parent_color(tmp, parent,
 							    RB_BLACK);
@@ -182,8 +224,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 			}
 
 			/* Case 3 - left rotate at gparent */
-			gparent->rb_right = tmp;  /* == parent->rb_left */
+			WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */
-			parent->rb_left = gparent;
+			WRITE_ONCE(parent->rb_left, gparent);
 			if (tmp)
 				rb_set_parent_color(tmp, gparent, RB_BLACK);
 			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
@@ -223,8 +265,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 				 *      / \         / \
 				 *     Sl  Sr      N   Sl
 				 */
-				parent->rb_right = tmp1 = sibling->rb_left;
+				tmp1 = sibling->rb_left;
-				sibling->rb_left = parent;
+				WRITE_ONCE(parent->rb_right, tmp1);
+				WRITE_ONCE(sibling->rb_left, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
@@ -268,15 +311,31 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 				 *
 				 *   (p)           (p)
 				 *   / \           / \
-				 *  N   S    -->  N   Sl
+				 *  N   S    -->  N   sl
 				 *     / \             \
-				 *    sl  Sr            s
+				 *    sl  Sr            S
 				 *                       \
 				 *                        Sr
+				 *
+				 * Note: p might be red, and then both
+				 * p and sl are red after rotation(which
+				 * breaks property 4). This is fixed in
+				 * Case 4 (in __rb_rotate_set_parents()
+				 *         which set sl the color of p
+				 *         and set p RB_BLACK)
+				 *
+				 *   (p)            (sl)
+				 *   / \            /  \
+				 *  N   sl   -->   P    S
+				 *       \        /      \
+				 *        S      N        Sr
+				 *         \
+				 *          Sr
 				 */
-				sibling->rb_left = tmp1 = tmp2->rb_right;
+				tmp1 = tmp2->rb_right;
-				tmp2->rb_right = sibling;
+				WRITE_ONCE(sibling->rb_left, tmp1);
-				parent->rb_right = tmp2;
+				WRITE_ONCE(tmp2->rb_right, sibling);
+				WRITE_ONCE(parent->rb_right, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
@@ -296,8 +355,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 			 *        / \         / \
 			 *      (sl) sr      N  (sl)
 			 */
-			parent->rb_right = tmp2 = sibling->rb_left;
+			tmp2 = sibling->rb_left;
-			sibling->rb_left = parent;
+			WRITE_ONCE(parent->rb_right, tmp2);
+			WRITE_ONCE(sibling->rb_left, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
@@ -309,8 +369,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 			sibling = parent->rb_left;
 			if (rb_is_red(sibling)) {
 				/* Case 1 - right rotate at parent */
-				parent->rb_left = tmp1 = sibling->rb_right;
+				tmp1 = sibling->rb_right;
-				sibling->rb_right = parent;
+				WRITE_ONCE(parent->rb_left, tmp1);
+				WRITE_ONCE(sibling->rb_right, parent);
 				rb_set_parent_color(tmp1, parent, RB_BLACK);
 				__rb_rotate_set_parents(parent, sibling, root,
 							RB_RED);
@@ -334,10 +395,11 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 					}
 					break;
 				}
-				/* Case 3 - right rotate at sibling */
+				/* Case 3 - left rotate at sibling */
-				sibling->rb_right = tmp1 = tmp2->rb_left;
+				tmp1 = tmp2->rb_left;
-				tmp2->rb_left = sibling;
+				WRITE_ONCE(sibling->rb_right, tmp1);
-				parent->rb_left = tmp2;
+				WRITE_ONCE(tmp2->rb_left, sibling);
+				WRITE_ONCE(parent->rb_left, tmp2);
 				if (tmp1)
 					rb_set_parent_color(tmp1, sibling,
 							    RB_BLACK);
@@ -345,9 +407,10 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 				tmp1 = sibling;
 				sibling = tmp2;
 			}
-			/* Case 4 - left rotate at parent + color flips */
+			/* Case 4 - right rotate at parent + color flips */
-			parent->rb_left = tmp2 = sibling->rb_right;
+			tmp2 = sibling->rb_right;
-			sibling->rb_right = parent;
+			WRITE_ONCE(parent->rb_left, tmp2);
+			WRITE_ONCE(sibling->rb_right, parent);
 			rb_set_parent_color(tmp1, sibling, RB_BLACK);
 			if (tmp2)
 				rb_set_parent(tmp2, parent);
@@ -378,22 +441,41 @@ static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
 static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
 
 static const struct rb_augment_callbacks dummy_callbacks = {
-	dummy_propagate, dummy_copy, dummy_rotate
+	.propagate = dummy_propagate,
+	.copy = dummy_copy,
+	.rotate = dummy_rotate
 };
 
 void rb_insert_color(struct rb_node *node, struct rb_root *root)
 {
-	__rb_insert(node, root, dummy_rotate);
+	__rb_insert(node, root, false, NULL, dummy_rotate);
 }
 
 void rb_erase(struct rb_node *node, struct rb_root *root)
 {
 	struct rb_node *rebalance;
-	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	rebalance = __rb_erase_augmented(node, root,
+					 NULL, &dummy_callbacks);
 	if (rebalance)
 		____rb_erase_color(rebalance, root, dummy_rotate);
 }
 
+void rb_insert_color_cached(struct rb_node *node,
+			    struct rb_root_cached *root, bool leftmost)
+{
+	__rb_insert(node, &root->rb_root, leftmost,
+		    &root->rb_leftmost, dummy_rotate);
+}
+
+void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root)
+{
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, &root->rb_root,
+					 &root->rb_leftmost, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, &root->rb_root, dummy_rotate);
+}
+
 /*
  * Augmented rbtree manipulation functions.
  *
@@ -402,9 +484,10 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
  */
 
 void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+			   bool newleft, struct rb_node **leftmost,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
-	__rb_insert(node, root, augment_rotate);
+	__rb_insert(node, root, newleft, leftmost, augment_rotate);
 }
 
 /*
@@ -498,15 +581,24 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 {
 	struct rb_node *parent = rb_parent(victim);
 
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+
 	/* Set the surrounding nodes to point to the replacement */
-	__rb_change_child(victim, new, parent, root);
 	if (victim->rb_left)
 		rb_set_parent(victim->rb_left, new);
 	if (victim->rb_right)
 		rb_set_parent(victim->rb_right, new);
+	__rb_change_child(victim, new, parent, root);
+}
 
-	/* Copy the pointers/colour from the victim to the replacement */
+void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
-	*new = *victim;
+			    struct rb_root_cached *root)
+{
+	rb_replace_node(victim, new, &root->rb_root);
+
+	if (root->rb_leftmost == victim)
+		root->rb_leftmost = new;
 }
 
 static struct rb_node *rb_left_deepest_node(const struct rb_node *node)

tools/perf/Build

@@ -46,10 +46,10 @@ CFLAGS_builtin-trace.o	   += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_
 CFLAGS_builtin-report.o	   += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
 CFLAGS_builtin-report.o	   += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
 
-libperf-y += util/
+perf-y += util/
-libperf-y += arch/
+perf-y += arch/
-libperf-y += ui/
+perf-y += ui/
-libperf-y += scripts/
+perf-y += scripts/
-libperf-$(CONFIG_TRACE) += trace/beauty/
+perf-$(CONFIG_TRACE) += trace/beauty/
 
 gtk-y += ui/gtk/

tools/perf/Documentation/perf-config.txt

@@ -120,6 +120,10 @@ Given a $HOME/.perfconfig like this:
 		children = true
 		group = true
 
+	[llvm]
+		dump-obj = true
+		clang-opt = -g
+
 You can hide source code of annotate feature setting the config to false with
 
 	% perf config annotate.hide_src_code=true
@@ -553,6 +557,33 @@ trace.*::
 	trace.show_zeros::
 		Do not suppress syscall arguments that are equal to zero.
 
+llvm.*::
+	llvm.clang-path::
+		Path to clang. If omit, search it from $PATH.
+
+	llvm.clang-bpf-cmd-template::
+		Cmdline template. Below lines show its default value. Environment
+		variable is used to pass options.
+		"$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS \
+		-Wno-unused-value -Wno-pointer-sign -working-directory \
+		$WORKING_DIR  -c $CLANG_SOURCE -target bpf -O2 -o -"
+
+	llvm.clang-opt::
+		Options passed to clang.
+
+	llvm.kbuild-dir::
+		kbuild directory. If not set, use /lib/modules/`uname -r`/build.
+		If set to "" deliberately, skip kernel header auto-detector.
+
+	llvm.kbuild-opts::
+		Options passed to 'make' when detecting kernel header options.
+
+	llvm.dump-obj::
+		Enable perf dump BPF object files compiled by LLVM.
+
+	llvm.opts::
+		Options passed to llc.
+
 SEE ALSO
 --------
 linkperf:perf[1]

tools/perf/Documentation/perf-record.txt

@@ -88,6 +88,20 @@ OPTIONS
           If you want to profile write accesses in [0x1000~1008), just set
           'mem:0x1000/8:w'.
 
+        - a BPF source file (ending in .c) or a precompiled object file (ending
+          in .o) selects one or more BPF events.
+          The BPF program can attach to various perf events based on the ELF section
+          names.
+
+          When processing a '.c' file, perf searches an installed LLVM to compile it
+          into an object file first. Optional clang options can be passed via the
+          '--clang-opt' command line option, e.g.:
+
+            perf record --clang-opt "-DLINUX_VERSION_CODE=0x50000" \
+                        -e tests/bpf-script-example.c
+
+          Note: '--clang-opt' must be placed before '--event/-e'.
+
 	- a group of events surrounded by a pair of brace ("{event1,event2,...}").
 	  Each event is separated by commas and the group should be quoted to
 	  prevent the shell interpretation.  You also need to use --group on
@@ -440,6 +454,11 @@ Use <n> control blocks in asynchronous (Posix AIO) trace writing mode (default:
 Asynchronous mode is supported only when linking Perf tool with libc library
 providing implementation for Posix AIO API.
 
+--affinity=mode::
+Set affinity mask of trace reading thread according to the policy defined by 'mode' value:
+  node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
+  cpu  - thread affinity mask is set to cpu of the processed mmap buffer
+
 --all-kernel::
 Configure all used events to run in kernel space.
 

tools/perf/Documentation/perf-script.txt

@@ -159,6 +159,12 @@ OPTIONS
 	the override, and the result of the above is that only S/W and H/W
 	events are displayed with the given fields.
 
+	It's possible tp add/remove fields only for specific event type:
+
+		-Fsw:-cpu,-period
+
+	removes cpu and period from software events.
+
 	For the 'wildcard' option if a user selected field is invalid for an
 	event type, a message is displayed to the user that the option is
 	ignored for that type. For example:

tools/perf/Documentation/perf-trace.txt

@@ -210,6 +210,14 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	may happen, for instance, when a thread gets migrated to a different CPU
 	while processing a syscall.
 
+--map-dump::
+	Dump BPF maps setup by events passed via -e, for instance the augmented_raw_syscalls
+	living in tools/perf/examples/bpf/augmented_raw_syscalls.c. For now this
+	dumps just boolean map values and integer keys, in time this will print in hex
+	by default and use BTF when available, as well as use functions to do pretty
+	printing using the existing 'perf trace' syscall arg beautifiers to map integer
+	arguments to strings (pid to comm, syscall id to syscall name, etc).
+
 
 PAGEFAULTS
 ----------

tools/perf/Documentation/perf.data-file-format.txt

@@ -43,11 +43,10 @@ struct perf_file_section {
 
 Flags section:
 
-The header is followed by different optional headers, described by the bits set
+For each of the optional features a perf_file_section it placed after the data
-in flags. Only headers for which the bit is set are included. Each header
+section if the feature bit is set in the perf_header flags bitset. The
-consists of a perf_file_section located after the initial header.
+respective perf_file_section points to the data of the additional header and
-The respective perf_file_section points to the data of the additional
+defines its size.
-header and defines its size.
 
 Some headers consist of strings, which are defined like this:
 
@@ -131,7 +130,7 @@ An uint64_t with the total memory in bytes.
 
 	HEADER_CMDLINE = 11,
 
-A perf_header_string with the perf command line used to collect the data.
+A perf_header_string_list with the perf arg-vector used to collect the data.
 
 	HEADER_EVENT_DESC = 12,
 

tools/perf/Makefile.config

@@ -109,6 +109,13 @@ FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 
+FEATURE_CHECK_LDFLAGS-libunwind-arm = -lunwind -lunwind-arm
+FEATURE_CHECK_LDFLAGS-libunwind-aarch64 = -lunwind -lunwind-aarch64
+FEATURE_CHECK_LDFLAGS-libunwind-x86 = -lunwind -llzma -lunwind-x86
+FEATURE_CHECK_LDFLAGS-libunwind-x86_64 = -lunwind -llzma -lunwind-x86_64
+
+FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto
+
 ifdef CSINCLUDES
   LIBOPENCSD_CFLAGS := -I$(CSINCLUDES)
 endif
@@ -218,6 +225,8 @@ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
 FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
+FEATURE_CHECK_LDFLAGS-libaio = -lrt
+
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -386,7 +395,8 @@ ifeq ($(feature-setns), 1)
   $(call detected,CONFIG_SETNS)
 endif
 
-ifndef NO_CORESIGHT
+ifdef CORESIGHT
+  $(call feature_check,libopencsd)
   ifeq ($(feature-libopencsd), 1)
     CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS)
     LDFLAGS += $(LIBOPENCSD_LDFLAGS)
@@ -482,6 +492,7 @@ endif
 ifndef NO_LIBUNWIND
   have_libunwind :=
 
+  $(call feature_check,libunwind-x86)
   ifeq ($(feature-libunwind-x86), 1)
     $(call detected,CONFIG_LIBUNWIND_X86)
     CFLAGS += -DHAVE_LIBUNWIND_X86_SUPPORT
@@ -490,6 +501,7 @@ ifndef NO_LIBUNWIND
     have_libunwind = 1
   endif
 
+  $(call feature_check,libunwind-aarch64)
   ifeq ($(feature-libunwind-aarch64), 1)
     $(call detected,CONFIG_LIBUNWIND_AARCH64)
     CFLAGS += -DHAVE_LIBUNWIND_AARCH64_SUPPORT

tools/perf/Makefile.perf

@@ -102,7 +102,7 @@ include ../scripts/utilities.mak
 # When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if
 # llvm-config is not in $PATH.
 #
-# Define NO_CORESIGHT if you do not want support for CoreSight trace decoding.
+# Define CORESIGHT if you DO WANT support for CoreSight trace decoding.
 #
 # Define NO_AIO if you do not want support of Posix AIO based trace
 # streaming for record mode. Currently Posix AIO trace streaming is
@@ -344,9 +344,9 @@ endif
 
 export PERL_PATH
 
-LIB_FILE=$(OUTPUT)libperf.a
+LIBPERF_A=$(OUTPUT)libperf.a
 
-PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD)
+PERFLIBS = $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD)
 ifndef NO_LIBBPF
   PERFLIBS += $(LIBBPF)
 endif
@@ -549,6 +549,8 @@ JEVENTS_IN    := $(OUTPUT)pmu-events/jevents-in.o
 
 PMU_EVENTS_IN := $(OUTPUT)pmu-events/pmu-events-in.o
 
+LIBPERF_IN := $(OUTPUT)libperf-in.o
+
 export JEVENTS
 
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
@@ -565,9 +567,12 @@ $(JEVENTS): $(JEVENTS_IN)
 $(PMU_EVENTS_IN): $(JEVENTS) FORCE
 	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=pmu-events
 
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
+$(LIBPERF_IN): prepare FORCE
+	$(Q)$(MAKE) $(build)=libperf
+
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBPERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
-		$(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
+		$(PERF_IN) $(PMU_EVENTS_IN) $(LIBPERF_IN) $(LIBS) -o $@
 
 $(GTK_IN): FORCE
 	$(Q)$(MAKE) $(build)=gtk
@@ -683,12 +688,7 @@ endif
 
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
 
-LIBPERF_IN := $(OUTPUT)libperf-in.o
+$(LIBPERF_A): $(LIBPERF_IN)
-
-$(LIBPERF_IN): prepare FORCE
-	$(Q)$(MAKE) $(build)=libperf
-
-$(LIB_FILE): $(LIBPERF_IN)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS)
 
 LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)'
@@ -863,8 +863,8 @@ ifndef NO_LIBPYTHON
 	$(call QUIET_INSTALL, python-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \
-		$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
-		$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
+		$(INSTALL) scripts/python/*.py -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
 		$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 endif
 	$(call QUIET_INSTALL, perf_completion-script) \
@@ -910,7 +910,7 @@ python-clean:
 	$(python-clean)
 
 clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean python-clean
-	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so

tools/perf/arch/Build

@@ -1,2 +1,2 @@
-libperf-y += common.o
+perf-y += common.o
-libperf-y += $(SRCARCH)/
+perf-y += $(SRCARCH)/

tools/perf/arch/arm/Build

@@ -1,2 +1,2 @@
-libperf-y += util/
+perf-y += util/
-libperf-$(CONFIG_DWARF_UNWIND) += tests/
+perf-$(CONFIG_DWARF_UNWIND) += tests/

tools/perf/arch/arm/tests/Build

@@ -1,5 +1,5 @@
-libperf-y += regs_load.o
+perf-y += regs_load.o
-libperf-y += dwarf-unwind.o
+perf-y += dwarf-unwind.o
-libperf-y += vectors-page.o
+perf-y += vectors-page.o
 
-libperf-y += arch-tests.o
+perf-y += arch-tests.o

tools/perf/arch/arm/tests/dwarf-unwind.c

@@ -3,6 +3,7 @@
 #include "perf_regs.h"
 #include "thread.h"
 #include "map.h"
+#include "map_groups.h"
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"

tools/perf/arch/arm/util/Build

@@ -1,6 +1,6 @@
-libperf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_DWARF) += dwarf-regs.o
 
-libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
+perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
-libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
-libperf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs-etm.o
+perf-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs-etm.o

tools/perf/arch/arm/util/cs-etm.c

@@ -5,6 +5,7 @@
  */
 
 #include <api/fs/fs.h>
+#include <linux/bits.h>
 #include <linux/bitops.h>
 #include <linux/compiler.h>
 #include <linux/coresight-pmu.h>
@@ -22,12 +23,10 @@
 #include "../../util/thread_map.h"
 #include "../../util/cs-etm.h"
 
+#include <errno.h>
 #include <stdlib.h>
 #include <sys/stat.h>
 
-#define ENABLE_SINK_MAX	128
-#define CS_BUS_DEVICE_PATH "/bus/coresight/devices/"
-
 struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
@@ -60,10 +59,48 @@ static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
 	return 0;
 }
 
+static int cs_etm_set_sink_attr(struct perf_pmu *pmu,
+				struct perf_evsel *evsel)
+{
+	char msg[BUFSIZ], path[PATH_MAX], *sink;
+	struct perf_evsel_config_term *term;
+	int ret = -EINVAL;
+	u32 hash;
+
+	if (evsel->attr.config2 & GENMASK(31, 0))
+		return 0;
+
+	list_for_each_entry(term, &evsel->config_terms, list) {
+		if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG)
+			continue;
+
+		sink = term->val.drv_cfg;
+		snprintf(path, PATH_MAX, "sinks/%s", sink);
+
+		ret = perf_pmu__scan_file(pmu, path, "%x", &hash);
+		if (ret != 1) {
+			pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n",
+			       sink, perf_evsel__name(evsel), errno,
+			       str_error_r(errno, msg, sizeof(msg)));
+			return ret;
+		}
+
+		evsel->attr.config2 |= hash;
+		return 0;
+	}
+
+	/*
+	 * No sink was provided on the command line - for _now_ treat
+	 * this as an error.
+	 */
+	return ret;
+}
+
 static int cs_etm_recording_options(struct auxtrace_record *itr,
 				    struct perf_evlist *evlist,
 				    struct record_opts *opts)
 {
+	int ret;
 	struct cs_etm_recording *ptr =
 				container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
@@ -92,6 +129,10 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	if (!cs_etm_evsel)
 		return 0;
 
+	ret = cs_etm_set_sink_attr(cs_etm_pmu, cs_etm_evsel);
+	if (ret)
+		return ret;
+
 	if (opts->use_clockid) {
 		pr_err("Cannot use clockid (-k option) with %s\n",
 		       CORESIGHT_ETM_PMU_NAME);
@@ -598,54 +639,3 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 out:
 	return NULL;
 }
-
-static FILE *cs_device__open_file(const char *name)
-{
-	struct stat st;
-	char path[PATH_MAX];
-	const char *sysfs;
-
-	sysfs = sysfs__mountpoint();
-	if (!sysfs)
-		return NULL;
-
-	snprintf(path, PATH_MAX,
-		 "%s" CS_BUS_DEVICE_PATH "%s", sysfs, name);
-
-	if (stat(path, &st) < 0)
-		return NULL;
-
-	return fopen(path, "w");
-
-}
-
-static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...)
-{
-	va_list args;
-	FILE *file;
-	int ret = -EINVAL;
-
-	va_start(args, fmt);
-	file = cs_device__open_file(name);
-	if (file) {
-		ret = vfprintf(file, fmt, args);
-		fclose(file);
-	}
-	va_end(args);
-	return ret;
-}
-
-int cs_etm_set_drv_config(struct perf_evsel_config_term *term)
-{
-	int ret;
-	char enable_sink[ENABLE_SINK_MAX];
-
-	snprintf(enable_sink, ENABLE_SINK_MAX, "%s/%s",
-		 term->val.drv_cfg, "enable_sink");
-
-	ret = cs_device__print_file(enable_sink, "%d", 1);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}

tools/perf/arch/arm/util/cs-etm.h

@@ -7,9 +7,6 @@
 #ifndef INCLUDE__PERF_CS_ETM_H__
 #define INCLUDE__PERF_CS_ETM_H__
 
-#include "../../util/evsel.h"
-
 struct auxtrace_record *cs_etm_record_init(int *err);
-int cs_etm_set_drv_config(struct perf_evsel_config_term *term);
 
 #endif

tools/perf/arch/arm/util/pmu.c

@@ -7,8 +7,8 @@
 #include <string.h>
 #include <linux/coresight-pmu.h>
 #include <linux/perf_event.h>
+#include <linux/string.h>
 
-#include "cs-etm.h"
 #include "arm-spe.h"
 #include "../../util/pmu.h"
 
@@ -19,7 +19,6 @@ struct perf_event_attr
 	if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) {
 		/* add ETM default config here */
 		pmu->selectable = true;
-		pmu->set_drv_config = cs_etm_set_drv_config;
 #if defined(__aarch64__)
 	} else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
 		return arm_spe_pmu_default_config(pmu);

tools/perf/arch/arm64/Build

@@ -1,2 +1,2 @@
-libperf-y += util/
+perf-y += util/
-libperf-$(CONFIG_DWARF_UNWIND) += tests/
+perf-$(CONFIG_DWARF_UNWIND) += tests/

tools/perf/arch/arm64/tests/Build

@@ -1,4 +1,4 @@
-libperf-y += regs_load.o
+perf-y += regs_load.o
-libperf-y += dwarf-unwind.o
+perf-y += dwarf-unwind.o
 
-libperf-y += arch-tests.o
+perf-y += arch-tests.o

tools/perf/arch/arm64/tests/dwarf-unwind.c

@@ -3,6 +3,7 @@
 #include "perf_regs.h"
 #include "thread.h"
 #include "map.h"
+#include "map_groups.h"
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"

tools/perf/arch/arm64/util/Build

@@ -1,10 +1,10 @@
-libperf-y += header.o
+perf-y += header.o
-libperf-y += sym-handling.o
+perf-y += sym-handling.o
-libperf-$(CONFIG_DWARF)     += dwarf-regs.o
+perf-$(CONFIG_DWARF)     += dwarf-regs.o
-libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
-libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
-libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
+perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
 			      ../../arm/util/cs-etm.o \
 			      arm-spe.o

tools/perf/arch/nds32/Build

@@ -1 +1 @@
-libperf-y += util/
+perf-y += util/