[GIT PULL] perf fixes

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c7a286577d7592720c2f179aadfb325a1ff48c95 perf/x86/intel: Allow PEBS multi-entry in watermark mode

An x86 PMU constraint fix, an interface fix, and a Sparse fix.

 Thanks,

	Ingo

------------------>
Stephane Eranian (2):
      perf/x86/intel: Fix INTEL_FLAGS_EVENT_CONSTRAINT* masking
      perf/x86/intel: Allow PEBS multi-entry in watermark mode

Wang Hai (1):
      perf/x86/amd/iommu: Make the 'amd_iommu_attr_groups' symbol static


 arch/x86/events/amd/iommu.c  | 2 +-
 arch/x86/events/intel/core.c | 2 +-
 arch/x86/events/perf_event.h | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 7635c23f7d82..58a6993d7eb3 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -393,7 +393,7 @@ static __init int _init_events_attrs(void)
 	return 0;
 }
 
-const struct attribute_group *amd_iommu_attr_groups[] = {
+static const struct attribute_group *amd_iommu_attr_groups[] = {
 	&amd_iommu_format_group,
 	&amd_iommu_cpumask_group,
 	&amd_iommu_events_group,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ef763f535e3a..12ec402f4114 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3265,7 +3265,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
-		if (!(event->attr.freq || event->attr.wakeup_events)) {
+		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
 			      ~intel_pmu_large_pebs_flags(event)))
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 07fc84bb85c1..a6ac2f4f76fc 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -394,10 +394,10 @@ struct cpu_hw_events {
 
 /* Event constraint, but match on all event flags too. */
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
-	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
 
 #define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n)			\
-	EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
 
 /* Check only flags, but allow all event/umask */
 #define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Thu, 16 May 2019 18:05:18 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/c77ee64f8a04166236666dfd540ff684d2daa1c0

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Fri, 6 Jan 2023 12:57:48 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2023-01-06

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/d7a0853d650b381921732ff5bca618432a279033

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2023-01-06

   # HEAD: 57512b57dcfaf63c52d8ad2fb35321328cde31b0 perf/x86/rapl: Add support for Intel Emerald Rapids

Intel RAPL updates for new model IDs.

NOTE: technically this is hardware-enablement, but we generally make an 
exception for trivial expansions of model check tables that only affect 
those models. Let me know if it's a bridge too far for -rc3.

 Thanks,

	Ingo

------------------>
Chris Wilson (1):
      perf/x86/rapl: Treat Tigerlake like Icelake

Zhang Rui (2):
      perf/x86/rapl: Add support for Intel Meteor Lake
      perf/x86/rapl: Add support for Intel Emerald Rapids


 arch/x86/events/rapl.c | 5 +++++
 1 file changed, 5 insertions(+)

Re: [GIT PULL] perf fixes

[Ingo Molnar]

* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Sun, Oct 2, 2022 at 3:56 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> >  - Fix KVM guest PEBS register handling.
> 
> I wondered why my diffstat wasn't the same as yours, but it turns out
> it's because I got this one from the kvm tree earlier.

Oh - indeed, didn't notice that.

> It all merged fine, just surprising.

Yeah. These are the two commits:

  [perf/urgent]     f2aeea57504c ("perf/x86/core: Completely disable guest PEBS via guest's global_ctrl")
  [KVM tree]        87693645ae89 ("perf/x86/core: Completely disable guest PEBS via guest's global_ctrl")

Just to make sure I double checked that they are identical:

  thule:~/tip> git log -1 -p f2aeea57504c | grep -A 100 "^@@" | tail +2 | sha1sum 
  e758bebe3046ef6a51d19d7b5498e165dc8e37be  -

  thule:~/tip> git log -1 -p 87693645ae89 | grep -A 100 "^@@" | tail +2 | sha1sum 
  e758bebe3046ef6a51d19d7b5498e165dc8e37be  -

Paolo applied the fix a couple of hours after Peter, but we
never noticed the overlap & the perf/urgent base didn't have
Paolo's commit so I didn't notice when sending the tree.

Sorry about that!

Thanks,

	Ingo

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 2 Oct 2022 12:56:34 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-10-02

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/febae48afe6063105a0fad83d8e12a6addda7c6a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

Re: [GIT PULL] perf fixes

[Linus Torvalds]

On Sun, Oct 2, 2022 at 3:56 AM Ingo Molnar <mingo@kernel.org> wrote:
>
>  - Fix KVM guest PEBS register handling.

I wondered why my diffstat wasn't the same as yours, but it turns out
it's because I got this one from the kvm tree earlier.

It all merged fine, just surprising.

            Linus

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-10-02

   # HEAD: 6b959ba22d34ca793ffdb15b5715457c78e38b1a perf/core: Fix reentry problem in perf_output_read_group()

Misc fixes:

 - Fix a PMU enumeration/initialization bug on Intel Alder Lake CPUs.
 - Fix KVM guest PEBS register handling.
 - Fix race/reentry bug in perf_output_read_group() reading of PMU counters.

 Thanks,

	Ingo

------------------>
Kan Liang (1):
      perf/x86/intel: Fix unchecked MSR access error for Alder Lake N

Like Xu (1):
      perf/x86/core: Completely disable guest PEBS via guest's global_ctrl

Yang Jihong (1):
      perf/core: Fix reentry problem in perf_output_read_group()


 arch/x86/events/intel/core.c | 43 +++++++++++++++++++++++++++++++++++++++++--
 arch/x86/events/intel/ds.c   |  9 +++++++--
 arch/x86/events/perf_event.h |  2 ++
 kernel/events/core.c         |  9 +++++++++
 4 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cb98a05ee743..c20d8cd47c48 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(mem-loads,	mem_ld_grt,	"event=0xd0,umask=0x5,ldlat=3");
+EVENT_ATTR_STR(mem-stores,	mem_st_grt,	"event=0xd0,umask=0x6");
+
+static struct attribute *grt_mem_attrs[] = {
+	EVENT_PTR(mem_ld_grt),
+	EVENT_PTR(mem_st_grt),
+	NULL
+};
+
 static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
@@ -4052,8 +4061,9 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		/* Disable guest PEBS if host PEBS is enabled. */
 		arr[pebs_enable].guest = 0;
 	} else {
-		/* Disable guest PEBS for cross-mapped PEBS counters. */
+		/* Disable guest PEBS thoroughly for cross-mapped PEBS counters. */
 		arr[pebs_enable].guest &= ~kvm_pmu->host_cross_mapped_mask;
+		arr[global_ctrl].guest &= ~kvm_pmu->host_cross_mapped_mask;
 		/* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
 		arr[global_ctrl].guest |= arr[pebs_enable].guest;
 	}
@@ -5974,6 +5984,36 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
+	case INTEL_FAM6_ALDERLAKE_N:
+		x86_pmu.mid_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_grt_extra_regs;
+
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+		intel_pmu_pebs_data_source_grt();
+		x86_pmu.pebs_latency_data = adl_latency_data_small;
+		x86_pmu.get_event_constraints = tnt_get_event_constraints;
+		x86_pmu.limit_period = spr_limit_period;
+		td_attr = tnt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = nhm_format_attr;
+		pr_cont("Gracemont events, ");
+		name = "gracemont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
@@ -6316,7 +6356,6 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 		/*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index de1f55d51784..ac973c6f82ad 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem)
 	__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
 }
 
-static void __init intel_pmu_pebs_data_source_grt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source)
 {
 	data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
 	data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
 	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
 }
 
+void __init intel_pmu_pebs_data_source_grt(void)
+{
+	__intel_pmu_pebs_data_source_grt(pebs_data_source);
+}
+
 void __init intel_pmu_pebs_data_source_adl(void)
 {
 	u64 *data_source;
@@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
 
 	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
 	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
-	intel_pmu_pebs_data_source_grt(data_source);
+	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
 static u64 precise_store_data(u64 status)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba3d24a6a4ec..266143abcbd8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem);
 
 void intel_pmu_pebs_data_source_adl(void);
 
+void intel_pmu_pebs_data_source_grt(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2621fd24ad26..ff4bffc502c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6893,9 +6893,16 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
+	unsigned long flags;
 	u64 values[6];
 	int n = 0;
 
+	/*
+	 * Disabling interrupts avoids all counter scheduling
+	 * (context switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -6931,6 +6938,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 
 		__output_copy(handle, values, n * sizeof(u64));
 	}
+
+	local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 28 Aug 2022 16:35:57 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-28

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/4459d800f71d01042b36326fd8ece1f823b9da16

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-28

   # HEAD: 11745ecfe8fea4b4a4c322967a7605d2ecbd5080 perf/x86/intel/uncore: Fix broken read_counter() for SNB IMC PMU

Misc fixes: an Arch-LBR fix, a PEBS enumeration fix, an Intel DS fix,
PEBS constraints fix on Alder Lake CPUs and an Intel uncore PMU fix.

 Thanks,

	Ingo

------------------>
Kan Liang (2):
      perf/x86/lbr: Enable the branch type for the Arch LBR by default
      perf/x86/intel: Fix pebs event constraints for ADL

Peter Zijlstra (1):
      perf/x86/core: Set pebs_capable and PMU_FL_PEBS_ALL for the Baseline

Stephane Eranian (2):
      perf/x86/intel/ds: Fix precise store latency handling
      perf/x86/intel/uncore: Fix broken read_counter() for SNB IMC PMU


 arch/x86/events/intel/core.c       |  4 ----
 arch/x86/events/intel/ds.c         | 13 +++++++++++--
 arch/x86/events/intel/lbr.c        |  8 ++++++++
 arch/x86/events/intel/uncore_snb.c | 18 +++++++++++++++++-
 4 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2db93498ff71..cb98a05ee743 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6291,10 +6291,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
-		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 
@@ -6337,10 +6335,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
-		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 		x86_pmu.lbr_pt_coexist = true;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba60427caa6d..de1f55d51784 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -291,6 +291,7 @@ static u64 load_latency_data(struct perf_event *event, u64 status)
 static u64 store_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
 	u64 val;
 
 	dse.val = status;
@@ -304,7 +305,14 @@ static u64 store_latency_data(struct perf_event *event, u64 status)
 
 	val |= P(BLK, NA);
 
-	return val;
+	/*
+	 * the pebs_data_source table is only for loads
+	 * so override the mem_op to say STORE instead
+	 */
+	src.val = val;
+	src.mem_op = P(OP,STORE);
+
+	return src.val;
 }
 
 struct pebs_record_core {
@@ -822,7 +830,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 
 struct event_constraint intel_grt_pebs_event_constraints[] = {
 	/* Allow all events as PEBS with no flags */
-	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3),
 	INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
 	EVENT_CONSTRAINT_END
 };
@@ -2262,6 +2270,7 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_BRANCH_STACK |
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
+				x86_pmu.pebs_capable = ~0ULL;
 				pebs_qual = "-baseline";
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4f70fb6c2c1e..47fca6a7a8bc 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1097,6 +1097,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
 		reg->config = mask;
+
+		/*
+		 * The Arch LBR HW can retrieve the common branch types
+		 * from the LBR_INFO. It doesn't require the high overhead
+		 * SW disassemble.
+		 * Enable the branch type by default for the Arch LBR.
+		 */
+		reg->reg |= X86_BR_TYPE_SAVE;
 		return 0;
 	}
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index ce440011cc4e..1ef4f7861e2e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -841,6 +841,22 @@ int snb_pci2phy_map_init(int devid)
 	return 0;
 }
 
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * SNB IMC counters are 32-bit and are laid out back to back
+	 * in MMIO space. Therefore we must use a 32-bit accessor function
+	 * using readq() from uncore_mmio_read_counter() causes problems
+	 * because it is reading 64-bit at a time. This is okay for the
+	 * uncore_perf_event_update() function because it drops the upper
+	 * 32-bits but not okay for plain uncore_read_counter() as invoked
+	 * in uncore_pmu_event_start().
+	 */
+	return (u64)readl(box->io_addr + hwc->event_base);
+}
+
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
@@ -860,7 +876,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.disable_event	= snb_uncore_imc_disable_event,
 	.enable_event	= snb_uncore_imc_enable_event,
 	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= uncore_mmio_read_counter,
+	.read_counter	= snb_uncore_imc_read_counter,
 };
 
 static struct intel_uncore_type snb_uncore_imc = {

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 6 Aug 2022 21:10:36 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-06

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/592d8362bc2526bbb08cf7d258661691e957b5ea

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2022-08-06

   # HEAD: 99643bab36b642be10bf09cd3285c37c9e5b597f perf/core: Fix ';;' typo

Misc fixes to kprobes and the faddr2line script, plus a cleanup.

 Thanks,

	Ingo

------------------>
Chen Zhongjin (1):
      kprobes: Forbid probing on trampoline and BPF code areas

Josh Poimboeuf (2):
      scripts/faddr2line: Fix vmlinux detection on arm64
      scripts/faddr2line: Add CONFIG_DEBUG_INFO check

Masami Hiramatsu (Google) (1):
      x86/kprobes: Update kcb status flag after singlestepping

Slark Xiao (1):
      perf/core: Fix ';;' typo


 arch/x86/kernel/kprobes/core.c | 18 +++++++++++-------
 kernel/events/core.c           |  2 +-
 kernel/kprobes.c               |  3 ++-
 scripts/faddr2line             |  7 ++++++-
 4 files changed, 20 insertions(+), 10 deletions(-)

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 11 Jul 2021 15:26:50 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-07-11

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/936b664fb20895277453c02be4f3a94d6ce2b3c8

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-07-11

   # HEAD: d4ba0b06306a70c99a43f9d452886a86e2d3bd26 perf/x86/intel/uncore: Clean up error handling path of iio mapping

A fix and a hardware-enablement addition:

 - Robustify uncore_snbep's skx_iio_set_mapping()'s error cleanup
 - Add cstate event support for Intel ICELAKE_X and ICELAKE_D

 Thanks,

	Ingo

------------------>
Kan Liang (1):
      perf/x86/intel/uncore: Clean up error handling path of iio mapping

Zhang Rui (1):
      perf/x86/cstate: Add ICELAKE_X and ICELAKE_D support


 arch/x86/events/intel/cstate.c       | 23 +++++++++++++++++------
 arch/x86/events/intel/uncore_snbep.c |  6 ++++--
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 433399069e27..c6262b154c3a 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,7 +40,7 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT,GLM,CNL,TNT,ADL
+ *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
@@ -50,8 +50,8 @@
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
- *						TNT,RKL,ADL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
+ *						TGL,TNT,RKL,ADL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -61,7 +61,7 @@
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL,TGL,TNT,RKL,ADL
+ *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
@@ -72,8 +72,8 @@
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
- *						TNT,RKL,ADL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
+ *						TGL,TNT,RKL,ADL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -566,6 +566,14 @@ static const struct cstate_model icl_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model icx_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
+};
+
 static const struct cstate_model adl_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES) |
@@ -664,6 +672,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&icx_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&icx_cstates),
+
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&icl_cstates),
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 3a75a2c601c2..1f7bb4898a9d 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3789,11 +3789,11 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 	/* One more for NULL. */
 	attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL);
 	if (!attrs)
-		goto err;
+		goto clear_topology;
 
 	eas = kcalloc(uncore_max_dies(), sizeof(*eas), GFP_KERNEL);
 	if (!eas)
-		goto err;
+		goto clear_attrs;
 
 	for (die = 0; die < uncore_max_dies(); die++) {
 		sprintf(buf, "die%ld", die);
@@ -3814,7 +3814,9 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type)
 	for (; die >= 0; die--)
 		kfree(eas[die].attr.attr.name);
 	kfree(eas);
+clear_attrs:
 	kfree(attrs);
+clear_topology:
 	kfree(type->topology);
 clear_attr_update:
 	type->attr_update = NULL;

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 12 Jun 2021 14:48:15 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-06-12

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/191aaf6cc4a7db907520f18af3a90b260e7dd091

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-06-12

   # HEAD: a8383dfb2138742a1bb77b481ada047aededa2ba x86/nmi_watchdog: Fix old-style NMI watchdog regression on old Intel CPUs

Misc fixes:

 - Fix the NMI watchdog on ancient Intel CPUs

 - Remove a misguided, NMI-unsafe KASAN callback
   from the NMI-safe irq_work path used by perf.

 - Fix uncore events on Ice Lake servers.

 - Someone booted maxcpus=1 on an SNB-EP, and the
   uncore driver emitted warnings and was probably
   buggy. Fix it.

 - KCSAN found a genuine data race in the core perf
   code. Somewhat ironically the bug was introduced
   through a recent race fix. :-/ In our defense, the
   new race window was much more narrow. Fix it.

 Thanks,

	Ingo

------------------>
CodyYao-oc (1):
      x86/nmi_watchdog: Fix old-style NMI watchdog regression on old Intel CPUs

Kan Liang (2):
      perf/x86/intel/uncore: Fix a kernel WARNING triggered by maxcpus=1
      perf/x86/intel/uncore: Fix M2M event umask for Ice Lake server

Marco Elver (1):
      perf: Fix data race between pin_count increment/decrement

Peter Zijlstra (1):
      irq_work: Make irq_work_queue() NMI-safe again


 arch/x86/events/intel/uncore_snbep.c   | 9 ++++++---
 arch/x86/kernel/cpu/perfctr-watchdog.c | 4 ++--
 kernel/events/core.c                   | 2 ++
 kernel/irq_work.c                      | 3 ---
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 63f097289a84..3a75a2c601c2 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1406,6 +1406,8 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 						die_id = i;
 					else
 						die_id = topology_phys_to_logical_pkg(i);
+					if (die_id < 0)
+						die_id = -ENODEV;
 					map->pbus_to_dieid[bus] = die_id;
 					break;
 				}
@@ -1452,14 +1454,14 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 			i = -1;
 			if (reverse) {
 				for (bus = 255; bus >= 0; bus--) {
-					if (map->pbus_to_dieid[bus] >= 0)
+					if (map->pbus_to_dieid[bus] != -1)
 						i = map->pbus_to_dieid[bus];
 					else
 						map->pbus_to_dieid[bus] = i;
 				}
 			} else {
 				for (bus = 0; bus <= 255; bus++) {
-					if (map->pbus_to_dieid[bus] >= 0)
+					if (map->pbus_to_dieid[bus] != -1)
 						i = map->pbus_to_dieid[bus];
 					else
 						map->pbus_to_dieid[bus] = i;
@@ -5097,9 +5099,10 @@ static struct intel_uncore_type icx_uncore_m2m = {
 	.perf_ctr	= SNR_M2M_PCI_PMON_CTR0,
 	.event_ctl	= SNR_M2M_PCI_PMON_CTL0,
 	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.event_mask_ext	= SNR_M2M_PCI_PMON_UMASK_EXT,
 	.box_ctl	= SNR_M2M_PCI_PMON_BOX_CTL,
 	.ops		= &snr_m2m_uncore_pci_ops,
-	.format_group	= &skx_uncore_format_group,
+	.format_group	= &snr_m2m_uncore_format_group,
 };
 
 static struct attribute *icx_upi_uncore_formats_attr[] = {
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 3ef5868ac588..7aecb2fc3186 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -63,7 +63,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
-		fallthrough;
+		break;
 	case X86_VENDOR_ZHAOXIN:
 	case X86_VENDOR_CENTAUR:
 		return msr - MSR_ARCH_PERFMON_PERFCTR0;
@@ -96,7 +96,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
-		fallthrough;
+		break;
 	case X86_VENDOR_ZHAOXIN:
 	case X86_VENDOR_CENTAUR:
 		return msr - MSR_ARCH_PERFMON_EVENTSEL0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6fee4a7e88d7..fe88d6eea3c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4609,7 +4609,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
+		raw_spin_lock_irqsave(&ctx->lock, flags);
 		++ctx->pin_count;
+		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 
 		return ctx;
 	}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 23a7a0ba1388..db8c248ebc8c 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -70,9 +70,6 @@ bool irq_work_queue(struct irq_work *work)
 	if (!irq_work_claim(work))
 		return false;
 
-	/*record irq_work call stack in order to print it in KASAN reports*/
-	kasan_record_aux_stack(work);
-
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 	__irq_work_queue_local(work);

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 21 Mar 2021 11:56:36 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-03-21

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/1c74516c2da40ead2c22c4ac07c117c20f9c31ec

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2021-03-21

   # HEAD: 2dc0572f2cef87425147658698dce2600b799bd3 perf/x86/intel: Fix unchecked MSR access error caused by VLBR_EVENT

Boundary condition fixes for bugs unearthed by the perf fuzzer.

 Thanks,

	Ingo

------------------>
Kan Liang (2):
      perf/x86/intel: Fix a crash caused by zero PEBS status
      perf/x86/intel: Fix unchecked MSR access error caused by VLBR_EVENT


 arch/x86/events/intel/core.c | 3 +++
 arch/x86/events/intel/ds.c   | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7bbb5bb98d8c..37ce38403cb8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3659,6 +3659,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
+		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
+			return -EINVAL;
+
 		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ebae1826403..d32b302719fe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2010,7 +2010,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		 */
 		if (!pebs_status && cpuc->pebs_enabled &&
 			!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
-			pebs_status = cpuc->pebs_enabled;
+			pebs_status = p->status = cpuc->pebs_enabled;
 
 		bit = find_first_bit((unsigned long *)&pebs_status,
 					x86_pmu.max_pebs_events);

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 15 Aug 2020 13:21:33 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-08-15

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/7f5faaaa5909bb0b26dcd309424da14bdf0c7e93

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-08-15

   # HEAD: bcfd218b66790243ef303c1b35ce59f786ded225 perf/x86/rapl: Add support for Intel SPR platform

Misc fixes, an expansion of perf syscall access to CAP_PERFMON privileged tools,
plus a RAPL HW-enablement for Intel SPR platforms.

 Thanks,

	Ingo

------------------>
Alexey Budankov (1):
      perf/core: Take over CAP_SYS_PTRACE creds to CAP_PERFMON capability

Bhupesh Sharma (1):
      hw_breakpoint: Remove unused __register_perf_hw_breakpoint() declaration

Masami Hiramatsu (1):
      kprobes: Remove show_registers() function prototype

Zhang Rui (3):
      perf/x86/rapl: Fix missing psys sysfs attributes
      perf/x86/rapl: Support multiple RAPL unit quirks
      perf/x86/rapl: Add support for Intel SPR platform


 arch/x86/events/rapl.c        | 46 +++++++++++++++++++++++++++++++++----------
 include/linux/hw_breakpoint.h |  3 ---
 include/linux/kprobes.h       |  1 -
 kernel/events/core.c          |  4 ++--
 4 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 68b38820b10e..67b411f7e8c4 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -130,11 +130,17 @@ struct rapl_pmus {
 	struct rapl_pmu		*pmus[];
 };
 
+enum rapl_unit_quirk {
+	RAPL_UNIT_QUIRK_NONE,
+	RAPL_UNIT_QUIRK_INTEL_HSW,
+	RAPL_UNIT_QUIRK_INTEL_SPR,
+};
+
 struct rapl_model {
 	struct perf_msr *rapl_msrs;
 	unsigned long	events;
 	unsigned int	msr_power_unit;
-	bool		apply_quirk;
+	enum rapl_unit_quirk	unit_quirk;
 };
 
  /* 1/2^hw_unit Joule */
@@ -612,14 +618,28 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	for (i = 0; i < NR_RAPL_DOMAINS; i++)
 		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 
+	switch (rm->unit_quirk) {
 	/*
 	 * DRAM domain on HSW server and KNL has fixed energy unit which can be
 	 * different than the unit from power unit MSR. See
 	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
-	if (rm->apply_quirk)
+	case RAPL_UNIT_QUIRK_INTEL_HSW:
+		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		break;
+	/*
+	 * SPR shares the same DRAM domain energy unit as HSW, plus it
+	 * also has a fixed energy unit for Psys domain.
+	 */
+	case RAPL_UNIT_QUIRK_INTEL_SPR:
 		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		rapl_hw_unit[PERF_RAPL_PSYS] = 0;
+		break;
+	default:
+		break;
+	}
+
 
 	/*
 	 * Calculate the timer rate:
@@ -665,7 +685,7 @@ static const struct attribute_group *rapl_attr_update[] = {
 	&rapl_events_pkg_group,
 	&rapl_events_ram_group,
 	&rapl_events_gpu_group,
-	&rapl_events_gpu_group,
+	&rapl_events_psys_group,
 	NULL,
 };
 
@@ -698,7 +718,6 @@ static struct rapl_model model_snb = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -707,7 +726,6 @@ static struct rapl_model model_snbep = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -717,7 +735,6 @@ static struct rapl_model model_hsw = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -726,7 +743,7 @@ static struct rapl_model model_hsx = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= true,
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -734,7 +751,7 @@ static struct rapl_model model_hsx = {
 static struct rapl_model model_knl = {
 	.events		= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
-	.apply_quirk	= true,
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
@@ -745,14 +762,22 @@ static struct rapl_model model_skl = {
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
-	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
+};
+
+static struct rapl_model model_spr = {
+	.events		= BIT(PERF_RAPL_PP0) |
+			  BIT(PERF_RAPL_PKG) |
+			  BIT(PERF_RAPL_RAM) |
+			  BIT(PERF_RAPL_PSYS),
+	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_SPR,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
 	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_amd_fam17h = {
 	.events		= BIT(PERF_RAPL_PKG),
-	.apply_quirk	= false,
 	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
 	.rapl_msrs      = amd_rapl_msrs,
 };
@@ -787,6 +812,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
 	X86_MATCH_VENDOR_FAM(AMD,	0x17,		&model_amd_fam17h),
 	X86_MATCH_VENDOR_FAM(HYGON,	0x18,		&model_amd_fam17h),
 	{},
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index d7d4250cd1e4..78dd7035d1e5 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -72,7 +72,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    void *context);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
-extern int __register_perf_hw_breakpoint(struct perf_event *bp);
 extern void unregister_hw_breakpoint(struct perf_event *bp);
 extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
 
@@ -119,8 +118,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    void *context)		{ return NULL; }
 static inline int
 register_perf_hw_breakpoint(struct perf_event *bp)	{ return -ENOSYS; }
-static inline int
-__register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
 static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
 static inline void
 unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)	{ }
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 45b8cdc9fad7..9be1bff4f586 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
-extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 78e69e10482a..41e0cefb429b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11689,7 +11689,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_task;
 
 		/*
-		 * Reuse ptrace permission checks for now.
+		 * Preserve ptrace permission check for backwards compatibility.
 		 *
 		 * We must hold exec_update_mutex across this and any potential
 		 * perf_install_in_context() call for this new event to
@@ -11697,7 +11697,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * perf_event_exit_task() that could imply).
 		 */
 		err = -EACCES;
-		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+		if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
 			goto err_cred;
 	}
 

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 25 Apr 2020 11:19:18 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-25

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/e18588005d79853c2d4101f9416e7c1e8c9584d2

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf/urgent git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-2020-04-25

   # HEAD: f3bed55e850926614b9898fe982f66d2541a36a5 perf/core: fix parent pid/tid in task exit events

Two changes:

 - fix exit event records
 - extend x86 PMU driver enumeration to add Intel Jasper Lake CPU support.

 Thanks,

	Ingo

------------------>
Harry Pan (1):
      perf/x86/cstate: Add Jasper Lake CPU support

Ian Rogers (1):
      perf/core: fix parent pid/tid in task exit events


 arch/x86/events/intel/cstate.c |  1 +
 kernel/events/core.c           | 13 ++++++++++---
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e4aa20c0426f..442e1ed4acd4 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -643,6 +643,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&glm_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc9b98a9af9a..633b4ae72ed5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7491,10 +7491,17 @@ static void perf_event_task_output(struct perf_event *event,
 		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
-	task_event->event_id.ppid = perf_event_pid(event, current);
-
 	task_event->event_id.tid = perf_event_tid(event, task);
-	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	if (task_event->event_id.header.type == PERF_RECORD_EXIT) {
+		task_event->event_id.ppid = perf_event_pid(event,
+							task->real_parent);
+		task_event->event_id.ptid = perf_event_pid(event,
+							task->real_parent);
+	} else {  /* PERF_RECORD_FORK */
+		task_event->event_id.ppid = perf_event_pid(event, current);
+		task_event->event_id.ptid = perf_event_tid(event, current);
+	}
 
 	task_event->event_id.time = perf_event_clock(event);
 

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Tue, 24 Mar 2020 10:19:52 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/76ccd234269bd05debdbc12c96eafe62dd9a6180

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 564200ed8e71d91327d337e46bc778cee02da866 tools headers uapi: Update linux/in.h copy

A handful of tooling fixes all across the map, no kernel changes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools headers uapi: Update linux/in.h copy

Ian Rogers (1):
      perf parse-events: Fix reading of invalid memory in event parsing

Ilie Halip (1):
      perf python: Fix clang detection when using CC=clang-version

Masami Hiramatsu (3):
      tools: Let O= makes handle a relative path with -C option
      perf probe: Fix to delete multiple probe event
      perf probe: Do not depend on dwfl_module_addrsym()

disconnect3d (1):
      perf map: Fix off by one in strncpy() size argument


 tools/include/uapi/linux/in.h  |  2 ++
 tools/perf/Makefile            |  2 +-
 tools/perf/util/map.c          |  2 +-
 tools/perf/util/parse-events.c | 46 +++++++++++++++++++++---------------------
 tools/perf/util/probe-file.c   |  3 +++
 tools/perf/util/probe-finder.c | 11 +++++++---
 tools/perf/util/setup.py       | 10 +++++----
 tools/scripts/Makefile.include |  4 ++--
 8 files changed, 46 insertions(+), 34 deletions(-)

diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 1521073b6348..8533bf07450f 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -74,6 +74,8 @@ enum {
 #define IPPROTO_UDPLITE		IPPROTO_UDPLITE
   IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
 #define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_ETHERNET = 143,	/* Ethernet-within-IPv6 Encapsulation	*/
+#define IPPROTO_ETHERNET	IPPROTO_ETHERNET
   IPPROTO_RAW = 255,		/* Raw IP packets			*/
 #define IPPROTO_RAW		IPPROTO_RAW
   IPPROTO_MPTCP = 262,		/* Multipath TCP connection		*/
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7902a5681fc8..b8fc7d972be9 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,7 +35,7 @@ endif
 # Only pass canonical directory names as the output directory:
 #
 ifneq ($(O),)
-  FULL_O := $(shell readlink -f $(O) || echo $(O))
+  FULL_O := $(shell cd $(PWD); readlink -f $(O) || echo $(O))
 endif
 
 #
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 95428511300d..b342f744b1fc 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 11)) {
+	if (!strncmp(filename, "/system/lib/", 12)) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a14995835d85..a7dc0b096974 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1213,7 +1213,7 @@ static int config_attr(struct perf_event_attr *attr,
 static int get_config_terms(struct list_head *head_config,
 			    struct list_head *head_terms __maybe_unused)
 {
-#define ADD_CONFIG_TERM(__type)					\
+#define ADD_CONFIG_TERM(__type, __weak)				\
 	struct perf_evsel_config_term *__t;			\
 								\
 	__t = zalloc(sizeof(*__t));				\
@@ -1222,18 +1222,18 @@ static int get_config_terms(struct list_head *head_config,
 								\
 	INIT_LIST_HEAD(&__t->list);				\
 	__t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;	\
-	__t->weak	= term->weak;				\
+	__t->weak	= __weak;				\
 	list_add_tail(&__t->list, head_terms)
 
-#define ADD_CONFIG_TERM_VAL(__type, __name, __val)		\
+#define ADD_CONFIG_TERM_VAL(__type, __name, __val, __weak)	\
 do {								\
-	ADD_CONFIG_TERM(__type);				\
+	ADD_CONFIG_TERM(__type, __weak);			\
 	__t->val.__name = __val;				\
 } while (0)
 
-#define ADD_CONFIG_TERM_STR(__type, __val)			\
+#define ADD_CONFIG_TERM_STR(__type, __val, __weak)		\
 do {								\
-	ADD_CONFIG_TERM(__type);				\
+	ADD_CONFIG_TERM(__type, __weak);			\
 	__t->val.str = strdup(__val);				\
 	if (!__t->val.str) {					\
 		zfree(&__t);					\
@@ -1247,62 +1247,62 @@ do {								\
 	list_for_each_entry(term, head_config, list) {
 		switch (term->type_term) {
 		case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
-			ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num);
+			ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
-			ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num);
+			ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_TIME:
-			ADD_CONFIG_TERM_VAL(TIME, time, term->val.num);
+			ADD_CONFIG_TERM_VAL(TIME, time, term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
-			ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str);
+			ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
-			ADD_CONFIG_TERM_STR(BRANCH, term->val.str);
+			ADD_CONFIG_TERM_STR(BRANCH, term->val.str, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 			ADD_CONFIG_TERM_VAL(STACK_USER, stack_user,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_INHERIT:
 			ADD_CONFIG_TERM_VAL(INHERIT, inherit,
-					    term->val.num ? 1 : 0);
+					    term->val.num ? 1 : 0, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 			ADD_CONFIG_TERM_VAL(INHERIT, inherit,
-					    term->val.num ? 0 : 1);
+					    term->val.num ? 0 : 1, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 			ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite,
-					    term->val.num ? 1 : 0);
+					    term->val.num ? 1 : 0, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 			ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite,
-					    term->val.num ? 0 : 1);
+					    term->val.num ? 0 : 1, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
-			ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str);
+			ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_PERCORE:
 			ADD_CONFIG_TERM_VAL(PERCORE, percore,
-					    term->val.num ? true : false);
+					    term->val.num ? true : false, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 			ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output,
-					    term->val.num ? 1 : 0);
+					    term->val.num ? 1 : 0, term->weak);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
 			ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size,
-					    term->val.num);
+					    term->val.num, term->weak);
 			break;
 		default:
 			break;
@@ -1339,7 +1339,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 	}
 
 	if (bits)
-		ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits);
+		ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits, false);
 
 #undef ADD_CONFIG_TERM
 	return 0;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 0f5fda11675f..8c852948513e 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -206,6 +206,9 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
 		} else
 			ret = strlist__add(sl, tev.event);
 		clear_probe_trace_event(&tev);
+		/* Skip if there is same name multi-probe event in the list */
+		if (ret == -EEXIST)
+			ret = 0;
 		if (ret < 0)
 			break;
 	}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1c817add6ca4..e4cff49384f4 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -637,14 +637,19 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 		return -EINVAL;
 	}
 
-	/* Try to get actual symbol name from symtab */
-	symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+	if (dwarf_entrypc(sp_die, &eaddr) == 0) {
+		/* If the DIE has entrypc, use it. */
+		symbol = dwarf_diename(sp_die);
+	} else {
+		/* Try to get actual symbol name and address from symtab */
+		symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+		eaddr = sym.st_value;
+	}
 	if (!symbol) {
 		pr_warning("Failed to find symbol at 0x%lx\n",
 			   (unsigned long)paddr);
 		return -ENOENT;
 	}
-	eaddr = sym.st_value;
 
 	tp->offset = (unsigned long)(paddr - eaddr);
 	tp->address = (unsigned long)paddr;
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index aa344a163eaf..8a065a6f9713 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -2,11 +2,13 @@ from os import getenv
 from subprocess import Popen, PIPE
 from re import sub
 
+cc = getenv("CC")
+cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline()
+
 def clang_has_option(option):
-    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+    return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
 
-cc = getenv("CC")
-if cc == "clang":
+if cc_is_clang:
     from distutils.sysconfig import get_config_vars
     vars = get_config_vars()
     for var in ('CFLAGS', 'OPT'):
@@ -40,7 +42,7 @@ class install_lib(_install_lib):
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
-if cc != "clang":
+if not cc_is_clang:
     cflags += ['-Wno-cast-function-type' ]
 
 src_perf  = getenv('srctree') + '/tools/perf'
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ded7a950dc40..6d2f3a1b2249 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 ifneq ($(O),)
 ifeq ($(origin O), command line)
-	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
-	ABSOLUTE_O := $(shell cd $(O) ; pwd)
+	dummy := $(if $(shell cd $(PWD); test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+	ABSOLUTE_O := $(shell cd $(PWD); cd $(O) ; pwd)
 	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
 ifeq ($(objtree),)

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Mon, 2 Mar 2020 08:23:14 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/852fb4a72822b6c03bcf6cf1d51fb05b319d301e

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7977fed974d60a72733243cf54d7955cd6dccd91 Merge tag 'perf-urgent-for-mingo-5.6-20200228' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

No kernel side changes, the rest is tooling fixes plus two tooling 
cleanups that were committed late in the merge window alongside the perf 
annotate fixes, delayed by Arnaldo's European trip.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf arm-spe: Fix endless record after being terminated
      perf auxtrace: Add auxtrace_record__read_finish()

Arnaldo Carvalho de Melo (4):
      perf bpf: Remove bpf/ subdir from bpf.h headers used to build bpf events
      perf arch powerpc: Sync powerpc syscall.tbl with the kernel sources
      tools arch x86: Sync the msr-index.h copy with the kernel sources
      tools headers UAPI: Update tools's copy of kvm.h headers

He Zhe (1):
      perf probe: Check return value of strlist__add() for -ENOMEM

Ravi Bangoria (12):
      perf annotate/tui: Re-render title bar after switching back from script browser
      perf annotate: Fix --show-total-period for tui/stdio2
      perf annotate: Fix --show-nr-samples for tui/stdio2
      perf config: Introduce perf_config_u8()
      perf annotate: Make perf config effective
      perf annotate: Prefer cmdline option over default config
      perf annotate: Fix perf config option description
      perf config: Document missing config options
      perf annotate: Remove privsize from symbol__annotate() args
      perf annotate: Simplify disasm_line allocation and freeing code
      perf annotate: Align struct annotate_args
      perf annotate: Fix segfault with source toggle

Thomas Richter (1):
      perf test: Fix test trace+probe_vfs_getname.sh on s390

Wei Li (3):
      perf intel-pt: Fix endless record after being terminated
      perf intel-bts: Fix endless record after being terminated
      perf cs-etm: Fix endless record after being terminated


 tools/arch/x86/include/asm/msr-index.h             |   2 +
 tools/arch/x86/include/uapi/asm/kvm.h              |   1 +
 tools/perf/Documentation/perf-config.txt           |  74 +++++++-
 tools/perf/arch/arm/util/cs-etm.c                  |  18 +-
 tools/perf/arch/arm64/util/arm-spe.c               |  17 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |   2 +
 tools/perf/arch/x86/util/intel-bts.c               |  17 +-
 tools/perf/arch/x86/util/intel-pt.c                |  17 +-
 tools/perf/builtin-annotate.c                      |   4 +-
 tools/perf/builtin-probe.c                         |   6 +-
 tools/perf/builtin-report.c                        |   2 +-
 tools/perf/builtin-top.c                           |   4 +-
 tools/perf/include/bpf/pid_filter.h                |   2 +-
 tools/perf/include/bpf/stdio.h                     |   2 +-
 tools/perf/include/bpf/unistd.h                    |   2 +-
 tools/perf/tests/shell/lib/probe_vfs_getname.sh    |   2 +-
 tools/perf/ui/browsers/annotate.c                  |  19 +-
 tools/perf/ui/gtk/annotate.c                       |   2 +-
 tools/perf/util/annotate.c                         | 194 ++++++++-------------
 tools/perf/util/annotate.h                         |   9 +-
 tools/perf/util/auxtrace.c                         |  22 ++-
 tools/perf/util/auxtrace.h                         |   6 +
 tools/perf/util/config.c                           |  12 ++
 tools/perf/util/config.h                           |   1 +
 tools/perf/util/probe-file.c                       |  28 ++-
 25 files changed, 251 insertions(+), 214 deletions(-)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index ebe1685e92dd..d5e517d1c3dd 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -512,6 +512,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 503d3f42da16..3f3f780c8c65 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -390,6 +390,7 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index c4dd23c4b478..8ead55593984 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -239,7 +239,6 @@ buildid.*::
 		set buildid.dir to /dev/null. The default is $HOME/.debug
 
 annotate.*::
-	These options work only for TUI.
 	These are in control of addresses, jump function, source code
 	in lines of assembly code from a specific program.
 
@@ -269,6 +268,8 @@ annotate.*::
 		│        mov    (%rdi),%rdx
 		│              return n;
 
+		This option works with tui, stdio2 browsers.
+
         annotate.use_offset::
 		Basing on a first address of a loaded function, offset can be used.
 		Instead of using original addresses of assembly code,
@@ -287,6 +288,8 @@ annotate.*::
 
 		             368:│  mov    0x8(%r14),%rdi
 
+		This option works with tui, stdio2 browsers.
+
 	annotate.jump_arrows::
 		There can be jump instruction among assembly code.
 		Depending on a boolean value of jump_arrows,
@@ -306,6 +309,8 @@ annotate.*::
 		│1330:   mov    %r15,%r10
 		│1333:   cmp    %r15,%r14
 
+		This option works with tui browser.
+
         annotate.show_linenr::
 		When showing source code if this option is 'true',
 		line numbers are printed as below.
@@ -325,6 +330,8 @@ annotate.*::
 		│                     array++;
 		│             }
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_nr_jumps::
 		Let's see a part of assembly code.
 
@@ -335,6 +342,8 @@ annotate.*::
 
 		│1 1382:   movb   $0x1,-0x270(%rbp)
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_total_period::
 		To compare two records on an instruction base, with this option
 		provided, display total number of samples that belong to a line
@@ -348,11 +357,30 @@ annotate.*::
 
 		99.93 │      mov    %eax,%eax
 
+		This option works with tui, stdio2, stdio browsers.
+
+	annotate.show_nr_samples::
+		By default perf annotate shows percentage of samples. This option
+		can be used to print absolute number of samples. Ex, when set as
+		false:
+
+		Percent│
+		 74.03 │      mov    %fs:0x28,%rax
+
+		When set as true:
+
+		Samples│
+		     6 │      mov    %fs:0x28,%rax
+
+		This option works with tui, stdio2, stdio browsers.
+
 	annotate.offset_level::
 		Default is '1', meaning just jump targets will have offsets show right beside
 		the instruction. When set to '2' 'call' instructions will also have its offsets
 		shown, 3 or higher will show offsets for all instructions.
 
+		This option works with tui, stdio2 browsers.
+
 hist.*::
 	hist.percentage::
 		This option control the way to calculate overhead of filtered entries -
@@ -490,6 +518,12 @@ top.*::
 		column by default.
 		The default is 'true'.
 
+	top.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'top' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf top' to actually use it,
+		the command line option -g must be specified.
+
 man.*::
 	man.viewer::
 		This option can assign a tool to view manual pages when 'help'
@@ -517,6 +551,16 @@ record.*::
 		But if this option is 'no-cache', it will not update the build-id cache.
 		'skip' skips post-processing and does not update the cache.
 
+	record.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'record' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf record' to actually use it,
+		the command line option -g must be specified.
+
+	record.aio::
+		Use 'n' control blocks in asynchronous (Posix AIO) trace writing
+		mode ('n' default: 1, max: 4).
+
 diff.*::
 	diff.order::
 		This option sets the number of columns to sort the result.
@@ -566,6 +610,11 @@ trace.*::
 		"libbeauty", the default, to use the same argument beautifiers used in the
 		strace-like sys_enter+sys_exit lines.
 
+ftrace.*::
+	ftrace.tracer::
+		Can be used to select the default tracer. Possible values are
+		'function' and 'function_graph'.
+
 llvm.*::
 	llvm.clang-path::
 		Path to clang. If omit, search it from $PATH.
@@ -610,6 +659,29 @@ scripts.*::
 	The script gets the same options passed as a full perf script,
 	in particular -i perfdata file, --cpu, --tid
 
+convert.*::
+
+	convert.queue-size::
+		Limit the size of ordered_events queue, so we could control
+		allocation size of perf data files without proper finished
+		round events.
+
+intel-pt.*::
+
+	intel-pt.cache-divisor::
+
+	intel-pt.mispred-all::
+		If set, Intel PT decoder will set the mispred flag on all
+		branches.
+
+auxtrace.*::
+
+	auxtrace.dumpdir::
+		s390 only. The directory to save the auxiliary trace buffer
+		can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
+		If the directory does not exist or has the wrong file type,
+		the current directory is used.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2898cfdf8fe1..941f814820b8 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 	free(ptr);
 }
 
-static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct cs_etm_recording *ptr =
-			container_of(itr, struct cs_etm_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist,
-							     evsel, idx);
-	}
-
-	return -EINVAL;
-}
-
 struct auxtrace_record *cs_etm_record_init(int *err)
 {
 	struct perf_pmu *cs_etm_pmu;
@@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	}
 
 	ptr->cs_etm_pmu			= cs_etm_pmu;
+	ptr->itr.pmu			= cs_etm_pmu;
 	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
 	ptr->itr.recording_options	= cs_etm_recording_options;
 	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
@@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
 	ptr->itr.reference		= cs_etm_reference;
 	ptr->itr.free			= cs_etm_recording_free;
-	ptr->itr.read_finish		= cs_etm_read_finish;
+	ptr->itr.read_finish		= auxtrace_record__read_finish;
 
 	*err = 0;
 	return &ptr->itr;
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index eba6541ec0f1..8d6821d9c3f6 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
 	free(sper);
 }
 
-static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct arm_spe_recording *sper =
-			container_of(itr, struct arm_spe_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(sper->evlist, evsel) {
-		if (evsel->core.attr.type == sper->arm_spe_pmu->type)
-			return perf_evlist__enable_event_idx(sper->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *arm_spe_recording_init(int *err,
 					       struct perf_pmu *arm_spe_pmu)
 {
@@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	}
 
 	sper->arm_spe_pmu = arm_spe_pmu;
+	sper->itr.pmu = arm_spe_pmu;
 	sper->itr.recording_options = arm_spe_recording_options;
 	sper->itr.info_priv_size = arm_spe_info_priv_size;
 	sper->itr.info_fill = arm_spe_info_fill;
 	sper->itr.free = arm_spe_recording_free;
 	sper->itr.reference = arm_spe_reference;
-	sper->itr.read_finish = arm_spe_read_finish;
+	sper->itr.read_finish = auxtrace_record__read_finish;
 	sper->itr.alignment = 0;
 
 	*err = 0;
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 43f736ed47f2..35b61bfc1b1a 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -517,3 +517,5 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
+437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 27d9e214d068..26cee1052179 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -413,20 +413,6 @@ static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
 	return err;
 }
 
-static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_bts_recording *btsr =
-			container_of(itr, struct intel_bts_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(btsr->evlist, evsel) {
-		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
-			return perf_evlist__enable_event_idx(btsr->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_bts_recording_init(int *err)
 {
 	struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
@@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	}
 
 	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.pmu = intel_bts_pmu;
 	btsr->itr.recording_options = intel_bts_recording_options;
 	btsr->itr.info_priv_size = intel_bts_info_priv_size;
 	btsr->itr.info_fill = intel_bts_info_fill;
@@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	btsr->itr.find_snapshot = intel_bts_find_snapshot;
 	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
 	btsr->itr.reference = intel_bts_reference;
-	btsr->itr.read_finish = intel_bts_read_finish;
+	btsr->itr.read_finish = auxtrace_record__read_finish;
 	btsr->itr.alignment = sizeof(struct branch);
 	return &btsr->itr;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 20df442fdf36..7eea4fd7ce58 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
-static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_pt_recording *ptr =
-			container_of(itr, struct intel_pt_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->intel_pt_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
-							     idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
@@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	}
 
 	ptr->intel_pt_pmu = intel_pt_pmu;
+	ptr->itr.pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
 	ptr->itr.info_fill = intel_pt_info_fill;
@@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	ptr->itr.find_snapshot = intel_pt_find_snapshot;
 	ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
 	ptr->itr.reference = intel_pt_reference;
-	ptr->itr.read_finish = intel_pt_read_finish;
+	ptr->itr.read_finish = auxtrace_record__read_finish;
 	/*
 	 * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
 	 * should give at least 1 PSB per sample.
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ff61795a4d13..6c0a0412502e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		return ret;
 
+	annotation_config__init(&annotate.opts);
+
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
 		/*
@@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		goto out_delete;
 
-	annotation_config__init();
-
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 26bc5923e6b5..70548df2abb9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret = probe_file__del_strlist(kfd, klist);
 		if (ret < 0)
 			goto error;
-	}
+	} else if (ret == -ENOMEM)
+		goto error;
 
 	ret2 = probe_file__get_events(ufd, filter, ulist);
 	if (ret2 == 0) {
@@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret2 = probe_file__del_strlist(ufd, ulist);
 		if (ret2 < 0)
 			goto error;
-	}
+	} else if (ret2 == -ENOMEM)
+		goto error;
 
 	if (ret == -ENOENT && ret2 == -ENOENT)
 		pr_warning("\"%s\" does not hit any event.\n", str);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9483b3f0cae3..72a12b69f120 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1507,7 +1507,7 @@ int cmd_report(int argc, const char **argv)
 			symbol_conf.priv_size += sizeof(u32);
 			symbol_conf.sort_by_name = true;
 		}
-		annotation_config__init();
+		annotation_config__init(&report.annotation_opts);
 	}
 
 	if (symbol__init(&session->header.env) < 0)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8affcab75604..f6dd1a63f159 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -143,7 +143,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL);
+	err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
 	if (err == 0) {
 		top->sym_filter_entry = he;
 	} else {
@@ -1683,7 +1683,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
-	annotation_config__init();
+	annotation_config__init(&top.annotation_opts);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	status = symbol__init(NULL);
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 607189a315b2..6e61c4bdf548 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
 #ifndef _PERF_BPF_PID_FILTER_
 #define _PERF_BPF_PID_FILTER_
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 #define pid_filter(name) pid_map(name, bool)
 
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 7ca6fa5463ee..316af5b2ff35 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 struct bpf_map SEC("maps") __bpf_stdout__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index d1a35b6c649d..ca7877f9a976 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
 
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 7cb99b433888..c2cc42daf924 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -14,7 +14,7 @@ add_probe_vfs_getname() {
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
 		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
 	fi
 }
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index badbddbb30f8..9023267e5643 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -754,10 +754,9 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"?             Search string backwards\n");
 			continue;
 		case 'r':
-			{
-				script_browse(NULL, NULL);
-				continue;
-			}
+			script_browse(NULL, NULL);
+			annotate_browser__show(&browser->b, title, help);
+			continue;
 		case 'k':
 			notes->options->show_linenr = !notes->options->show_linenr;
 			break;
@@ -834,13 +833,13 @@ static int annotate_browser__run(struct annotate_browser *browser,
 			map_symbol__annotation_dump(ms, evsel, browser->opts);
 			continue;
 		case 't':
-			if (notes->options->show_total_period) {
-				notes->options->show_total_period = false;
-				notes->options->show_nr_samples = true;
-			} else if (notes->options->show_nr_samples)
-				notes->options->show_nr_samples = false;
+			if (symbol_conf.show_total_period) {
+				symbol_conf.show_total_period = false;
+				symbol_conf.show_nr_samples = true;
+			} else if (symbol_conf.show_nr_samples)
+				symbol_conf.show_nr_samples = false;
 			else
-				notes->options->show_total_period = true;
+				symbol_conf.show_total_period = true;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'c':
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 22cc240f7371..35f9641bf670 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -174,7 +174,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (ms->map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL);
+	err = symbol__annotate(ms, evsel, &annotation__default_options, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ca73fb74ad03..0ea95be84b3b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1143,93 +1143,70 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 }
 
 struct annotate_args {
-	size_t			 privsize;
-	struct arch		*arch;
-	struct map_symbol	 ms;
-	struct evsel	*evsel;
+	struct arch		  *arch;
+	struct map_symbol	  ms;
+	struct evsel		  *evsel;
 	struct annotation_options *options;
-	s64			 offset;
-	char			*line;
-	int			 line_nr;
+	s64			  offset;
+	char			  *line;
+	int			  line_nr;
 };
 
-static void annotation_line__delete(struct annotation_line *al)
+static void annotation_line__init(struct annotation_line *al,
+				  struct annotate_args *args,
+				  int nr)
 {
-	void *ptr = (void *) al - al->privsize;
+	al->offset = args->offset;
+	al->line = strdup(args->line);
+	al->line_nr = args->line_nr;
+	al->data_nr = nr;
+}
 
+static void annotation_line__exit(struct annotation_line *al)
+{
 	free_srcline(al->path);
 	zfree(&al->line);
-	free(ptr);
 }
 
-/*
- * Allocating the annotation line data with following
- * structure:
- *
- *    --------------------------------------
- *    private space | struct annotation_line
- *    --------------------------------------
- *
- * Size of the private space is stored in 'struct annotation_line'.
- *
- */
-static struct annotation_line *
-annotation_line__new(struct annotate_args *args, size_t privsize)
+static size_t disasm_line_size(int nr)
 {
 	struct annotation_line *al;
-	struct evsel *evsel = args->evsel;
-	size_t size = privsize + sizeof(*al);
-	int nr = 1;
-
-	if (perf_evsel__is_group_event(evsel))
-		nr = evsel->core.nr_members;
 
-	size += sizeof(al->data[0]) * nr;
-
-	al = zalloc(size);
-	if (al) {
-		al = (void *) al + privsize;
-		al->privsize   = privsize;
-		al->offset     = args->offset;
-		al->line       = strdup(args->line);
-		al->line_nr    = args->line_nr;
-		al->data_nr    = nr;
-	}
-
-	return al;
+	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
 }
 
 /*
  * Allocating the disasm annotation line data with
  * following structure:
  *
- *    ------------------------------------------------------------
- *    privsize space | struct disasm_line | struct annotation_line
- *    ------------------------------------------------------------
+ *    -------------------------------------------
+ *    struct disasm_line | struct annotation_line
+ *    -------------------------------------------
  *
  * We have 'struct annotation_line' member as last member
  * of 'struct disasm_line' to have an easy access.
- *
  */
 static struct disasm_line *disasm_line__new(struct annotate_args *args)
 {
 	struct disasm_line *dl = NULL;
-	struct annotation_line *al;
-	size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+	int nr = 1;
 
-	al = annotation_line__new(args, privsize);
-	if (al != NULL) {
-		dl = disasm_line(al);
+	if (perf_evsel__is_group_event(args->evsel))
+		nr = args->evsel->core.nr_members;
 
-		if (dl->al.line == NULL)
-			goto out_delete;
+	dl = zalloc(disasm_line_size(nr));
+	if (!dl)
+		return NULL;
 
-		if (args->offset != -1) {
-			if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
-				goto out_free_line;
+	annotation_line__init(&dl->al, args, nr);
+	if (dl->al.line == NULL)
+		goto out_delete;
 
-			disasm_line__init_ins(dl, args->arch, &args->ms);
-		}
+	if (args->offset != -1) {
+		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+			goto out_free_line;
+
+		disasm_line__init_ins(dl, args->arch, &args->ms);
 	}
 
 	return dl;
@@ -1248,7 +1225,8 @@ void disasm_line__free(struct disasm_line *dl)
 	else
 		ins__delete(&dl->ops);
 	zfree(&dl->ins.name);
-	annotation_line__delete(&dl->al);
+	annotation_line__exit(&dl->al);
+	free(dl);
 }
 
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
@@ -2149,13 +2127,12 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize,
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 		     struct annotation_options *options, struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
-		.privsize	= privsize,
 		.evsel		= evsel,
 		.options	= options,
 	};
@@ -2644,6 +2621,8 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
 	struct annotation_line *al;
 
 	notes->max_line_len = 0;
+	notes->nr_entries = 0;
+	notes->nr_asm_entries = 0;
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		size_t line_len = strlen(al->line);
@@ -2790,7 +2769,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
 	struct symbol *sym = ms->sym;
 	struct rb_root source_line = RB_ROOT;
 
-	if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0)
+	if (symbol__annotate(ms, evsel, opts, NULL) < 0)
 		return -1;
 
 	symbol__calc_percent(sym, evsel);
@@ -2915,9 +2894,9 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			percent = annotation_data__percent(&al->data[i], percent_type);
 
 			obj__set_percent_color(obj, percent, current_entry);
-			if (notes->options->show_total_period) {
+			if (symbol_conf.show_total_period) {
 				obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
-			} else if (notes->options->show_nr_samples) {
+			} else if (symbol_conf.show_nr_samples) {
 				obj__printf(obj, "%6" PRIu64 " ",
 						   al->data[i].he.nr_samples);
 			} else {
@@ -2931,8 +2910,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			obj__printf(obj, "%-*s", pcnt_width, " ");
 		else {
 			obj__printf(obj, "%-*s", pcnt_width,
-					   notes->options->show_total_period ? "Period" :
-					   notes->options->show_nr_samples ? "Samples" : "Percent");
+					   symbol_conf.show_total_period ? "Period" :
+					   symbol_conf.show_nr_samples ? "Samples" : "Percent");
 		}
 	}
 
@@ -3070,7 +3049,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
-	err = symbol__annotate(ms, evsel, 0, options, parch);
+	err = symbol__annotate(ms, evsel, options, parch);
 	if (err)
 		goto out_free_offsets;
 
@@ -3094,69 +3073,46 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	return err;
 }
 
-#define ANNOTATION__CFG(n) \
-	{ .name = #n, .value = &annotation__default_options.n, }
-
-/*
- * Keep the entries sorted, they are bsearch'ed
- */
-static struct annotation_config {
-	const char *name;
-	void *value;
-} annotation__configs[] = {
-	ANNOTATION__CFG(hide_src_code),
-	ANNOTATION__CFG(jump_arrows),
-	ANNOTATION__CFG(offset_level),
-	ANNOTATION__CFG(show_linenr),
-	ANNOTATION__CFG(show_nr_jumps),
-	ANNOTATION__CFG(show_nr_samples),
-	ANNOTATION__CFG(show_total_period),
-	ANNOTATION__CFG(use_offset),
-};
-
-#undef ANNOTATION__CFG
-
-static int annotation_config__cmp(const void *name, const void *cfgp)
-{
-	const struct annotation_config *cfg = cfgp;
-
-	return strcmp(name, cfg->name);
-}
-
-static int annotation__config(const char *var, const char *value,
-			    void *data __maybe_unused)
+static int annotation__config(const char *var, const char *value, void *data)
 {
-	struct annotation_config *cfg;
-	const char *name;
+	struct annotation_options *opt = data;
 
 	if (!strstarts(var, "annotate."))
 		return 0;
 
-	name = var + 9;
-	cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs),
-		      sizeof(struct annotation_config), annotation_config__cmp);
-
-	if (cfg == NULL)
-		pr_debug("%s variable unknown, ignoring...", var);
-	else if (strcmp(var, "annotate.offset_level") == 0) {
-		perf_config_int(cfg->value, name, value);
-
-		if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
-			*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
-		else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
-			*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+	if (!strcmp(var, "annotate.offset_level")) {
+		perf_config_u8(&opt->offset_level, "offset_level", value);
+
+		if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+			opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
+		else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
+			opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else if (!strcmp(var, "annotate.hide_src_code")) {
+		opt->hide_src_code = perf_config_bool("hide_src_code", value);
+	} else if (!strcmp(var, "annotate.jump_arrows")) {
+		opt->jump_arrows = perf_config_bool("jump_arrows", value);
+	} else if (!strcmp(var, "annotate.show_linenr")) {
+		opt->show_linenr = perf_config_bool("show_linenr", value);
+	} else if (!strcmp(var, "annotate.show_nr_jumps")) {
+		opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value);
+	} else if (!strcmp(var, "annotate.show_nr_samples")) {
+		symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples",
+								value);
+	} else if (!strcmp(var, "annotate.show_total_period")) {
+		symbol_conf.show_total_period = perf_config_bool("show_total_period",
+								value);
+	} else if (!strcmp(var, "annotate.use_offset")) {
+		opt->use_offset = perf_config_bool("use_offset", value);
 	} else {
-		*(bool *)cfg->value = perf_config_bool(name, value);
+		pr_debug("%s variable unknown, ignoring...", var);
 	}
+
 	return 0;
 }
 
-void annotation_config__init(void)
+void annotation_config__init(struct annotation_options *opt)
 {
-	perf_config(annotation__config, NULL);
-
-	annotation__default_options.show_total_period = symbol_conf.show_total_period;
-	annotation__default_options.show_nr_samples   = symbol_conf.show_nr_samples;
+	perf_config(annotation__config, opt);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 455403e8fede..001258601a37 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -83,8 +83,6 @@ struct annotation_options {
 	     full_path,
 	     show_linenr,
 	     show_nr_jumps,
-	     show_nr_samples,
-	     show_total_period,
 	     show_minmax_cycle,
 	     show_asm_raw,
 	     annotate_src;
@@ -141,7 +139,6 @@ struct annotation_line {
 	u64			 cycles;
 	u64			 cycles_max;
 	u64			 cycles_min;
-	size_t			 privsize;
 	char			*path;
 	u32			 idx;
 	int			 idx_asm;
@@ -309,7 +306,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
 
 static inline int annotation__pcnt_width(struct annotation *notes)
 {
-	return (notes->options->show_total_period ? 12 : 7) * notes->nr_events;
+	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
 }
 
 static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
@@ -352,7 +349,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct map_symbol *ms,
-		     struct evsel *evsel, size_t privsize,
+		     struct evsel *evsel,
 		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct map_symbol *ms,
@@ -413,7 +410,7 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 }
 #endif
 
-void annotation_config__init(void);
+void annotation_config__init(struct annotation_options *opt);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index eb087e7df6f4..3571ce72ca28 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -629,8 +629,10 @@ int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct evlist *evlist,
 			     struct record_opts *opts)
 {
-	if (itr)
+	if (itr) {
+		itr->evlist = evlist;
 		return itr->recording_options(itr, evlist, opts);
+	}
 	return 0;
 }
 
@@ -664,6 +666,24 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 	return -EINVAL;
 }
 
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct evsel *evsel;
+
+	if (!itr->evlist || !itr->pmu)
+		return -EINVAL;
+
+	evlist__for_each_entry(itr->evlist, evsel) {
+		if (evsel->core.attr.type == itr->pmu->type) {
+			if (evsel->disabled)
+				return 0;
+			return perf_evlist__enable_event_idx(itr->evlist, evsel,
+							     idx);
+		}
+	}
+	return -EINVAL;
+}
+
 /*
  * Event record size is 16-bit which results in a maximum size of about 64KiB.
  * Allow about 4KiB for the rest of the sample record, to give a maximum
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 749d72cd9c7b..e58ef160b599 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -29,6 +29,7 @@ struct record_opts;
 struct perf_record_auxtrace_error;
 struct perf_record_auxtrace_info;
 struct events_stats;
+struct perf_pmu;
 
 enum auxtrace_error_type {
        PERF_AUXTRACE_ERROR_ITRACE  = 1,
@@ -322,6 +323,8 @@ struct auxtrace_mmap_params {
  * @read_finish: called after reading from an auxtrace mmap
  * @alignment: alignment (if any) for AUX area data
  * @default_aux_sample_size: default sample size for --aux sample option
+ * @pmu: associated pmu
+ * @evlist: selected events list
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
@@ -346,6 +349,8 @@ struct auxtrace_record {
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
 	unsigned int alignment;
 	unsigned int default_aux_sample_size;
+	struct perf_pmu *pmu;
+	struct evlist *evlist;
 };
 
 /**
@@ -537,6 +542,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
 				   struct auxtrace_mmap *mm,
 				   unsigned char *data, u64 *head, u64 *old);
 u64 auxtrace_record__reference(struct auxtrace_record *itr);
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx);
 
 int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
 				   off_t file_offset);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0bc9c4d7fdc5..ef38eba56ed0 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -374,6 +374,18 @@ int perf_config_int(int *dest, const char *name, const char *value)
 	return 0;
 }
 
+int perf_config_u8(u8 *dest, const char *name, const char *value)
+{
+	long ret = 0;
+
+	if (!perf_parse_long(value, &ret)) {
+		bad_config(name);
+		return -1;
+	}
+	*dest = ret;
+	return 0;
+}
+
 static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
 {
 	int ret;
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index bd0a5897c76a..c10b66dde2f3 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -29,6 +29,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 int perf_default_config(const char *, const char *, void *);
 int perf_config(config_fn_t fn, void *);
 int perf_config_int(int *dest, const char *, const char *);
+int perf_config_u8(u8 *dest, const char *name, const char *value);
 int perf_config_u64(u64 *dest, const char *, const char *);
 int perf_config_bool(const char *, const char *);
 int config_error_nonbool(const char *);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 5003ba403345..0f5fda11675f 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -301,10 +301,15 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
-			strlist__add(plist, ent->s);
+			ret = strlist__add(plist, ent->s);
+			if (ret == -ENOMEM) {
+				pr_err("strlist__add failed with -ENOMEM\n");
+				goto out;
+			}
 			ret = 0;
 		}
 	}
+out:
 	strlist__delete(namelist);
 
 	return ret;
@@ -511,7 +516,11 @@ static int probe_cache__load(struct probe_cache *pcache)
 				ret = -EINVAL;
 				goto out;
 			}
-			strlist__add(entry->tevlist, buf);
+			ret = strlist__add(entry->tevlist, buf);
+			if (ret == -ENOMEM) {
+				pr_err("strlist__add failed with -ENOMEM\n");
+				goto out;
+			}
 		}
 	}
 out:
@@ -672,7 +681,12 @@ int probe_cache__add_entry(struct probe_cache *pcache,
 		command = synthesize_probe_trace_command(&tevs[i]);
 		if (!command)
 			goto out_err;
-		strlist__add(entry->tevlist, command);
+		ret = strlist__add(entry->tevlist, command);
+		if (ret == -ENOMEM) {
+			pr_err("strlist__add failed with -ENOMEM\n");
+			goto out_err;
+		}
+
 		free(command);
 	}
 	list_add_tail(&entry->node, &pcache->entries);
@@ -853,9 +867,15 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 			break;
 		}
 
-		strlist__add(entry->tevlist, buf);
+		ret = strlist__add(entry->tevlist, buf);
+
 		free(buf);
 		entry = NULL;
+
+		if (ret == -ENOMEM) {
+			pr_err("strlist__add failed with -ENOMEM\n");
+			break;
+		}
 	}
 	if (entry) {
 		list_del_init(&entry->node);

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 15 Feb 2020 09:53:16 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/da99f9355b53ebc565747d0072ff038f3d9fa875

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: dfb9b69e3b84791e4c6b954ac3cc0c4a545484f2 Merge tag 'perf-urgent-for-mingo-5.6-20200214' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Contains the following fixes and HW enablement patches:

 - Tooling fixes, most of which are tooling header synchronization with v5.6 changes

 - Fix kprobes fallout on ARM

 - Add Intel Elkhart Lake support and extend Tremont support, these are 
   relatively simple and should only affect those models

 - Fix the AMD family 17h generic event table

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (15):
      tools include UAPI: Sync x86's syscalls_64.tbl, generic unistd.h and fcntl.h to pick up openat2 and pidfd_getfd
      tools headers UAPI: Sync copy of arm64's asm/unistd.h with the kernel sources
      tools headers UAPI: Sync prctl.h with the kernel sources
      perf beauty prctl: Export the 'options' strarray
      perf trace: Resolve prctl's 'option' arg strings to numbers
      tools headers UAPI: Sync sched.h with the kernel
      tools headers uapi: Sync linux/fscrypt.h with the kernel sources
      tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
      tools headers UAPI: Sync asm-generic/mman-common.h with the kernel
      tools include UAPI: Sync sound/asound.h copy
      tools headers x86: Sync disabled-features.h
      tools arch x86: Sync asm/cpufeatures.h with the kernel sources
      tools headers kvm: Sync kvm headers with the kernel sources
      tools headers kvm: Sync linux/kvm.h with the kernel sources
      perf llvm: Fix script used to obtain kernel make directives to work with new kbuild

Jiri Olsa (4):
      perf maps: Mark module DSOs with kernel type
      perf maps: Mark ksymbol DSOs with kernel type
      perf maps: Fix map__clone() for struct kmap
      perf maps: Move kmap::kmaps setup to maps__insert()

John Garry (1):
      perf tools: Add arm64 version of get_cpuid()

Kan Liang (4):
      perf/x86/intel: Add Elkhart Lake support
      perf/x86/cstate: Add Tremont support
      perf/x86/msr: Add Tremont support
      perf/x86/intel: Fix inaccurate period in context switch for auto-reload

Kim Phillips (4):
      perf stat: Don't report a null stalled cycles per insn metric
      perf symbols: Update the list of kernel idle symbols
      perf symbols: Convert symbol__is_idle() to use strlist
      perf/x86/amd: Add missing L2 misses event spec to AMD Family 17h's event map

Peter Zijlstra (2):
      arm/ftrace: Fix BE text poking
      arm/patch: Fix !MMU compile


 arch/arm/kernel/ftrace.c                          |   7 +-
 arch/arm/kernel/patch.c                           |  19 ++-
 arch/x86/events/amd/core.c                        |   1 +
 arch/x86/events/intel/core.c                      |   1 +
 arch/x86/events/intel/cstate.c                    |  22 +--
 arch/x86/events/intel/ds.c                        |   2 +
 arch/x86/events/msr.c                             |   3 +-
 tools/arch/arm64/include/uapi/asm/kvm.h           |  12 +-
 tools/arch/arm64/include/uapi/asm/unistd.h        |   1 +
 tools/arch/x86/include/asm/cpufeatures.h          |   2 +
 tools/arch/x86/include/asm/disabled-features.h    |   8 +-
 tools/include/uapi/asm-generic/mman-common.h      |   2 +
 tools/include/uapi/asm-generic/unistd.h           |   7 +-
 tools/include/uapi/drm/i915_drm.h                 |  32 +++++
 tools/include/uapi/linux/fcntl.h                  |   2 +-
 tools/include/uapi/linux/fscrypt.h                |  14 +-
 tools/include/uapi/linux/kvm.h                    |   5 +
 tools/include/uapi/linux/openat2.h                |  39 ++++++
 tools/include/uapi/linux/prctl.h                  |   4 +
 tools/include/uapi/linux/sched.h                  |   6 +
 tools/include/uapi/sound/asound.h                 | 155 ++++++++++++++++++----
 tools/perf/arch/arm64/util/header.c               |  63 ++++++---
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl |   2 +
 tools/perf/builtin-trace.c                        |   4 +-
 tools/perf/check-headers.sh                       |   1 +
 tools/perf/trace/beauty/beauty.h                  |   2 +
 tools/perf/trace/beauty/prctl.c                   |   3 +-
 tools/perf/util/llvm-utils.c                      |   1 +
 tools/perf/util/machine.c                         |  26 ++--
 tools/perf/util/map.c                             |  17 ++-
 tools/perf/util/stat-shadow.c                     |   6 -
 tools/perf/util/symbol.c                          |  17 ++-
 32 files changed, 383 insertions(+), 103 deletions(-)
 create mode 100644 tools/include/uapi/linux/openat2.h

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 2a5ff69c28e6..10499d44964a 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -78,13 +78,10 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old,
 {
 	unsigned long replaced;
 
-	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
 		old = __opcode_to_mem_thumb32(old);
-		new = __opcode_to_mem_thumb32(new);
-	} else {
+	else
 		old = __opcode_to_mem_arm(old);
-		new = __opcode_to_mem_arm(new);
-	}
 
 	if (validate) {
 		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index d0a05a3bdb96..e9e828b6bb30 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,10 +16,10 @@ struct patch {
 	unsigned int insn;
 };
 
+#ifdef CONFIG_MMU
 static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
-	__acquires(&patch_lock)
 {
 	unsigned int uintaddr = (uintptr_t) addr;
 	bool module = !core_kernel_text(uintaddr);
@@ -34,8 +34,6 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 
 	if (flags)
 		raw_spin_lock_irqsave(&patch_lock, *flags);
-	else
-		__acquire(&patch_lock);
 
 	set_fixmap(fixmap, page_to_phys(page));
 
@@ -43,15 +41,19 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 }
 
 static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
-	__releases(&patch_lock)
 {
 	clear_fixmap(fixmap);
 
 	if (flags)
 		raw_spin_unlock_irqrestore(&patch_lock, *flags);
-	else
-		__release(&patch_lock);
 }
+#else
+static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
+{
+	return addr;
+}
+static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { }
+#endif
 
 void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 {
@@ -64,8 +66,6 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 
 	if (remap)
 		waddr = patch_map(addr, FIX_TEXT_POKE0, &flags);
-	else
-		__acquire(&patch_lock);
 
 	if (thumb2 && __opcode_is_thumb16(insn)) {
 		*(u16 *)waddr = __opcode_to_mem_thumb16(insn);
@@ -102,8 +102,7 @@ void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 	if (waddr != addr) {
 		flush_kernel_vmap_range(waddr, twopage ? size / 2 : size);
 		patch_unmap(FIX_TEXT_POKE0, &flags);
-	} else
-		__release(&patch_lock);
+	}
 
 	flush_icache_range((uintptr_t)(addr),
 			   (uintptr_t)(addr) + size);
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1f22b6bbda68..39eb276d0277 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,6 +250,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
 	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3be51aa06e67..dff6623804c2 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4765,6 +4765,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e1daf4151e11..4814c964692c 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,17 +40,18 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT,GLM,CNL
+ *			 Available model: SLM,AMT,GLM,CNL,TNT
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
- *						CNL,KBL,CML
+ *						CNL,KBL,CML,TNT
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -60,17 +61,18 @@
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL,TGL
+ *						KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL,KBL,CML,ICL,TGL
+ *						GLM,CNL,KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -87,7 +89,8 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *
  */
@@ -640,8 +643,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT,   glm_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
-
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4b94ae4ae369..dc43cc124e09 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1714,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	old = ((s64)(prev_raw_count << shift) >> shift);
 	local64_add(new - old + count * period, &event->count);
 
+	local64_set(&hwc->period_left, -new);
+
 	perf_event_update_userpage(event);
 
 	return 0;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 6f86650b3f77..a949f6f55991 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data)
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:
-
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 820e5751ada7..ba85bb23f060 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -220,10 +220,18 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
 #define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
 
-/* EL0 Virtual Timer Registers */
+/*
+ * EL0 Virtual Timer Registers
+ *
+ * WARNING:
+ *      KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined
+ *      with the appropriate register encodings.  Their values have been
+ *      accidentally swapped.  As this is set API, the definitions here
+ *      must be used, rather than ones derived from the encodings.
+ */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 
 /* KVM-as-firmware specific pseudo-registers */
 #define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 4703d218663a..f83a70e07df8 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
 
 #include <asm-generic/unistd.h>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index e9b62498fe75..f3327cb56edf 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -220,6 +220,7 @@
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
+#define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -357,6 +358,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM		(18*32+ 4) /* Fast Short Rep Mov */
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 8e1d0bb46361..4ea8584682f9 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
  * cpu_feature_enabled().
  */
 
-#ifdef CONFIG_X86_INTEL_MPX
-# define DISABLE_MPX	0
-#else
-# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
-#endif
-
 #ifdef CONFIG_X86_SMAP
 # define DISABLE_SMAP	0
 #else
@@ -74,7 +68,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
+#define DISABLED_MASK9	(DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index c160a5354eb6..f94f65d429be 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -11,6 +11,8 @@
 #define PROT_WRITE	0x2		/* page can be written */
 #define PROT_EXEC	0x4		/* page can be executed */
 #define PROT_SEM	0x8		/* page may be used for atomic ops */
+/*			0x10		   reserved for arch-specific use */
+/*			0x20		   reserved for arch-specific use */
 #define PROT_NONE	0x0		/* page can not be accessed */
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 1fc8faa6e973..3a3201e4618e 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -851,8 +851,13 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 __SYSCALL(__NR_clone3, sys_clone3)
 #endif
 
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+
 #undef __NR_syscalls
-#define __NR_syscalls 436
+#define __NR_syscalls 439
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 5400d7e057f1..829c0a48577f 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -395,6 +395,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
 #define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
 #define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
 #define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
 #define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
 #define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
@@ -793,6 +794,37 @@ struct drm_i915_gem_mmap_gtt {
 	__u64 offset;
 };
 
+struct drm_i915_gem_mmap_offset {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/**
+	 * Fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+
+	/**
+	 * Flags for extended behaviour.
+	 *
+	 * It is mandatory that one of the MMAP_OFFSET types
+	 * (GTT, WC, WB, UC, etc) should be included.
+	 */
+	__u64 flags;
+#define I915_MMAP_OFFSET_GTT 0
+#define I915_MMAP_OFFSET_WC  1
+#define I915_MMAP_OFFSET_WB  2
+#define I915_MMAP_OFFSET_UC  3
+
+	/*
+	 * Zero-terminated chain of extensions.
+	 *
+	 * No current extensions defined; mbz.
+	 */
+	__u64 extensions;
+};
+
 struct drm_i915_gem_set_domain {
 	/** Handle for the object */
 	__u32 handle;
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 1f97b33c840e..ca88b7bce553 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -3,6 +3,7 @@
 #define _UAPI_LINUX_FCNTL_H
 
 #include <asm/fcntl.h>
+#include <linux/openat2.h>
 
 #define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
 #define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
@@ -100,5 +101,4 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
-
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 1beb174ad950..0d8a6f47711c 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -8,6 +8,7 @@
 #ifndef _UAPI_LINUX_FSCRYPT_H
 #define _UAPI_LINUX_FSCRYPT_H
 
+#include <linux/ioctl.h>
 #include <linux/types.h>
 
 /* Encryption policy flags */
@@ -109,11 +110,22 @@ struct fscrypt_key_specifier {
 	} u;
 };
 
+/*
+ * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by
+ * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw.
+ */
+struct fscrypt_provisioning_key_payload {
+	__u32 type;
+	__u32 __reserved;
+	__u8 raw[];
+};
+
 /* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
 struct fscrypt_add_key_arg {
 	struct fscrypt_key_specifier key_spec;
 	__u32 raw_size;
-	__u32 __reserved[9];
+	__u32 key_id;
+	__u32 __reserved[8];
 	__u8 raw[];
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f0a16b4adbbd..4b95f9a31a2f 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1473,6 +1474,10 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_ARM_SVE */
 #define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
 
+/* Available with  KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
+#define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
new file mode 100644
index 000000000000..58b1eb711360
--- /dev/null
+++ b/tools/include/uapi/linux/openat2.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_OPENAT2_H
+#define _UAPI_LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+	__u64 flags;
+	__u64 mode;
+	__u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+
+#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 7da1b37b27aa..07b4f8131e36 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -234,4 +234,8 @@ struct prctl_mm_map {
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
 
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER		57
+#define PR_GET_IO_FLUSHER		58
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 4a0217832464..2e3bc22c6f20 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -36,6 +36,12 @@
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
 
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME	0x00000080	/* New time namespace */
+
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index df1153cea0b7..535a7229e1d9 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -26,7 +26,9 @@
 
 #if defined(__KERNEL__) || defined(__linux__)
 #include <linux/types.h>
+#include <asm/byteorder.h>
 #else
+#include <endian.h>
 #include <sys/ioctl.h>
 #endif
 
@@ -154,7 +156,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 14)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 15)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -301,7 +303,9 @@ typedef int __bitwise snd_pcm_subformat_t;
 #define SNDRV_PCM_INFO_DRAIN_TRIGGER	0x40000000		/* internal kernel flag - trigger in drain */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 
-
+#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__
+#define __SND_STRUCT_TIME64
+#endif
 
 typedef int __bitwise snd_pcm_state_t;
 #define	SNDRV_PCM_STATE_OPEN		((__force snd_pcm_state_t) 0) /* stream is open */
@@ -317,8 +321,17 @@ typedef int __bitwise snd_pcm_state_t;
 
 enum {
 	SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
-	SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
-	SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000,
+#ifdef __SND_STRUCT_TIME64
+	SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW,
+#else
+	SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD,
+#endif
 };
 
 union snd_pcm_sync_id {
@@ -456,8 +469,13 @@ enum {
 	SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED
 };
 
+#ifndef __KERNEL__
+/* explicit padding avoids incompatibility between i386 and x86-64 */
+typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad;
+
 struct snd_pcm_status {
 	snd_pcm_state_t state;		/* stream state */
+	__time_pad pad1;		/* align to timespec */
 	struct timespec trigger_tstamp;	/* time when stream was started/stopped/paused */
 	struct timespec tstamp;		/* reference timestamp */
 	snd_pcm_uframes_t appl_ptr;	/* appl ptr */
@@ -473,17 +491,48 @@ struct snd_pcm_status {
 	__u32 audio_tstamp_accuracy;	/* in ns units, only valid if indicated in audio_tstamp_data */
 	unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */
 };
+#endif
+
+/*
+ * For mmap operations, we need the 64-bit layout, both for compat mode,
+ * and for y2038 compatibility. For 64-bit applications, the two definitions
+ * are identical, so we keep the traditional version.
+ */
+#ifdef __SND_STRUCT_TIME64
+#define __snd_pcm_mmap_status64		snd_pcm_mmap_status
+#define __snd_pcm_mmap_control64	snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr64		snd_pcm_sync_ptr
+#ifdef __KERNEL__
+#define __snd_timespec64		__kernel_timespec
+#else
+#define __snd_timespec64		timespec
+#endif
+struct __snd_timespec {
+	__s32 tv_sec;
+	__s32 tv_nsec;
+};
+#else
+#define __snd_pcm_mmap_status		snd_pcm_mmap_status
+#define __snd_pcm_mmap_control		snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr		snd_pcm_sync_ptr
+#define __snd_timespec			timespec
+struct __snd_timespec64 {
+	__s64 tv_sec;
+	__s64 tv_nsec;
+};
 
-struct snd_pcm_mmap_status {
+#endif
+
+struct __snd_pcm_mmap_status {
 	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
 	int pad1;			/* Needed for 64 bit alignment */
 	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
-	struct timespec tstamp;		/* Timestamp */
+	struct __snd_timespec tstamp;	/* Timestamp */
 	snd_pcm_state_t suspended_state; /* RO: suspended stream state */
-	struct timespec audio_tstamp;	/* from sample counter or wall clock */
+	struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */
 };
 
-struct snd_pcm_mmap_control {
+struct __snd_pcm_mmap_control {
 	snd_pcm_uframes_t appl_ptr;	/* RW: appl ptr (0...boundary-1) */
 	snd_pcm_uframes_t avail_min;	/* RW: min available frames for wakeup */
 };
@@ -492,14 +541,59 @@ struct snd_pcm_mmap_control {
 #define SNDRV_PCM_SYNC_PTR_APPL		(1<<1)	/* get appl_ptr from driver (r/w op) */
 #define SNDRV_PCM_SYNC_PTR_AVAIL_MIN	(1<<2)	/* get avail_min from driver */
 
-struct snd_pcm_sync_ptr {
+struct __snd_pcm_sync_ptr {
 	unsigned int flags;
 	union {
-		struct snd_pcm_mmap_status status;
+		struct __snd_pcm_mmap_status status;
+		unsigned char reserved[64];
+	} s;
+	union {
+		struct __snd_pcm_mmap_control control;
+		unsigned char reserved[64];
+	} c;
+};
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+typedef char __pad_after_uframe[0];
+#endif
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+typedef char __pad_before_uframe[0];
+typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+#endif
+
+struct __snd_pcm_mmap_status64 {
+	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
+	__u32 pad1;			/* Needed for 64 bit alignment */
+	__pad_before_uframe __pad1;
+	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
+	__pad_after_uframe __pad2;
+	struct __snd_timespec64 tstamp;	/* Timestamp */
+	snd_pcm_state_t suspended_state;/* RO: suspended stream state */
+	__u32 pad3;			/* Needed for 64 bit alignment */
+	struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */
+};
+
+struct __snd_pcm_mmap_control64 {
+	__pad_before_uframe __pad1;
+	snd_pcm_uframes_t appl_ptr;	 /* RW: appl ptr (0...boundary-1) */
+	__pad_before_uframe __pad2;
+
+	__pad_before_uframe __pad3;
+	snd_pcm_uframes_t  avail_min;	 /* RW: min available frames for wakeup */
+	__pad_after_uframe __pad4;
+};
+
+struct __snd_pcm_sync_ptr64 {
+	__u32 flags;
+	__u32 pad1;
+	union {
+		struct __snd_pcm_mmap_status64 status;
 		unsigned char reserved[64];
 	} s;
 	union {
-		struct snd_pcm_mmap_control control;
+		struct __snd_pcm_mmap_control64 control;
 		unsigned char reserved[64];
 	} c;
 };
@@ -584,6 +678,8 @@ enum {
 #define SNDRV_PCM_IOCTL_STATUS		_IOR('A', 0x20, struct snd_pcm_status)
 #define SNDRV_PCM_IOCTL_DELAY		_IOR('A', 0x21, snd_pcm_sframes_t)
 #define SNDRV_PCM_IOCTL_HWSYNC		_IO('A', 0x22)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct __snd_pcm_sync_ptr)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR64	_IOWR('A', 0x23, struct __snd_pcm_sync_ptr64)
 #define SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct snd_pcm_sync_ptr)
 #define SNDRV_PCM_IOCTL_STATUS_EXT	_IOWR('A', 0x24, struct snd_pcm_status)
 #define SNDRV_PCM_IOCTL_CHANNEL_INFO	_IOR('A', 0x32, struct snd_pcm_channel_info)
@@ -614,7 +710,7 @@ enum {
  *  Raw MIDI section - /dev/snd/midi??
  */
 
-#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 0)
+#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 1)
 
 enum {
 	SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
@@ -648,13 +744,16 @@ struct snd_rawmidi_params {
 	unsigned char reserved[16];	/* reserved for future use */
 };
 
+#ifndef __KERNEL__
 struct snd_rawmidi_status {
 	int stream;
+	__time_pad pad1;
 	struct timespec tstamp;		/* Timestamp */
 	size_t avail;			/* available bytes */
 	size_t xruns;			/* count of overruns since last status (in bytes) */
 	unsigned char reserved[16];	/* reserved for future use */
 };
+#endif
 
 #define SNDRV_RAWMIDI_IOCTL_PVERSION	_IOR('W', 0x00, int)
 #define SNDRV_RAWMIDI_IOCTL_INFO	_IOR('W', 0x01, struct snd_rawmidi_info)
@@ -667,7 +766,7 @@ struct snd_rawmidi_status {
  *  Timer section - /dev/snd/timer
  */
 
-#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 6)
+#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
 
 enum {
 	SNDRV_TIMER_CLASS_NONE = -1,
@@ -761,6 +860,7 @@ struct snd_timer_params {
 	unsigned char reserved[60];	/* reserved */
 };
 
+#ifndef __KERNEL__
 struct snd_timer_status {
 	struct timespec tstamp;		/* Timestamp - last update */
 	unsigned int resolution;	/* current period resolution in ns */
@@ -769,10 +869,11 @@ struct snd_timer_status {
 	unsigned int queue;		/* used queue size */
 	unsigned char reserved[64];	/* reserved */
 };
+#endif
 
 #define SNDRV_TIMER_IOCTL_PVERSION	_IOR('T', 0x00, int)
 #define SNDRV_TIMER_IOCTL_NEXT_DEVICE	_IOWR('T', 0x01, struct snd_timer_id)
-#define SNDRV_TIMER_IOCTL_TREAD		_IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_TREAD_OLD	_IOW('T', 0x02, int)
 #define SNDRV_TIMER_IOCTL_GINFO		_IOWR('T', 0x03, struct snd_timer_ginfo)
 #define SNDRV_TIMER_IOCTL_GPARAMS	_IOW('T', 0x04, struct snd_timer_gparams)
 #define SNDRV_TIMER_IOCTL_GSTATUS	_IOWR('T', 0x05, struct snd_timer_gstatus)
@@ -785,6 +886,15 @@ struct snd_timer_status {
 #define SNDRV_TIMER_IOCTL_STOP		_IO('T', 0xa1)
 #define SNDRV_TIMER_IOCTL_CONTINUE	_IO('T', 0xa2)
 #define SNDRV_TIMER_IOCTL_PAUSE		_IO('T', 0xa3)
+#define SNDRV_TIMER_IOCTL_TREAD64	_IOW('T', 0xa4, int)
+
+#if __BITS_PER_LONG == 64
+#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD
+#else
+#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \
+				 SNDRV_TIMER_IOCTL_TREAD_OLD : \
+				 SNDRV_TIMER_IOCTL_TREAD64)
+#endif
 
 struct snd_timer_read {
 	unsigned int resolution;
@@ -810,11 +920,15 @@ enum {
 	SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
 };
 
+#ifndef __KERNEL__
 struct snd_timer_tread {
 	int event;
+	__time_pad pad1;
 	struct timespec tstamp;
 	unsigned int val;
+	__time_pad pad2;
 };
+#endif
 
 /****************************************************************************
  *                                                                          *
@@ -822,7 +936,7 @@ struct snd_timer_tread {
  *                                                                          *
  ****************************************************************************/
 
-#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
+#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 8)
 
 struct snd_ctl_card_info {
 	int card;			/* card number */
@@ -860,7 +974,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
 #define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
 #define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP		(1<<3)	/* when was control changed */
+// (1 << 3) is unused.
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
@@ -926,11 +1040,7 @@ struct snd_ctl_elem_info {
 		} enumerated;
 		unsigned char reserved[128];
 	} value;
-	union {
-		unsigned short d[4];		/* dimensions */
-		unsigned short *d_ptr;		/* indirect - obsoleted */
-	} dimen;
-	unsigned char reserved[64-4*sizeof(unsigned short)];
+	unsigned char reserved[64];
 };
 
 struct snd_ctl_elem_value {
@@ -955,8 +1065,7 @@ struct snd_ctl_elem_value {
 		} bytes;
 		struct snd_aes_iec958 iec958;
 	} value;		/* RO */
-	struct timespec tstamp;
-	unsigned char reserved[128-sizeof(struct timespec)];
+	unsigned char reserved[128];
 };
 
 struct snd_ctl_tlv {
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index a32e4b72a98f..d730666ab95d 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,8 +1,10 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
+#include <util/cpumap.h>
 #include <internal/cpumap.h>
 #include <api/fs/fs.h>
+#include <errno.h>
 #include "debug.h"
 #include "header.h"
 
@@ -12,26 +14,21 @@
 #define MIDR_VARIANT_SHIFT      20
 #define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
 
-char *get_cpuid_str(struct perf_pmu *pmu)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 {
-	char *buf = NULL;
-	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
-	int cpu;
 	u64 midr = 0;
-	struct perf_cpu_map *cpus;
-	FILE *file;
+	int cpu;
 
-	if (!sysfs || !pmu || !pmu->cpus)
-		return NULL;
+	if (!sysfs || sz < MIDR_SIZE)
+		return EINVAL;
 
-	buf = malloc(MIDR_SIZE);
-	if (!buf)
-		return NULL;
+	cpus = perf_cpu_map__get(cpus);
 
-	/* read midr from list of cpus mapped to this pmu */
-	cpus = perf_cpu_map__get(pmu->cpus);
 	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+		char path[PATH_MAX];
+		FILE *file;
+
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
 				sysfs, cpus->map[cpu]);
 
@@ -57,12 +54,48 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 		break;
 	}
 
-	if (!midr) {
+	perf_cpu_map__put(cpus);
+
+	if (!midr)
+		return EINVAL;
+
+	return 0;
+}
+
+int get_cpuid(char *buf, size_t sz)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	int ret;
+
+	if (!cpus)
+		return EINVAL;
+
+	ret = _get_cpuid(buf, sz, cpus);
+
+	perf_cpu_map__put(cpus);
+
+	return ret;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+	char *buf = NULL;
+	int res;
+
+	if (!pmu || !pmu->cpus)
+		return NULL;
+
+	buf = malloc(MIDR_SIZE);
+	if (!buf)
+		return NULL;
+
+	/* read midr from list of cpus mapped to this pmu */
+	res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+	if (res) {
 		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
 		free(buf);
 		buf = NULL;
 	}
 
-	perf_cpu_map__put(cpus);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index c29976eca4a8..44d510bc9b78 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -357,6 +357,8 @@
 433	common	fspick			__x64_sys_fspick
 434	common	pidfd_open		__x64_sys_pidfd_open
 435	common	clone3			__x64_sys_clone3/ptregs
+437	common	openat2			__x64_sys_openat2
+438	common	pidfd_getfd		__x64_sys_pidfd_getfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 46a72ecac427..01d542007c8b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1065,7 +1065,9 @@ static struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "poll", .timeout = true, },
 	{ .name	    = "ppoll", .timeout = true, },
 	{ .name	    = "prctl",
-	  .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
+	  .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */
+			   .strtoul   = STUL_STRARRAY,
+			   .parm      = &strarray__prctl_options, },
 		   [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
 		   [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
 	{ .name	    = "pread", .alias = "pread64", },
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 68039a96c1dc..bfb21d049e6c 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -13,6 +13,7 @@ include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
 include/uapi/linux/mount.h
+include/uapi/linux/openat2.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 5a61043c2ff7..d6dfe68a7612 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -213,6 +213,8 @@ size_t syscall_arg__scnprintf_x86_arch_prctl_code(char *bf, size_t size, struct
 size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option
 
+extern struct strarray strarray__prctl_options;
+
 size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index ba2179abed00..6fe5ad5f5d3a 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -11,9 +11,10 @@
 
 #include "trace/beauty/generated/prctl_option_array.c"
 
+DEFINE_STRARRAY(prctl_options, "PR_");
+
 static size_t prctl__scnprintf_option(int option, char *bf, size_t size, bool show_prefix)
 {
-	static DEFINE_STRARRAY(prctl_options, "PR_");
 	return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", show_prefix, option);
 }
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index eae47c2509eb..b5af680fc667 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -288,6 +288,7 @@ static const char *kinc_fetch_script =
 "obj-y := dummy.o\n"
 "\\$(obj)/%.o: \\$(src)/%.c\n"
 "\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
+"\t\\$(CC) -c -o \\$@ \\$<\n"
 "EOF\n"
 "touch $TMPDIR/dummy.c\n"
 "make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c8c5410315e8..fb5c2cd44d30 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -686,6 +686,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 
 		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
+		dso->kernel = DSO_TYPE_KERNEL;
 	}
 
 	dso__get(dso);
@@ -726,9 +727,17 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr);
 
 	if (!map) {
-		map = dso__new_map(event->ksymbol.name);
-		if (!map)
+		struct dso *dso = dso__new(event->ksymbol.name);
+
+		if (dso) {
+			dso->kernel = DSO_TYPE_KERNEL;
+			map = map__new2(0, dso);
+		}
+
+		if (!dso || !map) {
+			dso__put(dso);
 			return -ENOMEM;
+		}
 
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
@@ -972,7 +981,6 @@ int machine__create_extra_kernel_map(struct machine *machine,
 
 	kmap = map__kmap(map);
 
-	kmap->kmaps = &machine->kmaps;
 	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
 
 	maps__insert(&machine->kmaps, map);
@@ -1082,9 +1090,6 @@ int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unu
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-	struct kmap *kmap;
-	struct map *map;
-
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
 
@@ -1093,14 +1098,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		return -1;
 
 	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
-	map = machine__kernel_map(machine);
-	kmap = map__kmap(map);
-	if (!kmap)
-		return -1;
-
-	kmap->kmaps = &machine->kmaps;
-	maps__insert(&machine->kmaps, map);
-
+	maps__insert(&machine->kmaps, machine->vmlinux_map);
 	return 0;
 }
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f67960bedebb..a08ca276098e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -375,8 +375,13 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 
 struct map *map__clone(struct map *from)
 {
-	struct map *map = memdup(from, sizeof(*map));
+	size_t size = sizeof(struct map);
+	struct map *map;
+
+	if (from->dso && from->dso->kernel)
+		size += sizeof(struct kmap);
 
+	map = memdup(from, size);
 	if (map != NULL) {
 		refcount_set(&map->refcnt, 1);
 		RB_CLEAR_NODE(&map->rb_node);
@@ -538,6 +543,16 @@ void maps__insert(struct maps *maps, struct map *map)
 	__maps__insert(maps, map);
 	++maps->nr_maps;
 
+	if (map->dso && map->dso->kernel) {
+		struct kmap *kmap = map__kmap(map);
+
+		if (kmap)
+			kmap->kmaps = maps;
+		else
+			pr_err("Internal error: kernel dso with non kernel map\n");
+	}
+
+
 	/*
 	 * If we already performed some search by name, then we need to add the just
 	 * inserted map and resort.
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2c41d47f6f83..90d23cc3c8d4 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -18,7 +18,6 @@
  * AGGR_NONE: Use matching CPU
  * AGGR_THREAD: Not supported?
  */
-static bool have_frontend_stalled;
 
 struct runtime_stat rt_stat;
 struct stats walltime_nsecs_stats;
@@ -144,7 +143,6 @@ void runtime_stat__exit(struct runtime_stat *st)
 
 void perf_stat__init_shadow_stats(void)
 {
-	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
 	runtime_stat__init(&rt_stat);
 }
 
@@ -853,10 +851,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
-		} else if (have_frontend_stalled) {
-			out->new_line(config, ctxp);
-			print_metric(config, ctxp, NULL, "%7.2f ",
-				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b379b1296f1..1077013d8ce2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -635,9 +635,12 @@ int modules__parse(const char *filename, void *arg,
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"acpi_idle_do_entry",
+		"acpi_processor_ffh_cstate_enter",
 		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
+		"idle_cpu",
 		"intel_idle",
 		"default_idle",
 		"native_safe_halt",
@@ -651,13 +654,17 @@ static bool symbol__is_idle(const char *name)
 		NULL
 	};
 	int i;
+	static struct strlist *idle_symbols_list;
 
-	for (i = 0; idle_symbols[i]; i++) {
-		if (!strcmp(idle_symbols[i], name))
-			return true;
-	}
+	if (idle_symbols_list)
+		return strlist__has_entry(idle_symbols_list, name);
 
-	return false;
+	idle_symbols_list = strlist__new(NULL, NULL);
+
+	for (i = 0; idle_symbols[i]; i++)
+		strlist__add(idle_symbols_list, idle_symbols[i]);
+
+	return strlist__has_entry(idle_symbols_list, name);
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 18 Jan 2020 18:58:28 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b07b9e8d631856c9e42af79900527509449206f4

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 2167f1625c2f04a33145f325db0de285630f7bd1 perf/x86/intel/uncore: Remove PCIe3 unit for SNR

Tooling fixes, three Intel uncore driver fixes, plus an AUX events fix 
uncovered by the perf fuzzer.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      perf map: Set kmap->kmaps backpointer for main kernel map chunks

Hewenliang (1):
      tools lib traceevent: Fix memory leakage in filter_event

Jin Yao (1):
      perf report: Fix incorrectly added dimensions as switch perf data file

Kan Liang (3):
      perf/x86/intel/uncore: Add PCI ID of IMC for Xeon E3 V5 Family
      perf/x86/intel/uncore: Fix missing marker for snr_uncore_imc_freerunning_events
      perf/x86/intel/uncore: Remove PCIe3 unit for SNR

Mark Rutland (1):
      perf: Correctly handle failed perf_get_aux_event()

Yuya Fujita (1):
      perf hists: Fix variable name's inconsistency in hists__for_each() macro


 arch/x86/events/intel/uncore_snb.c   |  6 ++++++
 arch/x86/events/intel/uncore_snbep.c | 25 +------------------------
 kernel/events/core.c                 |  4 +++-
 tools/lib/traceevent/parse-filter.c  |  4 +++-
 tools/perf/builtin-report.c          |  5 ++++-
 tools/perf/util/hist.h               |  4 ++--
 tools/perf/util/symbol-elf.c         |  3 +++
 7 files changed, 22 insertions(+), 29 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index dbaa1b088a30..c37cb12d0ef6 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,7 @@
 #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC		0x1910
 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC		0x190f
 #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC		0x191f
+#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC		0x1918
 #define PCI_DEVICE_ID_INTEL_KBL_Y_IMC		0x590c
 #define PCI_DEVICE_ID_INTEL_KBL_U_IMC		0x5904
 #define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC		0x5914
@@ -657,6 +658,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* IMC */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
@@ -826,6 +831,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
 	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
 	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
+	IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver),  /* Xeon E3 V5 Gen Core processor */
 	IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core Y */
 	IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U */
 	IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U Quad Core */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b10a5ec79e48..ad20220af303 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -369,11 +369,6 @@
 #define SNR_M2M_PCI_PMON_BOX_CTL		0x438
 #define SNR_M2M_PCI_PMON_UMASK_EXT		0xff
 
-/* SNR PCIE3 */
-#define SNR_PCIE3_PCI_PMON_CTL0			0x508
-#define SNR_PCIE3_PCI_PMON_CTR0			0x4e8
-#define SNR_PCIE3_PCI_PMON_BOX_CTL		0x4e4
-
 /* SNR IMC */
 #define SNR_IMC_MMIO_PMON_FIXED_CTL		0x54
 #define SNR_IMC_MMIO_PMON_FIXED_CTR		0x38
@@ -4328,27 +4323,12 @@ static struct intel_uncore_type snr_uncore_m2m = {
 	.format_group	= &snr_m2m_uncore_format_group,
 };
 
-static struct intel_uncore_type snr_uncore_pcie3 = {
-	.name		= "pcie3",
-	.num_counters	= 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.perf_ctr	= SNR_PCIE3_PCI_PMON_CTR0,
-	.event_ctl	= SNR_PCIE3_PCI_PMON_CTL0,
-	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
-	.box_ctl	= SNR_PCIE3_PCI_PMON_BOX_CTL,
-	.ops		= &ivbep_uncore_pci_ops,
-	.format_group	= &ivbep_uncore_format_group,
-};
-
 enum {
 	SNR_PCI_UNCORE_M2M,
-	SNR_PCI_UNCORE_PCIE3,
 };
 
 static struct intel_uncore_type *snr_pci_uncores[] = {
 	[SNR_PCI_UNCORE_M2M]		= &snr_uncore_m2m,
-	[SNR_PCI_UNCORE_PCIE3]		= &snr_uncore_pcie3,
 	NULL,
 };
 
@@ -4357,10 +4337,6 @@ static const struct pci_device_id snr_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
 	},
-	{ /* PCIe3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
-	},
 	{ /* end: all zeroes */ }
 };
 
@@ -4536,6 +4512,7 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
 	INTEL_UNCORE_EVENT_DESC(write,		"event=0xff,umask=0x21"),
 	INTEL_UNCORE_EVENT_DESC(write.scale,	"3.814697266e-6"),
 	INTEL_UNCORE_EVENT_DESC(write.unit,	"MiB"),
+	{ /* end: all zeroes */ },
 };
 
 static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a1f8bde19b56..2173c23c25b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
+	if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) {
+		err = -EINVAL;
 		goto err_locked;
+	}
 
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index f3cbf86e51ac..20eed719542e 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1228,8 +1228,10 @@ filter_event(struct tep_event_filter *filter, struct tep_event *event,
 	}
 
 	filter_type = add_filter_type(filter, event->id);
-	if (filter_type == NULL)
+	if (filter_type == NULL) {
+		free_arg(arg);
 		return TEP_ERRNO__MEM_ALLOC_FAILED;
+	}
 
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 387311c67264..de988589d99b 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1076,6 +1076,7 @@ int cmd_report(int argc, const char **argv)
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
+	int last_key = 0;
 	bool branch_call_mode = false;
 #define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
 	static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
@@ -1450,7 +1451,8 @@ int cmd_report(int argc, const char **argv)
 		sort_order = sort_tmp;
 	}
 
-	if (setup_sorting(session->evlist) < 0) {
+	if ((last_key != K_SWITCH_INPUT_DATA) &&
+	    (setup_sorting(session->evlist) < 0)) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
 		if (field_order)
@@ -1530,6 +1532,7 @@ int cmd_report(int argc, const char **argv)
 	ret = __cmd_report(&report);
 	if (ret == K_SWITCH_INPUT_DATA) {
 		perf_session__delete(session);
+		last_key = K_SWITCH_INPUT_DATA;
 		goto repeat;
 	} else
 		ret = 0;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 45286900aacb..0aa63aeb58ec 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -339,10 +339,10 @@ static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
 	list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
 
 #define hists__for_each_format(hists, format) \
-	perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+	perf_hpp_list__for_each_format((hists)->hpp_list, format)
 
 #define hists__for_each_sort_list(hists, format) \
-	perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
+	perf_hpp_list__for_each_sort_list((hists)->hpp_list, format)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6658fbf196e6..1965aefccb02 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -920,6 +920,9 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		if (curr_map == NULL)
 			return -1;
 
+		if (curr_dso->kernel)
+			map__kmap(curr_map)->kmaps = kmaps;
+
 		if (adjust_kernel_syms) {
 			curr_map->start  = shdr->sh_addr + ref_reloc(kmap);
 			curr_map->end	 = curr_map->start + shdr->sh_size;

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 21 Dec 2019 17:16:24 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/c4ff10efe8e487cd35f4475ed2dd1e5e0c6f784a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 9f0bff1180efc9ea988fed3fd93da7647151ac8b perf/core: Add SRCU annotation for pmus list walk

Misc fixes: a BTS fix, a PT NMI handling fix, a PMU sysfs fix and an SRCU 
annotation.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (2):
      perf/x86/intel/bts: Fix the use of page_private()
      perf/x86/intel: Fix PT PMI handling

Peter Zijlstra (1):
      perf/x86: Fix potential out-of-bounds access

Sebastian Andrzej Siewior (1):
      perf/core: Add SRCU annotation for pmus list walk


 arch/x86/events/core.c      | 19 +++++++++++++++----
 arch/x86/events/intel/bts.c | 16 +++++++++++-----
 kernel/events/core.c        |  2 +-
 3 files changed, 27 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9a89d98c55bd..f118af9f0718 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -376,7 +376,7 @@ int x86_add_exclusive(unsigned int what)
 	 * LBR and BTS are still mutually exclusive.
 	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
-		return 0;
+		goto out;
 
 	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
 		mutex_lock(&pmc_reserve_mutex);
@@ -388,6 +388,7 @@ int x86_add_exclusive(unsigned int what)
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 
+out:
 	atomic_inc(&active_events);
 	return 0;
 
@@ -398,11 +399,15 @@ int x86_add_exclusive(unsigned int what)
 
 void x86_del_exclusive(unsigned int what)
 {
+	atomic_dec(&active_events);
+
+	/*
+	 * See the comment in x86_add_exclusive().
+	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
 		return;
 
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
-	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)
@@ -1642,9 +1647,12 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = {
 
 ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
 {
-	struct perf_pmu_events_attr *pmu_attr = \
+	struct perf_pmu_events_attr *pmu_attr =
 		container_of(attr, struct perf_pmu_events_attr, attr);
-	u64 config = x86_pmu.event_map(pmu_attr->id);
+	u64 config = 0;
+
+	if (pmu_attr->id < x86_pmu.max_events)
+		config = x86_pmu.event_map(pmu_attr->id);
 
 	/* string trumps id */
 	if (pmu_attr->event_str)
@@ -1713,6 +1721,9 @@ is_visible(struct kobject *kobj, struct attribute *attr, int idx)
 {
 	struct perf_pmu_events_attr *pmu_attr;
 
+	if (idx >= x86_pmu.max_events)
+		return 0;
+
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
 	/* str trumps id */
 	return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 38de4a7f6752..6a3b599ee0fe 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -63,9 +63,17 @@ struct bts_buffer {
 
 static struct pmu bts_pmu;
 
+static int buf_nr_pages(struct page *page)
+{
+	if (!PagePrivate(page))
+		return 1;
+
+	return 1 << page_private(page);
+}
+
 static size_t buf_size(struct page *page)
 {
-	return 1 << (PAGE_SHIFT + page_private(page));
+	return buf_nr_pages(page) * PAGE_SIZE;
 }
 
 static void *
@@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages,
 	/* count all the high order buffers */
 	for (pg = 0, nbuf = 0; pg < nr_pages;) {
 		page = virt_to_page(pages[pg]);
-		if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1))
-			return NULL;
-		pg += 1 << page_private(page);
+		pg += buf_nr_pages(page);
 		nbuf++;
 	}
 
@@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages,
 		unsigned int __nr_pages;
 
 		page = virt_to_page(pages[pg]);
-		__nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1;
+		__nr_pages = buf_nr_pages(page);
 		buf->buf[nbuf].page = page;
 		buf->buf[nbuf].offset = offset;
 		buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4ff86d57f9e5..a1f8bde19b56 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10523,7 +10523,7 @@ static struct pmu *perf_init_event(struct perf_event *event)
 		goto unlock;
 	}
 
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
+	list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
 		ret = perf_try_init_event(pmu, event);
 		if (!ret)
 			goto unlock;

Re: [GIT PULL] perf fixes

[Ingo Molnar]

* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Tue, Dec 17, 2019 at 3:34 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Note that the large CPU count related fixes go beyond regression fixes -
> > but the IPI-flood symptoms are severe enough that I think justifies their
> > inclusion. If it's too much we'll redo the branch.
> 
> I'm much less sensitive to the perf _tooling_ changes than I am to 
> actual kernel code changes.
> 
> Of course, if you start having a history of breaking things during the 
> rc kernels, that may change, but at least for now, I tend to look at 
> diffstats and go "oh, this is perf tooling", and not worry too much 
> about it...

Thanks for pulling these in any case!

	Ingo

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Tue, 17 Dec 2019 12:34:25 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/89c683cd06e03dfd3186c4cab1e2a39982c42a48

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

Re: [GIT PULL] perf fixes

[Linus Torvalds]

On Tue, Dec 17, 2019 at 3:34 AM Ingo Molnar <mingo@kernel.org> wrote:
>
> Note that the large CPU count related fixes go beyond regression fixes -
> but the IPI-flood symptoms are severe enough that I think justifies their
> inclusion. If it's too much we'll redo the branch.

I'm much less sensitive to the perf _tooling_ changes than I am to
actual kernel code changes.

Of course, if you start having a history of breaking things during the
rc kernels, that may change, but at least for now, I tend to look at
diffstats and go "oh, this is perf tooling", and not worry too much
about it...

                     Linus

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 57e04eeda515ee979fec3bc3d64c408feae18acc Merge tag 'perf-urgent-for-mingo-5.5-20191216' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

These are all perf tooling changes: most of them are fixes.

Note that the large CPU count related fixes go beyond regression fixes - 
but the IPI-flood symptoms are severe enough that I think justifies their 
inclusion. If it's too much we'll redo the branch.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf inject: Fix processing of ID index for injected instruction tracing

Andi Kleen (10):
      perf cpumap: Maintain cpumaps ordered and without dups
      perf evlist: Maintain evlist->all_cpus
      perf evsel: Add iterator to iterate over events ordered by CPU
      perf evsel: Add functions to close evsel on a CPU
      perf stat: Use affinity for closing file descriptors
      perf stat: Factor out open error handling
      perf stat: Use affinity for opening events
      perf stat: Use affinity for reading
      perf evsel: Add functions to enable/disable for a specific CPU
      perf stat: Use affinity for enabling/disabling events

Arnaldo Carvalho de Melo (15):
      perf machine: Fill map_symbol->maps in append_inlines() to fix segfault
      perf bench: Update the copies of x86's mem{cpy,set}_64.S
      tools arch x86: Sync the msr-index.h copy with the kernel sources
      tools headers uapi: Sync linux/fscrypt.h with the kernel sources
      tools headers uapi: Sync linux/stat.h with the kernel sources
      tools headers kvm: Sync kvm headers with the kernel sources
      tools headers UAPI: Sync sched.h with the kernel
      perf beauty: Add CLEAR_SIGHAND support for clone's flags arg
      tools arch x86: Sync asm/cpufeatures.h with the kernel sources
      perf kvm: Clarify the 'perf kvm' -i and -o command line options
      tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
      tools headers UAPI: Update tools's copy of drm.h headers
      tools headers kvm: Sync linux/kvm.h with the kernel sources
      perf arch: Make the default get_cpuid() return compatible error
      perf top: Do not bail out when perf_env__read_cpuid() returns ENOSYS

Ed Maste (2):
      perf vendor events s390: Fix counter long description for DTLB1_GPAGE_WRITES
      perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description

Ian Rogers (1):
      perf jit: Move test functionality in to a test

Kajol Jain (1):
      perf metricgroup: Fix printing event names of metric group with multiple events

Michael Petlan (1):
      perf header: Fix false warning when there are no duplicate cache entries

Ravi Bangoria (4):
      perf report/top TUI: Replace pr_err() with ui__error()
      perf report: Make -F more strict like -s
      perf report: Bail out --mem-mode if mem info is not available
      perf/x86/pmu-events: Fix Kernel_Utilization metric

Sudip Mukherjee (3):
      libtraceevent: Fix lib installation with O=
      libtraceevent: Copy pkg-config file to output folder when using O=
      libtraceevent: Allow custom libdir path


 tools/arch/arm/include/uapi/asm/kvm.h              |   3 +-
 tools/arch/arm64/include/uapi/asm/kvm.h            |   5 +-
 tools/arch/powerpc/include/uapi/asm/kvm.h          |   3 +
 tools/arch/x86/include/asm/cpufeatures.h           |   3 +
 tools/arch/x86/include/asm/msr-index.h             |  18 ++
 tools/arch/x86/lib/memcpy_64.S                     |  20 +-
 tools/arch/x86/lib/memset_64.S                     |  16 +-
 tools/include/uapi/drm/drm.h                       |   3 +-
 tools/include/uapi/drm/i915_drm.h                  | 128 ++++++++-
 tools/include/uapi/linux/fscrypt.h                 |   3 +-
 tools/include/uapi/linux/kvm.h                     |  12 +
 tools/include/uapi/linux/sched.h                   |  60 +++--
 tools/include/uapi/linux/stat.h                    |   2 +-
 tools/lib/traceevent/Makefile                      |  11 +-
 tools/lib/traceevent/plugins/Makefile              |   5 +-
 tools/perf/Documentation/perf-kvm.txt              |   5 +-
 tools/perf/arch/arm/tests/regs_load.S              |   4 +-
 tools/perf/arch/arm64/tests/regs_load.S            |   4 +-
 tools/perf/arch/x86/tests/regs_load.S              |   8 +-
 tools/perf/builtin-inject.c                        |  13 +-
 tools/perf/builtin-record.c                        |   2 +-
 tools/perf/builtin-report.c                        |   8 +
 tools/perf/builtin-stat.c                          | 288 +++++++++++++++------
 tools/perf/builtin-top.c                           |  10 +-
 tools/perf/check-headers.sh                        |   4 +-
 tools/perf/lib/cpumap.c                            |  73 +++++-
 tools/perf/lib/evlist.c                            |   1 +
 tools/perf/lib/evsel.c                             |  76 ++++--
 tools/perf/lib/include/internal/evlist.h           |   1 +
 tools/perf/lib/include/perf/cpumap.h               |   2 +
 tools/perf/lib/include/perf/evsel.h                |   3 +
 .../perf/pmu-events/arch/s390/cf_z13/extended.json |   2 +-
 .../perf/pmu-events/arch/s390/cf_z14/extended.json |   2 +-
 .../pmu-events/arch/x86/broadwell/bdw-metrics.json |   2 +-
 .../arch/x86/broadwellde/bdwde-metrics.json        |   2 +-
 .../arch/x86/broadwellx/bdx-metrics.json           |   2 +-
 .../arch/x86/cascadelakex/clx-metrics.json         |   2 +-
 .../pmu-events/arch/x86/haswell/hsw-metrics.json   |   2 +-
 .../pmu-events/arch/x86/haswellx/hsx-metrics.json  |   2 +-
 .../pmu-events/arch/x86/ivybridge/ivb-metrics.json |   2 +-
 .../pmu-events/arch/x86/ivytown/ivt-metrics.json   |   2 +-
 .../pmu-events/arch/x86/jaketown/jkt-metrics.json  |   2 +-
 .../arch/x86/sandybridge/snb-metrics.json          |   2 +-
 .../pmu-events/arch/x86/skylake/skl-metrics.json   |   2 +-
 .../pmu-events/arch/x86/skylakex/skx-metrics.json  |   2 +-
 tools/perf/tests/Build                             |   1 +
 tools/perf/tests/builtin-test.c                    |   9 +
 tools/perf/tests/cpumap.c                          |  16 ++
 tools/perf/tests/event-times.c                     |   4 +-
 tools/perf/tests/genelf.c                          |  51 ++++
 tools/perf/tests/tests.h                           |   2 +
 tools/perf/trace/beauty/clone.c                    |   1 +
 tools/perf/util/cpumap.h                           |   1 +
 tools/perf/util/evlist.c                           | 113 +++++++-
 tools/perf/util/evlist.h                           |  11 +-
 tools/perf/util/evsel.c                            |  35 ++-
 tools/perf/util/evsel.h                            |   9 +-
 tools/perf/util/genelf.c                           |  46 ----
 tools/perf/util/header.c                           |  23 +-
 tools/perf/util/include/linux/linkage.h            |  89 ++++++-
 tools/perf/util/machine.c                          |   1 +
 tools/perf/util/metricgroup.c                      |   7 +-
 tools/perf/util/sort.c                             |  16 +-
 tools/perf/util/stat.c                             |   5 +-
 tools/perf/util/stat.h                             |   3 +-
 65 files changed, 976 insertions(+), 289 deletions(-)
 create mode 100644 tools/perf/tests/genelf.c

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 1 Dec 2019 23:15:22 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b7fcf31f7036895ca8fc3a30eefffab0e82f75f6

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e680a41fcaf07ccac8817c589fc4824988b48eac Merge tag 'perf-core-for-mingo-5.5-20191128' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly fixes:


 - Make /sys/devices/cpu/rdpmc based RDPMC enforcement more instantaneous

 - decoder: Update the Intel opcode map

 - Various tooling fixes, including a few late optimizations and cleanups.

 Thanks,

	Ingo

------------------>
Adrian Hunter (4):
      x86/insn: Add some more Intel instructions to the opcode map
      x86/insn: perf tools: Add some more instructions to the new instructions test
      perf script: Fix brstackinsn for AUXTRACE
      perf script: Fix invalid LBR/binary mismatch error

Andi Kleen (2):
      perf pmu: Use file system cache to optimize sysfs access
      perf affinity: Add infrastructure to save/restore affinity

Anthony Steinhauser (1):
      perf/x86: Implement immediate enforcement of /sys/devices/cpu/rdpmc value of 0

Arnaldo Carvalho de Melo (15):
      perf script: Move map__fprintf_srccode() to near its only user
      perf map: Ditch leftover map__reloc_vmlinux() prototype
      perf map: Remove needless struct forward declarations
      perf map: Remove unused functions
      perf maps: Merge 'struct maps' with 'struct map_groups'
      perf thread: Rename thread->mg to thread->maps
      perf addr_location: Rename al->mg to al->maps
      perf map_symbol: Rename ms->mg to ms->maps
      perf maps: Rename 'mg' variables to 'maps'
      perf maps: Rename map_groups.h to maps.h
      perf tests: Rename thread-mg-share to thread-maps-share
      perf tests: Rename tests/map_groups.c to tests/maps.c
      perf diff: Use llabs() with 64-bit values
      perf diff: Use llabs() with 64-bit values
      perf regs: Make perf_reg_name() return "unknown" instead of NULL

Jiri Olsa (1):
      perf tools: Allow to link with libbpf dynamicaly


 arch/x86/events/core.c                             |  18 +-
 arch/x86/include/asm/mmu_context.h                 |   4 +-
 arch/x86/lib/x86-opcode-map.txt                    |  44 +-
 tools/arch/x86/lib/x86-opcode-map.txt              |  44 +-
 tools/build/Makefile.feature                       |   3 +-
 tools/build/feature/Makefile                       |   4 +
 tools/build/feature/test-libbpf.c                  |   7 +
 tools/perf/Makefile.config                         |  10 +
 tools/perf/Makefile.perf                           |   6 +-
 tools/perf/arch/arm/tests/dwarf-unwind.c           |   4 +-
 tools/perf/arch/arm64/tests/dwarf-unwind.c         |   4 +-
 tools/perf/arch/powerpc/tests/dwarf-unwind.c       |   4 +-
 tools/perf/arch/s390/annotate/instructions.c       |   2 +-
 tools/perf/arch/x86/tests/dwarf-unwind.c           |   4 +-
 tools/perf/arch/x86/tests/insn-x86-dat-32.c        | 366 ++++++++++++
 tools/perf/arch/x86/tests/insn-x86-dat-64.c        | 484 +++++++++++++++
 tools/perf/arch/x86/tests/insn-x86-dat-src.c       | 655 +++++++++++++++++++++
 tools/perf/arch/x86/util/event.c                   |   5 +-
 tools/perf/builtin-diff.c                          |   6 +-
 tools/perf/builtin-report.c                        |   7 +-
 tools/perf/builtin-script.c                        |  46 +-
 tools/perf/tests/Build                             |   4 +-
 tools/perf/tests/builtin-test.c                    |   8 +-
 tools/perf/tests/code-reading.c                    |   2 +-
 tools/perf/tests/{map_groups.c => maps.c}          |  26 +-
 tools/perf/tests/tests.h                           |   4 +-
 .../{thread-mg-share.c => thread-maps-share.c}     |  36 +-
 tools/perf/tests/vmlinux-kallsyms.c                |   9 +-
 tools/perf/ui/browsers/annotate.c                  |   2 +-
 tools/perf/ui/stdio/hist.c                         |   4 +-
 tools/perf/util/Build                              |   2 +
 tools/perf/util/affinity.c                         |  73 +++
 tools/perf/util/affinity.h                         |  17 +
 tools/perf/util/annotate.c                         |   8 +-
 tools/perf/util/bpf-event.c                        |   4 +-
 tools/perf/util/callchain.c                        |   8 +-
 tools/perf/util/cs-etm.c                           |   2 +-
 tools/perf/util/db-export.c                        |  12 +-
 tools/perf/util/event.c                            |  14 +-
 tools/perf/util/fncache.c                          |  63 ++
 tools/perf/util/fncache.h                          |   7 +
 tools/perf/util/hist.c                             |   8 +-
 tools/perf/util/intel-pt.c                         |   2 +-
 tools/perf/util/machine.c                          |  80 ++-
 tools/perf/util/machine.h                          |  10 +-
 tools/perf/util/map.c                              | 223 ++-----
 tools/perf/util/map.h                              |  14 +-
 tools/perf/util/map_groups.h                       | 106 ----
 tools/perf/util/map_symbol.h                       |   4 +-
 tools/perf/util/maps.h                             |  87 +++
 tools/perf/util/perf_regs.h                        |   2 +-
 tools/perf/util/pmu.c                              |  34 +-
 tools/perf/util/probe-event.c                      |   4 +-
 tools/perf/util/python-ext-sources                 |   1 +
 .../util/scripting-engines/trace-event-python.c    |   2 +-
 tools/perf/util/srccode.c                          |   9 +-
 tools/perf/util/symbol-elf.c                       |  16 +-
 tools/perf/util/symbol.c                           |  91 ++-
 tools/perf/util/symbol.h                           |   6 +-
 tools/perf/util/synthetic-events.c                 |   2 +-
 tools/perf/util/thread-stack.c                     |   4 +-
 tools/perf/util/thread.c                           |  38 +-
 tools/perf/util/thread.h                           |   4 +-
 tools/perf/util/unwind-libdw.c                     |   4 +-
 tools/perf/util/unwind-libunwind-local.c           |  22 +-
 tools/perf/util/unwind-libunwind.c                 |  36 +-
 tools/perf/util/unwind.h                           |  27 +-
 tools/perf/util/vdso.c                             |   2 +-
 68 files changed, 2245 insertions(+), 625 deletions(-)
 create mode 100644 tools/build/feature/test-libbpf.c
 rename tools/perf/tests/{map_groups.c => maps.c} (83%)
 rename tools/perf/tests/{thread-mg-share.c => thread-maps-share.c} (64%)
 create mode 100644 tools/perf/util/affinity.c
 create mode 100644 tools/perf/util/affinity.h
 create mode 100644 tools/perf/util/fncache.c
 create mode 100644 tools/perf/util/fncache.h
 delete mode 100644 tools/perf/util/map_groups.h
 create mode 100644 tools/perf/util/maps.h

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 16 Nov 2019 22:33:33 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/5ffaf037e776fd5095561c27d879b4484549f7e4

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d00dbd29814236ad128ff9517e8f7af6b6ef4ba0 perf/core: Fix missing static inline on perf_cgroup_switch()

Misc fixes: a handful of AUX event handling related fixes, a Sparse fix 
and two ABI fixes.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (4):
      perf/aux: Fix the aux_output group inheritance fix
      perf/core: Reattach a misplaced comment
      perf/aux: Disallow aux_output for kernel events
      perf/core: Consistently fail fork on allocation failures

Ben Dooks (Codethink) (1):
      perf/core: Fix missing static inline on perf_cgroup_switch()

Peter Zijlstra (1):
      perf/core: Disallow uncore-cgroup events


 kernel/events/core.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index aec8dba2bea4..00a014670ed0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 }
 
-void
+static inline void
 perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
 {
 }
@@ -10535,6 +10535,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_ns;
 	}
 
+	/*
+	 * Disallow uncore-cgroup events, they don't make sense as the cgroup will
+	 * be different on other CPUs in the uncore mask.
+	 */
+	if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) {
+		err = -EINVAL;
+		goto err_pmu;
+	}
+
 	if (event->attr.aux_output &&
 	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
 		err = -EOPNOTSUPP;
@@ -11323,8 +11332,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	int err;
 
 	/*
-	 * Get the target context (task or percpu):
+	 * Grouping is not supported for kernel events, neither is 'AUX',
+	 * make sure the caller's intentions are adjusted.
 	 */
+	if (attr->aux_output)
+		return ERR_PTR(-EINVAL);
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
 				 overflow_handler, context, -1);
@@ -11336,6 +11348,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = TASK_TOMBSTONE;
 
+	/*
+	 * Get the target context (task or percpu):
+	 */
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -11787,7 +11802,7 @@ inherit_event(struct perf_event *parent_event,
 						   GFP_KERNEL);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
@@ -11890,7 +11905,7 @@ static int inherit_group(struct perf_event *parent_event,
 		if (IS_ERR(child_ctr))
 			return PTR_ERR(child_ctr);
 
-		if (sub->aux_event == parent_event &&
+		if (sub->aux_event == parent_event && child_ctr &&
 		    !perf_get_aux_event(child_ctr, leader))
 			return -EINVAL;
 	}

Re: [GIT PULL] perf fixes

[Linus Torvalds]

On Fri, Nov 1, 2019 at 1:30 PM Ingo Molnar <mingo@kernel.org> wrote:
>
> Firstly, non-existent fields are initialized to zero by default in the
> perf ABI: *even if user-space was built well before that new field was
> introduced in the kernel*.
>
> This is done in perf_copy_attr():
>
>         /* Zero the full structure, so that a short copy will be nice. */
>         memset(attr, 0, sizeof(*attr));
>
> The user-space structure that is passed in ('uattr' within that function)
> might indeed be short and not contain the new field - but we handle this
> via uattr->size, which is set by user-space - for example 'perf' sets it
> in event_attr_init() in tools/perf/util/util.c:
>
>         /* to capture ABI version */
>         attr->size = sizeof(*attr);
>
> Second, the kernel syscall then checks this size against the kernel's
> size of attr:
>
>  - if uattr->size < kattr_size: then old ABI user-space binary is
>    running on new kernel, and we zero out residual fields.

Very good. These were the two pieces I was missing - just readfing the
commit messages it wasn't clear that this was safe at all.

Thanks for following up on my worry,

               Linus

Re: [GIT PULL] perf fixes

[Ingo Molnar]

* Ingo Molnar <mingo@kernel.org> wrote:

> This actually works fine in practice. I just tried out a brand new kernel 
> with really old perf tooling in the v3.19 kernel, from 4.5 years ago:
> 
>   $ git checkout v3.19
>   $ cd tools/perf/
>   $ make install WERROR=0
> 
>   $ perf version
>   perf version 3.19.gbfa76d49
> 
>   $ perf top
> 
> This ancient version of 'perf top', 'perf record', 'perf report' works 
> just fine on the new kernel, despite passing in a smaller 'attr':
> 
>   [  558.408907] perf kABI size: 112
>   [  558.412855] perf uABI size: 104
> 
> when running new tooling on a new kernel the two sizes match:
> 
> [  331.598089] perf kABI size: 112
> [  331.602050] perf uABI size: 112
> 
> and everything works as usual.

Out of morbid curiosity I also tried out the v3.2 version of perf 
tooling, which is now more than 7.5 years old, and 'perf record' + 'perf 
report' is working fine on the latest kernel too:


  $ perf version
  perf version 3.2.dirty

  $ perf record ~/hackbench 20
  Time: 0.082
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.828 MB perf.data (~36166 samples) ]

  $ perf report --stdio
  ...
  # Overhead    Command      Shared Object                                      Symbol
  # ........  .........  .................  ..........................................
  #
     6.99%  hackbench  [kernel.kallsyms]  [k] queued_spin_lock_slowpath
     6.22%  hackbench  [kernel.kallsyms]  [k] entry_SYSENTER_compat
     4.06%  hackbench  [kernel.kallsyms]  [k] sysret32_from_system_call
     3.56%  hackbench  [kernel.kallsyms]  [k] do_fast_syscall_32
     3.40%  hackbench  [kernel.kallsyms]  [k] unix_stream_read_generic
     3.32%  hackbench  [kernel.kallsyms]  [k] _raw_spin_lock
     3.13%  hackbench  [kernel.kallsyms]  [k] __slab_free


It works despite 'perf record' using an ancient, 72 bytes long 'struct perf_attr' 
ABI:

  [ 3013.531125] perf kABI size: 112
  [ 3013.535097] perf uABI size: 72

If I'm reading the logs right then the perf ABI went through around ~15 
iterations in the v3.2..v5.4 timeframe that extended struct 
perf_event_attr - but binary compatibility was maintained with ancient 
tooling.

This is also useful for tooling bisectability: tooling should work on new 
and old kernels as well, even if a bisection point moves across ABI 
extension boundaries.

Thanks,

	Ingo

Re: [GIT PULL] perf fixes

[Ingo Molnar]

* Linus Torvalds <torvalds@linux-foundation.org> wrote:

> On Fri, Nov 1, 2019 at 10:48 AM Ingo Molnar <mingo@kernel.org> wrote:
> >
> > Alexander Shishkin (1):
> >       perf/core: Start rejecting the syscall with attr.__reserved_2 set
> 
> This seems to quite possibly break existing apps. Is there any reason 
> to believe that existing users have actually cleared that field?

Yes, there's good reason to believe that the field ends up being zero 
within the kernel even if old user-space uses the old, smaller structure:

> It's suspect for another reason too: the commit that added that field
> just added it to the end of the structure, with the argument that
> "aux_watermark will only matter for new AUX-aware code, so the old
> code should still be fine".
> 
> So by *definition* those old kinds of users would never have cleared
> that field, because that field didn't exist.

Firstly, non-existent fields are initialized to zero by default in the 
perf ABI: *even if user-space was built well before that new field was 
introduced in the kernel*.

This is done in perf_copy_attr():

        /* Zero the full structure, so that a short copy will be nice. */
        memset(attr, 0, sizeof(*attr));

The user-space structure that is passed in ('uattr' within that function) 
might indeed be short and not contain the new field - but we handle this 
via uattr->size, which is set by user-space - for example 'perf' sets it 
in event_attr_init() in tools/perf/util/util.c:

        /* to capture ABI version */
        attr->size = sizeof(*attr);

Second, the kernel syscall then checks this size against the kernel's 
size of attr:

 - if uattr->size < kattr_size: then old ABI user-space binary is 
   running on new kernel, and we zero out residual fields.

 - if uattr->size = kattr_size, this is the normal case of matching ABI (sizes)

 - if uattr->size > kattr_size, then new ABI user-space binary is running 
   on an old kernel - in this case the kernel copies in a shortened 
   structure from the new tool and ignores the remaining fields. To not 
   surprise new user-space the kernel copies back the recognized size to 
   uattr->size and user-space can decide whether they want to run on this 
   kernel or not:

             put_user(sizeof(*attr), &uattr->size);

This way the perf ABI is *both* backwards and forward compatible, even 
across multiple ABI changes. We seemingly didn't "care" about the zeroing 
of the new field in old binaries in that changelog, because it's 
guaranteed by the syscall implementation.

[ Note that there *is* still potential for more subtle ABI breakage, see 
  further below. ]

This actually works fine in practice. I just tried out a brand new kernel 
with really old perf tooling in the v3.19 kernel, from 4.5 years ago:

  $ git checkout v3.19
  $ cd tools/perf/
  $ make install WERROR=0

  $ perf version
  perf version 3.19.gbfa76d49

  $ perf top

This ancient version of 'perf top', 'perf record', 'perf report' works 
just fine on the new kernel, despite passing in a smaller 'attr':

  [  558.408907] perf kABI size: 112
  [  558.412855] perf uABI size: 104

when running new tooling on a new kernel the two sizes match:

[  331.598089] perf kABI size: 112
[  331.602050] perf uABI size: 112

and everything works as usual.

> And the people involved should stop claiming this "fixes" anything,
> and should look hard at their random ABI expansions and "fixes".
> 
> The original code that said "old users would not be impacted" is
> correct. But this "fix" is very very very questionable indeed, and I
> get the feeling that somebody doesn't understand what ABI is, when
> they claim that this "fixes" anything.

So if your primary worry is about old user-space that didn't know about 
the new field passing in the new field with some random value, then if 
the perf ABI handling logic I outlined above is implemented correctly 
(and I believe it's correct), then this should not happen.

But arguably there's still a more subtle ABI breakage that this change 
might trigger: if due to some bug user-space *does* initialize this 
reserved field to non-zero, and the kernel ignored that non-zero field 
for 4 years and new kernels suddenly start rejecting these syscalls, 
that's an ABI bug and grounds for an immediate revert.

I don't expect this to happen though, due to the combination of how 
user-space and kernel-space handles the extension of the perf ABI - but 
if it happens then it's an insta-revert.

I'd also argue that because we didn't check this field for years, the 
next ABI extension should probably not use the __reserved_2 field - which 
is a good idea anyway as it has an unnatural __u16 size.

> Honestly, this all shows a worrying complete disregard for backwards
> compatibility. Calling this a "fix" is questionable, when it is much
> more likely to break some old user.
> 
> I've pulled it, but I need people to be aware that this is utter
> garbage, and that if anybody ever reports it, this needs to be
> immediately reverted.

In light of the above logic I'd like to push back against this 
characterization: this kind of ABI compatibility is actually one of the 
most important aspects of the perf ABI, and we very much take it 
seriously.

In fact we are proud of it: the perf ABI is one of the most iterated, yet 
also one of the most compatible and tooling-friendly ABIs in the kernel. :-)

The reason it wasn't even mentioned in the changelog is because we tried 
to design out this kind of mishap from the ABI, and all the main perf 
developers are aware of that design. Will try to include a more careful 
explanation next time.

Thanks,

	Ingo

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Fri, 1 Nov 2019 18:48:40 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/355f83c1d098c27b3d912c7a397c13be17de6476

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

Re: [GIT PULL] perf fixes

[Linus Torvalds]

On Fri, Nov 1, 2019 at 10:48 AM Ingo Molnar <mingo@kernel.org> wrote:
>
> Alexander Shishkin (1):
>       perf/core: Start rejecting the syscall with attr.__reserved_2 set

This seems to quite possibly break existing apps. Is there any reason
to believe that existing users have actually cleared that field?

It's suspect for another reason too: the commit that added that field
just added it to the end of the structure, with the argument that
"aux_watermark will only matter for new AUX-aware code, so the old
code should still be fine".

So by *definition* those old kinds of users would never have cleared
that field, because that field didn't exist.

Honestly, this all shows a worrying complete disregard for backwards
compatibility. Calling this a "fix" is questionable, when it is much
more likely to break some old user.

I've pulled it, but I need people to be aware that this is utter
garbage, and that if anybody ever reports it, this needs to be
immediately reverted.

And the people involved should stop claiming this "fixes" anything,
and should look hard at their random ABI expansions and "fixes".

The original code that said "old users would not be impacted" is
correct. But this "fix" is very very very questionable indeed, and I
get the feeling that somebody doesn't understand what ABI is, when
they claim that this "fixes" anything.

      Linus

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 652521d460cbfa24ef27717b4b28acfac4281be6 perf/headers: Fix spelling s/EACCESS/EACCES/, s/privilidge/privilege/

Misc fixes: an ABI fix for a reserved field, AMD IBS fixes, an Intel 
uncore PMU driver fix and a header typo fix.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Start rejecting the syscall with attr.__reserved_2 set

Geert Uytterhoeven (1):
      perf/headers: Fix spelling s/EACCESS/EACCES/, s/privilidge/privilege/

Kan Liang (1):
      perf/x86/uncore: Fix event group support

Kim Phillips (2):
      perf/x86/amd/ibs: Fix reading of the IBS OpData register and thus precise RIP validity
      perf/x86/amd/ibs: Handle erratum #420 only on the affected CPU family (10h)


 arch/x86/events/amd/ibs.c      |  8 +++++---
 arch/x86/events/intel/uncore.c | 44 ++++++++++++++++++++++++++++++++++++------
 arch/x86/events/intel/uncore.h | 12 ------------
 include/linux/perf_event.h     |  2 +-
 kernel/events/core.c           |  2 +-
 5 files changed, 45 insertions(+), 23 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 5b35b7ea5d72..26c36357c4c9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
 					  struct hw_perf_event *hwc, u64 config)
 {
 	config &= ~perf_ibs->cnt_mask;
-	wrmsrl(hwc->config_base, config);
+	if (boot_cpu_data.x86 == 0x10)
+		wrmsrl(hwc->config_base, config);
 	config &= ~perf_ibs->enable_mask;
 	wrmsrl(hwc->config_base, config);
 }
@@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = {
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
-	.cnt_mask		= IBS_OP_MAX_CNT,
+	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
+				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
 	.max_period		= IBS_OP_MAX_CNT << 4,
@@ -614,7 +616,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	if (event->attr.sample_type & PERF_SAMPLE_RAW)
 		offset_max = perf_ibs->offset_max;
 	else if (check_rip)
-		offset_max = 2;
+		offset_max = 3;
 	else
 		offset_max = 1;
 	do {
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 6fc2e06ab4c6..86467f85c383 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags)
 	local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
 	uncore_enable_event(box, event);
 
-	if (box->n_active == 1) {
-		uncore_enable_box(box);
+	if (box->n_active == 1)
 		uncore_pmu_start_hrtimer(box);
-	}
 }
 
 void uncore_pmu_event_stop(struct perf_event *event, int flags)
@@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags)
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
 
-		if (box->n_active == 0) {
-			uncore_disable_box(box);
+		if (box->n_active == 0)
 			uncore_pmu_cancel_hrtimer(box);
-		}
 	}
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
@@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	return ret;
 }
 
+static void uncore_pmu_enable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->enable_box)
+		uncore_pmu->type->ops->enable_box(box);
+}
+
+static void uncore_pmu_disable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->disable_box)
+		uncore_pmu->type->ops->disable_box(box);
+}
+
 static ssize_t uncore_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 		pmu->pmu = (struct pmu) {
 			.attr_groups	= pmu->type->attr_groups,
 			.task_ctx_nr	= perf_invalid_context,
+			.pmu_enable	= uncore_pmu_enable,
+			.pmu_disable	= uncore_pmu_disable,
 			.event_init	= uncore_pmu_event_init,
 			.add		= uncore_pmu_event_add,
 			.del		= uncore_pmu_event_del,
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index f36f7bebbc1b..bbfdaa720b45 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
 	return -EINVAL;
 }
 
-static inline void uncore_disable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->disable_box)
-		box->pmu->type->ops->disable_box(box);
-}
-
-static inline void uncore_enable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->enable_box)
-		box->pmu->type->ops->enable_box(box);
-}
-
 static inline void uncore_disable_event(struct intel_uncore_box *box,
 				struct perf_event *event)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 61448c19a132..68ccc5b1913b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -292,7 +292,7 @@ struct pmu {
 	 *  -EBUSY	-- @event is for this PMU but PMU temporarily unavailable
 	 *  -EINVAL	-- @event is for this PMU but @event is not valid
 	 *  -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported
-	 *  -EACCESS	-- @event is for this PMU, @event is valid, but no privilidges
+	 *  -EACCES	-- @event is for this PMU, @event is valid, but no privileges
 	 *
 	 *  0		-- @event is for this PMU and valid
 	 *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bb3748d29b04..aec8dba2bea4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10635,7 +10635,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	attr->size = size;
 
-	if (attr->__reserved_1)
+	if (attr->__reserved_1 || attr->__reserved_2)
 		return -EINVAL;
 
 	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 12 Oct 2019 15:31:34 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/465a7e291fd4f056d81baf5d5ed557bdb44c5457

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 52e92f409dede388b7dc3ee13491fbf7a80db935 perf/x86/cstate: Add Tiger Lake CPU support

Mostly tooling fixes, but also a couple of updates for new Intel models 
(which are technically hw-enablement, but to users it's a fix to perf 
behavior on those new CPUs - hope this is fine), an AUX inheritance fix, 
event time-sharing fix, and a fix for lost non-perf NMI events on AMD 
systems.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Fix inheritance of aux_output groups

Andi Kleen (2):
      perf script brstackinsn: Fix recovery from LBR/binary mismatch
      perf jevents: Fix period for Intel fixed counters

Arnaldo Carvalho de Melo (13):
      tools headers uapi: Sync drm/i915_drm.h with the kernel sources
      tools headers uapi: Sync asm-generic/mman-common.h with the kernel
      tools headers uapi: Sync linux/usbdevice_fs.h with the kernel sources
      tools headers uapi: Sync linux/fs.h with the kernel sources
      tools headers kvm: Sync kvm headers with the kernel sources
      perf tools: Propagate get_cpuid() error
      perf evsel: Fall back to global 'perf_env' in perf_evsel__env()
      perf annotate: Propagate perf_env__arch() error
      perf annotate: Fix the signedness of failure returns
      perf annotate: Propagate the symbol__annotate() error return
      perf annotate: Fix arch specific ->init() failure errors
      perf annotate: Return appropriate error code for allocation failures
      perf annotate: Don't return -1 for error when doing BPF disassembly

Ian Rogers (4):
      libsubcmd: Make _FORTIFY_SOURCE defines dependent on the feature
      perf tests: Avoid raising SEGV using an obvious NULL dereference
      perf docs: Allow man page date to be specified
      perf llvm: Don't access out-of-scope array

Kan Liang (8):
      perf/x86/intel: Add Comet Lake CPU support
      perf/x86/msr: Add Comet Lake CPU support
      perf/x86/cstate: Add Comet Lake CPU support
      perf/x86/msr: Add new CPU model numbers for Ice Lake
      perf/x86/cstate: Update C-state counters for Ice Lake
      perf/x86/intel: Add Tiger Lake CPU support
      perf/x86/msr: Add Tiger Lake CPU support
      perf/x86/cstate: Add Tiger Lake CPU support

Song Liu (2):
      perf/core: Rework memory accounting in perf_mmap()
      perf/core: Fix corner case in perf_rotate_context()

Steve MacLean (3):
      perf map: Fix overlapped map handling
      perf inject jit: Fix JIT_CODE_MOVE filename
      perf docs: Correct and clarify jitdump spec

Thomas Richter (2):
      perf vendor events s390: Add JSON transaction for machine type 8561
      perf vendor events s390: Use s390 machine name instead of type 8561

Tom Lendacky (1):
      perf/x86/amd: Change/fix NMI latency mitigation to use a timestamp


 arch/x86/events/amd/core.c                         |  30 ++--
 arch/x86/events/intel/core.c                       |   4 +
 arch/x86/events/intel/cstate.c                     |  44 +++--
 arch/x86/events/msr.c                              |   7 +
 kernel/events/core.c                               |  43 ++++-
 tools/arch/arm/include/uapi/asm/kvm.h              |   4 +-
 tools/arch/arm64/include/uapi/asm/kvm.h            |   4 +-
 tools/arch/s390/include/uapi/asm/kvm.h             |   6 +
 tools/arch/x86/include/uapi/asm/vmx.h              |   2 +
 tools/include/uapi/asm-generic/mman-common.h       |   3 +
 tools/include/uapi/drm/i915_drm.h                  |   1 +
 tools/include/uapi/linux/fs.h                      |  55 +------
 tools/include/uapi/linux/fscrypt.h                 | 181 +++++++++++++++++++++
 tools/include/uapi/linux/kvm.h                     |   3 +
 tools/include/uapi/linux/usbdevice_fs.h            |   4 +
 tools/lib/subcmd/Makefile                          |   8 +-
 tools/perf/Documentation/asciidoc.conf             |   3 +
 tools/perf/Documentation/jitdump-specification.txt |   4 +-
 tools/perf/arch/arm/annotate/instructions.c        |   4 +-
 tools/perf/arch/arm64/annotate/instructions.c      |   4 +-
 tools/perf/arch/powerpc/util/header.c              |   3 +-
 tools/perf/arch/s390/annotate/instructions.c       |   6 +-
 tools/perf/arch/s390/util/header.c                 |   9 +-
 tools/perf/arch/x86/annotate/instructions.c        |   6 +-
 tools/perf/arch/x86/util/header.c                  |   3 +-
 tools/perf/builtin-kvm.c                           |   7 +-
 tools/perf/builtin-script.c                        |   6 +-
 tools/perf/check-headers.sh                        |   1 +
 .../arch/s390/{cf_m8561 => cf_z15}/basic.json      |   0
 .../arch/s390/{cf_m8561 => cf_z15}/crypto.json     |   0
 .../arch/s390/{cf_m8561 => cf_z15}/crypto6.json    |   0
 .../arch/s390/{cf_m8561 => cf_z15}/extended.json   |   0
 .../pmu-events/arch/s390/cf_z15/transaction.json   |   7 +
 tools/perf/pmu-events/arch/s390/mapfile.csv        |   2 +-
 tools/perf/pmu-events/jevents.c                    |  12 +-
 tools/perf/tests/perf-hooks.c                      |   3 +-
 tools/perf/util/annotate.c                         |  35 +++-
 tools/perf/util/annotate.h                         |   4 +
 tools/perf/util/evsel.c                            |   3 +-
 tools/perf/util/jitdump.c                          |   6 +-
 tools/perf/util/llvm-utils.c                       |   6 +-
 tools/perf/util/map.c                              |   3 +
 tools/perf/util/python.c                           |   6 +
 43 files changed, 411 insertions(+), 131 deletions(-)
 create mode 100644 tools/include/uapi/linux/fscrypt.h
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/basic.json (100%)
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/crypto.json (100%)
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/crypto6.json (100%)
 rename tools/perf/pmu-events/arch/s390/{cf_m8561 => cf_z15}/extended.json (100%)
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/transaction.json

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e7d35f60d53f..64c3e70b0556 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -5,12 +5,14 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/jiffies.h>
 #include <asm/apicdef.h>
 #include <asm/nmi.h>
 
 #include "../perf_event.h"
 
-static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp);
+static unsigned long perf_nmi_window;
 
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -641,11 +643,12 @@ static void amd_pmu_disable_event(struct perf_event *event)
  * handler when multiple PMCs are active or PMC overflow while handling some
  * other source of an NMI.
  *
- * Attempt to mitigate this by using the number of active PMCs to determine
- * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
- * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
- * number of active PMCs or 2. The value of 2 is used in case an NMI does not
- * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ * Attempt to mitigate this by creating an NMI window in which un-handled NMIs
+ * received during this window will be claimed. This prevents extending the
+ * window past when it is possible that latent NMIs should be received. The
+ * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has
+ * handled a counter. When an un-handled NMI is received, it will be claimed
+ * only if arriving within that window.
  */
 static int amd_pmu_handle_irq(struct pt_regs *regs)
 {
@@ -663,21 +666,19 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	handled = x86_pmu_handle_irq(regs);
 
 	/*
-	 * If a counter was handled, record the number of possible remaining
-	 * NMIs that can occur.
+	 * If a counter was handled, record a timestamp such that un-handled
+	 * NMIs will be claimed if arriving within that window.
 	 */
 	if (handled) {
-		this_cpu_write(perf_nmi_counter,
-			       min_t(unsigned int, 2, active));
+		this_cpu_write(perf_nmi_tstamp,
+			       jiffies + perf_nmi_window);
 
 		return handled;
 	}
 
-	if (!this_cpu_read(perf_nmi_counter))
+	if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp)))
 		return NMI_DONE;
 
-	this_cpu_dec(perf_nmi_counter);
-
 	return NMI_HANDLED;
 }
 
@@ -909,6 +910,9 @@ static int __init amd_core_pmu_init(void)
 	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
+	/* Avoid calulating the value each time in the NMI handler */
+	perf_nmi_window = msecs_to_jiffies(100);
+
 	switch (boot_cpu_data.x86) {
 	case 0x15:
 		pr_cont("Fam15h ");
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 27ee47a7be66..fcef678c3423 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4983,6 +4983,8 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_SKYLAKE:
 	case INTEL_FAM6_KABYLAKE_L:
 	case INTEL_FAM6_KABYLAKE:
+	case INTEL_FAM6_COMETLAKE_L:
+	case INTEL_FAM6_COMETLAKE:
 		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));
@@ -5031,6 +5033,8 @@ __init int intel_pmu_init(void)
 		/* fall through */
 	case INTEL_FAM6_ICELAKE_L:
 	case INTEL_FAM6_ICELAKE:
+	case INTEL_FAM6_TIGERLAKE_L:
+	case INTEL_FAM6_TIGERLAKE:
 		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));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f2f39003d96..e1daf4151e11 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -45,46 +45,49 @@
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
-						CNL
+ *						CNL,KBL,CML
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
- *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
+ *						ICL,TGL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
+ *						KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL
+ *						GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
+ *						KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,KBL,CNL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,KBL,CNL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *
  */
@@ -544,6 +547,19 @@ static const struct cstate_model cnl_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model icl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C7_RES) |
+				  BIT(PERF_CSTATE_PKG_C8_RES) |
+				  BIT(PERF_CSTATE_PKG_C9_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 static const struct cstate_model slm_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
@@ -614,6 +630,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE,   hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates),
 
@@ -625,8 +643,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b1afc77f0704..6f86650b3f77 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,7 +89,14 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_L:
 	case INTEL_FAM6_KABYLAKE:
+	case INTEL_FAM6_COMETLAKE_L:
+	case INTEL_FAM6_COMETLAKE:
 	case INTEL_FAM6_ICELAKE_L:
+	case INTEL_FAM6_ICELAKE:
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_D:
+	case INTEL_FAM6_TIGERLAKE_L:
+	case INTEL_FAM6_TIGERLAKE:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3f0cb82e4fbc..9ec0b0bfddbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3779,11 +3779,23 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event)
 	perf_event_groups_insert(&ctx->flexible_groups, event);
 }
 
+/* pick an event from the flexible_groups to rotate */
 static inline struct perf_event *
-ctx_first_active(struct perf_event_context *ctx)
+ctx_event_to_rotate(struct perf_event_context *ctx)
 {
-	return list_first_entry_or_null(&ctx->flexible_active,
-					struct perf_event, active_list);
+	struct perf_event *event;
+
+	/* pick the first active flexible event */
+	event = list_first_entry_or_null(&ctx->flexible_active,
+					 struct perf_event, active_list);
+
+	/* if no active flexible event, pick the first event */
+	if (!event) {
+		event = rb_entry_safe(rb_first(&ctx->flexible_groups.tree),
+				      typeof(*event), group_node);
+	}
+
+	return event;
 }
 
 static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
@@ -3808,9 +3820,9 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
 	if (task_rotate)
-		task_event = ctx_first_active(task_ctx);
+		task_event = ctx_event_to_rotate(task_ctx);
 	if (cpu_rotate)
-		cpu_event = ctx_first_active(&cpuctx->ctx);
+		cpu_event = ctx_event_to_rotate(&cpuctx->ctx);
 
 	/*
 	 * As per the order given at ctx_resched() first 'pop' task flexible
@@ -5668,7 +5680,8 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	 * undo the VM accounting.
 	 */
 
-	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked,
+			&mmap_user->locked_vm);
 	atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm);
 	free_uid(mmap_user);
 
@@ -5812,8 +5825,20 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
 
-	if (user_locked > user_lock_limit)
+	if (user_locked <= user_lock_limit) {
+		/* charge all to locked_vm */
+	} else if (atomic_long_read(&user->locked_vm) >= user_lock_limit) {
+		/* charge all to pinned_vm */
+		extra = user_extra;
+		user_extra = 0;
+	} else {
+		/*
+		 * charge locked_vm until it hits user_lock_limit;
+		 * charge the rest from pinned_vm
+		 */
 		extra = user_locked - user_lock_limit;
+		user_extra -= extra;
+	}
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
@@ -11862,6 +11887,10 @@ static int inherit_group(struct perf_event *parent_event,
 					    child, leader, child_ctx);
 		if (IS_ERR(child_ctr))
 			return PTR_ERR(child_ctr);
+
+		if (sub->aux_event == parent_event &&
+		    !perf_get_aux_event(child_ctr, leader))
+			return -EINVAL;
 	}
 	return 0;
 }
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a4217c1a5d01..2769360f195c 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -266,8 +266,10 @@ struct kvm_vcpu_events {
 #define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 9a507716ae2f..67c21f9bdbad 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -325,8 +325,10 @@ struct kvm_vcpu_events {
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 47104e5b47fd..436ec7636927 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -231,6 +231,12 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
 #define KVM_SYNC_ETOKEN (1UL << 11)
+
+#define KVM_SYNC_S390_VALID_FIELDS \
+	(KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \
+	 KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \
+	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN)
+
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..f01950aa7fae 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -31,6 +31,7 @@
 #define EXIT_REASON_EXCEPTION_NMI       0
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
+#define EXIT_REASON_INIT_SIGNAL			3
 
 #define EXIT_REASON_PENDING_INTERRUPT   7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -90,6 +91,7 @@
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
+	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
 	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 63b1f506ea67..c160a5354eb6 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -67,6 +67,9 @@
 #define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
 #define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
 
+#define MADV_COLD	20		/* deactivate these pages */
+#define MADV_PAGEOUT	21		/* reclaim these pages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 328d05e77d9f..469dc512cca3 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -521,6 +521,7 @@ typedef struct drm_i915_irq_wait {
 #define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
 #define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
 #define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
+#define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
 
 #define I915_PARAM_HUC_STATUS		 42
 
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 2a616aa3f686..379a612f8f1d 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -13,6 +13,9 @@
 #include <linux/limits.h>
 #include <linux/ioctl.h>
 #include <linux/types.h>
+#ifndef __KERNEL__
+#include <linux/fscrypt.h>
+#endif
 
 /* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
 #if !defined(__KERNEL__)
@@ -212,57 +215,6 @@ struct fsxattr {
 #define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
 #define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
 
-/*
- * File system encryption support
- */
-/* Policy provided via an ioctl on the topmost directory */
-#define FS_KEY_DESCRIPTOR_SIZE	8
-
-#define FS_POLICY_FLAGS_PAD_4		0x00
-#define FS_POLICY_FLAGS_PAD_8		0x01
-#define FS_POLICY_FLAGS_PAD_16		0x02
-#define FS_POLICY_FLAGS_PAD_32		0x03
-#define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAG_DIRECT_KEY	0x04	/* use master key directly */
-#define FS_POLICY_FLAGS_VALID		0x07
-
-/* Encryption algorithms */
-#define FS_ENCRYPTION_MODE_INVALID		0
-#define FS_ENCRYPTION_MODE_AES_256_XTS		1
-#define FS_ENCRYPTION_MODE_AES_256_GCM		2
-#define FS_ENCRYPTION_MODE_AES_256_CBC		3
-#define FS_ENCRYPTION_MODE_AES_256_CTS		4
-#define FS_ENCRYPTION_MODE_AES_128_CBC		5
-#define FS_ENCRYPTION_MODE_AES_128_CTS		6
-#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
-#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
-#define FS_ENCRYPTION_MODE_ADIANTUM		9
-
-struct fscrypt_policy {
-	__u8 version;
-	__u8 contents_encryption_mode;
-	__u8 filenames_encryption_mode;
-	__u8 flags;
-	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
-#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
-
-/* Parameters for passing an encryption key into the kernel keyring */
-#define FS_KEY_DESC_PREFIX		"fscrypt:"
-#define FS_KEY_DESC_PREFIX_SIZE		8
-
-/* Structure that userspace passes to the kernel keyring */
-#define FS_MAX_KEY_SIZE			64
-
-struct fscrypt_key {
-	__u32 mode;
-	__u8 raw[FS_MAX_KEY_SIZE];
-	__u32 size;
-};
-
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
  *
@@ -306,6 +258,7 @@ struct fscrypt_key {
 #define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
 #define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
 #define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_VERITY_FL			0x00100000 /* Verity protected inode */
 #define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
 #define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
 #define FS_NOCOW_FL			0x00800000 /* Do not cow file */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
new file mode 100644
index 000000000000..39ccfe9311c3
--- /dev/null
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * fscrypt user API
+ *
+ * These ioctls can be used on filesystems that support fscrypt.  See the
+ * "User API" section of Documentation/filesystems/fscrypt.rst.
+ */
+#ifndef _UAPI_LINUX_FSCRYPT_H
+#define _UAPI_LINUX_FSCRYPT_H
+
+#include <linux/types.h>
+
+/* Encryption policy flags */
+#define FSCRYPT_POLICY_FLAGS_PAD_4		0x00
+#define FSCRYPT_POLICY_FLAGS_PAD_8		0x01
+#define FSCRYPT_POLICY_FLAGS_PAD_16		0x02
+#define FSCRYPT_POLICY_FLAGS_PAD_32		0x03
+#define FSCRYPT_POLICY_FLAGS_PAD_MASK		0x03
+#define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
+#define FSCRYPT_POLICY_FLAGS_VALID		0x07
+
+/* Encryption algorithms */
+#define FSCRYPT_MODE_AES_256_XTS		1
+#define FSCRYPT_MODE_AES_256_CTS		4
+#define FSCRYPT_MODE_AES_128_CBC		5
+#define FSCRYPT_MODE_AES_128_CTS		6
+#define FSCRYPT_MODE_ADIANTUM			9
+#define __FSCRYPT_MODE_MAX			9
+
+/*
+ * Legacy policy version; ad-hoc KDF and no key verification.
+ * For new encrypted directories, use fscrypt_policy_v2 instead.
+ *
+ * Careful: the .version field for this is actually 0, not 1.
+ */
+#define FSCRYPT_POLICY_V1		0
+#define FSCRYPT_KEY_DESCRIPTOR_SIZE	8
+struct fscrypt_policy_v1 {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+};
+#define fscrypt_policy	fscrypt_policy_v1
+
+/*
+ * Process-subscribed "logon" key description prefix and payload format.
+ * Deprecated; prefer FS_IOC_ADD_ENCRYPTION_KEY instead.
+ */
+#define FSCRYPT_KEY_DESC_PREFIX		"fscrypt:"
+#define FSCRYPT_KEY_DESC_PREFIX_SIZE	8
+#define FSCRYPT_MAX_KEY_SIZE		64
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FSCRYPT_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * New policy version with HKDF and key verification (recommended).
+ */
+#define FSCRYPT_POLICY_V2		2
+#define FSCRYPT_KEY_IDENTIFIER_SIZE	16
+struct fscrypt_policy_v2 {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 __reserved[4];
+	__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */
+struct fscrypt_get_policy_ex_arg {
+	__u64 policy_size; /* input/output */
+	union {
+		__u8 version;
+		struct fscrypt_policy_v1 v1;
+		struct fscrypt_policy_v2 v2;
+	} policy; /* output */
+};
+
+/*
+ * v1 policy keys are specified by an arbitrary 8-byte key "descriptor",
+ * matching fscrypt_policy_v1::master_key_descriptor.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR	1
+
+/*
+ * v2 policy keys are specified by a 16-byte key "identifier" which the kernel
+ * calculates as a cryptographic hash of the key itself,
+ * matching fscrypt_policy_v2::master_key_identifier.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER	2
+
+/*
+ * Specifies a key, either for v1 or v2 policies.  This doesn't contain the
+ * actual key itself; this is just the "name" of the key.
+ */
+struct fscrypt_key_specifier {
+	__u32 type;	/* one of FSCRYPT_KEY_SPEC_TYPE_* */
+	__u32 __reserved;
+	union {
+		__u8 __reserved[32]; /* reserve some extra space */
+		__u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+		__u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+	} u;
+};
+
+/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
+struct fscrypt_add_key_arg {
+	struct fscrypt_key_specifier key_spec;
+	__u32 raw_size;
+	__u32 __reserved[9];
+	__u8 raw[];
+};
+
+/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */
+struct fscrypt_remove_key_arg {
+	struct fscrypt_key_specifier key_spec;
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY	0x00000001
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS	0x00000002
+	__u32 removal_status_flags;	/* output */
+	__u32 __reserved[5];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
+struct fscrypt_get_key_status_arg {
+	/* input */
+	struct fscrypt_key_specifier key_spec;
+	__u32 __reserved[6];
+
+	/* output */
+#define FSCRYPT_KEY_STATUS_ABSENT		1
+#define FSCRYPT_KEY_STATUS_PRESENT		2
+#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED	3
+	__u32 status;
+#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF   0x00000001
+	__u32 status_flags;
+	__u32 user_count;
+	__u32 __out_reserved[13];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT		_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY_EX		_IOWR('f', 22, __u8[9]) /* size + version */
+#define FS_IOC_ADD_ENCRYPTION_KEY		_IOWR('f', 23, struct fscrypt_add_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS	_IOWR('f', 25, struct fscrypt_remove_key_arg)
+#define FS_IOC_GET_ENCRYPTION_KEY_STATUS	_IOWR('f', 26, struct fscrypt_get_key_status_arg)
+
+/**********************************************************************/
+
+/* old names; don't add anything new here! */
+#ifndef __KERNEL__
+#define FS_KEY_DESCRIPTOR_SIZE		FSCRYPT_KEY_DESCRIPTOR_SIZE
+#define FS_POLICY_FLAGS_PAD_4		FSCRYPT_POLICY_FLAGS_PAD_4
+#define FS_POLICY_FLAGS_PAD_8		FSCRYPT_POLICY_FLAGS_PAD_8
+#define FS_POLICY_FLAGS_PAD_16		FSCRYPT_POLICY_FLAGS_PAD_16
+#define FS_POLICY_FLAGS_PAD_32		FSCRYPT_POLICY_FLAGS_PAD_32
+#define FS_POLICY_FLAGS_PAD_MASK	FSCRYPT_POLICY_FLAGS_PAD_MASK
+#define FS_POLICY_FLAG_DIRECT_KEY	FSCRYPT_POLICY_FLAG_DIRECT_KEY
+#define FS_POLICY_FLAGS_VALID		FSCRYPT_POLICY_FLAGS_VALID
+#define FS_ENCRYPTION_MODE_INVALID	0	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_XTS	FSCRYPT_MODE_AES_256_XTS
+#define FS_ENCRYPTION_MODE_AES_256_GCM	2	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CBC	3	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CTS	FSCRYPT_MODE_AES_256_CTS
+#define FS_ENCRYPTION_MODE_AES_128_CBC	FSCRYPT_MODE_AES_128_CBC
+#define FS_ENCRYPTION_MODE_AES_128_CTS	FSCRYPT_MODE_AES_128_CTS
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7	/* removed */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8	/* removed */
+#define FS_ENCRYPTION_MODE_ADIANTUM	FSCRYPT_MODE_ADIANTUM
+#define FS_KEY_DESC_PREFIX		FSCRYPT_KEY_DESC_PREFIX
+#define FS_KEY_DESC_PREFIX_SIZE		FSCRYPT_KEY_DESC_PREFIX_SIZE
+#define FS_MAX_KEY_SIZE			FSCRYPT_MAX_KEY_SIZE
+#endif /* !__KERNEL__ */
+
+#endif /* _UAPI_LINUX_FSCRYPT_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 5e3f12d5359e..233efbb1c81c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -243,6 +243,8 @@ struct kvm_hyperv_exit {
 #define KVM_INTERNAL_ERROR_SIMUL_EX	2
 /* Encounter unexpected vm-exit due to delivery event. */
 #define KVM_INTERNAL_ERROR_DELIVERY_EV	3
+/* Encounter unexpected vm-exit reason */
+#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -996,6 +998,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
index 78efe870c2b7..cf525cddeb94 100644
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -158,6 +158,7 @@ struct usbdevfs_hub_portinfo {
 #define USBDEVFS_CAP_MMAP			0x20
 #define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
 #define USBDEVFS_CAP_CONNINFO_EX		0x80
+#define USBDEVFS_CAP_SUSPEND			0x100
 
 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */
 
@@ -223,5 +224,8 @@ struct usbdevfs_streams {
  * extending size of the data returned.
  */
 #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
+#define USBDEVFS_FORBID_SUSPEND    _IO('U', 33)
+#define USBDEVFS_ALLOW_SUSPEND     _IO('U', 34)
+#define USBDEVFS_WAIT_FOR_RESUME   _IO('U', 35)
 
 #endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index ed61fb3a46c0..5b2cd5e58df0 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -20,7 +20,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libsubcmd.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -fPIC
+
+ifeq ($(DEBUG),0)
+  ifeq ($(feature-fortify-source), 1)
+    CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2
+  endif
+endif
 
 ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
diff --git a/tools/perf/Documentation/asciidoc.conf b/tools/perf/Documentation/asciidoc.conf
index 356b23a40339..2b62ba1e72b7 100644
--- a/tools/perf/Documentation/asciidoc.conf
+++ b/tools/perf/Documentation/asciidoc.conf
@@ -71,6 +71,9 @@ ifdef::backend-docbook[]
 [header]
 template::[header-declarations]
 <refentry>
+ifdef::perf_date[]
+<refentryinfo><date>{perf_date}</date></refentryinfo>
+endif::perf_date[]
 <refmeta>
 <refentrytitle>{mantitle}</refentrytitle>
 <manvolnum>{manvolnum}</manvolnum>
diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt
index 4c62b0713651..52152d156ad9 100644
--- a/tools/perf/Documentation/jitdump-specification.txt
+++ b/tools/perf/Documentation/jitdump-specification.txt
@@ -36,8 +36,8 @@ III/ Jitdump file header format
 Each jitdump file starts with a fixed size header containing the following fields in order:
 
 
-* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It is 0x4A695444 or 0x4454694a depending on the endianness. The field can be used to detect the endianness of the file
-* uint32_t version   : a 4-byte value representing the format version. It is currently set to 2
+* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It written is as 0x4A695444. The reader will detect an endian mismatch when it reads 0x4454694a.
+* uint32_t version   : a 4-byte value representing the format version. It is currently set to 1
 * uint32_t total_size: size in bytes of file header
 * uint32_t elf_mach  : ELF architecture encoding (ELF e_machine value as specified in /usr/include/elf.h)
 * uint32_t pad1      : padding. Reserved for future use
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index e1d4b484cc4b..2ff6cedeb9c5 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -37,7 +37,7 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 
 	arm = zalloc(sizeof(*arm));
 	if (!arm)
-		return -1;
+		return ENOMEM;
 
 #define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)"
 	err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED);
@@ -59,5 +59,5 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	regfree(&arm->call_insn);
 out_free_arm:
 	free(arm);
-	return -1;
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
 }
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 43aa93ed8414..037e292ecd8e 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -95,7 +95,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 
 	arm = zalloc(sizeof(*arm));
 	if (!arm)
-		return -1;
+		return ENOMEM;
 
 	/* bl, blr */
 	err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
@@ -118,5 +118,5 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	regfree(&arm->call_insn);
 out_free_arm:
 	free(arm);
-	return -1;
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
 }
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index b6b7bc7e31a1..3b4cdfc5efd6 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -30,7 +31,7 @@ get_cpuid(char *buffer, size_t sz)
 		buffer[nb-1] = '\0';
 		return 0;
 	}
-	return -1;
+	return ENOBUFS;
 }
 
 char *
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 89bb8f2c54ce..a50e70baf918 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -164,8 +164,10 @@ static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	if (!arch->initialized) {
 		arch->initialized = true;
 		arch->associate_instruction_ops = s390__associate_ins_ops;
-		if (cpuid)
-			err = s390__cpuid_parse(arch, cpuid);
+		if (cpuid) {
+			if (s390__cpuid_parse(arch, cpuid))
+				err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
+		}
 	}
 
 	return err;
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 8b0b018d896a..7933f6871c81 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -8,6 +8,7 @@
  */
 
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
@@ -54,7 +55,7 @@ int get_cpuid(char *buffer, size_t sz)
 
 	sysinfo = fopen(SYSINFO, "r");
 	if (sysinfo == NULL)
-		return -1;
+		return errno;
 
 	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
 		if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) {
@@ -89,7 +90,7 @@ int get_cpuid(char *buffer, size_t sz)
 
 	/* Missing manufacturer, type or model information should not happen */
 	if (!manufacturer[0] || !type[0] || !model[0])
-		return -1;
+		return EINVAL;
 
 	/*
 	 * Scan /proc/service_levels and return the CPU-MF counter facility
@@ -133,14 +134,14 @@ int get_cpuid(char *buffer, size_t sz)
 	else
 		nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type,
 				  model);
-	return (nbytes >= sz) ? -1 : 0;
+	return (nbytes >= sz) ? ENOBUFS : 0;
 }
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *buf = malloc(128);
 
-	if (buf && get_cpuid(buf, 128) < 0)
+	if (buf && get_cpuid(buf, 128))
 		zfree(&buf);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 44f5aba78210..7eb5621c021d 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -196,8 +196,10 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 	if (arch->initialized)
 		return 0;
 
-	if (cpuid)
-		err = x86__cpuid_parse(arch, cpuid);
+	if (cpuid) {
+		if (x86__cpuid_parse(arch, cpuid))
+			err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
+	}
 
 	arch->initialized = true;
 	return err;
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 662ecf84a421..aa6deb463bf3 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -58,7 +59,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 		buffer[nb-1] = '\0';
 		return 0;
 	}
-	return -1;
+	return ENOBUFS;
 }
 
 int
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 2227e2f42c09..58a9e0989491 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -705,14 +705,15 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
-	char buf[64], *cpuid;
+	char buf[128], *cpuid;
 	int err;
 
 	if (kvm->live) {
 		err = get_cpuid(buf, sizeof(buf));
 		if (err != 0) {
-			pr_err("Failed to look up CPU type\n");
-			return err;
+			pr_err("Failed to look up CPU type: %s\n",
+			       str_error_r(err, buf, sizeof(buf)));
+			return -err;
 		}
 		cpuid = buf;
 	} else
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 286fc70d7402..67be8d31afab 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1063,7 +1063,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			continue;
 
 		insn = 0;
-		for (off = 0;; off += ilen) {
+		for (off = 0; off < (unsigned)len; off += ilen) {
 			uint64_t ip = start + off;
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
@@ -1074,6 +1074,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 					printed += print_srccode(thread, x.cpumode, ip);
 				break;
 			} else {
+				ilen = 0;
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
 						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
 				if (ilen == 0)
@@ -1083,6 +1084,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				insn++;
 			}
 		}
+		if (off != (unsigned)len)
+			printed += fprintf(fp, "\tmismatch of LBR data and executable\n");
 	}
 
 	/*
@@ -1123,6 +1126,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		goto out;
 	}
 	for (off = 0; off <= end - start; off += ilen) {
+		ilen = 0;
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index e2e0f06c97d0..cea13cb987d0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -8,6 +8,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fadvise.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/fs.h
+include/uapi/linux/fscrypt.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/basic.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
similarity index 100%
rename from tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
rename to tools/perf/pmu-events/arch/s390/cf_z15/extended.json
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index bd3fc577139c..61641a3480e0 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -4,4 +4,4 @@ Family-model,Version,Filename,EventType
 ^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
-^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_m8561,core
+^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 9e37287da924..e2837260ca4d 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -450,12 +450,12 @@ static struct fixed {
 	const char *name;
 	const char *event;
 } fixed[] = {
-	{ "inst_retired.any", "event=0xc0" },
-	{ "inst_retired.any_p", "event=0xc0" },
-	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
-	{ "cpu_clk_unhalted.thread", "event=0x3c" },
-	{ "cpu_clk_unhalted.core", "event=0x3c" },
-	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
+	{ "inst_retired.any", "event=0xc0,period=2000003" },
+	{ "inst_retired.any_p", "event=0xc0,period=2000003" },
+	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03,period=2000003" },
+	{ "cpu_clk_unhalted.thread", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.core", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1,period=2000003" },
 	{ NULL, NULL},
 };
 
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index dbc27199c65e..dd865e0bea12 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -19,12 +19,11 @@ static void sigsegv_handler(int sig __maybe_unused)
 static void the_hook(void *_hook_flags)
 {
 	int *hook_flags = _hook_flags;
-	int *p = NULL;
 
 	*hook_flags = 1234;
 
 	/* Generate a segfault, test perf_hooks__recover */
-	*p = 0;
+	raise(SIGSEGV);
 }
 
 int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e830eadfca2a..4036c7f7b0fb 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1631,6 +1631,19 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
 	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
 		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
 		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+			  dso->long_name);
+		break;
 	default:
 		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
 		break;
@@ -1662,7 +1675,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 
 	build_id_path = strdup(filename);
 	if (!build_id_path)
-		return -1;
+		return ENOMEM;
 
 	/*
 	 * old style build-id cache has name of XX/XXXXXXX.. while
@@ -1713,13 +1726,13 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	char tpath[PATH_MAX];
 	size_t buf_size;
 	int nr_skip = 0;
-	int ret = -1;
 	char *buf;
 	bfd *bfdf;
+	int ret;
 	FILE *s;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
-		return -1;
+		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
 
 	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
 		  sym->name, sym->start, sym->end - sym->start);
@@ -1732,8 +1745,10 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	assert(bfd_check_format(bfdf, bfd_object));
 
 	s = open_memstream(&buf, &buf_size);
-	if (!s)
+	if (!s) {
+		ret = errno;
 		goto out;
+	}
 	init_disassemble_info(&info, s,
 			      (fprintf_ftype) fprintf);
 
@@ -1742,8 +1757,10 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 
 	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
 						 dso->bpf_prog.id);
-	if (!info_node)
+	if (!info_node) {
+		return SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
 		goto out;
+	}
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
@@ -2071,11 +2088,11 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 	int err;
 
 	if (!arch_name)
-		return -1;
+		return errno;
 
 	args.arch = arch = arch__find(arch_name);
 	if (arch == NULL)
-		return -ENOTSUP;
+		return ENOTSUP;
 
 	if (parch)
 		*parch = arch;
@@ -2971,7 +2988,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 
 	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
 	if (notes->offsets == NULL)
-		return -1;
+		return ENOMEM;
 
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
@@ -2997,7 +3014,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 
 out_free_offsets:
 	zfree(&notes->offsets);
-	return -1;
+	return err;
 }
 
 #define ANNOTATION__CFG(n) \
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index d94be9140e31..d76fd0e81f46 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -370,6 +370,10 @@ enum symbol_disassemble_errno {
 
 	SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX	= __SYMBOL_ANNOTATE_ERRNO__START,
 	SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP,
+	SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE,
+	SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF,
 
 	__SYMBOL_ANNOTATE_ERRNO__END,
 };
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5591af81a070..abc7fda4a0fe 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -30,6 +30,7 @@
 #include "counts.h"
 #include "event.h"
 #include "evsel.h"
+#include "util/env.h"
 #include "util/evsel_config.h"
 #include "util/evsel_fprintf.h"
 #include "evlist.h"
@@ -2512,7 +2513,7 @@ struct perf_env *perf_evsel__env(struct evsel *evsel)
 {
 	if (evsel && evsel->evlist)
 		return evsel->evlist->env;
-	return NULL;
+	return &perf_env;
 }
 
 static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 1bdf4c6ea3e5..e3ccb0ce1938 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -395,7 +395,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	size_t size;
 	u16 idr_size;
 	const char *sym;
-	uint32_t count;
+	uint64_t count;
 	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
@@ -418,7 +418,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 			jd->dir,
 			pid,
 			count);
@@ -529,7 +529,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 	         jd->dir,
 	         pid,
 		 jr->move.code_index);
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 8d04e3d070b1..8b14e4a7f1dc 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -233,14 +233,14 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *prefix_dir = "";
 	const char *suffix_dir = "";
 
+	/* _UTSNAME_LENGTH is 65 */
+	char release[128];
+
 	char *autoconf_path;
 
 	int err;
 
 	if (!test_dir) {
-		/* _UTSNAME_LENGTH is 65 */
-		char release[128];
-
 		err = fetch_kernel_version(NULL, release,
 					   sizeof(release));
 		if (err)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 5b83ed1ebbd6..eec9b282c047 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
+#include <assert.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -850,6 +851,8 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 53f31053a27a..02460362256d 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,6 +14,7 @@
 #include "thread_map.h"
 #include "trace-event.h"
 #include "mmap.h"
+#include "util/env.h"
 #include <internal/lib.h>
 #include "../perf-sys.h"
 
@@ -53,6 +54,11 @@ int parse_callchain_record(const char *arg __maybe_unused,
 	return 0;
 }
 
+/*
+ * Add this one here not to drag util/env.c
+ */
+struct perf_env perf_env;
+
 /*
  * Support debug printing even though util/debug.c is not linked.  That means
  * implementing 'verbose' and 'eprintf'.

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 14 Jul 2019 14:01:02 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/1d039859330b874d48080885eb31f4f129c246f1

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: e4557c1a46b0d32746bd309e1941914b5a6912b4 perf/x86/intel: Fix spurious NMI on fixed counter

A number of PMU driver corner case fixes, a race fix, an event grouping 
fix, plus a bunch of tooling fixes/updates.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf scripts python: export-to-postgresql.py: Fix DROP VIEW power_events_view
      perf scripts python: export-to-sqlite.py: Fix DROP VIEW power_events_view

Alexander Shishkin (1):
      perf/core: Fix exclusive events' grouping

Arnaldo Carvalho de Melo (9):
      perf inject: The tool->read() call may pass a NULL evsel, handle it
      perf evsel: perf_evsel__name(NULL) is valid, no need to check evsel
      perf tools: Add missing headers, mostly stdlib.h
      perf namespaces: Move the conditional setns() prototype to namespaces.h
      perf tools: Move get_current_dir_name() cond prototype out of util.h
      tools lib: Adopt zalloc()/zfree() from tools/perf
      perf tools: Use zfree() where applicable
      perf tools: Use list_del_init() more thorougly
      perf metricgroup: Add missing list_del_init() when flushing egroups list

Kan Liang (1):
      perf/x86/intel: Fix spurious NMI on fixed counter

Kim Phillips (2):
      perf/x86/amd/uncore: Do not set 'ThreadMask' and 'SliceMask' for non-L3 PMCs
      perf/x86/amd/uncore: Set the thread mask for F17h L3 PMCs

Leo Yan (10):
      perf stat: Fix use-after-freed pointer detected by the smatch tool
      perf top: Fix potential NULL pointer dereference detected by the smatch tool
      perf annotate: Fix dereferencing freed memory found by the smatch tool
      perf trace: Fix potential NULL pointer dereference found by the smatch tool
      perf map: Fix potential NULL pointer dereference found by smatch tool
      perf session: Fix potential NULL pointer dereference found by the smatch tool
      perf cs-etm: Fix potential NULL pointer dereference found by the smatch tool
      perf hists browser: Fix potential NULL pointer dereference found by the smatch tool
      perf intel-bts: Fix potential NULL pointer dereference found by the smatch tool
      perf intel-pt: Fix potential NULL pointer dereference found by the smatch tool

Luke Mujica (2):
      perf parse-events: Remove unused variable 'i'
      perf parse-events: Remove unused variable: error

Numfor Mbiziwo-Tiapo (1):
      perf test mmap-thread-lookup: Initialize variable to suppress memory sanitizer warning

Peter Zijlstra (1):
      perf/core: Fix race between close() and fork()

Song Liu (1):
      perf script: Assume native_arch for pipe mode


 arch/x86/events/amd/uncore.c                       | 15 ++--
 arch/x86/events/intel/core.c                       |  8 +--
 include/linux/perf_event.h                         |  5 ++
 kernel/events/core.c                               | 83 ++++++++++++++++------
 tools/include/linux/zalloc.h                       | 12 ++++
 tools/lib/zalloc.c                                 | 15 ++++
 tools/perf/MANIFEST                                |  1 +
 tools/perf/arch/arm/annotate/instructions.c        |  1 +
 tools/perf/arch/arm/util/auxtrace.c                |  1 +
 tools/perf/arch/arm/util/cs-etm.c                  |  1 +
 tools/perf/arch/arm64/util/arm-spe.c               |  1 +
 tools/perf/arch/common.c                           |  3 +-
 tools/perf/arch/powerpc/util/perf_regs.c           |  4 +-
 tools/perf/arch/s390/util/auxtrace.c               |  1 +
 tools/perf/arch/s390/util/header.c                 |  3 +-
 tools/perf/arch/x86/util/event.c                   |  2 +-
 tools/perf/arch/x86/util/intel-bts.c               |  2 +-
 tools/perf/arch/x86/util/intel-pt.c                |  2 +-
 tools/perf/arch/x86/util/perf_regs.c               |  2 +-
 tools/perf/bench/futex-hash.c                      |  3 +-
 tools/perf/bench/futex-lock-pi.c                   |  3 +-
 tools/perf/bench/mem-functions.c                   |  2 +-
 tools/perf/bench/numa.c                            |  2 +-
 tools/perf/builtin-annotate.c                      |  2 +-
 tools/perf/builtin-bench.c                         |  2 +-
 tools/perf/builtin-c2c.c                           |  2 +-
 tools/perf/builtin-config.c                        |  1 +
 tools/perf/builtin-diff.c                          |  2 +-
 tools/perf/builtin-ftrace.c                        |  2 +-
 tools/perf/builtin-help.c                          |  2 +
 tools/perf/builtin-inject.c                        |  2 +-
 tools/perf/builtin-kmem.c                          |  2 +-
 tools/perf/builtin-kvm.c                           |  2 +-
 tools/perf/builtin-lock.c                          | 10 +--
 tools/perf/builtin-probe.c                         |  2 +-
 tools/perf/builtin-record.c                        |  4 +-
 tools/perf/builtin-report.c                        |  4 +-
 tools/perf/builtin-sched.c                         |  2 +-
 tools/perf/builtin-script.c                        |  5 +-
 tools/perf/builtin-stat.c                          |  8 +--
 tools/perf/builtin-timechart.c                     |  4 +-
 tools/perf/builtin-top.c                           |  8 ++-
 tools/perf/builtin-trace.c                         |  7 +-
 tools/perf/perf.c                                  |  2 +-
 tools/perf/pmu-events/jevents.c                    |  2 +-
 tools/perf/scripts/python/export-to-postgresql.py  |  2 +-
 tools/perf/scripts/python/export-to-sqlite.py      |  2 +-
 tools/perf/tests/dwarf-unwind.c                    |  5 +-
 tools/perf/tests/expr.c                            |  3 +-
 tools/perf/tests/llvm.c                            |  1 +
 tools/perf/tests/mem2node.c                        |  3 +-
 tools/perf/tests/mmap-thread-lookup.c              |  2 +-
 tools/perf/tests/sample-parsing.c                  |  1 +
 tools/perf/tests/switch-tracking.c                 |  3 +-
 tools/perf/tests/thread-map.c                      |  3 +-
 tools/perf/tests/vmlinux-kallsyms.c                |  1 +
 tools/perf/ui/browser.c                            |  2 +-
 tools/perf/ui/browser.h                            |  1 +
 tools/perf/ui/browsers/annotate.c                  |  2 +-
 tools/perf/ui/browsers/hists.c                     | 17 +++--
 tools/perf/ui/browsers/map.c                       |  1 +
 tools/perf/ui/browsers/res_sample.c                |  6 +-
 tools/perf/ui/browsers/scripts.c                   |  4 +-
 tools/perf/ui/gtk/annotate.c                       |  2 +-
 tools/perf/ui/gtk/util.c                           |  3 +-
 tools/perf/ui/stdio/hist.c                         |  2 +-
 tools/perf/ui/tui/setup.c                          |  1 +
 tools/perf/ui/tui/util.c                           |  2 +-
 tools/perf/util/Build                              |  5 ++
 tools/perf/util/annotate.c                         | 13 ++--
 tools/perf/util/arm-spe.c                          |  2 +-
 tools/perf/util/auxtrace.c                         | 11 ++-
 tools/perf/util/bpf-loader.c                       |  3 +-
 tools/perf/util/build-id.c                         |  1 +
 tools/perf/util/call-path.c                        |  5 +-
 tools/perf/util/callchain.c                        | 12 ++--
 tools/perf/util/cgroup.c                           |  4 +-
 tools/perf/util/comm.c                             |  2 +-
 tools/perf/util/config.c                           |  3 +-
 tools/perf/util/counts.c                           |  2 +-
 tools/perf/util/cpumap.c                           |  2 +-
 tools/perf/util/cputopo.c                          |  5 +-
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c    |  1 +
 tools/perf/util/cs-etm.c                           |  8 +--
 tools/perf/util/data-convert-bt.c                  |  4 +-
 tools/perf/util/data.c                             |  3 +-
 tools/perf/util/db-export.c                        |  7 +-
 tools/perf/util/debug.c                            |  1 +
 tools/perf/util/demangle-java.c                    |  3 +-
 tools/perf/util/dso.c                              |  5 +-
 tools/perf/util/dwarf-aux.c                        |  2 +-
 tools/perf/util/env.c                              | 11 +--
 tools/perf/util/event.c                            |  3 +-
 tools/perf/util/evlist.c                           |  2 +-
 tools/perf/util/evsel.c                            |  4 +-
 tools/perf/util/get_current_dir_name.c             |  6 +-
 tools/perf/util/get_current_dir_name.h             |  8 +++
 tools/perf/util/header.c                           |  8 +--
 tools/perf/util/help-unknown-cmd.c                 |  2 +
 tools/perf/util/hist.c                             | 20 +++---
 tools/perf/util/intel-bts.c                        |  7 +-
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  |  2 +-
 tools/perf/util/intel-pt.c                         | 15 ++--
 tools/perf/util/jitdump.c                          |  7 +-
 tools/perf/util/llvm-utils.c                       |  4 +-
 tools/perf/util/machine.c                          |  6 +-
 tools/perf/util/map.c                              |  9 ++-
 tools/perf/util/mem2node.c                         |  2 +-
 tools/perf/util/metricgroup.c                      | 10 +--
 tools/perf/util/mmap.c                             |  1 +
 tools/perf/util/namespaces.c                       |  3 +-
 tools/perf/util/namespaces.h                       |  4 ++
 tools/perf/util/ordered-events.c                   |  6 +-
 tools/perf/util/parse-branch-options.c             |  2 +-
 tools/perf/util/parse-events.c                     |  3 +-
 tools/perf/util/parse-events.y                     |  2 -
 tools/perf/util/parse-regs-options.c               |  8 ++-
 tools/perf/util/pmu.c                              |  4 +-
 tools/perf/util/probe-event.c                      | 55 +++++++-------
 tools/perf/util/probe-file.c                       |  2 +-
 tools/perf/util/probe-finder.c                     |  2 +-
 tools/perf/util/pstack.c                           |  2 +-
 tools/perf/util/python-ext-sources                 |  1 +
 tools/perf/util/s390-cpumsf.c                      | 11 ++-
 tools/perf/util/session.c                          |  7 +-
 tools/perf/util/setns.c                            |  4 +-
 tools/perf/util/srccode.c                          | 11 +--
 tools/perf/util/srcline.c                          |  2 +-
 tools/perf/util/stat-shadow.c                      |  3 +-
 tools/perf/util/stat.c                             |  3 +-
 tools/perf/util/strbuf.c                           |  3 +-
 tools/perf/util/strfilter.c                        |  3 +-
 tools/perf/util/strlist.c                          |  2 +-
 tools/perf/util/svghelper.c                        |  2 +-
 tools/perf/util/symbol-elf.c                       | 18 ++---
 tools/perf/util/symbol-minimal.c                   |  3 +-
 tools/perf/util/symbol.c                           |  1 +
 tools/perf/util/syscalltbl.c                       |  2 +-
 tools/perf/util/target.c                           |  2 +-
 tools/perf/util/thread-stack.c                     |  3 +-
 tools/perf/util/thread.c                           |  6 +-
 tools/perf/util/thread_map.c                       |  4 +-
 tools/perf/util/trace-event-info.c                 |  1 +
 tools/perf/util/trace-event-scripting.c            |  2 +-
 tools/perf/util/unwind-libdw.c                     |  1 +
 tools/perf/util/unwind-libunwind-local.c           |  3 +-
 tools/perf/util/usage.c                            |  3 +
 tools/perf/util/util.h                             | 17 -----
 tools/perf/util/values.c                           |  2 +-
 tools/perf/util/vdso.c                             |  1 +
 tools/perf/util/xyarray.c                          |  2 +-
 151 files changed, 457 insertions(+), 308 deletions(-)
 create mode 100644 tools/include/linux/zalloc.h
 create mode 100644 tools/lib/zalloc.c
 create mode 100644 tools/perf/util/get_current_dir_name.h

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 29 Jun 2019 10:54:39 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/57103eb7c6cad04c0611b7a5767a381b34b8b0ab

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 8b12b812f5367c2469fb937da7e28dd321ad8d7b perf/x86/regs: Use PERF_REG_EXTENDED_MASK

Various fixes, most of them related to bugs perf fuzzing found in the x86 
code.

 Thanks,

	Ingo

------------------>
Kan Liang (5):
      perf/x86: Disable extended registers for non-supported PMUs
      perf/x86/regs: Check reserved bits
      perf/x86: Clean up PEBS_XMM_REGS
      perf/x86: Remove pmu->pebs_no_xmm_regs
      perf/x86/regs: Use PERF_REG_EXTENDED_MASK

Peter Zijlstra (1):
      perf/core: Fix perf_sample_regs_user() mm check

Ravi Bangoria (1):
      perf/ioctl: Add check for the sample_period value


 arch/x86/events/core.c                      |  6 +++---
 arch/x86/events/intel/ds.c                  |  9 ++++-----
 arch/x86/events/perf_event.h                | 21 +--------------------
 arch/x86/include/uapi/asm/perf_regs.h       |  3 +++
 arch/x86/kernel/perf_regs.c                 |  7 +++++--
 include/linux/perf_event.h                  |  1 +
 include/linux/perf_regs.h                   |  8 ++++++++
 kernel/events/core.c                        | 23 ++++++++++++++++++-----
 tools/arch/x86/include/uapi/asm/perf_regs.h |  3 +++
 tools/perf/arch/x86/include/perf_regs.h     |  1 -
 tools/perf/arch/x86/util/perf_regs.c        |  4 ++--
 11 files changed, 48 insertions(+), 38 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f315425d8468..52a97463cb24 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -561,14 +561,14 @@ int x86_pmu_hw_config(struct perf_event *event)
 	}
 
 	/* sample_regs_user never support XMM registers */
-	if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+	if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK))
 		return -EINVAL;
 	/*
 	 * Besides the general purpose registers, XMM registers may
 	 * be collected in PEBS on some platforms, e.g. Icelake
 	 */
-	if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
-		if (x86_pmu.pebs_no_xmm_regs)
+	if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) {
+		if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS))
 			return -EINVAL;
 
 		if (!event->attr.precise_ip)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7acc526b4ad2..505c73dc6a73 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -987,7 +987,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 		pebs_data_cfg |= PEBS_DATACFG_GP;
 
 	if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
-	    (attr->sample_regs_intr & PEBS_XMM_REGS))
+	    (attr->sample_regs_intr & PERF_REG_EXTENDED_MASK))
 		pebs_data_cfg |= PEBS_DATACFG_XMMS;
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -1964,10 +1964,9 @@ 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) {
+	if (x86_pmu.version <= 4)
 		x86_pmu.pebs_no_isolation = 1;
-		x86_pmu.pebs_no_xmm_regs = 1;
-	}
+
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		char *pebs_qual = "";
@@ -2020,9 +2019,9 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
 				pebs_qual = "-baseline";
+				x86_get_pmu()->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
 				/* Only basic record supported */
-				x86_pmu.pebs_no_xmm_regs = 1;
 				x86_pmu.large_pebs_flags &=
 					~(PERF_SAMPLE_ADDR |
 					  PERF_SAMPLE_TIME |
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a6ac2f4f76fc..4e346856ee19 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -121,24 +121,6 @@ struct amd_nb {
 	 (1ULL << PERF_REG_X86_R14)   | \
 	 (1ULL << PERF_REG_X86_R15))
 
-#define PEBS_XMM_REGS                   \
-	((1ULL << PERF_REG_X86_XMM0)  | \
-	 (1ULL << PERF_REG_X86_XMM1)  | \
-	 (1ULL << PERF_REG_X86_XMM2)  | \
-	 (1ULL << PERF_REG_X86_XMM3)  | \
-	 (1ULL << PERF_REG_X86_XMM4)  | \
-	 (1ULL << PERF_REG_X86_XMM5)  | \
-	 (1ULL << PERF_REG_X86_XMM6)  | \
-	 (1ULL << PERF_REG_X86_XMM7)  | \
-	 (1ULL << PERF_REG_X86_XMM8)  | \
-	 (1ULL << PERF_REG_X86_XMM9)  | \
-	 (1ULL << PERF_REG_X86_XMM10) | \
-	 (1ULL << PERF_REG_X86_XMM11) | \
-	 (1ULL << PERF_REG_X86_XMM12) | \
-	 (1ULL << PERF_REG_X86_XMM13) | \
-	 (1ULL << PERF_REG_X86_XMM14) | \
-	 (1ULL << PERF_REG_X86_XMM15))
-
 /*
  * Per register state.
  */
@@ -668,8 +650,7 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1,
-			pebs_no_xmm_regs	:1;
+			pebs_no_isolation	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	int		max_pebs_events;
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index ac67bbea10ca..7c9d2bb3833b 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -52,4 +52,7 @@ enum perf_event_x86_regs {
 	/* These include both GPRs and XMMX registers */
 	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
+
+#define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
+
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 07c30ee17425..bb7e1132290b 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -74,6 +74,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
+#define PERF_REG_X86_RESERVED	(((1ULL << PERF_REG_X86_XMM0) - 1) & \
+				 ~((1ULL << PERF_REG_X86_MAX) - 1))
+
 #ifdef CONFIG_X86_32
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
 		       (1ULL << PERF_REG_X86_R9) | \
@@ -86,7 +89,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & REG_NOSUPPORT))
+	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
 		return -EINVAL;
 
 	return 0;
@@ -112,7 +115,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & REG_NOSUPPORT))
+	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
 		return -EINVAL;
 
 	return 0;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0ab99c7b652d..2bca72f3028b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -241,6 +241,7 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_NO_NMI			0x02
 #define PERF_PMU_CAP_AUX_NO_SG			0x04
+#define PERF_PMU_CAP_EXTENDED_REGS		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 476747456bca..2d12e97d5e7b 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -11,6 +11,11 @@ struct perf_regs {
 
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
+
+#ifndef PERF_REG_EXTENDED_MASK
+#define PERF_REG_EXTENDED_MASK	0
+#endif
+
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
@@ -18,6 +23,9 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 			struct pt_regs *regs,
 			struct pt_regs *regs_user_copy);
 #else
+
+#define PERF_REG_EXTENDED_MASK	0
+
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
 	return 0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index abbd4b3b96c2..f85929ce13be 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5005,6 +5005,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (perf_event_check_period(event, value))
 		return -EINVAL;
 
+	if (!event->attr.freq && (value & (1ULL << 63)))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -5923,7 +5926,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
-	} else if (current->mm) {
+	} else if (!(current->flags & PF_KTHREAD)) {
 		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
@@ -10033,6 +10036,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
+static inline bool has_extended_regs(struct perf_event *event)
+{
+	return (event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK) ||
+	       (event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK);
+}
+
 static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 {
 	struct perf_event_context *ctx = NULL;
@@ -10064,12 +10073,16 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 		perf_event_ctx_unlock(event->group_leader, ctx);
 
 	if (!ret) {
+		if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) &&
+		    has_extended_regs(event))
+			ret = -EOPNOTSUPP;
+
 		if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE &&
-				event_has_any_exclude_flag(event)) {
-			if (event->destroy)
-				event->destroy(event);
+		    event_has_any_exclude_flag(event))
 			ret = -EINVAL;
-		}
+
+		if (ret && event->destroy)
+			event->destroy(event);
 	}
 
 	if (ret)
diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
index ac67bbea10ca..7c9d2bb3833b 100644
--- a/tools/arch/x86/include/uapi/asm/perf_regs.h
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -52,4 +52,7 @@ enum perf_event_x86_regs {
 	/* These include both GPRs and XMMX registers */
 	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
+
+#define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
+
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index b7cd91a9014f..b7321337d100 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -9,7 +9,6 @@
 void perf_regs_load(u64 *regs);
 
 #define PERF_REGS_MAX PERF_REG_X86_XMM_MAX
-#define PERF_XMM_REGS_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
 #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 7886ca5263e3..3666c0076df9 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -277,7 +277,7 @@ uint64_t arch__intr_reg_mask(void)
 		.type			= PERF_TYPE_HARDWARE,
 		.config			= PERF_COUNT_HW_CPU_CYCLES,
 		.sample_type		= PERF_SAMPLE_REGS_INTR,
-		.sample_regs_intr	= PERF_XMM_REGS_MASK,
+		.sample_regs_intr	= PERF_REG_EXTENDED_MASK,
 		.precise_ip		= 1,
 		.disabled 		= 1,
 		.exclude_kernel		= 1,
@@ -293,7 +293,7 @@ uint64_t arch__intr_reg_mask(void)
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 	if (fd != -1) {
 		close(fd);
-		return (PERF_XMM_REGS_MASK | PERF_REGS_MASK);
+		return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK);
 	}
 
 	return PERF_REGS_MASK;

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 2 Jun 2019 19:39:53 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/6751b8d91af515a5dc5196fe305eee0a635e2ea2

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 849e96f30068d4f6f8352715e02a10533a46deba Merge tag 'perf-urgent-for-mingo-5.2-20190528' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

On the kernel side there's a bunch of ring-buffer ordering fixes for a 
reproducible bug, plus a PEBS constraints regression fix - plus tooling 
fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (8):
      tools include UAPI: Update copy of files related to new fspick, fsmount, fsconfig, fsopen, move_mount and open_tree syscalls
      tools arch x86: Sync asm/cpufeatures.h with the with the kernel
      tools headers UAPI: Sync linux/sched.h with the kernel
      tools headers UAPI: Sync linux/fs.h with the kernel
      tools headers UAPI: Sync drm/i915_drm.h with the kernel
      tools headers UAPI: Sync drm/drm.h with the kernel
      perf test vmlinux-kallsyms: Ignore aliases to _etext when searching on kallsyms
      tools headers UAPI: Sync kvm.h headers with the kernel sources

Jiri Olsa (1):
      perf machine: Read also the end of the kernel

Namhyung Kim (2):
      perf namespace: Protect reading thread's namespace
      perf session: Add missing swap ops for namespace events

Peter Zijlstra (3):
      perf/ring_buffer: Add ordering to rb->nest increment
      perf/ring-buffer: Always use {READ,WRITE}_ONCE() for rb->user_page data
      perf/ring-buffer: Use regular variables for nesting

Shawn Landden (1):
      perf data: Fix 'strncat may truncate' build failure with recent gcc

Stephane Eranian (1):
      perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints

Thomas Richter (1):
      perf record: Fix s390 missing module symbol and warning for non-root users

Vitaly Chikunov (1):
      perf arm64: Fix mksyscalltbl when system kernel headers are ahead of the kernel

Yabin Cui (1):
      perf/ring_buffer: Fix exposing a temporarily decreased data_head


 arch/x86/events/intel/ds.c                        |  28 +--
 kernel/events/internal.h                          |   4 +-
 kernel/events/ring_buffer.c                       |  64 ++++--
 tools/arch/arm64/include/uapi/asm/kvm.h           |  43 ++++
 tools/arch/powerpc/include/uapi/asm/kvm.h         |  46 ++++
 tools/arch/s390/include/uapi/asm/kvm.h            |   4 +-
 tools/arch/x86/include/asm/cpufeatures.h          |   3 +
 tools/include/uapi/asm-generic/unistd.h           |  14 +-
 tools/include/uapi/drm/drm.h                      |  37 ++++
 tools/include/uapi/drm/i915_drm.h                 | 254 +++++++++++++++-------
 tools/include/uapi/linux/fcntl.h                  |   2 +
 tools/include/uapi/linux/fs.h                     |   3 +
 tools/include/uapi/linux/kvm.h                    |  15 +-
 tools/include/uapi/linux/mount.h                  |  62 ++++++
 tools/include/uapi/linux/sched.h                  |   1 +
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl |   2 +-
 tools/perf/arch/s390/util/machine.c               |   9 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl |   6 +
 tools/perf/tests/vmlinux-kallsyms.c               |   9 +-
 tools/perf/util/data-convert-bt.c                 |   2 +-
 tools/perf/util/machine.c                         |  27 ++-
 tools/perf/util/session.c                         |  21 ++
 tools/perf/util/thread.c                          |  15 +-
 23 files changed, 547 insertions(+), 124 deletions(-)

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 5 May 2019 14:47:46 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/7178fb0b239d1c037876301c116fc9a6c1bd2ac0

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 6f55967ad9d9752813e36de6d5fdbd19741adfc7 perf/x86/intel: Fix race in intel_pmu_disable_event()

I'd like to apologize for this very late pull request: I was dithering 
through the week whether to send the fixes, and then yesterday Jiri's 
crash fix for a regression introduced in this cycle clearly marked 
perf/urgent as 'must merge now'.

Most of the commits are tooling fixes, plus there's three kernel fixes 
via four commits:

 - race fix in the Intel PEBS code
 - fix an AUX bug and roll back a previous attempt
 - fix AMD family 17h generic HW cache-event perf  counters

The largest diffstat contribution comes from the AMD fix - a new event 
table is introduced, which is a fairly low risk change but has a large 
linecount.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (2):
      perf/ring_buffer: Fix AUX software double buffering
      perf/x86/intel/pt: Remove software double buffering PMU capability

Arnaldo Carvalho de Melo (5):
      tools uapi x86: Sync vmx.h with the kernel
      perf bench numa: Add define for RUSAGE_THREAD if not present
      tools build: Add -ldl to the disassembler-four-args feature test
      tools arch uapi: Copy missing unistd.h headers for arc, hexagon and riscv
      perf tools: Remove needless asm/unistd.h include fixing build in some places

Bo YU (1):
      perf bpf: Return value with unlocking in perf_env__find_btf()

Jiri Olsa (1):
      perf/x86/intel: Fix race in intel_pmu_disable_event()

Kim Phillips (2):
      perf/x86/amd: Update generic hardware cache events for Family 17h
      MAINTAINERS: Include vendor specific files under arch/*/events/*

Leo Yan (3):
      tools lib traceevent: Change tag string for error
      perf cs-etm: Don't check cs_etm_queue::prev_packet validity
      perf cs-etm: Always allocate memory for cs_etm_queue::prev_packet

Thadeu Lima de Souza Cascardo (1):
      perf annotate: Fix build on 32 bit for BPF annotation

Thomas Richter (1):
      perf report: Report OOM in status line in the GTK UI


 MAINTAINERS                                  |   1 +
 arch/x86/events/amd/core.c                   | 111 ++++++++++++++++++++++++++-
 arch/x86/events/intel/core.c                 |  10 ++-
 arch/x86/events/intel/pt.c                   |   3 +-
 include/linux/perf_event.h                   |   1 -
 kernel/events/ring_buffer.c                  |   3 +-
 tools/arch/arc/include/uapi/asm/unistd.h     |  51 ++++++++++++
 tools/arch/hexagon/include/uapi/asm/unistd.h |  40 ++++++++++
 tools/arch/riscv/include/uapi/asm/unistd.h   |  42 ++++++++++
 tools/arch/x86/include/uapi/asm/vmx.h        |   1 +
 tools/lib/traceevent/parse-utils.c           |   2 +-
 tools/perf/Makefile.config                   |   2 +-
 tools/perf/bench/numa.c                      |   4 +
 tools/perf/util/annotate.c                   |   8 +-
 tools/perf/util/cloexec.c                    |   1 -
 tools/perf/util/cs-etm.c                     |  14 +---
 tools/perf/util/env.c                        |   2 +-
 tools/perf/util/session.c                    |   8 +-
 18 files changed, 272 insertions(+), 32 deletions(-)
 create mode 100644 tools/arch/arc/include/uapi/asm/unistd.h
 create mode 100644 tools/arch/hexagon/include/uapi/asm/unistd.h
 create mode 100644 tools/arch/riscv/include/uapi/asm/unistd.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 5c38f21aee78..3a15b6d7584e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12176,6 +12176,7 @@ F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
 F:	arch/*/kernel/perf_callchain.c
 F:	arch/*/events/*
+F:	arch/*/events/*/*
 F:	tools/perf/
 
 PERSONALITY HANDLING
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index d45f3fbd232e..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -116,6 +116,110 @@ static __initconst const u64 amd_hw_cache_event_ids
  },
 };
 
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+		[C(RESULT_MISS)]   = 0xc860, /* L2$ access from DC Miss */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches  */
+		[C(RESULT_MISS)]   = 0x0081, /* Instruction cache misses   */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+		[C(RESULT_MISS)]   = 0xf045, /* L2 DTLB misses (PT walks) */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+		[C(RESULT_MISS)]   = 0xff85, /* L1 ITLB misses, L2 misses */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr.      */
+		[C(RESULT_MISS)]   = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+};
+
 /*
  * AMD Performance Monitor K7 and later, up to and including Family 16h:
  */
@@ -865,9 +969,10 @@ __init int amd_pmu_init(void)
 		x86_pmu.amd_nb_constraints = 0;
 	}
 
-	/* Events are common for all AMDs */
-	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
-	       sizeof(hw_cache_event_ids));
+	if (boot_cpu_data.x86 >= 0x17)
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+	else
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 
 	return 0;
 }
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f9451566cd9b..d35f4775d5f1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2091,15 +2091,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
+
+	/*
+	 * Needs to be called after x86_pmu_disable_event,
+	 * so we don't trigger the event without PEBS bit set.
+	 */
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fb3a2f13fc70..339d7628080c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1525,8 +1525,7 @@ static __init int pt_init(void)
 	}
 
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
-		pt_pmu.pmu.capabilities =
-			PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
 
 	pt_pmu.pmu.capabilities	|= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
 	pt_pmu.pmu.attr_groups		 = pt_attr_groups;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e47ef764f613..1f678f023850 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -240,7 +240,6 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_NO_NMI			0x02
 #define PERF_PMU_CAP_AUX_NO_SG			0x04
-#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5eedb49a65ea..674b35383491 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -610,8 +610,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 	 * PMU requests more than one contiguous chunks of memory
 	 * for SW double buffering
 	 */
-	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
-	    !overwrite) {
+	if (!overwrite) {
 		if (!max_order)
 			return -EINVAL;
 
diff --git a/tools/arch/arc/include/uapi/asm/unistd.h b/tools/arch/arc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5eafa1115162
--- /dev/null
+++ b/tools/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
+#define _UAPI_ASM_ARC_UNISTD_H
+
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls	__NR_syscalls
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
+/* ARC specific syscall */
+#define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#undef __SYSCALL
+
+#endif
diff --git a/tools/arch/hexagon/include/uapi/asm/unistd.h b/tools/arch/hexagon/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..432c4db1b623
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/unistd.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Syscall support for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+/*
+ *  The kernel pulls this unistd.h in three different ways:
+ *  1.  the "normal" way which gets all the __NR defines
+ *  2.  with __SYSCALL defined to produce function declarations
+ *  3.  with __SYSCALL defined to produce syscall table initialization
+ *  See also:  syscalltab.c
+ */
+
+#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/riscv/include/uapi/asm/unistd.h b/tools/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..0e2eeeb1fd27
--- /dev/null
+++ b/tools/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef __LP64__
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
+#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index 77e4ec6402dd..e99867111387 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -14,7 +14,7 @@
 void __vwarning(const char *fmt, va_list ap)
 {
 	if (errno)
-		perror("trace-cmd");
+		perror("libtraceevent");
 	errno = 0;
 
 	fprintf(stderr, "  ");
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fe3f97e342fa..6d65874e16c3 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -227,7 +227,7 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
-FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 98ad783efc69..a7784554a80d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -39,6 +39,10 @@
 #include <numa.h>
 #include <numaif.h>
 
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
 /*
  * Regular printout to the terminal, supressed if -q is specified:
  */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index c8b01176c9e1..09762985c713 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1714,8 +1714,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return -1;
 
-	pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
-		 sym->name, sym->start, sym->end - sym->start);
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
 
 	memset(tpath, 0, sizeof(tpath));
 	perf_exe(tpath, sizeof(tpath));
@@ -1740,7 +1740,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
-	info.buffer = (void *)(info_linear->info.jited_prog_insns);
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
 	info.buffer_length = info_linear->info.jited_prog_len;
 
 	if (info_linear->info.nr_line_info)
@@ -1776,7 +1776,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		const char *srcline;
 		u64 addr;
 
-		addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
 		count = disassemble(pc, &info);
 
 		if (prog_linfo)
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index ca0fff6272be..06f48312c5ed 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,7 +7,6 @@
 #include "asm/bug.h"
 #include "debug.h"
 #include <unistd.h>
-#include <asm/unistd.h>
 #include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 110804936fc3..de488b43f440 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -422,11 +422,9 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
 	if (!etmq->packet)
 		goto out_free;
 
-	if (etm->synth_opts.last_branch || etm->sample_branches) {
-		etmq->prev_packet = zalloc(szp);
-		if (!etmq->prev_packet)
-			goto out_free;
-	}
+	etmq->prev_packet = zalloc(szp);
+	if (!etmq->prev_packet)
+		goto out_free;
 
 	if (etm->synth_opts.last_branch) {
 		size_t sz = sizeof(struct branch_stack);
@@ -981,7 +979,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 	 * PREV_PACKET is a branch.
 	 */
 	if (etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
 	    etmq->prev_packet->last_instr_taken_branch)
 		cs_etm__update_last_branch_rb(etmq);
@@ -1014,7 +1011,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches && etmq->prev_packet) {
+	if (etm->sample_branches) {
 		bool generate_sample = false;
 
 		/* Generate sample for tracing on packet */
@@ -1071,9 +1068,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
-	if (!etmq->prev_packet)
-		return 0;
-
 	/* Handle start tracing packet */
 	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
 		goto swap_packet;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9494f9dc61ec..6a3eaf7d9353 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -115,8 +115,8 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 	}
 	node = NULL;
 
-	up_read(&env->bpf_progs.lock);
 out:
+	up_read(&env->bpf_progs.lock);
 	return node;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b17f1c9bc965..bad5f87ae001 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1928,12 +1928,14 @@ reader__process_events(struct reader *rd, struct perf_session *session,
 
 	size = event->header.size;
 
+	skip = -EINVAL;
+
 	if (size < sizeof(struct perf_event_header) ||
 	    (skip = rd->process(session, event, file_pos)) < 0) {
-		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       file_offset + head, event->header.size,
-		       event->header.type);
-		err = -EINVAL;
+		       event->header.type, strerror(-skip));
+		err = skip;
 		goto out;
 	}
 

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 20 Apr 2019 09:43:53 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b25c69b9d5e41159b54ad7cb33f7d9ead8523d33

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7579dfc42d2e3bef901991803efc81dc1ac65f2b Merge tag 'perf-urgent-for-mingo-5.1-20190419' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc fixes:

 - various tooling fixes
 - kretprobe fixes
 - kprobes annotation fixes
 - kprobes error checking fix
 - fix the default events for AMD Family 17h CPUs
 - PEBS fix
 - AUX record fix
 - address filtering fix

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf scripts python: export-to-sqlite.py: Fix use of parent_id in calls_view

Alexander Shishkin (2):
      perf/core: Fix the address filtering fix
      perf/ring_buffer: Fix AUX record suppression

Arnaldo Carvalho de Melo (1):
      tools include uapi: Sync sound/asound.h copy

Gustavo A. R. Silva (1):
      perf header: Fix lock/unlock imbalances when processing BPF/BTF info

Jiri Olsa (6):
      perf stat: Disable DIR_FORMAT feature for 'perf stat record'
      perf top: Always sample time to satisfy needs of use of ordered queuing
      perf bpf: Return NULL when RB tree lookup fails in perf_env__find_bpf_prog_info()
      perf evlist: Fix side band thread draining
      perf tools: Fix map reference counting
      perf bpf: Return NULL when RB tree lookup fails in perf_env__find_btf()

Kan Liang (1):
      perf/x86: Fix incorrect PEBS_REGS

Kim Phillips (1):
      perf/x86/amd: Add event map for AMD Family 17h

Mao Han (1):
      perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user)

Masami Hiramatsu (4):
      kprobes: Fix error check when reusing optimized probes
      x86/kprobes: Verify stack frame on kretprobe
      kprobes: Mark ftrace mcount handler functions nokprobe
      x86/kprobes: Avoid kretprobe recursion bug

Rikard Falkeborn (1):
      tools lib traceevent: Fix missing equality check for strcmp

Song Liu (1):
      perf tools: Check maps for bpf programs


 arch/x86/events/amd/core.c                    | 35 ++++++++++++++-----
 arch/x86/events/intel/core.c                  |  2 +-
 arch/x86/events/perf_event.h                  | 38 ++++++++++-----------
 arch/x86/kernel/kprobes/core.c                | 48 +++++++++++++++++++++++++--
 include/linux/kprobes.h                       |  1 +
 kernel/events/core.c                          | 37 ++++++++++++---------
 kernel/events/ring_buffer.c                   | 33 +++++++++---------
 kernel/kprobes.c                              |  6 ++--
 kernel/trace/ftrace.c                         |  6 +++-
 tools/include/uapi/sound/asound.h             |  1 +
 tools/lib/traceevent/event-parse.c            |  2 +-
 tools/perf/builtin-stat.c                     |  1 +
 tools/perf/builtin-top.c                      |  1 +
 tools/perf/scripts/python/export-to-sqlite.py |  2 +-
 tools/perf/util/env.c                         |  8 +++--
 tools/perf/util/evlist.c                      | 14 +++++---
 tools/perf/util/evsel.c                       | 12 +++----
 tools/perf/util/header.c                      | 22 +++++++-----
 tools/perf/util/map.c                         | 20 +++++++++--
 tools/perf/util/map.h                         |  4 ++-
 20 files changed, 195 insertions(+), 98 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 0ecfac84ba91..d45f3fbd232e 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -117,22 +117,39 @@ static __initconst const u64 amd_hw_cache_event_ids
 };
 
 /*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
  */
 static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
-  [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
-  [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x077d,
-  [PERF_COUNT_HW_CACHE_MISSES]			= 0x077e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
-  [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
-  [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
-  [PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x077d,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x077e,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x0187,
 };
 
 static u64 amd_pmu_event_map(int hw_event)
 {
+	if (boot_cpu_data.x86 >= 0x17)
+		return amd_f17h_perfmon_event_map[hw_event];
+
 	return amd_perfmon_event_map[hw_event];
 }
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f61dcbef20ff..f9451566cd9b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 		flags &= ~PERF_SAMPLE_TIME;
 	if (!event->attr.exclude_kernel)
 		flags &= ~PERF_SAMPLE_REGS_USER;
-	if (event->attr.sample_regs_user & ~PEBS_REGS)
+	if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
 		flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
 	return flags;
 }
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..1e98a42b560a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -96,25 +96,25 @@ struct amd_nb {
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
 	PERF_SAMPLE_PERIOD)
 
-#define PEBS_REGS \
-	(PERF_REG_X86_AX | \
-	 PERF_REG_X86_BX | \
-	 PERF_REG_X86_CX | \
-	 PERF_REG_X86_DX | \
-	 PERF_REG_X86_DI | \
-	 PERF_REG_X86_SI | \
-	 PERF_REG_X86_SP | \
-	 PERF_REG_X86_BP | \
-	 PERF_REG_X86_IP | \
-	 PERF_REG_X86_FLAGS | \
-	 PERF_REG_X86_R8 | \
-	 PERF_REG_X86_R9 | \
-	 PERF_REG_X86_R10 | \
-	 PERF_REG_X86_R11 | \
-	 PERF_REG_X86_R12 | \
-	 PERF_REG_X86_R13 | \
-	 PERF_REG_X86_R14 | \
-	 PERF_REG_X86_R15)
+#define PEBS_GP_REGS			\
+	((1ULL << PERF_REG_X86_AX)    | \
+	 (1ULL << PERF_REG_X86_BX)    | \
+	 (1ULL << PERF_REG_X86_CX)    | \
+	 (1ULL << PERF_REG_X86_DX)    | \
+	 (1ULL << PERF_REG_X86_DI)    | \
+	 (1ULL << PERF_REG_X86_SI)    | \
+	 (1ULL << PERF_REG_X86_SP)    | \
+	 (1ULL << PERF_REG_X86_BP)    | \
+	 (1ULL << PERF_REG_X86_IP)    | \
+	 (1ULL << PERF_REG_X86_FLAGS) | \
+	 (1ULL << PERF_REG_X86_R8)    | \
+	 (1ULL << PERF_REG_X86_R9)    | \
+	 (1ULL << PERF_REG_X86_R10)   | \
+	 (1ULL << PERF_REG_X86_R11)   | \
+	 (1ULL << PERF_REG_X86_R12)   | \
+	 (1ULL << PERF_REG_X86_R13)   | \
+	 (1ULL << PERF_REG_X86_R14)   | \
+	 (1ULL << PERF_REG_X86_R15))
 
 /*
  * Per register state.
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..fed46ddb1eef 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	unsigned long *sara = stack_addr(regs);
 
 	ri->ret_addr = (kprobe_opcode_t *) *sara;
+	ri->fp = sara;
 
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
@@ -748,26 +749,48 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
+static struct kprobe kretprobe_kprobe = {
+	.addr = (void *)kretprobe_trampoline,
+};
+
 /*
  * Called from kretprobe_trampoline
  */
 static __used void *trampoline_handler(struct pt_regs *regs)
 {
+	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 	kprobe_opcode_t *correct_ret_addr = NULL;
+	void *frame_pointer;
+	bool skipped = false;
+
+	preempt_disable();
+
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never run in kprobe handler, kprobe must not
+	 * be running at this point.
+	 */
+	kcb = get_kprobe_ctlblk();
+	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
+	/* On x86-64, we use pt_regs->sp for return address holder. */
+	frame_pointer = &regs->sp;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
 	regs->gs = 0;
+	/* On x86-32, we use pt_regs->flags for return address holder. */
+	frame_pointer = &regs->flags;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
@@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be poped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
 
 		if (orig_ret_address != trampoline_address)
 			/*
@@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		if (ri->fp != frame_pointer)
+			continue;
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
+			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 201f0f2683f2..9a897256e481 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -173,6 +173,7 @@ struct kretprobe_instance {
 	struct kretprobe *rp;
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
+	void *fp;
 	char data[0];
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 534e01e7bc36..dc7dead2d2cc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9077,26 +9077,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	if (task == TASK_TOMBSTONE)
 		return;
 
-	if (!ifh->nr_file_filters)
-		return;
-
-	mm = get_task_mm(event->ctx->task);
-	if (!mm)
-		goto restart;
+	if (ifh->nr_file_filters) {
+		mm = get_task_mm(event->ctx->task);
+		if (!mm)
+			goto restart;
 
-	down_read(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
+	}
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		event->addr_filter_ranges[count].start = 0;
-		event->addr_filter_ranges[count].size = 0;
+		if (filter->path.dentry) {
+			/*
+			 * Adjust base offset if the filter is associated to a
+			 * binary that needs to be mapped:
+			 */
+			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)
 			perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]);
+		} else {
+			event->addr_filter_ranges[count].start = filter->offset;
+			event->addr_filter_ranges[count].size  = filter->size;
+		}
 
 		count++;
 	}
@@ -9104,9 +9107,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	event->addr_filters_gen++;
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
-	up_read(&mm->mmap_sem);
+	if (ifh->nr_file_filters) {
+		up_read(&mm->mmap_sem);
 
-	mmput(mm);
+		mmput(mm);
+	}
 
 restart:
 	perf_event_stop(event, 1);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 2545ac08cc77..5eedb49a65ea 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		rb->aux_head += size;
 	}
 
-	if (size || handle->aux_flags) {
-		/*
-		 * Only send RECORD_AUX if we have something useful to communicate
-		 *
-		 * Note: the OVERWRITE records by themselves are not considered
-		 * useful, as they don't communicate any *new* information,
-		 * aside from the short-lived offset, that becomes history at
-		 * the next event sched-in and therefore isn't useful.
-		 * The userspace that needs to copy out AUX data in overwrite
-		 * mode should know to use user_page::aux_head for the actual
-		 * offset. So, from now on we don't output AUX records that
-		 * have *only* OVERWRITE flag set.
-		 */
-
-		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
-			perf_event_aux_event(handle->event, aux_head, size,
-			                     handle->aux_flags);
-	}
+	/*
+	 * Only send RECORD_AUX if we have something useful to communicate
+	 *
+	 * Note: the OVERWRITE records by themselves are not considered
+	 * useful, as they don't communicate any *new* information,
+	 * aside from the short-lived offset, that becomes history at
+	 * the next event sched-in and therefore isn't useful.
+	 * The userspace that needs to copy out AUX data in overwrite
+	 * mode should know to use user_page::aux_head for the actual
+	 * offset. So, from now on we don't output AUX records that
+	 * have *only* OVERWRITE flag set.
+	 */
+	if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
+		perf_event_aux_event(handle->event, aux_head, size,
+				     handle->aux_flags);
 
 	rb->user_page->aux_head = rb->aux_head;
 	if (rb_need_aux_wakeup(rb))
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c83e54727131..b1ea30a5540e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 static int reuse_unused_kprobe(struct kprobe *ap)
 {
 	struct optimized_kprobe *op;
-	int ret;
 
 	/*
 	 * Unused kprobe MUST be on the way of delayed unoptimizing (means
@@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap)
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
-	ret = kprobe_optready(ap);
-	if (ret)
-		return ret;
+	if (!kprobe_optready(ap))
+		return -EINVAL;
 
 	optimize_kprobe(ap);
 	return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 26c8ca9bd06b..b920358dd8f7 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -33,6 +33,7 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/rcupdate.h>
+#include <linux/kprobes.h>
 
 #include <trace/events/sched.h>
 
@@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr)
 	tr->ops->func = ftrace_stub;
 }
 
-static inline void
+static nokprobe_inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
@@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
 }
+NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
+NOKPROBE_SYMBOL(ftrace_ops_no_ops);
 #endif
 
 /*
@@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
+NOKPROBE_SYMBOL(ftrace_ops_assist_func);
 
 /**
  * ftrace_ops_get_func - get the function a trampoline should call
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 404d4b9ffe76..df1153cea0b7 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -32,6 +32,7 @@
 
 #ifndef __KERNEL__
 #include <stdlib.h>
+#include <time.h>
 #endif
 
 /*
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 87494c7c619d..981c6ce2da2c 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2233,7 +2233,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 		return val & 0xffffffff;
 
 	if (strcmp(type, "u64") == 0 ||
-	    strcmp(type, "s64"))
+	    strcmp(type, "s64") == 0)
 		return val;
 
 	if (strcmp(type, "s8") == 0)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 49ee3c2033ec..c3625ec374e0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1308,6 +1308,7 @@ static void init_features(struct perf_session *session)
 	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
 		perf_header__set_feat(&session->header, feat);
 
+	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
 	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1999d6533d12..fbbb0da43abb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1377,6 +1377,7 @@ int cmd_top(int argc, const char **argv)
 			 * */
 			.overwrite	= 0,
 			.sample_time	= true,
+			.sample_time_set = true,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index 3b71902a5a21..bf271fbc3a88 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -331,7 +331,7 @@ if perf_db_export_calls:
 			'return_id,'
 			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
 			'parent_call_path_id,'
-			'parent_id'
+			'calls.parent_id'
 		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
 
 do_query(query, 'CREATE VIEW samples_view AS '
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index c6351b557bb0..9494f9dc61ec 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -57,9 +57,11 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 		else if (prog_id > node->info_linear->info.id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
+out:
 	up_read(&env->bpf_progs.lock);
 	return node;
 }
@@ -109,10 +111,12 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
 	up_read(&env->bpf_progs.lock);
+out:
 	return node;
 }
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6689378ee577..51ead577533f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1868,12 +1868,12 @@ static void *perf_evlist__poll_thread(void *arg)
 {
 	struct perf_evlist *evlist = arg;
 	bool draining = false;
-	int i;
+	int i, done = 0;
+
+	while (!done) {
+		bool got_data = false;
 
-	while (draining || !(evlist->thread.done)) {
-		if (draining)
-			draining = false;
-		else if (evlist->thread.done)
+		if (evlist->thread.done)
 			draining = true;
 
 		if (!draining)
@@ -1894,9 +1894,13 @@ static void *perf_evlist__poll_thread(void *arg)
 					pr_warning("cannot locate proper evsel for the side band event\n");
 
 				perf_mmap__consume(map);
+				got_data = true;
 			}
 			perf_mmap__read_done(map);
 		}
+
+		if (draining && !got_data)
+			break;
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 66d066f18b5b..966360844fff 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2368,7 +2368,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->user_regs.abi) {
 			u64 mask = evsel->attr.sample_regs_user;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
@@ -2424,7 +2424,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
 			u64 mask = evsel->attr.sample_regs_intr;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->intr_regs.mask = mask;
 			data->intr_regs.regs = (u64 *)array;
@@ -2552,7 +2552,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2580,7 +2580,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2710,7 +2710,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			memcpy(array, sample->user_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
@@ -2746,7 +2746,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			*array++ = sample->intr_regs.abi;
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			memcpy(array, sample->intr_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b9e693825873..2d2af2ac2b1e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2606,6 +2606,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
+	up_write(&env->bpf_progs.lock);
 	return 0;
 out:
 	free(info_linear);
@@ -2623,7 +2624,9 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _
 static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 {
 	struct perf_env *env = &ff->ph->env;
+	struct btf_node *node = NULL;
 	u32 count, i;
+	int err = -1;
 
 	if (ff->ph->needs_swap) {
 		pr_warning("interpreting btf from systems with endianity is not yet supported\n");
@@ -2636,31 +2639,32 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 	down_write(&env->bpf_progs.lock);
 
 	for (i = 0; i < count; ++i) {
-		struct btf_node *node;
 		u32 id, data_size;
 
 		if (do_read_u32(ff, &id))
-			return -1;
+			goto out;
 		if (do_read_u32(ff, &data_size))
-			return -1;
+			goto out;
 
 		node = malloc(sizeof(struct btf_node) + data_size);
 		if (!node)
-			return -1;
+			goto out;
 
 		node->id = id;
 		node->data_size = data_size;
 
-		if (__do_read(ff, node->data, data_size)) {
-			free(node);
-			return -1;
-		}
+		if (__do_read(ff, node->data, data_size))
+			goto out;
 
 		perf_env__insert_btf(env, node);
+		node = NULL;
 	}
 
+	err = 0;
+out:
 	up_write(&env->bpf_progs.lock);
-	return 0;
+	free(node);
+	return err;
 }
 
 struct feature_ops {
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e32628cd20a7..ee71efb9db62 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map)
 	return kmap && kmap->name[0];
 }
 
+bool __map__is_bpf_prog(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return true;
+
+	/*
+	 * If PERF_RECORD_BPF_EVENT is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && (strstr(name, "bpf_prog_") == name);
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);
@@ -910,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map)
 		rc = strcmp(m->dso->short_name, map->dso->short_name);
 		if (rc < 0)
 			p = &(*p)->rb_left;
-		else if (rc  > 0)
-			p = &(*p)->rb_right;
 		else
-			return;
+			p = &(*p)->rb_right;
 	}
 	rb_link_node(&map->rb_node_name, parent, p);
 	rb_insert_color(&map->rb_node_name, &maps->names);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e20749f2c55..dc93787c74f0 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+	       !__map__is_bpf_prog(map);
 }
 
 bool map__has_symbols(const struct map *map);

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Fri, 12 Apr 2019 15:06:42 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/73fdb2c908c64a32e11c72c029d636f556859c0d

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 1d54ad944074010609562da5c89e4f5df2f4e5db perf/core: Fix perf_event_disable_inatomic() race

Six kernel side fixes: three related to NMI handling on AMD systems, a 
race fix, a kexec initialization fix and a PEBS sampling fix.

 Thanks,

	Ingo

------------------>
Lendacky, Thomas (3):
      x86/perf/amd: Resolve race condition when disabling PMC
      x86/perf/amd: Resolve NMI latency issues for active PMCs
      x86/perf/amd: Remove need to check "running" bit in NMI handler

Peter Zijlstra (2):
      perf/x86/intel: Initialize TFA MSR
      perf/core: Fix perf_event_disable_inatomic() race

Stephane Eranian (1):
      perf/x86/intel: Fix handling of wakeup_events for multi-entry PEBS


 arch/x86/events/amd/core.c   | 140 +++++++++++++++++++++++++++++++++++++++++--
 arch/x86/events/core.c       |  13 +---
 arch/x86/events/intel/core.c |   8 ++-
 kernel/events/core.c         |  52 +++++++++++++---
 kernel/events/ring_buffer.c  |   4 +-
 5 files changed, 190 insertions(+), 27 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 7d2d7c801dba..0ecfac84ba91 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -3,10 +3,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 #include <asm/apicdef.h>
+#include <asm/nmi.h>
 
 #include "../perf_event.h"
 
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -429,6 +433,132 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT	50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+	unsigned int i;
+	u64 counter;
+
+	/*
+	 * Wait for the counter to be reset if it has overflowed. This loop
+	 * should exit very, very quickly, but just in case, don't wait
+	 * forever...
+	 */
+	for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+		rdmsrl(x86_pmu_event_addr(idx), counter);
+		if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+			break;
+
+		/* Might be in IRQ context, so can't sleep */
+		udelay(1);
+	}
+}
+
+static void amd_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx;
+
+	x86_pmu_disable_all();
+
+	/*
+	 * This shouldn't be called from NMI context, but add a safeguard here
+	 * to return, since if we're in NMI context we can't wait for an NMI
+	 * to reset an overflowed counter value.
+	 */
+	if (in_nmi())
+		return;
+
+	/*
+	 * Check each counter for overflow and wait for it to be reset by the
+	 * NMI if it has overflowed. This relies on the fact that all active
+	 * counters are always enabled when this function is caled and
+	 * ARCH_PERFMON_EVENTSEL_INT is always set.
+	 */
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		amd_pmu_wait_on_overflow(idx);
+	}
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+	x86_pmu_disable_event(event);
+
+	/*
+	 * This can be called from NMI context (via x86_pmu_stop). The counter
+	 * may have overflowed, but either way, we'll never see it get reset
+	 * by the NMI if we're already in the NMI. And the NMI latency support
+	 * below will take care of any pending NMI that might have been
+	 * generated by the overflow.
+	 */
+	if (in_nmi())
+		return;
+
+	amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int active, handled;
+
+	/*
+	 * Obtain the active count before calling x86_pmu_handle_irq() since
+	 * it is possible that x86_pmu_handle_irq() may make a counter
+	 * inactive (through x86_pmu_stop).
+	 */
+	active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+	/* Process any counter overflows */
+	handled = x86_pmu_handle_irq(regs);
+
+	/*
+	 * If a counter was handled, record the number of possible remaining
+	 * NMIs that can occur.
+	 */
+	if (handled) {
+		this_cpu_write(perf_nmi_counter,
+			       min_t(unsigned int, 2, active));
+
+		return handled;
+	}
+
+	if (!this_cpu_read(perf_nmi_counter))
+		return NMI_DONE;
+
+	this_cpu_dec(perf_nmi_counter);
+
+	return NMI_HANDLED;
+}
+
 static struct event_constraint *
 amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -621,11 +751,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
 
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
+	.handle_irq		= amd_pmu_handle_irq,
+	.disable_all		= amd_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
+	.disable		= amd_pmu_disable_event,
 	.hw_config		= amd_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
@@ -732,7 +862,7 @@ void amd_pmu_enable_virt(void)
 	cpuc->perf_ctr_virt_mask = 0;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -750,7 +880,7 @@ void amd_pmu_disable_virt(void)
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..81911e11a15d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+	if (test_bit(hwc->idx, cpuc->active_mask)) {
 		x86_pmu.disable(event);
+		__clear_bit(hwc->idx, cpuc->active_mask);
 		cpuc->events[hwc->idx] = NULL;
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
@@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask)) {
-			/*
-			 * Though we deactivated the counter some cpus
-			 * might still deliver spurious interrupts still
-			 * in flight. Catch them:
-			 */
-			if (__test_and_clear_bit(idx, cpuc->running))
-				handled++;
+		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		}
 
 		event = cpuc->events[idx];
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8baa441d8000..f61dcbef20ff 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3185,7 +3185,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
-		if (!event->attr.freq) {
+		if (!(event->attr.freq || event->attr.wakeup_events)) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
 			      ~intel_pmu_large_pebs_flags(event)))
@@ -3575,6 +3575,12 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
+	if (x86_pmu.flags & PMU_FL_TFA) {
+		WARN_ON_ONCE(cpuc->tfa_shadow);
+		cpuc->tfa_shadow = ~0ULL;
+		intel_set_tfa(cpuc, false);
+	}
+
 	if (x86_pmu.version > 1)
 		flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72d06e302e99..534e01e7bc36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event,
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
+	if (READ_ONCE(event->pending_disable) >= 0) {
+		WRITE_ONCE(event->pending_disable, -1);
 		state = PERF_EVENT_STATE_OFF;
 	}
 	perf_event_set_state(event, state);
@@ -2198,7 +2198,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 
 void perf_event_disable_inatomic(struct perf_event *event)
 {
-	event->pending_disable = 1;
+	WRITE_ONCE(event->pending_disable, smp_processor_id());
+	/* can fail, see perf_pending_event_disable() */
 	irq_work_queue(&event->pending);
 }
 
@@ -5810,10 +5811,45 @@ void perf_event_wakeup(struct perf_event *event)
 	}
 }
 
+static void perf_pending_event_disable(struct perf_event *event)
+{
+	int cpu = READ_ONCE(event->pending_disable);
+
+	if (cpu < 0)
+		return;
+
+	if (cpu == smp_processor_id()) {
+		WRITE_ONCE(event->pending_disable, -1);
+		perf_event_disable_local(event);
+		return;
+	}
+
+	/*
+	 *  CPU-A			CPU-B
+	 *
+	 *  perf_event_disable_inatomic()
+	 *    @pending_disable = CPU-A;
+	 *    irq_work_queue();
+	 *
+	 *  sched-out
+	 *    @pending_disable = -1;
+	 *
+	 *				sched-in
+	 *				perf_event_disable_inatomic()
+	 *				  @pending_disable = CPU-B;
+	 *				  irq_work_queue(); // FAILS
+	 *
+	 *  irq_work_run()
+	 *    perf_pending_event()
+	 *
+	 * But the event runs on CPU-B and wants disabling there.
+	 */
+	irq_work_queue_on(&event->pending, cpu);
+}
+
 static void perf_pending_event(struct irq_work *entry)
 {
-	struct perf_event *event = container_of(entry,
-			struct perf_event, pending);
+	struct perf_event *event = container_of(entry, struct perf_event, pending);
 	int rctx;
 
 	rctx = perf_swevent_get_recursion_context();
@@ -5822,10 +5858,7 @@ static void perf_pending_event(struct irq_work *entry)
 	 * and we won't recurse 'further'.
 	 */
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
-		perf_event_disable_local(event);
-	}
+	perf_pending_event_disable(event);
 
 	if (event->pending_wakeup) {
 		event->pending_wakeup = 0;
@@ -10236,6 +10269,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 
 	init_waitqueue_head(&event->waitq);
+	event->pending_disable = -1;
 	init_irq_work(&event->pending, perf_pending_event);
 
 	mutex_init(&event->mmap_mutex);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a4047321d7d8..2545ac08cc77 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -392,7 +392,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = 1;
+			event->pending_disable = smp_processor_id();
 			perf_output_wakeup(handle);
 			local_set(&rb->aux_nest, 0);
 			goto err_put;
@@ -480,7 +480,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = 1;
+			handle->event->pending_disable = smp_processor_id();
 		perf_output_wakeup(handle);
 	}
 

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 17 Feb 2019 11:10:51 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/dd6f29da695dbfe5a8ff84ebfdd2110d68e8f511

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 528871b456026e6127d95b1b2bd8e3a003dc1614 perf/core: Fix impossible ring-buffer sizes warning

Two fixes on the kernel side: fix an over-eager condition that failed 
larger perf ring-buffer sizes, plus fix crashes in the Intel BTS code for 
a corner case, found by fuzzing.

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      perf/core: Fix impossible ring-buffer sizes warning

Jiri Olsa (1):
      perf/x86: Add check_period PMU callback


 arch/x86/events/core.c       | 14 ++++++++++++++
 arch/x86/events/intel/core.c |  9 +++++++++
 arch/x86/events/perf_event.h | 16 ++++++++++++++--
 include/linux/perf_event.h   |  5 +++++
 kernel/events/core.c         | 16 ++++++++++++++++
 kernel/events/ring_buffer.c  |  2 +-
 6 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 374a19712e20..b684f0294f35 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2278,6 +2278,19 @@ void perf_check_microcode(void)
 		x86_pmu.check_microcode();
 }
 
+static int x86_pmu_check_period(struct perf_event *event, u64 value)
+{
+	if (x86_pmu.check_period && x86_pmu.check_period(event, value))
+		return -EINVAL;
+
+	if (value && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, value) > value)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2302,6 +2315,7 @@ static struct pmu pmu = {
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
+	.check_period		= x86_pmu_check_period,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index daafb893449b..730978dff63f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3587,6 +3587,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3667,6 +3672,8 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.cpu_dead		= intel_pmu_cpu_dead,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3711,6 +3718,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78d7b7031bfc..d46fd6754d92 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -646,6 +646,11 @@ struct x86_pmu {
 	 * Intel host/guest support (KVM)
 	 */
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period) (struct perf_event *event, u64 period);
 };
 
 struct x86_perf_task_context {
@@ -857,7 +862,7 @@ static inline int amd_pmu_init(void)
 
 #ifdef CONFIG_CPU_SUP_INTEL
 
-static inline bool intel_pmu_has_bts(struct perf_event *event)
+static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
@@ -868,7 +873,14 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return hw_event == bts_event && hwc->sample_period == 1;
+	return hw_event == bts_event && period == 1;
+}
+
+static inline bool intel_pmu_has_bts(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1d5c551a5add..e1a051724f7e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -447,6 +447,11 @@ struct pmu {
 	 * Filter events for PMU-specific reasons.
 	 */
 	int (*filter_match)		(struct perf_event *event); /* optional */
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period)		(struct perf_event *event, u64 value); /* optional */
 };
 
 enum perf_addr_filter_action_t {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5ede6918050..26d6edab051a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4963,6 +4963,11 @@ static void __perf_event_period(struct perf_event *event,
 	}
 }
 
+static int perf_event_check_period(struct perf_event *event, u64 value)
+{
+	return event->pmu->check_period(event, value);
+}
+
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	u64 value;
@@ -4979,6 +4984,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
+	if (perf_event_check_period(event, value))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -9391,6 +9399,11 @@ static int perf_pmu_nop_int(struct pmu *pmu)
 	return 0;
 }
 
+static int perf_event_nop_int(struct perf_event *event, u64 value)
+{
+	return 0;
+}
+
 static DEFINE_PER_CPU(unsigned int, nop_txn_flags);
 
 static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
@@ -9691,6 +9704,9 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 		pmu->pmu_disable = perf_pmu_nop_void;
 	}
 
+	if (!pmu->check_period)
+		pmu->check_period = perf_event_nop_int;
+
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 309ef5a64af5..5ab4fe3b1dcc 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -734,7 +734,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct ring_buffer);
 	size += nr_pages * sizeof(void *);
 
-	if (order_base_2(size) >= MAX_ORDER)
+	if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER)
 		goto fail;
 
 	rb = kzalloc(size, GFP_KERNEL);

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sun, 10 Feb 2019 10:01:09 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/212146f0800e151bd61b98fb6fe4b8b6778a649a

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 3bb2600657dac78580e5b8fecc202eaaff5d4ced Merge tag 'perf-urgent-for-mingo-5.0-20190205' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

A couple of kernel side fixes:

 - Fix the Intel uncore driver on certain hardware configurations
 - Fix a CPU hotplug related memory allocation bug
 - Remove a spurious WARN()

Plus also a handful of perf tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf clang: Do not use 'return std::move(something)'
      tools headers uapi: Sync linux/in.h copy from the kernel sources
      perf symbols: Add fallback definitions for GELF_ST_VISIBILITY()
      perf trace: Support multiple "vfs_getname" probes

Gustavo A. R. Silva (1):
      perf tests evsel-tp-sched: Fix bitwise operator

Jiri Olsa (1):
      perf symbols: Filter out hidden symbols from labels

Kan Liang (1):
      perf/x86/intel/uncore: Add Node ID mask

Mark Rutland (1):
      perf/core: Don't WARN() for impossible ring-buffer sizes

Peter Zijlstra (1):
      perf/x86/intel: Delay memory deallocation until x86_pmu_dead_cpu()

Ravi Bangoria (1):
      perf mem/c2c: Fix perf_mem_events to support powerpc

Tony Jones (1):
      perf script python: Add Python3 support to tests/attr.py


 arch/x86/events/intel/core.c              | 16 +++++++++++-----
 arch/x86/events/intel/uncore_snbep.c      |  4 +++-
 kernel/events/ring_buffer.c               |  3 +++
 tools/include/uapi/linux/in.h             |  2 +-
 tools/perf/Documentation/perf-c2c.txt     | 16 ++++++++++++----
 tools/perf/Documentation/perf-mem.txt     |  2 +-
 tools/perf/arch/powerpc/util/Build        |  1 +
 tools/perf/arch/powerpc/util/mem-events.c | 11 +++++++++++
 tools/perf/builtin-trace.c                | 25 +++++++++++++++++-------
 tools/perf/tests/attr.py                  | 32 ++++++++++++++++++-------------
 tools/perf/tests/evsel-tp-sched.c         |  2 +-
 tools/perf/util/c++/clang.cpp             |  2 +-
 tools/perf/util/mem-events.c              |  2 +-
 tools/perf/util/symbol-elf.c              | 23 +++++++++++++++++++++-
 14 files changed, 105 insertions(+), 36 deletions(-)
 create mode 100644 tools/perf/arch/powerpc/util/mem-events.c

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 40e12cfc87f6..daafb893449b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3558,6 +3558,14 @@ static void free_excl_cntrs(int cpu)
 }
 
 static void intel_pmu_cpu_dying(int cpu)
+{
+	fini_debug_store_on_cpu(cpu);
+
+	if (x86_pmu.counter_freezing)
+		disable_counter_freeze();
+}
+
+static void intel_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	struct intel_shared_regs *pc;
@@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu)
 	}
 
 	free_excl_cntrs(cpu);
-
-	fini_debug_store_on_cpu(cpu);
-
-	if (x86_pmu.counter_freezing)
-		disable_counter_freeze();
 }
 
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3663,6 +3666,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3703,6 +3707,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
 };
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c07bee31abe8..b10e04387f38 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
 	.id_table	= snbep_uncore_pci_ids,
 };
 
+#define NODE_ID_MASK	0x7
+
 /*
  * build pci bus to socket mapping
  */
@@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 		err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
 		if (err)
 			break;
-		nodeid = config;
+		nodeid = config & NODE_ID_MASK;
 		/* get the Node ID mapping */
 		err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
 		if (err)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 4a9937076331..309ef5a64af5 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct ring_buffer);
 	size += nr_pages * sizeof(void *);
 
+	if (order_base_2(size) >= MAX_ORDER)
+		goto fail;
+
 	rb = kzalloc(size, GFP_KERNEL);
 	if (!rb)
 		goto fail;
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index f6052e70bf40..a55cb8b10165 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -268,7 +268,7 @@ struct sockaddr_in {
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
 #define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_BADCLASS(a)		(((long int) (a) ) == (long int)0xffffffff)
 #define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
 
 #define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 095aebdc5bb7..e6150f21267d 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -19,8 +19,11 @@ C2C stands for Cache To Cache.
 The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
 you to track down the cacheline contentions.
 
-The tool is based on x86's load latency and precise store facility events
-provided by Intel CPUs. These events provide:
+On x86, the tool is based on load latency and precise store facility events
+provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
+with thresholding feature.
+
+These events provide:
   - memory address of the access
   - type of the access (load and store details)
   - latency (in cycles) of the load access
@@ -46,7 +49,7 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency.
+	Configure mem-loads latency. (x86 only)
 
 -k::
 --all-kernel::
@@ -119,11 +122,16 @@ Following perf record options are configured by default:
   -W,-d,--phys-data,--sample-cpu
 
 Unless specified otherwise with '-e' option, following events are monitored by
-default:
+default on x86:
 
   cpu/mem-loads,ldlat=30/P
   cpu/mem-stores/P
 
+and following on PowerPC:
+
+  cpu/mem-loads/
+  cpu/mem-stores/
+
 User can pass any 'perf record' option behind '--' mark, like (to enable
 callchains and system wide monitoring):
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index f8d2167cf3e7..199ea0f0a6c0 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -82,7 +82,7 @@ RECORD OPTIONS
 	Be more verbose (show counter open errors, etc)
 
 --ldlat <n>::
-	Specify desired latency for loads event.
+	Specify desired latency for loads event. (x86 only)
 
 In addition, for report all perf report options are valid, and for record
 all perf record options.
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 2e6595310420..ba98bd006488 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
new file mode 100644
index 000000000000..d08311f04e95
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "mem-events.h"
+
+/* PowerPC does not support 'ldlat' parameter. */
+char *perf_mem_events__name(int i)
+{
+	if (i == PERF_MEM_EVENTS__LOAD)
+		return (char *) "cpu/mem-loads/";
+
+	return (char *) "cpu/mem-stores/";
+}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ed4583128b9c..b36061cd1ab8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
 
 static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
+	bool found = false;
+	struct perf_evsel *evsel, *tmp;
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, "probe:vfs_getname*", &err);
 
-	if (IS_ERR(evsel))
+	if (ret)
 		return false;
 
-	if (perf_evsel__field(evsel, "pathname") == NULL) {
+	evlist__for_each_entry_safe(evlist, evsel, tmp) {
+		if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
+			continue;
+
+		if (perf_evsel__field(evsel, "pathname")) {
+			evsel->handler = trace__vfs_getname;
+			found = true;
+			continue;
+		}
+
+		list_del_init(&evsel->node);
+		evsel->evlist = NULL;
 		perf_evsel__delete(evsel);
-		return false;
 	}
 
-	evsel->handler = trace__vfs_getname;
-	perf_evlist__add(evlist, evsel);
-	return true;
+	return found;
 }
 
 static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 44090a9a19f3..e952127e4fb0 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -1,6 +1,8 @@
 #! /usr/bin/python
 # SPDX-License-Identifier: GPL-2.0
 
+from __future__ import print_function
+
 import os
 import sys
 import glob
@@ -8,7 +10,11 @@ import optparse
 import tempfile
 import logging
 import shutil
-import ConfigParser
+
+try:
+    import configparser
+except ImportError:
+    import ConfigParser as configparser
 
 def data_equal(a, b):
     # Allow multiple values in assignment separated by '|'
@@ -100,20 +106,20 @@ class Event(dict):
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 return False
             if not data_equal(self[t], other[t]):
                 return False
         return True
 
     def optional(self):
-        if self.has_key('optional') and self['optional'] == '1':
+        if 'optional' in self and self['optional'] == '1':
             return True
         return False
 
     def diff(self, other):
         for t in Event.terms:
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 continue
             if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
@@ -134,7 +140,7 @@ class Event(dict):
 #   - expected values assignments
 class Test(object):
     def __init__(self, path, options):
-        parser = ConfigParser.SafeConfigParser()
+        parser = configparser.SafeConfigParser()
         parser.read(path)
 
         log.warning("running '%s'" % path)
@@ -193,7 +199,7 @@ class Test(object):
         return True
 
     def load_events(self, path, events):
-        parser_event = ConfigParser.SafeConfigParser()
+        parser_event = configparser.SafeConfigParser()
         parser_event.read(path)
 
         # The event record section header contains 'event' word,
@@ -207,7 +213,7 @@ class Test(object):
             # Read parent event if there's any
             if (':' in section):
                 base = section[section.index(':') + 1:]
-                parser_base = ConfigParser.SafeConfigParser()
+                parser_base = configparser.SafeConfigParser()
                 parser_base.read(self.test_dir + '/' + base)
                 base_items = parser_base.items('event')
 
@@ -322,9 +328,9 @@ def run_tests(options):
     for f in glob.glob(options.test_dir + '/' + options.test):
         try:
             Test(f, options).run()
-        except Unsup, obj:
+        except Unsup as obj:
             log.warning("unsupp  %s" % obj.getMsg())
-        except Notest, obj:
+        except Notest as obj:
             log.warning("skipped %s" % obj.getMsg())
 
 def setup_log(verbose):
@@ -363,7 +369,7 @@ def main():
     parser.add_option("-p", "--perf",
                       action="store", type="string", dest="perf")
     parser.add_option("-v", "--verbose",
-                      action="count", dest="verbose")
+                      default=0, action="count", dest="verbose")
 
     options, args = parser.parse_args()
     if args:
@@ -373,7 +379,7 @@ def main():
     setup_log(options.verbose)
 
     if not options.test_dir:
-        print 'FAILED no -d option specified'
+        print('FAILED no -d option specified')
         sys.exit(-1)
 
     if not options.test:
@@ -382,8 +388,8 @@ def main():
     try:
         run_tests(options)
 
-    except Fail, obj:
-        print "FAILED %s" % obj.getMsg();
+    except Fail as obj:
+        print("FAILED %s" % obj.getMsg())
         sys.exit(-1)
 
     sys.exit(0)
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 5f8501c68da4..5cbba70bcdd0 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
+	is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 89512504551b..39c0004f2886 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module)
 	}
 	PM.run(*Module);
 
-	return std::move(Buffer);
+	return Buffer;
 }
 
 }
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 93f74d8d3cdd..42c3e5a229d2 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
-char *perf_mem_events__name(int i)
+char * __weak perf_mem_events__name(int i)
 {
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 66a84d5846c8..dca7dfae69ad 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -19,6 +19,20 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+#ifndef ELF32_ST_VISIBILITY
+#define ELF32_ST_VISIBILITY(o)	((o) & 0x03)
+#endif
+
+/* For ELF64 the definitions are the same.  */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o)	ELF32_ST_VISIBILITY (o)
+#endif
+
+/* How to extract information held in the st_other field.  */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(val)	ELF64_ST_VISIBILITY (val)
+#endif
+
 typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
@@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 	return GELF_ST_TYPE(sym->st_info);
 }
 
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+	return GELF_ST_VISIBILITY(sym->st_other);
+}
+
 #ifndef STT_GNU_IFUNC
 #define STT_GNU_IFUNC 10
 #endif
@@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
 	return elf_sym__type(sym) == STT_NOTYPE &&
 		sym->st_name != 0 &&
 		sym->st_shndx != SHN_UNDEF &&
-		sym->st_shndx != SHN_ABS;
+		sym->st_shndx != SHN_ABS &&
+		elf_sym__visibility(sym) != STV_HIDDEN &&
+		elf_sym__visibility(sym) != STV_INTERNAL;
 }
 
 static bool elf_sym__filter(GElf_Sym *sym)

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Fri, 11 Jan 2019 08:44:18 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/40a31da414c39e3cd8c4137c1ceedf59b7ffd4ce

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4e72ee8872279a70ebe973172133b98e8acbf54e Merge tag 'perf-core-for-mingo-5.0-20190110' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling changes only: fixes and a few stray improvements.

Most of the diffstat is dominated by a PowerPC related fix of system call 
trace output beautification that allows us to (again) use the UAPI header 
version and sync up with the kernel's version of PowerPC system call 
names in the arch/powerpc/kernel/syscalls/syscall.tbl header.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (19):
      tools headers x86: Sync disabled-features.h
      tools headers uapi: Sync prctl.h with the kernel sources
      tools beauty: Make the prctl option table generator catch all PR_ options
      tools headers uapi: Update i915_drm.h
      tools headers uapi: Sync linux/in.h copy from the kernel sources
      tools headers uapi: Sync linux/kvm.h with the kernel sources
      tools headers uapi: Sync copy of asm-generic/unistd.h with the kernel sources
      tools headers x86: Sync asm/cpufeatures.h copy with the kernel sources
      perf python: Make sure the python binding output directory is in place
      perf test shell: Use a fallback to get the pathname in vfs_getname
      perf trace: Fix ')' placement in "interrupted" syscall lines
      perf trace: Fix alignment for [continued] lines
      perf top: Lift restriction on using callchains without "sym" in --sort
      tools include uapi: Grab a copy of linux/mount.h
      perf beauty: Switch from using uapi/linux/fs.h to uapi/linux/mount.h
      tools include uapi: Sync linux/fs.h copy with the kernel sources
      tools include uapi: Sync linux/vhost.h with the kernel sources
      tools include uapi: Sync linux/if_link.h copy with the kernel sources
      perf symbols: Add 'arch_cpu_idle' to the list of kernel idle symbols

Florian Fainelli (2):
      perf tools: Make find_vdso_map() more modular
      perf tests: Add a test for the ARM 32-bit [vectors] page

Ivan Krylov (1):
      perf annotate: Pass filename to objdump via execl

Jin Yao (2):
      perf stat: Fix endless wait for child process
      perf report: Fix wrong iteration count in --branch-history

Jiri Olsa (2):
      tools thermal tmon: Use -O3 instead of -O1 if available
      tools iio: Override CFLAGS assignments

Mattias Jacobsson (1):
      perf strbuf: Remove redundant va_end() in strbuf_addv()

Ravi Bangoria (2):
      perf powerpc: Rework syscall table generation
      tools headers powerpc: Remove unistd.h

Tzvetomir Stoyanov (7):
      tools lib traceevent: Introduce new libtracevent API: tep_override_comm()
      tools lib traceevent: Initialize host_bigendian at tep_handle allocation
      tools lib traceevent: Rename struct cmdline to struct tep_cmdline
      tools lib traceevent: Changed return logic of trace_seq_printf() and trace_seq_vprintf() APIs
      tools lib traceevent: Changed return logic of tep_register_event_handler() API
      tools lib traceevent: Rename tep_is_file_bigendian() to tep_file_bigendian()
      tools lib traceevent: Remove tep_data_event_from_type() API


 tools/arch/powerpc/include/uapi/asm/unistd.h       | 404 -------------------
 tools/arch/x86/include/asm/cpufeatures.h           |   2 +
 tools/arch/x86/include/asm/disabled-features.h     |   8 +-
 tools/include/uapi/asm-generic/unistd.h            |   4 +-
 tools/include/uapi/drm/i915_drm.h                  |   8 +
 tools/include/uapi/linux/fs.h                      |  60 +--
 tools/include/uapi/linux/if_link.h                 |  19 +
 tools/include/uapi/linux/in.h                      |  10 +-
 tools/include/uapi/linux/kvm.h                     |  19 +
 tools/include/uapi/linux/mount.h                   |  58 +++
 tools/include/uapi/linux/prctl.h                   |   8 +
 tools/include/uapi/linux/vhost.h                   | 113 +-----
 tools/lib/traceevent/event-parse-api.c             |   4 +-
 tools/lib/traceevent/event-parse-local.h           |   4 +-
 tools/lib/traceevent/event-parse.c                 | 129 ++++---
 tools/lib/traceevent/event-parse.h                 |  17 +-
 tools/lib/traceevent/plugin_kvm.c                  |   2 +-
 tools/lib/traceevent/trace-seq.c                   |  17 +-
 tools/perf/Makefile.perf                           |   8 +-
 tools/perf/arch/arm/tests/Build                    |   1 +
 tools/perf/arch/arm/tests/arch-tests.c             |   4 +
 tools/perf/arch/arm/tests/vectors-page.c           |  24 ++
 tools/perf/arch/powerpc/Makefile                   |  15 +-
 .../perf/arch/powerpc/entry/syscalls/mksyscalltbl  |  22 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 427 +++++++++++++++++++++
 tools/perf/builtin-stat.c                          |   3 +-
 tools/perf/builtin-top.c                           |   7 +-
 tools/perf/builtin-trace.c                         |  15 +-
 tools/perf/check-headers.sh                        |   2 +-
 tools/perf/perf-read-vdso.c                        |   6 +-
 tools/perf/tests/shell/lib/probe_vfs_getname.sh    |   3 +-
 tools/perf/tests/tests.h                           |   5 +
 tools/perf/trace/beauty/mount_flags.sh             |   4 +-
 tools/perf/trace/beauty/prctl_option.sh            |   2 +-
 tools/perf/util/annotate.c                         |   8 +-
 tools/perf/util/callchain.c                        |  32 +-
 tools/perf/util/callchain.h                        |   1 +
 tools/perf/util/{find-vdso-map.c => find-map.c}    |   7 +-
 tools/perf/util/machine.c                          |   2 +-
 tools/perf/util/strbuf.c                           |   1 -
 tools/perf/util/symbol.c                           |   1 +
 tools/perf/util/vdso.c                             |   6 +-
 tools/thermal/tmon/Makefile                        |   2 +-
 43 files changed, 797 insertions(+), 697 deletions(-)
 delete mode 100644 tools/arch/powerpc/include/uapi/asm/unistd.h
 create mode 100644 tools/include/uapi/linux/mount.h
 create mode 100644 tools/perf/arch/arm/tests/vectors-page.c
 create mode 100644 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
 rename tools/perf/util/{find-vdso-map.c => find-map.c} (71%)

diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
deleted file mode 100644
index 985534d0b448..000000000000
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,404 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*
- * This file contains the system call numbers.
- *
- * 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.
- */
-#ifndef _UAPI_ASM_POWERPC_UNISTD_H_
-#define _UAPI_ASM_POWERPC_UNISTD_H_
-
-
-#define __NR_restart_syscall	  0
-#define __NR_exit		  1
-#define __NR_fork		  2
-#define __NR_read		  3
-#define __NR_write		  4
-#define __NR_open		  5
-#define __NR_close		  6
-#define __NR_waitpid		  7
-#define __NR_creat		  8
-#define __NR_link		  9
-#define __NR_unlink		 10
-#define __NR_execve		 11
-#define __NR_chdir		 12
-#define __NR_time		 13
-#define __NR_mknod		 14
-#define __NR_chmod		 15
-#define __NR_lchown		 16
-#define __NR_break		 17
-#define __NR_oldstat		 18
-#define __NR_lseek		 19
-#define __NR_getpid		 20
-#define __NR_mount		 21
-#define __NR_umount		 22
-#define __NR_setuid		 23
-#define __NR_getuid		 24
-#define __NR_stime		 25
-#define __NR_ptrace		 26
-#define __NR_alarm		 27
-#define __NR_oldfstat		 28
-#define __NR_pause		 29
-#define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
-#define __NR_access		 33
-#define __NR_nice		 34
-#define __NR_ftime		 35
-#define __NR_sync		 36
-#define __NR_kill		 37
-#define __NR_rename		 38
-#define __NR_mkdir		 39
-#define __NR_rmdir		 40
-#define __NR_dup		 41
-#define __NR_pipe		 42
-#define __NR_times		 43
-#define __NR_prof		 44
-#define __NR_brk		 45
-#define __NR_setgid		 46
-#define __NR_getgid		 47
-#define __NR_signal		 48
-#define __NR_geteuid		 49
-#define __NR_getegid		 50
-#define __NR_acct		 51
-#define __NR_umount2		 52
-#define __NR_lock		 53
-#define __NR_ioctl		 54
-#define __NR_fcntl		 55
-#define __NR_mpx		 56
-#define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
-#define __NR_umask		 60
-#define __NR_chroot		 61
-#define __NR_ustat		 62
-#define __NR_dup2		 63
-#define __NR_getppid		 64
-#define __NR_getpgrp		 65
-#define __NR_setsid		 66
-#define __NR_sigaction		 67
-#define __NR_sgetmask		 68
-#define __NR_ssetmask		 69
-#define __NR_setreuid		 70
-#define __NR_setregid		 71
-#define __NR_sigsuspend		 72
-#define __NR_sigpending		 73
-#define __NR_sethostname	 74
-#define __NR_setrlimit		 75
-#define __NR_getrlimit		 76
-#define __NR_getrusage		 77
-#define __NR_gettimeofday	 78
-#define __NR_settimeofday	 79
-#define __NR_getgroups		 80
-#define __NR_setgroups		 81
-#define __NR_select		 82
-#define __NR_symlink		 83
-#define __NR_oldlstat		 84
-#define __NR_readlink		 85
-#define __NR_uselib		 86
-#define __NR_swapon		 87
-#define __NR_reboot		 88
-#define __NR_readdir		 89
-#define __NR_mmap		 90
-#define __NR_munmap		 91
-#define __NR_truncate		 92
-#define __NR_ftruncate		 93
-#define __NR_fchmod		 94
-#define __NR_fchown		 95
-#define __NR_getpriority	 96
-#define __NR_setpriority	 97
-#define __NR_profil		 98
-#define __NR_statfs		 99
-#define __NR_fstatfs		100
-#define __NR_ioperm		101
-#define __NR_socketcall		102
-#define __NR_syslog		103
-#define __NR_setitimer		104
-#define __NR_getitimer		105
-#define __NR_stat		106
-#define __NR_lstat		107
-#define __NR_fstat		108
-#define __NR_olduname		109
-#define __NR_iopl		110
-#define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86		113
-#define __NR_wait4		114
-#define __NR_swapoff		115
-#define __NR_sysinfo		116
-#define __NR_ipc		117
-#define __NR_fsync		118
-#define __NR_sigreturn		119
-#define __NR_clone		120
-#define __NR_setdomainname	121
-#define __NR_uname		122
-#define __NR_modify_ldt		123
-#define __NR_adjtimex		124
-#define __NR_mprotect		125
-#define __NR_sigprocmask	126
-#define __NR_create_module	127
-#define __NR_init_module	128
-#define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
-#define __NR_quotactl		131
-#define __NR_getpgid		132
-#define __NR_fchdir		133
-#define __NR_bdflush		134
-#define __NR_sysfs		135
-#define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
-#define __NR_setfsuid		138
-#define __NR_setfsgid		139
-#define __NR__llseek		140
-#define __NR_getdents		141
-#define __NR__newselect		142
-#define __NR_flock		143
-#define __NR_msync		144
-#define __NR_readv		145
-#define __NR_writev		146
-#define __NR_getsid		147
-#define __NR_fdatasync		148
-#define __NR__sysctl		149
-#define __NR_mlock		150
-#define __NR_munlock		151
-#define __NR_mlockall		152
-#define __NR_munlockall		153
-#define __NR_sched_setparam		154
-#define __NR_sched_getparam		155
-#define __NR_sched_setscheduler		156
-#define __NR_sched_getscheduler		157
-#define __NR_sched_yield		158
-#define __NR_sched_get_priority_max	159
-#define __NR_sched_get_priority_min	160
-#define __NR_sched_rr_get_interval	161
-#define __NR_nanosleep		162
-#define __NR_mremap		163
-#define __NR_setresuid		164
-#define __NR_getresuid		165
-#define __NR_query_module	166
-#define __NR_poll		167
-#define __NR_nfsservctl		168
-#define __NR_setresgid		169
-#define __NR_getresgid		170
-#define __NR_prctl		171
-#define __NR_rt_sigreturn	172
-#define __NR_rt_sigaction	173
-#define __NR_rt_sigprocmask	174
-#define __NR_rt_sigpending	175
-#define __NR_rt_sigtimedwait	176
-#define __NR_rt_sigqueueinfo	177
-#define __NR_rt_sigsuspend	178
-#define __NR_pread64		179
-#define __NR_pwrite64		180
-#define __NR_chown		181
-#define __NR_getcwd		182
-#define __NR_capget		183
-#define __NR_capset		184
-#define __NR_sigaltstack	185
-#define __NR_sendfile		186
-#define __NR_getpmsg		187	/* some people actually want streams */
-#define __NR_putpmsg		188	/* some people actually want streams */
-#define __NR_vfork		189
-#define __NR_ugetrlimit		190	/* SuS compliant getrlimit */
-#define __NR_readahead		191
-#ifndef __powerpc64__			/* these are 32-bit only */
-#define __NR_mmap2		192
-#define __NR_truncate64		193
-#define __NR_ftruncate64	194
-#define __NR_stat64		195
-#define __NR_lstat64		196
-#define __NR_fstat64		197
-#endif
-#define __NR_pciconfig_read	198
-#define __NR_pciconfig_write	199
-#define __NR_pciconfig_iobase	200
-#define __NR_multiplexer	201
-#define __NR_getdents64		202
-#define __NR_pivot_root		203
-#ifndef __powerpc64__
-#define __NR_fcntl64		204
-#endif
-#define __NR_madvise		205
-#define __NR_mincore		206
-#define __NR_gettid		207
-#define __NR_tkill		208
-#define __NR_setxattr		209
-#define __NR_lsetxattr		210
-#define __NR_fsetxattr		211
-#define __NR_getxattr		212
-#define __NR_lgetxattr		213
-#define __NR_fgetxattr		214
-#define __NR_listxattr		215
-#define __NR_llistxattr		216
-#define __NR_flistxattr		217
-#define __NR_removexattr	218
-#define __NR_lremovexattr	219
-#define __NR_fremovexattr	220
-#define __NR_futex		221
-#define __NR_sched_setaffinity	222
-#define __NR_sched_getaffinity	223
-/* 224 currently unused */
-#define __NR_tuxcall		225
-#ifndef __powerpc64__
-#define __NR_sendfile64		226
-#endif
-#define __NR_io_setup		227
-#define __NR_io_destroy		228
-#define __NR_io_getevents	229
-#define __NR_io_submit		230
-#define __NR_io_cancel		231
-#define __NR_set_tid_address	232
-#define __NR_fadvise64		233
-#define __NR_exit_group		234
-#define __NR_lookup_dcookie	235
-#define __NR_epoll_create	236
-#define __NR_epoll_ctl		237
-#define __NR_epoll_wait		238
-#define __NR_remap_file_pages	239
-#define __NR_timer_create	240
-#define __NR_timer_settime	241
-#define __NR_timer_gettime	242
-#define __NR_timer_getoverrun	243
-#define __NR_timer_delete	244
-#define __NR_clock_settime	245
-#define __NR_clock_gettime	246
-#define __NR_clock_getres	247
-#define __NR_clock_nanosleep	248
-#define __NR_swapcontext	249
-#define __NR_tgkill		250
-#define __NR_utimes		251
-#define __NR_statfs64		252
-#define __NR_fstatfs64		253
-#ifndef __powerpc64__
-#define __NR_fadvise64_64	254
-#endif
-#define __NR_rtas		255
-#define __NR_sys_debug_setcontext 256
-/* Number 257 is reserved for vserver */
-#define __NR_migrate_pages	258
-#define __NR_mbind		259
-#define __NR_get_mempolicy	260
-#define __NR_set_mempolicy	261
-#define __NR_mq_open		262
-#define __NR_mq_unlink		263
-#define __NR_mq_timedsend	264
-#define __NR_mq_timedreceive	265
-#define __NR_mq_notify		266
-#define __NR_mq_getsetattr	267
-#define __NR_kexec_load		268
-#define __NR_add_key		269
-#define __NR_request_key	270
-#define __NR_keyctl		271
-#define __NR_waitid		272
-#define __NR_ioprio_set		273
-#define __NR_ioprio_get		274
-#define __NR_inotify_init	275
-#define __NR_inotify_add_watch	276
-#define __NR_inotify_rm_watch	277
-#define __NR_spu_run		278
-#define __NR_spu_create		279
-#define __NR_pselect6		280
-#define __NR_ppoll		281
-#define __NR_unshare		282
-#define __NR_splice		283
-#define __NR_tee		284
-#define __NR_vmsplice		285
-#define __NR_openat		286
-#define __NR_mkdirat		287
-#define __NR_mknodat		288
-#define __NR_fchownat		289
-#define __NR_futimesat		290
-#ifdef __powerpc64__
-#define __NR_newfstatat		291
-#else
-#define __NR_fstatat64		291
-#endif
-#define __NR_unlinkat		292
-#define __NR_renameat		293
-#define __NR_linkat		294
-#define __NR_symlinkat		295
-#define __NR_readlinkat		296
-#define __NR_fchmodat		297
-#define __NR_faccessat		298
-#define __NR_get_robust_list	299
-#define __NR_set_robust_list	300
-#define __NR_move_pages		301
-#define __NR_getcpu		302
-#define __NR_epoll_pwait	303
-#define __NR_utimensat		304
-#define __NR_signalfd		305
-#define __NR_timerfd_create	306
-#define __NR_eventfd		307
-#define __NR_sync_file_range2	308
-#define __NR_fallocate		309
-#define __NR_subpage_prot	310
-#define __NR_timerfd_settime	311
-#define __NR_timerfd_gettime	312
-#define __NR_signalfd4		313
-#define __NR_eventfd2		314
-#define __NR_epoll_create1	315
-#define __NR_dup3		316
-#define __NR_pipe2		317
-#define __NR_inotify_init1	318
-#define __NR_perf_event_open	319
-#define __NR_preadv		320
-#define __NR_pwritev		321
-#define __NR_rt_tgsigqueueinfo	322
-#define __NR_fanotify_init	323
-#define __NR_fanotify_mark	324
-#define __NR_prlimit64		325
-#define __NR_socket		326
-#define __NR_bind		327
-#define __NR_connect		328
-#define __NR_listen		329
-#define __NR_accept		330
-#define __NR_getsockname	331
-#define __NR_getpeername	332
-#define __NR_socketpair		333
-#define __NR_send		334
-#define __NR_sendto		335
-#define __NR_recv		336
-#define __NR_recvfrom		337
-#define __NR_shutdown		338
-#define __NR_setsockopt		339
-#define __NR_getsockopt		340
-#define __NR_sendmsg		341
-#define __NR_recvmsg		342
-#define __NR_recvmmsg		343
-#define __NR_accept4		344
-#define __NR_name_to_handle_at	345
-#define __NR_open_by_handle_at	346
-#define __NR_clock_adjtime	347
-#define __NR_syncfs		348
-#define __NR_sendmmsg		349
-#define __NR_setns		350
-#define __NR_process_vm_readv	351
-#define __NR_process_vm_writev	352
-#define __NR_finit_module	353
-#define __NR_kcmp		354
-#define __NR_sched_setattr	355
-#define __NR_sched_getattr	356
-#define __NR_renameat2		357
-#define __NR_seccomp		358
-#define __NR_getrandom		359
-#define __NR_memfd_create	360
-#define __NR_bpf		361
-#define __NR_execveat		362
-#define __NR_switch_endian	363
-#define __NR_userfaultfd	364
-#define __NR_membarrier		365
-#define __NR_mlock2		378
-#define __NR_copy_file_range	379
-#define __NR_preadv2		380
-#define __NR_pwritev2		381
-#define __NR_kexec_file_load	382
-#define __NR_statx		383
-#define __NR_pkey_alloc		384
-#define __NR_pkey_free		385
-#define __NR_pkey_mprotect	386
-#define __NR_rseq		387
-#define __NR_io_pgetevents	388
-
-#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 28c4a502b419..6d6122524711 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -281,9 +281,11 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_WBNOINVD		(13*32+ 9) /* WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 33833d1909af..a5ea841cc6d2 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_SMAP
+# define DISABLE_SMAP	0
+#else
+# define DISABLE_SMAP	(1<<(X86_FEATURE_SMAP & 31))
+#endif
+
 #ifdef CONFIG_X86_INTEL_UMIP
 # define DISABLE_UMIP	0
 #else
@@ -68,7 +74,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index c7f3321fbe43..d90127298f12 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -738,9 +738,11 @@ __SYSCALL(__NR_statx,     sys_statx)
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 #define __NR_rseq 293
 __SYSCALL(__NR_rseq, sys_rseq)
+#define __NR_kexec_file_load 294
+__SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
 
 #undef __NR_syscalls
-#define __NR_syscalls 294
+#define __NR_syscalls 295
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index a4446f452040..298b2e197744 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -412,6 +412,14 @@ typedef struct drm_i915_irq_wait {
 	int irq_seq;
 } drm_i915_irq_wait_t;
 
+/*
+ * Different modes of per-process Graphics Translation Table,
+ * see I915_PARAM_HAS_ALIASING_PPGTT
+ */
+#define I915_GEM_PPGTT_NONE	0
+#define I915_GEM_PPGTT_ALIASING	1
+#define I915_GEM_PPGTT_FULL	2
+
 /* Ioctl to query kernel params:
  */
 #define I915_PARAM_IRQ_ACTIVE            1
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index a441ea1bfe6d..121e82ce296b 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -14,6 +14,11 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#if !defined(__KERNEL__)
+#include <linux/mount.h>
+#endif
+
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
  * the file limit at runtime and only root can increase the per-process
@@ -101,57 +106,6 @@ struct inodes_stat_t {
 
 #define NR_FILE  8192	/* this can well be larger on a larger system */
 
-
-/*
- * These are the fs-independent mount-flags: up to 32 flags are supported
- */
-#define MS_RDONLY	 1	/* Mount read-only */
-#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
-#define MS_NODEV	 4	/* Disallow access to device special files */
-#define MS_NOEXEC	 8	/* Disallow program execution */
-#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
-#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
-#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
-#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
-#define MS_NOATIME	1024	/* Do not update access times. */
-#define MS_NODIRATIME	2048	/* Do not update directory access times */
-#define MS_BIND		4096
-#define MS_MOVE		8192
-#define MS_REC		16384
-#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
-				   MS_VERBOSE is deprecated. */
-#define MS_SILENT	32768
-#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
-#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
-#define MS_PRIVATE	(1<<18)	/* change to private */
-#define MS_SLAVE	(1<<19)	/* change to slave */
-#define MS_SHARED	(1<<20)	/* change to shared */
-#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
-#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
-#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
-#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
-#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
-
-/* These sb flags are internal to the kernel */
-#define MS_SUBMOUNT     (1<<26)
-#define MS_NOREMOTELOCK	(1<<27)
-#define MS_NOSEC	(1<<28)
-#define MS_BORN		(1<<29)
-#define MS_ACTIVE	(1<<30)
-#define MS_NOUSER	(1<<31)
-
-/*
- * Superblock flags that can be altered by MS_REMOUNT
- */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
-			 MS_LAZYTIME)
-
-/*
- * Old magic mount flag and mask
- */
-#define MS_MGC_VAL 0xC0ED0000
-#define MS_MGC_MSK 0xffff0000
-
 /*
  * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
  */
@@ -269,7 +223,8 @@ struct fsxattr {
 #define FS_POLICY_FLAGS_PAD_16		0x02
 #define FS_POLICY_FLAGS_PAD_32		0x03
 #define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAGS_VALID		0x03
+#define FS_POLICY_FLAG_DIRECT_KEY	0x04	/* use master key directly */
+#define FS_POLICY_FLAGS_VALID		0x07
 
 /* Encryption algorithms */
 #define FS_ENCRYPTION_MODE_INVALID		0
@@ -281,6 +236,7 @@ struct fsxattr {
 #define FS_ENCRYPTION_MODE_AES_128_CTS		6
 #define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
 #define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_ADIANTUM		9
 
 struct fscrypt_policy {
 	__u8 version;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 1debfa42cba1..d6533828123a 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -288,6 +288,7 @@ enum {
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
+	IFLA_BR_MULTI_BOOLOPT,
 	__IFLA_BR_MAX,
 };
 
@@ -533,6 +534,7 @@ enum {
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
+	IFLA_VXLAN_DF,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -542,6 +544,14 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+enum ifla_vxlan_df {
+	VXLAN_DF_UNSET = 0,
+	VXLAN_DF_SET,
+	VXLAN_DF_INHERIT,
+	__VXLAN_DF_END,
+	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
@@ -557,10 +567,19 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
+	IFLA_GENEVE_DF,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
 
+enum ifla_geneve_df {
+	GENEVE_DF_UNSET = 0,
+	GENEVE_DF_SET,
+	GENEVE_DF_INHERIT,
+	__GENEVE_DF_END,
+	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 48e8a225b985..f6052e70bf40 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -266,10 +266,14 @@ struct sockaddr_in {
 
 #define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
-#define IN_MULTICAST_NET	0xF0000000
+#define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
-#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
+
+#define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_CLASSE_NET		0xffffffff
+#define	IN_CLASSE_NSHIFT	0
 
 /* Address to accept any incoming messages. */
 #define	INADDR_ANY		((unsigned long int) 0x00000000)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 2b7a652c9fa4..6d4ea4b6c922 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -492,6 +492,17 @@ struct kvm_dirty_log {
 	};
 };
 
+/* for KVM_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+	__u32 slot;
+	__u32 num_pages;
+	__u64 first_page;
+	union {
+		void __user *dirty_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
 /* for KVM_SET_SIGNAL_MASK */
 struct kvm_signal_mask {
 	__u32 len;
@@ -975,6 +986,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
 #define KVM_CAP_EXCEPTION_PAYLOAD 164
 #define KVM_CAP_ARM_VM_IPA_SIZE 165
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166
+#define KVM_CAP_HYPERV_CPUID 167
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1421,6 +1434,12 @@ struct kvm_enc_region {
 #define KVM_GET_NESTED_STATE         _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
 #define KVM_SET_NESTED_STATE         _IOW(KVMIO,  0xbf, struct kvm_nested_state)
 
+/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */
+#define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
+
+/* Available with KVM_CAP_HYPERV_CPUID */
+#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
new file mode 100644
index 000000000000..3f9ec42510b0
--- /dev/null
+++ b/tools/include/uapi/linux/mount.h
@@ -0,0 +1,58 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only.  Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index b17201edfa09..b4875a93363a 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -220,4 +220,12 @@ struct prctl_mm_map {
 # define PR_SPEC_DISABLE		(1UL << 2)
 # define PR_SPEC_FORCE_DISABLE		(1UL << 3)
 
+/* Reset arm64 pointer authentication keys */
+#define PR_PAC_RESET_KEYS		54
+# define PR_PAC_APIAKEY			(1UL << 0)
+# define PR_PAC_APIBKEY			(1UL << 1)
+# define PR_PAC_APDAKEY			(1UL << 2)
+# define PR_PAC_APDBKEY			(1UL << 3)
+# define PR_PAC_APGAKEY			(1UL << 4)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 84c3de89696a..40d028eed645 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -11,94 +11,9 @@
  * device configuration.
  */
 
+#include <linux/vhost_types.h>
 #include <linux/types.h>
-#include <linux/compiler.h>
 #include <linux/ioctl.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ring.h>
-
-struct vhost_vring_state {
-	unsigned int index;
-	unsigned int num;
-};
-
-struct vhost_vring_file {
-	unsigned int index;
-	int fd; /* Pass -1 to unbind from file. */
-
-};
-
-struct vhost_vring_addr {
-	unsigned int index;
-	/* Option flags. */
-	unsigned int flags;
-	/* Flag values: */
-	/* Whether log address is valid. If set enables logging. */
-#define VHOST_VRING_F_LOG 0
-
-	/* Start of array of descriptors (virtually contiguous) */
-	__u64 desc_user_addr;
-	/* Used structure address. Must be 32 bit aligned */
-	__u64 used_user_addr;
-	/* Available structure address. Must be 16 bit aligned */
-	__u64 avail_user_addr;
-	/* Logging support. */
-	/* Log writes to used structure, at offset calculated from specified
-	 * address. Address must be 32 bit aligned. */
-	__u64 log_guest_addr;
-};
-
-/* no alignment requirement */
-struct vhost_iotlb_msg {
-	__u64 iova;
-	__u64 size;
-	__u64 uaddr;
-#define VHOST_ACCESS_RO      0x1
-#define VHOST_ACCESS_WO      0x2
-#define VHOST_ACCESS_RW      0x3
-	__u8 perm;
-#define VHOST_IOTLB_MISS           1
-#define VHOST_IOTLB_UPDATE         2
-#define VHOST_IOTLB_INVALIDATE     3
-#define VHOST_IOTLB_ACCESS_FAIL    4
-	__u8 type;
-};
-
-#define VHOST_IOTLB_MSG 0x1
-#define VHOST_IOTLB_MSG_V2 0x2
-
-struct vhost_msg {
-	int type;
-	union {
-		struct vhost_iotlb_msg iotlb;
-		__u8 padding[64];
-	};
-};
-
-struct vhost_msg_v2 {
-	__u32 type;
-	__u32 reserved;
-	union {
-		struct vhost_iotlb_msg iotlb;
-		__u8 padding[64];
-	};
-};
-
-struct vhost_memory_region {
-	__u64 guest_phys_addr;
-	__u64 memory_size; /* bytes */
-	__u64 userspace_addr;
-	__u64 flags_padding; /* No flags are currently specified. */
-};
-
-/* All region addresses and sizes must be 4K aligned. */
-#define VHOST_PAGE_SIZE 0x1000
-
-struct vhost_memory {
-	__u32 nregions;
-	__u32 padding;
-	struct vhost_memory_region regions[0];
-};
 
 /* ioctls */
 
@@ -186,31 +101,7 @@ struct vhost_memory {
  * device.  This can be used to stop the ring (e.g. for migration). */
 #define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
 
-/* Feature bits */
-/* Log all write descriptors. Can be changed while device is active. */
-#define VHOST_F_LOG_ALL 26
-/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
-#define VHOST_NET_F_VIRTIO_NET_HDR 27
-
-/* VHOST_SCSI specific definitions */
-
-/*
- * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
- *
- * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
- *            RFC-v2 vhost-scsi userspace.  Add GET_ABI_VERSION ioctl usage
- * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
- *            All the targets under vhost_wwpn can be seen and used by guset.
- */
-
-#define VHOST_SCSI_ABI_VERSION	1
-
-struct vhost_scsi_target {
-	int abi_version;
-	char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
-	unsigned short vhost_tpgt;
-	unsigned short reserved;
-};
+/* VHOST_SCSI specific defines */
 
 #define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
 #define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
index 8b31c0e00ba3..d463761a58f4 100644
--- a/tools/lib/traceevent/event-parse-api.c
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -194,13 +194,13 @@ void tep_set_page_size(struct tep_handle *pevent, int _page_size)
 }
 
 /**
- * tep_is_file_bigendian - get if the file is in big endian order
+ * tep_file_bigendian - get if the file is in big endian order
  * @pevent: a handle to the tep_handle
  *
  * This returns if the file is in big endian order
  * If @pevent is NULL, 0 is returned.
  */
-int tep_is_file_bigendian(struct tep_handle *pevent)
+int tep_file_bigendian(struct tep_handle *pevent)
 {
 	if(pevent)
 		return pevent->file_bigendian;
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
index 9a092dd4a86d..35833ee32d6c 100644
--- a/tools/lib/traceevent/event-parse-local.h
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -7,7 +7,7 @@
 #ifndef _PARSE_EVENTS_INT_H
 #define _PARSE_EVENTS_INT_H
 
-struct cmdline;
+struct tep_cmdline;
 struct cmdline_list;
 struct func_map;
 struct func_list;
@@ -36,7 +36,7 @@ struct tep_handle {
 	int long_size;
 	int page_size;
 
-	struct cmdline *cmdlines;
+	struct tep_cmdline *cmdlines;
 	struct cmdline_list *cmdlist;
 	int cmdline_count;
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 69a96e39f0ab..abd4fa5d3088 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -124,15 +124,15 @@ struct tep_print_arg *alloc_arg(void)
 	return calloc(1, sizeof(struct tep_print_arg));
 }
 
-struct cmdline {
+struct tep_cmdline {
 	char *comm;
 	int pid;
 };
 
 static int cmdline_cmp(const void *a, const void *b)
 {
-	const struct cmdline *ca = a;
-	const struct cmdline *cb = b;
+	const struct tep_cmdline *ca = a;
+	const struct tep_cmdline *cb = b;
 
 	if (ca->pid < cb->pid)
 		return -1;
@@ -152,7 +152,7 @@ static int cmdline_init(struct tep_handle *pevent)
 {
 	struct cmdline_list *cmdlist = pevent->cmdlist;
 	struct cmdline_list *item;
-	struct cmdline *cmdlines;
+	struct tep_cmdline *cmdlines;
 	int i;
 
 	cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
@@ -179,8 +179,8 @@ static int cmdline_init(struct tep_handle *pevent)
 
 static const char *find_cmdline(struct tep_handle *pevent, int pid)
 {
-	const struct cmdline *comm;
-	struct cmdline key;
+	const struct tep_cmdline *comm;
+	struct tep_cmdline key;
 
 	if (!pid)
 		return "<idle>";
@@ -208,8 +208,8 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
  */
 int tep_pid_is_registered(struct tep_handle *pevent, int pid)
 {
-	const struct cmdline *comm;
-	struct cmdline key;
+	const struct tep_cmdline *comm;
+	struct tep_cmdline key;
 
 	if (!pid)
 		return 1;
@@ -232,11 +232,13 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid)
  * we must add this pid. This is much slower than when cmdlines
  * are added before the array is initialized.
  */
-static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int add_new_comm(struct tep_handle *pevent,
+			const char *comm, int pid, bool override)
 {
-	struct cmdline *cmdlines = pevent->cmdlines;
-	const struct cmdline *cmdline;
-	struct cmdline key;
+	struct tep_cmdline *cmdlines = pevent->cmdlines;
+	struct tep_cmdline *cmdline;
+	struct tep_cmdline key;
+	char *new_comm;
 
 	if (!pid)
 		return 0;
@@ -247,8 +249,19 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 	cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
 		       sizeof(*pevent->cmdlines), cmdline_cmp);
 	if (cmdline) {
-		errno = EEXIST;
-		return -1;
+		if (!override) {
+			errno = EEXIST;
+			return -1;
+		}
+		new_comm = strdup(comm);
+		if (!new_comm) {
+			errno = ENOMEM;
+			return -1;
+		}
+		free(cmdline->comm);
+		cmdline->comm = new_comm;
+
+		return 0;
 	}
 
 	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
@@ -275,21 +288,13 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 	return 0;
 }
 
-/**
- * tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
- * @comm: the command line to register
- * @pid: the pid to map the command line to
- *
- * This adds a mapping to search for command line names with
- * a given pid. The comm is duplicated.
- */
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+static int _tep_register_comm(struct tep_handle *pevent,
+			      const char *comm, int pid, bool override)
 {
 	struct cmdline_list *item;
 
 	if (pevent->cmdlines)
-		return add_new_comm(pevent, comm, pid);
+		return add_new_comm(pevent, comm, pid, override);
 
 	item = malloc(sizeof(*item));
 	if (!item)
@@ -312,6 +317,40 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
 	return 0;
 }
 
+/**
+ * tep_register_comm - register a pid / comm mapping
+ * @pevent: handle for the pevent
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, -1 is returned and errno is set to EEXIST
+ */
+int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+{
+	return _tep_register_comm(pevent, comm, pid, false);
+}
+
+/**
+ * tep_override_comm - register a pid / comm mapping
+ * @pevent: handle for the pevent
+ * @comm: the command line to register
+ * @pid: the pid to map the command line to
+ *
+ * This adds a mapping to search for command line names with
+ * a given pid. The comm is duplicated. If a command with the same pid
+ * already exist, the command string is udapted with the new one
+ */
+int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+{
+	if (!pevent->cmdlines && cmdline_init(pevent)) {
+		errno = ENOMEM;
+		return -1;
+	}
+	return _tep_register_comm(pevent, comm, pid, true);
+}
+
 int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
 {
 	pevent->trace_clock = strdup(trace_clock);
@@ -5226,18 +5265,6 @@ int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
 	return trace_parse_common_type(pevent, rec->data);
 }
 
-/**
- * tep_data_event_from_type - find the event by a given type
- * @pevent: a handle to the pevent
- * @type: the type of the event.
- *
- * This returns the event form a given @type;
- */
-struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type)
-{
-	return tep_find_event(pevent, type);
-}
-
 /**
  * tep_data_pid - parse the PID from record
  * @pevent: a handle to the pevent
@@ -5292,8 +5319,8 @@ const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
 	return comm;
 }
 
-static struct cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *next)
+static struct tep_cmdline *
+pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)next;
 
@@ -5305,7 +5332,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne
 	while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
 		cmdlist = cmdlist->next;
 
-	return (struct cmdline *)cmdlist;
+	return (struct tep_cmdline *)cmdlist;
 }
 
 /**
@@ -5321,10 +5348,10 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne
  * next pid.
  * Also, it does a linear search, so it may be slow.
  */
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
-				       struct cmdline *next)
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+					   struct tep_cmdline *next)
 {
-	struct cmdline *cmdline;
+	struct tep_cmdline *cmdline;
 
 	/*
 	 * If the cmdlines have not been converted yet, then use
@@ -5363,7 +5390,7 @@ struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *co
  * Returns the pid for a give cmdline. If @cmdline is NULL, then
  * -1 is returned.
  */
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
 
@@ -6593,6 +6620,12 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
  *
  * If @id is >= 0, then it is used to find the event.
  * else @sys_name and @event_name are used.
+ *
+ * Returns:
+ *  TEP_REGISTER_SUCCESS_OVERWRITE if an existing handler is overwritten
+ *  TEP_REGISTER_SUCCESS if a new handler is registered successfully
+ *  negative TEP_ERRNO_... in case of an error
+ *
  */
 int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
@@ -6610,7 +6643,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 
 	event->handler = func;
 	event->context = context;
-	return 0;
+	return TEP_REGISTER_SUCCESS_OVERWRITE;
 
  not_found:
 	/* Save for later use. */
@@ -6640,7 +6673,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 	pevent->handlers = handle;
 	handle->context = context;
 
-	return -1;
+	return TEP_REGISTER_SUCCESS;
 }
 
 static int handle_matches(struct event_handler *handler, int id,
@@ -6723,8 +6756,10 @@ struct tep_handle *tep_alloc(void)
 {
 	struct tep_handle *pevent = calloc(1, sizeof(*pevent));
 
-	if (pevent)
+	if (pevent) {
 		pevent->ref_count = 1;
+		pevent->host_bigendian = tep_host_bigendian();
+	}
 
 	return pevent;
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 35d37087d3c5..aec48f2aea8a 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -432,6 +432,7 @@ int tep_set_function_resolver(struct tep_handle *pevent,
 			      tep_func_resolver_t *func, void *priv);
 void tep_reset_function_resolver(struct tep_handle *pevent);
 int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
 int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
 int tep_register_function(struct tep_handle *pevent, char *name,
 			  unsigned long long addr, char *mod);
@@ -484,6 +485,11 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
 			 struct tep_event *event, const char *name,
 			 struct tep_record *record, int err);
 
+enum tep_reg_handler {
+	TEP_REGISTER_SUCCESS = 0,
+	TEP_REGISTER_SUCCESS_OVERWRITE,
+};
+
 int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context);
@@ -520,15 +526,14 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
 void tep_data_lat_fmt(struct tep_handle *pevent,
 		      struct trace_seq *s, struct tep_record *record);
 int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type);
 int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
 const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
-struct cmdline;
-struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
-				       struct cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
+struct tep_cmdline;
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+					   struct tep_cmdline *next);
+int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
 		     struct tep_format_field *field);
@@ -553,7 +558,7 @@ int tep_get_long_size(struct tep_handle *pevent);
 void tep_set_long_size(struct tep_handle *pevent, int long_size);
 int tep_get_page_size(struct tep_handle *pevent);
 void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_is_file_bigendian(struct tep_handle *pevent);
+int tep_file_bigendian(struct tep_handle *pevent);
 void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
 int tep_is_host_bigendian(struct tep_handle *pevent);
 void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 754050eea467..64b9c25a1fd3 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -389,7 +389,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 	 * We can only use the structure if file is of the same
 	 * endianness.
 	 */
-	if (tep_is_file_bigendian(event->pevent) ==
+	if (tep_file_bigendian(event->pevent) ==
 	    tep_is_host_bigendian(event->pevent)) {
 
 		trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index 8ff1d55954d1..8d5ecd2bf877 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -100,7 +100,8 @@ static void expand_buffer(struct trace_seq *s)
  * @fmt: printf format string
  *
  * It returns 0 if the trace oversizes the buffer's free
- * space, 1 otherwise.
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
  *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
@@ -129,9 +130,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 		goto try_again;
 	}
 
-	s->len += ret;
+	if (ret > 0)
+		s->len += ret;
 
-	return 1;
+	return ret;
 }
 
 /**
@@ -139,6 +141,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
  * @s: trace sequence descriptor
  * @fmt: printf format string
  *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, the number of characters printed, or a negative
+ * value in case of an error.
+ * *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
  * trace_seq_printf is used to store strings into a special
@@ -163,9 +169,10 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 		goto try_again;
 	}
 
-	s->len += ret;
+	if (ret > 0)
+		s->len += ret;
 
-	return len;
+	return ret;
 }
 
 /**
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ff29c3372ec3..0ee6795d82cc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -524,12 +524,14 @@ $(arch_errno_name_array): $(arch_errno_tbl)
 
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
+# Create python binding output directory if not already present
+_dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
+
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
 	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
         CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
-	mkdir -p $(OUTPUT)python && \
 	cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/
 
 please_set_SHELL_PATH_to_a_more_modern_shell:
@@ -660,12 +662,12 @@ $(OUTPUT)perf-%: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 ifndef NO_PERF_READ_VDSO32
-$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c
+$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-map.c
 	$(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 
 ifndef NO_PERF_READ_VDSOX32
-$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
+$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-map.c
 	$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 
diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build
index 883c57ff0c08..d9ae2733f9cc 100644
--- a/tools/perf/arch/arm/tests/Build
+++ b/tools/perf/arch/arm/tests/Build
@@ -1,4 +1,5 @@
 libperf-y += regs_load.o
 libperf-y += dwarf-unwind.o
+libperf-y += vectors-page.o
 
 libperf-y += arch-tests.o
diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c
index 5b1543c98022..6848101a855f 100644
--- a/tools/perf/arch/arm/tests/arch-tests.c
+++ b/tools/perf/arch/arm/tests/arch-tests.c
@@ -10,6 +10,10 @@ struct test arch_tests[] = {
 		.func = test__dwarf_unwind,
 	},
 #endif
+	{
+		.desc = "Vectors page",
+		.func = test__vectors_page,
+	},
 	{
 		.func = NULL,
 	},
diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c
new file mode 100644
index 000000000000..7ffdd79971c8
--- /dev/null
+++ b/tools/perf/arch/arm/tests/vectors-page.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+#include <linux/compiler.h>
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "util/find-map.c"
+
+#define VECTORS__MAP_NAME "[vectors]"
+
+int test__vectors_page(struct test *test __maybe_unused,
+		       int subtest __maybe_unused)
+{
+	void *start, *end;
+
+	if (find_map(&start, &end, VECTORS__MAP_NAME)) {
+		pr_err("%s not found, is CONFIG_KUSER_HELPERS enabled?\n",
+		       VECTORS__MAP_NAME);
+		return TEST_FAIL;
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index a111239df182..e58d00d62f02 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -14,18 +14,25 @@ PERF_HAVE_JITDUMP := 1
 out    := $(OUTPUT)arch/powerpc/include/generated/asm
 header32 := $(out)/syscalls_32.c
 header64 := $(out)/syscalls_64.c
-sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h
-sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/
+syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header64): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	(diff -B $(sysdef) $(syskrn) >/dev/null) \
+	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@
 
 $(header32): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+	(diff -B $(sysdef) $(syskrn) >/dev/null) \
+	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64)
diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
index ef52e1dd694b..6c58060aa03b 100755
--- a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
@@ -9,10 +9,9 @@
 # Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
 
 wordsize=$1
-gcc=$2
-input=$3
+SYSCALL_TBL=$2
 
-if ! test -r $input; then
+if ! test -r $SYSCALL_TBL; then
 	echo "Could not read input file" >&2
 	exit 1
 fi
@@ -20,18 +19,21 @@ fi
 create_table()
 {
 	local wordsize=$1
-	local max_nr
+	local max_nr nr abi sc discard
+	max_nr=-1
+	nr=0
 
 	echo "static const char *syscalltbl_powerpc_${wordsize}[] = {"
-	while read sc nr; do
-		printf '\t[%d] = "%s",\n' $nr $sc
-		max_nr=$nr
+	while read nr abi sc discard; do
+		if [ "$max_nr" -lt "$nr" ]; then
+			printf '\t[%d] = "%s",\n' $nr $sc
+			max_nr=$nr
+		fi
 	done
 	echo '};'
 	echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr"
 }
 
-$gcc -m${wordsize} -E -dM -x c  $input	       \
-	|sed -ne 's/^#define __NR_//p' \
-	|sort -t' ' -k2 -nu	       \
+grep -E "^[[:digit:]]+[[:space:]]+(common|spu|nospu|${wordsize})" $SYSCALL_TBL \
+	|sort -k1 -n                                                           \
 	|create_table ${wordsize}
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
new file mode 100644
index 000000000000..db3bbb8744af
--- /dev/null
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -0,0 +1,427 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# system call numbers and entry vectors for powerpc
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The <abi> can be common, spu, nospu, 64, or 32 for this file.
+#
+0	nospu	restart_syscall			sys_restart_syscall
+1	nospu	exit				sys_exit
+2	nospu	fork				ppc_fork
+3	common	read				sys_read
+4	common	write				sys_write
+5	common	open				sys_open			compat_sys_open
+6	common	close				sys_close
+7	common	waitpid				sys_waitpid
+8	common	creat				sys_creat
+9	common	link				sys_link
+10	common	unlink				sys_unlink
+11	nospu	execve				sys_execve			compat_sys_execve
+12	common	chdir				sys_chdir
+13	common	time				sys_time			compat_sys_time
+14	common	mknod				sys_mknod
+15	common	chmod				sys_chmod
+16	common	lchown				sys_lchown
+17	common	break				sys_ni_syscall
+18	32	oldstat				sys_stat			sys_ni_syscall
+18	64	oldstat				sys_ni_syscall
+18	spu	oldstat				sys_ni_syscall
+19	common	lseek				sys_lseek			compat_sys_lseek
+20	common	getpid				sys_getpid
+21	nospu	mount				sys_mount			compat_sys_mount
+22	32	umount				sys_oldumount
+22	64	umount				sys_ni_syscall
+22	spu	umount				sys_ni_syscall
+23	common	setuid				sys_setuid
+24	common	getuid				sys_getuid
+25	common	stime				sys_stime			compat_sys_stime
+26	nospu	ptrace				sys_ptrace			compat_sys_ptrace
+27	common	alarm				sys_alarm
+28	32	oldfstat			sys_fstat			sys_ni_syscall
+28	64	oldfstat			sys_ni_syscall
+28	spu	oldfstat			sys_ni_syscall
+29	nospu	pause				sys_pause
+30	nospu	utime				sys_utime			compat_sys_utime
+31	common	stty				sys_ni_syscall
+32	common	gtty				sys_ni_syscall
+33	common	access				sys_access
+34	common	nice				sys_nice
+35	common	ftime				sys_ni_syscall
+36	common	sync				sys_sync
+37	common	kill				sys_kill
+38	common	rename				sys_rename
+39	common	mkdir				sys_mkdir
+40	common	rmdir				sys_rmdir
+41	common	dup				sys_dup
+42	common	pipe				sys_pipe
+43	common	times				sys_times			compat_sys_times
+44	common	prof				sys_ni_syscall
+45	common	brk				sys_brk
+46	common	setgid				sys_setgid
+47	common	getgid				sys_getgid
+48	nospu	signal				sys_signal
+49	common	geteuid				sys_geteuid
+50	common	getegid				sys_getegid
+51	nospu	acct				sys_acct
+52	nospu	umount2				sys_umount
+53	common	lock				sys_ni_syscall
+54	common	ioctl				sys_ioctl			compat_sys_ioctl
+55	common	fcntl				sys_fcntl			compat_sys_fcntl
+56	common	mpx				sys_ni_syscall
+57	common	setpgid				sys_setpgid
+58	common	ulimit				sys_ni_syscall
+59	32	oldolduname			sys_olduname
+59	64	oldolduname			sys_ni_syscall
+59	spu	oldolduname			sys_ni_syscall
+60	common	umask				sys_umask
+61	common	chroot				sys_chroot
+62	nospu	ustat				sys_ustat			compat_sys_ustat
+63	common	dup2				sys_dup2
+64	common	getppid				sys_getppid
+65	common	getpgrp				sys_getpgrp
+66	common	setsid				sys_setsid
+67	32	sigaction			sys_sigaction			compat_sys_sigaction
+67	64	sigaction			sys_ni_syscall
+67	spu	sigaction			sys_ni_syscall
+68	common	sgetmask			sys_sgetmask
+69	common	ssetmask			sys_ssetmask
+70	common	setreuid			sys_setreuid
+71	common	setregid			sys_setregid
+72	32	sigsuspend			sys_sigsuspend
+72	64	sigsuspend			sys_ni_syscall
+72	spu	sigsuspend			sys_ni_syscall
+73	32	sigpending			sys_sigpending			compat_sys_sigpending
+73	64	sigpending			sys_ni_syscall
+73	spu	sigpending			sys_ni_syscall
+74	common	sethostname			sys_sethostname
+75	common	setrlimit			sys_setrlimit			compat_sys_setrlimit
+76	32	getrlimit			sys_old_getrlimit		compat_sys_old_getrlimit
+76	64	getrlimit			sys_ni_syscall
+76	spu	getrlimit			sys_ni_syscall
+77	common	getrusage			sys_getrusage			compat_sys_getrusage
+78	common	gettimeofday			sys_gettimeofday		compat_sys_gettimeofday
+79	common	settimeofday			sys_settimeofday		compat_sys_settimeofday
+80	common	getgroups			sys_getgroups
+81	common	setgroups			sys_setgroups
+82	32	select				ppc_select			sys_ni_syscall
+82	64	select				sys_ni_syscall
+82	spu	select				sys_ni_syscall
+83	common	symlink				sys_symlink
+84	32	oldlstat			sys_lstat			sys_ni_syscall
+84	64	oldlstat			sys_ni_syscall
+84	spu	oldlstat			sys_ni_syscall
+85	common	readlink			sys_readlink
+86	nospu	uselib				sys_uselib
+87	nospu	swapon				sys_swapon
+88	nospu	reboot				sys_reboot
+89	32	readdir				sys_old_readdir			compat_sys_old_readdir
+89	64	readdir				sys_ni_syscall
+89	spu	readdir				sys_ni_syscall
+90	common	mmap				sys_mmap
+91	common	munmap				sys_munmap
+92	common	truncate			sys_truncate			compat_sys_truncate
+93	common	ftruncate			sys_ftruncate			compat_sys_ftruncate
+94	common	fchmod				sys_fchmod
+95	common	fchown				sys_fchown
+96	common	getpriority			sys_getpriority
+97	common	setpriority			sys_setpriority
+98	common	profil				sys_ni_syscall
+99	nospu	statfs				sys_statfs			compat_sys_statfs
+100	nospu	fstatfs				sys_fstatfs			compat_sys_fstatfs
+101	common	ioperm				sys_ni_syscall
+102	common	socketcall			sys_socketcall			compat_sys_socketcall
+103	common	syslog				sys_syslog
+104	common	setitimer			sys_setitimer			compat_sys_setitimer
+105	common	getitimer			sys_getitimer			compat_sys_getitimer
+106	common	stat				sys_newstat			compat_sys_newstat
+107	common	lstat				sys_newlstat			compat_sys_newlstat
+108	common	fstat				sys_newfstat			compat_sys_newfstat
+109	32	olduname			sys_uname
+109	64	olduname			sys_ni_syscall
+109	spu	olduname			sys_ni_syscall
+110	common	iopl				sys_ni_syscall
+111	common	vhangup				sys_vhangup
+112	common	idle				sys_ni_syscall
+113	common	vm86				sys_ni_syscall
+114	common	wait4				sys_wait4			compat_sys_wait4
+115	nospu	swapoff				sys_swapoff
+116	common	sysinfo				sys_sysinfo			compat_sys_sysinfo
+117	nospu	ipc				sys_ipc				compat_sys_ipc
+118	common	fsync				sys_fsync
+119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
+119	64	sigreturn			sys_ni_syscall
+119	spu	sigreturn			sys_ni_syscall
+120	nospu	clone				ppc_clone
+121	common	setdomainname			sys_setdomainname
+122	common	uname				sys_newuname
+123	common	modify_ldt			sys_ni_syscall
+124	common	adjtimex			sys_adjtimex			compat_sys_adjtimex
+125	common	mprotect			sys_mprotect
+126	32	sigprocmask			sys_sigprocmask			compat_sys_sigprocmask
+126	64	sigprocmask			sys_ni_syscall
+126	spu	sigprocmask			sys_ni_syscall
+127	common	create_module			sys_ni_syscall
+128	nospu	init_module			sys_init_module
+129	nospu	delete_module			sys_delete_module
+130	common	get_kernel_syms			sys_ni_syscall
+131	nospu	quotactl			sys_quotactl
+132	common	getpgid				sys_getpgid
+133	common	fchdir				sys_fchdir
+134	common	bdflush				sys_bdflush
+135	common	sysfs				sys_sysfs
+136	32	personality			sys_personality			ppc64_personality
+136	64	personality			ppc64_personality
+136	spu	personality			ppc64_personality
+137	common	afs_syscall			sys_ni_syscall
+138	common	setfsuid			sys_setfsuid
+139	common	setfsgid			sys_setfsgid
+140	common	_llseek				sys_llseek
+141	common	getdents			sys_getdents			compat_sys_getdents
+142	common	_newselect			sys_select			compat_sys_select
+143	common	flock				sys_flock
+144	common	msync				sys_msync
+145	common	readv				sys_readv			compat_sys_readv
+146	common	writev				sys_writev			compat_sys_writev
+147	common	getsid				sys_getsid
+148	common	fdatasync			sys_fdatasync
+149	nospu	_sysctl				sys_sysctl			compat_sys_sysctl
+150	common	mlock				sys_mlock
+151	common	munlock				sys_munlock
+152	common	mlockall			sys_mlockall
+153	common	munlockall			sys_munlockall
+154	common	sched_setparam			sys_sched_setparam
+155	common	sched_getparam			sys_sched_getparam
+156	common	sched_setscheduler		sys_sched_setscheduler
+157	common	sched_getscheduler		sys_sched_getscheduler
+158	common	sched_yield			sys_sched_yield
+159	common	sched_get_priority_max		sys_sched_get_priority_max
+160	common	sched_get_priority_min		sys_sched_get_priority_min
+161	common	sched_rr_get_interval		sys_sched_rr_get_interval	compat_sys_sched_rr_get_interval
+162	common	nanosleep			sys_nanosleep			compat_sys_nanosleep
+163	common	mremap				sys_mremap
+164	common	setresuid			sys_setresuid
+165	common	getresuid			sys_getresuid
+166	common	query_module			sys_ni_syscall
+167	common	poll				sys_poll
+168	common	nfsservctl			sys_ni_syscall
+169	common	setresgid			sys_setresgid
+170	common	getresgid			sys_getresgid
+171	common	prctl				sys_prctl
+172	nospu	rt_sigreturn			sys_rt_sigreturn		compat_sys_rt_sigreturn
+173	nospu	rt_sigaction			sys_rt_sigaction		compat_sys_rt_sigaction
+174	nospu	rt_sigprocmask			sys_rt_sigprocmask		compat_sys_rt_sigprocmask
+175	nospu	rt_sigpending			sys_rt_sigpending		compat_sys_rt_sigpending
+176	nospu	rt_sigtimedwait			sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
+177	nospu 	rt_sigqueueinfo			sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+178	nospu 	rt_sigsuspend			sys_rt_sigsuspend		compat_sys_rt_sigsuspend
+179	common	pread64				sys_pread64			compat_sys_pread64
+180	common	pwrite64			sys_pwrite64			compat_sys_pwrite64
+181	common	chown				sys_chown
+182	common	getcwd				sys_getcwd
+183	common	capget				sys_capget
+184	common	capset				sys_capset
+185	nospu	sigaltstack			sys_sigaltstack			compat_sys_sigaltstack
+186	32	sendfile			sys_sendfile			compat_sys_sendfile
+186	64	sendfile			sys_sendfile64
+186	spu	sendfile			sys_sendfile64
+187	common	getpmsg				sys_ni_syscall
+188	common 	putpmsg				sys_ni_syscall
+189	nospu	vfork				ppc_vfork
+190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
+191	common	readahead			sys_readahead			compat_sys_readahead
+192	32	mmap2				sys_mmap2			compat_sys_mmap2
+193	32	truncate64			sys_truncate64			compat_sys_truncate64
+194	32	ftruncate64			sys_ftruncate64			compat_sys_ftruncate64
+195	32	stat64				sys_stat64
+196	32	lstat64				sys_lstat64
+197	32	fstat64				sys_fstat64
+198	nospu 	pciconfig_read			sys_pciconfig_read
+199	nospu 	pciconfig_write			sys_pciconfig_write
+200	nospu 	pciconfig_iobase		sys_pciconfig_iobase
+201	common 	multiplexer			sys_ni_syscall
+202	common	getdents64			sys_getdents64
+203	common	pivot_root			sys_pivot_root
+204	32	fcntl64				sys_fcntl64			compat_sys_fcntl64
+205	common	madvise				sys_madvise
+206	common	mincore				sys_mincore
+207	common	gettid				sys_gettid
+208	common	tkill				sys_tkill
+209	common	setxattr			sys_setxattr
+210	common	lsetxattr			sys_lsetxattr
+211	common	fsetxattr			sys_fsetxattr
+212	common	getxattr			sys_getxattr
+213	common	lgetxattr			sys_lgetxattr
+214	common	fgetxattr			sys_fgetxattr
+215	common	listxattr			sys_listxattr
+216	common	llistxattr			sys_llistxattr
+217	common	flistxattr			sys_flistxattr
+218	common	removexattr			sys_removexattr
+219	common	lremovexattr			sys_lremovexattr
+220	common	fremovexattr			sys_fremovexattr
+221	common	futex				sys_futex			compat_sys_futex
+222	common	sched_setaffinity		sys_sched_setaffinity		compat_sys_sched_setaffinity
+223	common	sched_getaffinity		sys_sched_getaffinity		compat_sys_sched_getaffinity
+# 224 unused
+225	common	tuxcall				sys_ni_syscall
+226	32	sendfile64			sys_sendfile64			compat_sys_sendfile64
+227	common	io_setup			sys_io_setup			compat_sys_io_setup
+228	common	io_destroy			sys_io_destroy
+229	common	io_getevents			sys_io_getevents		compat_sys_io_getevents
+230	common	io_submit			sys_io_submit			compat_sys_io_submit
+231	common	io_cancel			sys_io_cancel
+232	nospu	set_tid_address			sys_set_tid_address
+233	common	fadvise64			sys_fadvise64			ppc32_fadvise64
+234	nospu	exit_group			sys_exit_group
+235	nospu	lookup_dcookie			sys_lookup_dcookie		compat_sys_lookup_dcookie
+236	common	epoll_create			sys_epoll_create
+237	common	epoll_ctl			sys_epoll_ctl
+238	common	epoll_wait			sys_epoll_wait
+239	common	remap_file_pages		sys_remap_file_pages
+240	common	timer_create			sys_timer_create		compat_sys_timer_create
+241	common	timer_settime			sys_timer_settime		compat_sys_timer_settime
+242	common	timer_gettime			sys_timer_gettime		compat_sys_timer_gettime
+243	common	timer_getoverrun		sys_timer_getoverrun
+244	common	timer_delete			sys_timer_delete
+245	common	clock_settime			sys_clock_settime		compat_sys_clock_settime
+246	common	clock_gettime			sys_clock_gettime		compat_sys_clock_gettime
+247	common	clock_getres			sys_clock_getres		compat_sys_clock_getres
+248	common	clock_nanosleep			sys_clock_nanosleep		compat_sys_clock_nanosleep
+249	32	swapcontext			ppc_swapcontext			ppc32_swapcontext
+249	64	swapcontext			ppc64_swapcontext
+249	spu	swapcontext			sys_ni_syscall
+250	common	tgkill				sys_tgkill
+251	common	utimes				sys_utimes			compat_sys_utimes
+252	common	statfs64			sys_statfs64			compat_sys_statfs64
+253	common	fstatfs64			sys_fstatfs64			compat_sys_fstatfs64
+254	32	fadvise64_64			ppc_fadvise64_64
+254	spu	fadvise64_64			sys_ni_syscall
+255	common	rtas				sys_rtas
+256	32	sys_debug_setcontext		sys_debug_setcontext		sys_ni_syscall
+256	64	sys_debug_setcontext		sys_ni_syscall
+256	spu	sys_debug_setcontext		sys_ni_syscall
+# 257 reserved for vserver
+258	nospu	migrate_pages			sys_migrate_pages		compat_sys_migrate_pages
+259	nospu	mbind				sys_mbind			compat_sys_mbind
+260	nospu	get_mempolicy			sys_get_mempolicy		compat_sys_get_mempolicy
+261	nospu	set_mempolicy			sys_set_mempolicy		compat_sys_set_mempolicy
+262	nospu	mq_open				sys_mq_open			compat_sys_mq_open
+263	nospu	mq_unlink			sys_mq_unlink
+264	nospu	mq_timedsend			sys_mq_timedsend		compat_sys_mq_timedsend
+265	nospu	mq_timedreceive			sys_mq_timedreceive		compat_sys_mq_timedreceive
+266	nospu	mq_notify			sys_mq_notify			compat_sys_mq_notify
+267	nospu	mq_getsetattr			sys_mq_getsetattr		compat_sys_mq_getsetattr
+268	nospu	kexec_load			sys_kexec_load			compat_sys_kexec_load
+269	nospu	add_key				sys_add_key
+270	nospu	request_key			sys_request_key
+271	nospu	keyctl				sys_keyctl			compat_sys_keyctl
+272	nospu	waitid				sys_waitid			compat_sys_waitid
+273	nospu	ioprio_set			sys_ioprio_set
+274	nospu	ioprio_get			sys_ioprio_get
+275	nospu	inotify_init			sys_inotify_init
+276	nospu	inotify_add_watch		sys_inotify_add_watch
+277	nospu	inotify_rm_watch		sys_inotify_rm_watch
+278	nospu	spu_run				sys_spu_run
+279	nospu	spu_create			sys_spu_create
+280	nospu	pselect6			sys_pselect6			compat_sys_pselect6
+281	nospu	ppoll				sys_ppoll			compat_sys_ppoll
+282	common	unshare				sys_unshare
+283	common	splice				sys_splice
+284	common	tee				sys_tee
+285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+286	common	openat				sys_openat			compat_sys_openat
+287	common	mkdirat				sys_mkdirat
+288	common	mknodat				sys_mknodat
+289	common	fchownat			sys_fchownat
+290	common	futimesat			sys_futimesat			compat_sys_futimesat
+291	32	fstatat64			sys_fstatat64
+291	64	newfstatat			sys_newfstatat
+291	spu	newfstatat			sys_newfstatat
+292	common	unlinkat			sys_unlinkat
+293	common	renameat			sys_renameat
+294	common	linkat				sys_linkat
+295	common	symlinkat			sys_symlinkat
+296	common	readlinkat			sys_readlinkat
+297	common	fchmodat			sys_fchmodat
+298	common	faccessat			sys_faccessat
+299	common	get_robust_list			sys_get_robust_list		compat_sys_get_robust_list
+300	common	set_robust_list			sys_set_robust_list		compat_sys_set_robust_list
+301	common	move_pages			sys_move_pages			compat_sys_move_pages
+302	common	getcpu				sys_getcpu
+303	nospu	epoll_pwait			sys_epoll_pwait			compat_sys_epoll_pwait
+304	common	utimensat			sys_utimensat			compat_sys_utimensat
+305	common	signalfd			sys_signalfd			compat_sys_signalfd
+306	common	timerfd_create			sys_timerfd_create
+307	common	eventfd				sys_eventfd
+308	common	sync_file_range2		sys_sync_file_range2		compat_sys_sync_file_range2
+309	nospu	fallocate			sys_fallocate			compat_sys_fallocate
+310	nospu	subpage_prot			sys_subpage_prot
+311	common	timerfd_settime			sys_timerfd_settime		compat_sys_timerfd_settime
+312	common	timerfd_gettime			sys_timerfd_gettime		compat_sys_timerfd_gettime
+313	common	signalfd4			sys_signalfd4			compat_sys_signalfd4
+314	common	eventfd2			sys_eventfd2
+315	common	epoll_create1			sys_epoll_create1
+316	common	dup3				sys_dup3
+317	common	pipe2				sys_pipe2
+318	nospu	inotify_init1			sys_inotify_init1
+319	common	perf_event_open			sys_perf_event_open
+320	common	preadv				sys_preadv			compat_sys_preadv
+321	common	pwritev				sys_pwritev			compat_sys_pwritev
+322	nospu	rt_tgsigqueueinfo		sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
+323	nospu	fanotify_init			sys_fanotify_init
+324	nospu	fanotify_mark			sys_fanotify_mark		compat_sys_fanotify_mark
+325	common	prlimit64			sys_prlimit64
+326	common	socket				sys_socket
+327	common	bind				sys_bind
+328	common	connect				sys_connect
+329	common	listen				sys_listen
+330	common	accept				sys_accept
+331	common	getsockname			sys_getsockname
+332	common	getpeername			sys_getpeername
+333	common	socketpair			sys_socketpair
+334	common	send				sys_send
+335	common	sendto				sys_sendto
+336	common	recv				sys_recv			compat_sys_recv
+337	common	recvfrom			sys_recvfrom			compat_sys_recvfrom
+338	common	shutdown			sys_shutdown
+339	common	setsockopt			sys_setsockopt			compat_sys_setsockopt
+340	common	getsockopt			sys_getsockopt			compat_sys_getsockopt
+341	common	sendmsg				sys_sendmsg			compat_sys_sendmsg
+342	common	recvmsg				sys_recvmsg			compat_sys_recvmsg
+343	common	recvmmsg			sys_recvmmsg			compat_sys_recvmmsg
+344	common	accept4				sys_accept4
+345	common	name_to_handle_at		sys_name_to_handle_at
+346	common	open_by_handle_at		sys_open_by_handle_at		compat_sys_open_by_handle_at
+347	common	clock_adjtime			sys_clock_adjtime		compat_sys_clock_adjtime
+348	common	syncfs				sys_syncfs
+349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
+350	common	setns				sys_setns
+351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+353	nospu	finit_module			sys_finit_module
+354	nospu	kcmp				sys_kcmp
+355	common	sched_setattr			sys_sched_setattr
+356	common	sched_getattr			sys_sched_getattr
+357	common	renameat2			sys_renameat2
+358	common	seccomp				sys_seccomp
+359	common	getrandom			sys_getrandom
+360	common	memfd_create			sys_memfd_create
+361	common	bpf				sys_bpf
+362	nospu	execveat			sys_execveat			compat_sys_execveat
+363	32	switch_endian			sys_ni_syscall
+363	64	switch_endian			ppc_switch_endian
+363	spu	switch_endian			sys_ni_syscall
+364	common	userfaultfd			sys_userfaultfd
+365	common	membarrier			sys_membarrier
+378	nospu	mlock2				sys_mlock2
+379	nospu	copy_file_range			sys_copy_file_range
+380	common	preadv2				sys_preadv2			compat_sys_preadv2
+381	common	pwritev2			sys_pwritev2			compat_sys_pwritev2
+382	nospu	kexec_file_load			sys_kexec_file_load
+383	nospu	statx				sys_statx
+384	nospu	pkey_alloc			sys_pkey_alloc
+385	nospu	pkey_free			sys_pkey_free
+386	nospu	pkey_mprotect			sys_pkey_mprotect
+387	nospu	rseq				sys_rseq
+388	nospu	io_pgetevents			sys_io_pgetevents		compat_sys_io_pgetevents
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1410d66192f7..63a3afc7f32b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -561,7 +561,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 					break;
 			}
 		}
-		wait4(child_pid, &status, 0, &stat_config.ru_data);
+		if (child_pid != -1)
+			wait4(child_pid, &status, 0, &stat_config.ru_data);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fe3ecfb2e64b..f64e312db787 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1028,12 +1028,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 static int callchain_param__setup_sample_type(struct callchain_param *callchain)
 {
-	if (!perf_hpp_list.sym) {
-		if (callchain->enabled) {
-			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
-			return -EINVAL;
-		}
-	} else if (callchain->mode != CHAIN_NONE) {
+	if (callchain->mode != CHAIN_NONE) {
 		if (callchain_register_param(callchain) < 0) {
 			ui__error("Can't register callchain params.\n");
 			return -EINVAL;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index adbf28183560..ed4583128b9c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1758,6 +1758,7 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 {
 	struct thread_trace *ttrace;
 	size_t printed;
+	int len;
 
 	if (trace->failure_only || trace->current == NULL)
 		return 0;
@@ -1768,9 +1769,14 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 		return 0;
 
 	printed  = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
-	printed += fprintf(trace->output, ")%-*s ...\n", trace->args_alignment, ttrace->entry_str);
-	ttrace->entry_pending = false;
+	printed += len = fprintf(trace->output, "%s)", ttrace->entry_str);
+
+	if (len < trace->args_alignment - 4)
+		printed += fprintf(trace->output, "%-*s", trace->args_alignment - 4 - len, " ");
 
+	printed += fprintf(trace->output, " ...\n");
+
+	ttrace->entry_pending = false;
 	++trace->nr_events_printed;
 
 	return printed;
@@ -2026,9 +2032,10 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (ttrace->entry_pending) {
 		printed = fprintf(trace->output, "%s", ttrace->entry_str);
 	} else {
-		fprintf(trace->output, " ... [");
+		printed += fprintf(trace->output, " ... [");
 		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
-		fprintf(trace->output, "]: %s()", sc->name);
+		printed += 9;
+		printed += fprintf(trace->output, "]: %s()", sc->name);
 	}
 
 	printed++; /* the closing ')' */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 6cb98f8570a2..7b55613924de 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -10,6 +10,7 @@ include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
+include/uapi/linux/mount.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -49,7 +50,6 @@ arch/parisc/include/uapi/asm/errno.h
 arch/powerpc/include/uapi/asm/errno.h
 arch/sparc/include/uapi/asm/errno.h
 arch/x86/include/uapi/asm/errno.h
-arch/powerpc/include/uapi/asm/unistd.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/__fls.h
diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c
index 8c0ca0cc428f..aaa5210ea84a 100644
--- a/tools/perf/perf-read-vdso.c
+++ b/tools/perf/perf-read-vdso.c
@@ -5,17 +5,17 @@
 #define VDSO__MAP_NAME "[vdso]"
 
 /*
- * Include definition of find_vdso_map() also used in util/vdso.c for
+ * Include definition of find_map() also used in util/vdso.c for
  * building perf.
  */
-#include "util/find-vdso-map.c"
+#include "util/find-map.c"
 
 int main(void)
 {
 	void *start, *end;
 	size_t size, written;
 
-	if (find_vdso_map(&start, &end))
+	if (find_map(&start, &end, VDSO__MAP_NAME))
 		return 1;
 
 	size = end - start;
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 1c16e56cd93e..7cb99b433888 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -13,7 +13,8 @@ add_probe_vfs_getname() {
 	local verbose=$1
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string"
+		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
 	fi
 }
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index b82f55fcc294..399f18ca71a3 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -119,4 +119,9 @@ int test__arch_unwind_sample(struct perf_sample *sample,
 			     struct thread *thread);
 #endif
 #endif
+
+#if defined(__arm__)
+int test__vectors_page(struct test *test, int subtest);
+#endif
+
 #endif /* TESTS_H */
diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
index 45547573a1db..847850b2ef6c 100755
--- a/tools/perf/trace/beauty/mount_flags.sh
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -5,11 +5,11 @@
 
 printf "static const char *mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
-egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+egrep $regex ${header_dir}/mount.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
 	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
 	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
-egrep $regex ${header_dir}/fs.h | \
+egrep $regex ${header_dir}/mount.h | \
 	sed -r "s/$regex/\2 \1/g" | \
 	xargs printf "\t[%s + 1] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index d32f8f1124af..3109d7b05e11 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -4,7 +4,7 @@
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
-regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
+regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*'
 egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9805e0bc76..70de8f6b3aee 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1723,15 +1723,14 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 opts->show_asm_raw ? "" : "--no-show-raw",
-		 opts->annotate_src ? "-S" : "",
-		 symfs_filename, symfs_filename);
+		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
@@ -1756,7 +1755,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		close(stdout_fd[0]);
 		dup2(stdout_fd[1], 1);
 		close(stdout_fd[1]);
-		execl("/bin/sh", "sh", "-c", command, NULL);
+		execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
+		      NULL);
 		perror(command);
 		exit(-1);
 	}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 32ef7bdca1cf..dc2212e12184 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -766,6 +766,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->iter_cycles += node->iter_cycles;
+			cnode->from_count++;
 		}
 	}
 
@@ -1345,10 +1346,10 @@ static int branch_to_str(char *bf, int bfsize,
 static int branch_from_str(char *bf, int bfsize,
 			   u64 branch_count,
 			   u64 cycles_count, u64 iter_count,
-			   u64 iter_cycles)
+			   u64 iter_cycles, u64 from_count)
 {
 	int printed = 0, i = 0;
-	u64 cycles;
+	u64 cycles, v = 0;
 
 	cycles = cycles_count / branch_count;
 	if (cycles) {
@@ -1357,14 +1358,16 @@ static int branch_from_str(char *bf, int bfsize,
 				bf + printed, bfsize - printed);
 	}
 
-	if (iter_count) {
-		printed += count_pri64_printf(i++, "iter",
-				iter_count,
-				bf + printed, bfsize - printed);
+	if (iter_count && from_count) {
+		v = iter_count / from_count;
+		if (v) {
+			printed += count_pri64_printf(i++, "iter",
+					v, bf + printed, bfsize - printed);
 
-		printed += count_pri64_printf(i++, "avg_cycles",
-				iter_cycles / iter_count,
-				bf + printed, bfsize - printed);
+			printed += count_pri64_printf(i++, "avg_cycles",
+					iter_cycles / iter_count,
+					bf + printed, bfsize - printed);
+		}
 	}
 
 	if (i)
@@ -1377,6 +1380,7 @@ static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 iter_cycles,
+			     u64 from_count,
 			     struct branch_type_stat *brtype_stat)
 {
 	int printed;
@@ -1389,7 +1393,8 @@ static int counts_str_build(char *bf, int bfsize,
 				predicted_count, abort_count, brtype_stat);
 	} else {
 		printed = branch_from_str(bf, bfsize, branch_count,
-				cycles_count, iter_count, iter_cycles);
+				cycles_count, iter_count, iter_cycles,
+				from_count);
 	}
 
 	if (!printed)
@@ -1402,13 +1407,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 				   u64 branch_count, u64 predicted_count,
 				   u64 abort_count, u64 cycles_count,
 				   u64 iter_count, u64 iter_cycles,
+				   u64 from_count,
 				   struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, iter_cycles, brtype_stat);
+			 iter_count, iter_cycles, from_count, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1422,6 +1428,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	u64 branch_count, predicted_count;
 	u64 abort_count, cycles_count;
 	u64 iter_count, iter_cycles;
+	u64 from_count;
 
 	branch_count = clist->branch_count;
 	predicted_count = clist->predicted_count;
@@ -1429,11 +1436,12 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	cycles_count = clist->cycles_count;
 	iter_count = clist->iter_count;
 	iter_cycles = clist->iter_cycles;
+	from_count = clist->from_count;
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
 				       cycles_count, iter_count, iter_cycles,
-				       &clist->brtype_stat);
+				       from_count, &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 154560b1eb65..99d38ac019b8 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -118,6 +118,7 @@ struct callchain_list {
 		bool		has_children;
 	};
 	u64			branch_count;
+	u64			from_count;
 	u64			predicted_count;
 	u64			abort_count;
 	u64			cycles_count;
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-map.c
similarity index 71%
rename from tools/perf/util/find-vdso-map.c
rename to tools/perf/util/find-map.c
index d7823e3508fc..7b2300588ece 100644
--- a/tools/perf/util/find-vdso-map.c
+++ b/tools/perf/util/find-map.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-static int find_vdso_map(void **start, void **end)
+static int find_map(void **start, void **end, const char *name)
 {
 	FILE *maps;
 	char line[128];
@@ -7,7 +7,7 @@ static int find_vdso_map(void **start, void **end)
 
 	maps = fopen("/proc/self/maps", "r");
 	if (!maps) {
-		fprintf(stderr, "vdso: cannot open maps\n");
+		fprintf(stderr, "cannot open maps\n");
 		return -1;
 	}
 
@@ -21,8 +21,7 @@ static int find_vdso_map(void **start, void **end)
 		if (m < 0)
 			continue;
 
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
+		if (!strncmp(&line[m], name, strlen(name)))
 			found = 1;
 	}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6fcb3bce0442..143f7057d581 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2005,7 +2005,7 @@ static void save_iterations(struct iterations *iter,
 {
 	int i;
 
-	iter->nr_loop_iter = nr;
+	iter->nr_loop_iter++;
 	iter->cycles = 0;
 
 	for (i = 0; i < nr; i++)
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 9005fbe0780e..23092fd6451d 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -109,7 +109,6 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 			return ret;
 		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
-		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
 			va_end(ap_saved);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 01f2c7385e38..48efad6d0f90 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -614,6 +614,7 @@ int modules__parse(const char *filename, void *arg,
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
 		"intel_idle",
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 741af209b19d..3702cba11d7d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -18,10 +18,10 @@
 #include "debug.h"
 
 /*
- * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * Include definition of find_map() also used in perf-read-vdso.c for
  * building perf-read-vdso32 and perf-read-vdsox32.
  */
-#include "find-vdso-map.c"
+#include "find-map.c"
 
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
@@ -76,7 +76,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	if (vdso_file->found)
 		return vdso_file->temp_file_name;
 
-	if (vdso_file->error || find_vdso_map(&start, &end))
+	if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME))
 		return NULL;
 
 	size = end - start;
diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 89a2444c1df2..59e417ec3e13 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -6,7 +6,7 @@ VERSION = 1.0
 
 BINDIR=usr/bin
 WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int
-override CFLAGS+= -O1 ${WARNFLAGS}
+override CFLAGS+= $(call cc-option,-O3,-O1) ${WARNFLAGS}
 # Add "-fstack-protector" only if toolchain supports it.
 override CFLAGS+= $(call cc-option,-fstack-protector-strong)
 CC?= $(CROSS_COMPILE)gcc

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Fri, 30 Nov 2018 07:25:07 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/a1b3cf6d943800059adc262c4d839524c529db2d

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 09d3f015d1e1b4fee7e9bbdcf54201d239393391 uprobes: Fix handle_swbp() vs. unregister() + register() race once more

Misc fixes:

 - a counter freezing related regression fix,
 - an uprobes race fix,
 - an Intel PMU unusual event combination fix,
 - and diverse tooling fixes.

 Thanks,

	Ingo

------------------>
Andrea Parri (1):
      uprobes: Fix handle_swbp() vs. unregister() + register() race once more

Arnaldo Carvalho de Melo (5):
      tools build feature: Check if get_current_dir_name() is available
      tools headers uapi: Synchronize i915_drm.h
      tools arch x86: Update tools's copy of cpufeatures.h
      tools uapi asm-generic: Synchronize ioctls.h
      perf tools beauty ioctl: Support new ISO7816 commands

Jiri Olsa (5):
      perf tools: Fix crash on synthesizing the unit
      perf tools: Restore proper cwd on return from mnt namespace
      perf/x86/intel: Move branch tracing setup to the Intel-specific source file
      perf/x86/intel: Add generic branch tracing check to intel_pmu_has_bts()
      perf/x86/intel: Disallow precise_ip on BTS events

Peter Zijlstra (1):
      perf/x86/intel: Fix regression by default disabling perfmon v4 interrupt handling


 Documentation/admin-guide/kernel-parameters.txt |  3 +-
 arch/x86/events/core.c                          | 20 --------
 arch/x86/events/intel/core.c                    | 68 +++++++++++++++++++------
 arch/x86/events/perf_event.h                    | 13 +++--
 kernel/events/uprobes.c                         | 12 ++++-
 tools/arch/x86/include/asm/cpufeatures.h        |  2 +
 tools/build/Makefile.feature                    |  1 +
 tools/build/feature/Makefile                    |  4 ++
 tools/build/feature/test-all.c                  |  5 ++
 tools/build/feature/test-get_current_dir_name.c | 10 ++++
 tools/include/uapi/asm-generic/ioctls.h         |  2 +
 tools/include/uapi/drm/i915_drm.h               | 22 ++++++++
 tools/perf/Makefile.config                      |  5 ++
 tools/perf/tests/attr/base-record               |  2 +-
 tools/perf/trace/beauty/ioctl.c                 |  1 +
 tools/perf/util/Build                           |  1 +
 tools/perf/util/evsel.c                         |  2 +-
 tools/perf/util/get_current_dir_name.c          | 18 +++++++
 tools/perf/util/namespaces.c                    | 17 ++++++-
 tools/perf/util/namespaces.h                    |  1 +
 tools/perf/util/util.h                          |  4 ++
 21 files changed, 166 insertions(+), 47 deletions(-)
 create mode 100644 tools/build/feature/test-get_current_dir_name.c
 create mode 100644 tools/perf/util/get_current_dir_name.c

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 81d1d5a74728..5463d5a4d85c 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -856,7 +856,8 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
-	disable_counter_freezing [HW]
+	perf_v4_pmi=	[X86,INTEL]
+			Format: <bool>
 			Disable Intel PMU counter freezing feature.
 			The feature only exists starting from
 			Arch Perfmon v4 (Skylake and newer).
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 106911b603bd..374a19712e20 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -438,26 +438,6 @@ int x86_setup_perfctr(struct perf_event *event)
 	if (config == -1LL)
 		return -EINVAL;
 
-	/*
-	 * Branch tracing:
-	 */
-	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !attr->freq && hwc->sample_period == 1) {
-		/* BTS is not supported by this architecture. */
-		if (!x86_pmu.bts_active)
-			return -EOPNOTSUPP;
-
-		/* BTS is currently only allowed for user-mode. */
-		if (!attr->exclude_kernel)
-			return -EOPNOTSUPP;
-
-		/* disallow bts if conflicting events are present */
-		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
-			return -EBUSY;
-
-		event->destroy = hw_perf_lbr_event_destroy;
-	}
-
 	hwc->config |= config;
 
 	return 0;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 273c62e81546..ecc3e34ca955 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2306,14 +2306,18 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	return handled;
 }
 
-static bool disable_counter_freezing;
+static bool disable_counter_freezing = true;
 static int __init intel_perf_counter_freezing_setup(char *s)
 {
-	disable_counter_freezing = true;
-	pr_info("Intel PMU Counter freezing feature disabled\n");
+	bool res;
+
+	if (kstrtobool(s, &res))
+		return -EINVAL;
+
+	disable_counter_freezing = !res;
 	return 1;
 }
-__setup("disable_counter_freezing", intel_perf_counter_freezing_setup);
+__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup);
 
 /*
  * Simplified handler for Arch Perfmon v4:
@@ -2470,16 +2474,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 static struct event_constraint *
 intel_bts_constraints(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-	unsigned int hw_event, bts_event;
-
-	if (event->attr.freq)
-		return NULL;
-
-	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
-	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
-
-	if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
+	if (unlikely(intel_pmu_has_bts(event)))
 		return &bts_constraint;
 
 	return NULL;
@@ -3098,10 +3093,51 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 	return flags;
 }
 
+static int intel_pmu_bts_config(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	if (unlikely(intel_pmu_has_bts(event))) {
+		/* BTS is not supported by this architecture. */
+		if (!x86_pmu.bts_active)
+			return -EOPNOTSUPP;
+
+		/* BTS is currently only allowed for user-mode. */
+		if (!attr->exclude_kernel)
+			return -EOPNOTSUPP;
+
+		/* BTS is not allowed for precise events. */
+		if (attr->precise_ip)
+			return -EOPNOTSUPP;
+
+		/* disallow bts if conflicting events are present */
+		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
+			return -EBUSY;
+
+		event->destroy = hw_perf_lbr_event_destroy;
+	}
+
+	return 0;
+}
+
+static int core_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	return intel_pmu_bts_config(event);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
 
+	if (ret)
+		return ret;
+
+	ret = intel_pmu_bts_config(event);
 	if (ret)
 		return ret;
 
@@ -3127,7 +3163,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		/*
 		 * BTS is set up earlier in this path, so don't account twice
 		 */
-		if (!intel_pmu_has_bts(event)) {
+		if (!unlikely(intel_pmu_has_bts(event))) {
 			/* disallow lbr if conflicting events are present */
 			if (x86_add_exclusive(x86_lbr_exclusive_lbr))
 				return -EBUSY;
@@ -3596,7 +3632,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.enable_all		= core_pmu_enable_all,
 	.enable			= core_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
+	.hw_config		= core_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index adae087cecdd..78d7b7031bfc 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -859,11 +859,16 @@ static inline int amd_pmu_init(void)
 
 static inline bool intel_pmu_has_bts(struct perf_event *event)
 {
-	if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !event->attr.freq && event->hw.sample_period == 1)
-		return true;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int hw_event, bts_event;
+
+	if (event->attr.freq)
+		return false;
+
+	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return false;
+	return hw_event == bts_event && hwc->sample_period == 1;
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 96d4bee83489..322e97bbb437 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -829,7 +829,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	BUG_ON((uprobe->offset & ~PAGE_MASK) +
 			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
 
-	smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+	smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
  out:
@@ -2178,10 +2178,18 @@ static void handle_swbp(struct pt_regs *regs)
 	 * After we hit the bp, _unregister + _register can install the
 	 * new and not-yet-analyzed uprobe at the same address, restart.
 	 */
-	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
 	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
 		goto out;
 
+	/*
+	 * Pairs with the smp_wmb() in prepare_uprobe().
+	 *
+	 * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+	 * we must also see the stores to &uprobe->arch performed by the
+	 * prepare_uprobe() call.
+	 */
+	smp_rmb();
+
 	/* Tracing handlers use ->utask to communicate with fetch methods */
 	if (!get_utask())
 		goto out;
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 89a048c2faec..28c4a502b419 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -331,6 +331,8 @@
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
+#define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
+#define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index f216b2f5c3d7..d74bb9414d7c 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC :=                  \
         dwarf_getlocations              \
         fortify-source                  \
         sync-compare-and-swap           \
+        get_current_dir_name            \
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0516259be70f..304b984f11b9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -7,6 +7,7 @@ FILES=                                          \
          test-dwarf_getlocations.bin            \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
+         test-get_current_dir_name.bin          \
          test-glibc.bin                         \
          test-gtk2.bin                          \
          test-gtk2-infobar.bin                  \
@@ -101,6 +102,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-get_current_dir_name.bin:
+	$(BUILD)
+
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 8dc20a61341f..56722bfe6bdd 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -34,6 +34,10 @@
 # include "test-libelf-mmap.c"
 #undef main
 
+#define main main_test_get_current_dir_name
+# include "test-get_current_dir_name.c"
+#undef main
+
 #define main main_test_glibc
 # include "test-glibc.c"
 #undef main
@@ -174,6 +178,7 @@ int main(int argc, char *argv[])
 	main_test_hello();
 	main_test_libelf();
 	main_test_libelf_mmap();
+	main_test_get_current_dir_name();
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
diff --git a/tools/build/feature/test-get_current_dir_name.c b/tools/build/feature/test-get_current_dir_name.c
new file mode 100644
index 000000000000..573000f93212
--- /dev/null
+++ b/tools/build/feature/test-get_current_dir_name.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <stdlib.h>
+
+int main(void)
+{
+	free(get_current_dir_name());
+	return 0;
+}
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
index 040651735662..cdc9f4ca8c27 100644
--- a/tools/include/uapi/asm-generic/ioctls.h
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -79,6 +79,8 @@
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 #define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816	_IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816	_IOWR('T', 0x43, struct serial_iso7816)
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7f5634ce8e88..a4446f452040 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -529,6 +529,28 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
 
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT	52
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index e30d20fb482d..a0e8c23f9125 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -299,6 +299,11 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-get_current_dir_name), 1)
+  CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
+endif
+
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 37940665f736..efd0157b9d22 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -9,7 +9,7 @@ size=112
 config=0
 sample_period=*
 sample_type=263
-read_format=0
+read_format=0|4
 disabled=1
 inherit=1
 pinned=0
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 5d2a7fd8d407..eae59ad15ce3 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -31,6 +31,7 @@ static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 	"TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
 	"TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT",
 	"TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER",
+	"TIOCGISO7816", "TIOCSISO7816",
 	[_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
 	"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
 	"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ecd9f9ceda77..b7bf201fe8a8 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -10,6 +10,7 @@ libperf-y += evlist.o
 libperf-y += evsel.o
 libperf-y += evsel_fprintf.o
 libperf-y += find_bit.o
+libperf-y += get_current_dir_name.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d37bb1566cd9..dbc0466db368 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1092,7 +1092,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
-	if (evsel->own_cpus)
+	if (evsel->own_cpus || evsel->unit)
 		evsel->attr.read_format |= PERF_FORMAT_ID;
 
 	/*
diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c
new file mode 100644
index 000000000000..267aa609a582
--- /dev/null
+++ b/tools/perf/util/get_current_dir_name.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+#include "util.h"
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdlib.h>
+
+/* Android's 'bionic' library, for one, doesn't have this */
+
+char *get_current_dir_name(void)
+{
+	char pwd[PATH_MAX];
+
+	return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd);
+}
+#endif // HAVE_GET_CURRENT_DIR_NAME
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index cf8bd123cf73..aed170bd4384 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
+#include <asm/bug.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
@@ -186,6 +187,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	char curpath[PATH_MAX];
 	int oldns = -1;
 	int newns = -1;
+	char *oldcwd = NULL;
 
 	if (nc == NULL)
 		return;
@@ -199,9 +201,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
 		return;
 
+	oldcwd = get_current_dir_name();
+	if (!oldcwd)
+		return;
+
 	oldns = open(curpath, O_RDONLY);
 	if (oldns < 0)
-		return;
+		goto errout;
 
 	newns = open(nsi->mntns_path, O_RDONLY);
 	if (newns < 0)
@@ -210,11 +216,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (setns(newns, CLONE_NEWNS) < 0)
 		goto errout;
 
+	nc->oldcwd = oldcwd;
 	nc->oldns = oldns;
 	nc->newns = newns;
 	return;
 
 errout:
+	free(oldcwd);
 	if (oldns > -1)
 		close(oldns);
 	if (newns > -1)
@@ -223,11 +231,16 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 
 void nsinfo__mountns_exit(struct nscookie *nc)
 {
-	if (nc == NULL || nc->oldns == -1 || nc->newns == -1)
+	if (nc == NULL || nc->oldns == -1 || nc->newns == -1 || !nc->oldcwd)
 		return;
 
 	setns(nc->oldns, CLONE_NEWNS);
 
+	if (nc->oldcwd) {
+		WARN_ON_ONCE(chdir(nc->oldcwd));
+		zfree(&nc->oldcwd);
+	}
+
 	if (nc->oldns > -1) {
 		close(nc->oldns);
 		nc->oldns = -1;
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index cae1a9a39722..d5f46c09ea31 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -38,6 +38,7 @@ struct nsinfo {
 struct nscookie {
 	int			oldns;
 	int			newns;
+	char			*oldcwd;
 };
 
 int nsinfo__init(struct nsinfo *nsi);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 14508ee7707a..ece040b799f6 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -59,6 +59,10 @@ int fetch_kernel_version(unsigned int *puint,
 
 const char *perf_tip(const char *dirpath);
 
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif
+
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
 #endif

Re: [GIT PULL] perf fixes

[pr-tracker-bot]

The pull request you sent on Sat, 17 Nov 2018 11:55:18 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b53e27f618b58d50db72375eb8e1b6ddcef7cdb5

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4d47d6407ac7b4b442a4e717488a3bb137398b6c perf/x86/intel/uncore: Support CoffeeLake 8th CBOX

Fix uncore PMU enumeration for CofeeLake CPUs.

 Thanks,

	Ingo

------------------>
Kan Liang (2):
      perf/x86/intel/uncore: Add more IMC PCI IDs for KabyLake and CoffeeLake CPUs
      perf/x86/intel/uncore: Support CoffeeLake 8th CBOX


 arch/x86/events/intel/uncore.h     |  33 +++++++---
 arch/x86/events/intel/uncore_snb.c | 121 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 144 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index e17ab885b1e9..cb46d602a6b8 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -129,8 +129,15 @@ struct intel_uncore_box {
 	struct intel_uncore_extra_reg shared_regs[0];
 };
 
-#define UNCORE_BOX_FLAG_INITIATED	0
-#define UNCORE_BOX_FLAG_CTL_OFFS8	1 /* event config registers are 8-byte apart */
+/* CFL uncore 8th cbox MSRs */
+#define CFL_UNC_CBO_7_PERFEVTSEL0		0xf70
+#define CFL_UNC_CBO_7_PER_CTR0			0xf76
+
+#define UNCORE_BOX_FLAG_INITIATED		0
+/* event config registers are 8-byte apart */
+#define UNCORE_BOX_FLAG_CTL_OFFS8		1
+/* CFL 8th CBOX has different MSR space */
+#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS	2
 
 struct uncore_event_desc {
 	struct kobj_attribute attr;
@@ -297,17 +304,27 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
-	return box->pmu->type->event_ctl +
-		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		uncore_msr_box_offset(box);
+	if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+		return CFL_UNC_CBO_7_PERFEVTSEL0 +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+	} else {
+		return box->pmu->type->event_ctl +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+		       uncore_msr_box_offset(box);
+	}
 }
 
 static inline
 unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
-	return box->pmu->type->perf_ctr +
-		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		uncore_msr_box_offset(box);
+	if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+		return CFL_UNC_CBO_7_PER_CTR0 +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+	} else {
+		return box->pmu->type->perf_ctr +
+		       (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+		       uncore_msr_box_offset(box);
+	}
 }
 
 static inline
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 8527c3e1038b..2593b0d7aeee 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,25 @@
 #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
 #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC	0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC	0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC	0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC	0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC	0x591f
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC	0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC	0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC	0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC	0x3ec4
+#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC	0x3e0f
+#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC	0x3e1f
+#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC	0x3ec2
+#define PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC	0x3e30
+#define PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC	0x3e18
+#define PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC	0x3ec6
+#define PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC	0x3e31
+#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC	0x3e33
+#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC	0x3eca
+#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC	0x3e32
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -202,6 +221,10 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
 			SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
 	}
+
+	/* The 8th CBOX has different MSR space */
+	if (box->pmu->pmu_idx == 7)
+		__set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags);
 }
 
 static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
@@ -228,7 +251,7 @@ static struct intel_uncore_ops skl_uncore_msr_ops = {
 static struct intel_uncore_type skl_uncore_cbox = {
 	.name		= "cbox",
 	.num_counters   = 4,
-	.num_boxes	= 5,
+	.num_boxes	= 8,
 	.perf_ctr_bits	= 44,
 	.fixed_ctr_bits	= 48,
 	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
@@ -569,7 +592,82 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
-
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -618,6 +716,25 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
 	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
 	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
+	IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core Y */
+	IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U */
+	IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U Quad Core */
+	IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core S Dual Core */
+	IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core S Quad Core */
+	IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core U 2 Cores */
+	IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core U 4 Cores */
+	IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core H 4 Cores */
+	IMC_DEV(CFL_6H_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core H 6 Cores */
+	IMC_DEV(CFL_2S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 2 Cores Desktop */
+	IMC_DEV(CFL_4S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Desktop */
+	IMC_DEV(CFL_6S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Desktop */
+	IMC_DEV(CFL_8S_D_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Desktop */
+	IMC_DEV(CFL_4S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Work Station */
+	IMC_DEV(CFL_6S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Work Station */
+	IMC_DEV(CFL_8S_W_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Work Station */
+	IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Server */
+	IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Server */
+	IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Server */
 	{  /* end marker */ }
 };
 

Re: [GIT PULL] perf fixes

[Greg Kroah-Hartman]

On Sat, Oct 20, 2018 at 10:10:39AM +0200, Ingo Molnar wrote:
> Greg,
> 
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

Now merged, thanks.

greg k-h

[GIT PULL] perf fixes

[Ingo Molnar]

Greg,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 20e8e72d0fa8e26202932c30d592bade73fdc701 Merge tag 'perf-urgent-for-mingo-4.19-20181017' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc perf tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (3):
      tools arch uapi: Sync the x86 kvm.h copy
      tools headers uapi: Sync kvm.h copy
      perf tools: Stop fallbacking to kallsyms for vdso symbols lookup

David Miller (1):
      perf cpu_map: Align cpu map synthesized events properly.

Jarod Wilson (1):
      perf tools: Fix use of alternatives to find JDIR

Jiri Olsa (5):
      Revert "perf tools: Fix PMU term format max value calculation"
      perf vendor events intel: Fix wrong filter_band* values for uncore events
      perf evsel: Store ids for events with their own cpus perf_event__synthesize_event_update_cpus
      perf tools: Fix tracing_path_mount proper path
      perf tools: Pass build flags to traceevent build

Milian Wolff (1):
      perf report: Don't crash on invalid inline debug information


 tools/arch/x86/include/uapi/asm/kvm.h              |  1 +
 tools/include/uapi/linux/kvm.h                     |  1 +
 tools/lib/api/fs/tracing_path.c                    |  4 ++--
 tools/perf/Makefile.config                         |  2 +-
 tools/perf/Makefile.perf                           |  2 +-
 tools/perf/builtin-report.c                        |  1 +
 .../pmu-events/arch/x86/ivytown/uncore-power.json  | 16 ++++++++--------
 .../pmu-events/arch/x86/jaketown/uncore-power.json | 16 ++++++++--------
 tools/perf/util/event.c                            | 22 +++-------------------
 tools/perf/util/evsel.c                            |  3 +++
 tools/perf/util/pmu.c                              | 13 +++++++------
 tools/perf/util/srcline.c                          |  3 +++
 12 files changed, 39 insertions(+), 45 deletions(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..fd23d5778ea1 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -377,6 +377,7 @@ struct kvm_sync_regs {
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 07548de5c988..251be353f950 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_HPAGE_1M 156
 #define KVM_CAP_NESTED_STATE 157
 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 120037496f77..5afb11b30fca 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -36,7 +36,7 @@ static const char *tracing_path_tracefs_mount(void)
 
 	__tracing_path_set("", mnt);
 
-	return mnt;
+	return tracing_path;
 }
 
 static const char *tracing_path_debugfs_mount(void)
@@ -49,7 +49,7 @@ static const char *tracing_path_debugfs_mount(void)
 
 	__tracing_path_set("tracing/", mnt);
 
-	return mnt;
+	return tracing_path;
 }
 
 const char *tracing_path_mount(void)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f6d1a03c7523..e30d20fb482d 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -833,7 +833,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
     endif
   endif
   ifndef JDIR
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5224ade3d5af..0be411695379 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -635,7 +635,7 @@ $(LIBPERF_IN): prepare FORCE
 $(LIB_FILE): $(LIBPERF_IN)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS)
 
-LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)'
 
 $(LIBTRACEEVENT): FORCE
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76e12bcd1765..b2188e623e22 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -981,6 +981,7 @@ int cmd_report(int argc, const char **argv)
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_event__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
+			.event_update	 = perf_event__process_event_update,
 			.feature	 = process_feature_event,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
index d40498f2cb1e..635c09fda1d9 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -188,7 +188,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
-        "Filter": "filter_band0=1200",
+        "Filter": "filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -199,7 +199,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
-        "Filter": "filter_band1=2000",
+        "Filter": "filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -210,7 +210,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
-        "Filter": "filter_band2=3000",
+        "Filter": "filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -221,7 +221,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
-        "Filter": "filter_band3=4000",
+        "Filter": "filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
@@ -232,7 +232,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band0=1200",
+        "Filter": "edge=1,filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -243,7 +243,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band1=2000",
+        "Filter": "edge=1,filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -254,7 +254,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band2=4000",
+        "Filter": "edge=1,filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -265,7 +265,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band3=4000",
+        "Filter": "edge=1,filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
index 16034bfd06dd..8755693d86c6 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -187,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
-        "Filter": "filter_band0=1200",
+        "Filter": "filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -198,7 +198,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
-        "Filter": "filter_band1=2000",
+        "Filter": "filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -209,7 +209,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
-        "Filter": "filter_band2=3000",
+        "Filter": "filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -220,7 +220,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
-        "Filter": "filter_band3=4000",
+        "Filter": "filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
@@ -231,7 +231,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band0=1200",
+        "Filter": "edge=1,filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -242,7 +242,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band1=2000",
+        "Filter": "edge=1,filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -253,7 +253,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band2=4000",
+        "Filter": "edge=1,filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -264,7 +264,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band3=4000",
+        "Filter": "edge=1,filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0cd42150f712..bc646185f8d9 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1081,6 +1081,7 @@ void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max
 	}
 
 	*size += sizeof(struct cpu_map_data);
+	*size = PERF_ALIGN(*size, sizeof(u64));
 	return zalloc(*size);
 }
 
@@ -1560,26 +1561,9 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 
 		return NULL;
 	}
-try_again:
+
 	al->map = map_groups__find(mg, al->addr);
-	if (al->map == NULL) {
-		/*
-		 * If this is outside of all known maps, and is a negative
-		 * address, try to look it up in the kernel dso, as it might be
-		 * a vsyscall or vdso (which executes in user-mode).
-		 *
-		 * XXX This is nasty, we should have a symbol list in the
-		 * "[vdso]" dso, but for now lets use the old trick of looking
-		 * in the whole kernel symbol list.
-		 */
-		if (cpumode == PERF_RECORD_MISC_USER && machine &&
-		    mg != &machine->kmaps &&
-		    machine__kernel_ip(machine, al->addr)) {
-			mg = &machine->kmaps;
-			load_map = true;
-			goto try_again;
-		}
-	} else {
+	if (al->map != NULL) {
 		/*
 		 * Kernel maps might be changed when loading symbols so loading
 		 * must be done prior to using kernel maps.
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1a61628a1c12..e596ae358c4d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1089,6 +1089,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
+	if (evsel->own_cpus)
+		evsel->attr.read_format |= PERF_FORMAT_ID;
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index afd68524ffa9..7799788f662f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -930,13 +930,14 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
 
 static __u64 pmu_format_max_value(const unsigned long *format)
 {
-	__u64 w = 0;
-	int fbit;
-
-	for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS)
-		w |= (1ULL << fbit);
+	int w;
 
-	return w;
+	w = bitmap_weight(format, PERF_PMU_FORMAT_BITS);
+	if (!w)
+		return 0;
+	if (w < 64)
+		return (1ULL << w) - 1;
+	return -1;
 }
 
 /*
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 09d6746e6ec8..e767c4a9d4d2 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -85,6 +85,9 @@ static struct symbol *new_inline_sym(struct dso *dso,
 	struct symbol *inline_sym;
 	char *demangled = NULL;
 
+	if (!funcname)
+		funcname = "??";
+
 	if (dso) {
 		demangled = dso__demangle_sym(dso, 0, funcname);
 		if (demangled)

Re: [GIT PULL] perf fixes

[Greg Kroah-Hartman]

On Thu, Oct 11, 2018 at 11:12:02AM +0200, Ingo Molnar wrote:
> 
> Greg,
> 
> Please pull the latest perf-urgent-for-linus git tree from:
> 
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

Now merged, thanks.

greg k-h

[GIT PULL] perf fixes

[Ingo Molnar]

Greg,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c1883f10cfe05c707cce46d6999411c50a2413ca Merge tag 'perf-urgent-for-mingo-4.19-20181005' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc perf tooling fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf script python: Fix export-to-postgresql.py occasional failure
      perf script python: Fix export-to-sqlite.py sample columns

Arnaldo Carvalho de Melo (1):
      perf python: Use -Wno-redundant-decls to build with PYTHON=python3

Milian Wolff (2):
      perf report: Don't try to map ip to invalid map
      perf record: Use unmapped IP for inline callchain cursors


 tools/perf/scripts/python/export-to-postgresql.py | 9 +++++++++
 tools/perf/scripts/python/export-to-sqlite.py     | 6 +++++-
 tools/perf/util/machine.c                         | 8 +++++---
 tools/perf/util/setup.py                          | 2 +-
 4 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index efcaf6cac2eb..e46f51b17513 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -204,14 +204,23 @@ from ctypes import *
 libpq = CDLL("libpq.so.5")
 PQconnectdb = libpq.PQconnectdb
 PQconnectdb.restype = c_void_p
+PQconnectdb.argtypes = [ c_char_p ]
 PQfinish = libpq.PQfinish
+PQfinish.argtypes = [ c_void_p ]
 PQstatus = libpq.PQstatus
+PQstatus.restype = c_int
+PQstatus.argtypes = [ c_void_p ]
 PQexec = libpq.PQexec
 PQexec.restype = c_void_p
+PQexec.argtypes = [ c_void_p, c_char_p ]
 PQresultStatus = libpq.PQresultStatus
+PQresultStatus.restype = c_int
+PQresultStatus.argtypes = [ c_void_p ]
 PQputCopyData = libpq.PQputCopyData
+PQputCopyData.restype = c_int
 PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
 PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.restype = c_int
 PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index f827bf77e9d2..e4bb82c8aba9 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -440,7 +440,11 @@ def branch_type_table(*x):
 
 def sample_table(*x):
 	if branches:
-		bind_exec(sample_query, 18, x)
+		for xx in x[0:15]:
+			sample_query.addBindValue(str(xx))
+		for xx in x[19:22]:
+			sample_query.addBindValue(str(xx))
+		do_query_(sample_query)
 	else:
 		bind_exec(sample_query, 22, x)
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c4acd2001db0..111ae858cbcb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2286,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor,
 	if (!symbol_conf.inline_name || !map || !sym)
 		return ret;
 
-	addr = map__rip_2objdump(map, ip);
+	addr = map__map_ip(map, ip);
+	addr = map__rip_2objdump(map, addr);
 
 	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
 	if (!inline_node) {
@@ -2312,7 +2313,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
-	u64 addr;
+	u64 addr = entry->ip;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2324,7 +2325,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	 * Convert entry->ip from a virtual address to an offset in
 	 * its corresponding binary.
 	 */
-	addr = map__map_ip(entry->map, entry->ip);
+	if (entry->map)
+		addr = map__map_ip(entry->map, entry->ip);
 
 	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 

----- End forwarded message -----

[GIT PULL] perf fixes

[Ingo Molnar]

Greg,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c1883f10cfe05c707cce46d6999411c50a2413ca Merge tag 'perf-urgent-for-mingo-4.19-20181005' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc perf tooling fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (2):
      perf script python: Fix export-to-postgresql.py occasional failure
      perf script python: Fix export-to-sqlite.py sample columns

Arnaldo Carvalho de Melo (1):
      perf python: Use -Wno-redundant-decls to build with PYTHON=python3

Milian Wolff (2):
      perf report: Don't try to map ip to invalid map
      perf record: Use unmapped IP for inline callchain cursors


 tools/perf/scripts/python/export-to-postgresql.py | 9 +++++++++
 tools/perf/scripts/python/export-to-sqlite.py     | 6 +++++-
 tools/perf/util/machine.c                         | 8 +++++---
 tools/perf/util/setup.py                          | 2 +-
 4 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index efcaf6cac2eb..e46f51b17513 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -204,14 +204,23 @@ from ctypes import *
 libpq = CDLL("libpq.so.5")
 PQconnectdb = libpq.PQconnectdb
 PQconnectdb.restype = c_void_p
+PQconnectdb.argtypes = [ c_char_p ]
 PQfinish = libpq.PQfinish
+PQfinish.argtypes = [ c_void_p ]
 PQstatus = libpq.PQstatus
+PQstatus.restype = c_int
+PQstatus.argtypes = [ c_void_p ]
 PQexec = libpq.PQexec
 PQexec.restype = c_void_p
+PQexec.argtypes = [ c_void_p, c_char_p ]
 PQresultStatus = libpq.PQresultStatus
+PQresultStatus.restype = c_int
+PQresultStatus.argtypes = [ c_void_p ]
 PQputCopyData = libpq.PQputCopyData
+PQputCopyData.restype = c_int
 PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
 PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.restype = c_int
 PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index f827bf77e9d2..e4bb82c8aba9 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -440,7 +440,11 @@ def branch_type_table(*x):
 
 def sample_table(*x):
 	if branches:
-		bind_exec(sample_query, 18, x)
+		for xx in x[0:15]:
+			sample_query.addBindValue(str(xx))
+		for xx in x[19:22]:
+			sample_query.addBindValue(str(xx))
+		do_query_(sample_query)
 	else:
 		bind_exec(sample_query, 22, x)
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c4acd2001db0..111ae858cbcb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2286,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor,
 	if (!symbol_conf.inline_name || !map || !sym)
 		return ret;
 
-	addr = map__rip_2objdump(map, ip);
+	addr = map__map_ip(map, ip);
+	addr = map__rip_2objdump(map, addr);
 
 	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
 	if (!inline_node) {
@@ -2312,7 +2313,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
-	u64 addr;
+	u64 addr = entry->ip;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2324,7 +2325,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	 * Convert entry->ip from a virtual address to an offset in
 	 * its corresponding binary.
 	 */
-	addr = map__map_ip(entry->map, entry->ip);
+	if (entry->map)
+		addr = map__map_ip(entry->map, entry->ip);
 
 	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 

Re: [GIT PULL] perf fixes

[Greg Kroah-Hartman]

On Fri, Oct 05, 2018 at 11:55:24AM +0200, Ingo Molnar wrote:
> 
> * Ingo Molnar <mingo@kernel.org> wrote:
> 
> > Linus,
> 
> ... and Greg as well!! ;-)

Heh, not a big deal :)

Now merged, thanks.

greg k-h

Re: [GIT PULL] perf fixes

[Ingo Molnar]

* Ingo Molnar <mingo@kernel.org> wrote:

> Linus,

... and Greg as well!! ;-)

Thanks,

	Ingo

ps. script fixed.

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: d7cbbe49a9304520181fb8c9272d1327deec8453 perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events

Misc fixes:

 - fix a CPU#0 hot unplug bug and a PCI enumeration bug in the x86 Intel uncore PMU driver
 - fix a CPU event enumeration bug in the x86 AMD PMU driver
 - fix a perf ring-buffer corruption bug when using tracepoints
 - fix a PMU unregister locking bug

 Thanks,

	Ingo

------------------>
Jiri Olsa (1):
      perf/ring_buffer: Prevent concurent ring buffer access

Kan Liang (1):
      perf/x86/intel/uncore: Fix PCI BDF address of M3UPI on SKX

Masayoshi Mizuma (1):
      perf/x86/intel/uncore: Use boot_cpu_data.phys_proc_id instead of hardcorded physical package ID 0

Natarajan, Janakarajan (1):
      perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events

Peter Zijlstra (1):
      perf/core: Fix perf_pmu_unregister() locking


 arch/x86/events/amd/uncore.c         | 10 ++++++++++
 arch/x86/events/intel/uncore_snbep.c | 14 +++++++-------
 arch/x86/include/asm/perf_event.h    |  8 ++++++++
 kernel/events/core.c                 | 11 ++++-------
 4 files changed, 29 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e8241b..8671de126eac 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
 
 static int num_counters_llc;
 static int num_counters_nb;
+static bool l3_mask;
 
 static HLIST_HEAD(uncore_unused_list);
 
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events in
+	 * Family 17h. For other events, the two fields do not affect the count.
+	 */
+	if (l3_mask)
+		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l3";
 		format_attr_event_df.show = &event_show_df;
 		format_attr_event_l3.show = &event_show_l3;
+		l3_mask			  = true;
 	} else {
 		num_counters_nb		  = NUM_COUNTERS_NB;
 		num_counters_llc	  = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l2";
 		format_attr_event_df	  = format_attr_event;
 		format_attr_event_l3	  = format_attr_event;
+		l3_mask			  = false;
 	}
 
 	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 51d7c117e3c7..c07bee31abe8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
 
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
 	},
 	{ /* M3UPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
 	},
 	{ /* M3UPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
 	},
 	{ /* M3UPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
 	},
 	{ /* end: all zeroes */ }
 };
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f54082f4c8..78241b736f2a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
 #define INTEL_ARCH_EVENT_MASK	\
 	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
+#define AMD64_L3_SLICE_SHIFT				48
+#define AMD64_L3_SLICE_MASK				\
+	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT				56
+#define AMD64_L3_THREAD_MASK				\
+	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
 	 ARCH_PERFMON_EVENTSEL_UMASK |	\
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dcb093e7b377..5a97f34bc14c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8314,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->cpu != smp_processor_id())
+				continue;
 			if (event->attr.type != PERF_TYPE_TRACEPOINT)
 				continue;
 			if (event->attr.config != entry->type)
@@ -9431,9 +9433,7 @@ static void free_pmu_context(struct pmu *pmu)
 	if (pmu->task_ctx_nr > perf_invalid_context)
 		return;
 
-	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
-	mutex_unlock(&pmus_lock);
 }
 
 /*
@@ -9689,12 +9689,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
-	int remove_device;
-
 	mutex_lock(&pmus_lock);
-	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
-	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -9706,13 +9702,14 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (remove_device) {
+	if (pmu_bus_running) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
 		device_del(pmu->dev);
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
+	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: cb48b6a26cace226d8b299a48c73e808eb0c4f61 Merge tag 'perf-urgent-for-mingo-4.19-20180912' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Mostly tooling fixes, but also breakpoint and x86 PMU driver fixes.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf tools: Fix maps__find_symbol_by_name()

Arnaldo Carvalho de Melo (7):
      perf tools: Streamline bpf examples and headers installation
      tools headers uapi: Update tools's copy of linux/perf_event.h
      tools headers uapi: Update tools's copy of asm-generic/unistd.h
      tools headers uapi: Update tools's copy of drm/drm.h
      tools headers uapi: Update tools's copies of kvm headers
      tools headers uapi: Update tools's copy of linux/vhost.h
      tools headers uapi: Update tools's copy of linux/if_link.h

Chris Phlipot (2):
      perf util: Fix bad memory access in trace info.
      perf event-parse: Use fixed size string for comms

Hisao Tanabe (1):
      perf evsel: Fix potential null pointer dereference in perf_evsel__new_idx()

Jacek Tomaka (1):
      perf/x86/intel: Add support/quirk for the MISPREDICT bit on Knights Landing CPUs

Jiri Olsa (5):
      perf tests: Add breakpoint modify tests
      perf/hw_breakpoint: Modify breakpoint even if the new attr has disabled set
      perf/hw_breakpoint: Remove superfluous bp->attr.disabled = 0
      perf/hw_breakpoint: Enable breakpoint in modify_user_hw_breakpoint
      perf/hw_breakpoint: Simplify breakpoint enable in perf_event_modify_breakpoint

Kim Phillips (2):
      perf arm64: Fix include path for asm-generic/unistd.h
      perf annotate: Fix parsing aarch64 branch instructions after objdump update

Martin Liška (1):
      perf annotate: Properly interpret indirect call

Peter Zijlstra (1):
      perf/UAPI: Clearly mark __PERF_SAMPLE_CALLCHAIN_EARLY as internal use

Sandipan Das (1):
      perf probe powerpc: Ignore SyS symbols irrespective of endianness

Yabin Cui (1):
      perf/core: Force USER_DS when recording user stack data


 arch/x86/events/intel/lbr.c                       |   4 +
 include/uapi/linux/perf_event.h                   |   2 +-
 kernel/events/core.c                              |  15 +-
 kernel/events/hw_breakpoint.c                     |  13 +-
 tools/arch/arm/include/uapi/asm/kvm.h             |  13 ++
 tools/arch/arm64/include/uapi/asm/kvm.h           |  13 ++
 tools/arch/s390/include/uapi/asm/kvm.h            |   5 +-
 tools/arch/x86/include/uapi/asm/kvm.h             |  37 ++++
 tools/include/uapi/asm-generic/unistd.h           |   4 +-
 tools/include/uapi/drm/drm.h                      |   9 +
 tools/include/uapi/linux/if_link.h                |  17 ++
 tools/include/uapi/linux/kvm.h                    |   6 +
 tools/include/uapi/linux/perf_event.h             |   2 +-
 tools/include/uapi/linux/vhost.h                  |  18 ++
 tools/perf/Makefile.perf                          |  14 +-
 tools/perf/arch/arm64/Makefile                    |   5 +-
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl |   6 +-
 tools/perf/arch/powerpc/util/sym-handling.c       |   4 +-
 tools/perf/arch/x86/include/arch-tests.h          |   1 +
 tools/perf/arch/x86/tests/Build                   |   1 +
 tools/perf/arch/x86/tests/arch-tests.c            |   6 +
 tools/perf/arch/x86/tests/bp-modify.c             | 213 ++++++++++++++++++++++
 tools/perf/util/annotate.c                        |  32 +++-
 tools/perf/util/annotate.h                        |   1 +
 tools/perf/util/evsel.c                           |   5 +-
 tools/perf/util/map.c                             |  11 ++
 tools/perf/util/trace-event-info.c                |   2 +-
 tools/perf/util/trace-event-parse.c               |   7 +-
 28 files changed, 423 insertions(+), 43 deletions(-)
 create mode 100644 tools/perf/arch/x86/tests/bp-modify.c

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f3e006bed9a7..c88ed39582a1 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void)
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	/* Knights Landing does have MISPREDICT bit */
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
+		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index eeb787b1c53c..f35eb72739c0 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -144,7 +144,7 @@ enum perf_event_sample_format {
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 
-	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2a62b96600ad..c80549bf82c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp,
 	_perf_event_disable(bp);
 
 	err = modify_user_hw_breakpoint_check(bp, attr, true);
-	if (err) {
-		if (!bp->attr.disabled)
-			_perf_event_enable(bp);
 
-		return err;
-	}
-
-	if (!attr->disabled)
+	if (!bp->attr.disabled)
 		_perf_event_enable(bp);
-	return 0;
+
+	return err;
 }
 
 static int perf_event_modify_attr(struct perf_event *event,
@@ -5948,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 		unsigned long sp;
 		unsigned int rem;
 		u64 dyn_size;
+		mm_segment_t fs;
 
 		/*
 		 * We dump:
@@ -5965,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
+		fs = get_fs();
+		set_fs(USER_DS);
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
+		set_fs(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b3814fce5ecb..d6b56180827c 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
+	int err;
+
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	else
 		perf_event_disable(bp);
 
-	if (!attr->disabled) {
-		int err = modify_user_hw_breakpoint_check(bp, attr, false);
+	err = modify_user_hw_breakpoint_check(bp, attr, false);
 
-		if (err)
-			return err;
+	if (!bp->attr.disabled)
 		perf_event_enable(bp);
-		bp->attr.disabled = 0;
-	}
-	return 0;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
 
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 16e006f708ca..4602464ebdfb 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -27,6 +27,7 @@
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
@@ -125,6 +126,18 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 serror_pending;
+		__u8 serror_has_esr;
+		/* Align it to 8 bytes */
+		__u8 pad[6];
+		__u64 serror_esr;
+	} exception;
+	__u32 reserved[12];
+};
+
 /* If you need to interpret the index values, here is the key: */
 #define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
 #define KVM_REG_ARM_COPROC_SHIFT	16
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 4e76630dd655..97c3478ee6e7 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -39,6 +39,7 @@
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
@@ -154,6 +155,18 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 serror_pending;
+		__u8 serror_has_esr;
+		/* Align it to 8 bytes */
+		__u8 pad[6];
+		__u64 serror_esr;
+	} exception;
+	__u32 reserved[12];
+};
+
 /* If you need to interpret the index values, here is the key: */
 #define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
 #define KVM_REG_ARM_COPROC_SHIFT	16
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 4cdaa55fabfe..9a50f02b9894 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -4,7 +4,7 @@
 /*
  * KVM s390 specific structures and definitions
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008, 2018
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -225,6 +225,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
+#define KVM_SYNC_ETOKEN (1UL << 11)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -258,6 +259,8 @@ struct kvm_sync_regs {
 		struct {
 			__u64 reserved1[2];
 			__u64 gscb[4];
+			__u64 etoken;
+			__u64 etoken_extension;
 		};
 	};
 };
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index c535c2fdea13..86299efa804a 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -378,4 +378,41 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 
+#define KVM_STATE_NESTED_GUEST_MODE	0x00000001
+#define KVM_STATE_NESTED_RUN_PENDING	0x00000002
+
+#define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
+#define KVM_STATE_NESTED_SMM_VMXON	0x00000002
+
+struct kvm_vmx_nested_state {
+	__u64 vmxon_pa;
+	__u64 vmcs_pa;
+
+	struct {
+		__u16 flags;
+	} smm;
+};
+
+/* for KVM_CAP_NESTED_STATE */
+struct kvm_nested_state {
+	/* KVM_STATE_* flags */
+	__u16 flags;
+
+	/* 0 for VMX, 1 for SVM.  */
+	__u16 format;
+
+	/* 128 for SVM, 128 + VMCS size for VMX.  */
+	__u32 size;
+
+	union {
+		/* VMXON, VMCS */
+		struct kvm_vmx_nested_state vmx;
+
+		/* Pad the header to 128 bytes.  */
+		__u8 pad[120];
+	};
+
+	__u8 data[0];
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 42990676a55e..df4bedb9b01c 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 __SYSCALL(__NR_statx,     sys_statx)
 #define __NR_io_pgetevents 292
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+#define __NR_rseq 293
+__SYSCALL(__NR_rseq, sys_rseq)
 
 #undef __NR_syscalls
-#define __NR_syscalls 293
+#define __NR_syscalls 294
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 9c660e1688ab..300f336633f2 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -687,6 +687,15 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ASPECT_RATIO    4
 
+/**
+ * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
+ *
+ * If set to 1, the DRM core will expose special connectors to be used for
+ * writing back to memory the scene setup in the commit. Depends on client
+ * also supporting DRM_CLIENT_CAP_ATOMIC
+ */
+#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index cf01b6824244..43391e2d1153 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -164,6 +164,8 @@ enum {
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
+	IFLA_MIN_MTU,
+	IFLA_MAX_MTU,
 	__IFLA_MAX
 };
 
@@ -334,6 +336,7 @@ enum {
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
+	IFLA_BRPORT_BACKUP_PORT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -459,6 +462,16 @@ enum {
 
 #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
 
+/* XFRM section */
+enum {
+	IFLA_XFRM_UNSPEC,
+	IFLA_XFRM_LINK,
+	IFLA_XFRM_IF_ID,
+	__IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
 enum macsec_validation_type {
 	MACSEC_VALIDATE_DISABLED = 0,
 	MACSEC_VALIDATE_CHECK = 1,
@@ -920,6 +933,7 @@ enum {
 	XDP_ATTACHED_DRV,
 	XDP_ATTACHED_SKB,
 	XDP_ATTACHED_HW,
+	XDP_ATTACHED_MULTI,
 };
 
 enum {
@@ -928,6 +942,9 @@ enum {
 	IFLA_XDP_ATTACHED,
 	IFLA_XDP_FLAGS,
 	IFLA_XDP_PROG_ID,
+	IFLA_XDP_DRV_PROG_ID,
+	IFLA_XDP_SKB_PROG_ID,
+	IFLA_XDP_HW_PROG_ID,
 	__IFLA_XDP_MAX,
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index b6270a3b38e9..07548de5c988 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -949,6 +949,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
 #define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
+#define KVM_CAP_NESTED_STATE 157
+#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1391,6 +1394,9 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_HYPERV_EVENTFD */
 #define KVM_HYPERV_EVENTFD        _IOW(KVMIO,  0xbd, struct kvm_hyperv_eventfd)
 
+/* Available with KVM_CAP_NESTED_STATE */
+#define KVM_GET_NESTED_STATE         _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
+#define KVM_SET_NESTED_STATE         _IOW(KVMIO,  0xbf, struct kvm_nested_state)
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index eeb787b1c53c..f35eb72739c0 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -144,7 +144,7 @@ enum perf_event_sample_format {
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 
-	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
 
 /*
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index c51f8e5cc608..84c3de89696a 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -65,6 +65,7 @@ struct vhost_iotlb_msg {
 };
 
 #define VHOST_IOTLB_MSG 0x1
+#define VHOST_IOTLB_MSG_V2 0x2
 
 struct vhost_msg {
 	int type;
@@ -74,6 +75,15 @@ struct vhost_msg {
 	};
 };
 
+struct vhost_msg_v2 {
+	__u32 type;
+	__u32 reserved;
+	union {
+		struct vhost_iotlb_msg iotlb;
+		__u8 padding[64];
+	};
+};
+
 struct vhost_memory_region {
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
@@ -160,6 +170,14 @@ struct vhost_memory {
 #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,	\
 					 struct vhost_vring_state)
 
+/* Set or get vhost backend capability */
+
+/* Use message type V2 */
+#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+
+#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
+#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
+
 /* VHOST_NET specific defines */
 
 /* Attach virtio net ring to a raw socket, or tap device.
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index b3d1b12a5081..5224ade3d5af 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -777,14 +777,12 @@ endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBBPF
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, include/bpf) \
-		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, examples/bpf) \
-		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-headers) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-examples) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
+		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
 endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index f013b115dc86..dbef716a1913 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/arm64/include/generated/asm
 header := $(out)/syscalls.c
-sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
 sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
 systbl := $(sysprf)/mksyscalltbl
 
@@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, arm64) $(RM) $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 52e197317d3e..2dbb8cade048 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -11,7 +11,8 @@
 
 gcc=$1
 hostcc=$2
-input=$3
+incpath=$3
+input=$4
 
 if ! test -r $input; then
 	echo "Could not read input file" >&2
@@ -28,7 +29,6 @@ create_table_from_c()
 
 	cat <<-_EoHEADER
 		#include <stdio.h>
-		#define __ARCH_WANT_RENAMEAT
 		#include "$input"
 		int main(int argc, char *argv[])
 		{
@@ -42,7 +42,7 @@ create_table_from_c()
 	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
 	printf "}\n"
 
-	} | $hostcc -o $create_table_exe -x c -
+	} | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c -
 
 	$create_table_exe
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 20e7d74d86cd..10a44e946f77 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 
 #endif
 
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
 int arch__choose_best_symbol(struct symbol *syma,
 			     struct symbol *symb __maybe_unused)
 {
 	char *sym = syma->name;
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 	/* Skip over any initial dot */
 	if (*sym == '.')
 		sym++;
+#endif
 
 	/* Avoid "SyS" kernel syscall aliases */
 	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
@@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma,
 	return SYMBOL_A;
 }
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 /* Allow matching against dot variants */
 int arch__compare_symbol_names(const char *namea, const char *nameb)
 {
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index c1bd979b957b..613709cfbbd0 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -9,6 +9,7 @@ struct test;
 int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__bp_modify(struct test *test, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 8e2c5a38c3b9..586849ff83a0 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -5,3 +5,4 @@ libperf-y += arch-tests.o
 libperf-y += rdpmc.o
 libperf-y += perf-time-to-tsc.o
 libperf-$(CONFIG_AUXTRACE) += insn-x86.o
+libperf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index cc1802ff5410..d47d3f8e3c8e 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -23,6 +23,12 @@ struct test arch_tests[] = {
 		.desc = "x86 instruction decoder - new instructions",
 		.func = test__insn_x86,
 	},
+#endif
+#if defined(__x86_64__)
+	{
+		.desc = "x86 bp modify",
+		.func = test__bp_modify,
+	},
 #endif
 	{
 		.func = NULL,
diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c
new file mode 100644
index 000000000000..f53e4406709f
--- /dev/null
+++ b/tools/perf/arch/x86/tests/bp-modify.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <asm/ptrace.h>
+#include <errno.h>
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+static noinline int bp_1(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static noinline int bp_2(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static int spawn_child(void)
+{
+	int child = fork();
+
+	if (child == 0) {
+		/*
+		 * The child sets itself for as tracee and
+		 * waits in signal for parent to trace it,
+		 * then it calls bp_1 and quits.
+		 */
+		int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL);
+
+		if (err) {
+			pr_debug("failed to PTRACE_TRACEME\n");
+			exit(1);
+		}
+
+		raise(SIGCONT);
+		bp_1();
+		exit(0);
+	}
+
+	return child;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it and checks it was properly changed.
+ */
+static int bp_modify1(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_2 function
+	 *  - changes that breakponit to bp_1 function
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_2)) {
+		pr_debug("failed to set breakpoint, 1st time: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint, 2nd time: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it to bogus value and checks the original
+ * breakpoint is hit.
+ */
+static int bp_modify2(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_1 function
+	 *  - tries to change that breakpoint to (-1) address
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (!ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) {
+		pr_debug("failed, breakpoint set to bogus address\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno));
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %s\n",
+			 strerror(errno));
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %s", strerror(errno));
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+int test__bp_modify(struct test *test __maybe_unused,
+		    int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1());
+	TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2());
+
+	return 0;
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 20061cf42288..28cd6a17491b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -246,8 +246,14 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 
 indirect_call:
 	tok = strchr(endptr, '*');
-	if (tok != NULL)
-		ops->target.addr = strtoull(tok + 1, NULL, 16);
+	if (tok != NULL) {
+		endptr++;
+
+		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
+		 * Do not parse such instruction.  */
+		if (strstr(endptr, "(%r") == NULL)
+			ops->target.addr = strtoull(endptr, NULL, 16);
+	}
 	goto find_target;
 }
 
@@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins)
 	return ins->ops == &call_ops || ins->ops == &s390_call_ops;
 }
 
-static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms)
+/*
+ * Prevents from matching commas in the comment section, e.g.:
+ * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
+ */
+static inline const char *validate_comma(const char *c, struct ins_operands *ops)
+{
+	if (ops->raw_comment && c > ops->raw_comment)
+		return NULL;
+
+	return c;
+}
+
+static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
@@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	};
 	const char *c = strchr(ops->raw, ',');
 	u64 start, end;
+
+	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	c = validate_comma(c, ops);
+
 	/*
 	 * Examples of lines to parse for the _cpp_lex_token@@Base
 	 * function:
@@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 		ops->target.addr = strtoull(c, NULL, 16);
 		if (!ops->target.addr) {
 			c = strchr(c, ',');
+			c = validate_comma(c, ops);
 			if (c++ != NULL)
 				ops->target.addr = strtoull(c, NULL, 16);
 		}
@@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
 
 	c = strchr(ops->raw, ',');
+	c = validate_comma(c, ops);
+
 	if (c != NULL) {
 		const char *c2 = strchr(c + 1, ',');
 
+		c2 = validate_comma(c2, ops);
 		/* check for 3-op insn */
 		if (c2 != NULL)
 			c = c2;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 005a5fe8a8c6..5399ba2321bb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -22,6 +22,7 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
+	char	*raw_comment;
 	struct {
 		char	*raw;
 		char	*name;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c980bbff6353..1a61628a1c12 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
 	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
-	if (evsel != NULL)
-		perf_evsel__init(evsel, attr, idx);
+	if (!evsel)
+		return NULL;
+	perf_evsel__init(evsel, attr, idx);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
 		evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 36d0763311ef..6a6929f208b4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -576,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 	return NULL;
 }
 
+static bool map__contains_symbol(struct map *map, struct symbol *sym)
+{
+	u64 ip = map->unmap_ip(map, sym->start);
+
+	return ip >= map->start && ip < map->end;
+}
+
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 					 struct map **mapp)
 {
@@ -591,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
 		if (sym == NULL)
 			continue;
+		if (!map__contains_symbol(pos, sym)) {
+			sym = NULL;
+			continue;
+		}
 		if (mapp != NULL)
 			*mapp = pos;
 		goto out;
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c85d0d1a65ed..7b0ca7cbb7de 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -377,7 +377,7 @@ static int record_ftrace_printk(void)
 
 static int record_saved_cmdline(void)
 {
-	unsigned int size;
+	unsigned long long size;
 	char *path;
 	struct stat st;
 	int ret, err = 0;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 920b1d58a068..e76214f8d596 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent,
 void parse_saved_cmdline(struct tep_handle *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
-	char *comm;
+	char comm[17]; /* Max comm length in the kernel is 16. */
 	char *line;
 	char *next = NULL;
 	int pid;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
-		sscanf(line, "%d %ms", &pid, &comm);
-		tep_register_comm(pevent, comm, pid);
-		free(comm);
+		if (sscanf(line, "%d %16s", &pid, comm) == 2)
+			tep_register_comm(pevent, comm, pid);
 		line = strtok_r(NULL, "\n", &next);
 	}
 }

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 7f635ff187ab6be0b350b3ec06791e376af238ab perf/core: Fix crash when using HW tracing kernel filters

Misc fixes:

 - AMD IBS data corruptor fix (uncovered by UBSAN)
 - an Intel PEBS entry unwind error fix
 - a HW-tracing crash fix
 - a MAINTAINERS update

 Thanks,

	Ingo

------------------>
Ananth N Mavinakayanahalli (1):
      MAINTAINERS: Add Naveen N. Rao as kprobes co-maintainer

Mathieu Poirier (1):
      perf/core: Fix crash when using HW tracing kernel filters

Peter Zijlstra (1):
      perf/x86/intel: Fix unwind errors from PEBS entries (mk-II)

Thomas Gleixner (1):
      perf/x86/amd/ibs: Don't access non-started event


 MAINTAINERS                     |  2 +-
 arch/x86/events/amd/ibs.c       |  6 +++++-
 arch/x86/events/intel/core.c    |  3 +++
 arch/x86/events/intel/ds.c      | 25 +++++++++++--------------
 include/linux/perf_event.h      |  1 +
 include/uapi/linux/perf_event.h |  2 ++
 kernel/events/core.c            | 10 ++++++++--
 7 files changed, 31 insertions(+), 18 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0fe4228f78cb..42a884c1b0f7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7984,7 +7984,7 @@ F:	lib/test_kmod.c
 F:	tools/testing/selftests/kmod/
 
 KPROBES
-M:	Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
+M:	Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 4b98101209a1..d50bb4dc0650 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 {
 	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
 	struct perf_event *event = pcpu->event;
-	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event *hwc;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
@@ -602,6 +602,10 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 		return 0;
 	}
 
+	if (WARN_ON_ONCE(!event))
+		goto fail;
+
+	hwc = &event->hw;
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
 	rdmsrl(msr, *buf);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 707b2a96e516..86f0c15dcc2d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
+
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
 	}
 
 	if (needs_branch_stack(event)) {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8cf03f101938..8dbba77e0518 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1185,17 +1185,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		data->data_src.val = val;
 	}
 
+	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happend between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
 	 * contain a full regs set, specifically it seems to lack segment
 	 * descriptors, which get used by things like user_mode().
 	 *
 	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
-	 *
-	 * We must however always use BP,SP from iregs for the unwinder to stay
-	 * sane; the record BP,SP can point into thin air when the record is
-	 * from a previous PMI context or an (I)RET happend between the record
-	 * and PMI.
 	 */
 	*regs = *iregs;
 
@@ -1214,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->si = pebs->si;
 		regs->di = pebs->di;
 
-		/*
-		 * Per the above; only set BP,SP if we don't need callchains.
-		 *
-		 * XXX: does this make sense?
-		 */
-		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
-			regs->bp = pebs->bp;
-			regs->sp = pebs->sp;
-		}
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
 
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1fa12887ec02..87f6db437e4a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
+extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b8e288a1f740..eeb787b1c53c 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -143,6 +143,8 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8f0434a9951a..eec2d5fb676b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt)
 
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
 	bool kernel = !event->attr.exclude_callchain_kernel;
@@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
-		data->callchain = perf_callchain(event, regs);
+		if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+			data->callchain = perf_callchain(event, regs);
+
 		size += data->callchain->nr;
 
 		header->size += size * sizeof(u64);
@@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
+	/* d_inode(NULL) won't be equal to any mapped user-space file */
+	if (!filter->path.dentry)
+		return false;
+
 	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 6e1d33b24a2b4aebcb05782e937ebc9a7a4a3f50 Merge tag 'perf-urgent-for-mingo-4.18-20180711' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Misc tooling fixes: ptyhon3 related fixes, gcc8 fix, bashism fixes and some other 
smaller fixes.

 Thanks,

	Ingo

------------------>
Janne Huttunen (1):
      perf script python: Fix dict reference counting

Jeremy Cline (7):
      perf tools: Generate a Python script compatible with Python 2 and 3
      perf scripts python: Add Python 3 support to Core.py
      perf scripts python: Add Python 3 support to SchedGui.py
      perf scripts python: Add Python 3 support to Util.py
      perf scripts python: Add Python 3 support to sched-migration.py
      perf scripts python: Add Python 3 support to EventClass.py
      perf tools: Use python-config --includes rather than --cflags

Jiri Olsa (2):
      perf tools: Fix compilation errors on gcc8
      perf stat: Fix --interval_clear option

Kim Phillips (4):
      perf test shell: Replace '|&' with '2>&1 |' to work with more shells
      perf test shell: Make perf's inet_pton test more portable
      perf llvm-utils: Remove bashism from kernel include fetch script
      perf test shell: Prevent temporary editor files from being considered test scripts


 tools/perf/Makefile.config                         |  3 +-
 tools/perf/arch/x86/util/perf_regs.c               |  2 +-
 tools/perf/builtin-stat.c                          |  2 +-
 tools/perf/jvmti/jvmti_agent.c                     |  3 +-
 .../python/Perf-Trace-Util/lib/Perf/Trace/Core.py  | 40 +++++++++-------------
 .../Perf-Trace-Util/lib/Perf/Trace/EventClass.py   |  4 ++-
 .../Perf-Trace-Util/lib/Perf/Trace/SchedGui.py     |  2 +-
 .../python/Perf-Trace-Util/lib/Perf/Trace/Util.py  | 11 +++---
 tools/perf/scripts/python/sched-migration.py       | 14 +++++---
 tools/perf/tests/builtin-test.c                    |  2 +-
 .../tests/shell/record+probe_libc_inet_pton.sh     | 37 +++++++++++---------
 tools/perf/tests/shell/trace+probe_vfs_getname.sh  |  2 +-
 tools/perf/util/llvm-utils.c                       |  6 ++--
 .../util/scripting-engines/trace-event-python.c    | 37 +++++++++-----------
 14 files changed, 84 insertions(+), 81 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b5ac356ba323..f5a3b402589e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -207,8 +207,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 4b2caf6d48e7..fead6b3b4206 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 		else if (rm[2].rm_so != rm[2].rm_eo)
 			prefix[0] = '+';
 		else
-			strncpy(prefix, "+0", 2);
+			scnprintf(prefix, sizeof(prefix), "+0");
 	}
 
 	/* Rename register */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 22547a490e1f..05be023c3f0e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1742,7 +1742,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 		}
 	}
 
-	if ((num_print_interval == 0 && metric_only) || interval_clear)
+	if ((num_print_interval == 0 || interval_clear) && metric_only)
 		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 0c6d1002b524..ac1bcdc17dae 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -35,6 +35,7 @@
 #include <sys/mman.h>
 #include <syscall.h> /* for gettid() */
 #include <err.h>
+#include <linux/kernel.h>
 
 #include "jvmti_agent.h"
 #include "../util/jitdump.h"
@@ -249,7 +250,7 @@ void *jvmti_open(void)
 	/*
 	 * jitdump file name
 	 */
-	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 38dfb720fb6f..54ace2f6bc36 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -31,10 +31,8 @@ symbolic_fields = autodict()
     string = ""
 
     if flag_fields[event_name][field_name]:
-	print_delim = 0
-        keys = flag_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
             if not value and not idx:
                 string += flag_fields[event_name][field_name]['values'][idx]
                 break
@@ -51,14 +49,12 @@ symbolic_fields = autodict()
     string = ""
 
     if symbolic_fields[event_name][field_name]:
-        keys = symbolic_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
             if not value and not idx:
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
-	    if (value == idx):
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
 
     return string
@@ -74,19 +70,17 @@ trace_flags = { 0x00: "NONE", \
     string = ""
     print_delim = 0
 
-    keys = trace_flags.keys()
-
-    for idx in keys:
-	if not value and not idx:
-	    string += "NONE"
-	    break
-
-	if idx and (value & idx) == idx:
-	    if print_delim:
-		string += " | ";
-	    string += trace_flags[idx]
-	    print_delim = 1
-	    value &= ~idx
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
 
     return string
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 81a56cd2b3c1..21a7a1298094 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -8,6 +8,7 @@
 # PerfEvent is the base class for all perf event sample, PebsEvent
 # is a HW base Intel x86 PEBS event, and user could add more SW/HW
 # event classes based on requirements.
+from __future__ import print_function
 
 import struct
 
@@ -44,7 +45,8 @@ EVTYPE_IBS      = 3
                 PerfEvent.event_num += 1
 
         def show(self):
-                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
 
 #
 # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index fdd92f699055..cac7b2542ee8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -11,7 +11,7 @@
 try:
 	import wx
 except ImportError:
-	raise ImportError, "You need to install the wxpython lib for this script"
+	raise ImportError("You need to install the wxpython lib for this script")
 
 
 class RootFrame(wx.Frame):
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index f6c84966e4f8..7384dcb628c4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -5,6 +5,7 @@
 # This software may be distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
+from __future__ import print_function
 
 import errno, os
 
@@ -33,7 +34,7 @@ NSECS_PER_SEC    = 1000000000
     return str
 
 def add_stats(dict, key, value):
-	if not dict.has_key(key):
+	if key not in dict:
 		dict[key] = (value, value, value, 1)
 	else:
 		min, max, avg, count = dict[key]
@@ -72,10 +73,10 @@ audit_package_warned = False
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names.\n" \
-                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
-                    "\n  # yum install audit-libs-python (Fedora)" \
-                    "\n  etc.\n"
+		print("Install the audit-libs-python package to get syscall names.\n"
+                    "For example:\n  # apt-get install python-audit (Ubuntu)"
+                    "\n  # yum install audit-libs-python (Fedora)"
+                    "\n  etc.\n")
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index de66cb3b72c9..3473e7f66081 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -9,13 +9,17 @@
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
-
+from __future__ import print_function
 
 import os
 import sys
 
 from collections import defaultdict
-from UserList import UserList
+try:
+    from UserList import UserList
+except ImportError:
+    # Python 3: UserList moved to the collections package
+    from collections import UserList
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -300,7 +304,7 @@ threads = { 0 : "idle"}
 		if i == -1:
 			return
 
-		for i in xrange(i, len(self.data)):
+		for i in range(i, len(self.data)):
 			timeslice = self.data[i]
 			if timeslice.start > end:
 				return
@@ -336,8 +340,8 @@ threads = { 0 : "idle"}
 		on_cpu_task = self.current_tsk[headers.cpu]
 
 		if on_cpu_task != -1 and on_cpu_task != prev_pid:
-			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
-				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
 
 		threads[prev_pid] = prev_comm
 		threads[next_pid] = next_comm
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2bde505e2e7e..dd850a26d579 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size,
 
 #define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (!is_directory(base, ent))
+		if (!is_directory(base, ent) && ent->d_name[0] != '.')
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 263057039693..94e513e62b34 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -14,35 +14,40 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
-	idx=0
-	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
-		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-	file=`mktemp -u /tmp/perf.data.XXX`
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
 
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $file | while read line ; do
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
 		echo $line
-		echo "$line" | egrep -q "${expected[$idx]}"
+		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
-			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
 			exit 1
 		fi
-		let idx+=1
-		[ -z "${expected[$idx]}" ] && break
 	done
 
 	# If any statements are executed from this point onwards,
@@ -58,6 +63,6 @@ skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
-rm -f ${file}
+rm -f ${perf_data} ${perf_script} ${expected}
 perf probe -q -d probe_libc:inet_pton
 exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 55ad9793d544..4ce276efe6b4 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 976e658e38dc..5e94857dfca2 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -266,16 +266,16 @@ static const char *kinc_fetch_script =
 "#!/usr/bin/env sh\n"
 "if ! test -d \"$KBUILD_DIR\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "TMPDIR=`mktemp -d`\n"
 "if test -z \"$TMPDIR\"\n"
 "then\n"
-"    exit -1\n"
+"    exit 1\n"
 "fi\n"
 "cat << EOF > $TMPDIR/Makefile\n"
 "obj-y := dummy.o\n"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 46e9e19ab1ac..bc32e57d17be 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	if (!dict) {
+	if (!dict)
 		call_object(handler, t, handler_name);
-	} else {
+	else
 		call_object(handler, t, default_handler_name);
-		Py_DECREF(dict);
-	}
 
-	Py_XDECREF(all_entries_dict);
 	Py_DECREF(t);
 }
 
@@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	call_object(handler, t, handler_name);
 
-	Py_DECREF(dict);
 	Py_DECREF(t);
 }
 
@@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
+	fprintf(ofp, "from __future__ import print_function\n\n");
 	fprintf(ofp, "import os\n");
 	fprintf(ofp, "import sys\n\n");
 
@@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "from Core import *\n\n\n");
 
 	fprintf(ofp, "def trace_begin():\n");
-	fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
 
 	fprintf(ofp, "def trace_end():\n");
-	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
@@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			"common_secs, common_nsecs,\n\t\t\t"
 			"common_pid, common_comm)\n\n");
 
-		fprintf(ofp, "\t\tprint \"");
+		fprintf(ofp, "\t\tprint(\"");
 
 		not_first = 0;
 		count = 0;
@@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, ")\n\n");
+		fprintf(ofp, "))\n\n");
 
-		fprintf(ofp, "\t\tprint 'Sample: {'+"
-			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+		fprintf(ofp, "\t\tprint('Sample: {'+"
+			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 		fprintf(ofp, "\t\tfor node in common_callchain:");
 		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
 		fprintf(ofp, "\n\t\t\telse:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
-		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+		fprintf(ofp, "\t\tprint()\n\n");
 
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
 		"event_fields_dict, perf_sample_dict):\n");
 
-	fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
-	fprintf(ofp, "\t\tprint 'Sample: {'+"
-		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+	fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+	fprintf(ofp, "\t\tprint('Sample: {'+"
+		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"
-		"\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-		"(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+		"\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+		"(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
 
 	fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
 		"\treturn delimiter.join"

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 9331510135640429711afbd0c810686100824a79 perf/core: Move inline keyword at the beginning of declaration

Tooling fixes mostly, plus a build warning fix.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf intel-pt: Fix packet decoding of CYC packets

Arnaldo Carvalho de Melo (5):
      tools headers uapi: Synchronize drm/drm.h
      perf tools: Update x86's syscall_64.tbl, adding 'io_pgetevents' and 'rseq'
      tools include powerpc: Update arch/powerpc/include/uapi/asm/unistd.h copy to get 'rseq' syscall
      tools include uapi: Update if_link.h to pick IFLA_{BRPORT_ISOLATED,VXLAN_TTL_INHERIT}
      tools include uapi: Synchronize bpf.h with the kernel

Ingo Molnar (1):
      tools/headers: Pick up latest kernel ABIs

Jiri Olsa (3):
      perf tests: Add event parsing error handling to parse events test
      perf tests: Add valid callback for parse-events test
      perf bench: Fix numa report output code

Mathieu Malaterre (1):
      perf/core: Move inline keyword at the beginning of declaration

Ravi Bangoria (3):
      perf script: Add missing output fields in a hint
      perf script: Fix crash because of missing evsel->priv
      perf tools: Fix crash caused by accessing feat_ops[HEADER_LAST_FEATURE]

Sandipan Das (1):
      perf report powerpc: Fix crash if callchain is empty

Thomas Richter (5):
      perf record: Support s390 random socket_id assignment
      perf test session topology: Fix test on s390
      perf alias: Remove trailing newline when reading sysfs files
      perf alias: Rebuild alias expression string to make it comparable
      perf stat: Remove duplicate event counting

Yonghong Song (1):
      perf tools: Fix a clang 7.0 compilation error


 kernel/events/core.c                               |  2 +-
 tools/arch/arm/include/uapi/asm/kvm.h              |  1 +
 tools/arch/arm64/include/uapi/asm/kvm.h            |  1 +
 tools/arch/powerpc/include/uapi/asm/kvm.h          |  1 +
 tools/arch/powerpc/include/uapi/asm/unistd.h       |  1 +
 tools/arch/x86/include/asm/cpufeatures.h           |  2 +
 tools/include/uapi/drm/drm.h                       |  7 ++
 tools/include/uapi/linux/bpf.h                     |  2 +-
 tools/include/uapi/linux/if_link.h                 |  2 +
 tools/include/uapi/linux/kvm.h                     |  1 +
 tools/perf/arch/powerpc/util/skip-callchain-idx.c  |  2 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  2 +
 tools/perf/bench/numa.c                            |  5 +-
 tools/perf/builtin-annotate.c                      | 11 ++-
 tools/perf/builtin-report.c                        |  3 +-
 tools/perf/builtin-script.c                        | 30 ++++++-
 tools/perf/tests/parse-events.c                    | 25 ++++--
 tools/perf/tests/topology.c                        |  1 +
 tools/perf/util/c++/clang.cpp                      | 11 ++-
 tools/perf/util/header.c                           | 12 ++-
 .../util/intel-pt-decoder/intel-pt-pkt-decoder.c   |  2 +-
 tools/perf/util/pmu.c                              | 99 +++++++++++++++++++++-
 22 files changed, 201 insertions(+), 22 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..8f0434a9951a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6482,7 +6482,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
-static void __always_inline
+static __always_inline void
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index caae4843cb70..16e006f708ca 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 04b3256f8e6d..4e76630dd655 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
 #define KVM_VGIC_ITS_ADDR_TYPE		4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION	5
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 833ed9a16adf..1b32b56a03d3 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index 389c36fd8299..ac5ba55066dd 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -398,5 +398,6 @@
 #define __NR_pkey_alloc		384
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
+#define __NR_rseq		387
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index fb00a2fca990..5701f5cecd31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -282,7 +282,9 @@
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ATOMIC	3
 
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0b06784f227..59b19b6a40d7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2630,7 +2630,7 @@ struct bpf_fib_lookup {
 	union {
 		/* inputs to lookup */
 		__u8	tos;		/* AF_INET  */
-		__be32	flowlabel;	/* AF_INET6 */
+		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
 
 		/* output: metric of fib result (IPv4/IPv6 only) */
 		__u32	rt_metric;
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 68699f654118..cf01b6824244 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
 	IFLA_BRPORT_BCAST_FLOOD,
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
+	IFLA_BRPORT_ISOLATED,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
 	IFLA_VXLAN_COLLECT_METADATA,
 	IFLA_VXLAN_LABEL,
 	IFLA_VXLAN_GPE,
+	IFLA_VXLAN_TTL_INHERIT,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 39e364c70caf..b6270a3b38e9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_BPB 152
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..ef5d59a5742e 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -243,7 +243,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	u64 ip;
 	u64 skip_slot = -1;
 
-	if (chain->nr < 3)
+	if (!chain || chain->nr < 3)
 		return skip_slot;
 
 	ip = chain->ips[2];
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
 330	common	pkey_alloc		__x64_sys_pkey_alloc
 331	common	pkey_free		__x64_sys_pkey_free
 332	common	statx			__x64_sys_statx
+333	common	io_pgetevents		__x64_sys_io_pgetevents
+334	common	rseq			__x64_sys_rseq
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..8180319285af 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ static int process_sample_event(struct perf_tool *tool,
 	return ret;
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
-			.feature	= perf_event__process_feature,
+			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..c04dc7b53797 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
 	}
 
 	/*
-	 * All features are received, we can force the
+	 * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+	 * means all features are received, now we can force the
 	 * group if needed.
 	 */
 	setup_forced_leader(rep, session->evlist);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a31d7082188e..568ddfac3213 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel, *pos;
 	int err;
+	static struct perf_evsel_script *es;
 
 	err = perf_event__process_attr(tool, event, pevlist);
 	if (err)
@@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
+	if (!evsel->priv) {
+		if (scr->per_event_dump) {
+			evsel->priv = perf_evsel_script__new(evsel,
+						scr->session->data);
+		} else {
+			es = zalloc(sizeof(*es));
+			if (!es)
+				return -ENOMEM;
+			es->fp = stdout;
+			evsel->priv = es;
+		}
+	}
+
 	if (evsel->attr.type >= PERF_TYPE_MAX &&
 	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
@@ -3030,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+	return 0;
+}
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 static int perf_script__process_auxtrace_info(struct perf_tool *tool,
 					      union perf_event *event,
@@ -3074,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_script__process_auxtrace_info,
@@ -3125,8 +3148,9 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7d4077068454..61211918bfba 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static bool test__intel_pt_valid(void)
+{
+	return !!perf_pmu__find("intel_pt");
+}
+
 static int test__intel_pt(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1375,6 +1380,7 @@ struct evlist_test {
 	const char *name;
 	__u32 type;
 	const int id;
+	bool (*valid)(void);
 	int (*check)(struct perf_evlist *evlist);
 };
 
@@ -1648,6 +1654,7 @@ static struct evlist_test test__events[] = {
 	},
 	{
 		.name  = "intel_pt//u",
+		.valid = test__intel_pt_valid,
 		.check = test__intel_pt,
 		.id    = 52,
 	},
@@ -1686,17 +1693,24 @@ static struct terms_test test__terms[] = {
 
 static int test_event(struct evlist_test *e)
 {
+	struct parse_events_error err = { .idx = 0, };
 	struct perf_evlist *evlist;
 	int ret;
 
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP");
+		return 0;
+	}
+
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, NULL);
+	ret = parse_events(evlist, e->name, &err);
 	if (ret) {
-		pr_debug("failed to parse event '%s', err %d\n",
-			 e->name, ret);
+		pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+			 e->name, ret, err.str);
+		parse_events_print_error(&err, e->name);
 	} else {
 		ret = e->check(evlist);
 	}
@@ -1714,10 +1728,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", e->id, e->name);
+		pr_debug("running test %d '%s'", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
+		pr_debug("\n");
 	}
 
 	return ret2;
@@ -1799,7 +1814,7 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-		struct evlist_test e;
+		struct evlist_test e = { .id = 0, };
 		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 40e30a26b23c..9497d02f69e6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -45,6 +45,7 @@ static int session_write_header(char *path)
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
 	perf_header__set_feat(&session->header, HEADER_NRCPUS);
+	perf_header__set_feat(&session->header, HEADER_ARCH);
 
 	session->header.data_size += DATA_SIZE;
 
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index bf31ceab33bd..89512504551b 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
 	raw_svector_ostream ostream(*Buffer);
 
 	legacy::PassManager PM;
-	if (TargetMachine->addPassesToEmitFile(PM, ostream,
-					       TargetMachine::CGFT_ObjectFile)) {
+	bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+						      TargetMachine::CGFT_ObjectFile);
+#else
+	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+						      TargetMachine::CGFT_ObjectFile);
+#endif
+	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
 		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
 	}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 540cd2dcd3e7..653ff65aa2c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2129,6 +2129,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
 	struct perf_header *ph = ff->ph;
+	bool do_core_id_test = true;
 
 	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
 	if (!ph->env.cpu)
@@ -2183,6 +2184,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		return 0;
 	}
 
+	/* On s390 the socket_id number is not related to the numbers of cpus.
+	 * The socket_id number might be higher than the numbers of cpus.
+	 * This depends on the configuration.
+	 */
+	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+		do_core_id_test = false;
+
 	for (i = 0; i < (u32)cpu_nr; i++) {
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2192,7 +2200,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
 
-		if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+		if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
 			pr_debug("socket_id number is too big."
 				 "You may need to upgrade the perf tool.\n");
 			goto free_cpu;
@@ -3456,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return 0;
 	}
-	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+	if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
 		return -1;
 	}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d2fb597c9a8c..3ba6a1742f91 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+				char **new_str)
+{
+	if (!*old_str)
+		goto set_new;
+
+	if (*new_str) {	/* Have new string, check with old */
+		if (strcasecmp(*old_str, *new_str))
+			pr_debug("alias %s differs in field '%s'\n",
+				 name, field);
+		zfree(old_str);
+	} else		/* Nothing new --> keep old string */
+		return;
+set_new:
+	*old_str = *new_str;
+	*new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+				  struct perf_pmu_alias *newalias)
+{
+	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+			    &newalias->long_desc);
+	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+	perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+			    &newalias->metric_expr);
+	perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+			    &newalias->metric_name);
+	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+	old->scale = newalias->scale;
+	old->per_pkg = newalias->per_pkg;
+	old->snapshot = newalias->snapshot;
+	memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+	zfree(&newalias->name);
+	zfree(&newalias->desc);
+	zfree(&newalias->long_desc);
+	zfree(&newalias->topic);
+	zfree(&newalias->str);
+	zfree(&newalias->metric_expr);
+	zfree(&newalias->metric_name);
+	parse_events_terms__purge(&newalias->terms);
+	free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+				 struct list_head *alist)
+{
+	struct perf_pmu_alias *a;
+
+	list_for_each_entry(a, alist, list) {
+		if (!strcasecmp(newalias->name, a->name)) {
+			perf_pmu_update_alias(a, newalias);
+			perf_pmu_free_alias(newalias);
+			return true;
+		}
+	}
+	return false;
+}
+
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
@@ -241,9 +309,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *metric_expr,
 				 char *metric_name)
 {
+	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
 	int num;
+	char newval[256];
 
 	alias = malloc(sizeof(*alias));
 	if (!alias)
@@ -262,6 +332,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		return ret;
 	}
 
+	/* Scan event and remove leading zeroes, spaces, newlines, some
+	 * platforms have terms specified as
+	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
+	 * and terms specified as event=0x91 (read from JSON files).
+	 *
+	 * Rebuild string to make alias->str member comparable.
+	 */
+	memset(newval, 0, sizeof(newval));
+	ret = 0;
+	list_for_each_entry(term, &alias->terms, list) {
+		if (ret)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 ",");
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%#x", term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			ret += scnprintf(newval + ret, sizeof(newval) - ret,
+					 "%s=%s", term->config, term->val.str);
+	}
+
 	alias->name = strdup(name);
 	if (dir) {
 		/*
@@ -285,9 +376,10 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
-	alias->str = strdup(val);
+	alias->str = strdup(newval);
 
-	list_add_tail(&alias->list, list);
+	if (!perf_pmu_merge_alias(alias, list))
+		list_add_tail(&alias->list, list);
 
 	return 0;
 }
@@ -303,6 +395,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
+	/* Remove trailing newline from sysfs file */
+	rtrim(buf);
+
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
 				     NULL, NULL, NULL);
 }

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4e9ae0d3d5bf4e2f1b466ba451bd18f2c5b69845 Merge tag 'perf-urgent-for-mingo-4.17-20180602' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Leftover perf tooling fixes from the v4.17 cycle: they sync up updated ABI headers 
with their tooling versions.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf trace beauty prctl: Default header_dir to cwd to work without parms
      tools headers: Synchronize prctl.h ABI header
      tools headers: Sync x86 cpufeatures.h with the kernel sources
      perf tools intel-pt-decoder: Update insn.h from the kernel sources


 tools/arch/x86/include/asm/cpufeatures.h | 20 ++++++++++++++------
 tools/include/uapi/linux/prctl.h         | 12 ++++++++++++
 tools/perf/trace/beauty/prctl_option.sh  |  2 +-
 tools/perf/util/intel-pt-decoder/insn.h  | 18 ++++++++++++++++++
 4 files changed, 45 insertions(+), 7 deletions(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 578793e97431..fb00a2fca990 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -334,6 +340,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
  * BUG word(s)
@@ -363,5 +370,6 @@
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index af5f8c2df87a..db9f15f5db04 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -207,4 +207,16 @@ struct prctl_mm_map {
 # define PR_SVE_VL_LEN_MASK		0xffff
 # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL		52
+#define PR_SET_SPECULATION_CTRL		53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS		0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED		0
+# define PR_SPEC_PRCTL			(1UL << 0)
+# define PR_SPEC_ENABLE			(1UL << 1)
+# define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 0be4138fbe71..f24722146ebe 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
 regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index e23578c7b1be..2669c9f748e4 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
 #endif /* _ASM_X86_INSN_H */

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: f67b15037a7a50c57f72e69a6d59941ad90a0f0f perf/hwbp: Simplify the perf-hwbp code, fix documentation

Two fixlets.

 Thanks,

	Ingo

------------------>
Linus Torvalds (1):
      perf/hwbp: Simplify the perf-hwbp code, fix documentation

Stephane Eranian (1):
      perf/x86/intel: Fix linear IP of PEBS real_ip on Haswell and later CPUs


 arch/x86/events/intel/ds.c    | 25 +++++++++++++++++--------
 kernel/events/hw_breakpoint.c | 30 +++++++-----------------------
 2 files changed, 24 insertions(+), 31 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index d8015235ba76..5e526c54247e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1153,6 +1153,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	if (pebs == NULL)
 		return;
 
+	regs->flags &= ~PERF_EFLAGS_EXACT;
 	sample_type = event->attr.sample_type;
 	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
 
@@ -1197,7 +1198,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	 */
 	*regs = *iregs;
 	regs->flags = pebs->flags;
-	set_linear_ip(regs, pebs->ip);
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		regs->ax = pebs->ax;
@@ -1233,13 +1233,22 @@ static void setup_pebs_sample_data(struct perf_event *event,
 #endif
 	}
 
-	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
-		regs->ip = pebs->real_ip;
-		regs->flags |= PERF_EFLAGS_EXACT;
-	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
-		regs->flags |= PERF_EFLAGS_EXACT;
-	else
-		regs->flags &= ~PERF_EFLAGS_EXACT;
+	if (event->attr.precise_ip > 1) {
+		/* Haswell and later have the eventing IP, so use it: */
+		if (x86_pmu.intel_cap.pebs_format >= 2) {
+			set_linear_ip(regs, pebs->real_ip);
+			regs->flags |= PERF_EFLAGS_EXACT;
+		} else {
+			/* Otherwise use PEBS off-by-1 IP: */
+			set_linear_ip(regs, pebs->ip);
+
+			/* ... and try to fix it up using the LBR entries: */
+			if (intel_pmu_pebs_fixup_ip(regs))
+				regs->flags |= PERF_EFLAGS_EXACT;
+		}
+	} else
+		set_linear_ip(regs, pebs->ip);
+
 
 	if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 3f8cb1e14588..253ae2da13c3 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -427,16 +427,9 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
  * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
  * @bp: the breakpoint structure to modify
  * @attr: new breakpoint attributes
- * @triggered: callback to trigger when we hit the breakpoint
- * @tsk: pointer to 'task_struct' of the process to which the address belongs
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
-	u64 old_addr = bp->attr.bp_addr;
-	u64 old_len = bp->attr.bp_len;
-	int old_type = bp->attr.bp_type;
-	int err = 0;
-
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -451,27 +444,18 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	bp->attr.bp_addr = attr->bp_addr;
 	bp->attr.bp_type = attr->bp_type;
 	bp->attr.bp_len = attr->bp_len;
+	bp->attr.disabled = 1;
 
-	if (attr->disabled)
-		goto end;
-
-	err = validate_hw_breakpoint(bp);
-	if (!err)
-		perf_event_enable(bp);
+	if (!attr->disabled) {
+		int err = validate_hw_breakpoint(bp);
 
-	if (err) {
-		bp->attr.bp_addr = old_addr;
-		bp->attr.bp_type = old_type;
-		bp->attr.bp_len = old_len;
-		if (!bp->attr.disabled)
-			perf_event_enable(bp);
+		if (err)
+			return err;
 
-		return err;
+		perf_event_enable(bp);
+		bp->attr.disabled = 0;
 	}
 
-end:
-	bp->attr.disabled = attr->disabled;
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: c917e0f259908e75bd2a65877e25f9d90c22c848 perf/cgroup: Fix child event counting bug

Misc kernel side fixes:

 - a cgroup events counting fix
 - an x86 Intel PMU truncated-parameter fix
 - an x86 RDPMC fix
 - an x86 API naming fix/rename
 - an x86 uncore driver big-hardware PCI enumeration fix
 - an x86 uncore driver filter constraint fix

 Thanks,

	Ingo

------------------>
Dan Carpenter (1):
      perf/x86/intel: Don't accidentally clear high bits in bdw_limit_period()

Kan Liang (3):
      perf/x86/intel: Disable userspace RDPMC usage for large PEBS
      perf/x86/intel: Rename confusing 'freerunning PEBS' API and implementation to 'large PEBS'
      perf/x86/intel/uncore: Fix multi-domain PCI CHA enumeration bug on Skylake servers

Song Liu (1):
      perf/cgroup: Fix child event counting bug

Stephane Eranian (1):
      perf/x86/intel/uncore: Add missing filter constraint for SKX CHA event


 arch/x86/events/core.c               |  3 ++-
 arch/x86/events/intel/core.c         | 14 +++++++-------
 arch/x86/events/intel/ds.c           |  6 +++---
 arch/x86/events/intel/uncore_snbep.c | 32 ++++++++++++++++++--------------
 arch/x86/events/perf_event.h         |  6 +++---
 kernel/events/core.c                 | 21 ++++++++++++++++-----
 6 files changed, 49 insertions(+), 33 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 140d33288e78..88797c80b3e0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2118,7 +2118,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 			event->destroy(event);
 	}
 
-	if (READ_ONCE(x86_pmu.attr_rdpmc))
+	if (READ_ONCE(x86_pmu.attr_rdpmc) &&
+	    !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
 		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
 
 	return err;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 56457cb73448..1e41d7508d99 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2952,9 +2952,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
 	return intel_pebs_aliases_precdist(event);
 }
 
-static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 {
-	unsigned long flags = x86_pmu.free_running_flags;
+	unsigned long flags = x86_pmu.large_pebs_flags;
 
 	if (event->attr.use_clockid)
 		flags &= ~PERF_SAMPLE_TIME;
@@ -2976,8 +2976,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (!event->attr.freq) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
-			      ~intel_pmu_free_running_flags(event)))
-				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+			      ~intel_pmu_large_pebs_flags(event)))
+				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
@@ -3194,7 +3194,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
 			X86_CONFIG(.event=0xc0, .umask=0x01)) {
 		if (left < 128)
 			left = 128;
-		left &= ~0x3fu;
+		left &= ~0x3fULL;
 	}
 	return left;
 }
@@ -3460,7 +3460,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32-bit width,
@@ -3502,7 +3502,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32 bit width,
 	 * so we install an artificial 1<<31 period regardless of
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 18c25ab28557..d8015235ba76 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs++;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs--;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -1530,7 +1530,7 @@ void __init intel_ds_init(void)
 			x86_pmu.pebs_record_size =
 						sizeof(struct pebs_record_skl);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
-			x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
 		default:
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 22ec65bc033a..c98b943e58b4 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3),
 	EVENT_EXTRA_END
 };
 
@@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
 	NULL,
 };
 
+/*
+ * To determine the number of CHAs, it should read bits 27:0 in the CAPID6
+ * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083.
+ */
+#define SKX_CAPID6		0x9c
+#define SKX_CHA_BIT_MASK	GENMASK(27, 0)
+
 static int skx_count_chabox(void)
 {
-	struct pci_dev *chabox_dev = NULL;
-	int bus, count = 0;
+	struct pci_dev *dev = NULL;
+	u32 val = 0;
 
-	while (1) {
-		chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
-		if (!chabox_dev)
-			break;
-		if (count == 0)
-			bus = chabox_dev->bus->number;
-		if (bus != chabox_dev->bus->number)
-			break;
-		count++;
-	}
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev);
+	if (!dev)
+		goto out;
 
-	pci_dev_put(chabox_dev);
-	return count;
+	pci_read_config_dword(dev, SKX_CAPID6, &val);
+	val &= SKX_CHA_BIT_MASK;
+out:
+	pci_dev_put(dev);
+	return hweight32(val);
 }
 
 void skx_uncore_cpu_init(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78f91ec1056e..39cd0615f04f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -69,7 +69,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
 
 
 struct amd_nb {
@@ -88,7 +88,7 @@ struct amd_nb {
  * REGS_USER can be handled for events limited to ring 3.
  *
  */
-#define PEBS_FREERUNNING_FLAGS \
+#define LARGE_PEBS_FLAGS \
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
@@ -608,7 +608,7 @@ struct x86_pmu {
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	int 		max_pebs_events;
-	unsigned long	free_running_flags;
+	unsigned long	large_pebs_flags;
 
 	/*
 	 * Intel LBR
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4b838470fac4..709a55b9ad97 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -724,9 +724,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
-	if (cgrp_out)
-		__update_cgrp_time(cgrp_out);
+	struct perf_cgroup *cgrp = cpuctx->cgrp;
+	struct cgroup_subsys_state *css;
+
+	if (cgrp) {
+		for (css = &cgrp->css; css; css = css->parent) {
+			cgrp = container_of(css, struct perf_cgroup, css);
+			__update_cgrp_time(cgrp);
+		}
+	}
 }
 
 static inline void update_cgrp_time_from_event(struct perf_event *event)
@@ -754,6 +760,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 	struct perf_cgroup *cgrp;
 	struct perf_cgroup_info *info;
+	struct cgroup_subsys_state *css;
 
 	/*
 	 * ctx->lock held by caller
@@ -764,8 +771,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 		return;
 
 	cgrp = perf_cgroup_from_task(task, ctx);
-	info = this_cpu_ptr(cgrp->info);
-	info->timestamp = ctx->timestamp;
+
+	for (css = &cgrp->css; css; css = css->parent) {
+		cgrp = container_of(css, struct perf_cgroup, css);
+		info = this_cpu_ptr(cgrp->info);
+		info->timestamp = ctx->timestamp;
+	}
 }
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 59410f5ac70a0949a6f06ba43eecb8f99be31291 Merge tag 'perf-urgent-for-mingo-4.16-20180205' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Tooling fixes, plus add missing interval sampling to certain x86 PEBS events.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (5):
      tools headers: Synchronize sound/asound.h
      tooling headers: Synchronize updated s390 kvm UAPI headers
      tools headers: Sync {tools/,}arch/powerpc/include/uapi/asm/kvm.h
      tools headers: Synchronize uapi/linux/sched.h
      tools headers: Synchoronize x86 features UAPI headers

Jiri Olsa (3):
      perf evsel: Fix period/freq terms setup
      perf record: Fix period option handling
      x86/events/intel/ds: Add PERF_SAMPLE_PERIOD into PEBS_FREERUNNING_FLAGS

Ravi Bangoria (2):
      perf trace: Fix call-graph output
      perf tools: Add trace/beauty/generated/ into .gitignore


 arch/x86/events/perf_event.h                   |  3 ++-
 tools/arch/powerpc/include/uapi/asm/kvm.h      | 25 +++++++++++++++++++++++++
 tools/arch/s390/include/uapi/asm/kvm.h         |  5 ++++-
 tools/arch/x86/include/asm/cpufeatures.h       | 24 ++++++++++++++++++++----
 tools/arch/x86/include/asm/disabled-features.h |  3 ++-
 tools/arch/x86/include/asm/required-features.h |  3 ++-
 tools/include/uapi/linux/kvm.h                 |  4 ++++
 tools/include/uapi/linux/sched.h               |  5 +++++
 tools/include/uapi/sound/asound.h              |  9 +++++++++
 tools/perf/.gitignore                          |  1 +
 tools/perf/builtin-record.c                    |  3 ++-
 tools/perf/builtin-trace.c                     |  5 ++++-
 tools/perf/perf.h                              |  1 +
 tools/perf/util/evsel.c                        | 13 ++++++++++---
 14 files changed, 91 insertions(+), 13 deletions(-)

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8e4ea143ed96..78f91ec1056e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -93,7 +93,8 @@ struct amd_nb {
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
-	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
+	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
+	PERF_SAMPLE_PERIOD)
 
 #define PEBS_REGS \
 	(PERF_REG_X86_AX | \
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 61d6049f4c1e..637b7263cb86 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
 	__u32	ap_encodings[8];
 };
 
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 38535a57fef8..4cdaa55fabfe 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -224,6 +224,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -247,7 +248,9 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
+	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
 	union {
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 21ac898df2d8..1d9199e1c2ad 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NCAPINTS			19	   /* N 32-bit words worth of info */
 #define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
@@ -203,12 +203,15 @@
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
 #define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
+#define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
+
+#define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -243,6 +246,7 @@
 #define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT		( 9*32+25) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
@@ -268,6 +272,9 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -316,6 +323,13 @@
 #define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
 #define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
 
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+
 /*
  * BUG word(s)
  */
@@ -342,5 +356,7 @@
 #define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index b027633e7300..33833d1909af 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -77,6 +77,7 @@
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index d91ba04dd007..fb3a6de7440b 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -106,6 +106,7 @@
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 496e59a2738b..8fb90a0819c3 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -932,6 +932,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
 #define KVM_CAP_S390_AIS_MIGRATION 150
+#define KVM_CAP_PPC_GET_CPU_CHAR 151
+#define KVM_CAP_S390_BPB 152
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1261,6 +1263,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
 /* Available with KVM_CAP_PPC_RADIX_MMU */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
+/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
+#define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 30a9e51bbb1e..22627f80063e 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -49,5 +49,10 @@
  */
 #define SCHED_FLAG_RESET_ON_FORK	0x01
 #define SCHED_FLAG_RECLAIM		0x02
+#define SCHED_FLAG_DL_OVERRUN		0x04
+
+#define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
+			 SCHED_FLAG_RECLAIM		| \
+			 SCHED_FLAG_DL_OVERRUN)
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index c227ccba60ae..07d61583fd02 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -214,6 +214,11 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_IMA_ADPCM	((__force snd_pcm_format_t) 22)
 #define	SNDRV_PCM_FORMAT_MPEG		((__force snd_pcm_format_t) 23)
 #define	SNDRV_PCM_FORMAT_GSM		((__force snd_pcm_format_t) 24)
+#define	SNDRV_PCM_FORMAT_S20_LE	((__force snd_pcm_format_t) 25) /* in four bytes, LSB justified */
+#define	SNDRV_PCM_FORMAT_S20_BE	((__force snd_pcm_format_t) 26) /* in four bytes, LSB justified */
+#define	SNDRV_PCM_FORMAT_U20_LE	((__force snd_pcm_format_t) 27) /* in four bytes, LSB justified */
+#define	SNDRV_PCM_FORMAT_U20_BE	((__force snd_pcm_format_t) 28) /* in four bytes, LSB justified */
+/* gap in the numbering for a future standard linear format */
 #define	SNDRV_PCM_FORMAT_SPECIAL	((__force snd_pcm_format_t) 31)
 #define	SNDRV_PCM_FORMAT_S24_3LE	((__force snd_pcm_format_t) 32)	/* in three bytes */
 #define	SNDRV_PCM_FORMAT_S24_3BE	((__force snd_pcm_format_t) 33)	/* in three bytes */
@@ -248,6 +253,8 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_LE
 #define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_LE
 #define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
+#define	SNDRV_PCM_FORMAT_S20		SNDRV_PCM_FORMAT_S20_LE
+#define	SNDRV_PCM_FORMAT_U20		SNDRV_PCM_FORMAT_U20_LE
 #endif
 #ifdef SNDRV_BIG_ENDIAN
 #define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_BE
@@ -259,6 +266,8 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_BE
 #define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_BE
 #define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
+#define	SNDRV_PCM_FORMAT_S20		SNDRV_PCM_FORMAT_S20_BE
+#define	SNDRV_PCM_FORMAT_U20		SNDRV_PCM_FORMAT_U20_BE
 #endif
 
 typedef int __bitwise snd_pcm_subformat_t;
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 643cc4ba6872..3e5135dded16 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -31,5 +31,6 @@ config.mak.autogen
 .config-detected
 util/intel-pt-decoder/inat-tables.c
 arch/*/include/generated/
+trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 65681a1a292a..bf4ca749d1ac 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1566,7 +1566,8 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
 			&record.opts.sample_time_set,
 			"Record the sample timestamps"),
-	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
+	OPT_BOOLEAN_SET('P', "period", &record.opts.period, &record.opts.period_set,
+			"Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
 	OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 17d11deeb88d..e7f1b182fc15 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1661,9 +1661,12 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 				    struct callchain_cursor *cursor)
 {
 	struct addr_location al;
+	int max_stack = evsel->attr.sample_max_stack ?
+			evsel->attr.sample_max_stack :
+			trace->max_stack;
 
 	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, evsel->attr.sample_max_stack))
+	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
 		return -1;
 
 	return 0;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2357f4ccc9c7..cfe46236a5e5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -50,6 +50,7 @@ struct record_opts {
 	bool	     sample_time_set;
 	bool	     sample_cpu;
 	bool	     period;
+	bool	     period_set;
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 66fa45198a11..ff359c9ece2e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -745,12 +745,14 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
 				attr->sample_period = term->val.period;
 				attr->freq = 0;
+				perf_evsel__reset_sample_bit(evsel, PERIOD);
 			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
 			if (!(term->weak && opts->user_freq != UINT_MAX)) {
 				attr->sample_freq = term->val.freq;
 				attr->freq = 1;
+				perf_evsel__set_sample_bit(evsel, PERIOD);
 			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
@@ -969,9 +971,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	if (target__has_cpu(&opts->target) || opts->sample_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 
-	if (opts->period)
-		perf_evsel__set_sample_bit(evsel, PERIOD);
-
 	/*
 	 * When the user explicitly disabled time don't force it here.
 	 */
@@ -1073,6 +1072,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	apply_config_terms(evsel, opts, track);
 
 	evsel->ignore_missing_thread = opts->ignore_missing_thread;
+
+	/* The --period option takes the precedence. */
+	if (opts->period_set) {
+		if (opts->period)
+			perf_evsel__set_sample_bit(evsel, PERIOD);
+		else
+			perf_evsel__reset_sample_bit(evsel, PERIOD);
+	}
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 34c9ca37aaec2e307b837bb099d3b44f0ea04ddc tooling/headers: Synchronize updated s390 and x86 UAPI headers

This tree includes perf namespace support kernel side fixes, plus an accumulated 
set of perf tooling fixes - including UAPI header synchronization that should make 
the perf build less noisy.

 Thanks,

	Ingo

------------------>
Adrian Hunter (1):
      perf intel-pt: Bring instruction decoder files into line with the kernel

Andi Kleen (1):
      perf record: Fix -c/-F options for cpu event aliases

Andrei Vagin (1):
      perf trace: Fix an exit code of trace__symbols_init

Arnaldo Carvalho de Melo (16):
      perf evlist: Set the correct idx when adding dummy events
      perf record: Generate PERF_RECORD_{MMAP,COMM,EXEC} with --delay
      perf evsel: Fix up leftover perf_evsel_stat usage via evsel->priv
      perf script: Fix --per-event-dump for auxtrace synth evsels
      perf machine: Guard against NULL in machine__exit()
      perf evlist: Add helper to check if attr.exclude_kernel is set in all evsels
      perf report: Ignore kptr_restrict when not sampling the kernel
      perf record: Ignore kptr_restrict when not sampling the kernel
      perf top: Ignore kptr_restrict when not sampling the kernel
      tools headers: Synchronize kernel ABI headers wrt SPDX tags
      tools headers: Synchronize perf_event.h header
      tools headers uapi: Synchronize drm/drm.h
      tools headers: Synchronize drm/i915_drm.h
      tools headers: Synchronize KVM arch ABI headers
      tools headers: Synchronize prctl.h ABI header
      tools headers: Syncronize mman.h ABI header

Ingo Molnar (2):
      tools/headers: Synchronize kernel x86 UAPI headers
      tooling/headers: Synchronize updated s390 and x86 UAPI headers

Jiri Olsa (3):
      perf: Fix header.size for namespace events
      perf top: Fix window dimensions change handling
      perf top: Use signal interface for SIGWINCH handler

Namhyung Kim (1):
      perf help: Fix a bug during strstart() conversion

Ravi Bangoria (1):
      perf annotate: Do not truncate instruction names at 6 chars

Satheesh Rajendran (1):
      perf bench numa: Fixup discontiguous/sparse numa nodes

Thomas Richter (3):
      perf test shell: Fix check open filename arg using 'perf trace' on s390x
      perf test shell: Fix test case probe libc's inet_pton on s390x
      perf test: Fix test 21 for s390x

Vasily Averin (1):
      perf/core: Fix memory leak triggered by perf --namespace


 kernel/events/core.c                               |   5 +-
 tools/arch/arm/include/uapi/asm/kvm.h              |   7 +
 tools/arch/arm64/include/uapi/asm/kvm.h            |   7 +
 tools/arch/s390/include/uapi/asm/kvm.h             |   4 -
 tools/arch/s390/include/uapi/asm/kvm_perf.h        |   4 -
 tools/arch/x86/include/asm/cpufeatures.h           | 537 +++++++++++----------
 tools/arch/x86/include/asm/disabled-features.h     |   8 +-
 tools/include/uapi/asm-generic/mman.h              |   1 +
 tools/include/uapi/drm/drm.h                       |  41 ++
 tools/include/uapi/drm/i915_drm.h                  |  33 +-
 tools/include/uapi/linux/kcmp.h                    |   1 +
 tools/include/uapi/linux/kvm.h                     |   1 +
 tools/include/uapi/linux/perf_event.h              |   1 +
 tools/include/uapi/linux/prctl.h                   |  10 +
 tools/perf/bench/numa.c                            |  56 ++-
 tools/perf/builtin-help.c                          |   4 +-
 tools/perf/builtin-record.c                        |  42 +-
 tools/perf/builtin-report.c                        |   3 +
 tools/perf/builtin-script.c                        |  31 +-
 tools/perf/builtin-top.c                           |  36 +-
 tools/perf/builtin-trace.c                         |   6 +-
 .../perf/tests/shell/trace+probe_libc_inet_pton.sh |   7 +-
 tools/perf/tests/shell/trace+probe_vfs_getname.sh  |   6 +-
 tools/perf/tests/task-exit.c                       |   4 +
 tools/perf/trace/beauty/mmap.c                     |   3 +
 tools/perf/util/annotate.c                         |  18 +-
 tools/perf/util/evlist.c                           |  14 +-
 tools/perf/util/evlist.h                           |   2 +
 tools/perf/util/evsel.c                            |  14 +-
 tools/perf/util/evsel.h                            |   1 +
 tools/perf/util/intel-pt-decoder/inat.h            |  10 +
 .../perf/util/intel-pt-decoder/x86-opcode-map.txt  |   2 +-
 tools/perf/util/machine.c                          |   3 +
 tools/perf/util/parse-events.c                     |   2 +
 tools/perf/util/parse-events.h                     |   3 +
 tools/perf/util/pmu.c                              |   5 +
 36 files changed, 594 insertions(+), 338 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 16beab4767e1..5961ef6dfd64 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6639,6 +6639,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	struct perf_namespaces_event *namespaces_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
+	u16 header_size = namespaces_event->event_id.header.size;
 	int ret;
 
 	if (!perf_event_namespaces_match(event))
@@ -6649,7 +6650,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	ret = perf_output_begin(&handle, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
-		return;
+		goto out;
 
 	namespaces_event->event_id.pid = perf_event_pid(event,
 							namespaces_event->task);
@@ -6661,6 +6662,8 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	perf_event__output_id_sample(event, &handle, &sample);
 
 	perf_output_end(&handle);
+out:
+	namespaces_event->event_id.header.size = header_size;
 }
 
 static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 1f57bbe82b6f..6edd177bb1c7 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -152,6 +152,12 @@ struct kvm_arch_memory_slot {
 	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
+/* PL1 Physical Timer Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM_CP15_REG32(0, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CNT		ARM_CP15_REG64(0, 14)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM_CP15_REG64(2, 14)
+
+/* Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
 #define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
@@ -216,6 +222,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES		1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES	2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 51149ec75fe4..9abbf3044654 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -196,6 +196,12 @@ struct kvm_arch_memory_slot {
 
 #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
 
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
@@ -228,6 +234,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9ad172dcd912..38535a57fef8 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -6,10 +6,6 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
index c36c97ffdc6f..84606b8cc49e 100644
--- a/tools/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -4,10 +4,6 @@
  *
  * Copyright 2014 IBM Corp.
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_KVM_PERF_S390_H
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 793690fbda36..c0b0e9e8aa66 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,173 +13,176 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
+#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
  * in /proc/cpuinfo instead of the macro name.  If the string is "",
  * this feature bit is not displayed in /proc/cpuinfo at all.
+ *
+ * When adding new features here that depend on other features,
+ * please update the table in kernel/cpu/cpuid-deps.c as well.
  */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
+#define X86_FEATURE_FPU			( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME			( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE			( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE			( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC			( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR			( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE			( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE			( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8			( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC		( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP			( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR		( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE			( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA			( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV		( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT			( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36		( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN			( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH		( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS			( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI		( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX			( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR		( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM			( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2		( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP		( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT			( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC			( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64		( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE			( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL		( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP			( 1*32+19) /* MP Capable */
+#define X86_FEATURE_NX			( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT		( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT		( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES		( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP		( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM			( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT		( 1*32+30) /* AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW		( 1*32+31) /* 3DNow */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY		( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN		( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI		( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_CXMMX		( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+/* CPU types for specific tunings: */
+#define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP			( 3*32+ 9) /* SMP kernel running on UP */
+#define X86_FEATURE_ART			( 3*32+10) /* Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON	( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS		( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS			( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
+#define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
+#define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC	( 3*32+17) /* "" MFENCE synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY		( 3*32+22) /* CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE	( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC		( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CPUID		( 3*32+25) /* CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID		( 3*32+26) /* Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM		( 3*32+27) /* AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF		( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
+#define X86_FEATURE_XMM3		( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ		( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64		( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT		( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
+#define X86_FEATURE_DSCPL		( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
+#define X86_FEATURE_VMX			( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX			( 4*32+ 6) /* Safer Mode eXtensions */
+#define X86_FEATURE_EST			( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2			( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3		( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID			( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG		( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA			( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16		( 4*32+13) /* CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR		( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM		( 4*32+15) /* Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID		( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA			( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1		( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2		( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC		( 4*32+21) /* X2APIC */
+#define X86_FEATURE_MOVBE		( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT		( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* TSC deadline timer */
+#define X86_FEATURE_AES			( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE		( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE		( 4*32+27) /* "" XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX			( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C		( 4*32+29) /* 16-bit FP conversions */
+#define X86_FEATURE_RDRAND		( 4*32+30) /* RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR		( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE		( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN		( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT		( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN		( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2		( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN		( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE			( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN		( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM			( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN		( 5*32+13) /* PMM enabled */
 
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
-#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_LLC	( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
+#define X86_FEATURE_LAHF_LM		( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY		( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM			( 6*32+ 2) /* Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC		( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY		( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM			( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A		( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE		( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH	( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW		( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS			( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP			( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT		( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT			( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP			( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4		( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE			( 6*32+17) /* Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR		( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM			( 6*32+21) /* Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT		( 6*32+22) /* Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE	( 6*32+23) /* Core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB		( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT		( 6*32+26) /* Data breakpoint extension */
+#define X86_FEATURE_PTSC		( 6*32+27) /* Performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_LLC		( 6*32+28) /* Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX		( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -187,146 +190,154 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
-#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
-#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_RING3MWAIT		( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT		( 7*32+ 1) /* Intel CPUID faulting */
+#define X86_FEATURE_CPB			( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB			( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 
-#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
 
-#define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
+#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
-#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI		( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY	( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT			( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID		( 8*32+ 4) /* Intel Virtual Processor ID */
 
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+#define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
 
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
+#define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
+#define X86_FEATURE_TSC_ADJUST		( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_BMI1		( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE			( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2		( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP		( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2		( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS		( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
+#define X86_FEATURE_INVPCID		( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM			( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM			( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX			( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A		( 9*32+15) /* Resource Director Technology Allocation */
+#define X86_FEATURE_AVX512F		( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ		( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED		( 9*32+18) /* RDSEED instruction */
+#define X86_FEATURE_ADX			( 9*32+19) /* ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP		( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
+#define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI		( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW		( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL		( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
 
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
+#define X86_FEATURE_XSAVEOPT		(10*32+ 0) /* XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
+#define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
+#define X86_FEATURE_CQM_LLC		(11*32+ 1) /* LLC QoS if 1 */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC	(12*32+ 0) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL	(12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL	(12*32+ 2) /* LLC Local MBM monitoring */
 
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
+/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
+#define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
+#define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA			(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT		(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN			(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS			(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP			(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY		(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW	(14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP		(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ		(14*32+11) /* HWP Package Level Request */
 
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
-#define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
+#define X86_FEATURE_NPT			(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV		(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML		(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS		(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR		(15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN		(15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID		(15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS	(15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER		(15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD		(15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
-#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
-#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
+#define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP		(16*32+ 2) /* User Mode Instruction Protection */
+#define X86_FEATURE_PKU			(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
+#define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
+#define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 
-/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
 
 /*
  * BUG word(s)
  */
-#define X86_BUG(x)		(NCAPINTS*32 + (x))
+#define X86_BUG(x)			(NCAPINTS*32 + (x))
 
-#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_F00F			X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV			X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA			X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH		X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E		X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP			X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK		X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR		X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS		X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
  * to avoid confusion.
  */
-#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX			X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
-#define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
-#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
-#define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_NULL_SEG		X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..14d6d5007314 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_INTEL_UMIP
+# define DISABLE_UMIP	0
+#else
+# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
+#endif
+
 #ifdef CONFIG_X86_64
 # define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
@@ -63,7 +69,7 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 2dffcbf705b3..653687d9771b 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -13,6 +13,7 @@
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
 #define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x40000		/* create a huge page mapping */
+#define MAP_SYNC	0x80000		/* perform synchronous page faults for the mapping */
 
 /* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
 
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 97677cd6964d..6fdff5945c8a 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -737,6 +737,28 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+	__u32 crtc_id;		/* requested crtc_id */
+	__u32 active;		/* return: crtc output is active */
+	__u64 sequence;		/* return: most recent vblank sequence */
+	__s64 sequence_ns;	/* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE		0x00000001	/* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS		0x00000002	/* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+	__u32 crtc_id;
+	__u32 flags;
+	__u64 sequence;		/* on input, target sequence. on output, actual sequence */
+	__u64 user_data;	/* user data passed to event */
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -819,6 +841,9 @@ extern "C" {
 
 #define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)
 
+#define DRM_IOCTL_CRTC_GET_SEQUENCE	DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE	DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
 #define DRM_IOCTL_UPDATE_DRAW		DRM_IOW(0x3f, struct drm_update_draw)
 
 #define DRM_IOCTL_MODE_GETRESOURCES	DRM_IOWR(0xA0, struct drm_mode_card_res)
@@ -863,6 +888,11 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
 #define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
+#define DRM_IOCTL_MODE_CREATE_LEASE	DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES	DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
@@ -893,6 +923,7 @@ struct drm_event {
 
 #define DRM_EVENT_VBLANK 0x01
 #define DRM_EVENT_FLIP_COMPLETE 0x02
+#define DRM_EVENT_CRTC_SEQUENCE	0x03
 
 struct drm_event_vblank {
 	struct drm_event base;
@@ -903,6 +934,16 @@ struct drm_event_vblank {
 	__u32 crtc_id; /* 0 on older kernels that do not support this */
 };
 
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+	struct drm_event	base;
+	__u64			user_data;
+	__s64			time_ns;
+	__u64			sequence;
+};
+
 /* typedef area */
 #ifndef __KERNEL__
 typedef struct drm_clip_rect drm_clip_rect_t;
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 9816590d3ad2..ac3c6503ca27 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -397,10 +397,20 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_MIN_EU_IN_POOL	 39
 #define I915_PARAM_MMAP_GTT_VERSION	 40
 
-/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
  * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
  */
 #define I915_PARAM_HAS_SCHEDULER	 41
+#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+
 #define I915_PARAM_HUC_STATUS		 42
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
@@ -1309,14 +1319,16 @@ struct drm_i915_reg_read {
 	 * be specified
 	 */
 	__u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
 	__u64 val; /* Return value */
 };
 /* Known registers:
  *
  * Render engine timestamp - 0x2358 + 64bit - gen7+
  * - Note this register returns an invalid value if using the default
- *   single instruction 8byte read, in order to workaround that use
- *   offset (0x2538 | 1) instead.
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
  *
  */
 
@@ -1359,6 +1371,10 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 #define I915_CONTEXT_PARAM_BANNABLE	0x5
+#define I915_CONTEXT_PARAM_PRIORITY	0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY		0
+#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
 	__u64 value;
 };
 
@@ -1510,9 +1526,14 @@ struct drm_i915_perf_oa_config {
 	__u32 n_boolean_regs;
 	__u32 n_flex_regs;
 
-	__u64 __user mux_regs_ptr;
-	__u64 __user boolean_regs_ptr;
-	__u64 __user flex_regs_ptr;
+	/*
+	 * These fields are pointers to tuples of u32 values (register
+	 * address, value). For example the expected length of the buffer
+	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 */
+	__u64 mux_regs_ptr;
+	__u64 boolean_regs_ptr;
+	__u64 flex_regs_ptr;
 };
 
 #if defined(__cplusplus)
diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h
index 481e103da78e..ef1305010925 100644
--- a/tools/include/uapi/linux/kcmp.h
+++ b/tools/include/uapi/linux/kcmp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_KCMP_H
 #define _UAPI_LINUX_KCMP_H
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7e99999d6236..282d7613fce8 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -931,6 +931,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 362493a2f950..b9a4953018ed 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -942,6 +942,7 @@ enum perf_callchain_context {
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
 #define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION		0x08	/* sample collided with another */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index a8d0759a9e40..af5f8c2df87a 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
@@ -197,4 +198,13 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL			50	/* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL			51	/* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK		0xffff
+# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
 	NULL
 };
 
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+	int i, nr_nodes = 0;
+
+	for (i = 0; i < g->p.nr_nodes; i++) {
+		if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+			nr_nodes++;
+	}
+
+	return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+	return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+	struct bitmask *cpu = numa_allocate_cpumask();
+	unsigned int i;
+
+	if (cpu && !numa_node_to_cpus(node, cpu)) {
+		for (i = 0; i < cpu->size; i++) {
+			if (numa_bitmask_isbitset(cpu, i))
+				return true;
+		}
+	}
+
+	return false; /* lets fall back to nocpus safely */
+}
+
 static cpu_set_t bind_to_cpu(int target_cpu)
 {
 	cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
 
 static cpu_set_t bind_to_node(int target_node)
 {
-	int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+	int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
 	cpu_set_t orig_mask, mask;
 	int cpu;
 	int ret;
 
-	BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+	BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
 	BUG_ON(!cpus_per_node);
 
 	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
 			int i;
 
 			for (i = 0; i < mul; i++) {
-				if (t >= g->p.nr_tasks) {
+				if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
 					printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
 					goto out;
 				}
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	sum = 0;
 
 	for (node = 0; node < g->p.nr_nodes; node++) {
+		if (!is_node_present(node))
+			continue;
 		nr = nodes[node];
 		nr_min = min(nr, nr_min);
 		nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	process_groups = 0;
 
 	for (node = 0; node < g->p.nr_nodes; node++) {
-		int processes = count_node_processes(node);
+		int processes;
 
+		if (!is_node_present(node))
+			continue;
+		processes = count_node_processes(node);
 		nr = nodes[node];
 		tprintf(" %2d/%-2d", nr, processes);
 
@@ -1291,7 +1337,7 @@ static void print_summary(void)
 
 	printf("\n ###\n");
 	printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
-		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
 	printf(" #      %5dx %5ldMB global  shared mem operations\n",
 			g->p.nr_loops, g->p.bytes_global/1024/1024);
 	printf(" #      %5dx %5ldMB process shared mem operations\n",
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index bd1fedef3d1c..a0f7ed2b869b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 		add_man_viewer(value);
 		return 0;
 	}
-	if (!strstarts(var, "man."))
+	if (strstarts(var, "man."))
 		return add_man_viewer_info(var, value);
 
 	return 0;
@@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
 	if (!perf_cmd)
 		return "perf";
-	else if (!strstarts(perf_cmd, "perf"))
+	else if (strstarts(perf_cmd, "perf"))
 		return perf_cmd;
 
 	return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3d7f33e19df2..003255910c05 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -339,6 +339,22 @@ static int record__open(struct record *rec)
 	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
+	/*
+	 * For initial_delay we need to add a dummy event so that we can track
+	 * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+	 * real events, the ones asked by the user.
+	 */
+	if (opts->initial_delay) {
+		if (perf_evlist__add_dummy(evlist))
+			return -ENOMEM;
+
+		pos = perf_evlist__first(evlist);
+		pos->tracking = 0;
+		pos = perf_evlist__last(evlist);
+		pos->tracking = 1;
+		pos->attr.enable_on_exec = 1;
+	}
+
 	perf_evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
@@ -749,17 +765,19 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 	}
 
-	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/kallsyms permission or run as root.\n");
-
-	err = perf_event__synthesize_modules(tool, process_synthesized_event,
-					     machine);
-	WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
-			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-			   "Check /proc/modules permission or run as root.\n");
+	if (!perf_evlist__exclude_kernel(rec->evlist)) {
+		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+							 machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/kallsyms permission or run as root.\n");
+
+		err = perf_event__synthesize_modules(tool, process_synthesized_event,
+						     machine);
+		WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+				   "Check /proc/modules permission or run as root.\n");
+	}
 
 	if (perf_guest) {
 		machines__process_guests(&session->machines,
@@ -1693,7 +1711,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = -ENOMEM;
 
-	if (symbol_conf.kptr_restrict)
+	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1394cd8d96f7..af5dd038195e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -441,6 +441,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
 	struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
 	struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
+	if (perf_evlist__exclude_kernel(rep->session->evlist))
+		return;
+
 	if (kernel_map == NULL ||
 	    (kernel_map->dso->hit &&
 	     (kernel_kmap->ref_reloc_sym == NULL ||
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 68f36dc0344f..9b43bda45a41 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1955,6 +1955,16 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script)
 	struct perf_evsel *evsel;
 
 	evlist__for_each_entry(script->session->evlist, evsel) {
+		/*
+		 * Already setup? I.e. we may be called twice in cases like
+		 * Intel PT, one for the intel_pt// and dummy events, then
+		 * for the evsels syntheized from the auxtrace info.
+		 *
+		 * Ses perf_script__process_auxtrace_info.
+		 */
+		if (evsel->priv != NULL)
+			continue;
+
 		evsel->priv = perf_evsel_script__new(evsel, script->session->data);
 		if (evsel->priv == NULL)
 			goto out_err_fclose;
@@ -2838,6 +2848,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_script__process_auxtrace_info(struct perf_tool *tool,
+					      union perf_event *event,
+					      struct perf_session *session)
+{
+	int ret = perf_event__process_auxtrace_info(tool, event, session);
+
+	if (ret == 0) {
+		struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+		ret = perf_script__setup_per_event_dump(script);
+	}
+
+	return ret;
+}
+#else
+#define perf_script__process_auxtrace_info 0
+#endif
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -2866,7 +2895,7 @@ int cmd_script(int argc, const char **argv)
 			.feature	 = perf_event__process_feature,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
-			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace_info	 = perf_script__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
 			.auxtrace_error	 = perf_event__process_auxtrace_error,
 			.stat		 = perf_event__process_stat_event,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 477a8699f0b5..9e0d2645ae13 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -77,6 +77,7 @@
 #include "sane_ctype.h"
 
 static volatile int done;
+static volatile int resize;
 
 #define HEADER_LINE_NR  5
 
@@ -85,11 +86,13 @@ static void perf_top__update_print_entries(struct perf_top *top)
 	top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void perf_top__sig_winch(int sig __maybe_unused,
-				siginfo_t *info __maybe_unused, void *arg)
+static void winch_sig(int sig __maybe_unused)
 {
-	struct perf_top *top = arg;
+	resize = 1;
+}
 
+static void perf_top__resize(struct perf_top *top)
+{
 	get_term_dimensions(&top->winsize);
 	perf_top__update_print_entries(top);
 }
@@ -473,12 +476,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 		case 'e':
 			prompt_integer(&top->print_entries, "Enter display entries (lines)");
 			if (top->print_entries == 0) {
-				struct sigaction act = {
-					.sa_sigaction = perf_top__sig_winch,
-					.sa_flags     = SA_SIGINFO,
-				};
-				perf_top__sig_winch(SIGWINCH, NULL, top);
-				sigaction(SIGWINCH, &act, NULL);
+				perf_top__resize(top);
+				signal(SIGWINCH, winch_sig);
 			} else {
 				signal(SIGWINCH, SIG_DFL);
 			}
@@ -732,14 +731,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
-		ui__warning(
+		if (!perf_evlist__exclude_kernel(top->session->evlist)) {
+			ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
 			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
 			  " modules" : "");
-		if (use_browser <= 0)
-			sleep(5);
+			if (use_browser <= 0)
+				sleep(5);
+		}
 		machine->kptr_restrict_warned = true;
 	}
 
@@ -1030,6 +1031,11 @@ static int __cmd_top(struct perf_top *top)
 
 		if (hits == top->samples)
 			ret = perf_evlist__poll(top->evlist, 100);
+
+		if (resize) {
+			perf_top__resize(top);
+			resize = 0;
+		}
 	}
 
 	ret = 0;
@@ -1352,12 +1358,8 @@ int cmd_top(int argc, const char **argv)
 
 	get_term_dimensions(&top.winsize);
 	if (top.print_entries == 0) {
-		struct sigaction act = {
-			.sa_sigaction = perf_top__sig_winch,
-			.sa_flags     = SA_SIGINFO,
-		};
 		perf_top__update_print_entries(&top);
-		sigaction(SIGWINCH, &act, NULL);
+		signal(SIGWINCH, winch_sig);
 	}
 
 	status = __cmd_top(&top);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f2757d38c7d7..84debdbad327 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1152,12 +1152,14 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
-		return -errno;
+	err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
+	if (err < 0)
+		goto out;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
 					    trace->opts.proc_map_timeout, 1);
+out:
 	if (err)
 		symbol__exit();
 
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 7a84d73324e3..8b3da21a08f1 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,8 +10,8 @@
 
 . $(dirname $0)/lib/probe.sh
 
-ld=$(realpath /lib64/ld*.so.* | uniq)
-libc=$(echo $ld | sed 's/ld/libc/g')
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
 	idx=0
@@ -37,6 +37,9 @@ trace_libc_inet_pton_backtrace() {
 	done
 }
 
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
 skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2e68c5f120da..2a9ef080efd0 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,8 +17,10 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	perf trace -e open touch $file 2>&1 | \
-	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; }
+
+	perf trace -e ${svc:-open} touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a7344e274..89c8e1604ca7 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 	evsel = perf_evlist__first(evlist);
 	evsel->attr.task = 1;
+#ifdef __s390x__
+	evsel->attr.sample_freq = 1000000;
+#else
 	evsel->attr.sample_freq = 1;
+#endif
 	evsel->attr.inherit = 0;
 	evsel->attr.watermark = 0;
 	evsel->attr.wakeup_events = 1;
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9e1668b2c5d7..417e3ecfe9d7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -62,6 +62,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 	P_MMAP_FLAG(POPULATE);
 	P_MMAP_FLAG(STACK);
 	P_MMAP_FLAG(UNINITIALIZED);
+#ifdef MAP_SYNC
+	P_MMAP_FLAG(SYNC);
+#endif
 #undef P_MMAP_FLAG
 
 	if (flags)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index da1c4c4a0dd8..3369c7830260 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -165,7 +165,7 @@ static void ins__delete(struct ins_operands *ops)
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
 			      struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+	return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
@@ -230,12 +230,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
 	if (ops->target.name)
-		return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
 
 	if (ops->target.addr == 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -299,7 +299,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			c++;
 	}
 
-	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+	return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
 			 ins->name, c ? c - ops->raw : 0, ops->raw,
 			 ops->target.offset);
 }
@@ -372,7 +372,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 	if (ops->locked.ins.ops == NULL)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+	printed = scnprintf(bf, size, "%-6s ", ins->name);
 	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
 					size - printed, ops->locked.ops);
 }
@@ -448,7 +448,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+	return scnprintf(bf, size, "%-6s %s,%s", ins->name,
 			 ops->source.name ?: ops->source.raw,
 			 ops->target.name ?: ops->target.raw);
 }
@@ -488,7 +488,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name,
+	return scnprintf(bf, size, "%-6s %s", ins->name,
 			 ops->target.name ?: ops->target.raw);
 }
 
@@ -500,7 +500,7 @@ static struct ins_ops dec_ops = {
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
 			  struct ins_operands *ops __maybe_unused)
 {
-	return scnprintf(bf, size, "%-6.6s", "nop");
+	return scnprintf(bf, size, "%-6s", "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -924,7 +924,7 @@ void disasm_line__free(struct disasm_line *dl)
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
 {
 	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw);
+		return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
 
 	return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e154a6..b62e523a7035 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -257,7 +257,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist)
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
 	};
-	struct perf_evsel *evsel = perf_evsel__new(&attr);
+	struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
 
 	if (evsel == NULL)
 		return -ENOMEM;
@@ -1786,3 +1786,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 state_err:
 	return;
 }
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel->attr.exclude_kernel)
+			return false;
+	}
+
+	return true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e72ae64c11ac..491f69542920 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -312,4 +312,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
 struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f894893c203d..d5fbcf8c7aa7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -733,12 +733,16 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	list_for_each_entry(term, config_terms, list) {
 		switch (term->type) {
 		case PERF_EVSEL__CONFIG_TERM_PERIOD:
-			attr->sample_period = term->val.period;
-			attr->freq = 0;
+			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
+				attr->sample_period = term->val.period;
+				attr->freq = 0;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
-			attr->sample_freq = term->val.freq;
-			attr->freq = 1;
+			if (!(term->weak && opts->user_freq != UINT_MAX)) {
+				attr->sample_freq = term->val.freq;
+				attr->freq = 1;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
 			if (term->val.time)
@@ -1371,7 +1375,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader,
 static int
 perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
 {
-	struct perf_stat_evsel *ps = leader->priv;
+	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->attr.read_format;
 	int size = perf_evsel__read_size(leader);
 	u64 *data = ps->group_data;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9277df96ffda..157f49e8a772 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -67,6 +67,7 @@ struct perf_evsel_config_term {
 		bool	overwrite;
 		char	*branch;
 	} val;
+	bool weak;
 };
 
 struct perf_stat_evsel;
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 125ecd2a300d..52dc8d911173 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE	0
+#define INAT_SEG_REG_DEFAULT	1
+#define INAT_SEG_REG_CS		2
+#define INAT_SEG_REG_SS		3
+#define INAT_SEG_REG_DS		4
+#define INAT_SEG_REG_ES		5
+#define INAT_SEG_REG_FS		6
+#define INAT_SEG_REG_GS		7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index 12e377184ee4..c4d55919fac1 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6a8d03c3d9b7..270f3223c6df 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -172,6 +172,9 @@ void machine__exit(struct machine *machine)
 {
 	int i;
 
+	if (machine == NULL)
+		return;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a7fcd95961ef..170316795a18 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1116,6 +1116,7 @@ do {								\
 	INIT_LIST_HEAD(&__t->list);				\
 	__t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;	\
 	__t->val.__name = __val;				\
+	__t->weak	= term->weak;				\
 	list_add_tail(&__t->list, head_terms);			\
 } while (0)
 
@@ -2410,6 +2411,7 @@ static int new_term(struct parse_events_term **_term,
 
 	*term = *temp;
 	INIT_LIST_HEAD(&term->list);
+	term->weak = false;
 
 	switch (term->type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index be337c266697..88108cd11b4c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -101,6 +101,9 @@ struct parse_events_term {
 	/* error string indexes for within parsed string */
 	int err_term;
 	int err_val;
+
+	/* Coming from implicit alias */
+	bool weak;
 };
 
 struct parse_events_error {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 07cb2ac041d7..80fb1593913a 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -405,6 +405,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 			parse_events_terms__purge(&list);
 			return ret;
 		}
+		/*
+		 * Weak terms don't override command line options,
+		 * which we don't want for implicit terms in aliases.
+		 */
+		cloned->weak = true;
 		list_add_tail(&cloned->list, &list);
 	}
 	list_splice(&list, terms);

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 4a31b424ac0656d1bb17520ee861144fe7a19664 perf/core: Fix memory leak triggered by perf --namespace

Misc fixes: two PMU driver fixes and a memory leak fix.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf/x86/intel: Hide TSX events when RTM is not supported

Kan Liang (1):
      perf/x86/intel/uncore: Add event constraint for BDX PCU

Vasily Averin (1):
      perf/core: Fix memory leak triggered by perf --namespace


 arch/x86/events/intel/core.c         | 35 +++++++++++++++++++++++------------
 arch/x86/events/intel/uncore_snbep.c |  8 ++++++++
 kernel/events/core.c                 |  1 +
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9fb9a1f1e47b..f94855000d4e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3730,6 +3730,19 @@ EVENT_ATTR_STR(cycles-t,	cycles_t,	"event=0x3c,in_tx=1");
 EVENT_ATTR_STR(cycles-ct,	cycles_ct,	"event=0x3c,in_tx=1,in_tx_cp=1");
 
 static struct attribute *hsw_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
+	NULL
+};
+
+static struct attribute *hsw_tsx_events_attrs[] = {
 	EVENT_PTR(tx_start),
 	EVENT_PTR(tx_commit),
 	EVENT_PTR(tx_abort),
@@ -3742,18 +3755,16 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(el_conflict),
 	EVENT_PTR(cycles_t),
 	EVENT_PTR(cycles_ct),
-	EVENT_PTR(mem_ld_hsw),
-	EVENT_PTR(mem_st_hsw),
-	EVENT_PTR(td_slots_issued),
-	EVENT_PTR(td_slots_retired),
-	EVENT_PTR(td_fetch_bubbles),
-	EVENT_PTR(td_total_slots),
-	EVENT_PTR(td_total_slots_scale),
-	EVENT_PTR(td_recovery_bubbles),
-	EVENT_PTR(td_recovery_bubbles_scale),
 	NULL
 };
 
+static __init struct attribute **get_hsw_events_attrs(void)
+{
+	return boot_cpu_has(X86_FEATURE_RTM) ?
+		merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
+		hsw_events_attrs;
+}
+
 static ssize_t freeze_on_smi_show(struct device *cdev,
 				  struct device_attribute *attr,
 				  char *buf)
@@ -4182,7 +4193,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.cpu_events = get_hsw_events_attrs();
 		x86_pmu.lbr_double_abort = true;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
@@ -4221,7 +4232,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.cpu_events = get_hsw_events_attrs();
 		x86_pmu.limit_period = bdw_limit_period;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
@@ -4279,7 +4290,7 @@ __init int intel_pmu_init(void)
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
 		extra_attr = merge_attr(extra_attr, skl_format_attr);
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.cpu_events = get_hsw_events_attrs();
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
 		pr_cont("Skylake events, ");
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 95cb19f4e06f..f4e4168455a8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3035,11 +3035,19 @@ static struct intel_uncore_type *bdx_msr_uncores[] = {
 	NULL,
 };
 
+/* Bit 7 'Use Occupancy' is not available for counter 0 on BDX */
+static struct event_constraint bdx_uncore_pcu_constraints[] = {
+	EVENT_CONSTRAINT(0x80, 0xe, 0x80),
+	EVENT_CONSTRAINT_END
+};
+
 void bdx_uncore_cpu_init(void)
 {
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
+
+	hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 10cdb9c26b5d..ab5ac84f82e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6756,6 +6756,7 @@ static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
 		ns_inode = ns_path.dentry->d_inode;
 		ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev);
 		ns_link_info->ino = ns_inode->i_ino;
+		path_put(&ns_path);
 	}
 }
 

Re: [GIT PULL] perf fixes

[Markus Trippelsdorf]

On 2017.11.05 at 15:40 +0100, Ingo Molnar wrote:
> Linus,
>
> Please pull the latest perf-urgent-for-linus git tree from:
>
>    git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
>
> Jiri Olsa (1):
>       perf tools: Unwind properly location after REJECT

The patch above breaks the build for me:

util/parse-events.l: In function ‘parse_events_lex’:
util/parse-events-flex.c:4722:16: error: ‘reject_used_but_not_detected’ undeclared (first use in this function)
  */
                ^
util/parse-events.l:159:2: note: in expansion of macro ‘REJECT’
  REJECT
  ^~~~~~
util/parse-events.l:343:26: note: in expansion of macro ‘USER_REJECT’
 {bpf_source}  { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
                          ^~~~~~~~~~~
util/parse-events-flex.c:4722:16: note: each undeclared identifier is reported only once for each function it appears in
  */
                ^
util/parse-events.l:159:2: note: in expansion of macro ‘REJECT’
  REJECT
  ^~~~~~
util/parse-events.l:343:26: note: in expansion of macro ‘USER_REJECT’
 {bpf_source}  { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
                          ^~~~~~~~~~~
mv: cannot stat 'util/.parse-events-flex.o.tmp': No such file or directory

--
Markus

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: fb7df12d645cfba6a76a45fdcc7e3f7fbbcda661 tools/headers: Synchronize kernel ABI headers

Various fixes:

 - synchronize kernel and tooling headers

 - cgroup support fix

 - two tooling fixes

 Thanks,

	Ingo

------------------>
Ingo Molnar (1):
      tools/headers: Synchronize kernel ABI headers

Jiri Olsa (1):
      perf tools: Unwind properly location after REJECT

Ravi Bangoria (1):
      perf symbols: Fix memory corruption because of zero length symbols

Tejun Heo (1):
      perf/cgroup: Fix perf cgroup hierarchy support


 include/uapi/sound/asound.h                      |  6 +++---
 kernel/events/core.c                             |  6 ++++--
 tools/arch/x86/include/asm/disabled-features.h   |  1 -
 tools/arch/x86/include/asm/required-features.h   |  1 -
 tools/arch/x86/include/uapi/asm/unistd.h         |  1 +
 tools/arch/x86/lib/memcpy_64.S                   |  5 ++++-
 tools/include/asm-generic/bitops/__fls.h         |  1 +
 tools/include/asm-generic/bitops/arch_hweight.h  |  1 +
 tools/include/asm-generic/bitops/const_hweight.h |  1 +
 tools/include/asm-generic/bitops/fls.h           |  1 +
 tools/include/asm-generic/bitops/fls64.h         |  1 +
 tools/include/asm/export.h                       |  7 +++++++
 tools/include/linux/hash.h                       |  1 -
 tools/include/uapi/asm-generic/ioctls.h          |  1 +
 tools/include/uapi/asm-generic/mman-common.h     |  1 +
 tools/include/uapi/asm-generic/mman.h            |  4 ++--
 tools/include/uapi/linux/bpf.h                   |  4 ++--
 tools/include/uapi/linux/bpf_common.h            |  2 +-
 tools/include/uapi/linux/fcntl.h                 |  2 +-
 tools/include/uapi/linux/hw_breakpoint.h         |  2 +-
 tools/include/uapi/linux/kvm.h                   |  1 +
 tools/include/uapi/linux/mman.h                  |  2 +-
 tools/include/uapi/linux/perf_event.h            |  1 +
 tools/include/uapi/linux/sched.h                 |  1 +
 tools/include/uapi/linux/stat.h                  |  2 +-
 tools/include/uapi/linux/vhost.h                 |  1 +
 tools/include/uapi/sound/asound.h                |  1 +
 tools/perf/util/annotate.c                       | 12 +++++++++++-
 tools/perf/util/parse-events.l                   |  8 ++++++--
 29 files changed, 57 insertions(+), 21 deletions(-)
 create mode 100644 tools/include/asm/export.h

diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 299a822d2c4e..c227ccba60ae 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -94,7 +94,7 @@ enum {
 	SNDRV_HWDEP_IFACE_VX,		/* Digigram VX cards */
 	SNDRV_HWDEP_IFACE_MIXART,	/* Digigram miXart cards */
 	SNDRV_HWDEP_IFACE_USX2Y,	/* Tascam US122, US224 & US428 usb */
-	SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */	
+	SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */
 	SNDRV_HWDEP_IFACE_BLUETOOTH,	/* Bluetooth audio */
 	SNDRV_HWDEP_IFACE_USX2Y_PCM,	/* Tascam US122, US224 & US428 rawusb pcm */
 	SNDRV_HWDEP_IFACE_PCXHR,	/* Digigram PCXHR */
@@ -384,7 +384,7 @@ struct snd_mask {
 
 struct snd_pcm_hw_params {
 	unsigned int flags;
-	struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - 
+	struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK -
 			       SNDRV_PCM_HW_PARAM_FIRST_MASK + 1];
 	struct snd_mask mres[5];	/* reserved masks */
 	struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL -
@@ -857,7 +857,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_INACTIVE		(1<<8)	/* control does actually nothing, but may be updated */
 #define SNDRV_CTL_ELEM_ACCESS_LOCK		(1<<9)	/* write lock */
 #define SNDRV_CTL_ELEM_ACCESS_OWNER		(1<<10)	/* write lock owner */
-#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK	(1<<28)	/* kernel use a TLV callback */ 
+#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK	(1<<28)	/* kernel use a TLV callback */
 #define SNDRV_CTL_ELEM_ACCESS_USER		(1<<29) /* user space element */
 /* bits 30 and 31 are obsoleted (for indirect access) */
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d93db81fa36..10cdb9c26b5d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -901,9 +901,11 @@ list_update_cgroup_event(struct perf_event *event,
 	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
 	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
 	if (add) {
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+
 		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
-		if (perf_cgroup_from_task(current, ctx) == event->cgrp)
-			cpuctx->cgrp = event->cgrp;
+		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+			cpuctx->cgrp = cgrp;
 	} else {
 		list_del(cpuctx_entry);
 		cpuctx->cgrp = NULL;
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c1a6d5d0da0d..c10c9128f54e 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -1,4 +1,3 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_DISABLED_FEATURES_H
 #define _ASM_X86_DISABLED_FEATURES_H
 
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 59ac6baafb6a..d91ba04dd007 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -1,4 +1,3 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_REQUIRED_FEATURES_H
 #define _ASM_X86_REQUIRED_FEATURES_H
 
diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h
index a26df0d75cd0..30d7d04d72d6 100644
--- a/tools/arch/x86/include/uapi/asm/unistd.h
+++ b/tools/arch/x86/include/uapi/asm/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_ASM_X86_UNISTD_H
 #define _UAPI_ASM_X86_UNISTD_H
 
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index ecf2c2067281..9a53a06e5a3e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -1,10 +1,10 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen */
 
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
+#include <asm/export.h>
 
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
@@ -41,6 +41,8 @@ ENTRY(memcpy)
 	ret
 ENDPROC(memcpy)
 ENDPROC(__memcpy)
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(__memcpy)
 
 /*
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
@@ -275,6 +277,7 @@ ENTRY(memcpy_mcsafe_unrolled)
 	xorq %rax, %rax
 	ret
 ENDPROC(memcpy_mcsafe_unrolled)
+EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
 
 	.section .fixup, "ax"
 	/* Return -EFAULT for any failure */
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index a60a7ccb6782..03f721a8a2b1 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS___FLS_H_
 #define _ASM_GENERIC_BITOPS___FLS_H_
 
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
index 6a211f40665c..c2705e1d220d 100644
--- a/tools/include/asm-generic/bitops/arch_hweight.h
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
index 0a7e06623470..149faeeeeaf2 100644
--- a/tools/include/asm-generic/bitops/const_hweight.h
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index 0576d1f42f43..753aecaab641 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_FLS_H_
 #define _ASM_GENERIC_BITOPS_FLS_H_
 
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index b097cf8444e3..866f2b2304ff 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_FLS64_H_
 #define _ASM_GENERIC_BITOPS_FLS64_H_
 
diff --git a/tools/include/asm/export.h b/tools/include/asm/export.h
new file mode 100644
index 000000000000..2cb1a0d83035
--- /dev/null
+++ b/tools/include/asm/export.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_ASM_EXPORT_H
+#define _TOOLS_ASM_EXPORT_H
+
+#define EXPORT_SYMBOL(x)
+#define EXPORT_SYMBOL_GPL(x)
+
+#endif /* _TOOLS_ASM_EXPORT_H */
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
index 2c4183bbc504..ad6fa21d977b 100644
--- a/tools/include/linux/hash.h
+++ b/tools/include/linux/hash.h
@@ -1,4 +1,3 @@
-/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_HASH_H
 #define _LINUX_HASH_H
 /* Fast hashing routine for ints,  longs and pointers.
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
index 14baf9f23a14..040651735662 100644
--- a/tools/include/uapi/asm-generic/ioctls.h
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_IOCTLS_H
 #define __ASM_GENERIC_IOCTLS_H
 
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 203268f9231e..6d319c46fd90 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_MMAN_COMMON_H
 #define __ASM_GENERIC_MMAN_COMMON_H
 
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index f7c7b4355e56..2dffcbf705b3 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -1,8 +1,8 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <uapi/asm-generic/mman-common.h>
+#include <asm-generic/mman-common.h>
 
 #define MAP_GROWSDOWN	0x0100		/* stack-like segment */
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 01cc7ba39924..30f2ce76b517 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  *
  * This program is free software; you can redistribute it and/or
@@ -569,10 +570,9 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(skb, map, key, flags)
+ * int bpf_sk_redirect_map(map, key, flags)
  *     Redirect skb to a sock in map using key as a lookup key for the
  *     sock in map.
- *     @skb: pointer to skb
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h
index 64ba734aba80..18be90725ab0 100644
--- a/tools/include/uapi/linux/bpf_common.h
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI__LINUX_BPF_COMMON_H__
 #define _UAPI__LINUX_BPF_COMMON_H__
 
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index b6705247afe8..6448cdd9a350 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_FCNTL_H
 #define _UAPI_LINUX_FCNTL_H
 
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
index 6394ea9d5524..965e4d8606d8 100644
--- a/tools/include/uapi/linux/hw_breakpoint.h
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_HW_BREAKPOINT_H
 #define _UAPI_LINUX_HW_BREAKPOINT_H
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 838887587411..7e99999d6236 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __LINUX_KVM_H
 #define __LINUX_KVM_H
 
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 64d2b4e556e5..bfd5938fede6 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_MMAN_H
 #define _UAPI_LINUX_MMAN_H
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 140ae638cfd6..362493a2f950 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Performance events:
  *
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index e2a6c7b3510b..30a9e51bbb1e 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_SCHED_H
 #define _UAPI_LINUX_SCHED_H
 
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 9eac599afd91..7b35e98d3c58 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_STAT_H
 #define _UAPI_LINUX_STAT_H
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 60180c0b5dc6..c51f8e5cc608 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_VHOST_H
 #define _LINUX_VHOST_H
 /* Userspace interface for in-kernel virtio accelerators. */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 87bf30b182df..c227ccba60ae 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
 /*
  *  Advanced Linux Sound Architecture - ALSA - Driver
  *  Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>,
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4397a8b6e6cd..aa66791b1bfc 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -606,9 +606,19 @@ static struct arch *arch__find(const char *name)
 int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	const size_t size = symbol__size(sym);
+	size_t size = symbol__size(sym);
 	size_t sizeof_sym_hist;
 
+	/*
+	 * Add buffer of one element for zero length symbol.
+	 * When sample is taken from first instruction of
+	 * zero length symbol, perf still resolves it and
+	 * shows symbol name in perf report and allows to
+	 * annotate it.
+	 */
+	if (size == 0)
+		size = 1;
+
 	/* Check for overflow when calculating sizeof_sym_hist */
 	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry))
 		return -1;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index dcfdafdc2f1c..6680e4fb7967 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -154,6 +154,10 @@ do {							\
 	yycolumn += yyleng;				\
 } while (0);
 
+#define USER_REJECT		\
+	yycolumn -= yyleng;	\
+	REJECT
+
 %}
 
 %x mem
@@ -335,8 +339,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}		{ if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}		{ if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 47a74bdcbfeff543f706dc0e385eebbb5d655ed2 Merge tag 'perf-urgent-for-mingo-4.14-20171010' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Some tooling fixes plus three kernel fixes: a memory leak fix, a statistics fix 
and a crash fix.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools include uapi bpf.h: Sync kernel ABI header with tooling header

Colin Ian King (1):
      perf/x86/intel/uncore: Fix memory leaks on allocation failures

Mark Rutland (1):
      perf pmu: Unbreak perf record for arm/arm64 with events with explicit PMU

Mark Santaniello (1):
      perf script: Add missing separator for "-F ip,brstack" (and brstackoff)

Ravi Bangoria (1):
      perf callchain: Compare dsos (as well) for CCKEY_FUNCTION

Will Deacon (1):
      perf/core: Avoid freeing static PMU contexts when PMU is unregistered

leilei.lin (1):
      perf/core: Fix cgroup time when scheduling descendants


 arch/x86/events/intel/uncore.c | 12 +++++++--
 kernel/events/core.c           | 10 +++++++-
 tools/include/uapi/linux/bpf.h |  2 +-
 tools/perf/builtin-script.c    |  4 +--
 tools/perf/util/callchain.c    |  6 ++++-
 tools/perf/util/parse-events.c |  9 ++++---
 tools/perf/util/pmu.c          | 56 +++++++++++++++++++++++++++++++-----------
 tools/perf/util/pmu.h          |  1 +
 8 files changed, 74 insertions(+), 26 deletions(-)

diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 1c5390f1cf09..d45e06346f14 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
 		if (!pmus[i].boxes)
-			return -ENOMEM;
+			goto err;
 	}
 
 	type->pmus = pmus;
@@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 		attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
 					sizeof(*attr_group), GFP_KERNEL);
 		if (!attr_group)
-			return -ENOMEM;
+			goto err;
 
 		attrs = (struct attribute **)(attr_group + 1);
 		attr_group->name = "events";
@@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	}
 
 	type->pmu_group = &uncore_pmu_attr_group;
+
 	return 0;
+
+err:
+	for (i = 0; i < type->num_boxes; i++)
+		kfree(pmus[i].boxes);
+	kfree(pmus);
+
+	return -ENOMEM;
 }
 
 static int __init
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6bc21e202ae4..9d93db81fa36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgrp == event->cgrp)
+       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
@@ -8955,6 +8955,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 
 static void free_pmu_context(struct pmu *pmu)
 {
+	/*
+	 * Static contexts such as perf_sw_context have a global lifetime
+	 * and may be shared between different PMUs. Avoid freeing them
+	 * when a single PMU is going away.
+	 */
+	if (pmu->task_ctx_nr > perf_invalid_context)
+		return;
+
 	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
 	mutex_unlock(&pmus_lock);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 43ab5c402f98..f90860d1f897 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -312,7 +312,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3d4c3b5e1868..0c977b6e0f8b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -586,7 +586,7 @@ static void print_sample_brstack(struct perf_sample *sample,
 			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		}
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
@@ -681,7 +681,7 @@ static void print_sample_brstackoff(struct perf_sample *sample,
 		if (alt.map && !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index be09d77cade0..a971caf3759d 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -685,6 +685,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
+	struct dso *left_dso = NULL;
+	struct dso *right_dso = NULL;
 
 	if (callchain_param.key == CCKEY_SRCLINE) {
 		enum match_result match = match_chain_srcline(node, cnode);
@@ -696,12 +698,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
+		left_dso = cnode->ms.map->dso;
+		right_dso = node->map->dso;
 	} else {
 		left = cnode->ip;
 		right = node->ip;
 	}
 
-	if (left == right) {
+	if (left == right && left_dso == right_dso) {
 		if (node->branch) {
 			cnode->branch_count++;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f6257fb4f08c..39b15968eab1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -309,10 +309,11 @@ static char *get_config_name(struct list_head *head_terms)
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
-	    char *name, struct cpu_map *cpus,
+	    char *name, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats)
 {
 	struct perf_evsel *evsel;
+	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
 	event_attr_init(attr);
 
@@ -323,7 +324,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->cpus        = cpu_map__get(cpus);
 	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = !!cpus;
+	evsel->system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
@@ -1233,7 +1234,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1254,7 +1255,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
-			    get_config_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats);
 	if (evsel) {
 		evsel->unit = info.unit;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ac16a9db1fb5..1c4d7b4e4fb5 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -470,17 +470,36 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
+static struct cpu_map *__pmu_cpumask(const char *path)
+{
+	FILE *file;
+	struct cpu_map *cpus;
+
+	file = fopen(path, "r");
+	if (!file)
+		return NULL;
+
+	cpus = cpu_map__read(file);
+	fclose(file);
+	return cpus;
+}
+
+/*
+ * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
+ * may have a "cpus" file.
+ */
+#define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
+#define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
+
 static struct cpu_map *pmu_cpumask(const char *name)
 {
-	struct stat st;
 	char path[PATH_MAX];
-	FILE *file;
 	struct cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
 	const char *templates[] = {
-		 "%s/bus/event_source/devices/%s/cpumask",
-		 "%s/bus/event_source/devices/%s/cpus",
-		 NULL
+		CPUS_TEMPLATE_UNCORE,
+		CPUS_TEMPLATE_CPU,
+		NULL
 	};
 	const char **template;
 
@@ -489,20 +508,25 @@ static struct cpu_map *pmu_cpumask(const char *name)
 
 	for (template = templates; *template; template++) {
 		snprintf(path, PATH_MAX, *template, sysfs, name);
-		if (stat(path, &st) == 0)
-			break;
+		cpus = __pmu_cpumask(path);
+		if (cpus)
+			return cpus;
 	}
 
-	if (!*template)
-		return NULL;
+	return NULL;
+}
 
-	file = fopen(path, "r");
-	if (!file)
-		return NULL;
+static bool pmu_is_uncore(const char *name)
+{
+	char path[PATH_MAX];
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
 
-	cpus = cpu_map__read(file);
-	fclose(file);
-	return cpus;
+	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
+	cpus = __pmu_cpumask(path);
+	cpu_map__put(cpus);
+
+	return !!cpus;
 }
 
 /*
@@ -617,6 +641,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
 
 	pmu->cpus = pmu_cpumask(name);
 
+	pmu->is_uncore = pmu_is_uncore(name);
+
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 389e9729331f..fe0de0502ce2 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,7 @@ struct perf_pmu {
 	char *name;
 	__u32 type;
 	bool selectable;
+	bool is_uncore;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: b130a699c07155a1d6ef7d971a5f3bf0e3818d5a Merge tag 'perf-urgent-for-mingo-4.14-20170912' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

A handful of tooling fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (1):
      tools include linux: Guard against redefinition of some macros

Jiri Olsa (4):
      tools lib api: Fix make DEBUG=1 build
      perf tools: Open perf.data with O_CLOEXEC flag
      perf ui progress: Make sure we always define step value
      perf ui progress: Fix progress update

Milian Wolff (3):
      perf tests: Fix compile when libunwind's unwind.h is available
      perf tools: Support running perf binaries with a dash in their name
      perf stat: Wait for the correct child

Taeung Song (1):
      perf config: Check not only section->from_system_config but also item's


 tools/include/linux/compiler-gcc.h |  9 ++++++---
 tools/lib/api/Makefile             |  8 +++++++-
 tools/perf/builtin-config.c        |  2 +-
 tools/perf/builtin-stat.c          |  2 +-
 tools/perf/perf.c                  | 14 ++++++++++----
 tools/perf/tests/dwarf-unwind.c    |  2 +-
 tools/perf/ui/progress.c           |  9 +++++++--
 tools/perf/util/data.c             | 13 ++++++++++++-
 8 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index bd39b2090ad1..3723b9f8f964 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -21,11 +21,14 @@
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
 #define  noinline	__attribute__((noinline))
-
+#ifndef __packed
 #define __packed	__attribute__((packed))
-
+#endif
+#ifndef __noreturn
 #define __noreturn	__attribute__((noreturn))
-
+#endif
+#ifndef __aligned
 #define __aligned(x)	__attribute__((aligned(x)))
+#endif
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 #define __scanf(a, b)	__attribute__((format(scanf, a, b)))
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 4563ba7ede6f..1e83e3c07448 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -17,13 +17,19 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC
 
+ifeq ($(DEBUG),0)
 ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
 endif
+endif
+
+ifeq ($(DEBUG),0)
+  CFLAGS += -D_FORTIFY_SOURCE
+endif
 
 # Treat warnings as errors unless directed not to
 ifneq ($(WERROR),0)
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 3ddcc6e2abeb..a1d82e33282c 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -59,7 +59,7 @@ static int set_config(struct perf_config_set *set, const char *file_name,
 		fprintf(fp, "[%s]\n", section->name);
 
 		perf_config_items__for_each_entry(&section->items, item) {
-			if (!use_system_config && section->from_system_config)
+			if (!use_system_config && item->from_system_config)
 				continue;
 			if (item->value)
 				fprintf(fp, "\t%s = %s\n",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 85e992d9215b..69523ed55894 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -707,7 +707,7 @@ static int __run_perf_stat(int argc, const char **argv)
 				process_interval();
 			}
 		}
-		wait(&status);
+		waitpid(child_pid, &status, 0);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index e0279babe0c0..2f19e03c5c40 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -467,15 +467,21 @@ int main(int argc, const char **argv)
 	 *  - cannot execute it externally (since it would just do
 	 *    the same thing over again)
 	 *
-	 * So we just directly call the internal command handler, and
-	 * die if that one cannot handle it.
+	 * So we just directly call the internal command handler. If that one
+	 * fails to handle this, then maybe we just run a renamed perf binary
+	 * that contains a dash in its name. To handle this scenario, we just
+	 * fall through and ignore the "xxxx" part of the command string.
 	 */
 	if (strstarts(cmd, "perf-")) {
 		cmd += 5;
 		argv[0] = cmd;
 		handle_internal_command(argc, argv);
-		fprintf(stderr, "cannot handle %s internally", cmd);
-		goto out;
+		/*
+		 * If the command is handled, the above function does not
+		 * return undo changes and fall through in such a case.
+		 */
+		cmd -= 5;
+		argv[0] = cmd;
 	}
 	if (strstarts(cmd, "trace")) {
 #ifdef HAVE_LIBAUDIT_SUPPORT
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2a7b9b47bbcb..9ba1d216a89f 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -6,7 +6,7 @@
 #include "debug.h"
 #include "machine.h"
 #include "event.h"
-#include "unwind.h"
+#include "../util/unwind.h"
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index a0f24c7115c5..ae91c8148edf 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "progress.h"
 
@@ -14,10 +15,14 @@ struct ui_progress_ops *ui_progress__ops = &null_progress__ops;
 
 void ui_progress__update(struct ui_progress *p, u64 adv)
 {
+	u64 last = p->curr;
+
 	p->curr += adv;
 
 	if (p->curr >= p->next) {
-		p->next += p->step;
+		u64 nr = DIV_ROUND_UP(p->curr - last, p->step);
+
+		p->next += nr * p->step;
 		ui_progress__ops->update(p);
 	}
 }
@@ -25,7 +30,7 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
 void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
 {
 	p->curr = 0;
-	p->next = p->step = total / 16;
+	p->next = p->step = total / 16 ?: 1;
 	p->total = total;
 	p->title = title;
 
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e84bbc8ec058..263f5a906ba5 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -10,6 +10,16 @@
 #include "util.h"
 #include "debug.h"
 
+#ifndef O_CLOEXEC
+#ifdef __sparc__
+#define O_CLOEXEC	0x400000
+#elif defined(__alpha__) || defined(__hppa__)
+#define O_CLOEXEC	010000000
+#else
+#define O_CLOEXEC	02000000
+#endif
+#endif
+
 static bool check_pipe(struct perf_data_file *file)
 {
 	struct stat st;
@@ -96,7 +106,8 @@ static int open_file_write(struct perf_data_file *file)
 	if (check_backup(file))
 		return -1;
 
-	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+		  S_IRUSR|S_IWUSR);
 
 	if (fd < 0)
 		pr_err("failed to open %s : %s\n", file->path,

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 770e96125515daf1c7bc179323f2e0d488dfe6ac Merge tag 'perf-core-for-mingo-4.14-20170901' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Perf tooling updates and fixes.

 Thanks,

	Ingo

------------------>
Arnaldo Carvalho de Melo (4):
      perf syscalltbl: Support glob matching on syscall names
      perf trace: Support syscall name globbing
      perf stat: Only auto-merge events that are PMU aliases
      perf annotate browser: Help for cycling thru hottest instructions with TAB/shift+TAB

Jack Henschel (1):
      perf intel-pt: Fix syntax in documentation of config option

Jin Yao (1):
      perf report: Calculate the average cycles of iterations

Kan Liang (5):
      perf tools: Support new sample type for physical address
      perf sort: Add sort option for physical address
      perf mem: Support physical address
      perf script: Support physical address
      perf test: Add test case for PERF_SAMPLE_PHYS_ADDR

Ravi Bangoria (1):
      perf test powerpc: Fix 'Object code reading' test

Sukadev Bhattiprolu (1):
      perf vendor events powerpc: Remove duplicate events


 tools/include/uapi/linux/perf_event.h              |   4 +-
 tools/perf/Documentation/intel-pt.txt              |   2 +-
 tools/perf/Documentation/perf-mem.txt              |   4 +
 tools/perf/Documentation/perf-record.txt           |   5 +-
 tools/perf/Documentation/perf-report.txt           |   1 +
 tools/perf/Documentation/perf-script.txt           |   2 +-
 tools/perf/Documentation/perf-trace.txt            |   2 +-
 tools/perf/builtin-mem.c                           |  97 ++++++++++++-----
 tools/perf/builtin-record.c                        |   2 +
 tools/perf/builtin-script.c                        |  15 ++-
 tools/perf/builtin-stat.c                          |   2 +-
 tools/perf/builtin-trace.c                         |  39 ++++++-
 tools/perf/perf.h                                  |   1 +
 .../pmu-events/arch/powerpc/power9/frontend.json   |   7 +-
 .../perf/pmu-events/arch/powerpc/power9/other.json | 120 ---------------------
 .../pmu-events/arch/powerpc/power9/pipeline.json   |   7 +-
 tools/perf/pmu-events/arch/powerpc/power9/pmc.json |   7 +-
 tools/perf/tests/code-reading.c                    |   5 +
 tools/perf/tests/sample-parsing.c                  |   6 +-
 tools/perf/ui/browsers/annotate.c                  |   3 +-
 tools/perf/ui/browsers/hists.c                     |   8 +-
 tools/perf/ui/stdio/hist.c                         |  10 +-
 tools/perf/util/callchain.c                        |  49 ++++-----
 tools/perf/util/callchain.h                        |   9 +-
 tools/perf/util/event.h                            |   1 +
 tools/perf/util/evsel.c                            |  19 +++-
 tools/perf/util/evsel.h                            |   1 +
 tools/perf/util/hist.c                             |   4 +
 tools/perf/util/hist.h                             |   1 +
 tools/perf/util/machine.c                          |  96 ++++++++++-------
 tools/perf/util/parse-events.c                     |  24 +++--
 tools/perf/util/session.c                          |   3 +
 tools/perf/util/sort.c                             |  42 ++++++++
 tools/perf/util/sort.h                             |   1 +
 tools/perf/util/symbol.h                           |   1 +
 tools/perf/util/syscalltbl.c                       |  33 ++++++
 tools/perf/util/syscalltbl.h                       |   3 +
 37 files changed, 368 insertions(+), 268 deletions(-)

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: df6c3db8d30fb1699ccbc403196b86324f4257af perf/x86/intel: Add proper condition to run sched_task callbacks

Two hw-enablement patches, two race fixes, three fixes for regressions of 
semantics, plus a number of tooling fixes.

 Thanks,

	Ingo

------------------>
Alexander Shishkin (1):
      perf/core: Fix scheduling regression of pinned groups

Arnaldo Carvalho de Melo (3):
      perf evsel: Fix attr.exclude_kernel setting for default cycles:p
      perf evsel: State in the default event name if attr.exclude_kernel is set
      perf symbols: Accept zero as the kernel base address

Harry Pan (1):
      perf/x86/intel: Enable C-state residency events for Apollo Lake

Ingo Molnar (1):
      Revert "perf/core: Drop kernel samples even though :u is specified"

Jin Yao (1):
      perf annotate: Fix broken arrow at row 0 connecting jmp instruction to its target

Jiri Olsa (3):
      perf/x86/intel: Fix debug_store reset field for freq events
      perf/core: Fix locking for children siblings group read
      perf/x86/intel: Add proper condition to run sched_task callbacks

Kan Liang (1):
      perf/x86/intel: Add Goldmont Plus CPU PMU support


 arch/x86/events/intel/core.c   | 164 ++++++++++++++++++++++++++++++++++++++++-
 arch/x86/events/intel/cstate.c |  26 +++++--
 arch/x86/events/intel/ds.c     |  22 ++++--
 arch/x86/events/intel/lbr.c    |   4 +
 arch/x86/events/perf_event.h   |   2 +
 kernel/events/core.c           |  33 +++------
 tools/perf/ui/browser.c        |   2 +-
 tools/perf/util/evsel.c        |   8 +-
 tools/perf/util/machine.c      |   2 +-
 9 files changed, 221 insertions(+), 42 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index aa62437d1aa1..98b0f0729527 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1708,6 +1708,120 @@ static __initconst const u64 glm_hw_cache_extra_regs
 	},
 };
 
+static __initconst const u64 glp_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x0380,	/* ICACHE.ACCESSES */
+			[C(RESULT_MISS)]	= 0x0280,	/* ICACHE.MISSES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0xe08,	/* DTLB_LOAD_MISSES.WALK_COMPLETED */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0xe49,	/* DTLB_STORE_MISSES.WALK_COMPLETED */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c0,	/* INST_RETIRED.ANY_P */
+			[C(RESULT_MISS)]	= 0x0481,	/* ITLB.MISS */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c4,	/* BR_INST_RETIRED.ALL_BRANCHES */
+			[C(RESULT_MISS)]	= 0x00c5,	/* BR_MISP_RETIRED.ALL_BRANCHES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+};
+
+static __initconst const u64 glp_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -3016,6 +3130,9 @@ static int hsw_hw_config(struct perf_event *event)
 	return 0;
 }
 
+static struct event_constraint counter0_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x1);
+
 static struct event_constraint counter2_constraint =
 			EVENT_CONSTRAINT(0, 0x4, 0);
 
@@ -3037,6 +3154,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return c;
 }
 
+static struct event_constraint *
+glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	/* :ppp means to do reduced skid PEBS which is PMC0 only. */
+	if (event->attr.precise_ip == 3)
+		return &counter0_constraint;
+
+	c = intel_get_event_constraints(cpuc, idx, event);
+
+	return c;
+}
+
 /*
  * Broadwell:
  *
@@ -3265,10 +3397,8 @@ static void intel_pmu_cpu_dying(int cpu)
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
 				 bool sched_in)
 {
-	if (x86_pmu.pebs_active)
-		intel_pmu_pebs_sched_task(ctx, sched_in);
-	if (x86_pmu.lbr_nr)
-		intel_pmu_lbr_sched_task(ctx, sched_in);
+	intel_pmu_pebs_sched_task(ctx, sched_in);
+	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
@@ -3838,6 +3968,32 @@ __init int intel_pmu_init(void)
 		pr_cont("Goldmont events, ");
 		break;
 
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		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,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_glm_extra_regs;
+		/*
+		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+		 * for precise cycles.
+		 */
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.get_event_constraints = glp_get_event_constraints;
+		x86_pmu.cpu_events = glm_events_attrs;
+		/* Goldmont Plus has 4-wide pipeline */
+		event_attr_td_total_slots_scale_glm.event_str = "4";
+		pr_cont("Goldmont plus events, ");
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 238ae3248ba5..4cf100ff2a37 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,16 +40,16 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT
+ *			 Available model: SLM,AMT,GLM
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL
+ *						SKL,KNL,GLM
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -57,16 +57,17 @@
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
+ *						GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL
+ *						SKL,KNL,GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -82,7 +83,7 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT only
+ *			       Available model: HSW ULT, GLM
  *			       Scope: Package (physical package)
  *
  */
@@ -504,6 +505,17 @@ static const struct cstate_model knl_cstates __initconst = {
 };
 
 
+static const struct cstate_model glm_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C3_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 
 #define X86_CSTATES_MODEL(model, states)				\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
@@ -546,6 +558,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c6d23ffe422d..a322fed5f8ed 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -606,12 +606,6 @@ static inline void intel_pmu_drain_pebs_buffer(void)
 	x86_pmu.drain_pebs(&regs);
 }
 
-void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
-{
-	if (!sched_in)
-		intel_pmu_drain_pebs_buffer();
-}
-
 /*
  * PEBS
  */
@@ -651,6 +645,12 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_glp_pebs_event_constraints[] = {
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -816,6 +816,14 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
 	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
 }
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!sched_in && pebs_needs_sched_cb(cpuc))
+		intel_pmu_drain_pebs_buffer();
+}
+
 static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
@@ -889,6 +897,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		ds->pebs_event_reset[hwc->idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	} else {
+		ds->pebs_event_reset[hwc->idx] = 0;
 	}
 }
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index eb261656a320..955457a30197 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -380,8 +380,12 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
+	if (!cpuc->lbr_users)
+		return;
+
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 53728eea1bed..476aec3a4cab 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -879,6 +879,8 @@ extern struct event_constraint intel_slm_pebs_event_constraints[];
 
 extern struct event_constraint intel_glm_pebs_event_constraints[];
 
+extern struct event_constraint intel_glp_pebs_event_constraints[];
+
 extern struct event_constraint intel_nehalem_pebs_event_constraints[];
 
 extern struct event_constraint intel_westmere_pebs_event_constraints[];
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4d2c32f98482..c17c0881fd36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1452,6 +1452,13 @@ static enum event_type_t get_event_type(struct perf_event *event)
 
 	lockdep_assert_held(&ctx->lock);
 
+	/*
+	 * It's 'group type', really, because if our group leader is
+	 * pinned, so are we.
+	 */
+	if (event->group_leader != event)
+		event = event->group_leader;
+
 	event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
 	if (!ctx->task)
 		event_type |= EVENT_CPU;
@@ -4365,7 +4372,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
 static int __perf_read_group_add(struct perf_event *leader,
 					u64 read_format, u64 *values)
 {
+	struct perf_event_context *ctx = leader->ctx;
 	struct perf_event *sub;
+	unsigned long flags;
 	int n = 1; /* skip @nr */
 	int ret;
 
@@ -4395,12 +4404,15 @@ static int __perf_read_group_add(struct perf_event *leader,
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
 
+	raw_spin_lock_irqsave(&ctx->lock, flags);
+
 	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
 		values[n++] += perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
 	}
 
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	return 0;
 }
 
@@ -7308,21 +7320,6 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
-static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
-{
-	/*
-	 * Due to interrupt latency (AKA "skid"), we may enter the
-	 * kernel before taking an overflow, even if the PMU is only
-	 * counting user events.
-	 * To avoid leaking information to userspace, we must always
-	 * reject kernel samples when exclude_kernel is set.
-	 */
-	if (event->attr.exclude_kernel && !user_mode(regs))
-		return false;
-
-	return true;
-}
-
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7344,12 +7341,6 @@ static int __perf_event_overflow(struct perf_event *event,
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
-	 * For security, drop the skid kernel samples if necessary.
-	 */
-	if (!sample_is_allowed(event, regs))
-		return ret;
-
-	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index a4d3762cd825..83874b0e266c 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -704,7 +704,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 		ui_browser__gotorc(browser, row, column + 1);
 		SLsmg_draw_hline(2);
 
-		if (row++ == 0)
+		if (++row == 0)
 			goto out;
 	} else
 		row = 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 87b431886670..413f74df08de 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -273,7 +273,7 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
+		.exclude_kernel	= geteuid() != 0,
 	};
 	struct perf_evsel *evsel;
 
@@ -298,8 +298,10 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 		goto out;
 
 	/* use asprintf() because free(evsel) assumes name is allocated */
-	if (asprintf(&evsel->name, "cycles%.*s",
-		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
+	if (asprintf(&evsel->name, "cycles%s%s%.*s",
+		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
+		     attr.exclude_kernel ? "u" : "",
+		     attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0)
 		goto error_free;
 out:
 	return evsel;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5de2b86b9880..2e9eb6aa3ce2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2209,7 +2209,7 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (map->start)
+		if (!err)
 			machine->kernel_start = map->start;
 	}
 	return err;

[GIT PULL] perf fixes

[Ingo Molnar]

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

   # HEAD: 47c1ded7fef108c730b803cd386241beffcdd15c Merge tag 'perf-urgent-for-mingo-4.12-20170608' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

This is mostly tooling fixes, plus an instruction pointer filtering fix. It's more 
fixes than usual - Arnaldo got back from a longer vacation and there was a 
backlog.

 Thanks,

	Ingo

------------------>
Andi Kleen (1):
      perf stat: Only print NMI watchdog hint when enabled

Jin Yao (1):
      perf/core: Drop kernel samples even though :u is specified

Jiri Olsa (2):
      perf trace: Add mmap alias for s390
      perf test: Disable breakpoint signal tests for powerpc

Kim Phillips (2):
      perf annotate: Fix branch instruction with multiple operands
      perf annotate: Add missing powerpc triplet

Milian Wolff (2):
      perf report: Include partial stacks unwound with libdw
      perf report: Ensure the perf DSO mapping matches what libdw sees

Namhyung Kim (12):
      perf header: Set proper module name when build-id event found
      perf symbols: Set module info when build-id event found
      perf symbols: Use correct filename for compressed modules in build-id cache
      perf annotate: Fix symbolic link of build-id cache
      perf tools: Fix a memory leak in __open_dso()
      perf tools: Introduce dso__decompress_kmodule_{fd,path}
      perf annotate: Use dso__decompress_kmodule_path()
      perf tools: Decompress kernel module when reading DSO data
      perf tools: Consolidate error path in __open_dso()
      perf tests: Decompress kernel module before objdump
      perf symbols: Keep DSO->symtab_type after decompress
      perf symbols: Kill dso__build_id_is_kmod()

Ravi Bangoria (1):
      perf annotate: Fix failure when filename has special chars

SeongJae Park (6):
      perf probe: Fix examples section of documentation
      perf script: Fix outdated comment for perf-trace-python
      perf script: Fix documentation errors
      perf script python: Fix wrong code snippets in documentation
      perf script python: Updated trace_unhandled() signature
      perf script python: Remove dups in documentation examples


 kernel/events/core.c                               |  21 +++++
 tools/perf/Documentation/perf-probe.txt            |   8 +-
 tools/perf/Documentation/perf-script-perl.txt      |   2 +-
 tools/perf/Documentation/perf-script-python.txt    |  23 ++---
 tools/perf/arch/common.c                           |   1 +
 tools/perf/builtin-stat.c                          |   5 +-
 tools/perf/builtin-trace.c                         |   4 +
 tools/perf/tests/bp_signal.c                       |  14 +++
 tools/perf/tests/builtin-test.c                    |   7 ++
 tools/perf/tests/code-reading.c                    |  20 ++++-
 tools/perf/tests/tests.h                           |   3 +
 tools/perf/util/annotate.c                         |  72 +++++++++------
 tools/perf/util/build-id.c                         |  45 ----------
 tools/perf/util/build-id.h                         |   1 -
 tools/perf/util/dso.c                              | 100 +++++++++++++++++++--
 tools/perf/util/dso.h                              |   9 ++
 tools/perf/util/header.c                           |  12 ++-
 tools/perf/util/machine.c                          |  11 +--
 .../util/scripting-engines/trace-event-python.c    |   2 +-
 tools/perf/util/symbol-elf.c                       |  41 +--------
 tools/perf/util/symbol.c                           |   4 -
 tools/perf/util/unwind-libdw.c                     |  10 ++-
 22 files changed, 259 insertions(+), 156 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c9412d..6c4e523dc1e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7316,6 +7316,21 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7337,6 +7352,12 @@ static int __perf_event_overflow(struct perf_event *event,
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index e6c9902c6d82..165c2b1d4317 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -240,9 +240,13 @@ EXAMPLES
  or
  ./perf probe --add='schedule:12 cpu'
 
- this will add one or more probes which has the name start with "schedule".
+Add one or more probes which has the name start with "schedule".
 
- Add probes on lines in schedule() function which calls update_rq_clock().
+ ./perf probe schedule*
+ or
+ ./perf probe --add='schedule*'
+
+Add probes on lines in schedule() function which calls update_rq_clock().
 
  ./perf probe 'schedule;update_rq_clock*'
  or
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index dfbb506d2c34..142606c0ec9c 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -39,7 +39,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 54acba221558..51ec2d20068a 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -149,10 +149,8 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 		print "id=%d, args=%s\n" % \
 		(id, args),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
-		print_header(event_name, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm)
+def trace_unhandled(event_name, context, event_fields_dict):
+		print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
 
 def print_header(event_name, cpu, secs, nsecs, pid, comm):
 	print "%-20s %5u %05u.%09u %8u %-20s " % \
@@ -321,7 +319,7 @@ So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
 you're interested in - basically find the tracepoint(s) you're
 interested in by looking at the list of available events shown by
-'perf list' and/or look in /sys/kernel/debug/tracing events for
+'perf list' and/or look in /sys/kernel/debug/tracing/events/ for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
 generate a skeleton script using 'perf script -g python' and modify the
@@ -334,7 +332,7 @@ right place, you can have your script listed alongside the other
 scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -383,8 +381,6 @@ to be located in the perf/scripts/python directory in the kernel
 
 ----
 # ls -al kernel-source/tools/perf/scripts/python
-
-root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
 total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
@@ -399,7 +395,7 @@ otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -437,7 +433,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
@@ -532,7 +528,7 @@ Aside from the event handler functions discussed above, every script
 gives scripts a chance to do setup tasks:
 
 ----
-def trace_begin:
+def trace_begin():
     pass
 ----
 
@@ -541,7 +537,7 @@ Aside from the event handler functions discussed above, every script
  as display results:
 
 ----
-def trace_end:
+def trace_end():
     pass
 ----
 
@@ -550,8 +546,7 @@ Aside from the event handler functions discussed above, every script
  of common arguments are passed into it:
 
 ----
-def trace_unhandled(event_name, context, common_cpu, common_secs,
-        common_nsecs, common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     pass
 ----
 
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 837067f48a4c..6b40e9f01740 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -26,6 +26,7 @@ const char *const arm64_triplets[] = {
 
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
+	"powerpc-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
 	"powerpc64-linux-gnu-",
 	"powerpc64le-linux-gnu-",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a935b5023732..ad9324d1daf9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1578,6 +1578,7 @@ static void print_header(int argc, const char **argv)
 static void print_footer(void)
 {
 	FILE *output = stat_config.output;
+	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
@@ -1590,7 +1591,9 @@ static void print_footer(void)
 	}
 	fprintf(output, "\n\n");
 
-	if (print_free_counters_hint)
+	if (print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d014350adc52..4b2a5d298197 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -681,6 +681,10 @@ static struct syscall_fmt {
 	{ .name	    = "mlockall",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mmap",	    .hexret = true,
+/* The standard mmap maps to old_mmap on s390x */
+#if defined(__s390x__)
+	.alias = "old_mmap",
+#endif
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
 			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index e7664fe3bd33..8ba2c4618fe9 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -288,3 +288,17 @@ int test__bp_signal(int subtest __maybe_unused)
 	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
+
+bool test__bp_signal_is_supported(void)
+{
+/*
+ * The powerpc so far does not have support to even create
+ * instruction breakpoint using the perf event interface.
+ * Once it's there we can release this.
+ */
+#ifdef __powerpc__
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 9e08d297f1a9..3ccfd58a8c3c 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -97,10 +97,12 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint overflow signal handler",
 		.func = test__bp_signal,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Breakpoint overflow sampling",
 		.func = test__bp_signal_overflow,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",
@@ -401,6 +403,11 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		if (!perf_test__matches(t, curr, argc, argv))
 			continue;
 
+		if (t->is_supported && !t->is_supported()) {
+			pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
+			continue;
+		}
+
 		pr_info("%2d: %-*s:", i, width, t->desc);
 
 		if (intlist__find(skiplist, i)) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 1f14e7612cbb..94b7c7b02bde 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,6 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	unsigned char buf2[BUFSZ];
 	size_t ret_len;
 	u64 objdump_addr;
+	const char *objdump_name;
+	char decomp_name[KMOD_DECOMP_LEN];
 	int ret;
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -289,9 +291,25 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		state->done[state->done_cnt++] = al.map->start;
 	}
 
+	objdump_name = al.map->dso->long_name;
+	if (dso__needs_decompress(al.map->dso)) {
+		if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
+						 decomp_name,
+						 sizeof(decomp_name)) < 0) {
+			pr_debug("decompression failed\n");
+			return -1;
+		}
+
+		objdump_name = decomp_name;
+	}
+
 	/* Read the object code using objdump */
 	objdump_addr = map__rip_2objdump(al.map, al.addr);
-	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+	ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
+
+	if (dso__needs_decompress(al.map->dso))
+		unlink(objdump_name);
+
 	if (ret > 0) {
 		/*
 		 * The kernel maps are inaccurate - assume objdump is right in
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 631859629403..577363809c9b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -34,6 +34,7 @@ struct test {
 		int (*get_nr)(void);
 		const char *(*get_desc)(int subtest);
 	} subtest;
+	bool (*is_supported)(void);
 };
 
 /* Tests */
@@ -99,6 +100,8 @@ const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(int subtest);
 
+bool test__bp_signal_is_supported(void);
+
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 683f8340460c..ddbd56df9187 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -239,10 +239,20 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	const char *s = strchr(ops->raw, '+');
 	const char *c = strchr(ops->raw, ',');
 
-	if (c++ != NULL)
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
 		ops->target.addr = strtoull(c, NULL, 16);
-	else
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
 		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
 
 	if (s++ != NULL) {
 		ops->target.offset = strtoull(s, NULL, 16);
@@ -257,10 +267,27 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
+	const char *c = strchr(ops->raw, ',');
+
 	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
 }
 
 static struct ins_ops jump_ops = {
@@ -1294,6 +1321,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	char linkname[PATH_MAX];
 	char *build_id_filename;
 	char *build_id_path = NULL;
+	char *pos;
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso))
@@ -1313,7 +1341,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	if (!build_id_path)
 		return -1;
 
-	dirname(build_id_path);
+	/*
+	 * old style build-id cache has name of XX/XXXXXXX.. while
+	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+	 * extract the build-id part of dirname in the new style only.
+	 */
+	pos = strrchr(build_id_path, '/');
+	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+		dirname(build_id_path);
 
 	if (dso__is_kcore(dso) ||
 	    readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
@@ -1396,31 +1431,10 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 				sizeof(symfs_filename));
 		}
 	} else if (dso__needs_decompress(dso)) {
-		char tmp[PATH_MAX];
-		struct kmod_path m;
-		int fd;
-		bool ret;
-
-		if (kmod_path__parse_ext(&m, symfs_filename))
-			goto out;
-
-		snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
-
-		fd = mkstemp(tmp);
-		if (fd < 0) {
-			free(m.ext);
-			goto out;
-		}
-
-		ret = decompress_to_file(m.ext, symfs_filename, fd);
-
-		if (ret)
-			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
-
-		free(m.ext);
-		close(fd);
+		char tmp[KMOD_DECOMP_LEN];
 
-		if (!ret)
+		if (dso__decompress_kmodule_path(dso, symfs_filename,
+						 tmp, sizeof(tmp)) < 0)
 			goto out;
 
 		strcpy(symfs_filename, tmp);
@@ -1429,7 +1443,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
+		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 168cc49654e7..e0148b081bdf 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -278,51 +278,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return bf;
 }
 
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
-{
-	char *id_name = NULL, *ch;
-	struct stat sb;
-	char sbuild_id[SBUILD_ID_SIZE];
-
-	if (!dso->has_build_id)
-		goto err;
-
-	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-	id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
-	if (!id_name)
-		goto err;
-	if (access(id_name, F_OK))
-		goto err;
-	if (lstat(id_name, &sb) == -1)
-		goto err;
-	if ((size_t)sb.st_size > size - 1)
-		goto err;
-	if (readlink(id_name, bf, size - 1) < 0)
-		goto err;
-
-	bf[sb.st_size] = '\0';
-
-	/*
-	 * link should be:
-	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
-	 */
-	ch = strrchr(bf, '/');
-	if (!ch)
-		goto err;
-	if (ch - 3 < bf)
-		goto err;
-
-	free(id_name);
-	return strncmp(".ko", ch - 3, 3) == 0;
-err:
-	pr_err("Invalid build id: %s\n", id_name ? :
-					 dso->long_name ? :
-					 dso->short_name ? :
-					 "[unknown]");
-	free(id_name);
-	return false;
-}
-
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 8a89b195c1fc..96690a55c62c 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -17,7 +17,6 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
 				    size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index a96a99d2369f..4e7ab611377a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -248,6 +248,64 @@ bool dso__needs_decompress(struct dso *dso)
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+{
+	int fd = -1;
+	struct kmod_path m;
+
+	if (!dso__needs_decompress(dso))
+		return -1;
+
+	if (kmod_path__parse_ext(&m, dso->long_name))
+		return -1;
+
+	if (!m.comp)
+		goto out;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0) {
+		dso->load_errno = errno;
+		goto out;
+	}
+
+	if (!decompress_to_file(m.ext, name, fd)) {
+		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+		close(fd);
+		fd = -1;
+	}
+
+out:
+	free(m.ext);
+	return fd;
+}
+
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	unlink(tmpbuf);
+	return fd;
+}
+
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	if (fd < 0) {
+		unlink(tmpbuf);
+		return -1;
+	}
+
+	strncpy(pathname, tmpbuf, len);
+	close(fd);
+	return 0;
+}
+
 /*
  * Parses kernel module specified in @path and updates
  * @m argument like:
@@ -335,6 +393,21 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 	return 0;
 }
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine)
+{
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (m->kmod && m->comp)
+		dso->symtab_type++;
+
+	dso__set_short_name(dso, strdup(m->name), true);
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
@@ -381,7 +454,7 @@ static int do_open(char *name)
 
 static int __open_dso(struct dso *dso, struct machine *machine)
 {
-	int fd;
+	int fd = -EINVAL;
 	char *root_dir = (char *)"";
 	char *name = malloc(PATH_MAX);
 
@@ -392,15 +465,30 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		root_dir = machine->root_dir;
 
 	if (dso__read_binary_type_filename(dso, dso->binary_type,
-					    root_dir, name, PATH_MAX)) {
-		free(name);
-		return -EINVAL;
-	}
+					    root_dir, name, PATH_MAX))
+		goto out;
 
 	if (!is_regular_file(name))
-		return -EINVAL;
+		goto out;
+
+	if (dso__needs_decompress(dso)) {
+		char newpath[KMOD_DECOMP_LEN];
+		size_t len = sizeof(newpath);
+
+		if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
+			fd = -dso->load_errno;
+			goto out;
+		}
+
+		strcpy(name, newpath);
+	}
 
 	fd = do_open(name);
+
+	if (dso__needs_decompress(dso))
+		unlink(name);
+
+out:
 	free(name);
 	return fd;
 }