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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Intel Knights Landing support.  (Harish Chegondi)

   - Intel Broadwell-EP uncore PMU support.  (Kan Liang)

   - Core code improvements.  (Peter Zijlstra.)

   - Event filter, LBR and PEBS fixes.  (Stephane Eranian)

   - Enable cycles:pp on Intel Atom.  (Stephane Eranian)

   - Add cycles:ppp support for Skylake.  (Andi Kleen)

   - Various x86 NMI overhead optimizations.  (Andi Kleen)

   - Intel PT enhancements.  (Takao Indoh)

   - AMD cache events fix.  (Vince Weaver)

  Tons of tooling changes:

   - Show random perf tool tips in the 'perf report' bottom line
     (Namhyung Kim)

   - perf report now defaults to --group if the perf.data file has
     grouped events, try it with:

      # perf record -e '{cycles,instructions}' -a sleep 1
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
      # perf report
      # Samples: 1K of event 'anon group { cycles, instructions }'
      # Event count (approx.): 1955219195
      #
      #       Overhead  Command     Shared Object      Symbol

         2.86%   0.22%  swapper     [kernel.kallsyms]  [k] intel_idle
         1.05%   0.33%  firefox     libxul.so          [.] js::SetObjectElement
         1.05%   0.00%  kworker/0:3 [kernel.kallsyms]  [k] gen6_ring_get_seqno
         0.88%   0.17%  chrome      chrome             [.] 0x0000000000ee27ab
         0.65%   0.86%  firefox     libxul.so          [.] js::ValueToId<(js::AllowGC)1>
         0.64%   0.23%  JS Helper   libxul.so          [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
         0.62%   1.27%  firefox     libxul.so          [.] js::GetIterator
         0.61%   1.74%  firefox     libxul.so          [.] js::NativeSetProperty
         0.61%   0.31%  firefox     libxul.so          [.] js::SetPropertyByDefining

   - Introduce the 'perf stat record/report' workflow:

     Generate perf.data files from 'perf stat', to tap into the
     scripting capabilities perf has instead of defining a 'perf stat'
     specific scripting support to calculate event ratios, etc.

     Simple example:

        $ perf stat record -e cycles usleep 1

         Performance counter stats for 'usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $ perf stat report

         Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $

     It generates PERF_RECORD_ userspace records to store the details:

        $ perf report -D | grep PERF_RECORD
        0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
        0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
        0x12a [0x40]: PERF_RECORD_STAT_CONFIG
        0x16a [0x30]: PERF_RECORD_STAT
        -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
        0x1da [0x18]: PERF_RECORD_STAT_ROUND
        [acme@ssdandy linux]$

     An effort was made to make perf.data files generated like this to
     not generate cryptic messages when processed by older tools.

     The 'perf script' bits need rebasing, will go up later.

   - Make command line options always available, even when they depend
     on some feature being enabled, warning the user about use of such
     options (Wang Nan)

   - Support hw breakpoint events (mem:0xAddress) in the default output
     mode in 'perf script' (Wang Nan)

   - Fixes and improvements for supporting annotating ARM binaries,
     support ARM call and jump instructions, more work needed to have
     arch specific stuff separated into tools/perf/arch/*/annotate/
     (Russell King)

   - Add initial 'perf config' command, for now just with a --list
     command to the contents of the configuration file in use and a
     basic man page describing its format, commands for doing edits and
     detailed documentation are being reviewed and proof-read.  (Taeung
     Song)

   - Allows BPF scriptlets specify arguments to be fetched using DWARF
     info, using a prologue generated at compile/build time (He Kuang,
     Wang Nan)

   - Allow attaching BPF scriptlets to module symbols (Wang Nan)

   - Allow attaching BPF scriptlets to userspace code using uprobe (Wang
     Nan)

   - BPF programs now can specify 'perf probe' tunables via its section
     name, separating key=val values using semicolons (Wang Nan)

     Testing some of these new BPF features:

        Use case: get callchains when receiving SSL packets, filter then in the
                  kernel, at arbitrary place.

        # cat ssl.bpf.c
        #define SEC(NAME) __attribute__((section(NAME), used))

        struct pt_regs;

        SEC("func=__inet_lookup_established hnum")
        int func(struct pt_regs *ctx, int err, unsigned short port)
        {
                return err == 0 && port == 443;
        }

        char _license[] SEC("license") = "GPL";
        int  _version   SEC("version") = LINUX_VERSION_CODE;
        #
        # perf record -a -g -e ssl.bpf.c
        ^C[ perf record: Woken up 1 times to write data ]
        [ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ]
        # perf script | head -30
        swapper     0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux)
           856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux)
           2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux)
           2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux)
           96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux)
           969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux)
           2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux)
           95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux)
          1163ffa start_kernel ([kernel.vmlinux].init.text)
          11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text)
          1163623 x86_64_start_kernel ([kernel.vmlinux].init.text)

        qemu-system-x86  9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux)
           8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux)
             430a br_handle_frame_finish ([bridge])
             48bc br_handle_frame ([bridge])
           855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
        #

   - Use 'perf probe' various options to list functions, see what
     variables can be collected at any given point, experiment first
     collecting without a filter, then filter, use it together with
     'perf trace', 'perf top', with or without callchains, if it
     explodes, please tell us!

   - Introduce a new callchain mode: "folded", that will list per line
     representations of all callchains for a give histogram entry,
     facilitating 'perf report' output processing by other tools, such
     as Brendan Gregg's flamegraph tools (Namhyung Kim)

     E.g:

        # perf report | grep -v ^# | head
           18.37%     0.00%  swapper  [kernel.kallsyms]   [k] cpu_startup_entry
                           |
                           ---cpu_startup_entry
                              |
                              |--12.07%--start_secondary
                              |
                               --6.30%--rest_init
                                         start_kernel
                                         x86_64_start_reservations
                                         x86_64_start_kernel
         #

     Becomes, in "folded" mode:

        # perf report -g folded | grep -v ^# | head -5
            18.37%     0.00%  swapper [kernel.kallsyms]   [k] cpu_startup_entry
          12.07% cpu_startup_entry;start_secondary
           6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] call_cpuidle
          11.23% call_cpuidle;cpu_startup_entry;start_secondary
           5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter
          11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary
           5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            15.12%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter_state
         #

     The user can also select one of "count", "period" or "percent" as
     the first column.

  ... and lots of infrastructure enhancements, plus fixes and other
  changes, features I failed to list - see the shortlog and the git log
  for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits)
  perf evlist: Add --trace-fields option to show trace fields
  perf record: Store data mmaps for dwarf unwind
  perf libdw: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Use find_map function in access_dso_mem
  perf evlist: Remove perf_evlist__(enable|disable)_event functions
  perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
  perf report: Show random usage tip on the help line
  perf hists: Export a couple of hist functions
  perf diff: Use perf_hpp__register_sort_field interface
  perf tools: Add overhead/overhead_children keys defaults via string
  perf tools: Remove list entry from struct sort_entry
  perf tools: Include all tools/lib directory for tags/cscope/TAGS targets
  perf script: Align event name properly
  perf tools: Add missing headers in perf's MANIFEST
  perf tools: Do not show trace command if it's not compiled in
  perf report: Change default to use event group view
  perf top: Decay periods in callchains
  tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/
  tools lib: Sync tools/lib/find_bit.c with the kernel
  ...

1 files changed, 109 insertions, 177 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfc227ccfceb..bf8244190d0f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -126,6 +126,37 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info)
 	return data.ret;
 }
 
+static void event_function_call(struct perf_event *event,
+				int (*active)(void *),
+				void (*inactive)(void *),
+				void *data)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		cpu_function_call(event->cpu, active, data);
+		return;
+	}
+
+again:
+	if (!task_function_call(task, active, data))
+		return;
+
+	raw_spin_lock_irq(&ctx->lock);
+	if (ctx->is_active) {
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	inactive(data);
+	raw_spin_unlock_irq(&ctx->lock);
+}
+
 #define EVENT_OWNER_KERNEL ((void *) -1)
 
 static bool is_kernel_event(struct perf_event *event)
@@ -1629,6 +1660,17 @@ struct remove_event {
 	bool detach_group;
 };
 
+static void ___perf_remove_from_context(void *info)
+{
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
+	struct perf_event_context *ctx = event->ctx;
+
+	if (re->detach_group)
+		perf_group_detach(event);
+	list_del_event(event, ctx);
+}
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1656,7 +1698,6 @@ static int __perf_remove_from_context(void *info)
 	return 0;
 }
 
-
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
@@ -1673,7 +1714,6 @@ static int __perf_remove_from_context(void *info)
 static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
 	struct remove_event re = {
 		.event = event,
 		.detach_group = detach_group,
@@ -1681,44 +1721,8 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group
 
 	lockdep_assert_held(&ctx->mutex);
 
-	if (!task) {
-		/*
-		 * Per cpu events are removed via an smp call. The removal can
-		 * fail if the CPU is currently offline, but in that case we
-		 * already called __perf_remove_from_context from
-		 * perf_event_exit_cpu.
-		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
-		return;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_remove_from_context, &re))
-		return;
-
-	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * If we failed to find a running task, but find the context active now
-	 * that we've acquired the ctx->lock, retry.
-	 */
-	if (ctx->is_active) {
-		raw_spin_unlock_irq(&ctx->lock);
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-	/*
-	 * Since the task isn't running, its safe to remove the event, us
-	 * holding the ctx->lock ensures the task won't get scheduled in.
-	 */
-	if (detach_group)
-		perf_group_detach(event);
-	list_del_event(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_remove_from_context,
+			    ___perf_remove_from_context, &re);
 }
 
 /*
@@ -1762,6 +1766,20 @@ int __perf_event_disable(void *info)
 	return 0;
 }
 
+void ___perf_event_disable(void *info)
+{
+	struct perf_event *event = info;
+
+	/*
+	 * Since we have the lock this context can't be scheduled
+	 * in, so we can change the state safely.
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		update_group_times(event);
+		event->state = PERF_EVENT_STATE_OFF;
+	}
+}
+
 /*
  * Disable a event.
  *
@@ -1778,43 +1796,16 @@ int __perf_event_disable(void *info)
 static void _perf_event_disable(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
-
-	if (!task) {
-		/*
-		 * Disable the event on the cpu that it's on
-		 */
-		cpu_function_call(event->cpu, __perf_event_disable, event);
-		return;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_event_disable, event))
-		return;
 
 	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * If the event is still active, we need to retry the cross-call.
-	 */
-	if (event->state == PERF_EVENT_STATE_ACTIVE) {
+	if (event->state <= PERF_EVENT_STATE_OFF) {
 		raw_spin_unlock_irq(&ctx->lock);
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE) {
-		update_group_times(event);
-		event->state = PERF_EVENT_STATE_OFF;
+		return;
 	}
 	raw_spin_unlock_irq(&ctx->lock);
+
+	event_function_call(event, __perf_event_disable,
+			    ___perf_event_disable, event);
 }
 
 /*
@@ -2067,6 +2058,18 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 }
 
+static void ___perf_install_in_context(void *info)
+{
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
+
+	/*
+	 * Since the task isn't running, its safe to add the event, us holding
+	 * the ctx->lock ensures the task won't get scheduled in.
+	 */
+	add_event_to_ctx(event, ctx);
+}
+
 /*
  * Cross CPU call to install and enable a performance event
  *
@@ -2143,48 +2146,14 @@ perf_install_in_context(struct perf_event_context *ctx,
 			struct perf_event *event,
 			int cpu)
 {
-	struct task_struct *task = ctx->task;
-
 	lockdep_assert_held(&ctx->mutex);
 
 	event->ctx = ctx;
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
-	if (!task) {
-		/*
-		 * Per cpu events are installed via an smp call and
-		 * the install is always successful.
-		 */
-		cpu_function_call(cpu, __perf_install_in_context, event);
-		return;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_install_in_context, event))
-		return;
-
-	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * If we failed to find a running task, but find the context active now
-	 * that we've acquired the ctx->lock, retry.
-	 */
-	if (ctx->is_active) {
-		raw_spin_unlock_irq(&ctx->lock);
-		/*
-		 * Reload the task pointer, it might have been changed by
-		 * a concurrent perf_event_context_sched_out().
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-	/*
-	 * Since the task isn't running, its safe to add the event, us holding
-	 * the ctx->lock ensures the task won't get scheduled in.
-	 */
-	add_event_to_ctx(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_install_in_context,
+			    ___perf_install_in_context, event);
 }
 
 /*
@@ -2287,6 +2256,11 @@ unlock:
 	return 0;
 }
 
+void ___perf_event_enable(void *info)
+{
+	__perf_event_mark_enabled((struct perf_event *)info);
+}
+
 /*
  * Enable a event.
  *
@@ -2299,58 +2273,26 @@ unlock:
 static void _perf_event_enable(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task = ctx->task;
 
-	if (!task) {
-		/*
-		 * Enable the event on the cpu that it's on
-		 */
-		cpu_function_call(event->cpu, __perf_event_enable, event);
+	raw_spin_lock_irq(&ctx->lock);
+	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
+		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
 
-	raw_spin_lock_irq(&ctx->lock);
-	if (event->state >= PERF_EVENT_STATE_INACTIVE)
-		goto out;
-
 	/*
 	 * If the event is in error state, clear that first.
-	 * That way, if we see the event in error state below, we
-	 * know that it has gone back into error state, as distinct
-	 * from the task having been scheduled away before the
-	 * cross-call arrived.
+	 *
+	 * That way, if we see the event in error state below, we know that it
+	 * has gone back into error state, as distinct from the task having
+	 * been scheduled away before the cross-call arrived.
 	 */
 	if (event->state == PERF_EVENT_STATE_ERROR)
 		event->state = PERF_EVENT_STATE_OFF;
-
-retry:
-	if (!ctx->is_active) {
-		__perf_event_mark_enabled(event);
-		goto out;
-	}
-
 	raw_spin_unlock_irq(&ctx->lock);
 
-	if (!task_function_call(task, __perf_event_enable, event))
-		return;
-
-	raw_spin_lock_irq(&ctx->lock);
-
-	/*
-	 * If the context is active and the event is still off,
-	 * we need to retry the cross-call.
-	 */
-	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
-		/*
-		 * task could have been flipped by a concurrent
-		 * perf_event_context_sched_out()
-		 */
-		task = ctx->task;
-		goto retry;
-	}
-
-out:
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_event_enable,
+			    ___perf_event_enable, event);
 }
 
 /*
@@ -4149,6 +4091,22 @@ struct period_event {
 	u64 value;
 };
 
+static void ___perf_event_period(void *info)
+{
+	struct period_event *pe = info;
+	struct perf_event *event = pe->event;
+	u64 value = pe->value;
+
+	if (event->attr.freq) {
+		event->attr.sample_freq = value;
+	} else {
+		event->attr.sample_period = value;
+		event->hw.sample_period = value;
+	}
+
+	local64_set(&event->hw.period_left, 0);
+}
+
 static int __perf_event_period(void *info)
 {
 	struct period_event *pe = info;
@@ -4185,8 +4143,6 @@ static int __perf_event_period(void *info)
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct period_event pe = { .event = event, };
-	struct perf_event_context *ctx = event->ctx;
-	struct task_struct *task;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -4201,34 +4157,10 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
-	task = ctx->task;
 	pe.value = value;
 
-	if (!task) {
-		cpu_function_call(event->cpu, __perf_event_period, &pe);
-		return 0;
-	}
-
-retry:
-	if (!task_function_call(task, __perf_event_period, &pe))
-		return 0;
-
-	raw_spin_lock_irq(&ctx->lock);
-	if (ctx->is_active) {
-		raw_spin_unlock_irq(&ctx->lock);
-		task = ctx->task;
-		goto retry;
-	}
-
-	if (event->attr.freq) {
-		event->attr.sample_freq = value;
-	} else {
-		event->attr.sample_period = value;
-		event->hw.sample_period = value;
-	}
-
-	local64_set(&event->hw.period_left, 0);
-	raw_spin_unlock_irq(&ctx->lock);
+	event_function_call(event, __perf_event_period,
+			    ___perf_event_period, &pe);
 
 	return 0;
 }