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

…nux/kernel/git/tip/tip

Pull perf changes from Ingo Molnar:
 "Main changes:

  Kernel side changes:

   - Add SNB/IVB/HSW client uncore memory controller support (Stephane
     Eranian)

   - Fix various x86/P4 PMU driver bugs (Don Zickus)

  Tooling, user visible changes:

   - Add several futex 'perf bench' microbenchmarks (Davidlohr Bueso)

   - Speed up thread map generation (Don Zickus)

   - Introduce 'perf kvm --list-cmds' command line option for use by
     scripts (Ramkumar Ramachandra)

   - Print the evsel name in the annotate stdio output, prep to fix
     support outputting annotation for multiple events, not just for the
     first one (Arnaldo Carvalho de Melo)

   - Allow setting preferred callchain method in .perfconfig (Jiri Olsa)

   - Show in what binaries/modules 'perf probe's are set (Masami
     Hiramatsu)

   - Support distro-style debuginfo for uprobe in 'perf probe' (Masami
     Hiramatsu)

  Tooling, internal changes and fixes:

   - Use tid in mmap/mmap2 events to find maps (Don Zickus)

   - Record the reason for filtering an address_location (Namhyung Kim)

   - Apply all filters to an addr_location (Namhyung Kim)

   - Merge al->filtered with hist_entry->filtered in report/hists
     (Namhyung Kim)

   - Fix memory leak when synthesizing thread records (Namhyung Kim)

   - Use ui__has_annotation() in 'report' (Namhyung Kim)

   - hists browser refactorings to reuse code accross UIs (Namhyung Kim)

   - Add support for the new DWARF unwinder library in elfutils (Jiri
     Olsa)

   - Fix build race in the generation of bison files (Jiri Olsa)

   - Further streamline the feature detection display, trimming it a bit
     to show just the libraries detected, using VF=1 gets a more verbose
     output, showing the less interesting feature checks as well (Jiri
     Olsa).

   - Check compatible symtab type before loading dso (Namhyung Kim)

   - Check return value of filename__read_debuglink() (Stephane Eranian)

   - Move some hashing and fs related code from tools/perf/util/ to
     tools/lib/ so that it can be used by more tools/ living utilities
     (Borislav Petkov)

   - Prepare DWARF unwinding code for using an elfutils alternative
     unwinding library (Jiri Olsa)

   - Fix DWARF unwind max_stack processing (Jiri Olsa)

   - Add dwarf unwind 'perf test' entry (Jiri Olsa)

   - 'perf probe' improvements including memory leak fixes, sharing the
     intlist class with other tools, uprobes/kprobes code sharing and
     use of ref_reloc_sym (Masami Hiramatsu)

   - Shorten sample symbol resolving by adding cpumode to struct
     addr_location (Arnaldo Carvalho de Melo)

   - Fix synthesizing mmaps for threads (Don Zickus)

   - Fix invalid output on event group stdio report (Namhyung Kim)

   - Fixup header alignment in 'perf sched latency' output (Ramkumar
     Ramachandra)

   - Fix off-by-one error in 'perf timechart record' argv handling
     (Ramkumar Ramachandra)

  Tooling, cleanups:

   - Remove unused thread__find_map function (Jiri Olsa)

   - Remove unused simple_strtoul() function (Ramkumar Ramachandra)

  Tooling, documentation updates:

   - Update function names in debug messages (Ramkumar Ramachandra)

   - Update some code references in design.txt (Ramkumar Ramachandra)

   - Clarify load-latency information in the 'perf mem' docs (Andi
     Kleen)

   - Clarify x86 register naming in 'perf probe' docs (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (96 commits)
  perf tools: Remove unused simple_strtoul() function
  perf tools: Update some code references in design.txt
  perf evsel: Update function names in debug messages
  perf tools: Remove thread__find_map function
  perf annotate: Print the evsel name in the stdio output
  perf report: Use ui__has_annotation()
  perf tools: Fix memory leak when synthesizing thread records
  perf tools: Use tid in mmap/mmap2 events to find maps
  perf report: Merge al->filtered with hist_entry->filtered
  perf symbols: Apply all filters to an addr_location
  perf symbols: Record the reason for filtering an address_location
  perf sched: Fixup header alignment in 'latency' output
  perf timechart: Fix off-by-one error in 'record' argv handling
  perf machine: Factor machine__find_thread to take tid argument
  perf tools: Speed up thread map generation
  perf kvm: introduce --list-cmds for use by scripts
  perf ui hists: Pass evsel to hpp->header/width functions explicitly
  perf symbols: Introduce thread__find_cpumode_addr_location
  perf session: Change header.misc dump from decimal to hex
  perf ui/tui: Reuse generic __hpp__fmt() code
  ...

arch/x86/include/asm/nmi.h

@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_NMI_H
 #define _ASM_X86_NMI_H
 
+#include <linux/irq_work.h>
 #include <linux/pm.h>
 #include <asm/irq.h>
 #include <asm/io.h>
@@ -38,6 +39,8 @@ typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
 struct nmiaction {
 	struct list_head	list;
 	nmi_handler_t		handler;
+	u64			max_duration;
+	struct irq_work		irq_work;
 	unsigned long		flags;
 	const char		*name;
 };

arch/x86/kernel/cpu/perf_event.c

@@ -892,7 +892,6 @@ static void x86_pmu_enable(struct pmu *pmu)
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
 		 *
 		 * step1: save events moving to new counters
-		 * step2: reprogram moved events into new counters
 		 */
 		for (i = 0; i < n_running; i++) {
 			event = cpuc->event_list[i];
@@ -918,6 +917,9 @@ static void x86_pmu_enable(struct pmu *pmu)
 			x86_pmu_stop(event, PERF_EF_UPDATE);
 		}
 
+		/*
+		 * step2: reprogram moved events into new counters
+		 */
 		for (i = 0; i < cpuc->n_events; i++) {
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
@@ -1043,7 +1045,7 @@ static int x86_pmu_add(struct perf_event *event, int flags)
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be performed
-	 * at commit time (->commit_txn) as a whole
+	 * at commit time (->commit_txn) as a whole.
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		goto done_collect;
@@ -1058,6 +1060,10 @@ static int x86_pmu_add(struct perf_event *event, int flags)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 done_collect:
+	/*
+	 * Commit the collect_events() state. See x86_pmu_del() and
+	 * x86_pmu_*_txn().
+	 */
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
@@ -1183,28 +1189,38 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	 * If we're called during a txn, we don't need to do anything.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
+	 *
+	 * XXX assumes any ->del() called during a TXN will only be on
+	 * an event added during that same TXN.
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		return;
 
+	/*
+	 * Not a TXN, therefore cleanup properly.
+	 */
 	x86_pmu_stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < cpuc->n_events; i++) {
-		if (event == cpuc->event_list[i]) {
+		if (event == cpuc->event_list[i])
+			break;
+	}
 
-			if (i >= cpuc->n_events - cpuc->n_added)
-				--cpuc->n_added;
+	if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */
+		return;
 
-			if (x86_pmu.put_event_constraints)
-				x86_pmu.put_event_constraints(cpuc, event);
+	/* If we have a newly added event; make sure to decrease n_added. */
+	if (i >= cpuc->n_events - cpuc->n_added)
+		--cpuc->n_added;
 
-			while (++i < cpuc->n_events)
-				cpuc->event_list[i-1] = cpuc->event_list[i];
+	if (x86_pmu.put_event_constraints)
+		x86_pmu.put_event_constraints(cpuc, event);
+
+	/* Delete the array entry. */
+	while (++i < cpuc->n_events)
+		cpuc->event_list[i-1] = cpuc->event_list[i];
+	--cpuc->n_events;
 
-			--cpuc->n_events;
-			break;
-		}
-	}
 	perf_event_update_userpage(event);
 }
 
@@ -1598,7 +1614,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
 	__this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
 	/*
-	 * Truncate the collected events.
+	 * Truncate collected array by the number of events added in this
+	 * transaction. See x86_pmu_add() and x86_pmu_*_txn().
 	 */
 	__this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
 	__this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
@@ -1609,6 +1626,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
  * Commit group events scheduling transaction
  * Perform the group schedulability test as a whole
  * Return 0 if success
+ *
+ * Does not cancel the transaction on failure; expects the caller to do this.
  */
 static int x86_pmu_commit_txn(struct pmu *pmu)
 {

arch/x86/kernel/cpu/perf_event.h

@@ -130,9 +130,11 @@ struct cpu_hw_events {
 	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
-	int			n_events;
-	int			n_added;
-	int			n_txn;
+	int			n_events; /* the # of events in the below arrays */
+	int			n_added;  /* the # last events in the below arrays;
+					     they've never been enabled yet */
+	int			n_txn;    /* the # last events in the below arrays;
+					     added in the current transaction */
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */