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

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

   - Consolidate the PMU interrupt-disabled code amongst architectures
     (Vince Weaver)

   - misc fixes

  Tooling changes (new features, user visible changes):

   - Add support for pagefault tracing in 'trace', please see multiple
     examples in the changeset messages (Stanislav Fomichev).

   - Add pagefault statistics in 'trace' (Stanislav Fomichev)

   - Add header for columns in 'top' and 'report' TUI browsers (Jiri
     Olsa)

   - Add pagefault statistics in 'trace' (Stanislav Fomichev)

   - Add IO mode into timechart command (Stanislav Fomichev)

   - Fallback to syscalls:* when raw_syscalls:* is not available in the
     perl and python perf scripts.  (Daniel Bristot de Oliveira)

   - Add --repeat global option to 'perf bench' to be used in benchmarks
     such as the existing 'futex' one, that was modified to use it
     instead of a local option.  (Davidlohr Bueso)

   - Fix fd -> pathname resolution in 'trace', be it using /proc or a
     vfs_getname probe point.  (Arnaldo Carvalho de Melo)

   - Add suggestion of how to set perf_event_paranoid sysctl, to help
     non-root users trying tools like 'trace' to get a working
     environment.  (Arnaldo Carvalho de Melo)

   - Updates from trace-cmd for traceevent plugin_kvm plus args cleanup
     (Steven Rostedt, Jan Kiszka)

   - Support S/390 in 'perf kvm stat' (Alexander Yarygin)

  Tooling infrastructure changes:

   - Allow reserving a row for header purposes in the hists browser
     (Arnaldo Carvalho de Melo)

   - Various fixes and prep work related to supporting Intel PT (Adrian
     Hunter)

   - Introduce multiple debug variables control (Jiri Olsa)

   - Add callchain and additional sample information for python scripts
     (Joseph Schuchart)

   - More prep work to support Intel PT: (Adrian Hunter)
     - Polishing 'script' BTS output
     - 'inject' can specify --kallsym
     - VDSO is per machine, not a global var
     - Expose data addr lookup functions previously private to 'script'
     - Large mmap fixes in events processing

   - Include standard stringify macros in power pc code (Sukadev
     Bhattiprolu)

  Tooling cleanups:

   - Convert open coded equivalents to asprintf() (Andy Shevchenko)

   - Remove needless reassignments in 'trace' (Arnaldo Carvalho de Melo)

   - Cache the is_exit syscall test in 'trace) (Arnaldo Carvalho de
     Melo)

   - No need to reimplement err() in 'perf bench sched-messaging', drop
     barf().  (Davidlohr Bueso).

   - Remove ev_name argument from perf_evsel__hists_browse, can be
     obtained from the other parameters.  (Jiri Olsa)

  Tooling fixes:

   - Fix memory leak in the 'sched-messaging' perf bench test.
     (Davidlohr Bueso)

   - The -o and -n 'perf bench mem' options are mutually exclusive, emit
     error when both are specified.  (Davidlohr Bueso)

   - Fix scrollbar refresh row index in the ui browser, problem exposed
     now that headers will be added and will be allowed to be switched
     on/off.  (Jiri Olsa)

   - Handle the num array type in python properly (Sebastian Andrzej
     Siewior)

   - Fix wrong condition for allocation failure (Jiri Olsa)

   - Adjust callchain based on DWARF debug info on powerpc (Sukadev
     Bhattiprolu)

   - Fix a risk for doing free on uninitialized pointer in traceevent
     lib (Rickard Strandqvist)

   - Update attr test with PERF_FLAG_FD_CLOEXEC flag (Jiri Olsa)

   - Enable close-on-exec flag on perf file descriptor (Yann Droneaud)

   - Fix build on gcc 4.4.7 (Arnaldo Carvalho de Melo)

   - Event ordering fixes (Jiri Olsa)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (123 commits)
  Revert "perf tools: Fix jump label always changing during tracing"
  perf tools: Fix perf usage string leftover
  perf: Check permission only for parent tracepoint event
  perf record: Store PERF_RECORD_FINISHED_ROUND only for nonempty rounds
  perf record: Always force PERF_RECORD_FINISHED_ROUND event
  perf inject: Add --kallsyms parameter
  perf tools: Expose 'addr' functions so they can be reused
  perf session: Fix accounting of ordered samples queue
  perf powerpc: Include util/util.h and remove stringify macros
  perf tools: Fix build on gcc 4.4.7
  perf tools: Add thread parameter to vdso__dso_findnew()
  perf tools: Add dso__type()
  perf tools: Separate the VDSO map name from the VDSO dso name
  perf tools: Add vdso__new()
  perf machine: Fix the lifetime of the VDSO temporary file
  perf tools: Group VDSO global variables into a structure
  perf session: Add ability to skip 4GiB or more
  perf session: Add ability to 'skip' a non-piped event stream
  perf tools: Pass machine to vdso__dso_findnew()
  perf tools: Add dso__data_size()
  ...

4 files changed, 102 insertions, 31 deletions

diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index 09409c4..3dec769 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -22,6 +22,7 @@ header-y += ipcbuf.h
 header-y += ist.h
 header-y += kvm.h
 header-y += kvm_para.h
+header-y += kvm_perf.h
 header-y += ldt.h
 header-y += mce.h
 header-y += mman.h
diff --git a/arch/x86/include/uapi/asm/kvm_perf.h b/arch/x86/include/uapi/asm/kvm_perf.h
new file mode 100644
index 0000000..3bb964f
--- /dev/null
+++ b/arch/x86/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_KVM_PERF_H
+#define _ASM_X86_KVM_PERF_H
+
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
+
+#define DECODE_STR_LEN 20
+
+#define VCPU_ID "vcpu_id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_entry"
+#define KVM_EXIT_TRACE "kvm:kvm_exit"
+#define KVM_EXIT_REASON "exit_reason"
+
+#endif /* _ASM_X86_KVM_PERF_H */
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 3bbdf4c..30790d7 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -294,31 +294,41 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
 			cpu_to_node(cpu));
 }
 
-static void amd_uncore_cpu_up_prepare(unsigned int cpu)
+static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 {
-	struct amd_uncore *uncore;
+	struct amd_uncore *uncore_nb = NULL, *uncore_l2;
 
 	if (amd_uncore_nb) {
-		uncore = amd_uncore_alloc(cpu);
-		uncore->cpu = cpu;
-		uncore->num_counters = NUM_COUNTERS_NB;
-		uncore->rdpmc_base = RDPMC_BASE_NB;
-		uncore->msr_base = MSR_F15H_NB_PERF_CTL;
-		uncore->active_mask = &amd_nb_active_mask;
-		uncore->pmu = &amd_nb_pmu;
-		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+		uncore_nb = amd_uncore_alloc(cpu);
+		if (!uncore_nb)
+			goto fail;
+		uncore_nb->cpu = cpu;
+		uncore_nb->num_counters = NUM_COUNTERS_NB;
+		uncore_nb->rdpmc_base = RDPMC_BASE_NB;
+		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
+		uncore_nb->active_mask = &amd_nb_active_mask;
+		uncore_nb->pmu = &amd_nb_pmu;
+		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
 	if (amd_uncore_l2) {
-		uncore = amd_uncore_alloc(cpu);
-		uncore->cpu = cpu;
-		uncore->num_counters = NUM_COUNTERS_L2;
-		uncore->rdpmc_base = RDPMC_BASE_L2;
-		uncore->msr_base = MSR_F16H_L2I_PERF_CTL;
-		uncore->active_mask = &amd_l2_active_mask;
-		uncore->pmu = &amd_l2_pmu;
-		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+		uncore_l2 = amd_uncore_alloc(cpu);
+		if (!uncore_l2)
+			goto fail;
+		uncore_l2->cpu = cpu;
+		uncore_l2->num_counters = NUM_COUNTERS_L2;
+		uncore_l2->rdpmc_base = RDPMC_BASE_L2;
+		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
+		uncore_l2->active_mask = &amd_l2_active_mask;
+		uncore_l2->pmu = &amd_l2_pmu;
+		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
 	}
+
+	return 0;
+
+fail:
+	kfree(uncore_nb);
+	return -ENOMEM;
 }
 
 static struct amd_uncore *
@@ -441,7 +451,7 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
 
 	if (!--uncore->refcnt)
 		kfree(uncore);
-	*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
+	*per_cpu_ptr(uncores, cpu) = NULL;
 }
 
 static void amd_uncore_cpu_dead(unsigned int cpu)
@@ -461,7 +471,8 @@ amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-		amd_uncore_cpu_up_prepare(cpu);
+		if (amd_uncore_cpu_up_prepare(cpu))
+			return notifier_from_errno(-ENOMEM);
 		break;
 
 	case CPU_STARTING:
@@ -501,20 +512,33 @@ static void __init init_cpu_already_online(void *dummy)
 	amd_uncore_cpu_online(cpu);
 }
 
+static void cleanup_cpu_online(void *dummy)
+{
+	unsigned int cpu = smp_processor_id();
+
+	amd_uncore_cpu_dead(cpu);
+}
+
 static int __init amd_uncore_init(void)
 {
-	unsigned int cpu;
+	unsigned int cpu, cpu2;
 	int ret = -ENODEV;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
-		return -ENODEV;
+		goto fail_nodev;
 
 	if (!cpu_has_topoext)
-		return -ENODEV;
+		goto fail_nodev;
 
 	if (cpu_has_perfctr_nb) {
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
-		perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+		if (!amd_uncore_nb) {
+			ret = -ENOMEM;
+			goto fail_nb;
+		}
+		ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+		if (ret)
+			goto fail_nb;
 
 		printk(KERN_INFO "perf: AMD NB counters detected\n");
 		ret = 0;
@@ -522,20 +546,28 @@ static int __init amd_uncore_init(void)
 
 	if (cpu_has_perfctr_l2) {
 		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
-		perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		if (!amd_uncore_l2) {
+			ret = -ENOMEM;
+			goto fail_l2;
+		}
+		ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		if (ret)
+			goto fail_l2;
 
 		printk(KERN_INFO "perf: AMD L2I counters detected\n");
 		ret = 0;
 	}
 
 	if (ret)
-		return -ENODEV;
+		goto fail_nodev;
 
 	cpu_notifier_register_begin();
 
 	/* init cpus already online before registering for hotplug notifier */
 	for_each_online_cpu(cpu) {
-		amd_uncore_cpu_up_prepare(cpu);
+		ret = amd_uncore_cpu_up_prepare(cpu);
+		if (ret)
+			goto fail_online;
 		smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
 	}
 
@@ -543,5 +575,30 @@ static int __init amd_uncore_init(void)
 	cpu_notifier_register_done();
 
 	return 0;
+
+
+fail_online:
+	for_each_online_cpu(cpu2) {
+		if (cpu2 == cpu)
+			break;
+		smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1);
+	}
+	cpu_notifier_register_done();
+
+	/* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
+	amd_uncore_nb = amd_uncore_l2 = NULL;
+	if (cpu_has_perfctr_l2)
+		perf_pmu_unregister(&amd_l2_pmu);
+fail_l2:
+	if (cpu_has_perfctr_nb)
+		perf_pmu_unregister(&amd_nb_pmu);
+	if (amd_uncore_l2)
+		free_percpu(amd_uncore_l2);
+fail_nb:
+	if (amd_uncore_nb)
+		free_percpu(amd_uncore_nb);
+
+fail_nodev:
+	return ret;
 }
 device_initcall(amd_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index ae6552a..cfc6f9d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2947,10 +2947,7 @@ again:
 		 * extra registers. If we failed to take an extra
 		 * register, try the alternative.
 		 */
-		if (idx % 2)
-			idx--;
-		else
-			idx++;
+		idx ^= 1;
 		if (idx != reg1->idx % 6) {
 			if (idx == 2)
 				config1 >>= 8;