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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (121 commits)
  perf symbols: Increase symbol KSYM_NAME_LEN size
  perf hists browser: Refuse 'a' hotkey on non symbolic views
  perf ui browser: Use libslang to read keys
  perf tools: Fix tracing info recording
  perf hists browser: Elide DSO column when it is set to just one DSO, ditto for threads
  perf hists: Don't consider filtered entries when calculating column widths
  perf hists: Don't decay total_period for filtered entries
  perf hists browser: Honour symbol_conf.show_{nr_samples,total_period}
  perf hists browser: Do not exit on tab key with single event
  perf annotate browser: Don't change selection line when returning from callq
  perf tools: handle endianness of feature bitmap
  perf tools: Add prelink suggestion to dso update message
  perf script: Fix unknown feature comment
  perf hists browser: Apply the dso and thread filters when merging new batches
  perf hists: Move the dso and thread filters from hist_browser
  perf ui browser: Honour the xterm colors
  perf top tui: Give color hints just on the percentage, like on --stdio
  perf ui browser: Make the colors configurable and change the defaults
  perf tui: Remove unneeded call to newtCls on startup
  perf hists: Don't format the percentage on hist_entry__snprintf
  ...

Fix up conflicts in arch/x86/kernel/kprobes.c manually.

Ingo's tree did the insane "add volatile to const array", which just
doesn't make sense ("volatile const"?).  But we could remove the const
*and* make the array volatile to make doubly sure that gcc doesn't
optimize it away..

Also fix up kernel/trace/ring_buffer.c non-data-conflicts manually: the
reader_lock has been turned into a raw lock by the core locking merge,
and there was a new user of it introduced in this perf core merge.  Make
sure that new use also uses the raw accessor functions.

3 files changed, 71 insertions, 23 deletions

diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 4886a68f267e..fd3f9f18cf3f 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -22,27 +22,26 @@ void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 
-/*
- * Define some priorities for the nmi notifier call chain.
- *
- * Create a local nmi bit that has a higher priority than
- * external nmis, because the local ones are more frequent.
- *
- * Also setup some default high/normal/low settings for
- * subsystems to registers with.  Using 4 bits to separate
- * the priorities.  This can go a lot higher if needed be.
- */
-
-#define NMI_LOCAL_SHIFT         16      /* randomly picked */
-#define NMI_LOCAL_BIT           (1ULL << NMI_LOCAL_SHIFT)
-#define NMI_HIGH_PRIOR          (1ULL << 8)
-#define NMI_NORMAL_PRIOR        (1ULL << 4)
-#define NMI_LOW_PRIOR           (1ULL << 0)
-#define NMI_LOCAL_HIGH_PRIOR    (NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
-#define NMI_LOCAL_NORMAL_PRIOR  (NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
-#define NMI_LOCAL_LOW_PRIOR     (NMI_LOCAL_BIT | NMI_LOW_PRIOR)
+#define NMI_FLAG_FIRST  1
+
+enum {
+        NMI_LOCAL=0,
+        NMI_UNKNOWN,
+        NMI_MAX
+};
+
+#define NMI_DONE        0
+#define NMI_HANDLED     1
+
+typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
+
+int register_nmi_handler(unsigned int, nmi_handler_t, unsigned long,
+                         const char *);
+
+void unregister_nmi_handler(unsigned int, const char *);
 
 void stop_nmi(void);
 void restart_nmi(void);
+void local_touch_nmi(void);
 
 #endif /* _ASM_X86_NMI_H */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 094fb30817ab..f61c62f7d5d8 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,6 +29,9 @@
 #define ARCH_PERFMON_EVENTSEL_INV                       (1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK                     0xFF000000ULL
 
+#define AMD_PERFMON_EVENTSEL_GUESTONLY                  (1ULL << 40)
+#define AMD_PERFMON_EVENTSEL_HOSTONLY                   (1ULL << 41)
+
 #define AMD64_EVENTSEL_EVENT    \
         (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
 #define INTEL_ARCH_EVENT_MASK   \
@@ -43,14 +46,17 @@
 #define AMD64_RAW_EVENT_MASK            \
         (X86_RAW_EVENT_MASK          |  \
          AMD64_EVENTSEL_EVENT)
+#define AMD64_NUM_COUNTERS                              4
+#define AMD64_NUM_COUNTERS_F15H                         6
+#define AMD64_NUM_COUNTERS_MAX                          AMD64_NUM_COUNTERS_F15H
 
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL                 0x3c
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL           0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK         (0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX                  0
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX         0
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
                 (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
 
-#define ARCH_PERFMON_BRANCH_MISSES_RETIRED                       6
+#define ARCH_PERFMON_BRANCH_MISSES_RETIRED              6
 
 /*
  * Intel "Architectural Performance Monitoring" CPUID
@@ -110,6 +116,35 @@ union cpuid10_edx {
  */
 #define X86_PMC_IDX_FIXED_BTS                           (X86_PMC_IDX_FIXED + 16)
 
+/*
+ * IBS cpuid feature detection
+ */
+
+#define IBS_CPUID_FEATURES              0x8000001b
+
+/*
+ * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
+ * bit 0 is used to indicate the existence of IBS.
+ */
+#define IBS_CAPS_AVAIL                  (1U<<0)
+#define IBS_CAPS_FETCHSAM               (1U<<1)
+#define IBS_CAPS_OPSAM                  (1U<<2)
+#define IBS_CAPS_RDWROPCNT              (1U<<3)
+#define IBS_CAPS_OPCNT                  (1U<<4)
+#define IBS_CAPS_BRNTRGT                (1U<<5)
+#define IBS_CAPS_OPCNTEXT               (1U<<6)
+
+#define IBS_CAPS_DEFAULT                (IBS_CAPS_AVAIL         \
+                                         | IBS_CAPS_FETCHSAM    \
+                                         | IBS_CAPS_OPSAM)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL                          0x1cc
+#define IBSCTL_LVT_OFFSET_VALID         (1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK          0x0F
+
 /* IbsFetchCtl bits/masks */
 #define IBS_FETCH_RAND_EN       (1ULL<<57)
 #define IBS_FETCH_VAL           (1ULL<<49)
@@ -124,6 +159,8 @@ union cpuid10_edx {
 #define IBS_OP_MAX_CNT          0x0000FFFFULL
 #define IBS_OP_MAX_CNT_EXT      0x007FFFFFULL   /* not a register bit mask */
 
+extern u32 get_ibs_caps(void);
+
 #ifdef CONFIG_PERF_EVENTS
 extern void perf_events_lapic_init(void);
 
@@ -159,7 +196,19 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
         );                                                      \
 }
 
+struct perf_guest_switch_msr {
+        unsigned msr;
+        u64 host, guest;
+};
+
+extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 #else
+static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+        *nr = 0;
+        return NULL;
+}
+
 static inline void perf_events_lapic_init(void) { }
 #endif
 
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 3250e3d605d9..92f297069e87 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -23,7 +23,7 @@ void machine_real_restart(unsigned int type);
 #define MRR_BIOS        0
 #define MRR_APM         1
 
-typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
 
 #endif /* _ASM_X86_REBOOT_H */