Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (162 commits)
  tracing/kprobes: unregister_trace_probe needs to be called under mutex
  perf: expose event__process function
  perf events: Fix mmap offset determination
  perf, powerpc: fsl_emb: Restore setting perf_sample_data.period
  perf, powerpc: Convert the FSL driver to use local64_t
  perf tools: Don't keep unreferenced maps when unmaps are detected
  perf session: Invalidate last_match when removing threads from rb_tree
  perf session: Free the ref_reloc_sym memory at the right place
  x86,mmiotrace: Add support for tracing STOS instruction
  perf, sched migration: Librarize task states and event headers helpers
  perf, sched migration: Librarize the GUI class
  perf, sched migration: Make the GUI class client agnostic
  perf, sched migration: Make it vertically scrollable
  perf, sched migration: Parameterize cpu height and spacing
  perf, sched migration: Fix key bindings
  perf, sched migration: Ignore unhandled task states
  perf, sched migration: Handle ignored migrate out events
  perf: New migration tool overview
  tracing: Drop cpparg() macro
  perf: Use tracepoint_synchronize_unregister() to flush any pending tracepoint call
  ...

Fix up trivial conflicts in Makefile and drivers/cpufreq/cpufreq.c

6 files changed, 121 insertions, 50 deletions

diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 942255310e6a..528a11e8d3e3 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -20,10 +20,10 @@ struct arch_hw_breakpoint {
 #include <linux/list.h>
 
 /* Available HW breakpoint length encodings */
+#define X86_BREAKPOINT_LEN_X            0x00
 #define X86_BREAKPOINT_LEN_1            0x40
 #define X86_BREAKPOINT_LEN_2            0x44
 #define X86_BREAKPOINT_LEN_4            0x4c
-#define X86_BREAKPOINT_LEN_EXECUTE      0x40
 
 #ifdef CONFIG_X86_64
 #define X86_BREAKPOINT_LEN_8            0x48
diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/x86/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 93da9c3f3341..932f0f86b4b7 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu);
 
 extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
+#if !defined(CONFIG_LOCKUP_DETECTOR)
 extern int nmi_watchdog_enabled;
+#endif
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 254883d0c7e0..6e742cc4251b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -68,8 +68,9 @@ union cpuid10_eax {
 
 union cpuid10_edx {
         struct {
-                unsigned int num_counters_fixed:4;
-                unsigned int reserved:28;
+                unsigned int num_counters_fixed:5;
+                unsigned int bit_width_fixed:8;
+                unsigned int reserved:19;
         } split;
         unsigned int full;
 };
@@ -140,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)   perf_misc_flags(regs)
 
+#include <asm/stacktrace.h>
+
+/*
+ * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
+ * and the comment with PERF_EFLAGS_EXACT.
+ */
+#define perf_arch_fetch_caller_regs(regs, __ip)         {       \
+        (regs)->ip = (__ip);                                    \
+        (regs)->bp = caller_frame_pointer();                    \
+        (regs)->cs = __KERNEL_CS;                               \
+        regs->flags = 0;                                        \
+}
+
 #else
 static inline void init_hw_perf_events(void)            { }
 static inline void perf_events_lapic_init(void) { }
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 64a8ebff06fc..def500776b16 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -19,7 +19,6 @@
 #define ARCH_P4_RESERVED_ESCR   (2) /* IQ_ESCR(0,1) not always present */
 #define ARCH_P4_MAX_ESCR        (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
 #define ARCH_P4_MAX_CCCR        (18)
-#define ARCH_P4_MAX_COUNTER     (ARCH_P4_MAX_CCCR / 2)
 
 #define P4_ESCR_EVENT_MASK      0x7e000000U
 #define P4_ESCR_EVENT_SHIFT     25
@@ -71,10 +70,6 @@
 #define P4_CCCR_THRESHOLD(v)            ((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)                 ((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
-/* Custom bits in reerved CCCR area */
-#define P4_CCCR_CACHE_OPS_MASK          0x0000003fU
-
-
 /* Non HT mask */
 #define P4_CCCR_MASK                            \
         (P4_CCCR_OVF                    |       \
@@ -106,8 +101,7 @@
  * ESCR and CCCR but rather an only packed value should
  * be unpacked and written to a proper addresses
  *
- * the base idea is to pack as much info as
- * possible
+ * the base idea is to pack as much info as possible
  */
 #define p4_config_pack_escr(v)          (((u64)(v)) << 32)
 #define p4_config_pack_cccr(v)          (((u64)(v)) & 0xffffffffULL)
@@ -130,8 +124,6 @@
                 t;                                      \
         })
 
-#define p4_config_unpack_cache_event(v) (((u64)(v)) & P4_CCCR_CACHE_OPS_MASK)
-
 #define P4_CONFIG_HT_SHIFT              63
 #define P4_CONFIG_HT                    (1ULL << P4_CONFIG_HT_SHIFT)
 
@@ -214,6 +206,12 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr)
         return escr;
 }
 
+/*
+ * This are the events which should be used in "Event Select"
+ * field of ESCR register, they are like unique keys which allow
+ * the kernel to determinate which CCCR and COUNTER should be
+ * used to track an event
+ */
 enum P4_EVENTS {
         P4_EVENT_TC_DELIVER_MODE,
         P4_EVENT_BPU_FETCH_REQUEST,
@@ -561,7 +559,7 @@ enum P4_EVENT_OPCODES {
  * a caller should use P4_ESCR_EMASK_NAME helper to
  * pick the EventMask needed, for example
  *
- *      P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD)
+ *      P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD)
  */
 enum P4_ESCR_EMASKS {
         P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0),
@@ -753,43 +751,50 @@ enum P4_ESCR_EMASKS {
         P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1),
 };
 
-/* P4 PEBS: stale for a while */
-#define P4_PEBS_METRIC_MASK     0x00001fffU
-#define P4_PEBS_UOB_TAG         0x01000000U
-#define P4_PEBS_ENABLE          0x02000000U
-
-/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */
-#define P4_PEBS__1stl_cache_load_miss_retired   0x3000001
-#define P4_PEBS__2ndl_cache_load_miss_retired   0x3000002
-#define P4_PEBS__dtlb_load_miss_retired         0x3000004
-#define P4_PEBS__dtlb_store_miss_retired        0x3000004
-#define P4_PEBS__dtlb_all_miss_retired          0x3000004
-#define P4_PEBS__tagged_mispred_branch          0x3018000
-#define P4_PEBS__mob_load_replay_retired        0x3000200
-#define P4_PEBS__split_load_retired             0x3000400
-#define P4_PEBS__split_store_retired            0x3000400
-
-#define P4_VERT__1stl_cache_load_miss_retired   0x0000001
-#define P4_VERT__2ndl_cache_load_miss_retired   0x0000001
-#define P4_VERT__dtlb_load_miss_retired         0x0000001
-#define P4_VERT__dtlb_store_miss_retired        0x0000002
-#define P4_VERT__dtlb_all_miss_retired          0x0000003
-#define P4_VERT__tagged_mispred_branch          0x0000010
-#define P4_VERT__mob_load_replay_retired        0x0000001
-#define P4_VERT__split_load_retired             0x0000001
-#define P4_VERT__split_store_retired            0x0000002
-
-enum P4_CACHE_EVENTS {
-        P4_CACHE__NONE,
-
-        P4_CACHE__1stl_cache_load_miss_retired,
-        P4_CACHE__2ndl_cache_load_miss_retired,
-        P4_CACHE__dtlb_load_miss_retired,
-        P4_CACHE__dtlb_store_miss_retired,
-        P4_CACHE__itlb_reference_hit,
-        P4_CACHE__itlb_reference_miss,
-
-        P4_CACHE__MAX
+/*
+ * P4 PEBS specifics (Replay Event only)
+ *
+ * Format (bits):
+ *   0-6: metric from P4_PEBS_METRIC enum
+ *    7 : reserved
+ *    8 : reserved
+ * 9-11 : reserved
+ *
+ * Note we have UOP and PEBS bits reserved for now
+ * just in case if we will need them once
+ */
+#define P4_PEBS_CONFIG_ENABLE           (1 << 7)
+#define P4_PEBS_CONFIG_UOP_TAG          (1 << 8)
+#define P4_PEBS_CONFIG_METRIC_MASK      0x3f
+#define P4_PEBS_CONFIG_MASK             0xff
+
+/*
+ * mem: Only counters MSR_IQ_COUNTER4 (16) and
+ * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling
+ */
+#define P4_PEBS_ENABLE                  0x02000000U
+#define P4_PEBS_ENABLE_UOP_TAG          0x01000000U
+
+#define p4_config_unpack_metric(v)      (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK)
+#define p4_config_unpack_pebs(v)        (((u64)(v)) & P4_PEBS_CONFIG_MASK)
+
+#define p4_config_pebs_has(v, mask)     (p4_config_unpack_pebs(v) & (mask))
+
+enum P4_PEBS_METRIC {
+        P4_PEBS_METRIC__none,
+
+        P4_PEBS_METRIC__1stl_cache_load_miss_retired,
+        P4_PEBS_METRIC__2ndl_cache_load_miss_retired,
+        P4_PEBS_METRIC__dtlb_load_miss_retired,
+        P4_PEBS_METRIC__dtlb_store_miss_retired,
+        P4_PEBS_METRIC__dtlb_all_miss_retired,
+        P4_PEBS_METRIC__tagged_mispred_branch,
+        P4_PEBS_METRIC__mob_load_replay_retired,
+        P4_PEBS_METRIC__split_load_retired,
+        P4_PEBS_METRIC__split_store_retired,
+
+        P4_PEBS_METRIC__max
 };
 
 #endif /* PERF_EVENT_P4_H */
+
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 4dab78edbad9..2b16a2ad23dc 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -1,6 +1,13 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+
 #ifndef _ASM_X86_STACKTRACE_H
 #define _ASM_X86_STACKTRACE_H
 
+#include <linux/uaccess.h>
+
 extern int kstack_depth_to_print;
 
 struct thread_info;
@@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data);
 
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp, char *log_lvl);
+
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *sp, unsigned long bp, char *log_lvl);
+
+extern unsigned int code_bytes;
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+        struct stack_frame *next_frame;
+        unsigned long return_address;
+};
+
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
+static inline unsigned long caller_frame_pointer(void)
+{
+        struct stack_frame *frame;
+
+        get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+        frame = frame->next_frame;
+#endif
+
+        return (unsigned long)frame;
+}
+
 #endif /* _ASM_X86_STACKTRACE_H */