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

…nux/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: (470 commits)
  x86: Fix comments of register/stack access functions
  perf tools: Replace %m with %a in sscanf
  hw-breakpoints: Keep track of user disabled breakpoints
  tracing/syscalls: Make syscall events print callbacks static
  tracing: Add DEFINE_EVENT(), DEFINE_SINGLE_EVENT() support to docbook
  perf: Don't free perf_mmap_data until work has been done
  perf_event: Fix compile error
  perf tools: Fix _GNU_SOURCE macro related strndup() build error
  trace_syscalls: Remove unused syscall_name_to_nr()
  trace_syscalls: Simplify syscall profile
  trace_syscalls: Remove duplicate init_enter_##sname()
  trace_syscalls: Add syscall_nr field to struct syscall_metadata
  trace_syscalls: Remove enter_id exit_id
  trace_syscalls: Set event_enter_##sname->data to its metadata
  trace_syscalls: Remove unused event_syscall_enter and event_syscall_exit
  perf_event: Initialize data.period in perf_swevent_hrtimer()
  perf probe: Simplify event naming
  perf probe: Add --list option for listing current probe events
  perf probe: Add argv_split() from lib/argv_split.c
  perf probe: Move probe event utility functions to probe-event.c
  ...

Documentation/DocBook/tracepoint.tmpl

@@ -86,4 +86,9 @@
 !Iinclude/trace/events/irq.h
   </chapter>
 
+  <chapter id="signal">
+   <title>SIGNAL</title>
+!Iinclude/trace/events/signal.h
+  </chapter>
+
 </book>

Documentation/trace/kprobetrace.txt

@@ -0,0 +1,149 @@
+                        Kprobe-based Event Tracing
+                        ==========================
+
+                 Documentation is written by Masami Hiramatsu
+
+
+Overview
+--------
+These events are similar to tracepoint based events. Instead of Tracepoint,
+this is based on kprobes (kprobe and kretprobe). So it can probe wherever
+kprobes can probe (this means, all functions body except for __kprobes
+functions). Unlike the Tracepoint based event, this can be added and removed
+dynamically, on the fly.
+
+To enable this feature, build your kernel with CONFIG_KPROBE_TRACING=y.
+
+Similar to the events tracer, this doesn't need to be activated via
+current_tracer. Instead of that, add probe points via
+/sys/kernel/debug/tracing/kprobe_events, and enable it via
+/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enabled.
+
+
+Synopsis of kprobe_events
+-------------------------
+  p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]	: Set a probe
+  r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]		: Set a return probe
+
+ GRP		: Group name. If omitted, use "kprobes" for it.
+ EVENT		: Event name. If omitted, the event name is generated
+		  based on SYMBOL+offs or MEMADDR.
+ SYMBOL[+offs]	: Symbol+offset where the probe is inserted.
+ MEMADDR	: Address where the probe is inserted.
+
+ FETCHARGS	: Arguments. Each probe can have up to 128 args.
+  %REG		: Fetch register REG
+  @ADDR		: Fetch memory at ADDR (ADDR should be in kernel)
+  @SYM[+|-offs]	: Fetch memory at SYM +|- offs (SYM should be a data symbol)
+  $stackN	: Fetch Nth entry of stack (N >= 0)
+  $stack	: Fetch stack address.
+  $argN		: Fetch function argument. (N >= 0)(*)
+  $retval	: Fetch return value.(**)
+  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(***)
+  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+
+  (*) aN may not correct on asmlinkaged functions and at the middle of
+      function body.
+  (**) only for return probe.
+  (***) this is useful for fetching a field of data structures.
+
+
+Per-Probe Event Filtering
+-------------------------
+ Per-probe event filtering feature allows you to set different filter on each
+probe and gives you what arguments will be shown in trace buffer. If an event
+name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
+under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
+'enabled', 'format' and 'filter'.
+
+enabled:
+  You can enable/disable the probe by writing 1 or 0 on it.
+
+format:
+  This shows the format of this probe event.
+
+filter:
+  You can write filtering rules of this event.
+
+id:
+  This shows the id of this probe event.
+
+
+Event Profiling
+---------------
+ You can check the total number of probe hits and probe miss-hits via
+/sys/kernel/debug/tracing/kprobe_profile.
+ The first column is event name, the second is the number of probe hits,
+the third is the number of probe miss-hits.
+
+
+Usage examples
+--------------
+To add a probe as a new event, write a new definition to kprobe_events
+as below.
+
+  echo p:myprobe do_sys_open dfd=$arg0 filename=$arg1 flags=$arg2 mode=$arg3 > /sys/kernel/debug/tracing/kprobe_events
+
+ This sets a kprobe on the top of do_sys_open() function with recording
+1st to 4th arguments as "myprobe" event. As this example shows, users can
+choose more familiar names for each arguments.
+
+  echo r:myretprobe do_sys_open $retval >> /sys/kernel/debug/tracing/kprobe_events
+
+ This sets a kretprobe on the return point of do_sys_open() function with
+recording return value as "myretprobe" event.
+ You can see the format of these events via
+/sys/kernel/debug/tracing/events/kprobes/<EVENT>/format.
+
+  cat /sys/kernel/debug/tracing/events/kprobes/myprobe/format
+name: myprobe
+ID: 75
+format:
+	field:unsigned short common_type;	offset:0;	size:2;
+	field:unsigned char common_flags;	offset:2;	size:1;
+	field:unsigned char common_preempt_count;	offset:3;	size:1;
+	field:int common_pid;	offset:4;	size:4;
+	field:int common_tgid;	offset:8;	size:4;
+
+	field: unsigned long ip;	offset:16;tsize:8;
+	field: int nargs;	offset:24;tsize:4;
+	field: unsigned long dfd;	offset:32;tsize:8;
+	field: unsigned long filename;	offset:40;tsize:8;
+	field: unsigned long flags;	offset:48;tsize:8;
+	field: unsigned long mode;	offset:56;tsize:8;
+
+print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, REC->filename, REC->flags, REC->mode
+
+
+ You can see that the event has 4 arguments as in the expressions you specified.
+
+  echo > /sys/kernel/debug/tracing/kprobe_events
+
+ This clears all probe points.
+
+ Right after definition, each event is disabled by default. For tracing these
+events, you need to enable it.
+
+  echo 1 > /sys/kernel/debug/tracing/events/kprobes/myprobe/enable
+  echo 1 > /sys/kernel/debug/tracing/events/kprobes/myretprobe/enable
+
+ And you can see the traced information via /sys/kernel/debug/tracing/trace.
+
+  cat /sys/kernel/debug/tracing/trace
+# tracer: nop
+#
+#           TASK-PID    CPU#    TIMESTAMP  FUNCTION
+#              | |       |          |         |
+           <...>-1447  [001] 1038282.286875: myprobe: (do_sys_open+0x0/0xd6) dfd=3 filename=7fffd1ec4440 flags=8000 mode=0
+           <...>-1447  [001] 1038282.286878: myretprobe: (sys_openat+0xc/0xe <- do_sys_open) $retval=fffffffffffffffe
+           <...>-1447  [001] 1038282.286885: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=40413c flags=8000 mode=1b6
+           <...>-1447  [001] 1038282.286915: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
+           <...>-1447  [001] 1038282.286969: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=4041c6 flags=98800 mode=10
+           <...>-1447  [001] 1038282.286976: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
+
+
+ Each line shows when the kernel hits an event, and <- SYMBOL means kernel
+returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
+returns from do_sys_open to sys_open+0x1b).
+
+

arch/Kconfig

@@ -126,4 +126,11 @@ config HAVE_DMA_API_DEBUG
 config HAVE_DEFAULT_NO_SPIN_MUTEXES
 	bool
 
+config HAVE_HW_BREAKPOINT
+	bool
+	depends on HAVE_PERF_EVENTS
+	select ANON_INODES
+	select PERF_EVENTS
+
+
 source "kernel/gcov/Kconfig"

arch/powerpc/Kconfig.debug

@@ -46,7 +46,7 @@ config DEBUG_STACK_USAGE
 
 config HCALL_STATS
 	bool "Hypervisor call instrumentation"
-	depends on PPC_PSERIES && DEBUG_FS
+	depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS
 	help
 	  Adds code to keep track of the number of hypervisor calls made and
 	  the amount of time spent in hypervisor calls.  Wall time spent in

arch/powerpc/configs/pseries_defconfig

@@ -1683,7 +1683,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 # CONFIG_DEBUG_STACK_USAGE is not set
 # CONFIG_DEBUG_PAGEALLOC is not set
-CONFIG_HCALL_STATS=y
+# CONFIG_HCALL_STATS is not set
 # CONFIG_CODE_PATCHING_SELFTEST is not set
 # CONFIG_FTR_FIXUP_SELFTEST is not set
 # CONFIG_MSI_BITMAP_SELFTEST is not set

arch/powerpc/include/asm/emulated_ops.h

@@ -19,6 +19,7 @@
 #define _ASM_POWERPC_EMULATED_OPS_H
 
 #include <asm/atomic.h>
+#include <linux/perf_event.h>
 
 
 #ifdef CONFIG_PPC_EMULATED_STATS
@@ -57,7 +58,7 @@ extern u32 ppc_warn_emulated;
 
 extern void ppc_warn_emulated_print(const char *type);
 
-#define PPC_WARN_EMULATED(type)						 \
+#define __PPC_WARN_EMULATED(type)					 \
 	do {								 \
 		atomic_inc(&ppc_emulated.type.val);			 \
 		if (ppc_warn_emulated)					 \
@@ -66,8 +67,22 @@ extern void ppc_warn_emulated_print(const char *type);
 
 #else /* !CONFIG_PPC_EMULATED_STATS */
 
-#define PPC_WARN_EMULATED(type)	do { } while (0)
+#define __PPC_WARN_EMULATED(type)	do { } while (0)
 
 #endif /* !CONFIG_PPC_EMULATED_STATS */
 
+#define PPC_WARN_EMULATED(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,		\
+			1, 0, regs, 0);					\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
+#define PPC_WARN_ALIGNMENT(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,		\
+			1, 0, regs, regs->dar);				\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
 #endif /* _ASM_POWERPC_EMULATED_OPS_H */

arch/powerpc/include/asm/hvcall.h

@@ -274,6 +274,8 @@ struct hcall_stats {
 	unsigned long	num_calls;	/* number of calls (on this CPU) */
 	unsigned long	tb_total;	/* total wall time (mftb) of calls. */
 	unsigned long	purr_total;	/* total cpu time (PURR) of calls. */
+	unsigned long	tb_start;
+	unsigned long	purr_start;
 };
 #define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
 

arch/powerpc/include/asm/reg.h

@@ -489,6 +489,8 @@
 #define SPRN_MMCR1	798
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
+#define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
+#define   MMCRA_SDAR_ERAT_MISS   0x20000000UL
 #define   MMCRA_SIHV	0x10000000UL /* state of MSR HV when SIAR set */
 #define   MMCRA_SIPR	0x08000000UL /* state of MSR PR when SIAR set */
 #define   MMCRA_SLOT	0x07000000UL /* SLOT bits (37-39) */

arch/powerpc/include/asm/trace.h

@@ -0,0 +1,133 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM powerpc
+
+#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWERPC_H
+
+#include <linux/tracepoint.h>
+
+struct pt_regs;
+
+TRACE_EVENT(irq_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(irq_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+#ifdef CONFIG_PPC_PSERIES
+extern void hcall_tracepoint_regfunc(void);
+extern void hcall_tracepoint_unregfunc(void);
+
+TRACE_EVENT_FN(hcall_entry,
+
+	TP_PROTO(unsigned long opcode, unsigned long *args),
+
+	TP_ARGS(opcode, args),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+	),
+
+	TP_printk("opcode=%lu", __entry->opcode),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+
+TRACE_EVENT_FN(hcall_exit,
+
+	TP_PROTO(unsigned long opcode, unsigned long retval,
+		unsigned long *retbuf),
+
+	TP_ARGS(opcode, retval, retbuf),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+		__field(unsigned long, retval)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+		__entry->retval = retval;
+	),
+
+	TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+#endif
+
+#endif /* _TRACE_POWERPC_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH asm
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>