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: (184 commits)
  perf probe: Clean up probe_point_lazy_walker() return value
  tracing: Fix irqoff selftest expanding max buffer
  tracing: Align 4 byte ints together in struct tracer
  tracing: Export trace_set_clr_event()
  tracing: Explain about unstable clock on resume with ring buffer warning
  ftrace/graph: Trace function entry before updating index
  ftrace: Add .ref.text as one of the safe areas to trace
  tracing: Adjust conditional expression latency formatting.
  tracing: Fix event alignment: skb:kfree_skb
  tracing: Fix event alignment: mce:mce_record
  tracing: Fix event alignment: kvm:kvm_hv_hypercall
  tracing: Fix event alignment: module:module_request
  tracing: Fix event alignment: ftrace:context_switch and ftrace:wakeup
  tracing: Remove lock_depth from event entry
  perf header: Stop using 'self'
  perf session: Use evlist/evsel for managing perf.data attributes
  perf top: Don't let events to eat up whole header line
  perf top: Fix events overflow in top command
  ring-buffer: Remove unused #include <linux/trace_irq.h>
  tracing: Add an 'overwrite' trace_option.
  ...

Documentation/trace/ftrace-design.txt

@@ -247,6 +247,13 @@ You need very few things to get the syscalls tracing in an arch.
 - Support the TIF_SYSCALL_TRACEPOINT thread flags.
 - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
   in the ptrace syscalls tracing path.
+- If the system call table on this arch is more complicated than a simple array
+  of addresses of the system calls, implement an arch_syscall_addr to return
+  the address of a given system call.
+- If the symbol names of the system calls do not match the function names on
+  this arch, define ARCH_HAS_SYSCALL_MATCH_SYM_NAME in asm/ftrace.h and
+  implement arch_syscall_match_sym_name with the appropriate logic to return
+  true if the function name corresponds with the symbol name.
 - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
 
 

Documentation/trace/ftrace.txt

@@ -80,11 +80,11 @@ of ftrace. Here is a list of some of the key files:
 	tracers listed here can be configured by
 	echoing their name into current_tracer.
 
-  tracing_enabled:
+  tracing_on:
 
-	This sets or displays whether the current_tracer
-	is activated and tracing or not. Echo 0 into this
-	file to disable the tracer or 1 to enable it.
+	This sets or displays whether writing to the trace
+	ring buffer is enabled. Echo 0 into this file to disable
+	the tracer or 1 to enable it.
 
   trace:
 
@@ -202,10 +202,6 @@ Here is the list of current tracers that may be configured.
 	to draw a graph of function calls similar to C code
 	source.
 
-  "sched_switch"
-
-	Traces the context switches and wakeups between tasks.
-
   "irqsoff"
 
 	Traces the areas that disable interrupts and saves
@@ -273,39 +269,6 @@ format, the function name that was traced "path_put" and the
 parent function that called this function "path_walk". The
 timestamp is the time at which the function was entered.
 
-The sched_switch tracer also includes tracing of task wakeups
-and context switches.
-
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +  2916:115:S
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +    10:115:S
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:R ==>    10:115:R
-        events/1-10    [01]  1453.070013:     10:115:S ==>  2916:115:R
-     kondemand/1-2916  [01]  1453.070013:   2916:115:S ==>     7:115:R
-     ksoftirqd/1-7     [01]  1453.070013:      7:115:S ==>     0:140:R
-
-Wake ups are represented by a "+" and the context switches are
-shown as "==>".  The format is:
-
- Context switches:
-
-       Previous task              Next Task
-
-  <pid>:<prio>:<state>  ==>  <pid>:<prio>:<state>
-
- Wake ups:
-
-       Current task               Task waking up
-
-  <pid>:<prio>:<state>    +  <pid>:<prio>:<state>
-
-The prio is the internal kernel priority, which is the inverse
-of the priority that is usually displayed by user-space tools.
-Zero represents the highest priority (99). Prio 100 starts the
-"nice" priorities with 100 being equal to nice -20 and 139 being
-nice 19. The prio "140" is reserved for the idle task which is
-the lowest priority thread (pid 0).
-
-
 Latency trace format
 --------------------
 
@@ -491,78 +454,10 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
                    latencies, as described in "Latency
                    trace format".
 
-sched_switch
-------------
-
-This tracer simply records schedule switches. Here is an example
-of how to use it.
-
- # echo sched_switch > current_tracer
- # echo 1 > tracing_enabled
- # sleep 1
- # echo 0 > tracing_enabled
- # cat trace
-
-# tracer: sched_switch
-#
-#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
-#              | |      |          |         |
-            bash-3997  [01]   240.132281:   3997:120:R   +  4055:120:R
-            bash-3997  [01]   240.132284:   3997:120:R ==>  4055:120:R
-           sleep-4055  [01]   240.132371:   4055:120:S ==>  3997:120:R
-            bash-3997  [01]   240.132454:   3997:120:R   +  4055:120:S
-            bash-3997  [01]   240.132457:   3997:120:R ==>  4055:120:R
-           sleep-4055  [01]   240.132460:   4055:120:D ==>  3997:120:R
-            bash-3997  [01]   240.132463:   3997:120:R   +  4055:120:D
-            bash-3997  [01]   240.132465:   3997:120:R ==>  4055:120:R
-          <idle>-0     [00]   240.132589:      0:140:R   +     4:115:S
-          <idle>-0     [00]   240.132591:      0:140:R ==>     4:115:R
-     ksoftirqd/0-4     [00]   240.132595:      4:115:S ==>     0:140:R
-          <idle>-0     [00]   240.132598:      0:140:R   +     4:115:S
-          <idle>-0     [00]   240.132599:      0:140:R ==>     4:115:R
-     ksoftirqd/0-4     [00]   240.132603:      4:115:S ==>     0:140:R
-           sleep-4055  [01]   240.133058:   4055:120:S ==>  3997:120:R
- [...]
-
-
-As we have discussed previously about this format, the header
-shows the name of the trace and points to the options. The
-"FUNCTION" is a misnomer since here it represents the wake ups
-and context switches.
-
-The sched_switch file only lists the wake ups (represented with
-'+') and context switches ('==>') with the previous task or
-current task first followed by the next task or task waking up.
-The format for both of these is PID:KERNEL-PRIO:TASK-STATE.
-Remember that the KERNEL-PRIO is the inverse of the actual
-priority with zero (0) being the highest priority and the nice
-values starting at 100 (nice -20). Below is a quick chart to map
-the kernel priority to user land priorities.
-
-   Kernel Space                     User Space
- ===============================================================
-   0(high) to  98(low)     user RT priority 99(high) to 1(low)
-                           with SCHED_RR or SCHED_FIFO
- ---------------------------------------------------------------
-  99                       sched_priority is not used in scheduling
-                           decisions(it must be specified as 0)
- ---------------------------------------------------------------
- 100(high) to 139(low)     user nice -20(high) to 19(low)
- ---------------------------------------------------------------
- 140                       idle task priority
- ---------------------------------------------------------------
-
-The task states are:
-
- R - running : wants to run, may not actually be running
- S - sleep   : process is waiting to be woken up (handles signals)
- D - disk sleep (uninterruptible sleep) : process must be woken up
-					(ignores signals)
- T - stopped : process suspended
- t - traced  : process is being traced (with something like gdb)
- Z - zombie  : process waiting to be cleaned up
- X - unknown
-
+  overwrite - This controls what happens when the trace buffer is
+              full. If "1" (default), the oldest events are
+              discarded and overwritten. If "0", then the newest
+              events are discarded.
 
 ftrace_enabled
 --------------
@@ -607,10 +502,10 @@ an example:
  # echo irqsoff > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # ls -ltr
  [...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: irqsoff
 #
@@ -715,10 +610,10 @@ is much like the irqsoff tracer.
  # echo preemptoff > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # ls -ltr
  [...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: preemptoff
 #
@@ -863,10 +758,10 @@ tracers.
  # echo preemptirqsoff > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # ls -ltr
  [...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: preemptirqsoff
 #
@@ -1026,9 +921,9 @@ Instead of performing an 'ls', we will run 'sleep 1' under
  # echo wakeup > current_tracer
  # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # chrt -f 5 sleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: wakeup
 #
@@ -1140,9 +1035,9 @@ ftrace_enabled is set; otherwise this tracer is a nop.
 
  # sysctl kernel.ftrace_enabled=1
  # echo function > current_tracer
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: function
 #
@@ -1180,7 +1075,7 @@ int trace_fd;
 [...]
 int main(int argc, char *argv[]) {
 	[...]
-	trace_fd = open(tracing_file("tracing_enabled"), O_WRONLY);
+	trace_fd = open(tracing_file("tracing_on"), O_WRONLY);
 	[...]
 	if (condition_hit()) {
 		write(trace_fd, "0", 1);
@@ -1631,9 +1526,9 @@ If I am only interested in sys_nanosleep and hrtimer_interrupt:
  # echo sys_nanosleep hrtimer_interrupt \
 		> set_ftrace_filter
  # echo function > current_tracer
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: ftrace
 #
@@ -1879,9 +1774,9 @@ different. The trace is live.
  # echo function > current_tracer
  # cat trace_pipe > /tmp/trace.out &
 [1] 4153
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
  # usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
  # cat trace
 # tracer: function
 #

Documentation/trace/kprobetrace.txt

@@ -42,11 +42,25 @@ Synopsis of kprobe_events
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
-		  (u8/u16/u32/u64/s8/s16/s32/s64) and string are supported.
+		  (u8/u16/u32/u64/s8/s16/s32/s64), "string" and bitfield
+		  are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.
 
+Types
+-----
+Several types are supported for fetch-args. Kprobe tracer will access memory
+by given type. Prefix 's' and 'u' means those types are signed and unsigned
+respectively. Traced arguments are shown in decimal (signed) or hex (unsigned).
+String type is a special type, which fetches a "null-terminated" string from
+kernel space. This means it will fail and store NULL if the string container
+has been paged out.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-
+offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
 
 Per-Probe Event Filtering
 -------------------------

arch/x86/ia32/ia32entry.S

@@ -25,6 +25,8 @@
 #define sysretl_audit ia32_ret_from_sys_call
 #endif
 
+	.section .entry.text, "ax"
+
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
 
 	.macro IA32_ARG_FIXUP noebp=0

arch/x86/include/asm/cpufeature.h

@@ -160,6 +160,7 @@
 #define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 #define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -279,6 +280,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
+#define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1

arch/x86/include/asm/kdebug.h

@@ -13,7 +13,6 @@ enum die_val {
 	DIE_PANIC,
 	DIE_NMI,
 	DIE_DIE,
-	DIE_NMIWATCHDOG,
 	DIE_KERNELDEBUG,
 	DIE_TRAP,
 	DIE_GPF,

arch/x86/include/asm/msr-index.h

@@ -52,6 +52,9 @@
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
 
+#define MSR_OFFCORE_RSP_0		0x000001a6
+#define MSR_OFFCORE_RSP_1		0x000001a7
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345

arch/x86/include/asm/nmi.h

@@ -7,7 +7,6 @@
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);

arch/x86/include/asm/smp.h

@@ -17,10 +17,20 @@
 #endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
+#include <asm/cpufeature.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
+static inline bool cpu_has_ht_siblings(void)
+{
+	bool has_siblings = false;
+#ifdef CONFIG_SMP
+	has_siblings = cpu_has_ht && smp_num_siblings > 1;
+#endif
+	return has_siblings;
+}
+
 DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);