tracing: Provide trace events interface for uprobes

Implements trace_event support for uprobes. In its current form
it can be used to put probes at a specified offset in a file and
dump the required registers when the code flow reaches the
probed address.

The following example shows how to dump the instruction pointer
and %ax a register at the probed text address.  Here we are
trying to probe zfree in /bin/zsh:

 # cd /sys/kernel/debug/tracing/
 # cat /proc/`pgrep  zsh`/maps | grep /bin/zsh | grep r-xp
 00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh
 # objdump -T /bin/zsh | grep -w zfree
 0000000000446420 g    DF .text  0000000000000012  Base
 zfree # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events
 # cat uprobe_events
 p:uprobes/p_zsh_0x46420 /bin/zsh:0x0000000000046420
 # echo 1 > events/uprobes/enable
 # sleep 20
 # echo 0 > events/uprobes/enable
 # cat trace
 # tracer: nop
 #
 #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
 #              | |       |          |         |
              zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
              zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
              zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
              zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Jim Keniston <jkenisto@linux.vnet.ibm.com>
Cc: Linux-mm <linux-mm@kvack.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Anton Arapov <anton@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20120411103043.GB29437@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 919 insertions, 7 deletions

diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
new file mode 100644
index 000000000000..eae40a003eec
--- /dev/null
+++ b/Documentation/trace/uprobetracer.txt
@@ -0,0 +1,95 @@
+                Uprobe-tracer: Uprobe-based Event Tracing
+                =========================================
+                 Documentation written by Srikar Dronamraju
+
+Overview
+--------
+Uprobe based trace events are similar to kprobe based trace events.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
+
+Similar to the kprobe-event tracer, this doesn't need to be activated via
+current_tracer. Instead of that, add probe points via
+/sys/kernel/debug/tracing/uprobe_events, and enable it via
+/sys/kernel/debug/tracing/events/uprobes/<EVENT>/enabled.
+
+However unlike kprobe-event tracer, the uprobe event interface expects the
+user to calculate the offset of the probepoint in the object
+
+Synopsis of uprobe_tracer
+-------------------------
+  p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS]        : Set a probe
+
+ GRP            : Group name. If omitted, use "uprobes" for it.
+ EVENT          : Event name. If omitted, the event name is generated
+                  based on SYMBOL+offs.
+ PATH           : path to an executable or a library.
+ SYMBOL[+offs]  : Symbol+offset where the probe is inserted.
+
+ FETCHARGS      : Arguments. Each probe can have up to 128 args.
+  %REG          : Fetch register REG
+
+Event Profiling
+---------------
+ You can check the total number of probe hits and probe miss-hits via
+/sys/kernel/debug/tracing/uprobe_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 uprobe_events
+as below.
+
+  echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
+
+ This sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash
+
+  echo > /sys/kernel/debug/tracing/uprobe_events
+
+ This clears all probe points.
+
+The following example shows how to dump the instruction pointer and %ax
+a register at the probed text address.  Here we are trying to probe
+function zfree in /bin/zsh
+
+    # cd /sys/kernel/debug/tracing/
+    # cat /proc/`pgrep  zsh`/maps | grep /bin/zsh | grep r-xp
+    00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh
+    # objdump -T /bin/zsh | grep -w zfree
+    0000000000446420 g    DF .text  0000000000000012  Base        zfree
+
+0x46420 is the offset of zfree in object /bin/zsh that is loaded at
+0x00400000. Hence the command to probe would be :
+
+    # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events
+
+Please note: User has to explicitly calculate the offset of the probepoint
+in the object. We can see the events that are registered by looking at the
+uprobe_events file.
+
+    # cat uprobe_events
+    p:uprobes/p_zsh_0x46420 /bin/zsh:0x0000000000046420
+
+Right after definition, each event is disabled by default. For tracing these
+events, you need to enable it by:
+
+    # echo 1 > events/uprobes/enable
+
+Lets disable the event after sleeping for some time.
+    # sleep 20
+    # echo 0 > events/uprobes/enable
+
+And you can see the traced information via /sys/kernel/debug/tracing/trace.
+
+    # cat trace
+    # tracer: nop
+    #
+    #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
+    #              | |       |          |         |
+                 zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+                 zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+                 zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+                 zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+
+Each line shows us probes were triggered for a pid 24842 with ip being
+0x446421 and contents of ax register being 79.
diff --git a/arch/Kconfig b/arch/Kconfig
index e5d3778d5554..0f8f968015e2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -78,7 +78,7 @@ config OPTPROBES
 
 config UPROBES
         bool "Transparent user-space probes (EXPERIMENTAL)"
-        depends on ARCH_SUPPORTS_UPROBES && PERF_EVENTS
+        depends on UPROBE_EVENTS && PERF_EVENTS
         default n
         help
           Uprobes is the user-space counterpart to kprobes: they
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index ce5a5c54ac8f..ea4bff6295fc 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -386,6 +386,22 @@ config KPROBE_EVENT
           This option is also required by perf-probe subcommand of perf tools.
           If you want to use perf tools, this option is strongly recommended.
 
+config UPROBE_EVENT
+        bool "Enable uprobes-based dynamic events"
+        depends on ARCH_SUPPORTS_UPROBES
+        depends on MMU
+        select UPROBES
+        select PROBE_EVENTS
+        select TRACING
+        default n
+        help
+          This allows the user to add tracing events on top of userspace
+          dynamic events (similar to tracepoints) on the fly via the trace
+          events interface. Those events can be inserted wherever uprobes
+          can probe, and record various registers.
+          This option is required if you plan to use perf-probe subcommand
+          of perf tools on user space applications.
+
 config PROBE_EVENTS
         def_bool n
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index fa10d5ca5ab1..1734c03e048b 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -62,5 +62,6 @@ ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
+obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 95059f091a24..1bcdbec95a11 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -103,6 +103,11 @@ struct kretprobe_trace_entry_head {
         unsigned long           ret_ip;
 };
 
+struct uprobe_trace_entry_head {
+        struct trace_entry      ent;
+        unsigned long           ip;
+};
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f8b777367d8e..b31d3d5699fe 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -525,7 +525,7 @@ static int create_trace_probe(int argc, char **argv)
 
                 /* Parse fetch argument */
                 ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i],
-                                                                is_return);
+                                                is_return, true);
                 if (ret) {