summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig572
-rw-r--r--kernel/trace/Makefile60
-rw-r--r--kernel/trace/blktrace.c1767
-rw-r--r--kernel/trace/ftrace.c3401
-rw-r--r--kernel/trace/kmemtrace.c511
-rw-r--r--kernel/trace/power-traces.c18
-rw-r--r--kernel/trace/ring_buffer.c3888
-rw-r--r--kernel/trace/ring_buffer_benchmark.c486
-rw-r--r--kernel/trace/trace.c4560
-rw-r--r--kernel/trace/trace.h801
-rw-r--r--kernel/trace/trace_boot.c185
-rw-r--r--kernel/trace/trace_branch.c392
-rw-r--r--kernel/trace/trace_clock.c115
-rw-r--r--kernel/trace/trace_entries.h382
-rw-r--r--kernel/trace/trace_event_profile.c122
-rw-r--r--kernel/trace/trace_events.c1546
-rw-r--r--kernel/trace/trace_events_filter.c1443
-rw-r--r--kernel/trace/trace_export.c230
-rw-r--r--kernel/trace/trace_functions.c403
-rw-r--r--kernel/trace/trace_functions_graph.c1173
-rw-r--r--kernel/trace/trace_hw_branches.c312
-rw-r--r--kernel/trace/trace_irqsoff.c484
-rw-r--r--kernel/trace/trace_kprobe.c1553
-rw-r--r--kernel/trace/trace_ksym.c519
-rw-r--r--kernel/trace/trace_mmiotrace.c373
-rw-r--r--kernel/trace/trace_nop.c101
-rw-r--r--kernel/trace/trace_output.c1280
-rw-r--r--kernel/trace/trace_output.h53
-rw-r--r--kernel/trace/trace_printk.c251
-rw-r--r--kernel/trace/trace_sched_switch.c298
-rw-r--r--kernel/trace/trace_sched_wakeup.c415
-rw-r--r--kernel/trace/trace_selftest.c865
-rw-r--r--kernel/trace/trace_selftest_dynamic.c7
-rw-r--r--kernel/trace/trace_stack.c374
-rw-r--r--kernel/trace/trace_stat.c387
-rw-r--r--kernel/trace/trace_stat.h33
-rw-r--r--kernel/trace/trace_syscalls.c631
-rw-r--r--kernel/trace/trace_sysprof.c329
-rw-r--r--kernel/trace/trace_workqueue.c295
39 files changed, 30615 insertions, 0 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
new file mode 100644
index 00000000000..60e2ce0181e
--- /dev/null
+++ b/kernel/trace/Kconfig
@@ -0,0 +1,572 @@
+#
+# Architectures that offer an FUNCTION_TRACER implementation should
+# select HAVE_FUNCTION_TRACER:
+#
+
+config USER_STACKTRACE_SUPPORT
+ bool
+
+config NOP_TRACER
+ bool
+
+config HAVE_FTRACE_NMI_ENTER
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_FUNCTION_TRACER
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_FUNCTION_GRAPH_TRACER
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_FUNCTION_GRAPH_FP_TEST
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_DYNAMIC_FTRACE
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_FTRACE_MCOUNT_RECORD
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config HAVE_HW_BRANCH_TRACER
+ bool
+
+config HAVE_SYSCALL_TRACEPOINTS
+ bool
+ help
+ See Documentation/trace/ftrace-design.txt
+
+config TRACER_MAX_TRACE
+ bool
+
+config RING_BUFFER
+ bool
+
+config FTRACE_NMI_ENTER
+ bool
+ depends on HAVE_FTRACE_NMI_ENTER
+ default y
+
+config EVENT_TRACING
+ select CONTEXT_SWITCH_TRACER
+ bool
+
+config CONTEXT_SWITCH_TRACER
+ bool
+
+config RING_BUFFER_ALLOW_SWAP
+ bool
+ help
+ Allow the use of ring_buffer_swap_cpu.
+ Adds a very slight overhead to tracing when enabled.
+
+# All tracer options should select GENERIC_TRACER. For those options that are
+# enabled by all tracers (context switch and event tracer) they select TRACING.
+# This allows those options to appear when no other tracer is selected. But the
+# options do not appear when something else selects it. We need the two options
+# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
+# hiding of the automatic options.
+
+config TRACING
+ bool
+ select DEBUG_FS
+ select RING_BUFFER
+ select STACKTRACE if STACKTRACE_SUPPORT
+ select TRACEPOINTS
+ select NOP_TRACER
+ select BINARY_PRINTF
+ select EVENT_TRACING
+
+config GENERIC_TRACER
+ bool
+ select TRACING
+
+#
+# Minimum requirements an architecture has to meet for us to
+# be able to offer generic tracing facilities:
+#
+config TRACING_SUPPORT
+ bool
+ # PPC32 has no irqflags tracing support, but it can use most of the
+ # tracers anyway, they were tested to build and work. Note that new
+ # exceptions to this list aren't welcomed, better implement the
+ # irqflags tracing for your architecture.
+ depends on TRACE_IRQFLAGS_SUPPORT || PPC32
+ depends on STACKTRACE_SUPPORT
+ default y
+
+if TRACING_SUPPORT
+
+menuconfig FTRACE
+ bool "Tracers"
+ default y if DEBUG_KERNEL
+ help
+ Enable the kernel tracing infrastructure.
+
+if FTRACE
+
+config FUNCTION_TRACER
+ bool "Kernel Function Tracer"
+ depends on HAVE_FUNCTION_TRACER
+ select FRAME_POINTER
+ select KALLSYMS
+ select GENERIC_TRACER
+ select CONTEXT_SWITCH_TRACER
+ help
+ Enable the kernel to trace every kernel function. This is done
+ by using a compiler feature to insert a small, 5-byte No-Operation
+ instruction at the beginning of every kernel function, which NOP
+ sequence is then dynamically patched into a tracer call when
+ tracing is enabled by the administrator. If it's runtime disabled
+ (the bootup default), then the overhead of the instructions is very
+ small and not measurable even in micro-benchmarks.
+
+config FUNCTION_GRAPH_TRACER
+ bool "Kernel Function Graph Tracer"
+ depends on HAVE_FUNCTION_GRAPH_TRACER
+ depends on FUNCTION_TRACER
+ depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
+ default y
+ help
+ Enable the kernel to trace a function at both its return
+ and its entry.
+ Its first purpose is to trace the duration of functions and
+ draw a call graph for each thread with some information like
+ the return value. This is done by setting the current return
+ address on the current task structure into a stack of calls.
+
+
+config IRQSOFF_TRACER
+ bool "Interrupts-off Latency Tracer"
+ default n
+ depends on TRACE_IRQFLAGS_SUPPORT
+ depends on GENERIC_TIME
+ select TRACE_IRQFLAGS
+ select GENERIC_TRACER
+ select TRACER_MAX_TRACE
+ select RING_BUFFER_ALLOW_SWAP
+ help
+ This option measures the time spent in irqs-off critical
+ sections, with microsecond accuracy.
+
+ The default measurement method is a maximum search, which is
+ disabled by default and can be runtime (re-)started
+ via:
+
+ echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
+
+ (Note that kernel size and overhead increase with this option
+ enabled. This option and the preempt-off timing option can be
+ used together or separately.)
+
+config PREEMPT_TRACER
+ bool "Preemption-off Latency Tracer"
+ default n
+ depends on GENERIC_TIME
+ depends on PREEMPT
+ select GENERIC_TRACER
+ select TRACER_MAX_TRACE
+ select RING_BUFFER_ALLOW_SWAP
+ help
+ This option measures the time spent in preemption-off critical
+ sections, with microsecond accuracy.
+
+ The default measurement method is a maximum search, which is
+ disabled by default and can be runtime (re-)started
+ via:
+
+ echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
+
+ (Note that kernel size and overhead increase with this option
+ enabled. This option and the irqs-off timing option can be
+ used together or separately.)
+
+config SYSPROF_TRACER
+ bool "Sysprof Tracer"
+ depends on X86
+ select GENERIC_TRACER
+ select CONTEXT_SWITCH_TRACER
+ help
+ This tracer provides the trace needed by the 'Sysprof' userspace
+ tool.
+
+config SCHED_TRACER
+ bool "Scheduling Latency Tracer"
+ select GENERIC_TRACER
+ select CONTEXT_SWITCH_TRACER
+ select TRACER_MAX_TRACE
+ help
+ This tracer tracks the latency of the highest priority task
+ to be scheduled in, starting from the point it has woken up.
+
+config ENABLE_DEFAULT_TRACERS
+ bool "Trace process context switches and events"
+ depends on !GENERIC_TRACER
+ select TRACING
+ help
+ This tracer hooks to various trace points in the kernel,
+ allowing the user to pick and choose which trace point they
+ want to trace. It also includes the sched_switch tracer plugin.
+
+config FTRACE_SYSCALLS
+ bool "Trace syscalls"
+ depends on HAVE_SYSCALL_TRACEPOINTS
+ select GENERIC_TRACER
+ select KALLSYMS
+ help
+ Basic tracer to catch the syscall entry and exit events.
+
+config BOOT_TRACER
+ bool "Trace boot initcalls"
+ select GENERIC_TRACER
+ select CONTEXT_SWITCH_TRACER
+ help
+ This tracer helps developers to optimize boot times: it records
+ the timings of the initcalls and traces key events and the identity
+ of tasks that can cause boot delays, such as context-switches.
+
+ Its aim is to be parsed by the scripts/bootgraph.pl tool to
+ produce pretty graphics about boot inefficiencies, giving a visual
+ representation of the delays during initcalls - but the raw
+ /debug/tracing/trace text output is readable too.
+
+ You must pass in initcall_debug and ftrace=initcall to the kernel
+ command line to enable this on bootup.
+
+config TRACE_BRANCH_PROFILING
+ bool
+ select GENERIC_TRACER
+
+choice
+ prompt "Branch Profiling"
+ default BRANCH_PROFILE_NONE
+ help
+ The branch profiling is a software profiler. It will add hooks
+ into the C conditionals to test which path a branch takes.
+
+ The likely/unlikely profiler only looks at the conditions that
+ are annotated with a likely or unlikely macro.
+
+ The "all branch" profiler will profile every if-statement in the
+ kernel. This profiler will also enable the likely/unlikely
+ profiler.
+
+ Either of the above profilers adds a bit of overhead to the system.
+ If unsure, choose "No branch profiling".
+
+config BRANCH_PROFILE_NONE
+ bool "No branch profiling"
+ help
+ No branch profiling. Branch profiling adds a bit of overhead.
+ Only enable it if you want to analyse the branching behavior.
+ Otherwise keep it disabled.
+
+config PROFILE_ANNOTATED_BRANCHES
+ bool "Trace likely/unlikely profiler"
+ select TRACE_BRANCH_PROFILING
+ help
+ This tracer profiles all the the likely and unlikely macros
+ in the kernel. It will display the results in:
+
+ /sys/kernel/debug/tracing/profile_annotated_branch
+
+ Note: this will add a significant overhead; only turn this
+ on if you need to profile the system's use of these macros.
+
+config PROFILE_ALL_BRANCHES
+ bool "Profile all if conditionals"
+ select TRACE_BRANCH_PROFILING
+ help
+ This tracer profiles all branch conditions. Every if ()
+ taken in the kernel is recorded whether it hit or miss.
+ The results will be displayed in:
+
+ /sys/kernel/debug/tracing/profile_branch
+
+ This option also enables the likely/unlikely profiler.
+
+ This configuration, when enabled, will impose a great overhead
+ on the system. This should only be enabled when the system
+ is to be analyzed in much detail.
+endchoice
+
+config TRACING_BRANCHES
+ bool
+ help
+ Selected by tracers that will trace the likely and unlikely
+ conditions. This prevents the tracers themselves from being
+ profiled. Profiling the tracing infrastructure can only happen
+ when the likelys and unlikelys are not being traced.
+
+config BRANCH_TRACER
+ bool "Trace likely/unlikely instances"
+ depends on TRACE_BRANCH_PROFILING
+ select TRACING_BRANCHES
+ help
+ This traces the events of likely and unlikely condition
+ calls in the kernel. The difference between this and the
+ "Trace likely/unlikely profiler" is that this is not a
+ histogram of the callers, but actually places the calling
+ events into a running trace buffer to see when and where the
+ events happened, as well as their results.
+
+ Say N if unsure.
+
+config POWER_TRACER
+ bool "Trace power consumption behavior"
+ depends on X86
+ select GENERIC_TRACER
+ help
+ This tracer helps developers to analyze and optimize the kernel's
+ power management decisions, specifically the C-state and P-state
+ behavior.
+
+config KSYM_TRACER
+ bool "Trace read and write access on kernel memory locations"
+ depends on HAVE_HW_BREAKPOINT
+ select TRACING
+ help
+ This tracer helps find read and write operations on any given kernel
+ symbol i.e. /proc/kallsyms.
+
+config PROFILE_KSYM_TRACER
+ bool "Profile all kernel memory accesses on 'watched' variables"
+ depends on KSYM_TRACER
+ help
+ This tracer profiles kernel accesses on variables watched through the
+ ksym tracer ftrace plugin. Depending upon the hardware, all read
+ and write operations on kernel variables can be monitored for
+ accesses.
+
+ The results will be displayed in:
+ /debugfs/tracing/profile_ksym
+
+ Say N if unsure.
+
+config STACK_TRACER
+ bool "Trace max stack"
+ depends on HAVE_FUNCTION_TRACER
+ select FUNCTION_TRACER
+ select STACKTRACE
+ select KALLSYMS
+ help
+ This special tracer records the maximum stack footprint of the
+ kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
+
+ This tracer works by hooking into every function call that the
+ kernel executes, and keeping a maximum stack depth value and
+ stack-trace saved. If this is configured with DYNAMIC_FTRACE
+ then it will not have any overhead while the stack tracer
+ is disabled.
+
+ To enable the stack tracer on bootup, pass in 'stacktrace'
+ on the kernel command line.
+
+ The stack tracer can also be enabled or disabled via the
+ sysctl kernel.stack_tracer_enabled
+
+ Say N if unsure.
+
+config HW_BRANCH_TRACER
+ depends on HAVE_HW_BRANCH_TRACER
+ bool "Trace hw branches"
+ select GENERIC_TRACER
+ help
+ This tracer records all branches on the system in a circular
+ buffer, giving access to the last N branches for each cpu.
+
+config KMEMTRACE
+ bool "Trace SLAB allocations"
+ select GENERIC_TRACER
+ help
+ kmemtrace provides tracing for slab allocator functions, such as
+ kmalloc, kfree, kmem_cache_alloc, kmem_cache_free, etc. Collected
+ data is then fed to the userspace application in order to analyse
+ allocation hotspots, internal fragmentation and so on, making it
+ possible to see how well an allocator performs, as well as debug
+ and profile kernel code.
+
+ This requires an userspace application to use. See
+ Documentation/trace/kmemtrace.txt for more information.
+
+ Saying Y will make the kernel somewhat larger and slower. However,
+ if you disable kmemtrace at run-time or boot-time, the performance
+ impact is minimal (depending on the arch the kernel is built for).
+
+ If unsure, say N.
+
+config WORKQUEUE_TRACER
+ bool "Trace workqueues"
+ select GENERIC_TRACER
+ help
+ The workqueue tracer provides some statistical information
+ about each cpu workqueue thread such as the number of the
+ works inserted and executed since their creation. It can help
+ to evaluate the amount of work each of them has to perform.
+ For example it can help a developer to decide whether he should
+ choose a per-cpu workqueue instead of a singlethreaded one.
+
+config BLK_DEV_IO_TRACE
+ bool "Support for tracing block IO actions"
+ depends on SYSFS
+ depends on BLOCK
+ select RELAY
+ select DEBUG_FS
+ select TRACEPOINTS
+ select GENERIC_TRACER
+ select STACKTRACE
+ help
+ Say Y here if you want to be able to trace the block layer actions
+ on a given queue. Tracing allows you to see any traffic happening
+ on a block device queue. For more information (and the userspace
+ support tools needed), fetch the blktrace tools from:
+
+ git://git.kernel.dk/blktrace.git
+
+ Tracing also is possible using the ftrace interface, e.g.:
+
+ echo 1 > /sys/block/sda/sda1/trace/enable
+ echo blk > /sys/kernel/debug/tracing/current_tracer
+ cat /sys/kernel/debug/tracing/trace_pipe
+
+ If unsure, say N.
+
+config KPROBE_EVENT
+ depends on KPROBES
+ depends on X86
+ bool "Enable kprobes-based dynamic events"
+ select TRACING
+ default y
+ help
+ This allows the user to add tracing events (similar to tracepoints)
+ on the fly via the ftrace interface. See
+ Documentation/trace/kprobetrace.txt for more details.
+
+ Those events can be inserted wherever kprobes can probe, and record
+ various register and memory values.
+
+ 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 DYNAMIC_FTRACE
+ bool "enable/disable ftrace tracepoints dynamically"
+ depends on FUNCTION_TRACER
+ depends on HAVE_DYNAMIC_FTRACE
+ default y
+ help
+ This option will modify all the calls to ftrace dynamically
+ (will patch them out of the binary image and replace them
+ with a No-Op instruction) as they are called. A table is
+ created to dynamically enable them again.
+
+ This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
+ otherwise has native performance as long as no tracing is active.
+
+ The changes to the code are done by a kernel thread that
+ wakes up once a second and checks to see if any ftrace calls
+ were made. If so, it runs stop_machine (stops all CPUS)
+ and modifies the code to jump over the call to ftrace.
+
+config FUNCTION_PROFILER
+ bool "Kernel function profiler"
+ depends on FUNCTION_TRACER
+ default n
+ help
+ This option enables the kernel function profiler. A file is created
+ in debugfs called function_profile_enabled which defaults to zero.
+ When a 1 is echoed into this file profiling begins, and when a
+ zero is entered, profiling stops. A "functions" file is created in
+ the trace_stats directory; this file shows the list of functions that
+ have been hit and their counters.
+
+ If in doubt, say N.
+
+config FTRACE_MCOUNT_RECORD
+ def_bool y
+ depends on DYNAMIC_FTRACE
+ depends on HAVE_FTRACE_MCOUNT_RECORD
+
+config FTRACE_SELFTEST
+ bool
+
+config FTRACE_STARTUP_TEST
+ bool "Perform a startup test on ftrace"
+ depends on GENERIC_TRACER
+ select FTRACE_SELFTEST
+ help
+ This option performs a series of startup tests on ftrace. On bootup
+ a series of tests are made to verify that the tracer is
+ functioning properly. It will do tests on all the configured
+ tracers of ftrace.
+
+config EVENT_TRACE_TEST_SYSCALLS
+ bool "Run selftest on syscall events"
+ depends on FTRACE_STARTUP_TEST
+ help
+ This option will also enable testing every syscall event.
+ It only enables the event and disables it and runs various loads
+ with the event enabled. This adds a bit more time for kernel boot
+ up since it runs this on every system call defined.
+
+ TBD - enable a way to actually call the syscalls as we test their
+ events
+
+config MMIOTRACE
+ bool "Memory mapped IO tracing"
+ depends on HAVE_MMIOTRACE_SUPPORT && PCI
+ select GENERIC_TRACER
+ help
+ Mmiotrace traces Memory Mapped I/O access and is meant for
+ debugging and reverse engineering. It is called from the ioremap
+ implementation and works via page faults. Tracing is disabled by
+ default and can be enabled at run-time.
+
+ See Documentation/trace/mmiotrace.txt.
+ If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+ tristate "Test module for mmiotrace"
+ depends on MMIOTRACE && m
+ help
+ This is a dumb module for testing mmiotrace. It is very dangerous
+ as it will write garbage to IO memory starting at a given address.
+ However, it should be safe to use on e.g. unused portion of VRAM.
+
+ Say N, unless you absolutely know what you are doing.
+
+config RING_BUFFER_BENCHMARK
+ tristate "Ring buffer benchmark stress tester"
+ depends on RING_BUFFER
+ help
+ This option creates a test to stress the ring buffer and benchmark it.
+ It creates its own ring buffer such that it will not interfere with
+ any other users of the ring buffer (such as ftrace). It then creates
+ a producer and consumer that will run for 10 seconds and sleep for
+ 10 seconds. Each interval it will print out the number of events
+ it recorded and give a rough estimate of how long each iteration took.
+
+ It does not disable interrupts or raise its priority, so it may be
+ affected by processes that are running.
+
+ If unsure, say N.
+
+endif # FTRACE
+
+endif # TRACING_SUPPORT
+
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
new file mode 100644
index 00000000000..cd9ecd89ec7
--- /dev/null
+++ b/kernel/trace/Makefile
@@ -0,0 +1,60 @@
+
+# Do not instrument the tracer itself:
+
+ifdef CONFIG_FUNCTION_TRACER
+ORIG_CFLAGS := $(KBUILD_CFLAGS)
+KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
+
+# selftest needs instrumentation
+CFLAGS_trace_selftest_dynamic.o = -pg
+obj-y += trace_selftest_dynamic.o
+endif
+
+# If unlikely tracing is enabled, do not trace these files
+ifdef CONFIG_TRACING_BRANCHES
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+endif
+
+#
+# Make the trace clocks available generally: it's infrastructure
+# relied on by ptrace for example:
+#
+obj-y += trace_clock.o
+
+obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
+
+obj-$(CONFIG_TRACING) += trace.o
+obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_stat.o
+obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
+obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
+obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
+obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
+obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
+obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_NOP_TRACER) += trace_nop.o
+obj-$(CONFIG_STACK_TRACER) += trace_stack.o
+obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
+obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
+obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
+obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
+obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
+obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+ifeq ($(CONFIG_BLOCK),y)
+obj-$(CONFIG_EVENT_TRACING) += blktrace.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o
+obj-$(CONFIG_EVENT_TRACING) += power-traces.o
+
+libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
new file mode 100644
index 00000000000..d9d6206e0b1
--- /dev/null
+++ b/kernel/trace/blktrace.c
@@ -0,0 +1,1767 @@
+/*
+ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blktrace_api.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/smp_lock.h>
+#include <linux/time.h>
+#include <linux/uaccess.h>
+
+#include <trace/events/block.h>
+
+#include "trace_output.h"
+
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+
+static unsigned int blktrace_seq __read_mostly = 1;
+
+static struct trace_array *blk_tr;
+static bool blk_tracer_enabled __read_mostly;
+
+/* Select an alternative, minimalistic output than the original one */
+#define TRACE_BLK_OPT_CLASSIC 0x1
+
+static struct tracer_opt blk_tracer_opts[] = {
+ /* Default disable the minimalistic output */
+ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) },
+ { }
+};
+
+static struct tracer_flags blk_tracer_flags = {
+ .val = 0,
+ .opts = blk_tracer_opts,
+};
+
+/* Global reference count of probes */
+static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+
+static void blk_register_tracepoints(void);
+static void blk_unregister_tracepoints(void);
+
+/*
+ * Send out a notify message.
+ */
+static void trace_note(struct blk_trace *bt, pid_t pid, int action,
+ const void *data, size_t len)
+{
+ struct blk_io_trace *t;
+ struct ring_buffer_event *event = NULL;
+ struct ring_buffer *buffer = NULL;
+ int pc = 0;
+ int cpu = smp_processor_id();
+ bool blk_tracer = blk_tracer_enabled;
+
+ if (blk_tracer) {
+ buffer = blk_tr->buffer;
+ pc = preempt_count();
+ event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
+ sizeof(*t) + len,
+ 0, pc);
+ if (!event)
+ return;
+ t = ring_buffer_event_data(event);
+ goto record_it;
+ }
+
+ if (!bt->rchan)
+ return;
+
+ t = relay_reserve(bt->rchan, sizeof(*t) + len);
+ if (t) {
+ t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+ t->time = ktime_to_ns(ktime_get());
+record_it:
+ t->device = bt->dev;
+ t->action = action;
+ t->pid = pid;
+ t->cpu = cpu;
+ t->pdu_len = len;
+ memcpy((void *) t + sizeof(*t), data, len);
+
+ if (blk_tracer)
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+ }
+}
+
+/*
+ * Send out a notify for this process, if we haven't done so since a trace
+ * started
+ */
+static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+{
+ tsk->btrace_seq = blktrace_seq;
+ trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
+}
+
+static void trace_note_time(struct blk_trace *bt)
+{
+ struct timespec now;
+ unsigned long flags;
+ u32 words[2];
+
+ getnstimeofday(&now);
+ words[0] = now.tv_sec;
+ words[1] = now.tv_nsec;
+
+ local_irq_save(flags);
+ trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words));
+ local_irq_restore(flags);
+}
+
+void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
+{
+ int n;
+ va_list args;
+ unsigned long flags;
+ char *buf;
+
+ if (unlikely(bt->trace_state != Blktrace_running &&
+ !blk_tracer_enabled))
+ return;
+
+ local_irq_save(flags);
+ buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
+ va_start(args, fmt);
+ n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
+ va_end(args);
+
+ trace_note(bt, 0, BLK_TN_MESSAGE, buf, n);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(__trace_note_message);
+
+static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
+ pid_t pid)
+{
+ if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
+ return 1;
+ if (sector && (sector < bt->start_lba || sector > bt->end_lba))
+ return 1;
+ if (bt->pid && pid != bt->pid)
+ return 1;
+
+ return 0;
+}
+
+/*
+ * Data direction bit lookup
+ */
+static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
+ BLK_TC_ACT(BLK_TC_WRITE) };
+
+/* The ilog2() calls fall out because they're constant */
+#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
+ (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name))
+
+/*
+ * The worker for the various blk_add_trace*() types. Fills out a
+ * blk_io_trace structure and places it in a per-cpu subbuffer.
+ */
+static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
+ int rw, u32 what, int error, int pdu_len, void *pdu_data)
+{
+ struct task_struct *tsk = current;
+ struct ring_buffer_event *event = NULL;
+ struct ring_buffer *buffer = NULL;
+ struct blk_io_trace *t;
+ unsigned long flags = 0;
+ unsigned long *sequence;
+ pid_t pid;
+ int cpu, pc = 0;
+ bool blk_tracer = blk_tracer_enabled;
+
+ if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
+ return;
+
+ what |= ddir_act[rw & WRITE];
+ what |= MASK_TC_BIT(rw, BARRIER);
+ what |= MASK_TC_BIT(rw, SYNCIO);
+ what |= MASK_TC_BIT(rw, AHEAD);
+ what |= MASK_TC_BIT(rw, META);
+ what |= MASK_TC_BIT(rw, DISCARD);
+
+ pid = tsk->pid;
+ if (act_log_check(bt, what, sector, pid))
+ return;
+ cpu = raw_smp_processor_id();
+
+ if (blk_tracer) {
+ tracing_record_cmdline(current);
+
+ buffer = blk_tr->buffer;
+ pc = preempt_count();
+ event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
+ sizeof(*t) + pdu_len,
+ 0, pc);
+ if (!event)
+ return;
+ t = ring_buffer_event_data(event);
+ goto record_it;
+ }
+
+ /*
+ * A word about the locking here - we disable interrupts to reserve
+ * some space in the relay per-cpu buffer, to prevent an irq
+ * from coming in and stepping on our toes.
+ */
+ local_irq_save(flags);
+
+ if (unlikely(tsk->btrace_seq != blktrace_seq))
+ trace_note_tsk(bt, tsk);
+
+ t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
+ if (t) {
+ sequence = per_cpu_ptr(bt->sequence, cpu);
+
+ t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+ t->sequence = ++(*sequence);
+ t->time = ktime_to_ns(ktime_get());
+record_it:
+ /*
+ * These two are not needed in ftrace as they are in the
+ * generic trace_entry, filled by tracing_generic_entry_update,
+ * but for the trace_event->bin() synthesizer benefit we do it
+ * here too.
+ */
+ t->cpu = cpu;
+ t->pid = pid;
+
+ t->sector = sector;
+ t->bytes = bytes;
+ t->action = what;
+ t->device = bt->dev;
+ t->error = error;
+ t->pdu_len = pdu_len;
+
+ if (pdu_len)
+ memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
+
+ if (blk_tracer) {
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+ return;
+ }
+ }
+
+ local_irq_restore(flags);
+}
+
+static struct dentry *blk_tree_root;
+static DEFINE_MUTEX(blk_tree_mutex);
+
+static void blk_trace_free(struct blk_trace *bt)
+{
+ debugfs_remove(bt->msg_file);
+ debugfs_remove(bt->dropped_file);
+ relay_close(bt->rchan);
+ debugfs_remove(bt->dir);
+ free_percpu(bt->sequence);
+ free_percpu(bt->msg_data);
+ kfree(bt);
+}
+
+static void blk_trace_cleanup(struct blk_trace *bt)
+{
+ blk_trace_free(bt);
+ if (atomic_dec_and_test(&blk_probes_ref))
+ blk_unregister_tracepoints();
+}
+
+int blk_trace_remove(struct request_queue *q)
+{
+ struct blk_trace *bt;
+
+ bt = xchg(&q->blk_trace, NULL);
+ if (!bt)
+ return -EINVAL;
+
+ if (bt->trace_state != Blktrace_running)
+ blk_trace_cleanup(bt);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_trace_remove);
+
+static int blk_dropped_open(struct inode *inode, struct file *filp)
+{
+ filp->private_data = inode->i_private;
+
+ return 0;
+}
+
+static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct blk_trace *bt = filp->private_data;
+ char buf[16];
+
+ snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
+
+ return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+static const struct file_operations blk_dropped_fops = {
+ .owner = THIS_MODULE,
+ .open = blk_dropped_open,
+ .read = blk_dropped_read,
+};
+
+static int blk_msg_open(struct inode *inode, struct file *filp)
+{
+ filp->private_data = inode->i_private;
+
+ return 0;
+}
+
+static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ char *msg;
+ struct blk_trace *bt;
+
+ if (count >= BLK_TN_MAX_MSG)
+ return -EINVAL;
+
+ msg = kmalloc(count + 1, GFP_KERNEL);
+ if (msg == NULL)
+ return -ENOMEM;
+
+ if (copy_from_user(msg, buffer, count)) {
+ kfree(msg);
+ return -EFAULT;
+ }
+
+ msg[count] = '\0';
+ bt = filp->private_data;
+ __trace_note_message(bt, "%s", msg);
+ kfree(msg);
+
+ return count;
+}
+
+static const struct file_operations blk_msg_fops = {
+ .owner = THIS_MODULE,
+ .open = blk_msg_open,
+ .write = blk_msg_write,
+};
+
+/*
+ * Keep track of how many times we encountered a full subbuffer, to aid
+ * the user space app in telling how many lost events there were.
+ */
+static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
+ void *prev_subbuf, size_t prev_padding)
+{
+ struct blk_trace *bt;
+
+ if (!relay_buf_full(buf))
+ return 1;
+
+ bt = buf->chan->private_data;
+ atomic_inc(&bt->dropped);
+ return 0;
+}
+
+static int blk_remove_buf_file_callback(struct dentry *dentry)
+{
+ debugfs_remove(dentry);
+
+ return 0;
+}
+
+static struct dentry *blk_create_buf_file_callback(const char *filename,
+ struct dentry *parent,
+ int mode,
+ struct rchan_buf *buf,
+ int *is_global)
+{
+ return debugfs_create_file(filename, mode, parent, buf,
+ &relay_file_operations);
+}
+
+static struct rchan_callbacks blk_relay_callbacks = {
+ .subbuf_start = blk_subbuf_start_callback,
+ .create_buf_file = blk_create_buf_file_callback,
+ .remove_buf_file = blk_remove_buf_file_callback,
+};
+
+static void blk_trace_setup_lba(struct blk_trace *bt,
+ struct block_device *bdev)
+{
+ struct hd_struct *part = NULL;
+
+ if (bdev)
+ part = bdev->bd_part;
+
+ if (part) {
+ bt->start_lba = part->start_sect;
+ bt->end_lba = part->start_sect + part->nr_sects;
+ } else {
+ bt->start_lba = 0;
+ bt->end_lba = -1ULL;
+ }
+}
+
+/*
+ * Setup everything required to start tracing
+ */
+int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev,
+ struct blk_user_trace_setup *buts)
+{
+ struct blk_trace *old_bt, *bt = NULL;
+ struct dentry *dir = NULL;
+ int ret, i;
+
+ if (!buts->buf_size || !buts->buf_nr)
+ return -EINVAL;
+
+ strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
+ buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
+
+ /*
+ * some device names have larger paths - convert the slashes
+ * to underscores for this to work as expected
+ */
+ for (i = 0; i < strlen(buts->name); i++)
+ if (buts->name[i] == '/')
+ buts->name[i] = '_';
+
+ bt = kzalloc(sizeof(*bt), GFP_KERNEL);
+ if (!bt)
+ return -ENOMEM;
+
+ ret = -ENOMEM;
+ bt->sequence = alloc_percpu(unsigned long);
+ if (!bt->sequence)
+ goto err;
+
+ bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
+ if (!bt->msg_data)
+ goto err;
+
+ ret = -ENOENT;
+
+ mutex_lock(&blk_tree_mutex);
+ if (!blk_tree_root) {
+ blk_tree_root = debugfs_create_dir("block", NULL);
+ if (!blk_tree_root) {
+ mutex_unlock(&blk_tree_mutex);
+ goto err;
+ }
+ }
+ mutex_unlock(&blk_tree_mutex);
+
+ dir = debugfs_create_dir(buts->name, blk_tree_root);
+
+ if (!dir)
+ goto err;
+
+ bt->dir = dir;
+ bt->dev = dev;
+ atomic_set(&bt->dropped, 0);
+
+ ret = -EIO;
+ bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
+ &blk_dropped_fops);
+ if (!bt->dropped_file)
+ goto err;
+
+ bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
+ if (!bt->msg_file)
+ goto err;
+
+ bt->rchan = relay_open("trace", dir, buts->buf_size,
+ buts->buf_nr, &blk_relay_callbacks, bt);
+ if (!bt->rchan)
+ goto err;
+
+ bt->act_mask = buts->act_mask;
+ if (!bt->act_mask)
+ bt->act_mask = (u16) -1;
+
+ blk_trace_setup_lba(bt, bdev);
+
+ /* overwrite with user settings */
+ if (buts->start_lba)
+ bt->start_lba = buts->start_lba;
+ if (buts->end_lba)
+ bt->end_lba = buts->end_lba;
+
+ bt->pid = buts->pid;
+ bt->trace_state = Blktrace_setup;
+
+ ret = -EBUSY;
+ old_bt = xchg(&q->blk_trace, bt);
+ if (old_bt) {
+ (void) xchg(&q->blk_trace, old_bt);
+ goto err;
+ }
+
+ if (atomic_inc_return(&blk_probes_ref) == 1)
+ blk_register_tracepoints();
+
+ return 0;
+err:
+ blk_trace_free(bt);
+ return ret;
+}
+
+int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct block_device *bdev,
+ char __user *arg)
+{
+ struct blk_user_trace_setup buts;
+ int ret;
+
+ ret = copy_from_user(&buts, arg, sizeof(buts));
+ if (ret)
+ return -EFAULT;
+
+ ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(arg, &buts, sizeof(buts)))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_trace_setup);
+
+int blk_trace_startstop(struct request_queue *q, int start)
+{
+ int ret;
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt == NULL)
+ return -EINVAL;
+
+ /*
+ * For starting a trace, we can transition from a setup or stopped
+ * trace. For stopping a trace, the state must be running
+ */
+ ret = -EINVAL;
+ if (start) {
+ if (bt->trace_state == Blktrace_setup ||
+ bt->trace_state == Blktrace_stopped) {
+ blktrace_seq++;
+ smp_mb();
+ bt->trace_state = Blktrace_running;
+
+ trace_note_time(bt);
+ ret = 0;
+ }
+ } else {
+ if (bt->trace_state == Blktrace_running) {
+ bt->trace_state = Blktrace_stopped;
+ relay_flush(bt->rchan);
+ ret = 0;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(blk_trace_startstop);
+
+/**
+ * blk_trace_ioctl: - handle the ioctls associated with tracing
+ * @bdev: the block device
+ * @cmd: the ioctl cmd
+ * @arg: the argument data, if any
+ *
+ **/
+int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
+{
+ struct request_queue *q;
+ int ret, start = 0;
+ char b[BDEVNAME_SIZE];
+
+ q = bdev_get_queue(bdev);
+ if (!q)
+ return -ENXIO;
+
+ mutex_lock(&bdev->bd_mutex);
+
+ switch (cmd) {
+ case BLKTRACESETUP:
+ bdevname(bdev, b);
+ ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
+ break;
+ case BLKTRACESTART:
+ start = 1;
+ case BLKTRACESTOP:
+ ret = blk_trace_startstop(q, start);
+ break;
+ case BLKTRACETEARDOWN:
+ ret = blk_trace_remove(q);
+ break;
+ default:
+ ret = -ENOTTY;
+ break;
+ }
+
+ mutex_unlock(&bdev->bd_mutex);
+ return ret;
+}
+
+/**
+ * blk_trace_shutdown: - stop and cleanup trace structures
+ * @q: the request queue associated with the device
+ *
+ **/
+void blk_trace_shutdown(struct request_queue *q)
+{
+ if (q->blk_trace) {
+ blk_trace_startstop(q, 0);
+ blk_trace_remove(q);
+ }
+}
+
+/*
+ * blktrace probes
+ */
+
+/**
+ * blk_add_trace_rq - Add a trace for a request oriented action
+ * @q: queue the io is for
+ * @rq: the source request
+ * @what: the action
+ *
+ * Description:
+ * Records an action against a request. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
+ u32 what)
+{
+ struct blk_trace *bt = q->blk_trace;
+ int rw = rq->cmd_flags & 0x03;
+
+ if (likely(!bt))
+ return;
+
+ if (blk_discard_rq(rq))
+ rw |= (1 << BIO_RW_DISCARD);
+
+ if (blk_pc_request(rq)) {
+ what |= BLK_TC_ACT(BLK_TC_PC);
+ __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw,
+ what, rq->errors, rq->cmd_len, rq->cmd);
+ } else {
+ what |= BLK_TC_ACT(BLK_TC_FS);
+ __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rw,
+ what, rq->errors, 0, NULL);
+ }
+}
+
+static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+}
+
+static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+}
+
+static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+}
+
+static void blk_add_trace_rq_requeue(struct request_queue *q,
+ struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+}
+
+static void blk_add_trace_rq_complete(struct request_queue *q,
+ struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+}
+
+/**
+ * blk_add_trace_bio - Add a trace for a bio oriented action
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @what: the action
+ *
+ * Description:
+ * Records an action against a bio. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
+ u32 what)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what,
+ !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
+}
+
+static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
+}
+
+static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
+}
+
+static void blk_add_trace_bio_backmerge(struct request_queue *q,
+ struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+}
+
+static void blk_add_trace_bio_frontmerge(struct request_queue *q,
+ struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+}
+
+static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+}
+
+static void blk_add_trace_getrq(struct request_queue *q,
+ struct bio *bio, int rw)
+{
+ if (bio)
+ blk_add_trace_bio(q, bio, BLK_TA_GETRQ);
+ else {
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt)
+ __blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL);
+ }
+}
+
+
+static void blk_add_trace_sleeprq(struct request_queue *q,
+ struct bio *bio, int rw)
+{
+ if (bio)
+ blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ);
+ else {
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt)
+ __blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ,
+ 0, 0, NULL);
+ }
+}
+
+static void blk_add_trace_plug(struct request_queue *q)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt)
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
+}
+
+static void blk_add_trace_unplug_io(struct request_queue *q)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt) {
+ unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
+ __be64 rpdu = cpu_to_be64(pdu);
+
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0,
+ sizeof(rpdu), &rpdu);
+ }
+}
+
+static void blk_add_trace_unplug_timer(struct request_queue *q)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt) {
+ unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
+ __be64 rpdu = cpu_to_be64(pdu);
+
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0,
+ sizeof(rpdu), &rpdu);
+ }
+}
+
+static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
+ unsigned int pdu)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt) {
+ __be64 rpdu = cpu_to_be64(pdu);
+
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+ BLK_TA_SPLIT, !bio_flagged(bio, BIO_UPTODATE),
+ sizeof(rpdu), &rpdu);
+ }
+}
+
+/**
+ * blk_add_trace_remap - Add a trace for a remap operation
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @dev: target device
+ * @from: source sector
+ *
+ * Description:
+ * Device mapper or raid target sometimes need to split a bio because
+ * it spans a stripe (or similar). Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
+ dev_t dev, sector_t from)
+{
+ struct blk_trace *bt = q->blk_trace;
+ struct blk_io_trace_remap r;
+
+ if (likely(!bt))
+ return;
+
+ r.device_from = cpu_to_be32(dev);
+ r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev);
+ r.sector_from = cpu_to_be64(from);
+
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+ BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
+ sizeof(r), &r);
+}
+
+/**
+ * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @q: queue the io is for
+ * @rq: the source request
+ * @dev: target device
+ * @from: source sector
+ *
+ * Description:
+ * Device mapper remaps request to other devices.
+ * Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_rq_remap(struct request_queue *q,
+ struct request *rq, dev_t dev,
+ sector_t from)
+{
+ struct blk_trace *bt = q->blk_trace;
+ struct blk_io_trace_remap r;
+
+ if (likely(!bt))
+ return;
+
+ r.device_from = cpu_to_be32(dev);
+ r.device_to = cpu_to_be32(disk_devt(rq->rq_disk));
+ r.sector_from = cpu_to_be64(from);
+
+ __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+ rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+ sizeof(r), &r);
+}
+
+/**
+ * blk_add_driver_data - Add binary message with driver-specific data
+ * @q: queue the io is for
+ * @rq: io request
+ * @data: driver-specific data
+ * @len: length of driver-specific data
+ *
+ * Description:
+ * Some drivers might want to write driver-specific data per request.
+ *
+ **/
+void blk_add_driver_data(struct request_queue *q,
+ struct request *rq,
+ void *data, size_t len)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ if (blk_pc_request(rq))
+ __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
+ BLK_TA_DRV_DATA, rq->errors, len, data);
+ else
+ __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0,
+ BLK_TA_DRV_DATA, rq->errors, len, data);
+}
+EXPORT_SYMBOL_GPL(blk_add_driver_data);
+
+static void blk_register_tracepoints(void)
+{
+ int ret;
+
+ ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
+ WARN_ON(ret);
+ ret = register_trace_block_getrq(blk_add_trace_getrq);
+ WARN_ON(ret);
+ ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
+ WARN_ON(ret);
+ ret = register_trace_block_plug(blk_add_trace_plug);
+ WARN_ON(ret);
+ ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+ WARN_ON(ret);
+ ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
+ WARN_ON(ret);
+ ret = register_trace_block_split(blk_add_trace_split);
+ WARN_ON(ret);
+ ret = register_trace_block_remap(blk_add_trace_remap);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+ WARN_ON(ret);
+}
+
+static void blk_unregister_tracepoints(void)
+{
+ unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
+ unregister_trace_block_remap(blk_add_trace_remap);
+ unregister_trace_block_split(blk_add_trace_split);
+ unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
+ unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+ unregister_trace_block_plug(blk_add_trace_plug);
+ unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
+ unregister_trace_block_getrq(blk_add_trace_getrq);
+ unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
+ unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+ unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+ unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
+ unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+ unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
+ unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+ unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
+ unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
+ unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
+
+ tracepoint_synchronize_unregister();
+}
+
+/*
+ * struct blk_io_tracer formatting routines
+ */
+
+static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
+{
+ int i = 0;
+ int tc = t->action >> BLK_TC_SHIFT;
+
+ if (t->action == BLK_TN_MESSAGE) {
+ rwbs[i++] = 'N';
+ goto out;
+ }
+
+ if (tc & BLK_TC_DISCARD)
+ rwbs[i++] = 'D';
+ else if (tc & BLK_TC_WRITE)
+ rwbs[i++] = 'W';
+ else if (t->bytes)
+ rwbs[i++] = 'R';
+ else
+ rwbs[i++] = 'N';
+
+ if (tc & BLK_TC_AHEAD)
+ rwbs[i++] = 'A';
+ if (tc & BLK_TC_BARRIER)
+ rwbs[i++] = 'B';
+ if (tc & BLK_TC_SYNC)
+ rwbs[i++] = 'S';
+ if (tc & BLK_TC_META)
+ rwbs[i++] = 'M';
+out:
+ rwbs[i] = '\0';
+}
+
+static inline
+const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent)
+{
+ return (const struct blk_io_trace *)ent;
+}
+
+static inline const void *pdu_start(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent) + 1;
+}
+
+static inline u32 t_action(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->action;
+}
+
+static inline u32 t_bytes(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->bytes;
+}
+
+static inline u32 t_sec(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->bytes >> 9;
+}
+
+static inline unsigned long long t_sector(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->sector;
+}
+
+static inline __u16 t_error(const struct trace_entry *ent)
+{
+ return te_blk_io_trace(ent)->error;
+}
+
+static __u64 get_pdu_int(const struct trace_entry *ent)
+{
+ const __u64 *val = pdu_start(ent);
+ return be64_to_cpu(*val);
+}
+
+static void get_pdu_remap(const struct trace_entry *ent,
+ struct blk_io_trace_remap *r)
+{
+ const struct blk_io_trace_remap *__r = pdu_start(ent);
+ __u64 sector_from = __r->sector_from;
+
+ r->device_from = be32_to_cpu(__r->device_from);
+ r->device_to = be32_to_cpu(__r->device_to);
+ r->sector_from = be64_to_cpu(sector_from);
+}
+
+typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
+
+static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
+{
+ char rwbs[6];
+ unsigned long long ts = iter->ts;
+ unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
+ unsigned secs = (unsigned long)ts;
+ const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+
+ fill_rwbs(rwbs, t);
+
+ return trace_seq_printf(&iter->seq,
+ "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
+ MAJOR(t->device), MINOR(t->device), iter->cpu,
+ secs, nsec_rem, iter->ent->pid, act, rwbs);
+}
+
+static int blk_log_action(struct trace_iterator *iter, const char *act)
+{
+ char rwbs[6];
+ const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+
+ fill_rwbs(rwbs, t);
+ return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
+ MAJOR(t->device), MINOR(t->device), act, rwbs);
+}
+
+static int blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+{
+ const unsigned char *pdu_buf;
+ int pdu_len;
+ int i, end, ret;
+
+ pdu_buf = pdu_start(ent);
+ pdu_len = te_blk_io_trace(ent)->pdu_len;
+
+ if (!pdu_len)
+ return 1;
+
+ /* find the last zero that needs to be printed */
+ for (end = pdu_len - 1; end >= 0; end--)
+ if (pdu_buf[end])
+ break;
+ end++;
+
+ if (!trace_seq_putc(s, '('))
+ return 0;
+
+ for (i = 0; i < pdu_len; i++) {
+
+ ret = trace_seq_printf(s, "%s%02x",
+ i == 0 ? "" : " ", pdu_buf[i]);
+ if (!ret)
+ return ret;
+
+ /*
+ * stop when the rest is just zeroes and indicate so
+ * with a ".." appended
+ */
+ if (i == end && end != pdu_len - 1)
+ return trace_seq_puts(s, " ..) ");
+ }
+
+ return trace_seq_puts(s, ") ");
+}
+
+static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
+{
+ char cmd[TASK_COMM_LEN];
+
+ trace_find_cmdline(ent->pid, cmd);
+
+ if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+ int ret;
+
+ ret = trace_seq_printf(s, "%u ", t_bytes(ent));
+ if (!ret)
+ return 0;
+ ret = blk_log_dump_pdu(s, ent);
+ if (!ret)
+ return 0;
+ return trace_seq_printf(s, "[%s]\n", cmd);
+ } else {
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%s]\n",
+ t_sector(ent), t_sec(ent), cmd);
+ return trace_seq_printf(s, "[%s]\n", cmd);
+ }
+}
+
+static int blk_log_with_error(struct trace_seq *s,
+ const struct trace_entry *ent)
+{
+ if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+ int ret;
+
+ ret = blk_log_dump_pdu(s, ent);
+ if (ret)
+ return trace_seq_printf(s, "[%d]\n", t_error(ent));
+ return 0;
+ } else {
+ if (t_sec(ent))
+ return trace_seq_printf(s, "%llu + %u [%d]\n",
+ t_sector(ent),
+ t_sec(ent), t_error(ent));
+ return trace_seq_printf(s, "%llu [%d]\n",
+ t_sector(ent), t_error(ent));
+ }
+}
+
+static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
+{
+ struct blk_io_trace_remap r = { .device_from = 0, };
+
+ get_pdu_remap(ent, &r);
+ return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
+ t_sector(ent), t_sec(ent),
+ MAJOR(r.device_from), MINOR(r.device_from),
+ (unsigned long long)r.sector_from);
+}
+
+static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
+{
+ char cmd[TASK_COMM_LEN];
+
+ trace_find_cmdline(ent->pid, cmd);
+
+ return trace_seq_printf(s, "[%s]\n", cmd);
+}
+
+static int blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent)
+{
+ char cmd[TASK_COMM_LEN];
+
+ trace_find_cmdline(ent->pid, cmd);
+
+ return trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent));
+}
+
+static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
+{
+ char cmd[TASK_COMM_LEN];
+
+ trace_find_cmdline(ent->pid, cmd);
+
+ return trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent),
+ get_pdu_int(ent), cmd);
+}
+
+static int blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
+{
+ int ret;
+ const struct blk_io_trace *t = te_blk_io_trace(ent);
+
+ ret = trace_seq_putmem(s, t + 1, t->pdu_len);
+ if (ret)
+ return trace_seq_putc(s, '\n');
+ return ret;
+}
+
+/*
+ * struct tracer operations
+ */
+
+static void blk_tracer_print_header(struct seq_file *m)
+{
+ if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
+ return;
+ seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n"
+ "# | | | | | |\n");
+}
+
+static void blk_tracer_start(struct trace_array *tr)
+{
+ blk_tracer_enabled = true;
+}
+
+static int blk_tracer_init(struct trace_array *tr)
+{
+ blk_tr = tr;
+ blk_tracer_start(tr);
+ return 0;
+}
+
+static void blk_tracer_stop(struct trace_array *tr)
+{
+ blk_tracer_enabled = false;
+}
+
+static void blk_tracer_reset(struct trace_array *tr)
+{
+ blk_tracer_stop(tr);
+}
+
+static const struct {
+ const char *act[2];
+ int (*print)(struct trace_seq *s, const struct trace_entry *ent);
+} what2act[] = {
+ [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic },
+ [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic },
+ [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic },
+ [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic },
+ [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic },
+ [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error },
+ [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic },
+ [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error },
+ [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug },
+ [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug },
+ [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug },
+ [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic },
+ [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split },
+ [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic },
+ [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap },
+};
+
+static enum print_line_t print_one_line(struct trace_iterator *iter,
+ bool classic)
+{
+ struct trace_seq *s = &iter->seq;
+ const struct blk_io_trace *t;
+ u16 what;
+ int ret;
+ bool long_act;
+ blk_log_action_t *log_action;
+
+ t = te_blk_io_trace(iter->ent);
+ what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+ long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
+ log_action = classic ? &blk_log_action_classic : &blk_log_action;
+
+ if (t->action == BLK_TN_MESSAGE) {
+ ret = log_action(iter, long_act ? "message" : "m");
+ if (ret)
+ ret = blk_log_msg(s, iter->ent);
+ goto out;
+ }
+
+ if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
+ ret = trace_seq_printf(s, "Unknown action %x\n", what);
+ else {
+ ret = log_action(iter, what2act[what].act[long_act]);
+ if (ret)
+ ret = what2act[what].print(s, iter->ent);
+ }
+out:
+ return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
+ int flags)
+{
+ return print_one_line(iter, false);
+}
+
+static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct blk_io_trace *t = (struct blk_io_trace *)iter->ent;
+ const int offset = offsetof(struct blk_io_trace, sector);
+ struct blk_io_trace old = {
+ .magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION,
+ .time = iter->ts,
+ };
+
+ if (!trace_seq_putmem(s, &old, offset))
+ return 0;
+ return trace_seq_putmem(s, &t->sector,
+ sizeof(old) - offset + t->pdu_len);
+}
+
+static enum print_line_t
+blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
+{
+ return blk_trace_synthesize_old_trace(iter) ?
+ TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
+{
+ if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
+ return TRACE_TYPE_UNHANDLED;
+
+ return print_one_line(iter, true);
+}
+
+static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+{
+ /* don't output context-info for blk_classic output */
+ if (bit == TRACE_BLK_OPT_CLASSIC) {
+ if (set)
+ trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
+ else
+ trace_flags |= TRACE_ITER_CONTEXT_INFO;
+ }
+ return 0;
+}
+
+static struct tracer blk_tracer __read_mostly = {
+ .name = "blk",
+ .init = blk_tracer_init,
+ .reset = blk_tracer_reset,
+ .start = blk_tracer_start,
+ .stop = blk_tracer_stop,
+ .print_header = blk_tracer_print_header,
+ .print_line = blk_tracer_print_line,
+ .flags = &blk_tracer_flags,
+ .set_flag = blk_tracer_set_flag,
+};
+
+static struct trace_event trace_blk_event = {
+ .type = TRACE_BLK,
+ .trace = blk_trace_event_print,
+ .binary = blk_trace_event_print_binary,
+};
+
+static int __init init_blk_tracer(void)
+{
+ if (!register_ftrace_event(&trace_blk_event)) {
+ pr_warning("Warning: could not register block events\n");
+ return 1;
+ }
+
+ if (register_tracer(&blk_tracer) != 0) {
+ pr_warning("Warning: could not register the block tracer\n");
+ unregister_ftrace_event(&trace_blk_event);
+ return 1;
+ }
+
+ return 0;
+}
+
+device_initcall(init_blk_tracer);
+
+static int blk_trace_remove_queue(struct request_queue *q)
+{
+ struct blk_trace *bt;
+
+ bt = xchg(&q->blk_trace, NULL);
+ if (bt == NULL)
+ return -EINVAL;
+
+ if (atomic_dec_and_test(&blk_probes_ref))
+ blk_unregister_tracepoints();
+
+ blk_trace_free(bt);
+ return 0;
+}
+
+/*
+ * Setup everything required to start tracing
+ */
+static int blk_trace_setup_queue(struct request_queue *q,
+ struct block_device *bdev)
+{
+ struct blk_trace *old_bt, *bt = NULL;
+ int ret = -ENOMEM;
+
+ bt = kzalloc(sizeof(*bt), GFP_KERNEL);
+ if (!bt)
+ return -ENOMEM;
+
+ bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
+ if (!bt->msg_data)
+ goto free_bt;
+
+ bt->dev = bdev->bd_dev;
+ bt->act_mask = (u16)-1;
+
+ blk_trace_setup_lba(bt, bdev);
+
+ old_bt = xchg(&q->blk_trace, bt);
+ if (old_bt != NULL) {
+ (void)xchg(&q->blk_trace, old_bt);
+ ret = -EBUSY;
+ goto free_bt;
+ }
+
+ if (atomic_inc_return(&blk_probes_ref) == 1)
+ blk_register_tracepoints();
+ return 0;
+
+free_bt:
+ blk_trace_free(bt);
+ return ret;
+}
+
+/*
+ * sysfs interface to enable and configure tracing
+ */
+
+static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf);
+static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count);
+#define BLK_TRACE_DEVICE_ATTR(_name) \
+ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \
+ sysfs_blk_trace_attr_show, \
+ sysfs_blk_trace_attr_store)
+
+static BLK_TRACE_DEVICE_ATTR(enable);
+static BLK_TRACE_DEVICE_ATTR(act_mask);
+static BLK_TRACE_DEVICE_ATTR(pid);
+static BLK_TRACE_DEVICE_ATTR(start_lba);
+static BLK_TRACE_DEVICE_ATTR(end_lba);
+
+static struct attribute *blk_trace_attrs[] = {
+ &dev_attr_enable.attr,
+ &dev_attr_act_mask.attr,
+ &dev_attr_pid.attr,
+ &dev_attr_start_lba.attr,
+ &dev_attr_end_lba.attr,
+ NULL
+};
+
+struct attribute_group blk_trace_attr_group = {
+ .name = "trace",
+ .attrs = blk_trace_attrs,
+};
+
+static const struct {
+ int mask;
+ const char *str;
+} mask_maps[] = {
+ { BLK_TC_READ, "read" },
+ { BLK_TC_WRITE, "write" },
+ { BLK_TC_BARRIER, "barrier" },
+ { BLK_TC_SYNC, "sync" },
+ { BLK_TC_QUEUE, "queue" },
+ { BLK_TC_REQUEUE, "requeue" },
+ { BLK_TC_ISSUE, "issue" },
+ { BLK_TC_COMPLETE, "complete" },
+ { BLK_TC_FS, "fs" },
+ { BLK_TC_PC, "pc" },
+ { BLK_TC_AHEAD, "ahead" },
+ { BLK_TC_META, "meta" },
+ { BLK_TC_DISCARD, "discard" },
+ { BLK_TC_DRV_DATA, "drv_data" },
+};
+
+static int blk_trace_str2mask(const char *str)
+{
+ int i;
+ int mask = 0;
+ char *buf, *s, *token;
+
+ buf = kstrdup(str, GFP_KERNEL);
+ if (buf == NULL)
+ return -ENOMEM;
+ s = strstrip(buf);
+
+ while (1) {
+ token = strsep(&s, ",");
+ if (token == NULL)
+ break;
+
+ if (*token == '\0')
+ continue;
+
+ for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+ if (strcasecmp(token, mask_maps[i].str) == 0) {
+ mask |= mask_maps[i].mask;
+ break;
+ }
+ }
+ if (i == ARRAY_SIZE(mask_maps)) {
+ mask = -EINVAL;
+ break;
+ }
+ }
+ kfree(buf);
+
+ return mask;
+}
+
+static ssize_t blk_trace_mask2str(char *buf, int mask)
+{
+ int i;
+ char *p = buf;
+
+ for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+ if (mask & mask_maps[i].mask) {
+ p += sprintf(p, "%s%s",
+ (p == buf) ? "" : ",", mask_maps[i].str);
+ }
+ }
+ *p++ = '\n';
+
+ return p - buf;
+}
+
+static struct request_queue *blk_trace_get_queue(struct block_device *bdev)
+{
+ if (bdev->bd_disk == NULL)
+ return NULL;
+
+ return bdev_get_queue(bdev);
+}
+
+static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q;
+ struct block_device *bdev;
+ ssize_t ret = -ENXIO;
+
+ lock_kernel();
+ bdev = bdget(part_devt(p));
+ if (bdev == NULL)
+ goto out_unlock_kernel;
+
+ q = blk_trace_get_queue(bdev);
+ if (q == NULL)
+ goto out_bdput;
+
+ mutex_lock(&bdev->bd_mutex);
+
+ if (attr == &dev_attr_enable) {
+ ret = sprintf(buf, "%u\n", !!q->blk_trace);
+ goto out_unlock_bdev;
+ }
+
+ if (q->blk_trace == NULL)
+ ret = sprintf(buf, "disabled\n");
+ else if (attr == &dev_attr_act_mask)
+ ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
+ else if (attr == &dev_attr_pid)
+ ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+ else if (attr == &dev_attr_start_lba)
+ ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+ else if (attr == &dev_attr_end_lba)
+ ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+
+out_unlock_bdev:
+ mutex_unlock(&bdev->bd_mutex);
+out_bdput:
+ bdput(bdev);
+out_unlock_kernel:
+ unlock_kernel();
+ return ret;
+}
+
+static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct block_device *bdev;
+ struct request_queue *q;
+ struct hd_struct *p;
+ u64 value;
+ ssize_t ret = -EINVAL;
+
+ if (count == 0)
+ goto out;
+
+ if (attr == &dev_attr_act_mask) {
+ if (sscanf(buf, "%llx", &value) != 1) {
+ /* Assume it is a list of trace category names */
+ ret = blk_trace_str2mask(buf);
+ if (ret < 0)
+ goto out;
+ value = ret;
+ }
+ } else if (sscanf(buf, "%llu", &value) != 1)
+ goto out;
+
+ ret = -ENXIO;
+
+ lock_kernel();
+ p = dev_to_part(dev);
+ bdev = bdget(part_devt(p));
+ if (bdev == NULL)
+ goto out_unlock_kernel;
+
+ q = blk_trace_get_queue(bdev);
+ if (q == NULL)
+ goto out_bdput;
+
+ mutex_lock(&bdev->bd_mutex);
+
+ if (attr == &dev_attr_enable) {
+ if (value)
+ ret = blk_trace_setup_queue(q, bdev);
+ else
+ ret = blk_trace_remove_queue(q);
+ goto out_unlock_bdev;
+ }
+
+ ret = 0;
+ if (q->blk_trace == NULL)
+ ret = blk_trace_setup_queue(q, bdev);
+
+ if (ret == 0) {
+ if (attr == &dev_attr_act_mask)
+ q->blk_trace->act_mask = value;
+ else if (attr == &dev_attr_pid)
+ q->blk_trace->pid = value;
+ else if (attr == &dev_attr_start_lba)
+ q->blk_trace->start_lba = value;
+ else if (attr == &dev_attr_end_lba)
+ q->blk_trace->end_lba = value;
+ }
+
+out_unlock_bdev:
+ mutex_unlock(&bdev->bd_mutex);
+out_bdput:
+ bdput(bdev);
+out_unlock_kernel:
+ unlock_kernel();
+out:
+ return ret ? ret : count;
+}
+
+int blk_trace_init_sysfs(struct device *dev)
+{
+ return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
+}
+
+void blk_trace_remove_sysfs(struct device *dev)
+{
+ sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
+}
+
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#ifdef CONFIG_EVENT_TRACING
+
+void blk_dump_cmd(char *buf, struct request *rq)
+{
+ int i, end;
+ int len = rq->cmd_len;
+ unsigned char *cmd = rq->cmd;
+
+ if (!blk_pc_request(rq)) {
+ buf[0] = '\0';
+ return;
+ }
+
+ for (end = len - 1; end >= 0; end--)
+ if (cmd[end])
+ break;
+ end++;
+
+ for (i = 0; i < len; i++) {
+ buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
+ if (i == end && end != len - 1) {
+ sprintf(buf, " ..");
+ break;
+ }
+ }
+}
+
+void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+{
+ int i = 0;
+
+ if (rw & WRITE)
+ rwbs[i++] = 'W';
+ else if (rw & 1 << BIO_RW_DISCARD)
+ rwbs[i++] = 'D';
+ else if (bytes)
+ rwbs[i++] = 'R';
+ else
+ rwbs[i++] = 'N';
+
+ if (rw & 1 << BIO_RW_AHEAD)
+ rwbs[i++] = 'A';
+ if (rw & 1 << BIO_RW_BARRIER)
+ rwbs[i++] = 'B';
+ if (rw & 1 << BIO_RW_SYNCIO)
+ rwbs[i++] = 'S';
+ if (rw & 1 << BIO_RW_META)
+ rwbs[i++] = 'M';
+
+ rwbs[i] = '\0';
+}
+
+void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
+{
+ int rw = rq->cmd_flags & 0x03;
+ int bytes;
+
+ if (blk_discard_rq(rq))
+ rw |= (1 << BIO_RW_DISCARD);
+
+ bytes = blk_rq_bytes(rq);
+
+ blk_fill_rwbs(rwbs, rw, bytes);
+}
+
+#endif /* CONFIG_EVENT_TRACING */
+
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
new file mode 100644
index 00000000000..404c9ba1602
--- /dev/null
+++ b/kernel/trace/ftrace.c
@@ -0,0 +1,3401 @@
+/*
+ * Infrastructure for profiling code inserted by 'gcc -pg'.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2004-2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Originally ported from the -rt patch by:
+ * Copyright (C) 2007 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Based on code in the latency_tracer, that is:
+ *
+ * Copyright (C) 2004-2006 Ingo Molnar
+ * Copyright (C) 2004 William Lee Irwin III
+ */
+
+#include <linux/stop_machine.h>
+#include <linux/clocksource.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/suspend.h>
+#include <linux/debugfs.h>
+#include <linux/hardirq.h>
+#include <linux/kthread.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/ftrace.h>
+#include <linux/sysctl.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+
+#include <trace/events/sched.h>
+
+#include <asm/ftrace.h>
+#include <asm/setup.h>
+
+#include "trace_output.h"
+#include "trace_stat.h"
+
+#define FTRACE_WARN_ON(cond) \
+ do { \
+ if (WARN_ON(cond)) \
+ ftrace_kill(); \
+ } while (0)
+
+#define FTRACE_WARN_ON_ONCE(cond) \
+ do { \
+ if (WARN_ON_ONCE(cond)) \
+ ftrace_kill(); \
+ } while (0)
+
+/* hash bits for specific function selection */
+#define FTRACE_HASH_BITS 7
+#define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS)
+
+/* ftrace_enabled is a method to turn ftrace on or off */
+int ftrace_enabled __read_mostly;
+static int last_ftrace_enabled;
+
+/* Quick disabling of function tracer. */
+int function_trace_stop;
+
+/* List for set_ftrace_pid's pids. */
+LIST_HEAD(ftrace_pids);
+struct ftrace_pid {
+ struct list_head list;
+ struct pid *pid;
+};
+
+/*
+ * ftrace_disabled is set when an anomaly is discovered.
+ * ftrace_disabled is much stronger than ftrace_enabled.
+ */
+static int ftrace_disabled __read_mostly;
+
+static DEFINE_MUTEX(ftrace_lock);
+
+static struct ftrace_ops ftrace_list_end __read_mostly =
+{
+ .func = ftrace_stub,
+};
+
+static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
+ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+#endif
+
+static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_ops *op = ftrace_list;
+
+ /* in case someone actually ports this to alpha! */
+ read_barrier_depends();
+
+ while (op != &ftrace_list_end) {
+ /* silly alpha */
+ read_barrier_depends();
+ op->func(ip, parent_ip);
+ op = op->next;
+ };
+}
+
+static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
+{
+ if (!test_tsk_trace_trace(current))
+ return;
+
+ ftrace_pid_function(ip, parent_ip);
+}
+
+static void set_ftrace_pid_function(ftrace_func_t func)
+{
+ /* do not set ftrace_pid_function to itself! */
+ if (func != ftrace_pid_func)
+ ftrace_pid_function = func;
+}
+
+/**
+ * clear_ftrace_function - reset the ftrace function
+ *
+ * This NULLs the ftrace function and in essence stops
+ * tracing. There may be lag
+ */
+void clear_ftrace_function(void)
+{
+ ftrace_trace_function = ftrace_stub;
+ __ftrace_trace_function = ftrace_stub;
+ ftrace_pid_function = ftrace_stub;
+}
+
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+/*
+ * For those archs that do not test ftrace_trace_stop in their
+ * mcount call site, we need to do it from C.
+ */
+static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
+{
+ if (function_trace_stop)
+ return;
+
+ __ftrace_trace_function(ip, parent_ip);
+}
+#endif
+
+static int __register_ftrace_function(struct ftrace_ops *ops)
+{
+ ops->next = ftrace_list;
+ /*
+ * We are entering ops into the ftrace_list but another
+ * CPU might be walking that list. We need to make sure
+ * the ops->next pointer is valid before another CPU sees
+ * the ops pointer included into the ftrace_list.
+ */
+ smp_wmb();
+ ftrace_list = ops;
+
+ if (ftrace_enabled) {
+ ftrace_func_t func;
+
+ if (ops->next == &ftrace_list_end)
+ func = ops->func;
+ else
+ func = ftrace_list_func;
+
+ if (!list_empty(&ftrace_pids)) {
+ set_ftrace_pid_function(func);
+ func = ftrace_pid_func;
+ }
+
+ /*
+ * For one func, simply call it directly.
+ * For more than one func, call the chain.
+ */
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ftrace_trace_function = func;
+#else
+ __ftrace_trace_function = func;
+ ftrace_trace_function = ftrace_test_stop_func;
+#endif
+ }
+
+ return 0;
+}
+
+static int __unregister_ftrace_function(struct ftrace_ops *ops)
+{
+ struct ftrace_ops **p;
+
+ /*
+ * If we are removing the last function, then simply point
+ * to the ftrace_stub.
+ */
+ if (ftrace_list == ops && ops->next == &ftrace_list_end) {
+ ftrace_trace_function = ftrace_stub;
+ ftrace_list = &ftrace_list_end;
+ return 0;
+ }
+
+ for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next)
+ if (*p == ops)
+ break;
+
+ if (*p != ops)
+ return -1;
+
+ *p = (*p)->next;
+
+ if (ftrace_enabled) {
+ /* If we only have one func left, then call that directly */
+ if (ftrace_list->next == &ftrace_list_end) {
+ ftrace_func_t func = ftrace_list->func;
+
+ if (!list_empty(&ftrace_pids)) {
+ set_ftrace_pid_function(func);
+ func = ftrace_pid_func;
+ }
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ftrace_trace_function = func;
+#else
+ __ftrace_trace_function = func;
+#endif
+ }
+ }
+
+ return 0;
+}
+
+static void ftrace_update_pid_func(void)
+{
+ ftrace_func_t func;
+
+ if (ftrace_trace_function == ftrace_stub)
+ return;
+
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ func = ftrace_trace_function;
+#else
+ func = __ftrace_trace_function;
+#endif
+
+ if (!list_empty(&ftrace_pids)) {
+ set_ftrace_pid_function(func);
+ func = ftrace_pid_func;
+ } else {
+ if (func == ftrace_pid_func)
+ func = ftrace_pid_function;
+ }
+
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ftrace_trace_function = func;
+#else
+ __ftrace_trace_function = func;
+#endif
+}
+
+#ifdef CONFIG_FUNCTION_PROFILER
+struct ftrace_profile {
+ struct hlist_node node;
+ unsigned long ip;
+ unsigned long counter;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ unsigned long long time;
+#endif
+};
+
+struct ftrace_profile_page {
+ struct ftrace_profile_page *next;
+ unsigned long index;
+ struct ftrace_profile records[];
+};
+
+struct ftrace_profile_stat {
+ atomic_t disabled;
+ struct hlist_head *hash;
+ struct ftrace_profile_page *pages;
+ struct ftrace_profile_page *start;
+ struct tracer_stat stat;
+};
+
+#define PROFILE_RECORDS_SIZE \
+ (PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
+
+#define PROFILES_PER_PAGE \
+ (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
+
+static int ftrace_profile_bits __read_mostly;
+static int ftrace_profile_enabled __read_mostly;
+
+/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
+static DEFINE_MUTEX(ftrace_profile_lock);
+
+static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
+
+#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+
+static void *
+function_stat_next(void *v, int idx)
+{
+ struct ftrace_profile *rec = v;
+ struct ftrace_profile_page *pg;
+
+ pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
+
+ again:
+ if (idx != 0)
+ rec++;
+
+ if ((void *)rec >= (void *)&pg->records[pg->index]) {
+ pg = pg->next;
+ if (!pg)
+ return NULL;
+ rec = &pg->records[0];
+ if (!rec->counter)
+ goto again;
+ }
+
+ return rec;
+}
+
+static void *function_stat_start(struct tracer_stat *trace)
+{
+ struct ftrace_profile_stat *stat =
+ container_of(trace, struct ftrace_profile_stat, stat);
+
+ if (!stat || !stat->start)
+ return NULL;
+
+ return function_stat_next(&stat->start->records[0], 0);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* function graph compares on total time */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->time < b->time)
+ return -1;
+ if (a->time > b->time)
+ return 1;
+ else
+ return 0;
+}
+#else
+/* not function graph compares against hits */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->counter < b->counter)
+ return -1;
+ if (a->counter > b->counter)
+ return 1;
+ else
+ return 0;
+}
+#endif
+
+static int function_stat_headers(struct seq_file *m)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " Function "
+ "Hit Time Avg\n"
+ " -------- "
+ "--- ---- ---\n");
+#else
+ seq_printf(m, " Function Hit\n"
+ " -------- ---\n");
+#endif
+ return 0;
+}
+
+static int function_stat_show(struct seq_file *m, void *v)
+{
+ struct ftrace_profile *rec = v;
+ char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ static DEFINE_MUTEX(mutex);
+ static struct trace_seq s;
+ unsigned long long avg;
+#endif
+
+ kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+ seq_printf(m, " %-30.30s %10lu", str, rec->counter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " ");
+ avg = rec->time;
+ do_div(avg, rec->counter);
+
+ mutex_lock(&mutex);
+ trace_seq_init(&s);
+ trace_print_graph_duration(rec->time, &s);
+ trace_seq_puts(&s, " ");
+ trace_print_graph_duration(avg, &s);
+ trace_print_seq(m, &s);
+ mutex_unlock(&mutex);
+#endif
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+
+ pg = stat->pages = stat->start;
+
+ while (pg) {
+ memset(pg->records, 0, PROFILE_RECORDS_SIZE);
+ pg->index = 0;
+ pg = pg->next;
+ }
+
+ memset(stat->hash, 0,
+ FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
+}
+
+int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+ int functions;
+ int pages;
+ int i;
+
+ /* If we already allocated, do nothing */
+ if (stat->pages)
+ return 0;
+
+ stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!stat->pages)
+ return -ENOMEM;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ functions = ftrace_update_tot_cnt;
+#else
+ /*
+ * We do not know the number of functions that exist because
+ * dynamic tracing is what counts them. With past experience
+ * we have around 20K functions. That should be more than enough.
+ * It is highly unlikely we will execute every function in
+ * the kernel.
+ */
+ functions = 20000;
+#endif
+
+ pg = stat->start = stat->pages;
+
+ pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
+
+ for (i = 0; i < pages; i++) {
+ pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!pg->next)
+ goto out_free;
+ pg = pg->next;
+ }
+
+ return 0;
+
+ out_free:
+ pg = stat->start;
+ while (pg) {
+ unsigned long tmp = (unsigned long)pg;
+
+ pg = pg->next;
+ free_page(tmp);
+ }
+
+ free_page((unsigned long)stat->pages);
+ stat->pages = NULL;
+ stat->start = NULL;
+
+ return -ENOMEM;
+}
+
+static int ftrace_profile_init_cpu(int cpu)
+{
+ struct ftrace_profile_stat *stat;
+ int size;
+
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ if (stat->hash) {
+ /* If the profile is already created, simply reset it */
+ ftrace_profile_reset(stat);
+ return 0;
+ }
+
+ /*
+ * We are profiling all functions, but usually only a few thousand
+ * functions are hit. We'll make a hash of 1024 items.
+ */
+ size = FTRACE_PROFILE_HASH_SIZE;
+
+ stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
+
+ if (!stat->hash)
+ return -ENOMEM;
+
+ if (!ftrace_profile_bits) {
+ size--;
+
+ for (; size; size >>= 1)
+ ftrace_profile_bits++;
+ }
+
+ /* Preallocate the function profiling pages */
+ if (ftrace_profile_pages_init(stat) < 0) {
+ kfree(stat->hash);
+ stat->hash = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int ftrace_profile_init(void)
+{
+ int cpu;
+ int ret = 0;
+
+ for_each_online_cpu(cpu) {
+ ret = ftrace_profile_init_cpu(cpu);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* interrupts must be disabled */
+static struct ftrace_profile *
+ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec;
+ struct hlist_head *hhd;
+ struct hlist_node *n;
+ unsigned long key;
+
+ key = hash_long(ip, ftrace_profile_bits);
+ hhd = &stat->hash[key];
+
+ if (hlist_empty(hhd))
+ return NULL;
+
+ hlist_for_each_entry_rcu(rec, n, hhd, node) {
+ if (rec->ip == ip)
+ return rec;
+ }
+
+ return NULL;
+}
+
+static void ftrace_add_profile(struct ftrace_profile_stat *stat,
+ struct ftrace_profile *rec)
+{
+ unsigned long key;
+
+ key = hash_long(rec->ip, ftrace_profile_bits);
+ hlist_add_head_rcu(&rec->node, &stat->hash[key]);
+}
+
+/*
+ * The memory is already allocated, this simply finds a new record to use.
+ */
+static struct ftrace_profile *
+ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec = NULL;
+
+ /* prevent recursion (from NMIs) */
+ if (atomic_inc_return(&stat->disabled) != 1)
+ goto out;
+
+ /*
+ * Try to find the function again since an NMI
+ * could have added it
+ */
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (rec)
+ goto out;
+
+ if (stat->pages->index == PROFILES_PER_PAGE) {
+ if (!stat->pages->next)
+ goto out;
+ stat->pages = stat->pages->next;
+ }
+
+ rec = &stat->pages->records[stat->pages->index++];
+ rec->ip = ip;
+ ftrace_add_profile(stat, rec);
+
+ out:
+ atomic_dec(&stat->disabled);
+
+ return rec;
+}
+
+static void
+function_profile_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_profile_stat *stat;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ if (!ftrace_profile_enabled)
+ return;
+
+ local_irq_save(flags);
+
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash || !ftrace_profile_enabled)
+ goto out;
+
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (!rec) {
+ rec = ftrace_profile_alloc(stat, ip);
+ if (!rec)
+ goto out;
+ }
+
+ rec->counter++;
+ out:
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int profile_graph_entry(struct ftrace_graph_ent *trace)
+{
+ function_profile_call(trace->func, 0);
+ return 1;
+}
+
+static void profile_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct ftrace_profile_stat *stat;
+ unsigned long long calltime;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash || !ftrace_profile_enabled)
+ goto out;
+
+ calltime = trace->rettime - trace->calltime;
+
+ if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+ int index;
+
+ index = trace->depth;
+
+ /* Append this call time to the parent time to subtract */
+ if (index)
+ current->ret_stack[index - 1].subtime += calltime;
+
+ if (current->ret_stack[index].subtime < calltime)
+ calltime -= current->ret_stack[index].subtime;
+ else
+ calltime = 0;
+ }
+
+ rec = ftrace_find_profiled_func(stat, trace->func);
+ if (rec)
+ rec->time += calltime;
+
+ out:
+ local_irq_restore(flags);
+}
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_graph(&profile_graph_return,
+ &profile_graph_entry);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_graph();
+}
+#else
+static struct ftrace_ops ftrace_profile_ops __read_mostly =
+{
+ .func = function_profile_call,
+};
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_function(&ftrace_profile_ops);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_function(&ftrace_profile_ops);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static ssize_t
+ftrace_profile_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long val;
+ char buf[64]; /* big enough to hold a number */
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ val = !!val;
+
+ mutex_lock(&ftrace_profile_lock);
+ if (ftrace_profile_enabled ^ val) {
+ if (val) {
+ ret = ftrace_profile_init();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+
+ ret = register_ftrace_profiler();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+ ftrace_profile_enabled = 1;
+ } else {
+ ftrace_profile_enabled = 0;
+ /*
+ * unregister_ftrace_profiler calls stop_machine
+ * so this acts like an synchronize_sched.
+ */
+ unregister_ftrace_profiler();
+ }
+ }
+ out:
+ mutex_unlock(&ftrace_profile_lock);
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+ftrace_profile_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64]; /* big enough to hold a number */
+ int r;
+
+ r = sprintf(buf, "%u\n", ftrace_profile_enabled);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static const struct file_operations ftrace_profile_fops = {
+ .open = tracing_open_generic,
+ .read = ftrace_profile_read,
+ .write = ftrace_profile_write,
+};
+
+/* used to initialize the real stat files */
+static struct tracer_stat function_stats __initdata = {
+ .name = "functions",
+ .stat_start = function_stat_start,
+ .stat_next = function_stat_next,
+ .stat_cmp = function_stat_cmp,
+ .stat_headers = function_stat_headers,
+ .stat_show = function_stat_show
+};
+
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+ struct ftrace_profile_stat *stat;
+ struct dentry *entry;
+ char *name;
+ int ret;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ /* allocate enough for function name + cpu number */
+ name = kmalloc(32, GFP_KERNEL);
+ if (!name) {
+ /*
+ * The files created are permanent, if something happens
+ * we still do not free memory.
+ */
+ WARN(1,
+ "Could not allocate stat file for cpu %d\n",
+ cpu);
+ return;
+ }
+ stat->stat = function_stats;
+ snprintf(name, 32, "function%d", cpu);
+ stat->stat.name = name;
+ ret = register_stat_tracer(&stat->stat);
+ if (ret) {
+ WARN(1,
+ "Could not register function stat for cpu %d\n",
+ cpu);
+ kfree(name);
+ return;
+ }
+ }
+
+ entry = debugfs_create_file("function_profile_enabled", 0644,
+ d_tracer, NULL, &ftrace_profile_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'function_profile_enabled' entry\n");
+}
+
+#else /* CONFIG_FUNCTION_PROFILER */
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+}
+#endif /* CONFIG_FUNCTION_PROFILER */
+
+static struct pid * const ftrace_swapper_pid = &init_struct_pid;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#ifndef CONFIG_FTRACE_MCOUNT_RECORD
+# error Dynamic ftrace depends on MCOUNT_RECORD
+#endif
+
+static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly;
+
+struct ftrace_func_probe {
+ struct hlist_node node;
+ struct ftrace_probe_ops *ops;
+ unsigned long flags;
+ unsigned long ip;
+ void *data;
+ struct rcu_head rcu;
+};
+
+enum {
+ FTRACE_ENABLE_CALLS = (1 << 0),
+ FTRACE_DISABLE_CALLS = (1 << 1),
+ FTRACE_UPDATE_TRACE_FUNC = (1 << 2),
+ FTRACE_ENABLE_MCOUNT = (1 << 3),
+ FTRACE_DISABLE_MCOUNT = (1 << 4),
+ FTRACE_START_FUNC_RET = (1 << 5),
+ FTRACE_STOP_FUNC_RET = (1 << 6),
+};
+
+static int ftrace_filtered;
+
+static struct dyn_ftrace *ftrace_new_addrs;
+
+static DEFINE_MUTEX(ftrace_regex_lock);
+
+struct ftrace_page {
+ struct ftrace_page *next;
+ int index;
+ struct dyn_ftrace records[];
+};
+
+#define ENTRIES_PER_PAGE \
+ ((PAGE_SIZE - sizeof(struct ftrace_page)) / sizeof(struct dyn_ftrace))
+
+/* estimate from running different kernels */
+#define NR_TO_INIT 10000
+
+static struct ftrace_page *ftrace_pages_start;
+static struct ftrace_page *ftrace_pages;
+
+static struct dyn_ftrace *ftrace_free_records;
+
+/*
+ * This is a double for. Do not use 'break' to break out of the loop,
+ * you must use a goto.
+ */
+#define do_for_each_ftrace_rec(pg, rec) \
+ for (pg = ftrace_pages_start; pg; pg = pg->next) { \
+ int _____i; \
+ for (_____i = 0; _____i < pg->index; _____i++) { \
+ rec = &pg->records[_____i];
+
+#define while_for_each_ftrace_rec() \
+ } \
+ }
+
+#ifdef CONFIG_KPROBES
+
+static int frozen_record_count;
+
+static inline void freeze_record(struct dyn_ftrace *rec)
+{
+ if (!(rec->flags & FTRACE_FL_FROZEN)) {
+ rec->flags |= FTRACE_FL_FROZEN;
+ frozen_record_count++;
+ }
+}
+
+static inline void unfreeze_record(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_FROZEN) {
+ rec->flags &= ~FTRACE_FL_FROZEN;
+ frozen_record_count--;
+ }
+}
+
+static inline int record_frozen(struct dyn_ftrace *rec)
+{
+ return rec->flags & FTRACE_FL_FROZEN;
+}
+#else
+# define freeze_record(rec) ({ 0; })
+# define unfreeze_record(rec) ({ 0; })
+# define record_frozen(rec) ({ 0; })
+#endif /* CONFIG_KPROBES */
+
+static void ftrace_free_rec(struct dyn_ftrace *rec)
+{
+ rec->freelist = ftrace_free_records;
+ ftrace_free_records = rec;
+ rec->flags |= FTRACE_FL_FREE;
+}
+
+static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
+{
+ struct dyn_ftrace *rec;
+
+ /* First check for freed records */
+ if (ftrace_free_records) {
+ rec = ftrace_free_records;
+
+ if (unlikely(!(rec->flags & FTRACE_FL_FREE))) {
+ FTRACE_WARN_ON_ONCE(1);
+ ftrace_free_records = NULL;
+ return NULL;
+ }
+
+ ftrace_free_records = rec->freelist;
+ memset(rec, 0, sizeof(*rec));
+ return rec;
+ }
+
+ if (ftrace_pages->index == ENTRIES_PER_PAGE) {
+ if (!ftrace_pages->next) {
+ /* allocate another page */
+ ftrace_pages->next =
+ (void *)get_zeroed_page(GFP_KERNEL);
+ if (!ftrace_pages->next)
+ return NULL;
+ }
+ ftrace_pages = ftrace_pages->next;
+ }
+
+ return &ftrace_pages->records[ftrace_pages->index++];
+}
+
+static struct dyn_ftrace *
+ftrace_record_ip(unsigned long ip)
+{
+ struct dyn_ftrace *rec;
+
+ if (ftrace_disabled)
+ return NULL;
+
+ rec = ftrace_alloc_dyn_node(ip);
+ if (!rec)
+ return NULL;
+
+ rec->ip = ip;
+ rec->newlist = ftrace_new_addrs;
+ ftrace_new_addrs = rec;
+
+ return rec;
+}
+
+static void print_ip_ins(const char *fmt, unsigned char *p)
+{
+ int i;
+
+ printk(KERN_CONT "%s", fmt);
+
+ for (i = 0; i < MCOUNT_INSN_SIZE; i++)
+ printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
+}
+
+static void ftrace_bug(int failed, unsigned long ip)
+{
+ switch (failed) {
+ case -EFAULT:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace faulted on modifying ");
+ print_ip_sym(ip);
+ break;
+ case -EINVAL:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace failed to modify ");
+ print_ip_sym(ip);
+ print_ip_ins(" actual: ", (unsigned char *)ip);
+ printk(KERN_CONT "\n");
+ break;
+ case -EPERM:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace faulted on writing ");
+ print_ip_sym(ip);
+ break;
+ default:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace faulted on unknown error ");
+ print_ip_sym(ip);
+ }
+}
+
+
+static int
+__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
+{
+ unsigned long ftrace_addr;
+ unsigned long flag = 0UL;
+
+ ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+ /*
+ * If this record is not to be traced or we want to disable it,
+ * then disable it.
+ *
+ * If we want to enable it and filtering is off, then enable it.
+ *
+ * If we want to enable it and filtering is on, enable it only if
+ * it's filtered
+ */
+ if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) {
+ if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER))
+ flag = FTRACE_FL_ENABLED;
+ }
+
+ /* If the state of this record hasn't changed, then do nothing */
+ if ((rec->flags & FTRACE_FL_ENABLED) == flag)
+ return 0;
+
+ if (flag) {
+ rec->flags |= FTRACE_FL_ENABLED;
+ return ftrace_make_call(rec, ftrace_addr);
+ }
+
+ rec->flags &= ~FTRACE_FL_ENABLED;
+ return ftrace_make_nop(NULL, rec, ftrace_addr);
+}
+
+static void ftrace_replace_code(int enable)
+{
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+ int failed;
+
+ do_for_each_ftrace_rec(pg, rec) {
+ /*
+ * Skip over free records, records that have
+ * failed and not converted.
+ */
+ if (rec->flags & FTRACE_FL_FREE ||
+ rec->flags & FTRACE_FL_FAILED ||
+ !(rec->flags & FTRACE_FL_CONVERTED))
+ continue;
+
+ /* ignore updates to this record's mcount site */
+ if (get_kprobe((void *)rec->ip)) {
+ freeze_record(rec);
+ continue;
+ } else {
+ unfreeze_record(rec);
+ }
+
+ failed = __ftrace_replace_code(rec, enable);
+ if (failed) {
+ rec->flags |= FTRACE_FL_FAILED;
+ ftrace_bug(failed, rec->ip);
+ /* Stop processing */
+ return;
+ }
+ } while_for_each_ftrace_rec();
+}
+
+static int
+ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
+{
+ unsigned long ip;
+ int ret;
+
+ ip = rec->ip;
+
+ ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+ if (ret) {
+ ftrace_bug(ret, ip);
+ rec->flags |= FTRACE_FL_FAILED;
+ return 0;
+ }
+ return 1;
+}
+
+/*
+ * archs can override this function if they must do something
+ * before the modifying code is performed.
+ */
+int __weak ftrace_arch_code_modify_prepare(void)
+{
+ return 0;
+}
+
+/*
+ * archs can override this function if they must do something
+ * after the modifying code is performed.
+ */
+int __weak ftrace_arch_code_modify_post_process(void)
+{
+ return 0;
+}
+
+static int __ftrace_modify_code(void *data)
+{
+ int *command = data;
+
+ if (*command & FTRACE_ENABLE_CALLS)
+ ftrace_replace_code(1);
+ else if (*command & FTRACE_DISABLE_CALLS)
+ ftrace_replace_code(0);
+
+ if (*command & FTRACE_UPDATE_TRACE_FUNC)
+ ftrace_update_ftrace_func(ftrace_trace_function);
+
+ if (*command & FTRACE_START_FUNC_RET)
+ ftrace_enable_ftrace_graph_caller();
+ else if (*command & FTRACE_STOP_FUNC_RET)
+ ftrace_disable_ftrace_graph_caller();
+
+ return 0;
+}
+
+static void ftrace_run_update_code(int command)
+{
+ int ret;
+
+ ret = ftrace_arch_code_modify_prepare();
+ FTRACE_WARN_ON(ret);
+ if (ret)
+ return;
+
+ stop_machine(__ftrace_modify_code, &command, NULL);
+
+ ret = ftrace_arch_code_modify_post_process();
+ FTRACE_WARN_ON(ret);
+}
+
+static ftrace_func_t saved_ftrace_func;
+static int ftrace_start_up;
+
+static void ftrace_startup_enable(int command)
+{
+ if (saved_ftrace_func != ftrace_trace_function) {
+ saved_ftrace_func = ftrace_trace_function;
+ command |= FTRACE_UPDATE_TRACE_FUNC;
+ }
+
+ if (!command || !ftrace_enabled)
+ return;
+
+ ftrace_run_update_code(command);
+}
+
+static void ftrace_startup(int command)
+{
+ if (unlikely(ftrace_disabled))
+ return;
+
+ ftrace_start_up++;
+ command |= FTRACE_ENABLE_CALLS;
+
+ ftrace_startup_enable(command);
+}
+
+static void ftrace_shutdown(int command)
+{
+ if (unlikely(ftrace_disabled))
+ return;
+
+ ftrace_start_up--;
+ /*
+ * Just warn in case of unbalance, no need to kill ftrace, it's not
+ * critical but the ftrace_call callers may be never nopped again after
+ * further ftrace uses.
+ */
+ WARN_ON_ONCE(ftrace_start_up < 0);
+
+ if (!ftrace_start_up)
+ command |= FTRACE_DISABLE_CALLS;
+
+ if (saved_ftrace_func != ftrace_trace_function) {
+ saved_ftrace_func = ftrace_trace_function;
+ command |= FTRACE_UPDATE_TRACE_FUNC;
+ }
+
+ if (!command || !ftrace_enabled)
+ return;
+
+ ftrace_run_update_code(command);
+}
+
+static void ftrace_startup_sysctl(void)
+{
+ int command = FTRACE_ENABLE_MCOUNT;
+
+ if (unlikely(ftrace_disabled))
+ return;
+
+ /* Force update next time */
+ saved_ftrace_func = NULL;
+ /* ftrace_start_up is true if we want ftrace running */
+ if (ftrace_start_up)
+ command |= FTRACE_ENABLE_CALLS;
+
+ ftrace_run_update_code(command);
+}
+
+static void ftrace_shutdown_sysctl(void)
+{
+ int command = FTRACE_DISABLE_MCOUNT;
+
+ if (unlikely(ftrace_disabled))
+ return;
+
+ /* ftrace_start_up is true if ftrace is running */
+ if (ftrace_start_up)
+ command |= FTRACE_DISABLE_CALLS;
+
+ ftrace_run_update_code(command);
+}
+
+static cycle_t ftrace_update_time;
+static unsigned long ftrace_update_cnt;
+unsigned long ftrace_update_tot_cnt;
+
+static int ftrace_update_code(struct module *mod)
+{
+ struct dyn_ftrace *p;
+ cycle_t start, stop;
+
+ start = ftrace_now(raw_smp_processor_id());
+ ftrace_update_cnt = 0;
+
+ while (ftrace_new_addrs) {
+
+ /* If something went wrong, bail without enabling anything */
+ if (unlikely(ftrace_disabled))
+ return -1;
+
+ p = ftrace_new_addrs;
+ ftrace_new_addrs = p->newlist;
+ p->flags = 0L;
+
+ /*
+ * Do the initial record convertion from mcount jump
+ * to the NOP instructions.
+ */
+ if (!ftrace_code_disable(mod, p)) {
+ ftrace_free_rec(p);
+ continue;
+ }
+
+ p->flags |= FTRACE_FL_CONVERTED;
+ ftrace_update_cnt++;
+
+ /*
+ * If the tracing is enabled, go ahead and enable the record.
+ *
+ * The reason not to enable the record immediatelly is the
+ * inherent check of ftrace_make_nop/ftrace_make_call for
+ * correct previous instructions. Making first the NOP
+ * conversion puts the module to the correct state, thus
+ * passing the ftrace_make_call check.
+ */
+ if (ftrace_start_up) {
+ int failed = __ftrace_replace_code(p, 1);
+ if (failed) {
+ ftrace_bug(failed, p->ip);
+ ftrace_free_rec(p);
+ }
+ }
+ }
+
+ stop = ftrace_now(raw_smp_processor_id());
+ ftrace_update_time = stop - start;
+ ftrace_update_tot_cnt += ftrace_update_cnt;
+
+ return 0;
+}
+
+static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
+{
+ struct ftrace_page *pg;
+ int cnt;
+ int i;
+
+ /* allocate a few pages */
+ ftrace_pages_start = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!ftrace_pages_start)
+ return -1;
+
+ /*
+ * Allocate a few more pages.
+ *
+ * TODO: have some parser search vmlinux before
+ * final linking to find all calls to ftrace.
+ * Then we can:
+ * a) know how many pages to allocate.
+ * and/or
+ * b) set up the table then.
+ *
+ * The dynamic code is still necessary for
+ * modules.
+ */
+
+ pg = ftrace_pages = ftrace_pages_start;
+
+ cnt = num_to_init / ENTRIES_PER_PAGE;
+ pr_info("ftrace: allocating %ld entries in %d pages\n",
+ num_to_init, cnt + 1);
+
+ for (i = 0; i < cnt; i++) {
+ pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+
+ /* If we fail, we'll try later anyway */
+ if (!pg->next)
+ break;
+
+ pg = pg->next;
+ }
+
+ return 0;
+}
+
+enum {
+ FTRACE_ITER_FILTER = (1 << 0),
+ FTRACE_ITER_NOTRACE = (1 << 1),
+ FTRACE_ITER_FAILURES = (1 << 2),
+ FTRACE_ITER_PRINTALL = (1 << 3),
+ FTRACE_ITER_HASH = (1 << 4),
+};
+
+#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
+
+struct ftrace_iterator {
+ struct ftrace_page *pg;
+ int hidx;
+ int idx;
+ unsigned flags;
+ struct trace_parser parser;
+};
+
+static void *
+t_hash_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ struct hlist_node *hnd = v;
+ struct hlist_head *hhd;
+
+ WARN_ON(!(iter->flags & FTRACE_ITER_HASH));
+
+ (*pos)++;
+
+ retry:
+ if (iter->hidx >= FTRACE_FUNC_HASHSIZE)
+ return NULL;
+
+ hhd = &ftrace_func_hash[iter->hidx];
+
+ if (hlist_empty(hhd)) {
+ iter->hidx++;
+ hnd = NULL;
+ goto retry;
+ }
+
+ if (!hnd)
+ hnd = hhd->first;
+ else {
+ hnd = hnd->next;
+ if (!hnd) {
+ iter->hidx++;
+ goto retry;
+ }
+ }
+
+ return hnd;
+}
+
+static void *t_hash_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ void *p = NULL;
+ loff_t l;
+
+ if (!(iter->flags & FTRACE_ITER_HASH))
+ *pos = 0;
+
+ iter->flags |= FTRACE_ITER_HASH;
+
+ iter->hidx = 0;
+ for (l = 0; l <= *pos; ) {
+ p = t_hash_next(m, p, &l);
+ if (!p)
+ break;
+ }
+ return p;
+}
+
+static int t_hash_show(struct seq_file *m, void *v)
+{
+ struct ftrace_func_probe *rec;
+ struct hlist_node *hnd = v;
+
+ rec = hlist_entry(hnd, struct ftrace_func_probe, node);
+
+ if (rec->ops->print)
+ return rec->ops->print(m, rec->ip, rec->ops, rec->data);
+
+ seq_printf(m, "%ps:%ps", (void *)rec->ip, (void *)rec->ops->func);
+
+ if (rec->data)
+ seq_printf(m, ":%p", rec->data);
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ struct dyn_ftrace *rec = NULL;
+
+ if (iter->flags & FTRACE_ITER_HASH)
+ return t_hash_next(m, v, pos);
+
+ (*pos)++;
+
+ if (iter->flags & FTRACE_ITER_PRINTALL)
+ return NULL;
+
+ retry:
+ if (iter->idx >= iter->pg->index) {
+ if (iter->pg->next) {
+ iter->pg = iter->pg->next;
+ iter->idx = 0;
+ goto retry;
+ }
+ } else {
+ rec = &iter->pg->records[iter->idx++];
+ if ((rec->flags & FTRACE_FL_FREE) ||
+
+ (!(iter->flags & FTRACE_ITER_FAILURES) &&
+ (rec->flags & FTRACE_FL_FAILED)) ||
+
+ ((iter->flags & FTRACE_ITER_FAILURES) &&
+ !(rec->flags & FTRACE_FL_FAILED)) ||
+
+ ((iter->flags & FTRACE_ITER_FILTER) &&
+ !(rec->flags & FTRACE_FL_FILTER)) ||
+
+ ((iter->flags & FTRACE_ITER_NOTRACE) &&
+ !(rec->flags & FTRACE_FL_NOTRACE))) {
+ rec = NULL;
+ goto retry;
+ }
+ }
+
+ return rec;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ void *p = NULL;
+ loff_t l;
+
+ mutex_lock(&ftrace_lock);
+ /*
+ * For set_ftrace_filter reading, if we have the filter
+ * off, we can short cut and just print out that all
+ * functions are enabled.
+ */
+ if (iter->flags & FTRACE_ITER_FILTER && !ftrace_filtered) {
+ if (*pos > 0)
+ return t_hash_start(m, pos);
+ iter->flags |= FTRACE_ITER_PRINTALL;
+ return iter;
+ }
+
+ if (iter->flags & FTRACE_ITER_HASH)
+ return t_hash_start(m, pos);
+
+ iter->pg = ftrace_pages_start;
+ iter->idx = 0;
+ for (l = 0; l <= *pos; ) {
+ p = t_next(m, p, &l);
+ if (!p)
+ break;
+ }
+
+ if (!p && iter->flags & FTRACE_ITER_FILTER)
+ return t_hash_start(m, pos);
+
+ return p;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&ftrace_lock);
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+ struct ftrace_iterator *iter = m->private;
+ struct dyn_ftrace *rec = v;
+
+ if (iter->flags & FTRACE_ITER_HASH)
+ return t_hash_show(m, v);
+
+ if (iter->flags & FTRACE_ITER_PRINTALL) {
+ seq_printf(m, "#### all functions enabled ####\n");
+ return 0;
+ }
+
+ if (!rec)
+ return 0;
+
+ seq_printf(m, "%ps\n", (void *)rec->ip);
+
+ return 0;
+}
+
+static const struct seq_operations show_ftrace_seq_ops = {
+ .start = t_start,
+ .next = t_next,
+ .stop = t_stop,
+ .show = t_show,
+};
+
+static int
+ftrace_avail_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_iterator *iter;
+ int ret;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ iter->pg = ftrace_pages_start;
+
+ ret = seq_open(file, &show_ftrace_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+
+ m->private = iter;
+ } else {
+ kfree(iter);
+ }
+
+ return ret;
+}
+
+static int
+ftrace_failures_open(struct inode *inode, struct file *file)
+{
+ int ret;
+ struct seq_file *m;
+ struct ftrace_iterator *iter;
+
+ ret = ftrace_avail_open(inode, file);
+ if (!ret) {
+ m = (struct seq_file *)file->private_data;
+ iter = (struct ftrace_iterator *)m->private;
+ iter->flags = FTRACE_ITER_FAILURES;
+ }
+
+ return ret;
+}
+
+
+static void ftrace_filter_reset(int enable)
+{
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+ unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
+
+ mutex_lock(&ftrace_lock);
+ if (enable)
+ ftrace_filtered = 0;
+ do_for_each_ftrace_rec(pg, rec) {
+ if (rec->flags & FTRACE_FL_FAILED)
+ continue;
+ rec->flags &= ~type;
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+}
+
+static int
+ftrace_regex_open(struct inode *inode, struct file *file, int enable)
+{
+ struct ftrace_iterator *iter;
+ int ret = 0;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) {
+ kfree(iter);
+ return -ENOMEM;
+ }
+
+ mutex_lock(&ftrace_regex_lock);
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ ftrace_filter_reset(enable);
+
+ if (file->f_mode & FMODE_READ) {
+ iter->pg = ftrace_pages_start;
+ iter->flags = enable ? FTRACE_ITER_FILTER :
+ FTRACE_ITER_NOTRACE;
+
+ ret = seq_open(file, &show_ftrace_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = iter;
+ } else {
+ trace_parser_put(&iter->parser);
+ kfree(iter);
+ }
+ } else
+ file->private_data = iter;
+ mutex_unlock(&ftrace_regex_lock);
+
+ return ret;
+}
+
+static int
+ftrace_filter_open(struct inode *inode, struct file *file)
+{
+ return ftrace_regex_open(inode, file, 1);
+}
+
+static int
+ftrace_notrace_open(struct inode *inode, struct file *file)
+{
+ return ftrace_regex_open(inode, file, 0);
+}
+
+static loff_t
+ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
+{
+ loff_t ret;
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_lseek(file, offset, origin);
+ else
+ file->f_pos = ret = 1;
+
+ return ret;
+}
+
+static int ftrace_match(char *str, char *regex, int len, int type)
+{
+ int matched = 0;
+ int slen;
+
+ switch (type) {
+ case MATCH_FULL:
+ if (strcmp(str, regex) == 0)
+ matched = 1;
+ break;
+ case MATCH_FRONT_ONLY:
+ if (strncmp(str, regex, len) == 0)
+ matched = 1;
+ break;
+ case MATCH_MIDDLE_ONLY:
+ if (strstr(str, regex))
+ matched = 1;
+ break;
+ case MATCH_END_ONLY:
+ slen = strlen(str);
+ if (slen >= len && memcmp(str + slen - len, regex, len) == 0)
+ matched = 1;
+ break;
+ }
+
+ return matched;
+}
+
+static int
+ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type)
+{
+ char str[KSYM_SYMBOL_LEN];
+
+ kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+ return ftrace_match(str, regex, len, type);
+}
+
+static int ftrace_match_records(char *buff, int len, int enable)
+{
+ unsigned int search_len;
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+ unsigned long flag;
+ char *search;
+ int type;
+ int not;
+ int found = 0;
+
+ flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
+ type = filter_parse_regex(buff, len, &search, &not);
+
+ search_len = strlen(search);
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+
+ if (rec->flags & FTRACE_FL_FAILED)
+ continue;
+
+ if (ftrace_match_record(rec, search, search_len, type)) {
+ if (not)
+ rec->flags &= ~flag;
+ else
+ rec->flags |= flag;
+ found = 1;
+ }
+ /*
+ * Only enable filtering if we have a function that
+ * is filtered on.
+ */
+ if (enable && (rec->flags & FTRACE_FL_FILTER))
+ ftrace_filtered = 1;
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+
+ return found;
+}
+
+static int
+ftrace_match_module_record(struct dyn_ftrace *rec, char *mod,
+ char *regex, int len, int type)
+{
+ char str[KSYM_SYMBOL_LEN];
+ char *modname;
+
+ kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
+
+ if (!modname || strcmp(modname, mod))
+ return 0;
+
+ /* blank search means to match all funcs in the mod */
+ if (len)
+ return ftrace_match(str, regex, len, type);
+ else
+ return 1;
+}
+
+static int ftrace_match_module_records(char *buff, char *mod, int enable)
+{
+ unsigned search_len = 0;
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+ int type = MATCH_FULL;
+ char *search = buff;
+ unsigned long flag;
+ int not = 0;
+ int found = 0;
+
+ flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
+
+ /* blank or '*' mean the same */
+ if (strcmp(buff, "*") == 0)
+ buff[0] = 0;
+
+ /* handle the case of 'dont filter this module' */
+ if (strcmp(buff, "!") == 0 || strcmp(buff, "!*") == 0) {
+ buff[0] = 0;
+ not = 1;
+ }
+
+ if (strlen(buff)) {
+ type = filter_parse_regex(buff, strlen(buff), &search, &not);
+ search_len = strlen(search);
+ }
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+
+ if (rec->flags & FTRACE_FL_FAILED)
+ continue;
+
+ if (ftrace_match_module_record(rec, mod,
+ search, search_len, type)) {
+ if (not)
+ rec->flags &= ~flag;
+ else
+ rec->flags |= flag;
+ found = 1;
+ }
+ if (enable && (rec->flags & FTRACE_FL_FILTER))
+ ftrace_filtered = 1;
+
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+
+ return found;
+}
+
+/*
+ * We register the module command as a template to show others how
+ * to register the a command as well.
+ */
+
+static int
+ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
+{
+ char *mod;
+
+ /*
+ * cmd == 'mod' because we only registered this func
+ * for the 'mod' ftrace_func_command.
+ * But if you register one func with multiple commands,
+ * you can tell which command was used by the cmd
+ * parameter.
+ */
+
+ /* we must have a module name */
+ if (!param)
+ return -EINVAL;
+
+ mod = strsep(&param, ":");
+ if (!strlen(mod))
+ return -EINVAL;
+
+ if (ftrace_match_module_records(func, mod, enable))
+ return 0;
+ return -EINVAL;
+}
+
+static struct ftrace_func_command ftrace_mod_cmd = {
+ .name = "mod",
+ .func = ftrace_mod_callback,
+};
+
+static int __init ftrace_mod_cmd_init(void)
+{
+ return register_ftrace_command(&ftrace_mod_cmd);
+}
+device_initcall(ftrace_mod_cmd_init);
+
+static void
+function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_func_probe *entry;
+ struct hlist_head *hhd;
+ struct hlist_node *n;
+ unsigned long key;
+ int resched;
+
+ key = hash_long(ip, FTRACE_HASH_BITS);
+
+ hhd = &ftrace_func_hash[key];
+
+ if (hlist_empty(hhd))
+ return;
+
+ /*
+ * Disable preemption for these calls to prevent a RCU grace
+ * period. This syncs the hash iteration and freeing of items
+ * on the hash. rcu_read_lock is too dangerous here.
+ */
+ resched = ftrace_preempt_disable();
+ hlist_for_each_entry_rcu(entry, n, hhd, node) {
+ if (entry->ip == ip)
+ entry->ops->func(ip, parent_ip, &entry->data);
+ }
+ ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_probe_ops __read_mostly =
+{
+ .func = function_trace_probe_call,
+};
+
+static int ftrace_probe_registered;
+
+static void __enable_ftrace_function_probe(void)
+{
+ int i;
+
+ if (ftrace_probe_registered)
+ return;
+
+ for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
+ struct hlist_head *hhd = &ftrace_func_hash[i];
+ if (hhd->first)
+ break;
+ }
+ /* Nothing registered? */
+ if (i == FTRACE_FUNC_HASHSIZE)
+ return;
+
+ __register_ftrace_function(&trace_probe_ops);
+ ftrace_startup(0);
+ ftrace_probe_registered = 1;
+}
+
+static void __disable_ftrace_function_probe(void)
+{
+ int i;
+
+ if (!ftrace_probe_registered)
+ return;
+
+ for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
+ struct hlist_head *hhd = &ftrace_func_hash[i];
+ if (hhd->first)
+ return;
+ }
+
+ /* no more funcs left */
+ __unregister_ftrace_function(&trace_probe_ops);
+ ftrace_shutdown(0);
+ ftrace_probe_registered = 0;
+}
+
+
+static void ftrace_free_entry_rcu(struct rcu_head *rhp)
+{
+ struct ftrace_func_probe *entry =
+ container_of(rhp, struct ftrace_func_probe, rcu);
+
+ if (entry->ops->free)
+ entry->ops->free(&entry->data);
+ kfree(entry);
+}
+
+
+int
+register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+ void *data)
+{
+ struct ftrace_func_probe *entry;
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+ int type, len, not;
+ unsigned long key;
+ int count = 0;
+ char *search;
+
+ type = filter_parse_regex(glob, strlen(glob), &search, &not);
+ len = strlen(search);
+
+ /* we do not support '!' for function probes */
+ if (WARN_ON(not))
+ return -EINVAL;
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+
+ if (rec->flags & FTRACE_FL_FAILED)
+ continue;
+
+ if (!ftrace_match_record(rec, search, len, type))
+ continue;
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ /* If we did not process any, then return error */
+ if (!count)
+ count = -ENOMEM;
+ goto out_unlock;
+ }
+
+ count++;
+
+ entry->data = data;
+
+ /*
+ * The caller might want to do something special
+ * for each function we find. We call the callback
+ * to give the caller an opportunity to do so.
+ */
+ if (ops->callback) {
+ if (ops->callback(rec->ip, &entry->data) < 0) {
+ /* caller does not like this func */
+ kfree(entry);
+ continue;
+ }
+ }
+
+ entry->ops = ops;
+ entry->ip = rec->ip;
+
+ key = hash_long(entry->ip, FTRACE_HASH_BITS);
+ hlist_add_head_rcu(&entry->node, &ftrace_func_hash[key]);
+
+ } while_for_each_ftrace_rec();
+ __enable_ftrace_function_probe();
+
+ out_unlock:
+ mutex_unlock(&ftrace_lock);
+
+ return count;
+}
+
+enum {
+ PROBE_TEST_FUNC = 1,
+ PROBE_TEST_DATA = 2
+};
+
+static void
+__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+ void *data, int flags)
+{
+ struct ftrace_func_probe *entry;
+ struct hlist_node *n, *tmp;
+ char str[KSYM_SYMBOL_LEN];
+ int type = MATCH_FULL;
+ int i, len = 0;
+ char *search;
+
+ if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
+ glob = NULL;
+ else if (glob) {
+ int not;
+
+ type = filter_parse_regex(glob, strlen(glob), &search, &not);
+ len = strlen(search);
+
+ /* we do not support '!' for function probes */
+ if (WARN_ON(not))
+ return;
+ }
+
+ mutex_lock(&ftrace_lock);
+ for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
+ struct hlist_head *hhd = &ftrace_func_hash[i];
+
+ hlist_for_each_entry_safe(entry, n, tmp, hhd, node) {
+
+ /* break up if statements for readability */
+ if ((flags & PROBE_TEST_FUNC) && entry->ops != ops)
+ continue;
+
+ if ((flags & PROBE_TEST_DATA) && entry->data != data)
+ continue;
+
+ /* do this last, since it is the most expensive */
+ if (glob) {
+ kallsyms_lookup(entry->ip, NULL, NULL,
+ NULL, str);
+ if (!ftrace_match(str, glob, len, type))
+ continue;
+ }
+
+ hlist_del(&entry->node);
+ call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+ }
+ }
+ __disable_ftrace_function_probe();
+ mutex_unlock(&ftrace_lock);
+}
+
+void
+unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+ void *data)
+{
+ __unregister_ftrace_function_probe(glob, ops, data,
+ PROBE_TEST_FUNC | PROBE_TEST_DATA);
+}
+
+void
+unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops)
+{
+ __unregister_ftrace_function_probe(glob, ops, NULL, PROBE_TEST_FUNC);
+}
+
+void unregister_ftrace_function_probe_all(char *glob)
+{
+ __unregister_ftrace_function_probe(glob, NULL, NULL, 0);
+}
+
+static LIST_HEAD(ftrace_commands);
+static DEFINE_MUTEX(ftrace_cmd_mutex);
+
+int register_ftrace_command(struct ftrace_func_command *cmd)
+{
+ struct ftrace_func_command *p;
+ int ret = 0;
+
+ mutex_lock(&ftrace_cmd_mutex);
+ list_for_each_entry(p, &ftrace_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ }
+ list_add(&cmd->list, &ftrace_commands);
+ out_unlock:
+ mutex_unlock(&ftrace_cmd_mutex);
+
+ return ret;
+}
+
+int unregister_ftrace_command(struct ftrace_func_command *cmd)
+{
+ struct ftrace_func_command *p, *n;
+ int ret = -ENODEV;
+
+ mutex_lock(&ftrace_cmd_mutex);
+ list_for_each_entry_safe(p, n, &ftrace_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = 0;
+ list_del_init(&p->list);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&ftrace_cmd_mutex);
+
+ return ret;
+}
+
+static int ftrace_process_regex(char *buff, int len, int enable)
+{
+ char *func, *command, *next = buff;
+ struct ftrace_func_command *p;
+ int ret = -EINVAL;
+
+ func = strsep(&next, ":");
+
+ if (!next) {
+ if (ftrace_match_records(func, len, enable))
+ return 0;
+ return ret;
+ }
+
+ /* command found */
+
+ command = strsep(&next, ":");
+
+ mutex_lock(&ftrace_cmd_mutex);
+ list_for_each_entry(p, &ftrace_commands, list) {
+ if (strcmp(p->name, command) == 0) {
+ ret = p->func(func, command, next, enable);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&ftrace_cmd_mutex);
+
+ return ret;
+}
+
+static ssize_t
+ftrace_regex_write(struct file *file, const char __user *ubuf,
+ size_t cnt, loff_t *ppos, int enable)
+{
+ struct ftrace_iterator *iter;
+ struct trace_parser *parser;
+ ssize_t ret, read;
+
+ if (!cnt)
+ return 0;
+
+ mutex_lock(&ftrace_regex_lock);
+
+ if (file->f_mode & FMODE_READ) {
+ struct seq_file *m = file->private_data;
+ iter = m->private;
+ } else
+ iter = file->private_data;
+
+ parser = &iter->parser;
+ read = trace_get_user(parser, ubuf, cnt, ppos);
+
+ if (read >= 0 && trace_parser_loaded(parser) &&
+ !trace_parser_cont(parser)) {
+ ret = ftrace_process_regex(parser->buffer,
+ parser->idx, enable);
+ trace_parser_clear(parser);
+ if (ret)
+ goto out_unlock;
+ }
+
+ ret = read;
+out_unlock:
+ mutex_unlock(&ftrace_regex_lock);
+
+ return ret;
+}
+
+static ssize_t
+ftrace_filter_write(struct file *file, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return ftrace_regex_write(file, ubuf, cnt, ppos, 1);
+}
+
+static ssize_t
+ftrace_notrace_write(struct file *file, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return ftrace_regex_write(file, ubuf, cnt, ppos, 0);
+}
+
+static void
+ftrace_set_regex(unsigned char *buf, int len, int reset, int enable)
+{
+ if (unlikely(ftrace_disabled))
+ return;
+
+ mutex_lock(&ftrace_regex_lock);
+ if (reset)
+ ftrace_filter_reset(enable);
+ if (buf)
+ ftrace_match_records(buf, len, enable);
+ mutex_unlock(&ftrace_regex_lock);
+}
+
+/**
+ * ftrace_set_filter - set a function to filter on in ftrace
+ * @buf - the string that holds the function filter text.
+ * @len - the length of the string.
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Filters denote which functions should be enabled when tracing is enabled.
+ * If @buf is NULL and reset is set, all functions will be enabled for tracing.
+ */
+void ftrace_set_filter(unsigned char *buf, int len, int reset)
+{
+ ftrace_set_regex(buf, len, reset, 1);
+}
+
+/**
+ * ftrace_set_notrace - set a function to not trace in ftrace
+ * @buf - the string that holds the function notrace text.
+ * @len - the length of the string.
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Notrace Filters denote which functions should not be enabled when tracing
+ * is enabled. If @buf is NULL and reset is set, all functions will be enabled
+ * for tracing.
+ */
+void ftrace_set_notrace(unsigned char *buf, int len, int reset)
+{
+ ftrace_set_regex(buf, len, reset, 0);
+}
+
+/*
+ * command line interface to allow users to set filters on boot up.
+ */
+#define FTRACE_FILTER_SIZE COMMAND_LINE_SIZE
+static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
+static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
+
+static int __init set_ftrace_notrace(char *str)
+{
+ strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_notrace=", set_ftrace_notrace);
+
+static int __init set_ftrace_filter(char *str)
+{
+ strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_filter=", set_ftrace_filter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int __init set_graph_function(char *str)
+{
+ strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_graph_filter=", set_graph_function);
+
+static void __init set_ftrace_early_graph(char *buf)
+{
+ int ret;
+ char *func;
+
+ while (buf) {
+ func = strsep(&buf, ",");
+ /* we allow only one expression at a time */
+ ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+ func);
+ if (ret)
+ printk(KERN_DEBUG "ftrace: function %s not "
+ "traceable\n", func);
+ }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static void __init set_ftrace_early_filter(char *buf, int enable)
+{
+ char *func;
+
+ while (buf) {
+ func = strsep(&buf, ",");
+ ftrace_set_regex(func, strlen(func), 0, enable);
+ }
+}
+
+static void __init set_ftrace_early_filters(void)
+{
+ if (ftrace_filter_buf[0])
+ set_ftrace_early_filter(ftrace_filter_buf, 1);
+ if (ftrace_notrace_buf[0])
+ set_ftrace_early_filter(ftrace_notrace_buf, 0);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ if (ftrace_graph_buf[0])
+ set_ftrace_early_graph(ftrace_graph_buf);
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+}
+
+static int
+ftrace_regex_release(struct inode *inode, struct file *file, int enable)
+{
+ struct seq_file *m = (struct seq_file *)file->private_data;
+ struct ftrace_iterator *iter;
+ struct trace_parser *parser;
+
+ mutex_lock(&ftrace_regex_lock);
+ if (file->f_mode & FMODE_READ) {
+ iter = m->private;
+
+ seq_release(inode, file);
+ } else
+ iter = file->private_data;
+
+ parser = &iter->parser;
+ if (trace_parser_loaded(parser)) {
+ parser->buffer[parser->idx] = 0;
+ ftrace_match_records(parser->buffer, parser->idx, enable);
+ }
+
+ mutex_lock(&ftrace_lock);
+ if (ftrace_start_up && ftrace_enabled)
+ ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+ mutex_unlock(&ftrace_lock);
+
+ trace_parser_put(parser);
+ kfree(iter);
+
+ mutex_unlock(&ftrace_regex_lock);
+ return 0;
+}
+
+static int
+ftrace_filter_release(struct inode *inode, struct file *file)
+{
+ return ftrace_regex_release(inode, file, 1);
+}
+
+static int
+ftrace_notrace_release(struct inode *inode, struct file *file)
+{
+ return ftrace_regex_release(inode, file, 0);
+}
+
+static const struct file_operations ftrace_avail_fops = {
+ .open = ftrace_avail_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static const struct file_operations ftrace_failures_fops = {
+ .open = ftrace_failures_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static const struct file_operations ftrace_filter_fops = {
+ .open = ftrace_filter_open,
+ .read = seq_read,
+ .write = ftrace_filter_write,
+ .llseek = ftrace_regex_lseek,
+ .release = ftrace_filter_release,
+};
+
+static const struct file_operations ftrace_notrace_fops = {
+ .open = ftrace_notrace_open,
+ .read = seq_read,
+ .write = ftrace_notrace_write,
+ .llseek = ftrace_regex_lseek,
+ .release = ftrace_notrace_release,
+};
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+static DEFINE_MUTEX(graph_lock);
+
+int ftrace_graph_count;
+unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+
+static void *
+__g_next(struct seq_file *m, loff_t *pos)
+{
+ if (*pos >= ftrace_graph_count)
+ return NULL;
+ return &ftrace_graph_funcs[*pos];
+}
+
+static void *
+g_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return __g_next(m, pos);
+}
+
+static void *g_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&graph_lock);
+
+ /* Nothing, tell g_show to print all functions are enabled */
+ if (!ftrace_graph_count && !*pos)
+ return (void *)1;
+
+ return __g_next(m, pos);
+}
+
+static void g_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&graph_lock);
+}
+
+static int g_show(struct seq_file *m, void *v)
+{
+ unsigned long *ptr = v;
+
+ if (!ptr)
+ return 0;
+
+ if (ptr == (unsigned long *)1) {
+ seq_printf(m, "#### all functions enabled ####\n");
+ return 0;
+ }
+
+ seq_printf(m, "%ps\n", (void *)*ptr);
+
+ return 0;
+}
+
+static const struct seq_operations ftrace_graph_seq_ops = {
+ .start = g_start,
+ .next = g_next,
+ .stop = g_stop,
+ .show = g_show,
+};
+
+static int
+ftrace_graph_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ mutex_lock(&graph_lock);
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC)) {
+ ftrace_graph_count = 0;
+ memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
+ }
+ mutex_unlock(&graph_lock);
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_open(file, &ftrace_graph_seq_ops);
+
+ return ret;
+}
+
+static int
+ftrace_graph_release(struct inode *inode, struct file *file)
+{
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+ return 0;
+}
+
+static int
+ftrace_set_func(unsigned long *array, int *idx, char *buffer)
+{
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+ int search_len;
+ int found = 0;
+ int type, not;
+ char *search;
+ bool exists;
+ int i;
+
+ if (ftrace_disabled)
+ return -ENODEV;
+
+ /* decode regex */
+ type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
+ if (not)
+ return -EINVAL;
+
+ search_len = strlen(search);
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+
+ if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+ break;
+
+ if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
+ continue;
+
+ if (ftrace_match_record(rec, search, search_len, type)) {
+ /* ensure it is not already in the array */
+ exists = false;
+ for (i = 0; i < *idx; i++)
+ if (array[i] == rec->ip) {
+ exists = true;
+ break;
+ }
+ if (!exists)
+ array[(*idx)++] = rec->ip;
+ found = 1;
+ }
+ } while_for_each_ftrace_rec();
+
+ mutex_unlock(&ftrace_lock);
+
+ return found ? 0 : -EINVAL;
+}
+
+static ssize_t
+ftrace_graph_write(struct file *file, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_parser parser;
+ ssize_t read, ret;
+
+ if (!cnt || cnt < 0)
+ return 0;
+
+ mutex_lock(&graph_lock);
+
+ if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+
+ if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
+ ret = -ENOMEM;
+ goto out_unlock;
+ }
+
+ read = trace_get_user(&parser, ubuf, cnt, ppos);
+
+ if (read >= 0 && trace_parser_loaded((&parser))) {
+ parser.buffer[parser.idx] = 0;
+
+ /* we allow only one expression at a time */
+ ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+ parser.buffer);
+ if (ret)
+ goto out_free;
+ }
+
+ ret = read;
+
+out_free:
+ trace_parser_put(&parser);
+out_unlock:
+ mutex_unlock(&graph_lock);
+
+ return ret;
+}
+
+static const struct file_operations ftrace_graph_fops = {
+ .open = ftrace_graph_open,
+ .read = seq_read,
+ .write = ftrace_graph_write,
+ .release = ftrace_graph_release,
+};
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
+{
+
+ trace_create_file("available_filter_functions", 0444,
+ d_tracer, NULL, &ftrace_avail_fops);
+
+ trace_create_file("failures", 0444,
+ d_tracer, NULL, &ftrace_failures_fops);
+
+ trace_create_file("set_ftrace_filter", 0644, d_tracer,
+ NULL, &ftrace_filter_fops);
+
+ trace_create_file("set_ftrace_notrace", 0644, d_tracer,
+ NULL, &ftrace_notrace_fops);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ trace_create_file("set_graph_function", 0444, d_tracer,
+ NULL,
+ &ftrace_graph_fops);
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+ return 0;
+}
+
+static int ftrace_process_locs(struct module *mod,
+ unsigned long *start,
+ unsigned long *end)
+{
+ unsigned long *p;
+ unsigned long addr;
+ unsigned long flags;
+
+ mutex_lock(&ftrace_lock);
+ p = start;
+ while (p < end) {
+ addr = ftrace_call_adjust(*p++);
+ /*
+ * Some architecture linkers will pad between
+ * the different mcount_loc sections of different
+ * object files to satisfy alignments.
+ * Skip any NULL pointers.
+ */
+ if (!addr)
+ continue;
+ ftrace_record_ip(addr);
+ }
+
+ /* disable interrupts to prevent kstop machine */
+ local_irq_save(flags);
+ ftrace_update_code(mod);
+ local_irq_restore(flags);
+ mutex_unlock(&ftrace_lock);
+
+ return 0;
+}
+
+#ifdef CONFIG_MODULES
+void ftrace_release_mod(struct module *mod)
+{
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+
+ if (ftrace_disabled)
+ return;
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+ if (within_module_core(rec->ip, mod)) {
+ /*
+ * rec->ip is changed in ftrace_free_rec()
+ * It should not between s and e if record was freed.
+ */
+ FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
+ ftrace_free_rec(rec);
+ }
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+}
+
+static void ftrace_init_module(struct module *mod,
+ unsigned long *start, unsigned long *end)
+{
+ if (ftrace_disabled || start == end)
+ return;
+ ftrace_process_locs(mod, start, end);
+}
+
+static int ftrace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ ftrace_init_module(mod, mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
+ break;
+ case MODULE_STATE_GOING:
+ ftrace_release_mod(mod);
+ break;
+ }
+
+ return 0;
+}
+#else
+static int ftrace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block ftrace_module_nb = {
+ .notifier_call = ftrace_module_notify,
+ .priority = 0,
+};
+
+extern unsigned long __start_mcount_loc[];
+extern unsigned long __stop_mcount_loc[];
+
+void __init ftrace_init(void)
+{
+ unsigned long count, addr, flags;
+ int ret;
+
+ /* Keep the ftrace pointer to the stub */
+ addr = (unsigned long)ftrace_stub;
+
+ local_irq_save(flags);
+ ftrace_dyn_arch_init(&addr);
+ local_irq_restore(flags);
+
+ /* ftrace_dyn_arch_init places the return code in addr */
+ if (addr)
+ goto failed;
+
+ count = __stop_mcount_loc - __start_mcount_loc;
+
+ ret = ftrace_dyn_table_alloc(count);
+ if (ret)
+ goto failed;
+
+ last_ftrace_enabled = ftrace_enabled = 1;
+
+ ret = ftrace_process_locs(NULL,
+ __start_mcount_loc,
+ __stop_mcount_loc);
+
+ ret = register_module_notifier(&ftrace_module_nb);
+ if (ret)
+ pr_warning("Failed to register trace ftrace module notifier\n");
+
+ set_ftrace_early_filters();
+
+ return;
+ failed:
+ ftrace_disabled = 1;
+}
+
+#else
+
+static int __init ftrace_nodyn_init(void)
+{
+ ftrace_enabled = 1;
+ return 0;
+}
+device_initcall(ftrace_nodyn_init);
+
+static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
+static inline void ftrace_startup_enable(int command) { }
+/* Keep as macros so we do not need to define the commands */
+# define ftrace_startup(command) do { } while (0)
+# define ftrace_shutdown(command) do { } while (0)
+# define ftrace_startup_sysctl() do { } while (0)
+# define ftrace_shutdown_sysctl() do { } while (0)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+static void clear_ftrace_swapper(void)
+{
+ struct task_struct *p;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ p = idle_task(cpu);
+ clear_tsk_trace_trace(p);
+ }
+ put_online_cpus();
+}
+
+static void set_ftrace_swapper(void)
+{
+ struct task_struct *p;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ p = idle_task(cpu);
+ set_tsk_trace_trace(p);
+ }
+ put_online_cpus();
+}
+
+static void clear_ftrace_pid(struct pid *pid)
+{
+ struct task_struct *p;
+
+ rcu_read_lock();
+ do_each_pid_task(pid, PIDTYPE_PID, p) {
+ clear_tsk_trace_trace(p);
+ } while_each_pid_task(pid, PIDTYPE_PID, p);
+ rcu_read_unlock();
+
+ put_pid(pid);
+}
+
+static void set_ftrace_pid(struct pid *pid)
+{
+ struct task_struct *p;
+
+ rcu_read_lock();
+ do_each_pid_task(pid, PIDTYPE_PID, p) {
+ set_tsk_trace_trace(p);
+ } while_each_pid_task(pid, PIDTYPE_PID, p);
+ rcu_read_unlock();
+}
+
+static void clear_ftrace_pid_task(struct pid *pid)
+{
+ if (pid == ftrace_swapper_pid)
+ clear_ftrace_swapper();
+ else
+ clear_ftrace_pid(pid);
+}
+
+static void set_ftrace_pid_task(struct pid *pid)
+{
+ if (pid == ftrace_swapper_pid)
+ set_ftrace_swapper();
+ else
+ set_ftrace_pid(pid);
+}
+
+static int ftrace_pid_add(int p)
+{
+ struct pid *pid;
+ struct ftrace_pid *fpid;
+ int ret = -EINVAL;
+
+ mutex_lock(&ftrace_lock);
+
+ if (!p)
+ pid = ftrace_swapper_pid;
+ else
+ pid = find_get_pid(p);
+
+ if (!pid)
+ goto out;
+
+ ret = 0;
+
+ list_for_each_entry(fpid, &ftrace_pids, list)
+ if (fpid->pid == pid)
+ goto out_put;
+
+ ret = -ENOMEM;
+
+ fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
+ if (!fpid)
+ goto out_put;
+
+ list_add(&fpid->list, &ftrace_pids);
+ fpid->pid = pid;
+
+ set_ftrace_pid_task(pid);
+
+ ftrace_update_pid_func();
+ ftrace_startup_enable(0);
+
+ mutex_unlock(&ftrace_lock);
+ return 0;
+
+out_put:
+ if (pid != ftrace_swapper_pid)
+ put_pid(pid);
+
+out:
+ mutex_unlock(&ftrace_lock);
+ return ret;
+}
+
+static void ftrace_pid_reset(void)
+{
+ struct ftrace_pid *fpid, *safe;
+
+ mutex_lock(&ftrace_lock);
+ list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
+ struct pid *pid = fpid->pid;
+
+ clear_ftrace_pid_task(pid);
+
+ list_del(&fpid->list);
+ kfree(fpid);
+ }
+
+ ftrace_update_pid_func();
+ ftrace_startup_enable(0);
+
+ mutex_unlock(&ftrace_lock);
+}
+
+static void *fpid_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&ftrace_lock);
+
+ if (list_empty(&ftrace_pids) && (!*pos))
+ return (void *) 1;
+
+ return seq_list_start(&ftrace_pids, *pos);
+}
+
+static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ if (v == (void *)1)
+ return NULL;
+
+ return seq_list_next(v, &ftrace_pids, pos);
+}
+
+static void fpid_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&ftrace_lock);
+}
+
+static int fpid_show(struct seq_file *m, void *v)
+{
+ const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
+
+ if (v == (void *)1) {
+ seq_printf(m, "no pid\n");
+ return 0;
+ }
+
+ if (fpid->pid == ftrace_swapper_pid)
+ seq_printf(m, "swapper tasks\n");
+ else
+ seq_printf(m, "%u\n", pid_vnr(fpid->pid));
+
+ return 0;
+}
+
+static const struct seq_operations ftrace_pid_sops = {
+ .start = fpid_start,
+ .next = fpid_next,
+ .stop = fpid_stop,
+ .show = fpid_show,
+};
+
+static int
+ftrace_pid_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ ftrace_pid_reset();
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_open(file, &ftrace_pid_sops);
+
+ return ret;
+}
+
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64], *tmp;
+ long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ /*
+ * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
+ * to clean the filter quietly.
+ */
+ tmp = strstrip(buf);
+ if (strlen(tmp) == 0)
+ return 1;
+
+ ret = strict_strtol(tmp, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = ftrace_pid_add(val);
+
+ return ret ? ret : cnt;
+}
+
+static int
+ftrace_pid_release(struct inode *inode, struct file *file)
+{
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+
+ return 0;
+}
+
+static const struct file_operations ftrace_pid_fops = {
+ .open = ftrace_pid_open,
+ .write = ftrace_pid_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = ftrace_pid_release,
+};
+
+static __init int ftrace_init_debugfs(void)
+{
+ struct dentry *d_tracer;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ ftrace_init_dyn_debugfs(d_tracer);
+
+ trace_create_file("set_ftrace_pid", 0644, d_tracer,
+ NULL, &ftrace_pid_fops);
+
+ ftrace_profile_debugfs(d_tracer);
+
+ return 0;
+}
+fs_initcall(ftrace_init_debugfs);
+
+/**
+ * ftrace_kill - kill ftrace
+ *
+ * This function should be used by panic code. It stops ftrace
+ * but in a not so nice way. If you need to simply kill ftrace
+ * from a non-atomic section, use ftrace_kill.
+ */
+void ftrace_kill(void)
+{
+ ftrace_disabled = 1;
+ ftrace_enabled = 0;
+ clear_ftrace_function();
+}
+
+/**
+ * register_ftrace_function - register a function for profiling
+ * @ops - ops structure that holds the function for profiling.
+ *
+ * Register a function to be called by all functions in the
+ * kernel.
+ *
+ * Note: @ops->func and all the functions it calls must be labeled
+ * with "notrace", otherwise it will go into a
+ * recursive loop.
+ */
+int register_ftrace_function(struct ftrace_ops *ops)
+{
+ int ret;
+
+ if (unlikely(ftrace_disabled))
+ return -1;
+
+ mutex_lock(&ftrace_lock);
+
+ ret = __register_ftrace_function(ops);
+ ftrace_startup(0);
+
+ mutex_unlock(&ftrace_lock);
+ return ret;
+}
+
+/**
+ * unregister_ftrace_function - unregister a function for profiling.
+ * @ops - ops structure that holds the function to unregister
+ *
+ * Unregister a function that was added to be called by ftrace profiling.
+ */
+int unregister_ftrace_function(struct ftrace_ops *ops)
+{
+ int ret;
+
+ mutex_lock(&ftrace_lock);
+ ret = __unregister_ftrace_function(ops);
+ ftrace_shutdown(0);
+ mutex_unlock(&ftrace_lock);
+
+ return ret;
+}
+
+int
+ftrace_enable_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ mutex_lock(&ftrace_lock);
+
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
+ goto out;
+
+ last_ftrace_enabled = !!ftrace_enabled;
+
+ if (ftrace_enabled) {
+
+ ftrace_startup_sysctl();
+
+ /* we are starting ftrace again */
+ if (ftrace_list != &ftrace_list_end) {
+ if (ftrace_list->next == &ftrace_list_end)
+ ftrace_trace_function = ftrace_list->func;
+ else
+ ftrace_trace_function = ftrace_list_func;
+ }
+
+ } else {
+ /* stopping ftrace calls (just send to ftrace_stub) */
+ ftrace_trace_function = ftrace_stub;
+
+ ftrace_shutdown_sysctl();
+ }
+
+ out:
+ mutex_unlock(&ftrace_lock);
+ return ret;
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+static int ftrace_graph_active;
+static struct notifier_block ftrace_suspend_notifier;
+
+int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
+{
+ return 0;
+}
+
+/* The callbacks that hook a function */
+trace_func_graph_ret_t ftrace_graph_return =
+ (trace_func_graph_ret_t)ftrace_stub;
+trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+
+/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
+static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
+{
+ int i;
+ int ret = 0;
+ unsigned long flags;
+ int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
+ struct task_struct *g, *t;
+
+ for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
+ ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH
+ * sizeof(struct ftrace_ret_stack),
+ GFP_KERNEL);
+ if (!ret_stack_list[i]) {
+ start = 0;
+ end = i;
+ ret = -ENOMEM;
+ goto free;
+ }
+ }
+
+ read_lock_irqsave(&tasklist_lock, flags);
+ do_each_thread(g, t) {
+ if (start == end) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
+
+ if (t->ret_stack == NULL) {
+ atomic_set(&t->tracing_graph_pause, 0);
+ atomic_set(&t->trace_overrun, 0);
+ t->curr_ret_stack = -1;
+ /* Make sure the tasks see the -1 first: */
+ smp_wmb();
+ t->ret_stack = ret_stack_list[start++];
+ }
+ } while_each_thread(g, t);
+
+unlock:
+ read_unlock_irqrestore(&tasklist_lock, flags);
+free:
+ for (i = start; i < end; i++)
+ kfree(ret_stack_list[i]);
+ return ret;
+}
+
+static void
+ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
+ struct task_struct *next)
+{
+ unsigned long long timestamp;
+ int index;
+
+ /*
+ * Does the user want to count the time a function was asleep.
+ * If so, do not update the time stamps.
+ */
+ if (trace_flags & TRACE_ITER_SLEEP_TIME)
+ return;
+
+ timestamp = trace_clock_local();
+
+ prev->ftrace_timestamp = timestamp;
+
+ /* only process tasks that we timestamped */
+ if (!next->ftrace_timestamp)
+ return;
+
+ /*
+ * Update all the counters in next to make up for the
+ * time next was sleeping.
+ */
+ timestamp -= next->ftrace_timestamp;
+
+ for (index = next->curr_ret_stack; index >= 0; index--)
+ next->ret_stack[index].calltime += timestamp;
+}
+
+/* Allocate a return stack for each task */
+static int start_graph_tracing(void)
+{
+ struct ftrace_ret_stack **ret_stack_list;
+ int ret, cpu;
+
+ ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
+ sizeof(struct ftrace_ret_stack *),
+ GFP_KERNEL);
+
+ if (!ret_stack_list)
+ return -ENOMEM;
+
+ /* The cpu_boot init_task->ret_stack will never be freed */
+ for_each_online_cpu(cpu) {
+ if (!idle_task(cpu)->ret_stack)
+ ftrace_graph_init_task(idle_task(cpu));
+ }
+
+ do {
+ ret = alloc_retstack_tasklist(ret_stack_list);
+ } while (ret == -EAGAIN);
+
+ if (!ret) {
+ ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+ if (ret)
+ pr_info("ftrace_graph: Couldn't activate tracepoint"
+ " probe to kernel_sched_switch\n");
+ }
+
+ kfree(ret_stack_list);
+ return ret;
+}
+
+/*
+ * Hibernation protection.
+ * The state of the current task is too much unstable during
+ * suspend/restore to disk. We want to protect against that.
+ */
+static int
+ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
+ void *unused)
+{
+ switch (state) {
+ case PM_HIBERNATION_PREPARE:
+ pause_graph_tracing();
+ break;
+
+ case PM_POST_HIBERNATION:
+ unpause_graph_tracing();
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+int register_ftrace_graph(trace_func_graph_ret_t retfunc,
+ trace_func_graph_ent_t entryfunc)
+{
+ int ret = 0;
+
+ mutex_lock(&ftrace_lock);
+
+ /* we currently allow only one tracer registered at a time */
+ if (ftrace_graph_active) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
+ register_pm_notifier(&ftrace_suspend_notifier);
+
+ ftrace_graph_active++;
+ ret = start_graph_tracing();
+ if (ret) {
+ ftrace_graph_active--;
+ goto out;
+ }
+
+ ftrace_graph_return = retfunc;
+ ftrace_graph_entry = entryfunc;
+
+ ftrace_startup(FTRACE_START_FUNC_RET);
+
+out:
+ mutex_unlock(&ftrace_lock);
+ return ret;
+}
+
+void unregister_ftrace_graph(void)
+{
+ mutex_lock(&ftrace_lock);
+
+ if (unlikely(!ftrace_graph_active))
+ goto out;
+
+ ftrace_graph_active--;
+ unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
+ ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
+ ftrace_graph_entry = ftrace_graph_entry_stub;
+ ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+ unregister_pm_notifier(&ftrace_suspend_notifier);
+
+ out:
+ mutex_unlock(&ftrace_lock);
+}
+
+/* Allocate a return stack for newly created task */
+void ftrace_graph_init_task(struct task_struct *t)
+{
+ /* Make sure we do not use the parent ret_stack */
+ t->ret_stack = NULL;
+ t->curr_ret_stack = -1;
+
+ if (ftrace_graph_active) {
+ struct ftrace_ret_stack *ret_stack;
+
+ ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+ * sizeof(struct ftrace_ret_stack),
+ GFP_KERNEL);
+ if (!ret_stack)
+ return;
+ atomic_set(&t->tracing_graph_pause, 0);
+ atomic_set(&t->trace_overrun, 0);
+ t->ftrace_timestamp = 0;
+ /* make curr_ret_stack visable before we add the ret_stack */
+ smp_wmb();
+ t->ret_stack = ret_stack;
+ }
+}
+
+void ftrace_graph_exit_task(struct task_struct *t)
+{
+ struct ftrace_ret_stack *ret_stack = t->ret_stack;
+
+ t->ret_stack = NULL;
+ /* NULL must become visible to IRQs before we free it: */
+ barrier();
+
+ kfree(ret_stack);
+}
+
+void ftrace_graph_stop(void)
+{
+ ftrace_stop();
+}
+#endif
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
new file mode 100644
index 00000000000..a91da69f153
--- /dev/null
+++ b/kernel/trace/kmemtrace.c
@@ -0,0 +1,511 @@
+/*
+ * Memory allocator tracing
+ *
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+#include <linux/tracepoint.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/dcache.h>
+#include <linux/fs.h>
+
+#include <linux/kmemtrace.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+/* Select an alternative, minimalistic output than the original one */
+#define TRACE_KMEM_OPT_MINIMAL 0x1
+
+static struct tracer_opt kmem_opts[] = {
+ /* Default disable the minimalistic output */
+ { TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
+ { }
+};
+
+static struct tracer_flags kmem_tracer_flags = {
+ .val = 0,
+ .opts = kmem_opts
+};
+
+static struct trace_array *kmemtrace_array;
+
+/* Trace allocations */
+static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
+ unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node)
+{
+ struct ftrace_event_call *call = &event_kmem_alloc;
+ struct trace_array *tr = kmemtrace_array;
+ struct kmemtrace_alloc_entry *entry;
+ struct ring_buffer_event *event;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+
+ entry->ent.type = TRACE_KMEM_ALLOC;
+ entry->type_id = type_id;
+ entry->call_site = call_site;
+ entry->ptr = ptr;
+ entry->bytes_req = bytes_req;
+ entry->bytes_alloc = bytes_alloc;
+ entry->gfp_flags = gfp_flags;
+ entry->node = node;
+
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
+
+ trace_wake_up();
+}
+
+static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
+ unsigned long call_site,
+ const void *ptr)
+{
+ struct ftrace_event_call *call = &event_kmem_free;
+ struct trace_array *tr = kmemtrace_array;
+ struct kmemtrace_free_entry *entry;
+ struct ring_buffer_event *event;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+
+ entry->ent.type = TRACE_KMEM_FREE;
+ entry->type_id = type_id;
+ entry->call_site = call_site;
+ entry->ptr = ptr;
+
+ if (!filter_check_discard(call, entry, tr->buffer, event))
+ ring_buffer_unlock_commit(tr->buffer, event);
+
+ trace_wake_up();
+}
+
+static void kmemtrace_kmalloc(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmalloc_node(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+{
+ kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
+}
+
+static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+{
+ kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
+}
+
+static int kmemtrace_start_probes(void)
+{
+ int err;
+
+ err = register_trace_kmalloc(kmemtrace_kmalloc);
+ if (err)
+ return err;
+ err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+ if (err)
+ return err;
+ err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+ if (err)
+ return err;
+ err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+ if (err)
+ return err;
+ err = register_trace_kfree(kmemtrace_kfree);
+ if (err)
+ return err;
+ err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+
+ return err;
+}
+
+static void kmemtrace_stop_probes(void)
+{
+ unregister_trace_kmalloc(kmemtrace_kmalloc);
+ unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+ unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
+ unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+ unregister_trace_kfree(kmemtrace_kfree);
+ unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+}
+
+static int kmem_trace_init(struct trace_array *tr)
+{
+ kmemtrace_array = tr;
+
+ tracing_reset_online_cpus(tr);
+
+ kmemtrace_start_probes();
+
+ return 0;
+}
+
+static void kmem_trace_reset(struct trace_array *tr)
+{
+ kmemtrace_stop_probes();
+}
+
+static void kmemtrace_headers(struct seq_file *s)
+{
+ /* Don't need headers for the original kmemtrace output */
+ if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+ return;
+
+ seq_printf(s, "#\n");
+ seq_printf(s, "# ALLOC TYPE REQ GIVEN FLAGS "
+ " POINTER NODE CALLER\n");
+ seq_printf(s, "# FREE | | | | "
+ " | | | |\n");
+ seq_printf(s, "# |\n\n");
+}
+
+/*
+ * The following functions give the original output from kmemtrace,
+ * plus the origin CPU, since reordering occurs in-kernel now.
+ */
+
+#define KMEMTRACE_USER_ALLOC 0
+#define KMEMTRACE_USER_FREE 1
+
+struct kmemtrace_user_event {
+ u8 event_id;
+ u8 type_id;
+ u16 event_size;
+ u32 cpu;
+ u64 timestamp;
+ unsigned long call_site;
+ unsigned long ptr;
+};
+
+struct kmemtrace_user_event_alloc {
+ size_t bytes_req;
+ size_t bytes_alloc;
+ unsigned gfp_flags;
+ int node;
+};
+
+static enum print_line_t
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
+{
+ struct trace_seq *s = &iter->seq;
+ struct kmemtrace_alloc_entry *entry;
+ int ret;
+
+ trace_assign_type(entry, iter->ent);
+
+ ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
+ "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+ entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
+ (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
+ (unsigned long)entry->gfp_flags, entry->node);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free(struct trace_iterator *iter, int flags)
+{
+ struct trace_seq *s = &iter->seq;
+ struct kmemtrace_free_entry *entry;
+ int ret;
+
+ trace_assign_type(entry, iter->ent);
+
+ ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
+ entry->type_id, (void *)entry->call_site,
+ (unsigned long)entry->ptr);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+{
+ struct trace_seq *s = &iter->seq;
+ struct kmemtrace_alloc_entry *entry;
+ struct kmemtrace_user_event *ev;
+ struct kmemtrace_user_event_alloc *ev_alloc;
+
+ trace_assign_type(entry, iter->ent);
+
+ ev = trace_seq_reserve(s, sizeof(*ev));
+ if (!ev)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ev->event_id = KMEMTRACE_USER_ALLOC;
+ ev->type_id = entry->type_id;
+ ev->event_size = sizeof(*ev) + sizeof(*ev_alloc);
+ ev->cpu = iter->cpu;
+ ev->timestamp = iter->ts;
+ ev->call_site = entry->call_site;
+ ev->ptr = (unsigned long)entry->ptr;
+
+ ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc));
+ if (!ev_alloc)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ev_alloc->bytes_req = entry->bytes_req;
+ ev_alloc->bytes_alloc = entry->bytes_alloc;
+ ev_alloc->gfp_flags = entry->gfp_flags;
+ ev_alloc->node = entry->node;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
+{
+ struct trace_seq *s = &iter->seq;
+ struct kmemtrace_free_entry *entry;
+ struct kmemtrace_user_event *ev;
+
+ trace_assign_type(entry, iter->ent);
+
+ ev = trace_seq_reserve(s, sizeof(*ev));
+ if (!ev)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ev->event_id = KMEMTRACE_USER_FREE;
+ ev->type_id = entry->type_id;
+ ev->event_size = sizeof(*ev);
+ ev->cpu = iter->cpu;
+ ev->timestamp = iter->ts;
+ ev->call_site = entry->call_site;
+ ev->ptr = (unsigned long)entry->ptr;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+/* The two other following provide a more minimalistic output */
+static enum print_line_t
+kmemtrace_print_alloc_compress(struct trace_iterator *iter)
+{
+ struct kmemtrace_alloc_entry *entry;
+ struct trace_seq *s = &iter->seq;
+ int ret;
+
+ trace_assign_type(entry, iter->ent);
+
+ /* Alloc entry */
+ ret = trace_seq_printf(s, " + ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Type */
+ switch (entry->type_id) {
+ case KMEMTRACE_TYPE_KMALLOC:
+ ret = trace_seq_printf(s, "K ");
+ break;
+ case KMEMTRACE_TYPE_CACHE:
+ ret = trace_seq_printf(s, "C ");
+ break;
+ case KMEMTRACE_TYPE_PAGES:
+ ret = trace_seq_printf(s, "P ");
+ break;
+ default:
+ ret = trace_seq_printf(s, "? ");
+ }
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Requested */
+ ret = trace_seq_printf(s, "%4zu ", entry->bytes_req);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Allocated */
+ ret = trace_seq_printf(s, "%4zu ", entry->bytes_alloc);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Flags
+ * TODO: would be better to see the name of the GFP flag names
+ */
+ ret = trace_seq_printf(s, "%08x ", entry->gfp_flags);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Pointer to allocated */
+ ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Node and call site*/
+ ret = trace_seq_printf(s, "%4d %pf\n", entry->node,
+ (void *)entry->call_site);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free_compress(struct trace_iterator *iter)
+{
+ struct kmemtrace_free_entry *entry;
+ struct trace_seq *s = &iter->seq;
+ int ret;
+
+ trace_assign_type(entry, iter->ent);
+
+ /* Free entry */
+ ret = trace_seq_printf(s, " - ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Type */
+ switch (entry->type_id) {
+ case KMEMTRACE_TYPE_KMALLOC:
+ ret = trace_seq_printf(s, "K ");
+ break;
+ case KMEMTRACE_TYPE_CACHE:
+ ret = trace_seq_printf(s, "C ");
+ break;
+ case KMEMTRACE_TYPE_PAGES:
+ ret = trace_seq_printf(s, "P ");
+ break;
+ default:
+ ret = trace_seq_printf(s, "? ");
+ }
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Skip requested/allocated/flags */
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Pointer to allocated */
+ ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Skip node and print call site*/
+ ret = trace_seq_printf(s, " %pf\n", (void *)entry->call_site);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+
+ if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+ return TRACE_TYPE_UNHANDLED;
+
+ switch (entry->type) {
+ case TRACE_KMEM_ALLOC:
+ return kmemtrace_print_alloc_compress(iter);
+ case TRACE_KMEM_FREE:
+ return kmemtrace_print_free_compress(iter);
+ default:
+ return TRACE_TYPE_UNHANDLED;
+ }
+}
+
+static struct trace_event kmem_trace_alloc = {
+ .type = TRACE_KMEM_ALLOC,
+ .trace = kmemtrace_print_alloc,
+ .binary = kmemtrace_print_alloc_user,
+};
+
+static struct trace_event kmem_trace_free = {
+ .type = TRACE_KMEM_FREE,
+ .trace = kmemtrace_print_free,
+ .binary = kmemtrace_print_free_user,
+};
+
+static struct tracer kmem_tracer __read_mostly = {
+ .name = "kmemtrace",
+ .init = kmem_trace_init,
+ .reset = kmem_trace_reset,
+ .print_line = kmemtrace_print_line,
+ .print_header = kmemtrace_headers,
+ .flags = &kmem_tracer_flags
+};
+
+void kmemtrace_init(void)
+{
+ /* earliest opportunity to start kmem tracing */
+}
+
+static int __init init_kmem_tracer(void)
+{
+ if (!register_ftrace_event(&kmem_trace_alloc)) {
+ pr_warning("Warning: could not register kmem events\n");
+ return 1;
+ }
+
+ if (!register_ftrace_event(&kmem_trace_free)) {
+ pr_warning("Warning: could not register kmem events\n");
+ return 1;
+ }
+
+ if (register_tracer(&kmem_tracer) != 0) {
+ pr_warning("Warning: could not register the kmem tracer\n");
+ return 1;
+ }
+
+ return 0;
+}
+device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
new file mode 100644
index 00000000000..9f4f565b01e
--- /dev/null
+++ b/kernel/trace/power-traces.c
@@ -0,0 +1,18 @@
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
new file mode 100644
index 00000000000..54191d6ed19
--- /dev/null
+++ b/kernel/trace/ring_buffer.c
@@ -0,0 +1,3888 @@
+/*
+ * Generic ring buffer
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/trace_clock.h>
+#include <linux/ftrace_irq.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/hardirq.h>
+#include <linux/kmemcheck.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/list.h>
+#include <linux/cpu.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+/*
+ * The ring buffer header is special. We must manually up keep it.
+ */
+int ring_buffer_print_entry_header(struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_seq_printf(s, "# compressed entry header\n");
+ ret = trace_seq_printf(s, "\ttype_len : 5 bits\n");
+ ret = trace_seq_printf(s, "\ttime_delta : 27 bits\n");
+ ret = trace_seq_printf(s, "\tarray : 32 bits\n");
+ ret = trace_seq_printf(s, "\n");
+ ret = trace_seq_printf(s, "\tpadding : type == %d\n",
+ RINGBUF_TYPE_PADDING);
+ ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
+ RINGBUF_TYPE_TIME_EXTEND);
+ ret = trace_seq_printf(s, "\tdata max type_len == %d\n",
+ RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+
+ return ret;
+}
+
+/*
+ * The ring buffer is made up of a list of pages. A separate list of pages is
+ * allocated for each CPU. A writer may only write to a buffer that is
+ * associated with the CPU it is currently executing on. A reader may read
+ * from any per cpu buffer.
+ *
+ * The reader is special. For each per cpu buffer, the reader has its own
+ * reader page. When a reader has read the entire reader page, this reader
+ * page is swapped with another page in the ring buffer.
+ *
+ * Now, as long as the writer is off the reader page, the reader can do what
+ * ever it wants with that page. The writer will never write to that page
+ * again (as long as it is out of the ring buffer).
+ *
+ * Here's some silly ASCII art.
+ *
+ * +------+
+ * |reader| RING BUFFER
+ * |page |
+ * +------+ +---+ +---+ +---+
+ * | |-->| |-->| |
+ * +---+ +---+ +---+
+ * ^ |
+ * | |
+ * +---------------+
+ *
+ *
+ * +------+
+ * |reader| RING BUFFER
+ * |page |------------------v
+ * +------+ +---+ +---+ +---+
+ * | |-->| |-->| |
+ * +---+ +---+ +---+
+ * ^ |
+ * | |
+ * +---------------+
+ *
+ *
+ * +------+
+ * |reader| RING BUFFER
+ * |page |------------------v
+ * +------+ +---+ +---+ +---+
+ * ^ | |-->| |-->| |
+ * | +---+ +---+ +---+
+ * | |
+ * | |
+ * +------------------------------+
+ *
+ *
+ * +------+
+ * |buffer| RING BUFFER
+ * |page |------------------v
+ * +------+ +---+ +---+ +---+
+ * ^ | | | |-->| |
+ * | New +---+ +---+ +---+
+ * | Reader------^ |
+ * | page |
+ * +------------------------------+
+ *
+ *
+ * After we make this swap, the reader can hand this page off to the splice
+ * code and be done with it. It can even allocate a new page if it needs to
+ * and swap that into the ring buffer.
+ *
+ * We will be using cmpxchg soon to make all this lockless.
+ *
+ */
+
+/*
+ * A fast way to enable or disable all ring buffers is to
+ * call tracing_on or tracing_off. Turning off the ring buffers
+ * prevents all ring buffers from being recorded to.
+ * Turning this switch on, makes it OK to write to the
+ * ring buffer, if the ring buffer is enabled itself.
+ *
+ * There's three layers that must be on in order to write
+ * to the ring buffer.
+ *
+ * 1) This global flag must be set.
+ * 2) The ring buffer must be enabled for recording.
+ * 3) The per cpu buffer must be enabled for recording.
+ *
+ * In case of an anomaly, this global flag has a bit set that
+ * will permantly disable all ring buffers.
+ */
+
+/*
+ * Global flag to disable all recording to ring buffers
+ * This has two bits: ON, DISABLED
+ *
+ * ON DISABLED
+ * ---- ----------
+ * 0 0 : ring buffers are off
+ * 1 0 : ring buffers are on
+ * X 1 : ring buffers are permanently disabled
+ */
+
+enum {
+ RB_BUFFERS_ON_BIT = 0,
+ RB_BUFFERS_DISABLED_BIT = 1,
+};
+
+enum {
+ RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT,
+ RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT,
+};
+
+static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
+
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
+
+/**
+ * tracing_on - enable all tracing buffers
+ *
+ * This function enables all tracing buffers that may have been
+ * disabled with tracing_off.
+ */
+void tracing_on(void)
+{
+ set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
+}
+EXPORT_SYMBOL_GPL(tracing_on);
+
+/**
+ * tracing_off - turn off all tracing buffers
+ *
+ * This function stops all tracing buffers from recording data.
+ * It does not disable any overhead the tracers themselves may
+ * be causing. This function simply causes all recording to
+ * the ring buffers to fail.
+ */
+void tracing_off(void)
+{
+ clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
+}
+EXPORT_SYMBOL_GPL(tracing_off);
+
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanently.
+ */
+void tracing_off_permanent(void)
+{
+ set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
+}
+
+/**
+ * tracing_is_on - show state of ring buffers enabled
+ */
+int tracing_is_on(void)
+{
+ return ring_buffer_flags == RB_BUFFERS_ON;
+}
+EXPORT_SYMBOL_GPL(tracing_is_on);
+
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
+#define RB_ALIGNMENT 4U
+#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+#define RB_EVNT_MIN_SIZE 8U /* two 32bit words */
+
+/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
+#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
+
+enum {
+ RB_LEN_TIME_EXTEND = 8,
+ RB_LEN_TIME_STAMP = 16,
+};
+
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+ return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
+}
+
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+ /* padding has a NULL time_delta */
+ event->type_len = RINGBUF_TYPE_PADDING;
+ event->time_delta = 0;
+}
+
+static unsigned
+rb_event_data_length(struct ring_buffer_event *event)
+{
+ unsigned length;
+
+ if (event->type_len)
+ length = event->type_len * RB_ALIGNMENT;
+ else
+ length = event->array[0];
+ return length + RB_EVNT_HDR_SIZE;
+}
+
+/* inline for ring buffer fast paths */
+static unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ if (rb_null_event(event))
+ /* undefined */
+ return -1;
+ return event->array[0] + RB_EVNT_HDR_SIZE;
+
+ case RINGBUF_TYPE_TIME_EXTEND:
+ return RB_LEN_TIME_EXTEND;
+
+ case RINGBUF_TYPE_TIME_STAMP:
+ return RB_LEN_TIME_STAMP;
+
+ case RINGBUF_TYPE_DATA:
+ return rb_event_data_length(event);
+ default:
+ BUG();
+ }
+ /* not hit */
+ return 0;
+}
+
+/**
+ * ring_buffer_event_length - return the length of the event
+ * @event: the event to get the length of
+ */
+unsigned ring_buffer_event_length(struct ring_buffer_event *event)
+{
+ unsigned length = rb_event_length(event);
+ if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+ return length;
+ length -= RB_EVNT_HDR_SIZE;
+ if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
+ length -= sizeof(event->array[0]);
+ return length;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_length);
+
+/* inline for ring buffer fast paths */
+static void *
+rb_event_data(struct ring_buffer_event *event)
+{
+ BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+ /* If length is in len field, then array[0] has the data */
+ if (event->type_len)
+ return (void *)&event->array[0];
+ /* Otherwise length is in array[0] and array[1] has the data */
+ return (void *)&event->array[1];
+}
+
+/**
+ * ring_buffer_event_data - return the data of the event
+ * @event: the event to get the data from
+ */
+void *ring_buffer_event_data(struct ring_buffer_event *event)
+{
+ return rb_event_data(event);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_data);
+
+#define for_each_buffer_cpu(buffer, cpu) \
+ for_each_cpu(cpu, buffer->cpumask)
+
+#define TS_SHIFT 27
+#define TS_MASK ((1ULL << TS_SHIFT) - 1)
+#define TS_DELTA_TEST (~TS_MASK)
+
+struct buffer_data_page {
+ u64 time_stamp; /* page time stamp */
+ local_t commit; /* write committed index */
+ unsigned char data[]; /* data of buffer page */
+};
+
+/*
+ * Note, the buffer_page list must be first. The buffer pages
+ * are allocated in cache lines, which means that each buffer
+ * page will be at the beginning of a cache line, and thus
+ * the least significant bits will be zero. We use this to
+ * add flags in the list struct pointers, to make the ring buffer
+ * lockless.
+ */
+struct buffer_page {
+ struct list_head list; /* list of buffer pages */
+ local_t write; /* index for next write */
+ unsigned read; /* index for next read */
+ local_t entries; /* entries on this page */
+ struct buffer_data_page *page; /* Actual data page */
+};
+
+/*
+ * The buffer page counters, write and entries, must be reset
+ * atomically when crossing page boundaries. To synchronize this
+ * update, two counters are inserted into the number. One is
+ * the actual counter for the write position or count on the page.
+ *
+ * The other is a counter of updaters. Before an update happens
+ * the update partition of the counter is incremented. This will
+ * allow the updater to update the counter atomically.
+ *
+ * The counter is 20 bits, and the state data is 12.
+ */
+#define RB_WRITE_MASK 0xfffff
+#define RB_WRITE_INTCNT (1 << 20)
+
+static void rb_init_page(struct buffer_data_page *bpage)
+{
+ local_set(&bpage->commit, 0);
+}
+
+/**
+ * ring_buffer_page_len - the size of data on the page.
+ * @page: The page to read
+ *
+ * Returns the amount of data on the page, including buffer page header.
+ */
+size_t ring_buffer_page_len(void *page)
+{
+ return local_read(&((struct buffer_data_page *)page)->commit)
+ + BUF_PAGE_HDR_SIZE;
+}
+
+/*
+ * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
+ * this issue out.
+ */
+static void free_buffer_page(struct buffer_page *bpage)
+{
+ free_page((unsigned long)bpage->page);
+ kfree(bpage);
+}
+
+/*
+ * We need to fit the time_stamp delta into 27 bits.
+ */
+static inline int test_time_stamp(u64 delta)
+{
+ if (delta & TS_DELTA_TEST)
+ return 1;
+ return 0;
+}
+
+#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
+
+/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
+#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
+
+/* Max number of timestamps that can fit on a page */
+#define RB_TIMESTAMPS_PER_PAGE (BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+ struct buffer_data_page field;
+ int ret;
+
+ ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+ "offset:0;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)sizeof(field.time_stamp),
+ (unsigned int)is_signed_type(u64));
+
+ ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ (unsigned int)sizeof(field.commit),
+ (unsigned int)is_signed_type(long));
+
+ ret = trace_seq_printf(s, "\tfield: char data;\t"
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)offsetof(typeof(field), data),
+ (unsigned int)BUF_PAGE_SIZE,
+ (unsigned int)is_signed_type(char));
+
+ return ret;
+}
+
+/*
+ * head_page == tail_page && head == tail then buffer is empty.
+ */
+struct ring_buffer_per_cpu {
+ int cpu;
+ struct ring_buffer *buffer;
+ spinlock_t reader_lock; /* serialize readers */
+ arch_spinlock_t lock;
+ struct lock_class_key lock_key;
+ struct list_head *pages;
+ struct buffer_page *head_page; /* read from head */
+ struct buffer_page *tail_page; /* write to tail */
+ struct buffer_page *commit_page; /* committed pages */
+ struct buffer_page *reader_page;
+ local_t commit_overrun;
+ local_t overrun;
+ local_t entries;
+ local_t committing;
+ local_t commits;
+ unsigned long read;
+ u64 write_stamp;
+ u64 read_stamp;
+ atomic_t record_disabled;
+};
+
+struct ring_buffer {
+ unsigned pages;
+ unsigned flags;
+ int cpus;
+ atomic_t record_disabled;
+ cpumask_var_t cpumask;
+
+ struct lock_class_key *reader_lock_key;
+
+ struct mutex mutex;
+
+ struct ring_buffer_per_cpu **buffers;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ struct notifier_block cpu_notify;
+#endif
+ u64 (*clock)(void);
+};
+
+struct ring_buffer_iter {
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long head;
+ struct buffer_page *head_page;
+ struct buffer_page *cache_reader_page;
+ unsigned long cache_read;
+ u64 read_stamp;
+};
+
+/* buffer may be either ring_buffer or ring_buffer_per_cpu */
+#define RB_WARN_ON(b, cond) \
+ ({ \
+ int _____ret = unlikely(cond); \
+ if (_____ret) { \
+ if (__same_type(*(b), struct ring_buffer_per_cpu)) { \
+ struct ring_buffer_per_cpu *__b = \
+ (void *)b; \
+ atomic_inc(&__b->buffer->record_disabled); \
+ } else \
+ atomic_inc(&b->record_disabled); \
+ WARN_ON(1); \
+ } \
+ _____ret; \
+ })
+
+/* Up this if you want to test the TIME_EXTENTS and normalization */
+#define DEBUG_SHIFT 0
+
+static inline u64 rb_time_stamp(struct ring_buffer *buffer)
+{
+ /* shift to debug/test normalization and TIME_EXTENTS */
+ return buffer->clock() << DEBUG_SHIFT;
+}
+
+u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
+{
+ u64 time;
+
+ preempt_disable_notrace();
+ time = rb_time_stamp(buffer);
+ preempt_enable_no_resched_notrace();
+
+ return time;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
+
+void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
+ int cpu, u64 *ts)
+{
+ /* Just stupid testing the normalize function and deltas */
+ *ts >>= DEBUG_SHIFT;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
+
+/*
+ * Making the ring buffer lockless makes things tricky.
+ * Although writes only happen on the CPU that they are on,
+ * and they only need to worry about interrupts. Reads can
+ * happen on any CPU.
+ *
+ * The reader page is always off the ring buffer, but when the
+ * reader finishes with a page, it needs to swap its page with
+ * a new one from the buffer. The reader needs to take from
+ * the head (writes go to the tail). But if a writer is in overwrite
+ * mode and wraps, it must push the head page forward.
+ *
+ * Here lies the problem.
+ *
+ * The reader must be careful to replace only the head page, and
+ * not another one. As described at the top of the file in the
+ * ASCII art, the reader sets its old page to point to the next
+ * page after head. It then sets the page after head to point to
+ * the old reader page. But if the writer moves the head page
+ * during this operation, the reader could end up with the tail.
+ *
+ * We use cmpxchg to help prevent this race. We also do something
+ * special with the page before head. We set the LSB to 1.
+ *
+ * When the writer must push the page forward, it will clear the
+ * bit that points to the head page, move the head, and then set
+ * the bit that points to the new head page.
+ *
+ * We also don't want an interrupt coming in and moving the head
+ * page on another writer. Thus we use the second LSB to catch
+ * that too. Thus:
+ *
+ * head->list->prev->next bit 1 bit 0
+ * ------- -------
+ * Normal page 0 0
+ * Points to head page 0 1
+ * New head page 1 0
+ *
+ * Note we can not trust the prev pointer of the head page, because:
+ *
+ * +----+ +-----+ +-----+
+ * | |------>| T |---X--->| N |
+ * | |<------| | | |
+ * +----+ +-----+ +-----+
+ * ^ ^ |
+ * | +-----+ | |
+ * +----------| R |----------+ |
+ * | |<-----------+
+ * +-----+
+ *
+ * Key: ---X--> HEAD flag set in pointer
+ * T Tail page
+ * R Reader page
+ * N Next page
+ *
+ * (see __rb_reserve_next() to see where this happens)
+ *
+ * What the above shows is that the reader just swapped out
+ * the reader page with a page in the buffer, but before it
+ * could make the new header point back to the new page added
+ * it was preempted by a writer. The writer moved forward onto
+ * the new page added by the reader and is about to move forward
+ * again.
+ *
+ * You can see, it is legitimate for the previous pointer of
+ * the head (or any page) not to point back to itself. But only
+ * temporarially.
+ */
+
+#define RB_PAGE_NORMAL 0UL
+#define RB_PAGE_HEAD 1UL
+#define RB_PAGE_UPDATE 2UL
+
+
+#define RB_FLAG_MASK 3UL
+
+/* PAGE_MOVED is not part of the mask */
+#define RB_PAGE_MOVED 4UL
+
+/*
+ * rb_list_head - remove any bit
+ */
+static struct list_head *rb_list_head(struct list_head *list)
+{
+ unsigned long val = (unsigned long)list;
+
+ return (struct list_head *)(val & ~RB_FLAG_MASK);
+}
+
+/*
+ * rb_is_head_page - test if the given page is the head page
+ *
+ * Because the reader may move the head_page pointer, we can
+ * not trust what the head page is (it may be pointing to
+ * the reader page). But if the next page is a header page,
+ * its flags will be non zero.
+ */
+static int inline
+rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *page, struct list_head *list)
+{
+ unsigned long val;
+
+ val = (unsigned long)list->next;
+
+ if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
+ return RB_PAGE_MOVED;
+
+ return val & RB_FLAG_MASK;
+}
+
+/*
+ * rb_is_reader_page
+ *
+ * The unique thing about the reader page, is that, if the
+ * writer is ever on it, the previous pointer never points
+ * back to the reader page.
+ */
+static int rb_is_reader_page(struct buffer_page *page)
+{
+ struct list_head *list = page->list.prev;
+
+ return rb_list_head(list->next) != &page->list;
+}
+
+/*
+ * rb_set_list_to_head - set a list_head to be pointing to head.
+ */
+static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
+ struct list_head *list)
+{
+ unsigned long *ptr;
+
+ ptr = (unsigned long *)&list->next;
+ *ptr |= RB_PAGE_HEAD;
+ *ptr &= ~RB_PAGE_UPDATE;
+}
+
+/*
+ * rb_head_page_activate - sets up head page
+ */
+static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct buffer_page *head;
+
+ head = cpu_buffer->head_page;
+ if (!head)
+ return;
+
+ /*
+ * Set the previous list pointer to have the HEAD flag.
+ */
+ rb_set_list_to_head(cpu_buffer, head->list.prev);
+}
+
+static void rb_list_head_clear(struct list_head *list)
+{
+ unsigned long *ptr = (unsigned long *)&list->next;
+
+ *ptr &= ~RB_FLAG_MASK;
+}
+
+/*
+ * rb_head_page_dactivate - clears head page ptr (for free list)
+ */
+static void
+rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct list_head *hd;
+
+ /* Go through the whole list and clear any pointers found. */
+ rb_list_head_clear(cpu_buffer->pages);
+
+ list_for_each(hd, cpu_buffer->pages)
+ rb_list_head_clear(hd);
+}
+
+static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *head,
+ struct buffer_page *prev,
+ int old_flag, int new_flag)
+{
+ struct list_head *list;
+ unsigned long val = (unsigned long)&head->list;
+ unsigned long ret;
+
+ list = &prev->list;
+
+ val &= ~RB_FLAG_MASK;
+
+ ret = cmpxchg((unsigned long *)&list->next,
+ val | old_flag, val | new_flag);
+
+ /* check if the reader took the page */
+ if ((ret & ~RB_FLAG_MASK) != val)
+ return RB_PAGE_MOVED;
+
+ return ret & RB_FLAG_MASK;
+}
+
+static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *head,
+ struct buffer_page *prev,
+ int old_flag)
+{
+ return rb_head_page_set(cpu_buffer, head, prev,
+ old_flag, RB_PAGE_UPDATE);
+}
+
+static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *head,
+ struct buffer_page *prev,
+ int old_flag)
+{
+ return rb_head_page_set(cpu_buffer, head, prev,
+ old_flag, RB_PAGE_HEAD);
+}
+
+static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *head,
+ struct buffer_page *prev,
+ int old_flag)
+{
+ return rb_head_page_set(cpu_buffer, head, prev,
+ old_flag, RB_PAGE_NORMAL);
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page **bpage)
+{
+ struct list_head *p = rb_list_head((*bpage)->list.next);
+
+ *bpage = list_entry(p, struct buffer_page, list);
+}
+
+static struct buffer_page *
+rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct buffer_page *head;
+ struct buffer_page *page;
+ struct list_head *list;
+ int i;
+
+ if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
+ return NULL;
+
+ /* sanity check */
+ list = cpu_buffer->pages;
+ if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
+ return NULL;
+
+ page = head = cpu_buffer->head_page;
+ /*
+ * It is possible that the writer moves the header behind
+ * where we started, and we miss in one loop.
+ * A second loop should grab the header, but we'll do
+ * three loops just because I'm paranoid.
+ */
+ for (i = 0; i < 3; i++) {
+ do {
+ if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
+ cpu_buffer->head_page = page;
+ return page;
+ }
+ rb_inc_page(cpu_buffer, &page);
+ } while (page != head);
+ }
+
+ RB_WARN_ON(cpu_buffer, 1);
+
+ return NULL;
+}
+
+static int rb_head_page_replace(struct buffer_page *old,
+ struct buffer_page *new)
+{
+ unsigned long *ptr = (unsigned long *)&old->list.prev->next;
+ unsigned long val;
+ unsigned long ret;
+
+ val = *ptr & ~RB_FLAG_MASK;
+ val |= RB_PAGE_HEAD;
+
+ ret = cmpxchg(ptr, val, (unsigned long)&new->list);
+
+ return ret == val;
+}
+
+/*
+ * rb_tail_page_update - move the tail page forward
+ *
+ * Returns 1 if moved tail page, 0 if someone else did.
+ */
+static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *tail_page,
+ struct buffer_page *next_page)
+{
+ struct buffer_page *old_tail;
+ unsigned long old_entries;
+ unsigned long old_write;
+ int ret = 0;
+
+ /*
+ * The tail page now needs to be moved forward.
+ *
+ * We need to reset the tail page, but without messing
+ * with possible erasing of data brought in by interrupts
+ * that have moved the tail page and are currently on it.
+ *
+ * We add a counter to the write field to denote this.
+ */
+ old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
+ old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
+
+ /*
+ * Just make sure we have seen our old_write and synchronize
+ * with any interrupts that come in.
+ */
+ barrier();
+
+ /*
+ * If the tail page is still the same as what we think
+ * it is, then it is up to us to update the tail
+ * pointer.
+ */
+ if (tail_page == cpu_buffer->tail_page) {
+ /* Zero the write counter */
+ unsigned long val = old_write & ~RB_WRITE_MASK;
+ unsigned long eval = old_entries & ~RB_WRITE_MASK;
+
+ /*
+ * This will only succeed if an interrupt did
+ * not come in and change it. In which case, we
+ * do not want to modify it.
+ *
+ * We add (void) to let the compiler know that we do not care
+ * about the return value of these functions. We use the
+ * cmpxchg to only update if an interrupt did not already
+ * do it for us. If the cmpxchg fails, we don't care.
+ */
+ (void)local_cmpxchg(&next_page->write, old_write, val);
+ (void)local_cmpxchg(&next_page->entries, old_entries, eval);
+
+ /*
+ * No need to worry about races with clearing out the commit.
+ * it only can increment when a commit takes place. But that
+ * only happens in the outer most nested commit.
+ */
+ local_set(&next_page->page->commit, 0);
+
+ old_tail = cmpxchg(&cpu_buffer->tail_page,
+ tail_page, next_page);
+
+ if (old_tail == tail_page)
+ ret = 1;
+ }
+
+ return ret;
+}
+
+static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *bpage)
+{
+ unsigned long val = (unsigned long)bpage;
+
+ if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
+ return 1;
+
+ return 0;
+}
+
+/**
+ * rb_check_list - make sure a pointer to a list has the last bits zero
+ */
+static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
+ struct list_head *list)
+{
+ if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev))
+ return 1;
+ if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next))
+ return 1;
+ return 0;
+}
+
+/**
+ * check_pages - integrity check of buffer pages
+ * @cpu_buffer: CPU buffer with pages to test
+ *
+ * As a safety measure we check to make sure the data pages have not
+ * been corrupted.
+ */
+static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct list_head *head = cpu_buffer->pages;
+ struct buffer_page *bpage, *tmp;
+
+ rb_head_page_deactivate(cpu_buffer);
+
+ if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
+ return -1;
+ if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
+ return -1;
+
+ if (rb_check_list(cpu_buffer, head))
+ return -1;
+
+ list_for_each_entry_safe(bpage, tmp, head, list) {
+ if (RB_WARN_ON(cpu_buffer,
+ bpage->list.next->prev != &bpage->list))
+ return -1;
+ if (RB_WARN_ON(cpu_buffer,
+ bpage->list.prev->next != &bpage->list))
+ return -1;
+ if (rb_check_list(cpu_buffer, &bpage->list))
+ return -1;
+ }
+
+ rb_head_page_activate(cpu_buffer);
+
+ return 0;
+}
+
+static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned nr_pages)
+{
+ struct buffer_page *bpage, *tmp;
+ unsigned long addr;
+ LIST_HEAD(pages);
+ unsigned i;
+
+ WARN_ON(!nr_pages);
+
+ for (i = 0; i < nr_pages; i++) {
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
+ if (!bpage)
+ goto free_pages;
+
+ rb_check_bpage(cpu_buffer, bpage);
+
+ list_add(&bpage->list, &pages);
+
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ goto free_pages;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
+ }
+
+ /*
+ * The ring buffer page list is a circular list that does not
+ * start and end with a list head. All page list items point to
+ * other pages.
+ */
+ cpu_buffer->pages = pages.next;
+ list_del(&pages);
+
+ rb_check_pages(cpu_buffer);
+
+ return 0;
+
+ free_pages:
+ list_for_each_entry_safe(bpage, tmp, &pages, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
+ }
+ return -ENOMEM;
+}
+
+static struct ring_buffer_per_cpu *
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct buffer_page *bpage;
+ unsigned long addr;
+ int ret;
+
+ cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!cpu_buffer)
+ return NULL;
+
+ cpu_buffer->cpu = cpu;
+ cpu_buffer->buffer = buffer;
+ spin_lock_init(&cpu_buffer->reader_lock);
+ lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
+ cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!bpage)
+ goto fail_free_buffer;
+
+ rb_check_bpage(cpu_buffer, bpage);
+
+ cpu_buffer->reader_page = bpage;
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ goto fail_free_reader;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
+
+ INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+
+ ret = rb_allocate_pages(cpu_buffer, buffer->pages);
+ if (ret < 0)
+ goto fail_free_reader;
+
+ cpu_buffer->head_page
+ = list_entry(cpu_buffer->pages, struct buffer_page, list);
+ cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
+
+ rb_head_page_activate(cpu_buffer);
+
+ return cpu_buffer;
+
+ fail_free_reader:
+ free_buffer_page(cpu_buffer->reader_page);
+
+ fail_free_buffer:
+ kfree(cpu_buffer);
+ return NULL;
+}
+
+static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct list_head *head = cpu_buffer->pages;
+ struct buffer_page *bpage, *tmp;
+
+ free_buffer_page(cpu_buffer->reader_page);
+
+ rb_head_page_deactivate(cpu_buffer);
+
+ if (head) {
+ list_for_each_entry_safe(bpage, tmp, head, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
+ }
+ bpage = list_entry(head, struct buffer_page, list);
+ free_buffer_page(bpage);
+ }
+
+ kfree(cpu_buffer);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int rb_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu);
+#endif
+
+/**
+ * ring_buffer_alloc - allocate a new ring_buffer
+ * @size: the size in bytes per cpu that is needed.
+ * @flags: attributes to set for the ring buffer.
+ *
+ * Currently the only flag that is available is the RB_FL_OVERWRITE
+ * flag. This flag means that the buffer will overwrite old data
+ * when the buffer wraps. If this flag is not set, the buffer will
+ * drop data when the tail hits the head.
+ */
+struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
+ struct lock_class_key *key)
+{
+ struct ring_buffer *buffer;
+ int bsize;
+ int cpu;
+
+ /* keep it in its own cache line */
+ buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
+ GFP_KERNEL);
+ if (!buffer)
+ return NULL;
+
+ if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
+ goto fail_free_buffer;
+
+ buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+ buffer->flags = flags;
+ buffer->clock = trace_clock_local;
+ buffer->reader_lock_key = key;
+
+ /* need at least two pages */
+ if (buffer->pages < 2)
+ buffer->pages = 2;
+
+ /*
+ * In case of non-hotplug cpu, if the ring-buffer is allocated
+ * in early initcall, it will not be notified of secondary cpus.
+ * In that off case, we need to allocate for all possible cpus.
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+ get_online_cpus();
+ cpumask_copy(buffer->cpumask, cpu_online_mask);
+#else
+ cpumask_copy(buffer->cpumask, cpu_possible_mask);
+#endif
+ buffer->cpus = nr_cpu_ids;
+
+ bsize = sizeof(void *) * nr_cpu_ids;
+ buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
+ GFP_KERNEL);
+ if (!buffer->buffers)
+ goto fail_free_cpumask;
+
+ for_each_buffer_cpu(buffer, cpu) {
+ buffer->buffers[cpu] =
+ rb_allocate_cpu_buffer(buffer, cpu);
+ if (!buffer->buffers[cpu])
+ goto fail_free_buffers;
+ }
+
+#ifdef CONFIG_HOTPLUG_CPU
+ buffer->cpu_notify.notifier_call = rb_cpu_notify;
+ buffer->cpu_notify.priority = 0;
+ register_cpu_notifier(&buffer->cpu_notify);
+#endif
+
+ put_online_cpus();
+ mutex_init(&buffer->mutex);
+
+ return buffer;
+
+ fail_free_buffers:
+ for_each_buffer_cpu(buffer, cpu) {
+ if (buffer->buffers[cpu])
+ rb_free_cpu_buffer(buffer->buffers[cpu]);
+ }
+ kfree(buffer->buffers);
+
+ fail_free_cpumask:
+ free_cpumask_var(buffer->cpumask);
+ put_online_cpus();
+
+ fail_free_buffer:
+ kfree(buffer);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
+
+/**
+ * ring_buffer_free - free a ring buffer.
+ * @buffer: the buffer to free.
+ */
+void
+ring_buffer_free(struct ring_buffer *buffer)
+{
+ int cpu;
+
+ get_online_cpus();
+
+#ifdef CONFIG_HOTPLUG_CPU
+ unregister_cpu_notifier(&buffer->cpu_notify);
+#endif
+
+ for_each_buffer_cpu(buffer, cpu)
+ rb_free_cpu_buffer(buffer->buffers[cpu]);
+
+ put_online_cpus();
+
+ kfree(buffer->buffers);
+ free_cpumask_var(buffer->cpumask);
+
+ kfree(buffer);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_free);
+
+void ring_buffer_set_clock(struct ring_buffer *buffer,
+ u64 (*clock)(void))
+{
+ buffer->clock = clock;
+}
+
+static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
+
+static void
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
+{
+ struct buffer_page *bpage;
+ struct list_head *p;
+ unsigned i;
+
+ spin_lock_irq(&cpu_buffer->reader_lock);
+ rb_head_page_deactivate(cpu_buffer);
+
+ for (i = 0; i < nr_pages; i++) {
+ if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
+ return;
+ p = cpu_buffer->pages->next;
+ bpage = list_entry(p, struct buffer_page, list);
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
+ }
+ if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
+ return;
+
+ rb_reset_cpu(cpu_buffer);
+ rb_check_pages(cpu_buffer);
+
+ spin_unlock_irq(&cpu_buffer->reader_lock);
+}
+
+static void
+rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
+ struct list_head *pages, unsigned nr_pages)
+{
+ struct buffer_page *bpage;
+ struct list_head *p;
+ unsigned i;
+
+ spin_lock_irq(&cpu_buffer->reader_lock);
+ rb_head_page_deactivate(cpu_buffer);
+
+ for (i = 0; i < nr_pages; i++) {
+ if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
+ return;
+ p = pages->next;
+ bpage = list_entry(p, struct buffer_page, list);
+ list_del_init(&bpage->list);
+ list_add_tail(&bpage->list, cpu_buffer->pages);
+ }
+ rb_reset_cpu(cpu_buffer);
+ rb_check_pages(cpu_buffer);
+
+ spin_unlock_irq(&cpu_buffer->reader_lock);
+}
+
+/**
+ * ring_buffer_resize - resize the ring buffer
+ * @buffer: the buffer to resize.
+ * @size: the new size.
+ *
+ * Minimum size is 2 * BUF_PAGE_SIZE.
+ *
+ * Returns -1 on failure.
+ */
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned nr_pages, rm_pages, new_pages;
+ struct buffer_page *bpage, *tmp;
+ unsigned long buffer_size;
+ unsigned long addr;
+ LIST_HEAD(pages);
+ int i, cpu;
+
+ /*
+ * Always succeed at resizing a non-existent buffer:
+ */
+ if (!buffer)
+ return size;
+
+ size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+ size *= BUF_PAGE_SIZE;
+ buffer_size = buffer->pages * BUF_PAGE_SIZE;
+
+ /* we need a minimum of two pages */
+ if (size < BUF_PAGE_SIZE * 2)
+ size = BUF_PAGE_SIZE * 2;
+
+ if (size == buffer_size)
+ return size;
+
+ atomic_inc(&buffer->record_disabled);
+
+ /* Make sure all writers are done with this buffer. */
+ synchronize_sched();
+
+ mutex_lock(&buffer->mutex);
+ get_online_cpus();
+
+ nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+
+ if (size < buffer_size) {
+
+ /* easy case, just free pages */
+ if (RB_WARN_ON(buffer, nr_pages >= buffer->pages))
+ goto out_fail;
+
+ rm_pages = buffer->pages - nr_pages;
+
+ for_each_buffer_cpu(buffer, cpu) {
+ cpu_buffer = buffer->buffers[cpu];
+ rb_remove_pages(cpu_buffer, rm_pages);
+ }
+ goto out;
+ }
+
+ /*
+ * This is a bit more difficult. We only want to add pages
+ * when we can allocate enough for all CPUs. We do this
+ * by allocating all the pages and storing them on a local
+ * link list. If we succeed in our allocation, then we
+ * add these pages to the cpu_buffers. Otherwise we just free
+ * them all and return -ENOMEM;
+ */
+ if (RB_WARN_ON(buffer, nr_pages <= buffer->pages))
+ goto out_fail;
+
+ new_pages = nr_pages - buffer->pages;
+
+ for_each_buffer_cpu(buffer, cpu) {
+ for (i = 0; i < new_pages; i++) {
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage),
+ cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!bpage)
+ goto free_pages;
+ list_add(&bpage->list, &pages);
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ goto free_pages;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
+ }
+ }
+
+ for_each_buffer_cpu(buffer, cpu) {
+ cpu_buffer = buffer->buffers[cpu];
+ rb_insert_pages(cpu_buffer, &pages, new_pages);
+ }
+
+ if (RB_WARN_ON(buffer, !list_empty(&pages)))
+ goto out_fail;
+
+ out:
+ buffer->pages = nr_pages;
+ put_online_cpus();
+ mutex_unlock(&buffer->mutex);
+
+ atomic_dec(&buffer->record_disabled);
+
+ return size;
+
+ free_pages:
+ list_for_each_entry_safe(bpage, tmp, &pages, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
+ }
+ put_online_cpus();
+ mutex_unlock(&buffer->mutex);
+ atomic_dec(&buffer->record_disabled);
+ return -ENOMEM;
+
+ /*
+ * Something went totally wrong, and we are too paranoid
+ * to even clean up the mess.
+ */
+ out_fail:
+ put_online_cpus();
+ mutex_unlock(&buffer->mutex);
+ atomic_dec(&buffer->record_disabled);
+ return -1;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_resize);
+
+static inline void *
+__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
+{
+ return bpage->data + index;
+}
+
+static inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
+{
+ return bpage->page->data + index;
+}
+
+static inline struct ring_buffer_event *
+rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ return __rb_page_index(cpu_buffer->reader_page,
+ cpu_buffer->reader_page->read);
+}
+
+static inline struct ring_buffer_event *
+rb_iter_head_event(struct ring_buffer_iter *iter)
+{
+ return __rb_page_index(iter->head_page, iter->head);
+}
+
+static inline unsigned long rb_page_write(struct buffer_page *bpage)
+{
+ return local_read(&bpage->write) & RB_WRITE_MASK;
+}
+
+static inline unsigned rb_page_commit(struct buffer_page *bpage)
+{
+ return local_read(&bpage->page->commit);
+}
+
+static inline unsigned long rb_page_entries(struct buffer_page *bpage)
+{
+ return local_read(&bpage->entries) & RB_WRITE_MASK;
+}
+
+/* Size is determined by what has been commited */
+static inline unsigned rb_page_size(struct buffer_page *bpage)
+{
+ return rb_page_commit(bpage);
+}
+
+static inline unsigned
+rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ return rb_page_commit(cpu_buffer->commit_page);
+}
+
+static inline unsigned
+rb_event_index(struct ring_buffer_event *event)
+{
+ unsigned long addr = (unsigned long)event;
+
+ return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
+}
+
+static inline int
+rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ unsigned long addr = (unsigned long)event;
+ unsigned long index;
+
+ index = rb_event_index(event);
+ addr &= PAGE_MASK;
+
+ return cpu_buffer->commit_page->page == (void *)addr &&
+ rb_commit_index(cpu_buffer) == index;
+}
+
+static void
+rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ unsigned long max_count;
+
+ /*
+ * We only race with interrupts and NMIs on this CPU.
+ * If we own the commit event, then we can commit
+ * all others that interrupted us, since the interruptions
+ * are in stack format (they finish before they come
+ * back to us). This allows us to do a simple loop to
+ * assign the commit to the tail.
+ */
+ again:
+ max_count = cpu_buffer->buffer->pages * 100;
+
+ while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
+ if (RB_WARN_ON(cpu_buffer, !(--max_count)))
+ return;
+ if (RB_WARN_ON(cpu_buffer,
+ rb_is_reader_page(cpu_buffer->tail_page)))
+ return;
+ local_set(&cpu_buffer->commit_page->page->commit,
+ rb_page_write(cpu_buffer->commit_page));
+ rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
+ cpu_buffer->write_stamp =
+ cpu_buffer->commit_page->page->time_stamp;
+ /* add barrier to keep gcc from optimizing too much */
+ barrier();
+ }
+ while (rb_commit_index(cpu_buffer) !=
+ rb_page_write(cpu_buffer->commit_page)) {
+
+ local_set(&cpu_buffer->commit_page->page->commit,
+ rb_page_write(cpu_buffer->commit_page));
+ RB_WARN_ON(cpu_buffer,
+ local_read(&cpu_buffer->commit_page->page->commit) &
+ ~RB_WRITE_MASK);
+ barrier();
+ }
+
+ /* again, keep gcc from optimizing */
+ barrier();
+
+ /*
+ * If an interrupt came in just after the first while loop
+ * and pushed the tail page forward, we will be left with
+ * a dangling commit that will never go forward.
+ */
+ if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page))
+ goto again;
+}
+
+static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
+ cpu_buffer->reader_page->read = 0;
+}
+
+static void rb_inc_iter(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+ /*
+ * The iterator could be on the reader page (it starts there).
+ * But the head could have moved, since the reader was
+ * found. Check for this case and assign the iterator
+ * to the head page instead of next.
+ */
+ if (iter->head_page == cpu_buffer->reader_page)
+ iter->head_page = rb_set_head_page(cpu_buffer);
+ else
+ rb_inc_page(cpu_buffer, &iter->head_page);
+
+ iter->read_stamp = iter->head_page->page->time_stamp;
+ iter->head = 0;
+}
+
+/**
+ * ring_buffer_update_event - update event type and data
+ * @event: the even to update
+ * @type: the type of event
+ * @length: the size of the event field in the ring buffer
+ *
+ * Update the type and data fields of the event. The length
+ * is the actual size that is written to the ring buffer,
+ * and with this, we can determine what to place into the
+ * data field.
+ */
+static void
+rb_update_event(struct ring_buffer_event *event,
+ unsigned type, unsigned length)
+{
+ event->type_len = type;
+
+ switch (type) {
+
+ case RINGBUF_TYPE_PADDING:
+ case RINGBUF_TYPE_TIME_EXTEND:
+ case RINGBUF_TYPE_TIME_STAMP:
+ break;
+
+ case 0:
+ length -= RB_EVNT_HDR_SIZE;
+ if (length > RB_MAX_SMALL_DATA)
+ event->array[0] = length;
+ else
+ event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+ break;
+ default:
+ BUG();
+ }
+}
+
+/*
+ * rb_handle_head_page - writer hit the head page
+ *
+ * Returns: +1 to retry page
+ * 0 to continue
+ * -1 on error
+ */
+static int
+rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *tail_page,
+ struct buffer_page *next_page)
+{
+ struct buffer_page *new_head;
+ int entries;
+ int type;
+ int ret;
+
+ entries = rb_page_entries(next_page);
+
+ /*
+ * The hard part is here. We need to move the head
+ * forward, and protect against both readers on
+ * other CPUs and writers coming in via interrupts.
+ */
+ type = rb_head_page_set_update(cpu_buffer, next_page, tail_page,
+ RB_PAGE_HEAD);
+
+ /*
+ * type can be one of four:
+ * NORMAL - an interrupt already moved it for us
+ * HEAD - we are the first to get here.
+ * UPDATE - we are the interrupt interrupting
+ * a current move.
+ * MOVED - a reader on another CPU moved the next
+ * pointer to its reader page. Give up
+ * and try again.
+ */
+
+ switch (type) {
+ case RB_PAGE_HEAD:
+ /*
+ * We changed the head to UPDATE, thus
+ * it is our responsibility to update
+ * the counters.
+ */
+ local_add(entries, &cpu_buffer->overrun);
+
+ /*
+ * The entries will be zeroed out when we move the
+ * tail page.
+ */
+
+ /* still more to do */
+ break;
+
+ case RB_PAGE_UPDATE:
+ /*
+ * This is an interrupt that interrupt the
+ * previous update. Still more to do.
+ */
+ break;
+ case RB_PAGE_NORMAL:
+ /*
+ * An interrupt came in before the update
+ * and processed this for us.
+ * Nothing left to do.
+ */
+ return 1;
+ case RB_PAGE_MOVED:
+ /*
+ * The reader is on another CPU and just did
+ * a swap with our next_page.
+ * Try again.
+ */
+ return 1;
+ default:
+ RB_WARN_ON(cpu_buffer, 1); /* WTF??? */
+ return -1;
+ }
+
+ /*
+ * Now that we are here, the old head pointer is
+ * set to UPDATE. This will keep the reader from
+ * swapping the head page with the reader page.
+ * The reader (on another CPU) will spin till
+ * we are finished.
+ *
+ * We just need to protect against interrupts
+ * doing the job. We will set the next pointer
+ * to HEAD. After that, we set the old pointer
+ * to NORMAL, but only if it was HEAD before.
+ * otherwise we are an interrupt, and only
+ * want the outer most commit to reset it.
+ */
+ new_head = next_page;
+ rb_inc_page(cpu_buffer, &new_head);
+
+ ret = rb_head_page_set_head(cpu_buffer, new_head, next_page,
+ RB_PAGE_NORMAL);
+
+ /*
+ * Valid returns are:
+ * HEAD - an interrupt came in and already set it.
+ * NORMAL - One of two things:
+ * 1) We really set it.
+ * 2) A bunch of interrupts came in and moved
+ * the page forward again.
+ */
+ switch (ret) {
+ case RB_PAGE_HEAD:
+ case RB_PAGE_NORMAL:
+ /* OK */
+ break;
+ default:
+ RB_WARN_ON(cpu_buffer, 1);
+ return -1;
+ }
+
+ /*
+ * It is possible that an interrupt came in,
+ * set the head up, then more interrupts came in
+ * and moved it again. When we get back here,
+ * the page would have been set to NORMAL but we
+ * just set it back to HEAD.
+ *
+ * How do you detect this? Well, if that happened
+ * the tail page would have moved.
+ */
+ if (ret == RB_PAGE_NORMAL) {
+ /*
+ * If the tail had moved passed next, then we need
+ * to reset the pointer.
+ */
+ if (cpu_buffer->tail_page != tail_page &&
+ cpu_buffer->tail_page != next_page)
+ rb_head_page_set_normal(cpu_buffer, new_head,
+ next_page,
+ RB_PAGE_HEAD);
+ }
+
+ /*
+ * If this was the outer most commit (the one that
+ * changed the original pointer from HEAD to UPDATE),
+ * then it is up to us to reset it to NORMAL.
+ */
+ if (type == RB_PAGE_HEAD) {
+ ret = rb_head_page_set_normal(cpu_buffer, next_page,
+ tail_page,
+ RB_PAGE_UPDATE);
+ if (RB_WARN_ON(cpu_buffer,
+ ret != RB_PAGE_UPDATE))
+ return -1;
+ }
+
+ return 0;
+}
+
+static unsigned rb_calculate_event_length(unsigned length)
+{
+ struct ring_buffer_event event; /* Used only for sizeof array */
+
+ /* zero length can cause confusions */
+ if (!length)
+ length = 1;
+
+ if (length > RB_MAX_SMALL_DATA)
+ length += sizeof(event.array[0]);
+
+ length += RB_EVNT_HDR_SIZE;
+ length = ALIGN(length, RB_ALIGNMENT);
+
+ return length;
+}
+
+static inline void
+rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_page *tail_page,
+ unsigned long tail, unsigned long length)
+{
+ struct ring_buffer_event *event;
+
+ /*
+ * Only the event that crossed the page boundary
+ * must fill the old tail_page with padding.
+ */
+ if (tail >= BUF_PAGE_SIZE) {
+ local_sub(length, &tail_page->write);
+ return;
+ }
+
+ event = __rb_page_index(tail_page, tail);
+ kmemcheck_annotate_bitfield(event, bitfield);
+
+ /*
+ * If this event is bigger than the minimum size, then
+ * we need to be careful that we don't subtract the
+ * write counter enough to allow another writer to slip
+ * in on this page.
+ * We put in a discarded commit instead, to make sure
+ * that this space is not used again.
+ *
+ * If we are less than the minimum size, we don't need to
+ * worry about it.
+ */
+ if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+ /* No room for any events */
+
+ /* Mark the rest of the page with padding */
+ rb_event_set_padding(event);
+
+ /* Set the write back to the previous setting */
+ local_sub(length, &tail_page->write);
+ return;
+ }
+
+ /* Put in a discarded event */
+ event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+ event->type_len = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ event->time_delta = 1;
+
+ /* Set write to end of buffer */
+ length = (tail + length) - BUF_PAGE_SIZE;
+ local_sub(length, &tail_page->write);
+}
+
+static struct ring_buffer_event *
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned long length, unsigned long tail,
+ struct buffer_page *tail_page, u64 *ts)
+{
+ struct buffer_page *commit_page = cpu_buffer->commit_page;
+ struct ring_buffer *buffer = cpu_buffer->buffer;
+ struct buffer_page *next_page;
+ int ret;
+
+ next_page = tail_page;
+
+ rb_inc_page(cpu_buffer, &next_page);
+
+ /*
+ * If for some reason, we had an interrupt storm that made
+ * it all the way around the buffer, bail, and warn
+ * about it.
+ */
+ if (unlikely(next_page == commit_page)) {
+ local_inc(&cpu_buffer->commit_overrun);
+ goto out_reset;
+ }
+
+ /*
+ * This is where the fun begins!
+ *
+ * We are fighting against races between a reader that
+ * could be on another CPU trying to swap its reader
+ * page with the buffer head.
+ *
+ * We are also fighting against interrupts coming in and
+ * moving the head or tail on us as well.
+ *
+ * If the next page is the head page then we have filled
+ * the buffer, unless the commit page is still on the
+ * reader page.
+ */
+ if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) {
+
+ /*
+ * If the commit is not on the reader page, then
+ * move the header page.
+ */
+ if (!rb_is_reader_page(cpu_buffer->commit_page)) {
+ /*
+ * If we are not in overwrite mode,
+ * this is easy, just stop here.
+ */
+ if (!(buffer->flags & RB_FL_OVERWRITE))
+ goto out_reset;
+
+ ret = rb_handle_head_page(cpu_buffer,
+ tail_page,
+ next_page);
+ if (ret < 0)
+ goto out_reset;
+ if (ret)
+ goto out_again;
+ } else {
+ /*
+ * We need to be careful here too. The
+ * commit page could still be on the reader
+ * page. We could have a small buffer, and
+ * have filled up the buffer with events
+ * from interrupts and such, and wrapped.
+ *
+ * Note, if the tail page is also the on the
+ * reader_page, we let it move out.
+ */
+ if (unlikely((cpu_buffer->commit_page !=
+ cpu_buffer->tail_page) &&
+ (cpu_buffer->commit_page ==
+ cpu_buffer->reader_page))) {
+ local_inc(&cpu_buffer->commit_overrun);
+ goto out_reset;
+ }
+ }
+ }
+
+ ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
+ if (ret) {
+ /*
+ * Nested commits always have zero deltas, so
+ * just reread the time stamp
+ */
+ *ts = rb_time_stamp(buffer);
+ next_page->page->time_stamp = *ts;
+ }
+
+ out_again:
+
+ rb_reset_tail(cpu_buffer, tail_page, tail, length);
+
+ /* fail and let the caller try again */
+ return ERR_PTR(-EAGAIN);
+
+ out_reset:
+ /* reset write */
+ rb_reset_tail(cpu_buffer, tail_page, tail, length);
+
+ return NULL;
+}
+
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned type, unsigned long length, u64 *ts)
+{
+ struct buffer_page *tail_page;
+ struct ring_buffer_event *event;
+ unsigned long tail, write;
+
+ tail_page = cpu_buffer->tail_page;
+ write = local_add_return(length, &tail_page->write);
+
+ /* set write to only the index of the write */
+ write &= RB_WRITE_MASK;
+ tail = write - length;
+
+ /* See if we shot pass the end of this buffer page */
+ if (write > BUF_PAGE_SIZE)
+ return rb_move_tail(cpu_buffer, length, tail,
+ tail_page, ts);
+
+ /* We reserved something on the buffer */
+
+ event = __rb_page_index(tail_page, tail);
+ kmemcheck_annotate_bitfield(event, bitfield);
+ rb_update_event(event, type, length);
+
+ /* The passed in type is zero for DATA */
+ if (likely(!type))
+ local_inc(&tail_page->entries);
+
+ /*
+ * If this is the first commit on the page, then update
+ * its timestamp.
+ */
+ if (!tail)
+ tail_page->page->time_stamp = *ts;
+
+ return event;
+}
+
+static inline int
+rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ unsigned long new_index, old_index;
+ struct buffer_page *bpage;
+ unsigned long index;
+ unsigned long addr;
+
+ new_index = rb_event_index(event);
+ old_index = new_index + rb_event_length(event);
+ addr = (unsigned long)event;
+ addr &= PAGE_MASK;
+
+ bpage = cpu_buffer->tail_page;
+
+ if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+ unsigned long write_mask =
+ local_read(&bpage->write) & ~RB_WRITE_MASK;
+ /*
+ * This is on the tail page. It is possible that
+ * a write could come in and move the tail page
+ * and write to the next page. That is fine
+ * because we just shorten what is on this page.
+ */
+ old_index += write_mask;
+ new_index += write_mask;
+ index = local_cmpxchg(&bpage->write, old_index, new_index);
+ if (index == old_index)
+ return 1;
+ }
+
+ /* could not discard */
+ return 0;
+}
+
+static int
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+ u64 *ts, u64 *delta)
+{
+ struct ring_buffer_event *event;
+ static int once;
+ int ret;
+
+ if (unlikely(*delta > (1ULL << 59) && !once++)) {
+ printk(KERN_WARNING "Delta way too big! %llu"
+ " ts=%llu write stamp = %llu\n",
+ (unsigned long long)*delta,
+ (unsigned long long)*ts,
+ (unsigned long long)cpu_buffer->write_stamp);
+ WARN_ON(1);
+ }
+
+ /*
+ * The delta is too big, we to add a
+ * new timestamp.
+ */
+ event = __rb_reserve_next(cpu_buffer,
+ RINGBUF_TYPE_TIME_EXTEND,
+ RB_LEN_TIME_EXTEND,
+ ts);
+ if (!event)
+ return -EBUSY;
+
+ if (PTR_ERR(event) == -EAGAIN)
+ return -EAGAIN;
+
+ /* Only a commited time event can update the write stamp */
+ if (rb_event_is_commit(cpu_buffer, event)) {
+ /*
+ * If this is the first on the page, then it was
+ * updated with the page itself. Try to discard it
+ * and if we can't just make it zero.
+ */
+ if (rb_event_index(event)) {
+ event->time_delta = *delta & TS_MASK;
+ event->array[0] = *delta >> TS_SHIFT;
+ } else {
+ /* try to discard, since we do not need this */
+ if (!rb_try_to_discard(cpu_buffer, event)) {
+ /* nope, just zero it */
+ event->time_delta = 0;
+ event->array[0] = 0;
+ }
+ }
+ cpu_buffer->write_stamp = *ts;
+ /* let the caller know this was the commit */
+ ret = 1;
+ } else {
+ /* Try to discard the event */
+ if (!rb_try_to_discard(cpu_buffer, event)) {
+ /* Darn, this is just wasted space */
+ event->time_delta = 0;
+ event->array[0] = 0;
+ }
+ ret = 0;
+ }
+
+ *delta = 0;
+
+ return ret;
+}
+
+static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ local_inc(&cpu_buffer->committing);
+ local_inc(&cpu_buffer->commits);
+}
+
+static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ unsigned long commits;
+
+ if (RB_WARN_ON(cpu_buffer,
+ !local_read(&cpu_buffer->committing)))
+ return;
+
+ again:
+ commits = local_read(&cpu_buffer->commits);
+ /* synchronize with interrupts */
+ barrier();
+ if (local_read(&cpu_buffer->committing) == 1)
+ rb_set_commit_to_write(cpu_buffer);
+
+ local_dec(&cpu_buffer->committing);
+
+ /* synchronize with interrupts */
+ barrier();
+
+ /*
+ * Need to account for interrupts coming in between the
+ * updating of the commit page and the clearing of the
+ * committing counter.
+ */
+ if (unlikely(local_read(&cpu_buffer->commits) != commits) &&
+ !local_read(&cpu_buffer->committing)) {
+ local_inc(&cpu_buffer->committing);
+ goto again;
+ }
+}
+
+static struct ring_buffer_event *
+rb_reserve_next_event(struct ring_buffer *buffer,
+ struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned long length)
+{
+ struct ring_buffer_event *event;
+ u64 ts, delta = 0;
+ int commit = 0;
+ int nr_loops = 0;
+
+ rb_start_commit(cpu_buffer);
+
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+ /*
+ * Due to the ability to swap a cpu buffer from a buffer
+ * it is possible it was swapped before we committed.
+ * (committing stops a swap). We check for it here and
+ * if it happened, we have to fail the write.
+ */
+ barrier();
+ if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) {
+ local_dec(&cpu_buffer->committing);
+ local_dec(&cpu_buffer->commits);
+ return NULL;
+ }
+#endif
+
+ length = rb_calculate_event_length(length);
+ again:
+ /*
+ * We allow for interrupts to reenter here and do a trace.
+ * If one does, it will cause this original code to loop
+ * back here. Even with heavy interrupts happening, this
+ * should only happen a few times in a row. If this happens
+ * 1000 times in a row, there must be either an interrupt
+ * storm or we have something buggy.
+ * Bail!
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
+ goto out_fail;
+
+ ts = rb_time_stamp(cpu_buffer->buffer);
+
+ /*
+ * Only the first commit can update the timestamp.
+ * Yes there is a race here. If an interrupt comes in
+ * just after the conditional and it traces too, then it
+ * will also check the deltas. More than one timestamp may
+ * also be made. But only the entry that did the actual
+ * commit will be something other than zero.
+ */
+ if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page &&
+ rb_page_write(cpu_buffer->tail_page) ==
+ rb_commit_index(cpu_buffer))) {
+ u64 diff;
+
+ diff = ts - cpu_buffer->write_stamp;
+
+ /* make sure this diff is calculated here */
+ barrier();
+
+ /* Did the write stamp get updated already? */
+ if (unlikely(ts < cpu_buffer->write_stamp))
+ goto get_event;
+
+ delta = diff;
+ if (unlikely(test_time_stamp(delta))) {
+
+ commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
+ if (commit == -EBUSY)
+ goto out_fail;
+
+ if (commit == -EAGAIN)
+ goto again;
+
+ RB_WARN_ON(cpu_buffer, commit < 0);
+ }
+ }
+
+ get_event:
+ event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
+ if (unlikely(PTR_ERR(event) == -EAGAIN))
+ goto again;
+
+ if (!event)
+ goto out_fail;
+
+ if (!rb_event_is_commit(cpu_buffer, event))
+ delta = 0;
+
+ event->time_delta = delta;
+
+ return event;
+
+ out_fail:
+ rb_end_commit(cpu_buffer);
+ return NULL;
+}
+
+#ifdef CONFIG_TRACING
+
+#define TRACE_RECURSIVE_DEPTH 16
+
+static int trace_recursive_lock(void)
+{
+ current->trace_recursion++;
+
+ if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+ return 0;
+
+ /* Disable all tracing before we do anything else */
+ tracing_off_permanent();
+
+ printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
+ "HC[%lu]:SC[%lu]:NMI[%lu]\n",
+ current->trace_recursion,
+ hardirq_count() >> HARDIRQ_SHIFT,
+ softirq_count() >> SOFTIRQ_SHIFT,
+ in_nmi());
+
+ WARN_ON_ONCE(1);
+ return -1;
+}
+
+static void trace_recursive_unlock(void)
+{
+ WARN_ON_ONCE(!current->trace_recursion);
+
+ current->trace_recursion--;
+}
+
+#else
+
+#define trace_recursive_lock() (0)
+#define trace_recursive_unlock() do { } while (0)
+
+#endif
+
+static DEFINE_PER_CPU(int, rb_need_resched);
+
+/**
+ * ring_buffer_lock_reserve - reserve a part of the buffer
+ * @buffer: the ring buffer to reserve from
+ * @length: the length of the data to reserve (excluding event header)
+ *
+ * Returns a reseverd event on the ring buffer to copy directly to.
+ * The user of this interface will need to get the body to write into
+ * and can use the ring_buffer_event_data() interface.
+ *
+ * The length is the length of the data needed, not the event length
+ * which also includes the event header.
+ *
+ * Must be paired with ring_buffer_unlock_commit, unless NULL is returned.
+ * If NULL is returned, then nothing has been allocated or locked.
+ */
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event;
+ int cpu, resched;
+
+ if (ring_buffer_flags != RB_BUFFERS_ON)
+ return NULL;
+
+ /* If we are tracing schedule, we don't want to recurse */
+ resched = ftrace_preempt_disable();
+
+ if (atomic_read(&buffer->record_disabled))
+ goto out_nocheck;
+
+ if (trace_recursive_lock())
+ goto out_nocheck;
+
+ cpu = raw_smp_processor_id();
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
+
+ cpu_buffer = buffer->buffers[cpu];
+
+ if (atomic_read(&cpu_buffer->record_disabled))
+ goto out;
+
+ if (length > BUF_MAX_DATA_SIZE)
+ goto out;
+
+ event = rb_reserve_next_event(buffer, cpu_buffer, length);
+ if (!event)
+ goto out;
+
+ /*
+ * Need to store resched state on this cpu.
+ * Only the first needs to.
+ */
+
+ if (preempt_count() == 1)
+ per_cpu(rb_need_resched, cpu) = resched;
+
+ return event;
+
+ out:
+ trace_recursive_unlock();
+
+ out_nocheck:
+ ftrace_preempt_enable(resched);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
+
+static void
+rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ /*
+ * The event first in the commit queue updates the
+ * time stamp.
+ */
+ if (rb_event_is_commit(cpu_buffer, event))
+ cpu_buffer->write_stamp += event->time_delta;
+}
+
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ local_inc(&cpu_buffer->entries);
+ rb_update_write_stamp(cpu_buffer, event);
+ rb_end_commit(cpu_buffer);
+}
+
+/**
+ * ring_buffer_unlock_commit - commit a reserved
+ * @buffer: The buffer to commit to
+ * @event: The event pointer to commit.
+ *
+ * This commits the data to the ring buffer, and releases any locks held.
+ *
+ * Must be paired with ring_buffer_lock_reserve.
+ */
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ int cpu = raw_smp_processor_id();
+
+ cpu_buffer = buffer->buffers[cpu];
+
+ rb_commit(cpu_buffer, event);
+
+ trace_recursive_unlock();
+
+ /*
+ * Only the last preempt count needs to restore preemption.
+ */
+ if (preempt_count() == 1)
+ ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+ else
+ preempt_enable_no_resched_notrace();
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
+
+static inline void rb_event_discard(struct ring_buffer_event *event)
+{
+ /* array[0] holds the actual length for the discarded event */
+ event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
+ event->type_len = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ if (!event->time_delta)
+ event->time_delta = 1;
+}
+
+/*
+ * Decrement the entries to the page that an event is on.
+ * The event does not even need to exist, only the pointer
+ * to the page it is on. This may only be called before the commit
+ * takes place.
+ */
+static inline void
+rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ unsigned long addr = (unsigned long)event;
+ struct buffer_page *bpage = cpu_buffer->commit_page;
+ struct buffer_page *start;
+
+ addr &= PAGE_MASK;
+
+ /* Do the likely case first */
+ if (likely(bpage->page == (void *)addr)) {
+ local_dec(&bpage->entries);
+ return;
+ }
+
+ /*
+ * Because the commit page may be on the reader page we
+ * start with the next page and check the end loop there.
+ */
+ rb_inc_page(cpu_buffer, &bpage);
+ start = bpage;
+ do {
+ if (bpage->page == (void *)addr) {
+ local_dec(&bpage->entries);
+ return;
+ }
+ rb_inc_page(cpu_buffer, &bpage);
+ } while (bpage != start);
+
+ /* commit not part of this buffer?? */
+ RB_WARN_ON(cpu_buffer, 1);
+}
+
+/**
+ * ring_buffer_commit_discard - discard an event that has not been committed
+ * @buffer: the ring buffer
+ * @event: non committed event to discard
+ *
+ * Sometimes an event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * This function only works if it is called before the the item has been
+ * committed. It will try to free the event from the ring buffer
+ * if another event has not been added behind it.
+ *
+ * If another event has been added behind it, it will set the event
+ * up as discarded, and perform the commit.
+ *
+ * If this function is called, do not call ring_buffer_unlock_commit on
+ * the event.
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ int cpu;
+
+ /* The event is discarded regardless */
+ rb_event_discard(event);
+
+ cpu = smp_processor_id();
+ cpu_buffer = buffer->buffers[cpu];
+
+ /*
+ * This must only be called if the event has not been
+ * committed yet. Thus we can assume that preemption
+ * is still disabled.
+ */
+ RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
+
+ rb_decrement_entry(cpu_buffer, event);
+ if (rb_try_to_discard(cpu_buffer, event))
+ goto out;
+
+ /*
+ * The commit is still visible by the reader, so we
+ * must still update the timestamp.
+ */
+ rb_update_write_stamp(cpu_buffer, event);
+ out:
+ rb_end_commit(cpu_buffer);
+
+ trace_recursive_unlock();
+
+ /*
+ * Only the last preempt count needs to restore preemption.
+ */
+ if (preempt_count() == 1)
+ ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+ else
+ preempt_enable_no_resched_notrace();
+
+}
+EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
+
+/**
+ * ring_buffer_write - write data to the buffer without reserving
+ * @buffer: The ring buffer to write to.
+ * @length: The length of the data being written (excluding the event header)
+ * @data: The data to write to the buffer.
+ *
+ * This is like ring_buffer_lock_reserve and ring_buffer_unlock_commit as
+ * one function. If you already have the data to write to the buffer, it
+ * may be easier to simply call this function.
+ *
+ * Note, like ring_buffer_lock_reserve, the length is the length of the data
+ * and not the length of the event which would hold the header.
+ */
+int ring_buffer_write(struct ring_buffer *buffer,
+ unsigned long length,
+ void *data)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event;
+ void *body;
+ int ret = -EBUSY;
+ int cpu, resched;
+
+ if (ring_buffer_flags != RB_BUFFERS_ON)
+ return -EBUSY;
+
+ resched = ftrace_preempt_disable();
+
+ if (atomic_read(&buffer->record_disabled))
+ goto out;
+
+ cpu = raw_smp_processor_id();
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
+
+ cpu_buffer = buffer->buffers[cpu];
+
+ if (atomic_read(&cpu_buffer->record_disabled))
+ goto out;
+
+ if (length > BUF_MAX_DATA_SIZE)
+ goto out;
+
+ event = rb_reserve_next_event(buffer, cpu_buffer, length);
+ if (!event)
+ goto out;
+
+ body = rb_event_data(event);
+
+ memcpy(body, data, length);
+
+ rb_commit(cpu_buffer, event);
+
+ ret = 0;
+ out:
+ ftrace_preempt_enable(resched);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_write);
+
+static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct buffer_page *reader = cpu_buffer->reader_page;
+ struct buffer_page *head = rb_set_head_page(cpu_buffer);
+ struct buffer_page *commit = cpu_buffer->commit_page;
+
+ /* In case of error, head will be NULL */
+ if (unlikely(!head))
+ return 1;
+
+ return reader->read == rb_page_commit(reader) &&
+ (commit == reader ||
+ (commit == head &&
+ head->read == rb_page_commit(commit)));
+}
+
+/**
+ * ring_buffer_record_disable - stop all writes into the buffer
+ * @buffer: The ring buffer to stop writes to.
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * The caller should call synchronize_sched() after this.
+ */
+void ring_buffer_record_disable(struct ring_buffer *buffer)
+{
+ atomic_inc(&buffer->record_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
+
+/**
+ * ring_buffer_record_enable - enable writes to the buffer
+ * @buffer: The ring buffer to enable writes
+ *
+ * Note, multiple disables will need the same number of enables
+ * to truely enable the writing (much like preempt_disable).
+ */
+void ring_buffer_record_enable(struct ring_buffer *buffer)
+{
+ atomic_dec(&buffer->record_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
+
+/**
+ * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
+ * @buffer: The ring buffer to stop writes to.
+ * @cpu: The CPU buffer to stop
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * The caller should call synchronize_sched() after this.
+ */
+void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return;
+
+ cpu_buffer = buffer->buffers[cpu];
+ atomic_inc(&cpu_buffer->record_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
+
+/**
+ * ring_buffer_record_enable_cpu - enable writes to the buffer
+ * @buffer: The ring buffer to enable writes
+ * @cpu: The CPU to enable.
+ *
+ * Note, multiple disables will need the same number of enables
+ * to truely enable the writing (much like preempt_disable).
+ */
+void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return;
+
+ cpu_buffer = buffer->buffers[cpu];
+ atomic_dec(&cpu_buffer->record_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
+
+/**
+ * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the entries from.
+ */
+unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun))
+ - cpu_buffer->read;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
+
+/**
+ * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = local_read(&cpu_buffer->overrun);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = local_read(&cpu_buffer->commit_overrun);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
+
+/**
+ * ring_buffer_entries - get the number of entries in a buffer
+ * @buffer: The ring buffer
+ *
+ * Returns the total number of entries in the ring buffer
+ * (all CPU entries)
+ */
+unsigned long ring_buffer_entries(struct ring_buffer *buffer)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long entries = 0;
+ int cpu;
+
+ /* if you care about this being correct, lock the buffer */
+ for_each_buffer_cpu(buffer, cpu) {
+ cpu_buffer = buffer->buffers[cpu];
+ entries += (local_read(&cpu_buffer->entries) -
+ local_read(&cpu_buffer->overrun)) - cpu_buffer->read;
+ }
+
+ return entries;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_entries);
+
+/**
+ * ring_buffer_overruns - get the number of overruns in buffer
+ * @buffer: The ring buffer
+ *
+ * Returns the total number of overruns in the ring buffer
+ * (all CPU entries)
+ */
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long overruns = 0;
+ int cpu;
+
+ /* if you care about this being correct, lock the buffer */
+ for_each_buffer_cpu(buffer, cpu) {
+ cpu_buffer = buffer->buffers[cpu];
+ overruns += local_read(&cpu_buffer->overrun);
+ }
+
+ return overruns;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_overruns);
+
+static void rb_iter_reset(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+ /* Iterator usage is expected to have record disabled */
+ if (list_empty(&cpu_buffer->reader_page->list)) {
+ iter->head_page = rb_set_head_page(cpu_buffer);
+ if (unlikely(!iter->head_page))
+ return;
+ iter->head = iter->head_page->read;
+ } else {
+ iter->head_page = cpu_buffer->reader_page;
+ iter->head = cpu_buffer->reader_page->read;
+ }
+ if (iter->head)
+ iter->read_stamp = cpu_buffer->read_stamp;
+ else
+ iter->read_stamp = iter->head_page->page->time_stamp;
+ iter->cache_reader_page = cpu_buffer->reader_page;
+ iter->cache_read = cpu_buffer->read;
+}
+
+/**
+ * ring_buffer_iter_reset - reset an iterator
+ * @iter: The iterator to reset
+ *
+ * Resets the iterator, so that it will start from the beginning
+ * again.
+ */
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+
+ if (!iter)
+ return;
+
+ cpu_buffer = iter->cpu_buffer;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ rb_iter_reset(iter);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
+
+/**
+ * ring_buffer_iter_empty - check if an iterator has no more to read
+ * @iter: The iterator to check
+ */
+int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+
+ cpu_buffer = iter->cpu_buffer;
+
+ return iter->head_page == cpu_buffer->commit_page &&
+ iter->head == rb_commit_index(cpu_buffer);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
+
+static void
+rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ u64 delta;
+
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ return;
+
+ case RINGBUF_TYPE_TIME_EXTEND:
+ delta = event->array[0];
+ delta <<= TS_SHIFT;
+ delta += event->time_delta;
+ cpu_buffer->read_stamp += delta;
+ return;
+
+ case RINGBUF_TYPE_TIME_STAMP:
+ /* FIXME: not implemented */
+ return;
+
+ case RINGBUF_TYPE_DATA:
+ cpu_buffer->read_stamp += event->time_delta;
+ return;
+
+ default:
+ BUG();
+ }
+ return;
+}
+
+static void
+rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
+ struct ring_buffer_event *event)
+{
+ u64 delta;
+
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ return;
+
+ case RINGBUF_TYPE_TIME_EXTEND:
+ delta = event->array[0];
+ delta <<= TS_SHIFT;
+ delta += event->time_delta;
+ iter->read_stamp += delta;
+ return;
+
+ case RINGBUF_TYPE_TIME_STAMP:
+ /* FIXME: not implemented */
+ return;
+
+ case RINGBUF_TYPE_DATA:
+ iter->read_stamp += event->time_delta;
+ return;
+
+ default:
+ BUG();
+ }
+ return;
+}
+
+static struct buffer_page *
+rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct buffer_page *reader = NULL;
+ unsigned long flags;
+ int nr_loops = 0;
+ int ret;
+
+ local_irq_save(flags);
+ arch_spin_lock(&cpu_buffer->lock);
+
+ again:
+ /*
+ * This should normally only loop twice. But because the
+ * start of the reader inserts an empty page, it causes
+ * a case where we will loop three times. There should be no
+ * reason to loop four times (that I know of).
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
+ reader = NULL;
+ goto out;
+ }
+
+ reader = cpu_buffer->reader_page;
+
+ /* If there's more to read, return this page */
+ if (cpu_buffer->reader_page->read < rb_page_size(reader))
+ goto out;
+
+ /* Never should we have an index greater than the size */
+ if (RB_WARN_ON(cpu_buffer,
+ cpu_buffer->reader_page->read > rb_page_size(reader)))
+ goto out;
+
+ /* check if we caught up to the tail */
+ reader = NULL;
+ if (cpu_buffer->commit_page == cpu_buffer->reader_page)
+ goto out;
+
+ /*
+ * Reset the reader page to size zero.
+ */
+ local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
+
+ spin:
+ /*
+ * Splice the empty reader page into the list around the head.
+ */
+ reader = rb_set_head_page(cpu_buffer);
+ cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next);
+ cpu_buffer->reader_page->list.prev = reader->list.prev;
+
+ /*
+ * cpu_buffer->pages just needs to point to the buffer, it
+ * has no specific buffer page to point to. Lets move it out
+ * of our way so we don't accidently swap it.
+ */
+ cpu_buffer->pages = reader->list.prev;
+
+ /* The reader page will be pointing to the new head */
+ rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
+
+ /*
+ * Here's the tricky part.
+ *
+ * We need to move the pointer past the header page.
+ * But we can only do that if a writer is not currently
+ * moving it. The page before the header page has the
+ * flag bit '1' set if it is pointing to the page we want.
+ * but if the writer is in the process of moving it
+ * than it will be '2' or already moved '0'.
+ */
+
+ ret = rb_head_page_replace(reader, cpu_buffer->reader_page);
+
+ /*
+ * If we did not convert it, then we must try again.
+ */
+ if (!ret)
+ goto spin;
+
+ /*
+ * Yeah! We succeeded in replacing the page.
+ *
+ * Now make the new head point back to the reader page.
+ */
+ rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
+ rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+
+ /* Finally update the reader page to the new head */
+ cpu_buffer->reader_page = reader;
+ rb_reset_reader_page(cpu_buffer);
+
+ goto again;
+
+ out:
+ arch_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ return reader;
+}
+
+static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct ring_buffer_event *event;
+ struct buffer_page *reader;
+ unsigned length;
+
+ reader = rb_get_reader_page(cpu_buffer);
+
+ /* This function should not be called when buffer is empty */
+ if (RB_WARN_ON(cpu_buffer, !reader))
+ return;
+
+ event = rb_reader_event(cpu_buffer);
+
+ if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+ cpu_buffer->read++;
+
+ rb_update_read_stamp(cpu_buffer, event);
+
+ length = rb_event_length(event);
+ cpu_buffer->reader_page->read += length;
+}
+
+static void rb_advance_iter(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer *buffer;
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event;
+ unsigned length;
+
+ cpu_buffer = iter->cpu_buffer;
+ buffer = cpu_buffer->buffer;
+
+ /*
+ * Check if we are at the end of the buffer.
+ */
+ if (iter->head >= rb_page_size(iter->head_page)) {
+ /* discarded commits can make the page empty */
+ if (iter->head_page == cpu_buffer->commit_page)
+ return;
+ rb_inc_iter(iter);
+ return;
+ }
+
+ event = rb_iter_head_event(iter);
+
+ length = rb_event_length(event);
+
+ /*
+ * This should not be called to advance the header if we are
+ * at the tail of the buffer.
+ */
+ if (RB_WARN_ON(cpu_buffer,
+ (iter->head_page == cpu_buffer->commit_page) &&
+ (iter->head + length > rb_commit_index(cpu_buffer))))
+ return;
+
+ rb_update_iter_read_stamp(iter, event);
+
+ iter->head += length;
+
+ /* check for end of page padding */
+ if ((iter->head >= rb_page_size(iter->head_page)) &&
+ (iter->head_page != cpu_buffer->commit_page))
+ rb_advance_iter(iter);
+}
+
+static struct ring_buffer_event *
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+{
+ struct ring_buffer_event *event;
+ struct buffer_page *reader;
+ int nr_loops = 0;
+
+ again:
+ /*
+ * We repeat when a timestamp is encountered. It is possible
+ * to get multiple timestamps from an interrupt entering just
+ * as one timestamp is about to be written, or from discarded
+ * commits. The most that we can have is the number on a single page.
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
+ return NULL;
+
+ reader = rb_get_reader_page(cpu_buffer);
+ if (!reader)
+ return NULL;
+
+ event = rb_reader_event(cpu_buffer);
+
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ if (rb_null_event(event))
+ RB_WARN_ON(cpu_buffer, 1);
+ /*
+ * Because the writer could be discarding every
+ * event it creates (which would probably be bad)
+ * if we were to go back to "again" then we may never
+ * catch up, and will trigger the warn on, or lock
+ * the box. Return the padding, and we will release
+ * the current locks, and try again.
+ */
+ return event;
+
+ case RINGBUF_TYPE_TIME_EXTEND:
+ /* Internal data, OK to advance */
+ rb_advance_reader(cpu_buffer);
+ goto again;
+
+ case RINGBUF_TYPE_TIME_STAMP:
+ /* FIXME: not implemented */
+ rb_advance_reader(cpu_buffer);
+ goto again;
+
+ case RINGBUF_TYPE_DATA:
+ if (ts) {
+ *ts = cpu_buffer->read_stamp + event->time_delta;
+ ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+ cpu_buffer->cpu, ts);
+ }
+ return event;
+
+ default:
+ BUG();
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_peek);
+
+static struct ring_buffer_event *
+rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+ struct ring_buffer *buffer;
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event;
+ int nr_loops = 0;
+
+ cpu_buffer = iter->cpu_buffer;
+ buffer = cpu_buffer->buffer;
+
+ /*
+ * Check if someone performed a consuming read to
+ * the buffer. A consuming read invalidates the iterator
+ * and we need to reset the iterator in this case.
+ */
+ if (unlikely(iter->cache_read != cpu_buffer->read ||
+ iter->cache_reader_page != cpu_buffer->reader_page))
+ rb_iter_reset(iter);
+
+ again:
+ if (ring_buffer_iter_empty(iter))
+ return NULL;
+
+ /*
+ * We repeat when a timestamp is encountered.
+ * We can get multiple timestamps by nested interrupts or also
+ * if filtering is on (discarding commits). Since discarding
+ * commits can be frequent we can get a lot of timestamps.
+ * But we limit them by not adding timestamps if they begin
+ * at the start of a page.
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
+ return NULL;
+
+ if (rb_per_cpu_empty(cpu_buffer))
+ return NULL;
+
+ if (iter->head >= local_read(&iter->head_page->page->commit)) {
+ rb_inc_iter(iter);
+ goto again;
+ }
+
+ event = rb_iter_head_event(iter);
+
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ if (rb_null_event(event)) {
+ rb_inc_iter(iter);
+ goto again;
+ }
+ rb_advance_iter(iter);
+ return event;
+
+ case RINGBUF_TYPE_TIME_EXTEND:
+ /* Internal data, OK to advance */
+ rb_advance_iter(iter);
+ goto again;
+
+ case RINGBUF_TYPE_TIME_STAMP:
+ /* FIXME: not implemented */
+ rb_advance_iter(iter);
+ goto again;
+
+ case RINGBUF_TYPE_DATA:
+ if (ts) {
+ *ts = iter->read_stamp + event->time_delta;
+ ring_buffer_normalize_time_stamp(buffer,
+ cpu_buffer->cpu, ts);
+ }
+ return event;
+
+ default:
+ BUG();
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
+
+static inline int rb_ok_to_lock(void)
+{
+ /*
+ * If an NMI die dumps out the content of the ring buffer
+ * do not grab locks. We also permanently disable the ring
+ * buffer too. A one time deal is all you get from reading
+ * the ring buffer from an NMI.
+ */
+ if (likely(!in_nmi()))
+ return 1;
+
+ tracing_off_permanent();
+ return 0;
+}
+
+/**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ unsigned long flags;
+ int dolock;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return NULL;
+
+ dolock = rb_ok_to_lock();
+ again:
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
+ event = rb_buffer_peek(cpu_buffer, ts);
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ rb_advance_reader(cpu_buffer);
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
+
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ goto again;
+
+ return event;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ struct ring_buffer_event *event;
+ unsigned long flags;
+
+ again:
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_iter_peek(iter, ts);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ goto again;
+
+ return event;
+}
+
+/**
+ * ring_buffer_consume - return an event and consume it
+ * @buffer: The ring buffer to get the next event from
+ *
+ * Returns the next event in the ring buffer, and that event is consumed.
+ * Meaning, that sequential reads will keep returning a different event,
+ * and eventually empty the ring buffer if the producer is slower.
+ */
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event = NULL;
+ unsigned long flags;
+ int dolock;
+
+ dolock = rb_ok_to_lock();
+
+ again:
+ /* might be called in atomic */
+ preempt_disable();
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
+
+ cpu_buffer = buffer->buffers[cpu];
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
+
+ event = rb_buffer_peek(cpu_buffer, ts);
+ if (event)
+ rb_advance_reader(cpu_buffer);
+
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
+
+ out:
+ preempt_enable();
+
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ goto again;
+
+ return event;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_consume);
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @buffer: The ring buffer to read from
+ * @cpu: The cpu buffer to iterate over
+ *
+ * This starts up an iteration through the buffer. It also disables
+ * the recording to the buffer until the reading is finished.
+ * This prevents the reading from being corrupted. This is not
+ * a consuming read, so a producer is not expected.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_iter *iter;
+ unsigned long flags;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return NULL;
+
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return NULL;
+
+ cpu_buffer = buffer->buffers[cpu];
+
+ iter->cpu_buffer = cpu_buffer;
+
+ atomic_inc(&cpu_buffer->record_disabled);
+ synchronize_sched();
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ arch_spin_lock(&cpu_buffer->lock);
+ rb_iter_reset(iter);
+ arch_spin_unlock(&cpu_buffer->lock);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return iter;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_start);
+
+/**
+ * ring_buffer_finish - finish reading the iterator of the buffer
+ * @iter: The iterator retrieved by ring_buffer_start
+ *
+ * This re-enables the recording to the buffer, and frees the
+ * iterator.
+ */
+void
+ring_buffer_read_finish(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+ atomic_dec(&cpu_buffer->record_disabled);
+ kfree(iter);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
+
+/**
+ * ring_buffer_read - read the next item in the ring buffer by the iterator
+ * @iter: The ring buffer iterator
+ * @ts: The time stamp of the event read.
+ *
+ * This reads the next event in the ring buffer and increments the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
+{
+ struct ring_buffer_event *event;
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ again:
+ event = rb_iter_peek(iter, ts);
+ if (!event)
+ goto out;
+
+ if (event->type_len == RINGBUF_TYPE_PADDING)
+ goto again;
+
+ rb_advance_iter(iter);
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return event;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read);
+
+/**
+ * ring_buffer_size - return the size of the ring buffer (in bytes)
+ * @buffer: The ring buffer.
+ */
+unsigned long ring_buffer_size(struct ring_buffer *buffer)
+{
+ return BUF_PAGE_SIZE * buffer->pages;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_size);
+
+static void
+rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ rb_head_page_deactivate(cpu_buffer);
+
+ cpu_buffer->head_page
+ = list_entry(cpu_buffer->pages, struct buffer_page, list);
+ local_set(&cpu_buffer->head_page->write, 0);
+ local_set(&cpu_buffer->head_page->entries, 0);
+ local_set(&cpu_buffer->head_page->page->commit, 0);
+
+ cpu_buffer->head_page->read = 0;
+
+ cpu_buffer->tail_page = cpu_buffer->head_page;
+ cpu_buffer->commit_page = cpu_buffer->head_page;
+
+ INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+ local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
+ cpu_buffer->reader_page->read = 0;
+
+ local_set(&cpu_buffer->commit_overrun, 0);
+ local_set(&cpu_buffer->overrun, 0);
+ local_set(&cpu_buffer->entries, 0);
+ local_set(&cpu_buffer->committing, 0);
+ local_set(&cpu_buffer->commits, 0);
+ cpu_buffer->read = 0;
+
+ cpu_buffer->write_stamp = 0;
+ cpu_buffer->read_stamp = 0;
+
+ rb_head_page_activate(cpu_buffer);
+}
+
+/**
+ * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * @buffer: The ring buffer to reset a per cpu buffer of
+ * @cpu: The CPU buffer to be reset
+ */
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ unsigned long flags;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return;
+
+ atomic_inc(&cpu_buffer->record_disabled);
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+ goto out;
+
+ arch_spin_lock(&cpu_buffer->lock);
+
+ rb_reset_cpu(cpu_buffer);
+
+ arch_spin_unlock(&cpu_buffer->lock);
+
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ atomic_dec(&cpu_buffer->record_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
+
+/**
+ * ring_buffer_reset - reset a ring buffer
+ * @buffer: The ring buffer to reset all cpu buffers
+ */
+void ring_buffer_reset(struct ring_buffer *buffer)
+{
+ int cpu;
+
+ for_each_buffer_cpu(buffer, cpu)
+ ring_buffer_reset_cpu(buffer, cpu);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_reset);
+
+/**
+ * rind_buffer_empty - is the ring buffer empty?
+ * @buffer: The ring buffer to test
+ */
+int ring_buffer_empty(struct ring_buffer *buffer)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+ int dolock;
+ int cpu;
+ int ret;
+
+ dolock = rb_ok_to_lock();
+
+ /* yes this is racy, but if you don't like the race, lock the buffer */
+ for_each_buffer_cpu(buffer, cpu) {
+ cpu_buffer = buffer->buffers[cpu];
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
+ ret = rb_per_cpu_empty(cpu_buffer);
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
+
+ if (!ret)
+ return 0;
+ }
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_empty);
+
+/**
+ * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
+ * @buffer: The ring buffer
+ * @cpu: The CPU buffer to test
+ */
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+ int dolock;
+ int ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 1;
+
+ dolock = rb_ok_to_lock();
+
+ cpu_buffer = buffer->buffers[cpu];
+ local_irq_save(flags);
+ if (dolock)
+ spin_lock(&cpu_buffer->reader_lock);
+ ret = rb_per_cpu_empty(cpu_buffer);
+ if (dolock)
+ spin_unlock(&cpu_buffer->reader_lock);
+ local_irq_restore(flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
+
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+/**
+ * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
+ * @buffer_a: One buffer to swap with
+ * @buffer_b: The other buffer to swap with
+ *
+ * This function is useful for tracers that want to take a "snapshot"
+ * of a CPU buffer and has another back up buffer lying around.
+ * it is expected that the tracer handles the cpu buffer not being
+ * used at the moment.
+ */
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+ struct ring_buffer *buffer_b, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer_a;
+ struct ring_buffer_per_cpu *cpu_buffer_b;
+ int ret = -EINVAL;
+
+ if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
+ !cpumask_test_cpu(cpu, buffer_b->cpumask))
+ goto out;
+
+ /* At least make sure the two buffers are somewhat the same */
+ if (buffer_a->pages != buffer_b->pages)
+ goto out;
+
+ ret = -EAGAIN;
+
+ if (ring_buffer_flags != RB_BUFFERS_ON)
+ goto out;
+
+ if (atomic_read(&buffer_a->record_disabled))
+ goto out;
+
+ if (atomic_read(&buffer_b->record_disabled))
+ goto out;
+
+ cpu_buffer_a = buffer_a->buffers[cpu];
+ cpu_buffer_b = buffer_b->buffers[cpu];
+
+ if (atomic_read(&cpu_buffer_a->record_disabled))
+ goto out;
+
+ if (atomic_read(&cpu_buffer_b->record_disabled))
+ goto out;
+
+ /*
+ * We can't do a synchronize_sched here because this
+ * function can be called in atomic context.
+ * Normally this will be called from the same CPU as cpu.
+ * If not it's up to the caller to protect this.
+ */
+ atomic_inc(&cpu_buffer_a->record_disabled);
+ atomic_inc(&cpu_buffer_b->record_disabled);
+
+ ret = -EBUSY;
+ if (local_read(&cpu_buffer_a->committing))
+ goto out_dec;
+ if (local_read(&cpu_buffer_b->committing))
+ goto out_dec;
+
+ buffer_a->buffers[cpu] = cpu_buffer_b;
+ buffer_b->buffers[cpu] = cpu_buffer_a;
+
+ cpu_buffer_b->buffer = buffer_a;
+ cpu_buffer_a->buffer = buffer_b;
+
+ ret = 0;
+
+out_dec:
+ atomic_dec(&cpu_buffer_a->record_disabled);
+ atomic_dec(&cpu_buffer_b->record_disabled);
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
+#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */
+
+/**
+ * ring_buffer_alloc_read_page - allocate a page to read from buffer
+ * @buffer: the buffer to allocate for.
+ *
+ * This function is used in conjunction with ring_buffer_read_page.
+ * When reading a full page from the ring buffer, these functions
+ * can be used to speed up the process. The calling function should
+ * allocate a few pages first with this function. Then when it
+ * needs to get pages from the ring buffer, it passes the result
+ * of this function into ring_buffer_read_page, which will swap
+ * the page that was allocated, with the read page of the buffer.
+ *
+ * Returns:
+ * The page allocated, or NULL on error.
+ */
+void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
+{
+ struct buffer_data_page *bpage;
+ unsigned long addr;
+
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ return NULL;
+
+ bpage = (void *)addr;
+
+ rb_init_page(bpage);
+
+ return bpage;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
+
+/**
+ * ring_buffer_free_read_page - free an allocated read page
+ * @buffer: the buffer the page was allocate for
+ * @data: the page to free
+ *
+ * Free a page allocated from ring_buffer_alloc_read_page.
+ */
+void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
+{
+ free_page((unsigned long)data);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
+
+/**
+ * ring_buffer_read_page - extract a page from the ring buffer
+ * @buffer: buffer to extract from
+ * @data_page: the page to use allocated from ring_buffer_alloc_read_page
+ * @len: amount to extract
+ * @cpu: the cpu of the buffer to extract
+ * @full: should the extraction only happen when the page is full.
+ *
+ * This function will pull out a page from the ring buffer and consume it.
+ * @data_page must be the address of the variable that was returned
+ * from ring_buffer_alloc_read_page. This is because the page might be used
+ * to swap with a page in the ring buffer.
+ *
+ * for example:
+ * rpage = ring_buffer_alloc_read_page(buffer);
+ * if (!rpage)
+ * return error;
+ * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
+ * if (ret >= 0)
+ * process_page(rpage, ret);
+ *
+ * When @full is set, the function will not return true unless
+ * the writer is off the reader page.
+ *
+ * Note: it is up to the calling functions to handle sleeps and wakeups.
+ * The ring buffer can be used anywhere in the kernel and can not
+ * blindly call wake_up. The layer that uses the ring buffer must be
+ * responsible for that.
+ *
+ * Returns:
+ * >=0 if data has been transferred, returns the offset of consumed data.
+ * <0 if no data has been transferred.
+ */
+int ring_buffer_read_page(struct ring_buffer *buffer,
+ void **data_page, size_t len, int cpu, int full)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ struct buffer_data_page *bpage;
+ struct buffer_page *reader;
+ unsigned long flags;
+ unsigned int commit;
+ unsigned int read;
+ u64 save_timestamp;
+ int ret = -1;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
+
+ /*
+ * If len is not big enough to hold the page header, then
+ * we can not copy anything.
+ */
+ if (len <= BUF_PAGE_HDR_SIZE)
+ goto out;
+
+ len -= BUF_PAGE_HDR_SIZE;
+
+ if (!data_page)
+ goto out;
+
+ bpage = *data_page;
+ if (!bpage)
+ goto out;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ reader = rb_get_reader_page(cpu_buffer);
+ if (!reader)
+ goto out_unlock;
+
+ event = rb_reader_event(cpu_buffer);
+
+ read = reader->read;
+ commit = rb_page_commit(reader);
+
+ /*
+ * If this page has been partially read or
+ * if len is not big enough to read the rest of the page or
+ * a writer is still on the page, then
+ * we must copy the data from the page to the buffer.
+ * Otherwise, we can simply swap the page with the one passed in.
+ */
+ if (read || (len < (commit - read)) ||
+ cpu_buffer->reader_page == cpu_buffer->commit_page) {
+ struct buffer_data_page *rpage = cpu_buffer->reader_page->page;
+ unsigned int rpos = read;
+ unsigned int pos = 0;
+ unsigned int size;
+
+ if (full)
+ goto out_unlock;
+
+ if (len > (commit - read))
+ len = (commit - read);
+
+ size = rb_event_length(event);
+
+ if (len < size)
+ goto out_unlock;
+
+ /* save the current timestamp, since the user will need it */
+ save_timestamp = cpu_buffer->read_stamp;
+
+ /* Need to copy one event at a time */
+ do {
+ memcpy(bpage->data + pos, rpage->data + rpos, size);
+
+ len -= size;
+
+ rb_advance_reader(cpu_buffer);
+ rpos = reader->read;
+ pos += size;
+
+ event = rb_reader_event(cpu_buffer);
+ size = rb_event_length(event);
+ } while (len > size);
+
+ /* update bpage */
+ local_set(&bpage->commit, pos);
+ bpage->time_stamp = save_timestamp;
+
+ /* we copied everything to the beginning */
+ read = 0;
+ } else {
+ /* update the entry counter */
+ cpu_buffer->read += rb_page_entries(reader);
+
+ /* swap the pages */
+ rb_init_page(bpage);
+ bpage = reader->page;
+ reader->page = *data_page;
+ local_set(&reader->write, 0);
+ local_set(&reader->entries, 0);
+ reader->read = 0;
+ *data_page = bpage;
+ }
+ ret = read;
+
+ out_unlock:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page);
+
+#ifdef CONFIG_TRACING
+static ssize_t
+rb_simple_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long *p = filp->private_data;
+ char buf[64];
+ int r;
+
+ if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
+ r = sprintf(buf, "permanently disabled\n");
+ else
+ r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+rb_simple_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long *p = filp->private_data;
+ char buf[64];
+ unsigned long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val)
+ set_bit(RB_BUFFERS_ON_BIT, p);
+ else
+ clear_bit(RB_BUFFERS_ON_BIT, p);
+
+ (*ppos)++;
+
+ return cnt;
+}
+
+static const struct file_operations rb_simple_fops = {
+ .open = tracing_open_generic,
+ .read = rb_simple_read,
+ .write = rb_simple_write,
+};
+
+
+static __init int rb_init_debugfs(void)
+{
+ struct dentry *d_tracer;
+
+ d_tracer = tracing_init_dentry();
+
+ trace_create_file("tracing_on", 0644, d_tracer,
+ &ring_buffer_flags, &rb_simple_fops);
+
+ return 0;
+}
+
+fs_initcall(rb_init_debugfs);
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int rb_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ struct ring_buffer *buffer =
+ container_of(self, struct ring_buffer, cpu_notify);
+ long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ if (cpumask_test_cpu(cpu, buffer->cpumask))
+ return NOTIFY_OK;
+
+ buffer->buffers[cpu] =
+ rb_allocate_cpu_buffer(buffer, cpu);
+ if (!buffer->buffers[cpu]) {
+ WARN(1, "failed to allocate ring buffer on CPU %ld\n",
+ cpu);
+ return NOTIFY_OK;
+ }
+ smp_wmb();
+ cpumask_set_cpu(cpu, buffer->cpumask);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ /*
+ * Do nothing.
+ * If we were to free the buffer, then the user would
+ * lose any trace that was in the buffer.
+ */
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+#endif
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
new file mode 100644
index 00000000000..b2477caf09c
--- /dev/null
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -0,0 +1,486 @@
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/time.h>
+
+struct rb_page {
+ u64 ts;
+ local_t commit;
+ char data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME 10
+#define SLEEP_TIME 10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static struct completion read_start;
+static struct completion read_done;
+
+static struct ring_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = 19;
+static int consumer_nice = 19;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, uint, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, uint, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, uint, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, uint, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
+static int read_events;
+
+static int kill_test;
+
+#define KILL_TEST() \
+ do { \
+ if (!kill_test) { \
+ kill_test = 1; \
+ WARN_ON(1); \
+ } \
+ } while (0)
+
+enum event_status {
+ EVENT_FOUND,
+ EVENT_DROPPED,
+};
+
+static enum event_status read_event(int cpu)
+{
+ struct ring_buffer_event *event;
+ int *entry;
+ u64 ts;
+
+ event = ring_buffer_consume(buffer, cpu, &ts);
+ if (!event)
+ return EVENT_DROPPED;
+
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ return EVENT_DROPPED;
+ }
+
+ read++;
+ return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+ struct ring_buffer_event *event;
+ struct rb_page *rpage;
+ unsigned long commit;
+ void *bpage;
+ int *entry;
+ int ret;
+ int inc;
+ int i;
+
+ bpage = ring_buffer_alloc_read_page(buffer);
+ if (!bpage)
+ return EVENT_DROPPED;
+
+ ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+ if (ret >= 0) {
+ rpage = bpage;
+ commit = local_read(&rpage->commit);
+ for (i = 0; i < commit && !kill_test; i += inc) {
+
+ if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+ KILL_TEST();
+ break;
+ }
+
+ inc = -1;
+ event = (void *)&rpage->data[i];
+ switch (event->type_len) {
+ case RINGBUF_TYPE_PADDING:
+ /* failed writes may be discarded events */
+ if (!event->time_delta)
+ KILL_TEST();
+ inc = event->array[0] + 4;
+ break;
+ case RINGBUF_TYPE_TIME_EXTEND:
+ inc = 8;
+ break;
+ case 0:
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ break;
+ }
+ read++;
+ if (!event->array[0]) {
+ KILL_TEST();
+ break;
+ }
+ inc = event->array[0] + 4;
+ break;
+ default:
+ entry = ring_buffer_event_data(event);
+ if (*entry != cpu) {
+ KILL_TEST();
+ break;
+ }
+ read++;
+ inc = ((event->type_len + 1) * 4);
+ }
+ if (kill_test)
+ break;
+
+ if (inc <= 0) {
+ KILL_TEST();
+ break;
+ }
+ }
+ }
+ ring_buffer_free_read_page(buffer, bpage);
+
+ if (ret < 0)
+ return EVENT_DROPPED;
+ return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+ /* toggle between reading pages and events */
+ read_events ^= 1;
+
+ read = 0;
+ while (!reader_finish && !kill_test) {
+ int found;
+
+ do {
+ int cpu;
+
+ found = 0;
+ for_each_online_cpu(cpu) {
+ enum event_status stat;
+
+ if (read_events)
+ stat = read_event(cpu);
+ else
+ stat = read_page(cpu);
+
+ if (kill_test)
+ break;
+ if (stat == EVENT_FOUND)
+ found = 1;
+ }
+ } while (found && !kill_test);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (reader_finish)
+ break;
+
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+ reader_finish = 0;
+ complete(&read_done);
+}
+
+static void ring_buffer_producer(void)
+{
+ struct timeval start_tv;
+ struct timeval end_tv;
+ unsigned long long time;
+ unsigned long long entries;
+ unsigned long long overruns;
+ unsigned long missed = 0;
+ unsigned long hit = 0;
+ unsigned long avg;
+ int cnt = 0;
+
+ /*
+ * Hammer the buffer for 10 secs (this may
+ * make the system stall)
+ */
+ trace_printk("Starting ring buffer hammer\n");
+ do_gettimeofday(&start_tv);
+ do {
+ struct ring_buffer_event *event;
+ int *entry;
+ int i;
+
+ for (i = 0; i < write_iteration; i++) {
+ event = ring_buffer_lock_reserve(buffer, 10);
+ if (!event) {
+ missed++;
+ } else {
+ hit++;
+ entry = ring_buffer_event_data(event);
+ *entry = smp_processor_id();
+ ring_buffer_unlock_commit(buffer, event);
+ }
+ }
+ do_gettimeofday(&end_tv);
+
+ cnt++;
+ if (consumer && !(cnt % wakeup_interval))
+ wake_up_process(consumer);
+
+#ifndef CONFIG_PREEMPT
+ /*
+ * If we are a non preempt kernel, the 10 second run will
+ * stop everything while it runs. Instead, we will call
+ * cond_resched and also add any time that was lost by a
+ * rescedule.
+ *
+ * Do a cond resched at the same frequency we would wake up
+ * the reader.
+ */
+ if (cnt % wakeup_interval)
+ cond_resched();
+#endif
+
+ } while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
+ trace_printk("End ring buffer hammer\n");
+
+ if (consumer) {
+ /* Init both completions here to avoid races */
+ init_completion(&read_start);
+ init_completion(&read_done);
+ /* the completions must be visible before the finish var */
+ smp_wmb();
+ reader_finish = 1;
+ /* finish var visible before waking up the consumer */
+ smp_wmb();
+ wake_up_process(consumer);
+ wait_for_completion(&read_done);
+ }
+
+ time = end_tv.tv_sec - start_tv.tv_sec;
+ time *= USEC_PER_SEC;
+ time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec);
+
+ entries = ring_buffer_entries(buffer);
+ overruns = ring_buffer_overruns(buffer);
+
+ if (kill_test)
+ trace_printk("ERROR!\n");
+
+ if (!disable_reader) {
+ if (consumer_fifo < 0)
+ trace_printk("Running Consumer at nice: %d\n",
+ consumer_nice);
+ else
+ trace_printk("Running Consumer at SCHED_FIFO %d\n",
+ consumer_fifo);
+ }
+ if (producer_fifo < 0)
+ trace_printk("Running Producer at nice: %d\n",
+ producer_nice);
+ else
+ trace_printk("Running Producer at SCHED_FIFO %d\n",
+ producer_fifo);
+
+ /* Let the user know that the test is running at low priority */
+ if (producer_fifo < 0 && consumer_fifo < 0 &&
+ producer_nice == 19 && consumer_nice == 19)
+ trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
+ trace_printk("Time: %lld (usecs)\n", time);
+ trace_printk("Overruns: %lld\n", overruns);
+ if (disable_reader)
+ trace_printk("Read: (reader disabled)\n");
+ else
+ trace_printk("Read: %ld (by %s)\n", read,
+ read_events ? "events" : "pages");
+ trace_printk("Entries: %lld\n", entries);
+ trace_printk("Total: %lld\n", entries + overruns + read);
+ trace_printk("Missed: %ld\n", missed);
+ trace_printk("Hit: %ld\n", hit);
+
+ /* Convert time from usecs to millisecs */
+ do_div(time, USEC_PER_MSEC);
+ if (time)
+ hit /= (long)time;
+ else
+ trace_printk("TIME IS ZERO??\n");
+
+ trace_printk("Entries per millisec: %ld\n", hit);
+
+ if (hit) {
+ /* Calculate the average time in nanosecs */
+ avg = NSEC_PER_MSEC / hit;
+ trace_printk("%ld ns per entry\n", avg);
+ }
+
+ if (missed) {
+ if (time)
+ missed /= (long)time;
+
+ trace_printk("Total iterations per millisec: %ld\n",
+ hit + missed);
+
+ /* it is possible that hit + missed will overflow and be zero */
+ if (!(hit + missed)) {
+ trace_printk("hit + missed overflowed and totalled zero!\n");
+ hit--; /* make it non zero */
+ }
+
+ /* Caculate the average time in nanosecs */
+ avg = NSEC_PER_MSEC / (hit + missed);
+ trace_printk("%ld ns per entry\n", avg);
+ }
+}
+
+static void wait_to_die(void)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+ while (!kthread_should_stop() && !kill_test) {
+ complete(&read_start);
+
+ ring_buffer_consumer();
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (kthread_should_stop() || kill_test)
+ break;
+
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+ __set_current_state(TASK_RUNNING);
+
+ if (kill_test)
+ wait_to_die();
+
+ return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+ init_completion(&read_start);
+
+ while (!kthread_should_stop() && !kill_test) {
+ ring_buffer_reset(buffer);
+
+ if (consumer) {
+ smp_wmb();
+ wake_up_process(consumer);
+ wait_for_completion(&read_start);
+ }
+
+ ring_buffer_producer();
+
+ trace_printk("Sleeping for 10 secs\n");
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ * SLEEP_TIME);
+ __set_current_state(TASK_RUNNING);
+ }
+
+ if (kill_test)
+ wait_to_die();
+
+ return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+ int ret;
+
+ /* make a one meg buffer in overwite mode */
+ buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+ if (!buffer)
+ return -ENOMEM;
+
+ if (!disable_reader) {
+ consumer = kthread_create(ring_buffer_consumer_thread,
+ NULL, "rb_consumer");
+ ret = PTR_ERR(consumer);
+ if (IS_ERR(consumer))
+ goto out_fail;
+ }
+
+ producer = kthread_run(ring_buffer_producer_thread,
+ NULL, "rb_producer");
+ ret = PTR_ERR(producer);
+
+ if (IS_ERR(producer))
+ goto out_kill;
+
+ /*
+ * Run them as low-prio background tasks by default:
+ */
+ if (!disable_reader) {
+ if (consumer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(consumer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(consumer, consumer_nice);
+ }
+
+ if (producer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(producer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(producer, producer_nice);
+
+ return 0;
+
+ out_kill:
+ if (consumer)
+ kthread_stop(consumer);
+
+ out_fail:
+ ring_buffer_free(buffer);
+ return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+ kthread_stop(producer);
+ if (consumer)
+ kthread_stop(consumer);
+ ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
new file mode 100644
index 00000000000..7d12c179fc2
--- /dev/null
+++ b/kernel/trace/trace.c
@@ -0,0 +1,4560 @@
+/*
+ * ring buffer based function tracer
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Originally taken from the RT patch by:
+ * Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Based on code from the latency_tracer, that is:
+ * Copyright (C) 2004-2006 Ingo Molnar
+ * Copyright (C) 2004 William Lee Irwin III
+ */
+#include <linux/ring_buffer.h>
+#include <generated/utsrelease.h>
+#include <linux/stacktrace.h>
+#include <linux/writeback.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/smp_lock.h>
+#include <linux/notifier.h>
+#include <linux/irqflags.h>
+#include <linux/debugfs.h>
+#include <linux/pagemap.h>
+#include <linux/hardirq.h>
+#include <linux/linkage.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/splice.h>
+#include <linux/kdebug.h>
+#include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE)
+
+/*
+ * On boot up, the ring buffer is set to the minimum size, so that
+ * we do not waste memory on systems that are not using tracing.
+ */
+int ring_buffer_expanded;
+
+/*
+ * We need to change this state when a selftest is running.
+ * A selftest will lurk into the ring-buffer to count the
+ * entries inserted during the selftest although some concurrent
+ * insertions into the ring-buffer such as trace_printk could occurred
+ * at the same time, giving false positive or negative results.
+ */
+static bool __read_mostly tracing_selftest_running;
+
+/*
+ * If a tracer is running, we do not want to run SELFTEST.
+ */
+bool __read_mostly tracing_selftest_disabled;
+
+/* For tracers that don't implement custom flags */
+static struct tracer_opt dummy_tracer_opt[] = {
+ { }
+};
+
+static struct tracer_flags dummy_tracer_flags = {
+ .val = 0,
+ .opts = dummy_tracer_opt
+};
+
+static int dummy_set_flag(u32 old_flags, u32 bit, int set)
+{
+ return 0;
+}
+
+/*
+ * Kill all tracing for good (never come back).
+ * It is initialized to 1 but will turn to zero if the initialization
+ * of the tracer is successful. But that is the only place that sets
+ * this back to zero.
+ */
+static int tracing_disabled = 1;
+
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
+
+static inline void ftrace_disable_cpu(void)
+{
+ preempt_disable();
+ __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
+}
+
+static inline void ftrace_enable_cpu(void)
+{
+ __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
+ preempt_enable();
+}
+
+static cpumask_var_t __read_mostly tracing_buffer_mask;
+
+#define for_each_tracing_cpu(cpu) \
+ for_each_cpu(cpu, tracing_buffer_mask)
+
+/*
+ * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
+ *
+ * If there is an oops (or kernel panic) and the ftrace_dump_on_oops
+ * is set, then ftrace_dump is called. This will output the contents
+ * of the ftrace buffers to the console. This is very useful for
+ * capturing traces that lead to crashes and outputing it to a
+ * serial console.
+ *
+ * It is default off, but you can enable it with either specifying
+ * "ftrace_dump_on_oops" in the kernel command line, or setting
+ * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ */
+int ftrace_dump_on_oops;
+
+static int tracing_set_tracer(const char *buf);
+
+#define MAX_TRACER_SIZE 100
+static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
+static char *default_bootup_tracer;
+
+static int __init set_cmdline_ftrace(char *str)
+{
+ strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
+ default_bootup_tracer = bootup_tracer_buf;
+ /* We are using ftrace early, expand it */
+ ring_buffer_expanded = 1;
+ return 1;
+}
+__setup("ftrace=", set_cmdline_ftrace);
+
+static int __init set_ftrace_dump_on_oops(char *str)
+{
+ ftrace_dump_on_oops = 1;
+ return 1;
+}
+__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
+
+unsigned long long ns2usecs(cycle_t nsec)
+{
+ nsec += 500;
+ do_div(nsec, 1000);
+ return nsec;
+}
+
+/*
+ * The global_trace is the descriptor that holds the tracing
+ * buffers for the live tracing. For each CPU, it contains
+ * a link list of pages that will store trace entries. The
+ * page descriptor of the pages in the memory is used to hold
+ * the link list by linking the lru item in the page descriptor
+ * to each of the pages in the buffer per CPU.
+ *
+ * For each active CPU there is a data field that holds the
+ * pages for the buffer for that CPU. Each CPU has the same number
+ * of pages allocated for its buffer.
+ */
+static struct trace_array global_trace;
+
+static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+
+int filter_current_check_discard(struct ring_buffer *buffer,
+ struct ftrace_event_call *call, void *rec,
+ struct ring_buffer_event *event)
+{
+ return filter_check_discard(call, rec, buffer, event);
+}
+EXPORT_SYMBOL_GPL(filter_current_check_discard);
+
+cycle_t ftrace_now(int cpu)
+{
+ u64 ts;
+
+ /* Early boot up does not have a buffer yet */
+ if (!global_trace.buffer)
+ return trace_clock_local();
+
+ ts = ring_buffer_time_stamp(global_trace.buffer, cpu);
+ ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts);
+
+ return ts;
+}
+
+/*
+ * The max_tr is used to snapshot the global_trace when a maximum
+ * latency is reached. Some tracers will use this to store a maximum
+ * trace while it continues examining live traces.
+ *
+ * The buffers for the max_tr are set up the same as the global_trace.
+ * When a snapshot is taken, the link list of the max_tr is swapped
+ * with the link list of the global_trace and the buffers are reset for
+ * the global_trace so the tracing can continue.
+ */
+static struct trace_array max_tr;
+
+static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
+
+/* tracer_enabled is used to toggle activation of a tracer */
+static int tracer_enabled = 1;
+
+/**
+ * tracing_is_enabled - return tracer_enabled status
+ *
+ * This function is used by other tracers to know the status
+ * of the tracer_enabled flag. Tracers may use this function
+ * to know if it should enable their features when starting
+ * up. See irqsoff tracer for an example (start_irqsoff_tracer).
+ */
+int tracing_is_enabled(void)
+{
+ return tracer_enabled;
+}
+
+/*
+ * trace_buf_size is the size in bytes that is allocated
+ * for a buffer. Note, the number of bytes is always rounded
+ * to page size.
+ *
+ * This number is purposely set to a low number of 16384.
+ * If the dump on oops happens, it will be much appreciated
+ * to not have to wait for all that output. Anyway this can be
+ * boot time and run time configurable.
+ */
+#define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */
+
+static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
+
+/* trace_types holds a link list of available tracers. */
+static struct tracer *trace_types __read_mostly;
+
+/* current_trace points to the tracer that is currently active */
+static struct tracer *current_trace __read_mostly;
+
+/*
+ * trace_types_lock is used to protect the trace_types list.
+ */
+static DEFINE_MUTEX(trace_types_lock);
+
+/*
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ * A) the page of the consumed events may become a normal page
+ * (not reader page) in ring buffer, and this page will be rewrited
+ * by events producer.
+ * B) The page of the consumed events may become a page for splice_read,
+ * and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
+ */
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+ if (cpu == TRACE_PIPE_ALL_CPU) {
+ /* gain it for accessing the whole ring buffer. */
+ down_write(&all_cpu_access_lock);
+ } else {
+ /* gain it for accessing a cpu ring buffer. */
+
+ /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+ down_read(&all_cpu_access_lock);
+
+ /* Secondly block other access to this @cpu ring buffer. */
+ mutex_lock(&per_cpu(cpu_access_lock, cpu));
+ }
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+ if (cpu == TRACE_PIPE_ALL_CPU) {
+ up_write(&all_cpu_access_lock);
+ } else {
+ mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+ up_read(&all_cpu_access_lock);
+ }
+}
+
+static inline void trace_access_lock_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+ (void)cpu;
+ mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+ (void)cpu;
+ mutex_unlock(&access_lock);
+}
+
+static inline void trace_access_lock_init(void)
+{
+}
+
+#endif
+
+/* trace_wait is a waitqueue for tasks blocked on trace_poll */
+static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
+
+/* trace_flags holds trace_options default values */
+unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
+ TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+ TRACE_ITER_GRAPH_TIME;
+
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
+/**
+ * trace_wake_up - wake up tasks waiting for trace input
+ *
+ * Simply wakes up any task that is blocked on the trace_wait
+ * queue. These is used with trace_poll for tasks polling the trace.
+ */
+void trace_wake_up(void)
+{
+ int cpu;
+
+ if (trace_flags & TRACE_ITER_BLOCK)
+ return;
+ /*
+ * The runqueue_is_locked() can fail, but this is the best we
+ * have for now:
+ */
+ cpu = get_cpu();
+ if (!runqueue_is_locked(cpu))
+ wake_up(&trace_wait);
+ put_cpu();
+}
+
+static int __init set_buf_size(char *str)
+{
+ unsigned long buf_size;
+
+ if (!str)
+ return 0;
+ buf_size = memparse(str, &str);
+ /* nr_entries can not be zero */
+ if (buf_size == 0)
+ return 0;
+ trace_buf_size = buf_size;
+ return 1;
+}
+__setup("trace_buf_size=", set_buf_size);
+
+unsigned long nsecs_to_usecs(unsigned long nsecs)
+{
+ return nsecs / 1000;
+}
+
+/* These must match the bit postions in trace_iterator_flags */
+static const char *trace_options[] = {
+ "print-parent",
+ "sym-offset",
+ "sym-addr",
+ "verbose",
+ "raw",
+ "hex",
+ "bin",
+ "block",
+ "stacktrace",
+ "trace_printk",
+ "ftrace_preempt",
+ "branch",
+ "annotate",
+ "userstacktrace",
+ "sym-userobj",
+ "printk-msg-only",
+ "context-info",
+ "latency-format",
+ "sleep-time",
+ "graph-time",
+ NULL
+};
+
+static struct {
+ u64 (*func)(void);
+ const char *name;
+} trace_clocks[] = {
+ { trace_clock_local, "local" },
+ { trace_clock_global, "global" },
+};
+
+int trace_clock_id;
+
+/*
+ * trace_parser_get_init - gets the buffer for trace parser
+ */
+int trace_parser_get_init(struct trace_parser *parser, int size)
+{
+ memset(parser, 0, sizeof(*parser));
+
+ parser->buffer = kmalloc(size, GFP_KERNEL);
+ if (!parser->buffer)
+ return 1;
+
+ parser->size = size;
+ return 0;
+}
+
+/*
+ * trace_parser_put - frees the buffer for trace parser
+ */
+void trace_parser_put(struct trace_parser *parser)
+{
+ kfree(parser->buffer);
+}
+
+/*
+ * trace_get_user - reads the user input string separated by space
+ * (matched by isspace(ch))
+ *
+ * For each string found the 'struct trace_parser' is updated,
+ * and the function returns.
+ *
+ * Returns number of bytes read.
+ *
+ * See kernel/trace/trace.h for 'struct trace_parser' details.
+ */
+int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char ch;
+ size_t read = 0;
+ ssize_t ret;
+
+ if (!*ppos)
+ trace_parser_clear(parser);
+
+ ret = get_user(ch, ubuf++);
+ if (ret)
+ goto out;
+
+ read++;
+ cnt--;
+
+ /*
+ * The parser is not finished with the last write,
+ * continue reading the user input without skipping spaces.
+ */
+ if (!parser->cont) {
+ /* skip white space */
+ while (cnt && isspace(ch)) {
+ ret = get_user(ch, ubuf++);
+ if (ret)
+ goto out;
+ read++;
+ cnt--;
+ }
+
+ /* only spaces were written */
+ if (isspace(ch)) {
+ *ppos += read;
+ ret = read;
+ goto out;
+ }
+
+ parser->idx = 0;
+ }
+
+ /* read the non-space input */
+ while (cnt && !isspace(ch)) {
+ if (parser->idx < parser->size - 1)
+ parser->buffer[parser->idx++] = ch;
+ else {
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = get_user(ch, ubuf++);
+ if (ret)
+ goto out;
+ read++;
+ cnt--;
+ }
+
+ /* We either got finished input or we have to wait for another call. */
+ if (isspace(ch)) {
+ parser->buffer[parser->idx] = 0;
+ parser->cont = false;
+ } else {
+ parser->cont = true;
+ parser->buffer[parser->idx++] = ch;
+ }
+
+ *ppos += read;
+ ret = read;
+
+out:
+ return ret;
+}
+
+ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
+{
+ int len;
+ int ret;
+
+ if (!cnt)
+ return 0;
+
+ if (s->len <= s->readpos)
+ return -EBUSY;
+
+ len = s->len - s->readpos;
+ if (cnt > len)
+ cnt = len;
+ ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
+ if (ret == cnt)
+ return -EFAULT;
+
+ cnt -= ret;
+
+ s->readpos += cnt;
+ return cnt;
+}
+
+static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
+{
+ int len;
+ void *ret;
+
+ if (s->len <= s->readpos)
+ return -EBUSY;
+
+ len = s->len - s->readpos;
+ if (cnt > len)
+ cnt = len;
+ ret = memcpy(buf, s->buffer + s->readpos, cnt);
+ if (!ret)
+ return -EFAULT;
+
+ s->readpos += cnt;
+ return cnt;
+}
+
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a arch_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ *
+ * It is also used in other places outside the update_max_tr
+ * so it needs to be defined outside of the
+ * CONFIG_TRACER_MAX_TRACE.
+ */
+static arch_spinlock_t ftrace_max_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+unsigned long __read_mostly tracing_max_latency;
+unsigned long __read_mostly tracing_thresh;
+
+/*
+ * Copy the new maximum trace into the separate maximum-trace
+ * structure. (this way the maximum trace is permanently saved,
+ * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ */
+static void
+__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+{
+ struct trace_array_cpu *data = tr->data[cpu];
+ struct trace_array_cpu *max_data = tr->data[cpu];
+
+ max_tr.cpu = cpu;
+ max_tr.time_start = data->preempt_timestamp;
+
+ max_data = max_tr.data[cpu];
+ max_data->saved_latency = tracing_max_latency;
+ max_data->critical_start = data->critical_start;
+ max_data->critical_end = data->critical_end;
+
+ memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+ max_data->pid = tsk->pid;
+ max_data->uid = task_uid(tsk);
+ max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+ max_data->policy = tsk->policy;
+ max_data->rt_priority = tsk->rt_priority;
+
+ /* record this tasks comm */
+ tracing_record_cmdline(tsk);
+}
+
+/**
+ * update_max_tr - snapshot all trace buffers from global_trace to max_tr
+ * @tr: tracer
+ * @tsk: the task with the latency
+ * @cpu: The cpu that initiated the trace.
+ *
+ * Flip the buffers between the @tr and the max_tr and record information
+ * about which task was the cause of this latency.
+ */
+void
+update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+{
+ struct ring_buffer *buf = tr->buffer;
+
+ if (trace_stop_count)
+ return;
+
+ WARN_ON_ONCE(!irqs_disabled());
+ arch_spin_lock(&ftrace_max_lock);
+
+ tr->buffer = max_tr.buffer;
+ max_tr.buffer = buf;
+
+ __update_max_tr(tr, tsk, cpu);
+ arch_spin_unlock(&ftrace_max_lock);
+}
+
+/**
+ * update_max_tr_single - only copy one trace over, and reset the rest
+ * @tr - tracer
+ * @tsk - task with the latency
+ * @cpu - the cpu of the buffer to copy.
+ *
+ * Flip the trace of a single CPU buffer between the @tr and the max_tr.
+ */
+void
+update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
+{
+ int ret;
+
+ if (trace_stop_count)
+ return;
+
+ WARN_ON_ONCE(!irqs_disabled());
+ arch_spin_lock(&ftrace_max_lock);
+
+ ftrace_disable_cpu();
+
+ ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
+
+ if (ret == -EBUSY) {
+ /*
+ * We failed to swap the buffer due to a commit taking
+ * place on this CPU. We fail to record, but we reset
+ * the max trace buffer (no one writes directly to it)
+ * and flag that it failed.
+ */
+ trace_array_printk(&max_tr, _THIS_IP_,
+ "Failed to swap buffers due to commit in progress\n");
+ }
+
+ ftrace_enable_cpu();
+
+ WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
+
+ __update_max_tr(tr, tsk, cpu);
+ arch_spin_unlock(&ftrace_max_lock);
+}
+#endif /* CONFIG_TRACER_MAX_TRACE */
+
+/**
+ * register_tracer - register a tracer with the ftrace system.
+ * @type - the plugin for the tracer
+ *
+ * Register a new plugin tracer.
+ */
+int register_tracer(struct tracer *type)
+__releases(kernel_lock)
+__acquires(kernel_lock)
+{
+ struct tracer *t;
+ int ret = 0;
+
+ if (!type->name) {
+ pr_info("Tracer must have a name\n");
+ return -1;
+ }
+
+ if (strlen(type->name) > MAX_TRACER_SIZE) {
+ pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
+ return -1;
+ }
+
+ /*
+ * When this gets called we hold the BKL which means that
+ * preemption is disabled. Various trace selftests however
+ * need to disable and enable preemption for successful tests.
+ * So we drop the BKL here and grab it after the tests again.
+ */
+ unlock_kernel();
+ mutex_lock(&trace_types_lock);
+
+ tracing_selftest_running = true;
+
+ for (t = trace_types; t; t = t->next) {
+ if (strcmp(type->name, t->name) == 0) {
+ /* already found */
+ pr_info("Tracer %s already registered\n",
+ type->name);
+ ret = -1;
+ goto out;
+ }
+ }
+
+ if (!type->set_flag)
+ type->set_flag = &dummy_set_flag;
+ if (!type->flags)
+ type->flags = &dummy_tracer_flags;
+ else
+ if (!type->flags->opts)
+ type->flags->opts = dummy_tracer_opt;
+ if (!type->wait_pipe)
+ type->wait_pipe = default_wait_pipe;
+
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+ if (type->selftest && !tracing_selftest_disabled) {
+ struct tracer *saved_tracer = current_trace;
+ struct trace_array *tr = &global_trace;
+
+ /*
+ * Run a selftest on this tracer.
+ * Here we reset the trace buffer, and set the current
+ * tracer to be this tracer. The tracer can then run some
+ * internal tracing to verify that everything is in order.
+ * If we fail, we do not register this tracer.
+ */
+ tracing_reset_online_cpus(tr);
+
+ current_trace = type;
+ /* the test is responsible for initializing and enabling */
+ pr_info("Testing tracer %s: ", type->name);
+ ret = type->selftest(type, tr);
+ /* the test is responsible for resetting too */
+ current_trace = saved_tracer;
+ if (ret) {
+ printk(KERN_CONT "FAILED!\n");
+ goto out;
+ }
+ /* Only reset on passing, to avoid touching corrupted buffers */
+ tracing_reset_online_cpus(tr);
+
+ printk(KERN_CONT "PASSED\n");
+ }
+#endif
+
+ type->next = trace_types;
+ trace_types = type;
+
+ out:
+ tracing_selftest_running = false;
+ mutex_unlock(&trace_types_lock);
+
+ if (ret || !default_bootup_tracer)
+ goto out_unlock;
+
+ if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE))
+ goto out_unlock;
+
+ printk(KERN_INFO "Starting tracer '%s'\n", type->name);
+ /* Do we want this tracer to start on bootup? */
+ tracing_set_tracer(type->name);
+ default_bootup_tracer = NULL;
+ /* disable other selftests, since this will break it. */
+ tracing_selftest_disabled = 1;
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+ printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n",
+ type->name);
+#endif
+
+ out_unlock:
+ lock_kernel();
+ return ret;
+}
+
+void unregister_tracer(struct tracer *type)
+{
+ struct tracer **t;
+
+ mutex_lock(&trace_types_lock);
+ for (t = &trace_types; *t; t = &(*t)->next) {
+ if (*t == type)
+ goto found;
+ }
+ pr_info("Tracer %s not registered\n", type->name);
+ goto out;
+
+ found:
+ *t = (*t)->next;
+
+ if (type == current_trace && tracer_enabled) {
+ tracer_enabled = 0;
+ tracing_stop();
+ if (current_trace->stop)
+ current_trace->stop(&global_trace);
+ current_trace = &nop_trace;
+ }
+out:
+ mutex_unlock(&trace_types_lock);
+}
+
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
+{
+ ftrace_disable_cpu();
+ ring_buffer_reset_cpu(buffer, cpu);
+ ftrace_enable_cpu();
+}
+
+void tracing_reset(struct trace_array *tr, int cpu)
+{
+ struct ring_buffer *buffer = tr->buffer;
+
+ ring_buffer_record_disable(buffer);
+
+ /* Make sure all commits have finished */
+ synchronize_sched();
+ __tracing_reset(buffer, cpu);
+
+ ring_buffer_record_enable(buffer);
+}
+
+void tracing_reset_online_cpus(struct trace_array *tr)
+{
+ struct ring_buffer *buffer = tr->buffer;
+ int cpu;
+
+ ring_buffer_record_disable(buffer);
+
+ /* Make sure all commits have finished */
+ synchronize_sched();
+
+ tr->time_start = ftrace_now(tr->cpu);
+
+ for_each_online_cpu(cpu)
+ __tracing_reset(buffer, cpu);
+
+ ring_buffer_record_enable(buffer);
+}
+
+void tracing_reset_current(int cpu)
+{
+ tracing_reset(&global_trace, cpu);
+}
+
+void tracing_reset_current_online_cpus(void)
+{
+ tracing_reset_online_cpus(&global_trace);
+}
+
+#define SAVED_CMDLINES 128
+#define NO_CMDLINE_MAP UINT_MAX
+static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
+static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
+static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
+static int cmdline_idx;
+static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+/* temporary disable recording */
+static atomic_t trace_record_cmdline_disabled __read_mostly;
+
+static void trace_init_cmdlines(void)
+{
+ memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
+ memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
+ cmdline_idx = 0;
+}
+
+int is_tracing_stopped(void)
+{
+ return trace_stop_count;
+}
+
+/**
+ * ftrace_off_permanent - disable all ftrace code permanently
+ *
+ * This should only be called when a serious anomally has
+ * been detected. This will turn off the function tracing,
+ * ring buffers, and other tracing utilites. It takes no
+ * locks and can be called from any context.
+ */
+void ftrace_off_permanent(void)
+{
+ tracing_disabled = 1;
+ ftrace_stop();
+ tracing_off_permanent();
+}
+
+/**
+ * tracing_start - quick start of the tracer
+ *
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
+ */
+void tracing_start(void)
+{
+ struct ring_buffer *buffer;
+ unsigned long flags;
+
+ if (tracing_disabled)
+ return;
+
+ spin_lock_irqsave(&tracing_start_lock, flags);
+ if (--trace_stop_count) {
+ if (trace_stop_count < 0) {
+ /* Someone screwed up their debugging */
+ WARN_ON_ONCE(1);
+ trace_stop_count = 0;
+ }
+ goto out;
+ }
+
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
+
+ buffer = global_trace.buffer;
+ if (buffer)
+ ring_buffer_record_enable(buffer);
+
+ buffer = max_tr.buffer;
+ if (buffer)
+ ring_buffer_record_enable(buffer);
+
+ arch_spin_unlock(&ftrace_max_lock);
+
+ ftrace_start();
+ out:
+ spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
+{
+ struct ring_buffer *buffer;
+ unsigned long flags;
+
+ ftrace_stop();
+ spin_lock_irqsave(&tracing_start_lock, flags);
+ if (trace_stop_count++)
+ goto out;
+
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
+
+ buffer = global_trace.buffer;
+ if (buffer)
+ ring_buffer_record_disable(buffer);
+
+ buffer = max_tr.buffer;
+ if (buffer)
+ ring_buffer_record_disable(buffer);
+
+ arch_spin_unlock(&ftrace_max_lock);
+
+ out:
+ spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
+void trace_stop_cmdline_recording(void);
+
+static void trace_save_cmdline(struct task_struct *tsk)
+{
+ unsigned pid, idx;
+
+ if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
+ return;
+
+ /*
+ * It's not the end of the world if we don't get
+ * the lock, but we also don't want to spin
+ * nor do we want to disable interrupts,
+ * so if we miss here, then better luck next time.
+ */
+ if (!arch_spin_trylock(&trace_cmdline_lock))
+ return;
+
+ idx = map_pid_to_cmdline[tsk->pid];
+ if (idx == NO_CMDLINE_MAP) {
+ idx = (cmdline_idx + 1) % SAVED_CMDLINES;
+
+ /*
+ * Check whether the cmdline buffer at idx has a pid
+ * mapped. We are going to overwrite that entry so we
+ * need to clear the map_pid_to_cmdline. Otherwise we
+ * would read the new comm for the old pid.
+ */
+ pid = map_cmdline_to_pid[idx];
+ if (pid != NO_CMDLINE_MAP)
+ map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
+
+ map_cmdline_to_pid[idx] = tsk->pid;
+ map_pid_to_cmdline[tsk->pid] = idx;
+
+ cmdline_idx = idx;
+ }
+
+ memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
+
+ arch_spin_unlock(&trace_cmdline_lock);
+}
+
+void trace_find_cmdline(int pid, char comm[])
+{
+ unsigned map;
+
+ if (!pid) {
+ strcpy(comm, "<idle>");
+ return;
+ }
+
+ if (WARN_ON_ONCE(pid < 0)) {
+ strcpy(comm, "<XXX>");
+ return;
+ }
+
+ if (pid > PID_MAX_DEFAULT) {
+ strcpy(comm, "<...>");
+ return;
+ }
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+ map = map_pid_to_cmdline[pid];
+ if (map != NO_CMDLINE_MAP)
+ strcpy(comm, saved_cmdlines[map]);
+ else
+ strcpy(comm, "<...>");
+
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+}
+
+void tracing_record_cmdline(struct task_struct *tsk)
+{
+ if (atomic_read(&trace_record_cmdline_disabled) || !tracer_enabled ||
+ !tracing_is_on())
+ return;
+
+ trace_save_cmdline(tsk);
+}
+
+void
+tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
+ int pc)
+{
+ struct task_struct *tsk = current;
+
+ entry->preempt_count = pc & 0xff;
+ entry->pid = (tsk) ? tsk->pid : 0;
+ entry->lock_depth = (tsk) ? tsk->lock_depth : 0;
+ entry->flags =
+#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
+ (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
+#else
+ TRACE_FLAG_IRQS_NOSUPPORT |
+#endif
+ ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
+ ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+ (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
+}
+EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
+
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+ int type,
+ unsigned long len,
+ unsigned long flags, int pc)
+{
+ struct ring_buffer_event *event;
+
+ event = ring_buffer_lock_reserve(buffer, len);
+ if (event != NULL) {
+ struct trace_entry *ent = ring_buffer_event_data(event);
+
+ tracing_generic_entry_update(ent, flags, pc);
+ ent->type = type;
+ }
+
+ return event;
+}
+
+static inline void
+__trace_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc,
+ int wake)
+{
+ ring_buffer_unlock_commit(buffer, event);
+
+ ftrace_trace_stack(buffer, flags, 6, pc);
+ ftrace_trace_userstack(buffer, flags, pc);
+
+ if (wake)
+ trace_wake_up();
+}
+
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc)
+{
+ __trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
+}
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
+ int type, unsigned long len,
+ unsigned long flags, int pc)
+{
+ *current_rb = global_trace.buffer;
+ return trace_buffer_lock_reserve(*current_rb,
+ type, len, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
+
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc)
+{
+ __trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
+}
+EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
+
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc)
+{
+ __trace_buffer_unlock_commit(buffer, event, flags, pc, 0);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
+
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ ring_buffer_discard_commit(buffer, event);
+}
+EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
+
+void
+trace_function(struct trace_array *tr,
+ unsigned long ip, unsigned long parent_ip, unsigned long flags,
+ int pc)
+{
+ struct ftrace_event_call *call = &event_function;
+ struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer_event *event;
+ struct ftrace_entry *entry;
+
+ /* If we are reading the ring buffer, don't trace */
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ return;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
+ flags, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+ entry->parent_ip = parent_ip;
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+}
+
+void
+ftrace(struct trace_array *tr, struct trace_array_cpu *data,
+ unsigned long ip, unsigned long parent_ip, unsigned long flags,
+ int pc)
+{
+ if (likely(!atomic_read(&data->disabled)))
+ trace_function(tr, ip, parent_ip, flags, pc);
+}
+
+#ifdef CONFIG_STACKTRACE
+static void __ftrace_trace_stack(struct ring_buffer *buffer,
+ unsigned long flags,
+ int skip, int pc)
+{
+ struct ftrace_event_call *call = &event_kernel_stack;
+ struct ring_buffer_event *event;
+ struct stack_entry *entry;
+ struct stack_trace trace;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ memset(&entry->caller, 0, sizeof(entry->caller));
+
+ trace.nr_entries = 0;
+ trace.max_entries = FTRACE_STACK_ENTRIES;
+ trace.skip = skip;
+ trace.entries = entry->caller;
+
+ save_stack_trace(&trace);
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+}
+
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+ int skip, int pc)
+{
+ if (!(trace_flags & TRACE_ITER_STACKTRACE))
+ return;
+
+ __ftrace_trace_stack(buffer, flags, skip, pc);
+}
+
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+ int pc)
+{
+ __ftrace_trace_stack(tr->buffer, flags, skip, pc);
+}
+
+/**
+ * trace_dump_stack - record a stack back trace in the trace buffer
+ */
+void trace_dump_stack(void)
+{
+ unsigned long flags;
+
+ if (tracing_disabled || tracing_selftest_running)
+ return;
+
+ local_save_flags(flags);
+
+ /* skipping 3 traces, seems to get us at the caller of this function */
+ __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
+}
+
+void
+ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
+{
+ struct ftrace_event_call *call = &event_user_stack;
+ struct ring_buffer_event *event;
+ struct userstack_entry *entry;
+ struct stack_trace trace;
+
+ if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
+ return;
+
+ /*
+ * NMIs can not handle page faults, even with fix ups.
+ * The save user stack can (and often does) fault.
+ */
+ if (unlikely(in_nmi()))
+ return;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+
+ entry->tgid = current->tgid;
+ memset(&entry->caller, 0, sizeof(entry->caller));
+
+ trace.nr_entries = 0;
+ trace.max_entries = FTRACE_STACK_ENTRIES;
+ trace.skip = 0;
+ trace.entries = entry->caller;
+
+ save_stack_trace_user(&trace);
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+}
+
+#ifdef UNUSED
+static void __trace_userstack(struct trace_array *tr, unsigned long flags)
+{
+ ftrace_trace_userstack(tr, flags, preempt_count());
+}
+#endif /* UNUSED */
+
+#endif /* CONFIG_STACKTRACE */
+
+static void
+ftrace_trace_special(void *__tr,
+ unsigned long arg1, unsigned long arg2, unsigned long arg3,
+ int pc)
+{
+ struct ftrace_event_call *call = &event_special;
+ struct ring_buffer_event *event;
+ struct trace_array *tr = __tr;
+ struct ring_buffer *buffer = tr->buffer;
+ struct special_entry *entry;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL,
+ sizeof(*entry), 0, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ entry->arg1 = arg1;
+ entry->arg2 = arg2;
+ entry->arg3 = arg3;
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+void
+__trace_special(void *__tr, void *__data,
+ unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+ ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count());
+}
+
+void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+ struct trace_array *tr = &global_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ int cpu;
+ int pc;
+
+ if (tracing_disabled)
+ return;
+
+ pc = preempt_count();
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+
+ if (likely(atomic_inc_return(&data->disabled) == 1))
+ ftrace_trace_special(tr, arg1, arg2, arg3, pc);
+
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+
+/**
+ * trace_vbprintk - write binary msg to tracing buffer
+ *
+ */
+int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
+{
+ static arch_spinlock_t trace_buf_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+ static u32 trace_buf[TRACE_BUF_SIZE];
+
+ struct ftrace_event_call *call = &event_bprint;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct trace_array *tr = &global_trace;
+ struct trace_array_cpu *data;
+ struct bprint_entry *entry;
+ unsigned long flags;
+ int disable;
+ int resched;
+ int cpu, len = 0, size, pc;
+
+ if (unlikely(tracing_selftest_running || tracing_disabled))
+ return 0;
+
+ /* Don't pollute graph traces with trace_vprintk internals */
+ pause_graph_tracing();
+
+ pc = preempt_count();
+ resched = ftrace_preempt_disable();
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+
+ disable = atomic_inc_return(&data->disabled);
+ if (unlikely(disable != 1))
+ goto out;
+
+ /* Lockdep uses trace_printk for lock tracing */
+ local_irq_save(flags);
+ arch_spin_lock(&trace_buf_lock);
+ len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+
+ if (len > TRACE_BUF_SIZE || len < 0)
+ goto out_unlock;
+
+ size = sizeof(*entry) + sizeof(u32) * len;
+ buffer = tr->buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+ flags, pc);
+ if (!event)
+ goto out_unlock;
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+ entry->fmt = fmt;
+
+ memcpy(entry->buf, trace_buf, sizeof(u32) * len);
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+
+out_unlock:
+ arch_spin_unlock(&trace_buf_lock);
+ local_irq_restore(flags);
+
+out:
+ atomic_dec_return(&data->disabled);
+ ftrace_preempt_enable(resched);
+ unpause_graph_tracing();
+
+ return len;
+}
+EXPORT_SYMBOL_GPL(trace_vbprintk);
+
+int trace_array_printk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ va_start(ap, fmt);
+ ret = trace_array_vprintk(tr, ip, fmt, ap);
+ va_end(ap);
+ return ret;
+}
+
+int trace_array_vprintk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, va_list args)
+{
+ static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+ static char trace_buf[TRACE_BUF_SIZE];
+
+ struct ftrace_event_call *call = &event_print;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct trace_array_cpu *data;
+ int cpu, len = 0, size, pc;
+ struct print_entry *entry;
+ unsigned long irq_flags;
+ int disable;
+
+ if (tracing_disabled || tracing_selftest_running)
+ return 0;
+
+ pc = preempt_count();
+ preempt_disable_notrace();
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+
+ disable = atomic_inc_return(&data->disabled);
+ if (unlikely(disable != 1))
+ goto out;
+
+ pause_graph_tracing();
+ raw_local_irq_save(irq_flags);
+ arch_spin_lock(&trace_buf_lock);
+ len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+
+ size = sizeof(*entry) + len + 1;
+ buffer = tr->buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+ irq_flags, pc);
+ if (!event)
+ goto out_unlock;
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+
+ memcpy(&entry->buf, trace_buf, len);
+ entry->buf[len] = '\0';
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+
+ out_unlock:
+ arch_spin_unlock(&trace_buf_lock);
+ raw_local_irq_restore(irq_flags);
+ unpause_graph_tracing();
+ out:
+ atomic_dec_return(&data->disabled);
+ preempt_enable_notrace();
+
+ return len;
+}
+
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+{
+ return trace_array_vprintk(&global_trace, ip, fmt, args);
+}
+EXPORT_SYMBOL_GPL(trace_vprintk);
+
+enum trace_file_type {
+ TRACE_FILE_LAT_FMT = 1,
+ TRACE_FILE_ANNOTATE = 2,
+};
+
+static void trace_iterator_increment(struct trace_iterator *iter)
+{
+ /* Don't allow ftrace to trace into the ring buffers */
+ ftrace_disable_cpu();
+
+ iter->idx++;
+ if (iter->buffer_iter[iter->cpu])
+ ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+
+ ftrace_enable_cpu();
+}
+
+static struct trace_entry *
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+{
+ struct ring_buffer_event *event;
+ struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
+
+ /* Don't allow ftrace to trace into the ring buffers */
+ ftrace_disable_cpu();
+
+ if (buf_iter)
+ event = ring_buffer_iter_peek(buf_iter, ts);
+ else
+ event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+
+ ftrace_enable_cpu();
+
+ return event ? ring_buffer_event_data(event) : NULL;
+}
+
+static struct trace_entry *
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+{
+ struct ring_buffer *buffer = iter->tr->buffer;
+ struct trace_entry *ent, *next = NULL;
+ int cpu_file = iter->cpu_file;
+ u64 next_ts = 0, ts;
+ int next_cpu = -1;
+ int cpu;
+
+ /*
+ * If we are in a per_cpu trace file, don't bother by iterating over
+ * all cpu and peek directly.
+ */
+ if (cpu_file > TRACE_PIPE_ALL_CPU) {
+ if (ring_buffer_empty_cpu(buffer, cpu_file))
+ return NULL;
+ ent = peek_next_entry(iter, cpu_file, ent_ts);
+ if (ent_cpu)
+ *ent_cpu = cpu_file;
+
+ return ent;
+ }
+
+ for_each_tracing_cpu(cpu) {
+
+ if (ring_buffer_empty_cpu(buffer, cpu))
+ continue;
+
+ ent = peek_next_entry(iter, cpu, &ts);
+
+ /*
+ * Pick the entry with the smallest timestamp:
+ */
+ if (ent && (!next || ts < next_ts)) {
+ next = ent;
+ next_cpu = cpu;
+ next_ts = ts;
+ }
+ }
+
+ if (ent_cpu)
+ *ent_cpu = next_cpu;
+
+ if (ent_ts)
+ *ent_ts = next_ts;
+
+ return next;
+}
+
+/* Find the next real entry, without updating the iterator itself */
+struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
+ int *ent_cpu, u64 *ent_ts)
+{
+ return __find_next_entry(iter, ent_cpu, ent_ts);
+}
+
+/* Find the next real entry, and increment the iterator to the next entry */
+static void *find_next_entry_inc(struct trace_iterator *iter)
+{
+ iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+
+ if (iter->ent)
+ trace_iterator_increment(iter);
+
+ return iter->ent ? iter : NULL;
+}
+
+static void trace_consume(struct trace_iterator *iter)
+{
+ /* Don't allow ftrace to trace into the ring buffers */
+ ftrace_disable_cpu();
+ ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+ ftrace_enable_cpu();
+}
+
+static void *s_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct trace_iterator *iter = m->private;
+ int i = (int)*pos;
+ void *ent;
+
+ WARN_ON_ONCE(iter->leftover);
+
+ (*pos)++;
+
+ /* can't go backwards */
+ if (iter->idx > i)
+ return NULL;
+
+ if (iter->idx < 0)
+ ent = find_next_entry_inc(iter);
+ else
+ ent = iter;
+
+ while (ent && iter->idx < i)
+ ent = find_next_entry_inc(iter);
+
+ iter->pos = *pos;
+
+ return ent;
+}
+
+static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+{
+ struct trace_array *tr = iter->tr;
+ struct ring_buffer_event *event;
+ struct ring_buffer_iter *buf_iter;
+ unsigned long entries = 0;
+ u64 ts;
+
+ tr->data[cpu]->skipped_entries = 0;
+
+ if (!iter->buffer_iter[cpu])
+ return;
+
+ buf_iter = iter->buffer_iter[cpu];
+ ring_buffer_iter_reset(buf_iter);
+
+ /*
+ * We could have the case with the max latency tracers
+ * that a reset never took place on a cpu. This is evident
+ * by the timestamp being before the start of the buffer.
+ */
+ while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+ if (ts >= iter->tr->time_start)
+ break;
+ entries++;
+ ring_buffer_read(buf_iter, NULL);
+ }
+
+ tr->data[cpu]->skipped_entries = entries;
+}
+
+/*
+ * The current tracer is copied to avoid a global locking
+ * all around.
+ */
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+ struct trace_iterator *iter = m->private;
+ static struct tracer *old_tracer;
+ int cpu_file = iter->cpu_file;
+ void *p = NULL;
+ loff_t l = 0;
+ int cpu;
+
+ /* copy the tracer to avoid using a global lock all around */
+ mutex_lock(&trace_types_lock);
+ if (unlikely(old_tracer != current_trace && current_trace)) {
+ old_tracer = current_trace;
+ *iter->trace = *current_trace;
+ }
+ mutex_unlock(&trace_types_lock);
+
+ atomic_inc(&trace_record_cmdline_disabled);
+
+ if (*pos != iter->pos) {
+ iter->ent = NULL;
+ iter->cpu = 0;
+ iter->idx = -1;
+
+ ftrace_disable_cpu();
+
+ if (cpu_file == TRACE_PIPE_ALL_CPU) {
+ for_each_tracing_cpu(cpu)
+ tracing_iter_reset(iter, cpu);
+ } else
+ tracing_iter_reset(iter, cpu_file);
+
+ ftrace_enable_cpu();
+
+ iter->leftover = 0;
+ for (p = iter; p && l < *pos; p = s_next(m, p, &l))
+ ;
+
+ } else {
+ /*
+ * If we overflowed the seq_file before, then we want
+ * to just reuse the trace_seq buffer again.
+ */
+ if (iter->leftover)
+ p = iter;
+ else {
+ l = *pos - 1;
+ p = s_next(m, p, &l);
+ }
+ }
+
+ trace_event_read_lock();
+ trace_access_lock(cpu_file);
+ return p;
+}
+
+static void s_stop(struct seq_file *m, void *p)
+{
+ struct trace_iterator *iter = m->private;
+
+ atomic_dec(&trace_record_cmdline_disabled);
+ trace_access_unlock(iter->cpu_file);
+ trace_event_read_unlock();
+}
+
+static void print_lat_help_header(struct seq_file *m)
+{
+ seq_puts(m, "# _------=> CPU# \n");
+ seq_puts(m, "# / _-----=> irqs-off \n");
+ seq_puts(m, "# | / _----=> need-resched \n");
+ seq_puts(m, "# || / _---=> hardirq/softirq \n");
+ seq_puts(m, "# ||| / _--=> preempt-depth \n");
+ seq_puts(m, "# |||| /_--=> lock-depth \n");
+ seq_puts(m, "# |||||/ delay \n");
+ seq_puts(m, "# cmd pid |||||| time | caller \n");
+ seq_puts(m, "# \\ / |||||| \\ | / \n");
+}
+
+static void print_func_help_header(struct seq_file *m)
+{
+ seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | |\n");
+}
+
+
+static void
+print_trace_header(struct seq_file *m, struct trace_iterator *iter)
+{
+ unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+ struct trace_array *tr = iter->tr;
+ struct trace_array_cpu *data = tr->data[tr->cpu];
+ struct tracer *type = current_trace;
+ unsigned long entries = 0;
+ unsigned long total = 0;
+ unsigned long count;
+ const char *name = "preemption";
+ int cpu;
+
+ if (type)
+ name = type->name;
+
+
+ for_each_tracing_cpu(cpu) {
+ count = ring_buffer_entries_cpu(tr->buffer, cpu);
+ /*
+ * If this buffer has skipped entries, then we hold all
+ * entries for the trace and we need to ignore the
+ * ones before the time stamp.
+ */
+ if (tr->data[cpu]->skipped_entries) {
+ count -= tr->data[cpu]->skipped_entries;
+ /* total is the same as the entries */
+ total += count;
+ } else
+ total += count +
+ ring_buffer_overrun_cpu(tr->buffer, cpu);
+ entries += count;
+ }
+
+ seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
+ name, UTS_RELEASE);
+ seq_puts(m, "# -----------------------------------"
+ "---------------------------------\n");
+ seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |"
+ " (M:%s VP:%d, KP:%d, SP:%d HP:%d",
+ nsecs_to_usecs(data->saved_latency),
+ entries,
+ total,
+ tr->cpu,
+#if defined(CONFIG_PREEMPT_NONE)
+ "server",
+#elif defined(CONFIG_PREEMPT_VOLUNTARY)
+ "desktop",
+#elif defined(CONFIG_PREEMPT)
+ "preempt",
+#else
+ "unknown",
+#endif
+ /* These are reserved for later use */
+ 0, 0, 0, 0);
+#ifdef CONFIG_SMP
+ seq_printf(m, " #P:%d)\n", num_online_cpus());
+#else
+ seq_puts(m, ")\n");
+#endif
+ seq_puts(m, "# -----------------\n");
+ seq_printf(m, "# | task: %.16s-%d "
+ "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n",
+ data->comm, data->pid, data->uid, data->nice,
+ data->policy, data->rt_priority);
+ seq_puts(m, "# -----------------\n");
+
+ if (data->critical_start) {
+ seq_puts(m, "# => started at: ");
+ seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags);
+ trace_print_seq(m, &iter->seq);
+ seq_puts(m, "\n# => ended at: ");
+ seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
+ trace_print_seq(m, &iter->seq);
+ seq_puts(m, "\n#\n");
+ }
+
+ seq_puts(m, "#\n");
+}
+
+static void test_cpu_buff_start(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+
+ if (!(trace_flags & TRACE_ITER_ANNOTATE))
+ return;
+
+ if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
+ return;
+
+ if (cpumask_test_cpu(iter->cpu, iter->started))
+ return;
+
+ if (iter->tr->data[iter->cpu]->skipped_entries)
+ return;
+
+ cpumask_set_cpu(iter->cpu, iter->started);
+
+ /* Don't print started cpu buffer for the first entry of the trace */
+ if (iter->idx > 1)
+ trace_seq_printf(s, "##### CPU %u buffer started ####\n",
+ iter->cpu);
+}
+
+static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+ struct trace_entry *entry;
+ struct trace_event *event;
+
+ entry = iter->ent;
+
+ test_cpu_buff_start(iter);
+
+ event = ftrace_find_event(entry->type);
+
+ if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+ if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+ if (!trace_print_lat_context(iter))
+ goto partial;
+ } else {
+ if (!trace_print_context(iter))
+ goto partial;
+ }
+ }
+
+ if (event)
+ return event->trace(iter, sym_flags);
+
+ if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry;
+ struct trace_event *event;
+
+ entry = iter->ent;
+
+ if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+ if (!trace_seq_printf(s, "%d %d %llu ",
+ entry->pid, iter->cpu, iter->ts))
+ goto partial;
+ }
+
+ event = ftrace_find_event(entry->type);
+ if (event)
+ return event->raw(iter, 0);
+
+ if (!trace_seq_printf(s, "%d ?\n", entry->type))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ unsigned char newline = '\n';
+ struct trace_entry *entry;
+ struct trace_event *event;
+
+ entry = iter->ent;
+
+ if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+ SEQ_PUT_HEX_FIELD_RET(s, entry->pid);
+ SEQ_PUT_HEX_FIELD_RET(s, iter->cpu);
+ SEQ_PUT_HEX_FIELD_RET(s, iter->ts);
+ }
+
+ event = ftrace_find_event(entry->type);
+ if (event) {
+ enum print_line_t ret = event->hex(iter, 0);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
+ }
+
+ SEQ_PUT_FIELD_RET(s, newline);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry;
+ struct trace_event *event;
+
+ entry = iter->ent;
+
+ if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+ SEQ_PUT_FIELD_RET(s, entry->pid);
+ SEQ_PUT_FIELD_RET(s, iter->cpu);
+ SEQ_PUT_FIELD_RET(s, iter->ts);
+ }
+
+ event = ftrace_find_event(entry->type);
+ return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+}
+
+static int trace_empty(struct trace_iterator *iter)
+{
+ int cpu;
+
+ /* If we are looking at one CPU buffer, only check that one */
+ if (iter->cpu_file != TRACE_PIPE_ALL_CPU) {
+ cpu = iter->cpu_file;
+ if (iter->buffer_iter[cpu]) {
+ if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+ return 0;
+ } else {
+ if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+ return 0;
+ }
+ return 1;
+ }
+
+ for_each_tracing_cpu(cpu) {
+ if (iter->buffer_iter[cpu]) {
+ if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+ return 0;
+ } else {
+ if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+/* Called with trace_event_read_lock() held. */
+static enum print_line_t print_trace_line(struct trace_iterator *iter)
+{
+ enum print_line_t ret;
+
+ if (iter->trace && iter->trace->print_line) {
+ ret = iter->trace->print_line(iter);
+ if (ret != TRACE_TYPE_UNHANDLED)
+ return ret;
+ }
+
+ if (iter->ent->type == TRACE_BPRINT &&
+ trace_flags & TRACE_ITER_PRINTK &&
+ trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+ return trace_print_bprintk_msg_only(iter);
+
+ if (iter->ent->type == TRACE_PRINT &&
+ trace_flags & TRACE_ITER_PRINTK &&
+ trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+ return trace_print_printk_msg_only(iter);
+
+ if (trace_flags & TRACE_ITER_BIN)
+ return print_bin_fmt(iter);
+
+ if (trace_flags & TRACE_ITER_HEX)
+ return print_hex_fmt(iter);
+
+ if (trace_flags & TRACE_ITER_RAW)
+ return print_raw_fmt(iter);
+
+ return print_trace_fmt(iter);
+}
+
+static int s_show(struct seq_file *m, void *v)
+{
+ struct trace_iterator *iter = v;
+ int ret;
+
+ if (iter->ent == NULL) {
+ if (iter->tr) {
+ seq_printf(m, "# tracer: %s\n", iter->trace->name);
+ seq_puts(m, "#\n");
+ }
+ if (iter->trace && iter->trace->print_header)
+ iter->trace->print_header(m);
+ else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+ /* print nothing if the buffers are empty */
+ if (trace_empty(iter))
+ return 0;
+ print_trace_header(m, iter);
+ if (!(trace_flags & TRACE_ITER_VERBOSE))
+ print_lat_help_header(m);
+ } else {
+ if (!(trace_flags & TRACE_ITER_VERBOSE))
+ print_func_help_header(m);
+ }
+ } else if (iter->leftover) {
+ /*
+ * If we filled the seq_file buffer earlier, we
+ * want to just show it now.
+ */
+ ret = trace_print_seq(m, &iter->seq);
+
+ /* ret should this time be zero, but you never know */
+ iter->leftover = ret;
+
+ } else {
+ print_trace_line(iter);
+ ret = trace_print_seq(m, &iter->seq);
+ /*
+ * If we overflow the seq_file buffer, then it will
+ * ask us for this data again at start up.
+ * Use that instead.
+ * ret is 0 if seq_file write succeeded.
+ * -1 otherwise.
+ */
+ iter->leftover = ret;
+ }
+
+ return 0;
+}
+
+static const struct seq_operations tracer_seq_ops = {
+ .start = s_start,
+ .next = s_next,
+ .stop = s_stop,
+ .show = s_show,
+};
+
+static struct trace_iterator *
+__tracing_open(struct inode *inode, struct file *file)
+{
+ long cpu_file = (long) inode->i_private;
+ void *fail_ret = ERR_PTR(-ENOMEM);
+ struct trace_iterator *iter;
+ struct seq_file *m;
+ int cpu, ret;
+
+ if (tracing_disabled)
+ return ERR_PTR(-ENODEV);
+
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * We make a copy of the current tracer to avoid concurrent
+ * changes on it while we are reading.
+ */
+ mutex_lock(&trace_types_lock);
+ iter->trace = kzalloc(sizeof(*iter->trace), GFP_KERNEL);
+ if (!iter->trace)
+ goto fail;
+
+ if (current_trace)
+ *iter->trace = *current_trace;
+
+ if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
+ goto fail;
+
+ if (current_trace && current_trace->print_max)
+ iter->tr = &max_tr;
+ else
+ iter->tr = &global_trace;
+ iter->pos = -1;
+ mutex_init(&iter->mutex);
+ iter->cpu_file = cpu_file;
+
+ /* Notify the tracer early; before we stop tracing. */
+ if (iter->trace && iter->trace->open)
+ iter->trace->open(iter);
+
+ /* Annotate start of buffers if we had overruns */
+ if (ring_buffer_overruns(iter->tr->buffer))
+ iter->iter_flags |= TRACE_FILE_ANNOTATE;
+
+ /* stop the trace while dumping */
+ tracing_stop();
+
+ if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
+ for_each_tracing_cpu(cpu) {
+
+ iter->buffer_iter[cpu] =
+ ring_buffer_read_start(iter->tr->buffer, cpu);
+ tracing_iter_reset(iter, cpu);
+ }
+ } else {
+ cpu = iter->cpu_file;
+ iter->buffer_iter[cpu] =
+ ring_buffer_read_start(iter->tr->buffer, cpu);
+ tracing_iter_reset(iter, cpu);
+ }
+
+ ret = seq_open(file, &tracer_seq_ops);
+ if (ret < 0) {
+ fail_ret = ERR_PTR(ret);
+ goto fail_buffer;
+ }
+
+ m = file->private_data;
+ m->private = iter;
+
+ mutex_unlock(&trace_types_lock);
+
+ return iter;
+
+ fail_buffer:
+ for_each_tracing_cpu(cpu) {
+ if (iter->buffer_iter[cpu])
+ ring_buffer_read_finish(iter->buffer_iter[cpu]);
+ }
+ free_cpumask_var(iter->started);
+ tracing_start();
+ fail:
+ mutex_unlock(&trace_types_lock);
+ kfree(iter->trace);
+ kfree(iter);
+
+ return fail_ret;
+}
+
+int tracing_open_generic(struct inode *inode, struct file *filp)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+
+ filp->private_data = inode->i_private;
+ return 0;
+}
+
+static int tracing_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *m = (struct seq_file *)file->private_data;
+ struct trace_iterator *iter;
+ int cpu;
+
+ if (!(file->f_mode & FMODE_READ))
+ return 0;
+
+ iter = m->private;
+
+ mutex_lock(&trace_types_lock);
+ for_each_tracing_cpu(cpu) {
+ if (iter->buffer_iter[cpu])
+ ring_buffer_read_finish(iter->buffer_iter[cpu]);
+ }
+
+ if (iter->trace && iter->trace->close)
+ iter->trace->close(iter);
+
+ /* reenable tracing if it was previously enabled */
+ tracing_start();
+ mutex_unlock(&trace_types_lock);
+
+ seq_release(inode, file);
+ mutex_destroy(&iter->mutex);
+ free_cpumask_var(iter->started);
+ kfree(iter->trace);
+ kfree(iter);
+ return 0;
+}
+
+static int tracing_open(struct inode *inode, struct file *file)
+{
+ struct trace_iterator *iter;
+ int ret = 0;
+
+ /* If this file was open for write, then erase contents */
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC)) {
+ long cpu = (long) inode->i_private;
+
+ if (cpu == TRACE_PIPE_ALL_CPU)
+ tracing_reset_online_cpus(&global_trace);
+ else
+ tracing_reset(&global_trace, cpu);
+ }
+
+ if (file->f_mode & FMODE_READ) {
+ iter = __tracing_open(inode, file);
+ if (IS_ERR(iter))
+ ret = PTR_ERR(iter);
+ else if (trace_flags & TRACE_ITER_LATENCY_FMT)
+ iter->iter_flags |= TRACE_FILE_LAT_FMT;
+ }
+ return ret;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct tracer *t = v;
+
+ (*pos)++;
+
+ if (t)
+ t = t->next;
+
+ return t;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+ struct tracer *t;
+ loff_t l = 0;
+
+ mutex_lock(&trace_types_lock);
+ for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
+ ;
+
+ return t;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&trace_types_lock);
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+ struct tracer *t = v;
+
+ if (!t)
+ return 0;
+
+ seq_printf(m, "%s", t->name);
+ if (t->next)
+ seq_putc(m, ' ');
+ else
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static const struct seq_operations show_traces_seq_ops = {
+ .start = t_start,
+ .next = t_next,
+ .stop = t_stop,
+ .show = t_show,
+};
+
+static int show_traces_open(struct inode *inode, struct file *file)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+
+ return seq_open(file, &show_traces_seq_ops);
+}
+
+static ssize_t
+tracing_write_stub(struct file *filp, const char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ return count;
+}
+
+static const struct file_operations tracing_fops = {
+ .open = tracing_open,
+ .read = seq_read,
+ .write = tracing_write_stub,
+ .llseek = seq_lseek,
+ .release = tracing_release,
+};
+
+static const struct file_operations show_traces_fops = {
+ .open = show_traces_open,
+ .read = seq_read,
+ .release = seq_release,
+};
+
+/*
+ * Only trace on a CPU if the bitmask is set:
+ */
+static cpumask_var_t tracing_cpumask;
+
+/*
+ * The tracer itself will not take this lock, but still we want
+ * to provide a consistent cpumask to user-space:
+ */
+static DEFINE_MUTEX(tracing_cpumask_update_lock);
+
+/*
+ * Temporary storage for the character representation of the
+ * CPU bitmask (and one more byte for the newline):
+ */
+static char mask_str[NR_CPUS + 1];
+
+static ssize_t
+tracing_cpumask_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ int len;
+
+ mutex_lock(&tracing_cpumask_update_lock);
+
+ len = cpumask_scnprintf(mask_str, count, tracing_cpumask);
+ if (count - len < 2) {
+ count = -EINVAL;
+ goto out_err;
+ }
+ len += sprintf(mask_str + len, "\n");
+ count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+
+out_err:
+ mutex_unlock(&tracing_cpumask_update_lock);
+
+ return count;
+}
+
+static ssize_t
+tracing_cpumask_write(struct file *filp, const char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ int err, cpu;
+ cpumask_var_t tracing_cpumask_new;
+
+ if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+ return -ENOMEM;
+
+ err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
+ if (err)
+ goto err_unlock;
+
+ mutex_lock(&tracing_cpumask_update_lock);
+
+ local_irq_disable();
+ arch_spin_lock(&ftrace_max_lock);
+ for_each_tracing_cpu(cpu) {
+ /*
+ * Increase/decrease the disabled counter if we are
+ * about to flip a bit in the cpumask:
+ */
+ if (cpumask_test_cpu(cpu, tracing_cpumask) &&
+ !cpumask_test_cpu(cpu, tracing_cpumask_new)) {
+ atomic_inc(&global_trace.data[cpu]->disabled);
+ }
+ if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
+ cpumask_test_cpu(cpu, tracing_cpumask_new)) {
+ atomic_dec(&global_trace.data[cpu]->disabled);
+ }
+ }
+ arch_spin_unlock(&ftrace_max_lock);
+ local_irq_enable();
+
+ cpumask_copy(tracing_cpumask, tracing_cpumask_new);
+
+ mutex_unlock(&tracing_cpumask_update_lock);
+ free_cpumask_var(tracing_cpumask_new);
+
+ return count;
+
+err_unlock:
+ free_cpumask_var(tracing_cpumask_new);
+
+ return err;
+}
+
+static const struct file_operations tracing_cpumask_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_cpumask_read,
+ .write = tracing_cpumask_write,
+};
+
+static int tracing_trace_options_show(struct seq_file *m, void *v)
+{
+ struct tracer_opt *trace_opts;
+ u32 tracer_flags;
+ int i;
+
+ mutex_lock(&trace_types_lock);
+ tracer_flags = current_trace->flags->val;
+ trace_opts = current_trace->flags->opts;
+
+ for (i = 0; trace_options[i]; i++) {
+ if (trace_flags & (1 << i))
+ seq_printf(m, "%s\n", trace_options[i]);
+ else
+ seq_printf(m, "no%s\n", trace_options[i]);
+ }
+
+ for (i = 0; trace_opts[i].name; i++) {
+ if (tracer_flags & trace_opts[i].bit)
+ seq_printf(m, "%s\n", trace_opts[i].name);
+ else
+ seq_printf(m, "no%s\n", trace_opts[i].name);
+ }
+ mutex_unlock(&trace_types_lock);
+
+ return 0;
+}
+
+static int __set_tracer_option(struct tracer *trace,
+ struct tracer_flags *tracer_flags,
+ struct tracer_opt *opts, int neg)
+{
+ int ret;
+
+ ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
+ if (ret)
+ return ret;
+
+ if (neg)
+ tracer_flags->val &= ~opts->bit;
+ else
+ tracer_flags->val |= opts->bit;
+ return 0;
+}
+
+/* Try to assign a tracer specific option */
+static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
+{
+ struct tracer_flags *tracer_flags = trace->flags;
+ struct tracer_opt *opts = NULL;
+ int i;
+
+ for (i = 0; tracer_flags->opts[i].name; i++) {
+ opts = &tracer_flags->opts[i];
+
+ if (strcmp(cmp, opts->name) == 0)
+ return __set_tracer_option(trace, trace->flags,
+ opts, neg);
+ }
+
+ return -EINVAL;
+}
+
+static void set_tracer_flags(unsigned int mask, int enabled)
+{
+ /* do nothing if flag is already set */
+ if (!!(trace_flags & mask) == !!enabled)
+ return;
+
+ if (enabled)
+ trace_flags |= mask;
+ else
+ trace_flags &= ~mask;
+}
+
+static ssize_t
+tracing_trace_options_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64];
+ char *cmp;
+ int neg = 0;
+ int ret;
+ int i;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+ cmp = strstrip(buf);
+
+ if (strncmp(cmp, "no", 2) == 0) {
+ neg = 1;
+ cmp += 2;
+ }
+
+ for (i = 0; trace_options[i]; i++) {
+ if (strcmp(cmp, trace_options[i]) == 0) {
+ set_tracer_flags(1 << i, !neg);
+ break;
+ }
+ }
+
+ /* If no option could be set, test the specific tracer options */
+ if (!trace_options[i]) {
+ mutex_lock(&trace_types_lock);
+ ret = set_tracer_option(current_trace, cmp, neg);
+ mutex_unlock(&trace_types_lock);
+ if (ret)
+ return ret;
+ }
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+static int tracing_trace_options_open(struct inode *inode, struct file *file)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+ return single_open(file, tracing_trace_options_show, NULL);
+}
+
+static const struct file_operations tracing_iter_fops = {
+ .open = tracing_trace_options_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .write = tracing_trace_options_write,
+};
+
+static const char readme_msg[] =
+ "tracing mini-HOWTO:\n\n"
+ "# mount -t debugfs nodev /sys/kernel/debug\n\n"
+ "# cat /sys/kernel/debug/tracing/available_tracers\n"
+ "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
+ "# cat /sys/kernel/debug/tracing/current_tracer\n"
+ "nop\n"
+ "# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n"
+ "# cat /sys/kernel/debug/tracing/current_tracer\n"
+ "sched_switch\n"
+ "# cat /sys/kernel/debug/tracing/trace_options\n"
+ "noprint-parent nosym-offset nosym-addr noverbose\n"
+ "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
+ "# echo 1 > /sys/kernel/debug/tracing/tracing_enabled\n"
+ "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n"
+ "# echo 0 > /sys/kernel/debug/tracing/tracing_enabled\n"
+;
+
+static ssize_t
+tracing_readme_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return simple_read_from_buffer(ubuf, cnt, ppos,
+ readme_msg, strlen(readme_msg));
+}
+
+static const struct file_operations tracing_readme_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_readme_read,
+};
+
+static ssize_t
+tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *buf_comm;
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int pid;
+ int i;
+
+ file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
+ if (!file_buf)
+ return -ENOMEM;
+
+ buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
+ if (!buf_comm) {
+ kfree(file_buf);
+ return -ENOMEM;
+ }
+
+ buf = file_buf;
+
+ for (i = 0; i < SAVED_CMDLINES; i++) {
+ int r;
+
+ pid = map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ trace_find_cmdline(pid, buf_comm);
+ r = sprintf(buf, "%d %s\n", pid, buf_comm);
+ buf += r;
+ len += r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, len);
+
+ kfree(file_buf);
+ kfree(buf_comm);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_cmdlines_read,
+};
+
+static ssize_t
+tracing_ctrl_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64];
+ int r;
+
+ r = sprintf(buf, "%u\n", tracer_enabled);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_ctrl_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_array *tr = filp->private_data;
+ char buf[64];
+ unsigned long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ val = !!val;
+
+ mutex_lock(&trace_types_lock);
+ if (tracer_enabled ^ val) {
+ if (val) {
+ tracer_enabled = 1;
+ if (current_trace->start)
+ current_trace->start(tr);
+ tracing_start();
+ } else {
+ tracer_enabled = 0;
+ tracing_stop();
+ if (current_trace->stop)
+ current_trace->stop(tr);
+ }
+ }
+ mutex_unlock(&trace_types_lock);
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+tracing_set_trace_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[MAX_TRACER_SIZE+2];
+ int r;
+
+ mutex_lock(&trace_types_lock);
+ if (current_trace)
+ r = sprintf(buf, "%s\n", current_trace->name);
+ else
+ r = sprintf(buf, "\n");
+ mutex_unlock(&trace_types_lock);
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+int tracer_init(struct tracer *t, struct trace_array *tr)
+{
+ tracing_reset_online_cpus(tr);
+ return t->init(tr);
+}
+
+static int tracing_resize_ring_buffer(unsigned long size)
+{
+ int ret;
+
+ /*
+ * If kernel or user changes the size of the ring buffer
+ * we use the size that was given, and we can forget about
+ * expanding it later.
+ */
+ ring_buffer_expanded = 1;
+
+ ret = ring_buffer_resize(global_trace.buffer, size);
+ if (ret < 0)
+ return ret;
+
+ ret = ring_buffer_resize(max_tr.buffer, size);
+ if (ret < 0) {
+ int r;
+
+ r = ring_buffer_resize(global_trace.buffer,
+ global_trace.entries);
+ if (r < 0) {
+ /*
+ * AARGH! We are left with different
+ * size max buffer!!!!
+ * The max buffer is our "snapshot" buffer.
+ * When a tracer needs a snapshot (one of the
+ * latency tracers), it swaps the max buffer
+ * with the saved snap shot. We succeeded to
+ * update the size of the main buffer, but failed to
+ * update the size of the max buffer. But when we tried
+ * to reset the main buffer to the original size, we
+ * failed there too. This is very unlikely to
+ * happen, but if it does, warn and kill all
+ * tracing.
+ */
+ WARN_ON(1);
+ tracing_disabled = 1;
+ }
+ return ret;
+ }
+
+ global_trace.entries = size;
+
+ return ret;
+}
+
+/**
+ * tracing_update_buffers - used by tracing facility to expand ring buffers
+ *
+ * To save on memory when the tracing is never used on a system with it
+ * configured in. The ring buffers are set to a minimum size. But once
+ * a user starts to use the tracing facility, then they need to grow
+ * to their default size.
+ *
+ * This function is to be called when a tracer is about to be used.
+ */
+int tracing_update_buffers(void)
+{
+ int ret = 0;
+
+ mutex_lock(&trace_types_lock);
+ if (!ring_buffer_expanded)
+ ret = tracing_resize_ring_buffer(trace_buf_size);
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+}
+
+struct trace_option_dentry;
+
+static struct trace_option_dentry *
+create_trace_option_files(struct tracer *tracer);
+
+static void
+destroy_trace_option_files(struct trace_option_dentry *topts);
+
+static int tracing_set_tracer(const char *buf)
+{
+ static struct trace_option_dentry *topts;
+ struct trace_array *tr = &global_trace;
+ struct tracer *t;
+ int ret = 0;
+
+ mutex_lock(&trace_types_lock);
+
+ if (!ring_buffer_expanded) {
+ ret = tracing_resize_ring_buffer(trace_buf_size);
+ if (ret < 0)
+ goto out;
+ ret = 0;
+ }
+
+ for (t = trace_types; t; t = t->next) {
+ if (strcmp(t->name, buf) == 0)
+ break;
+ }
+ if (!t) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (t == current_trace)
+ goto out;
+
+ trace_branch_disable();
+ if (current_trace && current_trace->reset)
+ current_trace->reset(tr);
+
+ destroy_trace_option_files(topts);
+
+ current_trace = t;
+
+ topts = create_trace_option_files(current_trace);
+
+ if (t->init) {
+ ret = tracer_init(t, tr);
+ if (ret)
+ goto out;
+ }
+
+ trace_branch_enable(tr);
+ out:
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+}
+
+static ssize_t
+tracing_set_trace_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[MAX_TRACER_SIZE+1];
+ int i;
+ size_t ret;
+ int err;
+
+ ret = cnt;
+
+ if (cnt > MAX_TRACER_SIZE)
+ cnt = MAX_TRACER_SIZE;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ /* strip ending whitespace. */
+ for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
+ buf[i] = 0;
+
+ err = tracing_set_tracer(buf);
+ if (err)
+ return err;
+
+ *ppos += ret;
+
+ return ret;
+}
+
+static ssize_t
+tracing_max_lat_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long *ptr = filp->private_data;
+ char buf[64];
+ int r;
+
+ r = snprintf(buf, sizeof(buf), "%ld\n",
+ *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
+ if (r > sizeof(buf))
+ r = sizeof(buf);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_max_lat_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long *ptr = filp->private_data;
+ char buf[64];
+ unsigned long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ *ptr = val * 1000;
+
+ return cnt;
+}
+
+static int tracing_open_pipe(struct inode *inode, struct file *filp)
+{
+ long cpu_file = (long) inode->i_private;
+ struct trace_iterator *iter;
+ int ret = 0;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ mutex_lock(&trace_types_lock);
+
+ /* create a buffer to store the information to pass to userspace */
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * We make a copy of the current tracer to avoid concurrent
+ * changes on it while we are reading.
+ */
+ iter->trace = kmalloc(sizeof(*iter->trace), GFP_KERNEL);
+ if (!iter->trace) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ if (current_trace)
+ *iter->trace = *current_trace;
+
+ if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+
+ /* trace pipe does not show start of buffer */
+ cpumask_setall(iter->started);
+
+ if (trace_flags & TRACE_ITER_LATENCY_FMT)
+ iter->iter_flags |= TRACE_FILE_LAT_FMT;
+
+ iter->cpu_file = cpu_file;
+ iter->tr = &global_trace;
+ mutex_init(&iter->mutex);
+ filp->private_data = iter;
+
+ if (iter->trace->pipe_open)
+ iter->trace->pipe_open(iter);
+
+out:
+ mutex_unlock(&trace_types_lock);
+ return ret;
+
+fail:
+ kfree(iter->trace);
+ kfree(iter);
+ mutex_unlock(&trace_types_lock);
+ return ret;
+}
+
+static int tracing_release_pipe(struct inode *inode, struct file *file)
+{
+ struct trace_iterator *iter = file->private_data;
+
+ mutex_lock(&trace_types_lock);
+
+ if (iter->trace->pipe_close)
+ iter->trace->pipe_close(iter);
+
+ mutex_unlock(&trace_types_lock);
+
+ free_cpumask_var(iter->started);
+ mutex_destroy(&iter->mutex);
+ kfree(iter->trace);
+ kfree(iter);
+
+ return 0;
+}
+
+static unsigned int
+tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+{
+ struct trace_iterator *iter = filp->private_data;
+
+ if (trace_flags & TRACE_ITER_BLOCK) {
+ /*
+ * Always select as readable when in blocking mode
+ */
+ return POLLIN | POLLRDNORM;
+ } else {
+ if (!trace_empty(iter))
+ return POLLIN | POLLRDNORM;
+ poll_wait(filp, &trace_wait, poll_table);
+ if (!trace_empty(iter))
+ return POLLIN | POLLRDNORM;
+
+ return 0;
+ }
+}
+
+
+void default_wait_pipe(struct trace_iterator *iter)
+{
+ DEFINE_WAIT(wait);
+
+ prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
+
+ if (trace_empty(iter))
+ schedule();
+
+ finish_wait(&trace_wait, &wait);
+}
+
+/*
+ * This is a make-shift waitqueue.
+ * A tracer might use this callback on some rare cases:
+ *
+ * 1) the current tracer might hold the runqueue lock when it wakes up
+ * a reader, hence a deadlock (sched, function, and function graph tracers)
+ * 2) the function tracers, trace all functions, we don't want
+ * the overhead of calling wake_up and friends
+ * (and tracing them too)
+ *
+ * Anyway, this is really very primitive wakeup.
+ */
+void poll_wait_pipe(struct trace_iterator *iter)
+{
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* sleep for 100 msecs, and try again. */
+ schedule_timeout(HZ / 10);
+}
+
+/* Must be called with trace_types_lock mutex held. */
+static int tracing_wait_pipe(struct file *filp)
+{
+ struct trace_iterator *iter = filp->private_data;
+
+ while (trace_empty(iter)) {
+
+ if ((filp->f_flags & O_NONBLOCK)) {
+ return -EAGAIN;
+ }
+
+ mutex_unlock(&iter->mutex);
+
+ iter->trace->wait_pipe(iter);
+
+ mutex_lock(&iter->mutex);
+
+ if (signal_pending(current))
+ return -EINTR;
+
+ /*
+ * We block until we read something and tracing is disabled.
+ * We still block if tracing is disabled, but we have never
+ * read anything. This allows a user to cat this file, and
+ * then enable tracing. But after we have read something,
+ * we give an EOF when tracing is again disabled.
+ *
+ * iter->pos will be 0 if we haven't read anything.
+ */
+ if (!tracer_enabled && iter->pos)
+ break;
+ }
+
+ return 1;
+}
+
+/*
+ * Consumer reader.
+ */
+static ssize_t
+tracing_read_pipe(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_iterator *iter = filp->private_data;
+ static struct tracer *old_tracer;
+ ssize_t sret;
+
+ /* return any leftover data */
+ sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ if (sret != -EBUSY)
+ return sret;
+
+ trace_seq_init(&iter->seq);
+
+ /* copy the tracer to avoid using a global lock all around */
+ mutex_lock(&trace_types_lock);
+ if (unlikely(old_tracer != current_trace && current_trace)) {
+ old_tracer = current_trace;
+ *iter->trace = *current_trace;
+ }
+ mutex_unlock(&trace_types_lock);
+
+ /*
+ * Avoid more than one consumer on a single file descriptor
+ * This is just a matter of traces coherency, the ring buffer itself
+ * is protected.
+ */
+ mutex_lock(&iter->mutex);
+ if (iter->trace->read) {
+ sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
+ if (sret)
+ goto out;
+ }
+
+waitagain:
+ sret = tracing_wait_pipe(filp);
+ if (sret <= 0)
+ goto out;
+
+ /* stop when tracing is finished */
+ if (trace_empty(iter)) {
+ sret = 0;
+ goto out;
+ }
+
+ if (cnt >= PAGE_SIZE)
+ cnt = PAGE_SIZE - 1;
+
+ /* reset all but tr, trace, and overruns */
+ memset(&iter->seq, 0,
+ sizeof(struct trace_iterator) -
+ offsetof(struct trace_iterator, seq));
+ iter->pos = -1;
+
+ trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
+ while (find_next_entry_inc(iter) != NULL) {
+ enum print_line_t ret;
+ int len = iter->seq.len;
+
+ ret = print_trace_line(iter);
+ if (ret == TRACE_TYPE_PARTIAL_LINE) {
+ /* don't print partial lines */
+ iter->seq.len = len;
+ break;
+ }
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(iter);
+
+ if (iter->seq.len >= cnt)
+ break;
+ }
+ trace_access_unlock(iter->cpu_file);
+ trace_event_read_unlock();
+
+ /* Now copy what we have to the user */
+ sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ if (iter->seq.readpos >= iter->seq.len)
+ trace_seq_init(&iter->seq);
+
+ /*
+ * If there was nothing to send to user, inspite of consuming trace
+ * entries, go back to wait for more entries.
+ */
+ if (sret == -EBUSY)
+ goto waitagain;
+
+out:
+ mutex_unlock(&iter->mutex);
+
+ return sret;
+}
+
+static void tracing_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ __free_page(buf->page);
+}
+
+static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
+ unsigned int idx)
+{
+ __free_page(spd->pages[idx]);
+}
+
+static const struct pipe_buf_operations tracing_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = tracing_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
+static size_t
+tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
+{
+ size_t count;
+ int ret;
+
+ /* Seq buffer is page-sized, exactly what we need. */
+ for (;;) {
+ count = iter->seq.len;
+ ret = print_trace_line(iter);
+ count = iter->seq.len - count;
+ if (rem < count) {
+ rem = 0;
+ iter->seq.len -= count;
+ break;
+ }
+ if (ret == TRACE_TYPE_PARTIAL_LINE) {
+ iter->seq.len -= count;
+ break;
+ }
+
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(iter);
+ rem -= count;
+ if (!find_next_entry_inc(iter)) {
+ rem = 0;
+ iter->ent = NULL;
+ break;
+ }
+ }
+
+ return rem;
+}
+
+static ssize_t tracing_splice_read_pipe(struct file *filp,
+ loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len,
+ unsigned int flags)
+{
+ struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial[PIPE_BUFFERS];
+ struct trace_iterator *iter = filp->private_data;
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .nr_pages = 0, /* This gets updated below. */
+ .flags = flags,
+ .ops = &tracing_pipe_buf_ops,
+ .spd_release = tracing_spd_release_pipe,
+ };
+ static struct tracer *old_tracer;
+ ssize_t ret;
+ size_t rem;
+ unsigned int i;
+
+ /* copy the tracer to avoid using a global lock all around */
+ mutex_lock(&trace_types_lock);
+ if (unlikely(old_tracer != current_trace && current_trace)) {
+ old_tracer = current_trace;
+ *iter->trace = *current_trace;
+ }
+ mutex_unlock(&trace_types_lock);
+
+ mutex_lock(&iter->mutex);
+
+ if (iter->trace->splice_read) {
+ ret = iter->trace->splice_read(iter, filp,
+ ppos, pipe, len, flags);
+ if (ret)
+ goto out_err;
+ }
+
+ ret = tracing_wait_pipe(filp);
+ if (ret <= 0)
+ goto out_err;
+
+ if (!iter->ent && !find_next_entry_inc(iter)) {
+ ret = -EFAULT;
+ goto out_err;
+ }
+
+ trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
+
+ /* Fill as many pages as possible. */
+ for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
+ pages[i] = alloc_page(GFP_KERNEL);
+ if (!pages[i])
+ break;
+
+ rem = tracing_fill_pipe_page(rem, iter);
+
+ /* Copy the data into the page, so we can start over. */
+ ret = trace_seq_to_buffer(&iter->seq,
+ page_address(pages[i]),
+ iter->seq.len);
+ if (ret < 0) {
+ __free_page(pages[i]);
+ break;
+ }
+ partial[i].offset = 0;
+ partial[i].len = iter->seq.len;
+
+ trace_seq_init(&iter->seq);
+ }
+
+ trace_access_unlock(iter->cpu_file);
+ trace_event_read_unlock();
+ mutex_unlock(&iter->mutex);
+
+ spd.nr_pages = i;
+
+ return splice_to_pipe(pipe, &spd);
+
+out_err:
+ mutex_unlock(&iter->mutex);
+
+ return ret;
+}
+
+static ssize_t
+tracing_entries_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_array *tr = filp->private_data;
+ char buf[96];
+ int r;
+
+ mutex_lock(&trace_types_lock);
+ if (!ring_buffer_expanded)
+ r = sprintf(buf, "%lu (expanded: %lu)\n",
+ tr->entries >> 10,
+ trace_buf_size >> 10);
+ else
+ r = sprintf(buf, "%lu\n", tr->entries >> 10);
+ mutex_unlock(&trace_types_lock);
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_entries_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long val;
+ char buf[64];
+ int ret, cpu;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ /* must have at least 1 entry */
+ if (!val)
+ return -EINVAL;
+
+ mutex_lock(&trace_types_lock);
+
+ tracing_stop();
+
+ /* disable all cpu buffers */
+ for_each_tracing_cpu(cpu) {
+ if (global_trace.data[cpu])
+ atomic_inc(&global_trace.data[cpu]->disabled);
+ if (max_tr.data[cpu])
+ atomic_inc(&max_tr.data[cpu]->disabled);
+ }
+
+ /* value is in KB */
+ val <<= 10;
+
+ if (val != global_trace.entries) {
+ ret = tracing_resize_ring_buffer(val);
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+ }
+
+ *ppos += cnt;
+
+ /* If check pages failed, return ENOMEM */
+ if (tracing_disabled)
+ cnt = -ENOMEM;
+ out:
+ for_each_tracing_cpu(cpu) {
+ if (global_trace.data[cpu])
+ atomic_dec(&global_trace.data[cpu]->disabled);
+ if (max_tr.data[cpu])
+ atomic_dec(&max_tr.data[cpu]->disabled);
+ }
+
+ tracing_start();
+ max_tr.entries = global_trace.entries;
+ mutex_unlock(&trace_types_lock);
+
+ return cnt;
+}
+
+static int mark_printk(const char *fmt, ...)
+{
+ int ret;
+ va_list args;
+ va_start(args, fmt);
+ ret = trace_vprintk(0, fmt, args);
+ va_end(args);
+ return ret;
+}
+
+static ssize_t
+tracing_mark_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *fpos)
+{
+ char *buf;
+
+ if (tracing_disabled)
+ return -EINVAL;
+
+ if (cnt > TRACE_BUF_SIZE)
+ cnt = TRACE_BUF_SIZE;
+
+ buf = kmalloc(cnt + 2, GFP_KERNEL);
+ if (buf == NULL)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, ubuf, cnt)) {
+ kfree(buf);
+ return -EFAULT;
+ }
+ if (buf[cnt-1] != '\n') {
+ buf[cnt] = '\n';
+ buf[cnt+1] = '\0';
+ } else
+ buf[cnt] = '\0';
+
+ cnt = mark_printk("%s", buf);
+ kfree(buf);
+ *fpos += cnt;
+
+ return cnt;
+}
+
+static int tracing_clock_show(struct seq_file *m, void *v)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
+ seq_printf(m,
+ "%s%s%s%s", i ? " " : "",
+ i == trace_clock_id ? "[" : "", trace_clocks[i].name,
+ i == trace_clock_id ? "]" : "");
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *fpos)
+{
+ char buf[64];
+ const char *clockstr;
+ int i;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ clockstr = strstrip(buf);
+
+ for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
+ if (strcmp(trace_clocks[i].name, clockstr) == 0)
+ break;
+ }
+ if (i == ARRAY_SIZE(trace_clocks))
+ return -EINVAL;
+
+ trace_clock_id = i;
+
+ mutex_lock(&trace_types_lock);
+
+ ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func);
+ if (max_tr.buffer)
+ ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func);
+
+ mutex_unlock(&trace_types_lock);
+
+ *fpos += cnt;
+
+ return cnt;
+}
+
+static int tracing_clock_open(struct inode *inode, struct file *file)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+ return single_open(file, tracing_clock_show, NULL);
+}
+
+static const struct file_operations tracing_max_lat_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_max_lat_read,
+ .write = tracing_max_lat_write,
+};
+
+static const struct file_operations tracing_ctrl_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_ctrl_read,
+ .write = tracing_ctrl_write,
+};
+
+static const struct file_operations set_tracer_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_set_trace_read,
+ .write = tracing_set_trace_write,
+};
+
+static const struct file_operations tracing_pipe_fops = {
+ .open = tracing_open_pipe,
+ .poll = tracing_poll_pipe,
+ .read = tracing_read_pipe,
+ .splice_read = tracing_splice_read_pipe,
+ .release = tracing_release_pipe,
+};
+
+static const struct file_operations tracing_entries_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_entries_read,
+ .write = tracing_entries_write,
+};
+
+static const struct file_operations tracing_mark_fops = {
+ .open = tracing_open_generic,
+ .write = tracing_mark_write,
+};
+
+static const struct file_operations trace_clock_fops = {
+ .open = tracing_clock_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .write = tracing_clock_write,
+};
+
+struct ftrace_buffer_info {
+ struct trace_array *tr;
+ void *spare;
+ int cpu;
+ unsigned int read;
+};
+
+static int tracing_buffers_open(struct inode *inode, struct file *filp)
+{
+ int cpu = (int)(long)inode->i_private;
+ struct ftrace_buffer_info *info;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return -ENOMEM;
+
+ info->tr = &global_trace;
+ info->cpu = cpu;
+ info->spare = NULL;
+ /* Force reading ring buffer for first read */
+ info->read = (unsigned int)-1;
+
+ filp->private_data = info;
+
+ return nonseekable_open(inode, filp);
+}
+
+static ssize_t
+tracing_buffers_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ struct ftrace_buffer_info *info = filp->private_data;
+ unsigned int pos;
+ ssize_t ret;
+ size_t size;
+
+ if (!count)
+ return 0;
+
+ if (!info->spare)
+ info->spare = ring_buffer_alloc_read_page(info->tr->buffer);
+ if (!info->spare)
+ return -ENOMEM;
+
+ /* Do we have previous read data to read? */
+ if (info->read < PAGE_SIZE)
+ goto read;
+
+ info->read = 0;
+
+ trace_access_lock(info->cpu);
+ ret = ring_buffer_read_page(info->tr->buffer,
+ &info->spare,
+ count,
+ info->cpu, 0);
+ trace_access_unlock(info->cpu);
+ if (ret < 0)
+ return 0;
+
+ pos = ring_buffer_page_len(info->spare);
+
+ if (pos < PAGE_SIZE)
+ memset(info->spare + pos, 0, PAGE_SIZE - pos);
+
+read:
+ size = PAGE_SIZE - info->read;
+ if (size > count)
+ size = count;
+
+ ret = copy_to_user(ubuf, info->spare + info->read, size);
+ if (ret == size)
+ return -EFAULT;
+ size -= ret;
+
+ *ppos += size;
+ info->read += size;
+
+ return size;
+}
+
+static int tracing_buffers_release(struct inode *inode, struct file *file)
+{
+ struct ftrace_buffer_info *info = file->private_data;
+
+ if (info->spare)
+ ring_buffer_free_read_page(info->tr->buffer, info->spare);
+ kfree(info);
+
+ return 0;
+}
+
+struct buffer_ref {
+ struct ring_buffer *buffer;
+ void *page;
+ int ref;
+};
+
+static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+
+ if (--ref->ref)
+ return;
+
+ ring_buffer_free_read_page(ref->buffer, ref->page);
+ kfree(ref);
+ buf->private = 0;
+}
+
+static int buffer_pipe_buf_steal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return 1;
+}
+
+static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+
+ ref->ref++;
+}
+
+/* Pipe buffer operations for a buffer. */
+static const struct pipe_buf_operations buffer_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = buffer_pipe_buf_release,
+ .steal = buffer_pipe_buf_steal,
+ .get = buffer_pipe_buf_get,
+};
+
+/*
+ * Callback from splice_to_pipe(), if we need to release some pages
+ * at the end of the spd in case we error'ed out in filling the pipe.
+ */
+static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
+{
+ struct buffer_ref *ref =
+ (struct buffer_ref *)spd->partial[i].private;
+
+ if (--ref->ref)
+ return;
+
+ ring_buffer_free_read_page(ref->buffer, ref->page);
+ kfree(ref);
+ spd->partial[i].private = 0;
+}
+
+static ssize_t
+tracing_buffers_splice_read(struct file *file, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct ftrace_buffer_info *info = file->private_data;
+ struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_BUFFERS];
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .flags = flags,
+ .ops = &buffer_pipe_buf_ops,
+ .spd_release = buffer_spd_release,
+ };
+ struct buffer_ref *ref;
+ int entries, size, i;
+ size_t ret;
+
+ if (*ppos & (PAGE_SIZE - 1)) {
+ WARN_ONCE(1, "Ftrace: previous read must page-align\n");
+ return -EINVAL;
+ }
+
+ if (len & (PAGE_SIZE - 1)) {
+ WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
+ if (len < PAGE_SIZE)
+ return -EINVAL;
+ len &= PAGE_MASK;
+ }
+
+ trace_access_lock(info->cpu);
+ entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+
+ for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+ struct page *page;
+ int r;
+
+ ref = kzalloc(sizeof(*ref), GFP_KERNEL);
+ if (!ref)
+ break;
+
+ ref->ref = 1;
+ ref->buffer = info->tr->buffer;
+ ref->page = ring_buffer_alloc_read_page(ref->buffer);
+ if (!ref->page) {
+ kfree(ref);
+ break;
+ }
+
+ r = ring_buffer_read_page(ref->buffer, &ref->page,
+ len, info->cpu, 1);
+ if (r < 0) {
+ ring_buffer_free_read_page(ref->buffer,
+ ref->page);
+ kfree(ref);
+ break;
+ }
+
+ /*
+ * zero out any left over data, this is going to
+ * user land.
+ */
+ size = ring_buffer_page_len(ref->page);
+ if (size < PAGE_SIZE)
+ memset(ref->page + size, 0, PAGE_SIZE - size);
+
+ page = virt_to_page(ref->page);
+
+ spd.pages[i] = page;
+ spd.partial[i].len = PAGE_SIZE;
+ spd.partial[i].offset = 0;
+ spd.partial[i].private = (unsigned long)ref;
+ spd.nr_pages++;
+ *ppos += PAGE_SIZE;
+
+ entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+ }
+
+ trace_access_unlock(info->cpu);
+ spd.nr_pages = i;
+
+ /* did we read anything? */
+ if (!spd.nr_pages) {
+ if (flags & SPLICE_F_NONBLOCK)
+ ret = -EAGAIN;
+ else
+ ret = 0;
+ /* TODO: block */
+ return ret;
+ }
+
+ ret = splice_to_pipe(pipe, &spd);
+
+ return ret;
+}
+
+static const struct file_operations tracing_buffers_fops = {
+ .open = tracing_buffers_open,
+ .read = tracing_buffers_read,
+ .release = tracing_buffers_release,
+ .splice_read = tracing_buffers_splice_read,
+ .llseek = no_llseek,
+};
+
+static ssize_t
+tracing_stats_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long cpu = (unsigned long)filp->private_data;
+ struct trace_array *tr = &global_trace;
+ struct trace_seq *s;
+ unsigned long cnt;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "entries: %ld\n", cnt);
+
+ cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "overrun: %ld\n", cnt);
+
+ cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+ trace_seq_printf(s, "commit overrun: %ld\n", cnt);
+
+ count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return count;
+}
+
+static const struct file_operations tracing_stats_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_stats_read,
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+int __weak ftrace_arch_read_dyn_info(char *buf, int size)
+{
+ return 0;
+}
+
+static ssize_t
+tracing_read_dyn_info(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ static char ftrace_dyn_info_buffer[1024];
+ static DEFINE_MUTEX(dyn_info_mutex);
+ unsigned long *p = filp->private_data;
+ char *buf = ftrace_dyn_info_buffer;
+ int size = ARRAY_SIZE(ftrace_dyn_info_buffer);
+ int r;
+
+ mutex_lock(&dyn_info_mutex);
+ r = sprintf(buf, "%ld ", *p);
+
+ r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r);
+ buf[r++] = '\n';
+
+ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+
+ mutex_unlock(&dyn_info_mutex);
+
+ return r;
+}
+
+static const struct file_operations tracing_dyn_info_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_read_dyn_info,
+};
+#endif
+
+static struct dentry *d_tracer;
+
+struct dentry *tracing_init_dentry(void)
+{
+ static int once;
+
+ if (d_tracer)
+ return d_tracer;
+
+ if (!debugfs_initialized())
+ return NULL;
+
+ d_tracer = debugfs_create_dir("tracing", NULL);
+
+ if (!d_tracer && !once) {
+ once = 1;
+ pr_warning("Could not create debugfs directory 'tracing'\n");
+ return NULL;
+ }
+
+ return d_tracer;
+}
+
+static struct dentry *d_percpu;
+
+struct dentry *tracing_dentry_percpu(void)
+{
+ static int once;
+ struct dentry *d_tracer;
+
+ if (d_percpu)
+ return d_percpu;
+
+ d_tracer = tracing_init_dentry();
+
+ if (!d_tracer)
+ return NULL;
+
+ d_percpu = debugfs_create_dir("per_cpu", d_tracer);
+
+ if (!d_percpu && !once) {
+ once = 1;
+ pr_warning("Could not create debugfs directory 'per_cpu'\n");
+ return NULL;
+ }
+
+ return d_percpu;
+}
+
+static void tracing_init_debugfs_percpu(long cpu)
+{
+ struct dentry *d_percpu = tracing_dentry_percpu();
+ struct dentry *d_cpu;
+ /* strlen(cpu) + MAX(log10(cpu)) + '\0' */
+ char cpu_dir[7];
+
+ if (cpu > 999 || cpu < 0)
+ return;
+
+ sprintf(cpu_dir, "cpu%ld", cpu);
+ d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
+ if (!d_cpu) {
+ pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);
+ return;
+ }
+
+ /* per cpu trace_pipe */
+ trace_create_file("trace_pipe", 0444, d_cpu,
+ (void *) cpu, &tracing_pipe_fops);
+
+ /* per cpu trace */
+ trace_create_file("trace", 0644, d_cpu,
+ (void *) cpu, &tracing_fops);
+
+ trace_create_file("trace_pipe_raw", 0444, d_cpu,
+ (void *) cpu, &tracing_buffers_fops);
+
+ trace_create_file("stats", 0444, d_cpu,
+ (void *) cpu, &tracing_stats_fops);
+}
+
+#ifdef CONFIG_FTRACE_SELFTEST
+/* Let selftest have access to static functions in this file */
+#include "trace_selftest.c"
+#endif
+
+struct trace_option_dentry {
+ struct tracer_opt *opt;
+ struct tracer_flags *flags;
+ struct dentry *entry;
+};
+
+static ssize_t
+trace_options_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct trace_option_dentry *topt = filp->private_data;
+ char *buf;
+
+ if (topt->flags->val & topt->opt->bit)
+ buf = "1\n";
+ else
+ buf = "0\n";
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+}
+
+static ssize_t
+trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct trace_option_dentry *topt = filp->private_data;
+ unsigned long val;
+ char buf[64];
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
+ if (!!(topt->flags->val & topt->opt->bit) != val) {
+ mutex_lock(&trace_types_lock);
+ ret = __set_tracer_option(current_trace, topt->flags,
+ topt->opt, !val);
+ mutex_unlock(&trace_types_lock);
+ if (ret)
+ return ret;
+ }
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+
+static const struct file_operations trace_options_fops = {
+ .open = tracing_open_generic,
+ .read = trace_options_read,
+ .write = trace_options_write,
+};
+
+static ssize_t
+trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ long index = (long)filp->private_data;
+ char *buf;
+
+ if (trace_flags & (1 << index))
+ buf = "1\n";
+ else
+ buf = "0\n";
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+}
+
+static ssize_t
+trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ long index = (long)filp->private_data;
+ char buf[64];
+ unsigned long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+ set_tracer_flags(1 << index, val);
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+static const struct file_operations trace_options_core_fops = {
+ .open = tracing_open_generic,
+ .read = trace_options_core_read,
+ .write = trace_options_core_write,
+};
+
+struct dentry *trace_create_file(const char *name,
+ mode_t mode,
+ struct dentry *parent,
+ void *data,
+ const struct file_operations *fops)
+{
+ struct dentry *ret;
+
+ ret = debugfs_create_file(name, mode, parent, data, fops);
+ if (!ret)
+ pr_warning("Could not create debugfs '%s' entry\n", name);
+
+ return ret;
+}
+
+
+static struct dentry *trace_options_init_dentry(void)
+{
+ struct dentry *d_tracer;
+ static struct dentry *t_options;
+
+ if (t_options)
+ return t_options;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return NULL;
+
+ t_options = debugfs_create_dir("options", d_tracer);
+ if (!t_options) {
+ pr_warning("Could not create debugfs directory 'options'\n");
+ return NULL;
+ }
+
+ return t_options;
+}
+
+static void
+create_trace_option_file(struct trace_option_dentry *topt,
+ struct tracer_flags *flags,
+ struct tracer_opt *opt)
+{
+ struct dentry *t_options;
+
+ t_options = trace_options_init_dentry();
+ if (!t_options)
+ return;
+
+ topt->flags = flags;
+ topt->opt = opt;
+
+ topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
+ &trace_options_fops);
+
+}
+
+static struct trace_option_dentry *
+create_trace_option_files(struct tracer *tracer)
+{
+ struct trace_option_dentry *topts;
+ struct tracer_flags *flags;
+ struct tracer_opt *opts;
+ int cnt;
+
+ if (!tracer)
+ return NULL;
+
+ flags = tracer->flags;
+
+ if (!flags || !flags->opts)
+ return NULL;
+
+ opts = flags->opts;
+
+ for (cnt = 0; opts[cnt].name; cnt++)
+ ;
+
+ topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL);
+ if (!topts)
+ return NULL;
+
+ for (cnt = 0; opts[cnt].name; cnt++)
+ create_trace_option_file(&topts[cnt], flags,
+ &opts[cnt]);
+
+ return topts;
+}
+
+static void
+destroy_trace_option_files(struct trace_option_dentry *topts)
+{
+ int cnt;
+
+ if (!topts)
+ return;
+
+ for (cnt = 0; topts[cnt].opt; cnt++) {
+ if (topts[cnt].entry)
+ debugfs_remove(topts[cnt].entry);
+ }
+
+ kfree(topts);
+}
+
+static struct dentry *
+create_trace_option_core_file(const char *option, long index)
+{
+ struct dentry *t_options;
+
+ t_options = trace_options_init_dentry();
+ if (!t_options)
+ return NULL;
+
+ return trace_create_file(option, 0644, t_options, (void *)index,
+ &trace_options_core_fops);
+}
+
+static __init void create_trace_options_dir(void)
+{
+ struct dentry *t_options;
+ int i;
+
+ t_options = trace_options_init_dentry();
+ if (!t_options)
+ return;
+
+ for (i = 0; trace_options[i]; i++)
+ create_trace_option_core_file(trace_options[i], i);
+}
+
+static __init int tracer_init_debugfs(void)
+{
+ struct dentry *d_tracer;
+ int cpu;
+
+ trace_access_lock_init();
+
+ d_tracer = tracing_init_dentry();
+
+ trace_create_file("tracing_enabled", 0644, d_tracer,
+ &global_trace, &tracing_ctrl_fops);
+
+ trace_create_file("trace_options", 0644, d_tracer,
+ NULL, &tracing_iter_fops);
+
+ trace_create_file("tracing_cpumask", 0644, d_tracer,
+ NULL, &tracing_cpumask_fops);
+
+ trace_create_file("trace", 0644, d_tracer,
+ (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
+
+ trace_create_file("available_tracers", 0444, d_tracer,
+ &global_trace, &show_traces_fops);
+
+ trace_create_file("current_tracer", 0644, d_tracer,
+ &global_trace, &set_tracer_fops);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ trace_create_file("tracing_max_latency", 0644, d_tracer,
+ &tracing_max_latency, &tracing_max_lat_fops);
+
+ trace_create_file("tracing_thresh", 0644, d_tracer,
+ &tracing_thresh, &tracing_max_lat_fops);
+#endif
+
+ trace_create_file("README", 0444, d_tracer,
+ NULL, &tracing_readme_fops);
+
+ trace_create_file("trace_pipe", 0444, d_tracer,
+ (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
+
+ trace_create_file("buffer_size_kb", 0644, d_tracer,
+ &global_trace, &tracing_entries_fops);
+
+ trace_create_file("trace_marker", 0220, d_tracer,
+ NULL, &tracing_mark_fops);
+
+ trace_create_file("saved_cmdlines", 0444, d_tracer,
+ NULL, &tracing_saved_cmdlines_fops);
+
+ trace_create_file("trace_clock", 0644, d_tracer, NULL,
+ &trace_clock_fops);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
+ &ftrace_update_tot_cnt, &tracing_dyn_info_fops);
+#endif
+#ifdef CONFIG_SYSPROF_TRACER
+ init_tracer_sysprof_debugfs(d_tracer);
+#endif
+
+ create_trace_options_dir();
+
+ for_each_tracing_cpu(cpu)
+ tracing_init_debugfs_percpu(cpu);
+
+ return 0;
+}
+
+static int trace_panic_handler(struct notifier_block *this,
+ unsigned long event, void *unused)
+{
+ if (ftrace_dump_on_oops)
+ ftrace_dump();
+ return NOTIFY_OK;
+}
+
+static struct notifier_block trace_panic_notifier = {
+ .notifier_call = trace_panic_handler,
+ .next = NULL,
+ .priority = 150 /* priority: INT_MAX >= x >= 0 */
+};
+
+static int trace_die_handler(struct notifier_block *self,
+ unsigned long val,
+ void *data)
+{
+ switch (val) {
+ case DIE_OOPS:
+ if (ftrace_dump_on_oops)
+ ftrace_dump();
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block trace_die_notifier = {
+ .notifier_call = trace_die_handler,
+ .priority = 200
+};
+
+/*
+ * printk is set to max of 1024, we really don't need it that big.
+ * Nothing should be printing 1000 characters anyway.
+ */
+#define TRACE_MAX_PRINT 1000
+
+/*
+ * Define here KERN_TRACE so that we have one place to modify
+ * it if we decide to change what log level the ftrace dump
+ * should be at.
+ */
+#define KERN_TRACE KERN_EMERG
+
+static void
+trace_printk_seq(struct trace_seq *s)
+{
+ /* Probably should print a warning here. */
+ if (s->len >= 1000)
+ s->len = 1000;
+
+ /* should be zero ended, but we are paranoid. */
+ s->buffer[s->len] = 0;
+
+ printk(KERN_TRACE "%s", s->buffer);
+
+ trace_seq_init(s);
+}
+
+static void __ftrace_dump(bool disable_tracing)
+{
+ static arch_spinlock_t ftrace_dump_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+ /* use static because iter can be a bit big for the stack */
+ static struct trace_iterator iter;
+ unsigned int old_userobj;
+ static int dump_ran;
+ unsigned long flags;
+ int cnt = 0, cpu;
+
+ /* only one dump */
+ local_irq_save(flags);
+ arch_spin_lock(&ftrace_dump_lock);
+ if (dump_ran)
+ goto out;
+
+ dump_ran = 1;
+
+ tracing_off();
+
+ if (disable_tracing)
+ ftrace_kill();
+
+ for_each_tracing_cpu(cpu) {
+ atomic_inc(&global_trace.data[cpu]->disabled);
+ }
+
+ old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
+
+ /* don't look at user memory in panic mode */
+ trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
+ printk(KERN_TRACE "Dumping ftrace buffer:\n");
+
+ /* Simulate the iterator */
+ iter.tr = &global_trace;
+ iter.trace = current_trace;
+ iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+ /*
+ * We need to stop all tracing on all CPUS to read the
+ * the next buffer. This is a bit expensive, but is
+ * not done often. We fill all what we can read,
+ * and then release the locks again.
+ */
+
+ while (!trace_empty(&iter)) {
+
+ if (!cnt)
+ printk(KERN_TRACE "---------------------------------\n");
+
+ cnt++;
+
+ /* reset all but tr, trace, and overruns */
+ memset(&iter.seq, 0,
+ sizeof(struct trace_iterator) -
+ offsetof(struct trace_iterator, seq));
+ iter.iter_flags |= TRACE_FILE_LAT_FMT;
+ iter.pos = -1;
+
+ if (find_next_entry_inc(&iter) != NULL) {
+ int ret;
+
+ ret = print_trace_line(&iter);
+ if (ret != TRACE_TYPE_NO_CONSUME)
+ trace_consume(&iter);
+ }
+
+ trace_printk_seq(&iter.seq);
+ }
+
+ if (!cnt)
+ printk(KERN_TRACE " (ftrace buffer empty)\n");
+ else
+ printk(KERN_TRACE "---------------------------------\n");
+
+ /* Re-enable tracing if requested */
+ if (!disable_tracing) {
+ trace_flags |= old_userobj;
+
+ for_each_tracing_cpu(cpu) {
+ atomic_dec(&global_trace.data[cpu]->disabled);
+ }
+ tracing_on();
+ }
+
+ out:
+ arch_spin_unlock(&ftrace_dump_lock);
+ local_irq_restore(flags);
+}
+
+/* By default: disable tracing after the dump */
+void ftrace_dump(void)
+{
+ __ftrace_dump(true);
+}
+
+__init static int tracer_alloc_buffers(void)
+{
+ int ring_buf_size;
+ int i;
+ int ret = -ENOMEM;
+
+ if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
+ goto out;
+
+ if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
+ goto out_free_buffer_mask;
+
+ /* To save memory, keep the ring buffer size to its minimum */
+ if (ring_buffer_expanded)
+ ring_buf_size = trace_buf_size;
+ else
+ ring_buf_size = 1;
+
+ cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
+ cpumask_copy(tracing_cpumask, cpu_all_mask);
+
+ /* TODO: make the number of buffers hot pluggable with CPUS */
+ global_trace.buffer = ring_buffer_alloc(ring_buf_size,
+ TRACE_BUFFER_FLAGS);
+ if (!global_trace.buffer) {
+ printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
+ WARN_ON(1);
+ goto out_free_cpumask;
+ }
+ global_trace.entries = ring_buffer_size(global_trace.buffer);
+
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ max_tr.buffer = ring_buffer_alloc(ring_buf_size,
+ TRACE_BUFFER_FLAGS);
+ if (!max_tr.buffer) {
+ printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
+ WARN_ON(1);
+ ring_buffer_free(global_trace.buffer);
+ goto out_free_cpumask;
+ }
+ max_tr.entries = ring_buffer_size(max_tr.buffer);
+ WARN_ON(max_tr.entries != global_trace.entries);
+#endif
+
+ /* Allocate the first page for all buffers */
+ for_each_tracing_cpu(i) {
+ global_trace.data[i] = &per_cpu(global_trace_cpu, i);
+ max_tr.data[i] = &per_cpu(max_tr_data, i);
+ }
+
+ trace_init_cmdlines();
+
+ register_tracer(&nop_trace);
+ current_trace = &nop_trace;
+#ifdef CONFIG_BOOT_TRACER
+ register_tracer(&boot_tracer);
+#endif
+ /* All seems OK, enable tracing */
+ tracing_disabled = 0;
+
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &trace_panic_notifier);
+
+ register_die_notifier(&trace_die_notifier);
+
+ return 0;
+
+out_free_cpumask:
+ free_cpumask_var(tracing_cpumask);
+out_free_buffer_mask:
+ free_cpumask_var(tracing_buffer_mask);
+out:
+ return ret;
+}
+
+__init static int clear_boot_tracer(void)
+{
+ /*
+ * The default tracer at boot buffer is an init section.
+ * This function is called in lateinit. If we did not
+ * find the boot tracer, then clear it out, to prevent
+ * later registration from accessing the buffer that is
+ * about to be freed.
+ */
+ if (!default_bootup_tracer)
+ return 0;
+
+ printk(KERN_INFO "ftrace bootup tracer '%s' not registered.\n",
+ default_bootup_tracer);
+ default_bootup_tracer = NULL;
+
+ return 0;
+}
+
+early_initcall(tracer_alloc_buffers);
+fs_initcall(tracer_init_debugfs);
+late_initcall(clear_boot_tracer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
new file mode 100644
index 00000000000..a1edaa8518e
--- /dev/null
+++ b/kernel/trace/trace.h
@@ -0,0 +1,801 @@
+#ifndef _LINUX_KERNEL_TRACE_H
+#define _LINUX_KERNEL_TRACE_H
+
+#include <linux/fs.h>
+#include <asm/atomic.h>
+#include <linux/sched.h>
+#include <linux/clocksource.h>
+#include <linux/ring_buffer.h>
+#include <linux/mmiotrace.h>
+#include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+#include <trace/boot.h>
+#include <linux/kmemtrace.h>
+#include <linux/hw_breakpoint.h>
+
+#include <linux/trace_seq.h>
+#include <linux/ftrace_event.h>
+
+enum trace_type {
+ __TRACE_FIRST_TYPE = 0,
+
+ TRACE_FN,
+ TRACE_CTX,
+ TRACE_WAKE,
+ TRACE_STACK,
+ TRACE_PRINT,
+ TRACE_BPRINT,
+ TRACE_SPECIAL,
+ TRACE_MMIO_RW,
+ TRACE_MMIO_MAP,
+ TRACE_BRANCH,
+ TRACE_BOOT_CALL,
+ TRACE_BOOT_RET,
+ TRACE_GRAPH_RET,
+ TRACE_GRAPH_ENT,
+ TRACE_USER_STACK,
+ TRACE_HW_BRANCHES,
+ TRACE_KMEM_ALLOC,
+ TRACE_KMEM_FREE,
+ TRACE_BLK,
+ TRACE_KSYM,
+
+ __TRACE_LAST_TYPE,
+};
+
+enum kmemtrace_type_id {
+ KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */
+ KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */
+ KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */
+};
+
+extern struct tracer boot_tracer;
+
+#undef __field
+#define __field(type, item) type item;
+
+#undef __field_struct
+#define __field_struct(type, item) __field(type, item)
+
+#undef __field_desc
+#define __field_desc(type, container, item)
+
+#undef __array
+#define __array(type, item, size) type item[size];
+
+#undef __array_desc
+#define __array_desc(type, container, item, size)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item) type item[];
+
+#undef F_STRUCT
+#define F_STRUCT(args...) args
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
+ struct struct_name { \
+ struct trace_entry ent; \
+ tstruct \
+ }
+
+#undef TP_ARGS
+#define TP_ARGS(args...) args
+
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
+
+#include "trace_entries.h"
+
+/*
+ * syscalls are special, and need special handling, this is why
+ * they are not included in trace_entries.h
+ */
+struct syscall_trace_enter {
+ struct trace_entry ent;
+ int nr;
+ unsigned long args[];
+};
+
+struct syscall_trace_exit {
+ struct trace_entry ent;
+ int nr;
+ long ret;
+};
+
+struct kprobe_trace_entry {
+ struct trace_entry ent;
+ unsigned long ip;
+ int nargs;
+ unsigned long args[];
+};
+
+#define SIZEOF_KPROBE_TRACE_ENTRY(n) \
+ (offsetof(struct kprobe_trace_entry, args) + \
+ (sizeof(unsigned long) * (n)))
+
+struct kretprobe_trace_entry {
+ struct trace_entry ent;
+ unsigned long func;
+ unsigned long ret_ip;
+ int nargs;
+ unsigned long args[];
+};
+
+#define SIZEOF_KRETPROBE_TRACE_ENTRY(n) \
+ (offsetof(struct kretprobe_trace_entry, args) + \
+ (sizeof(unsigned long) * (n)))
+
+/*
+ * trace_flag_type is an enumeration that holds different
+ * states when a trace occurs. These are:
+ * IRQS_OFF - interrupts were disabled
+ * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags
+ * NEED_RESCHED - reschedule is requested
+ * HARDIRQ - inside an interrupt handler
+ * SOFTIRQ - inside a softirq handler
+ */
+enum trace_flag_type {
+ TRACE_FLAG_IRQS_OFF = 0x01,
+ TRACE_FLAG_IRQS_NOSUPPORT = 0x02,
+ TRACE_FLAG_NEED_RESCHED = 0x04,
+ TRACE_FLAG_HARDIRQ = 0x08,
+ TRACE_FLAG_SOFTIRQ = 0x10,
+};
+
+#define TRACE_BUF_SIZE 1024
+
+/*
+ * The CPU trace array - it consists of thousands of trace entries
+ * plus some other descriptor data: (for example which task started
+ * the trace, etc.)
+ */
+struct trace_array_cpu {
+ atomic_t disabled;
+ void *buffer_page; /* ring buffer spare */
+
+ unsigned long saved_latency;
+ unsigned long critical_start;
+ unsigned long critical_end;
+ unsigned long critical_sequence;
+ unsigned long nice;
+ unsigned long policy;
+ unsigned long rt_priority;
+ unsigned long skipped_entries;
+ cycle_t preempt_timestamp;
+ pid_t pid;
+ uid_t uid;
+ char comm[TASK_COMM_LEN];
+};
+
+/*
+ * The trace array - an array of per-CPU trace arrays. This is the
+ * highest level data structure that individual tracers deal with.
+ * They have on/off state as well:
+ */
+struct trace_array {
+ struct ring_buffer *buffer;
+ unsigned long entries;
+ int cpu;
+ cycle_t time_start;
+ struct task_struct *waiter;
+ struct trace_array_cpu *data[NR_CPUS];
+};
+
+#define FTRACE_CMP_TYPE(var, type) \
+ __builtin_types_compatible_p(typeof(var), type *)
+
+#undef IF_ASSIGN
+#define IF_ASSIGN(var, entry, etype, id) \
+ if (FTRACE_CMP_TYPE(var, etype)) { \
+ var = (typeof(var))(entry); \
+ WARN_ON(id && (entry)->type != id); \
+ break; \
+ }
+
+/* Will cause compile errors if type is not found. */
+extern void __ftrace_bad_type(void);
+
+/*
+ * The trace_assign_type is a verifier that the entry type is
+ * the same as the type being assigned. To add new types simply
+ * add a line with the following format:
+ *
+ * IF_ASSIGN(var, ent, type, id);
+ *
+ * Where "type" is the trace type that includes the trace_entry
+ * as the "ent" item. And "id" is the trace identifier that is
+ * used in the trace_type enum.
+ *
+ * If the type can have more than one id, then use zero.
+ */
+#define trace_assign_type(var, ent) \
+ do { \
+ IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \
+ IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \
+ IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \
+ IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
+ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
+ IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \
+ IF_ASSIGN(var, ent, struct special_entry, 0); \
+ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
+ TRACE_MMIO_RW); \
+ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \
+ TRACE_MMIO_MAP); \
+ IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
+ IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
+ IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
+ IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \
+ TRACE_GRAPH_ENT); \
+ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \
+ TRACE_GRAPH_RET); \
+ IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
+ IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \
+ TRACE_KMEM_ALLOC); \
+ IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \
+ TRACE_KMEM_FREE); \
+ IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
+ __ftrace_bad_type(); \
+ } while (0)
+
+/*
+ * An option specific to a tracer. This is a boolean value.
+ * The bit is the bit index that sets its value on the
+ * flags value in struct tracer_flags.
+ */
+struct tracer_opt {
+ const char *name; /* Will appear on the trace_options file */
+ u32 bit; /* Mask assigned in val field in tracer_flags */
+};
+
+/*
+ * The set of specific options for a tracer. Your tracer
+ * have to set the initial value of the flags val.
+ */
+struct tracer_flags {
+ u32 val;
+ struct tracer_opt *opts;
+};
+
+/* Makes more easy to define a tracer opt */
+#define TRACER_OPT(s, b) .name = #s, .bit = b
+
+
+/**
+ * struct tracer - a specific tracer and its callbacks to interact with debugfs
+ * @name: the name chosen to select it on the available_tracers file
+ * @init: called when one switches to this tracer (echo name > current_tracer)
+ * @reset: called when one switches to another tracer
+ * @start: called when tracing is unpaused (echo 1 > tracing_enabled)
+ * @stop: called when tracing is paused (echo 0 > tracing_enabled)
+ * @open: called when the trace file is opened
+ * @pipe_open: called when the trace_pipe file is opened
+ * @wait_pipe: override how the user waits for traces on trace_pipe
+ * @close: called when the trace file is released
+ * @pipe_close: called when the trace_pipe file is released
+ * @read: override the default read callback on trace_pipe
+ * @splice_read: override the default splice_read callback on trace_pipe
+ * @selftest: selftest to run on boot (see trace_selftest.c)
+ * @print_headers: override the first lines that describe your columns
+ * @print_line: callback that prints a trace
+ * @set_flag: signals one of your private flags changed (trace_options file)
+ * @flags: your private flags
+ */
+struct tracer {
+ const char *name;
+ int (*init)(struct trace_array *tr);
+ void (*reset)(struct trace_array *tr);
+ void (*start)(struct trace_array *tr);
+ void (*stop)(struct trace_array *tr);
+ void (*open)(struct trace_iterator *iter);
+ void (*pipe_open)(struct trace_iterator *iter);
+ void (*wait_pipe)(struct trace_iterator *iter);
+ void (*close)(struct trace_iterator *iter);
+ void (*pipe_close)(struct trace_iterator *iter);
+ ssize_t (*read)(struct trace_iterator *iter,
+ struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos);
+ ssize_t (*splice_read)(struct trace_iterator *iter,
+ struct file *filp,
+ loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len,
+ unsigned int flags);
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+ int (*selftest)(struct tracer *trace,
+ struct trace_array *tr);
+#endif
+ void (*print_header)(struct seq_file *m);
+ enum print_line_t (*print_line)(struct trace_iterator *iter);
+ /* If you handled the flag setting, return 0 */
+ int (*set_flag)(u32 old_flags, u32 bit, int set);
+ struct tracer *next;
+ int print_max;
+ struct tracer_flags *flags;
+};
+
+
+#define TRACE_PIPE_ALL_CPU -1
+
+int tracer_init(struct tracer *t, struct trace_array *tr);
+int tracing_is_enabled(void);
+void trace_wake_up(void);
+void tracing_reset(struct trace_array *tr, int cpu);
+void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset_current(int cpu);
+void tracing_reset_current_online_cpus(void);
+int tracing_open_generic(struct inode *inode, struct file *filp);
+struct dentry *trace_create_file(const char *name,
+ mode_t mode,
+ struct dentry *parent,
+ void *data,
+ const struct file_operations *fops);
+
+struct dentry *tracing_init_dentry(void);
+void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
+
+struct ring_buffer_event;
+
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+ int type,
+ unsigned long len,
+ unsigned long flags,
+ int pc);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc);
+
+struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
+ struct trace_array_cpu *data);
+
+struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
+ int *ent_cpu, u64 *ent_ts);
+
+void default_wait_pipe(struct trace_iterator *iter);
+void poll_wait_pipe(struct trace_iterator *iter);
+
+void ftrace(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ unsigned long ip,
+ unsigned long parent_ip,
+ unsigned long flags, int pc);
+void tracing_sched_switch_trace(struct trace_array *tr,
+ struct task_struct *prev,
+ struct task_struct *next,
+ unsigned long flags, int pc);
+
+void tracing_sched_wakeup_trace(struct trace_array *tr,
+ struct task_struct *wakee,
+ struct task_struct *cur,
+ unsigned long flags, int pc);
+void trace_special(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ unsigned long arg1,
+ unsigned long arg2,
+ unsigned long arg3, int pc);
+void trace_function(struct trace_array *tr,
+ unsigned long ip,
+ unsigned long parent_ip,
+ unsigned long flags, int pc);
+
+void trace_graph_return(struct ftrace_graph_ret *trace);
+int trace_graph_entry(struct ftrace_graph_ent *trace);
+void set_graph_array(struct trace_array *tr);
+
+void tracing_start_cmdline_record(void);
+void tracing_stop_cmdline_record(void);
+void tracing_sched_switch_assign_trace(struct trace_array *tr);
+void tracing_stop_sched_switch_record(void);
+void tracing_start_sched_switch_record(void);
+int register_tracer(struct tracer *type);
+void unregister_tracer(struct tracer *type);
+int is_tracing_stopped(void);
+
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
+extern unsigned long nsecs_to_usecs(unsigned long nsecs);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+extern unsigned long tracing_max_latency;
+extern unsigned long tracing_thresh;
+
+void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
+void update_max_tr_single(struct trace_array *tr,
+ struct task_struct *tsk, int cpu);
+#endif /* CONFIG_TRACER_MAX_TRACE */
+
+#ifdef CONFIG_STACKTRACE
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+ int skip, int pc);
+
+void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
+ int pc);
+
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+ int pc);
+#else
+static inline void ftrace_trace_stack(struct trace_array *tr,
+ unsigned long flags, int skip, int pc)
+{
+}
+
+static inline void ftrace_trace_userstack(struct trace_array *tr,
+ unsigned long flags, int pc)
+{
+}
+
+static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
+ int skip, int pc)
+{
+}
+#endif /* CONFIG_STACKTRACE */
+
+extern cycle_t ftrace_now(int cpu);
+
+extern void trace_find_cmdline(int pid, char comm[]);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern unsigned long ftrace_update_tot_cnt;
+#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
+extern int DYN_FTRACE_TEST_NAME(void);
+#endif
+
+extern int ring_buffer_expanded;
+extern bool tracing_selftest_disabled;
+DECLARE_PER_CPU(int, ftrace_cpu_disabled);
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+extern int trace_selftest_startup_function(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_function_graph(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_irqsoff(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_preemptoff(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_wakeup(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_nop(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_sched_switch(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_sysprof(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_branch(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_hw_branches(struct tracer *trace,
+ struct trace_array *tr);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+ struct trace_array *tr);
+#endif /* CONFIG_FTRACE_STARTUP_TEST */
+
+extern void *head_page(struct trace_array_cpu *data);
+extern unsigned long long ns2usecs(cycle_t nsec);
+extern int
+trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_array_vprintk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, va_list args);
+int trace_array_printk(struct trace_array *tr,
+ unsigned long ip, const char *fmt, ...);
+
+extern unsigned long trace_flags;
+
+extern int trace_clock_id;
+
+/* Standard output formatting function used for function return traces */
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/* TODO: make this variable */
+#define FTRACE_GRAPH_MAX_FUNCS 32
+extern int ftrace_graph_count;
+extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
+
+static inline int ftrace_graph_addr(unsigned long addr)
+{
+ int i;
+
+ if (!ftrace_graph_count || test_tsk_trace_graph(current))
+ return 1;
+
+ for (i = 0; i < ftrace_graph_count; i++) {
+ if (addr == ftrace_graph_funcs[i])
+ return 1;
+ }
+
+ return 0;
+}
+#else
+static inline int ftrace_graph_addr(unsigned long addr)
+{
+ return 1;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#else /* CONFIG_FUNCTION_GRAPH_TRACER */
+static inline enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+ return TRACE_TYPE_UNHANDLED;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+extern struct list_head ftrace_pids;
+
+#ifdef CONFIG_FUNCTION_TRACER
+static inline int ftrace_trace_task(struct task_struct *task)
+{
+ if (list_empty(&ftrace_pids))
+ return 1;
+
+ return test_tsk_trace_trace(task);
+}
+#else
+static inline int ftrace_trace_task(struct task_struct *task)
+{
+ return 1;
+}
+#endif
+
+/*
+ * struct trace_parser - servers for reading the user input separated by spaces
+ * @cont: set if the input is not complete - no final space char was found
+ * @buffer: holds the parsed user input
+ * @idx: user input lenght
+ * @size: buffer size
+ */
+struct trace_parser {
+ bool cont;
+ char *buffer;
+ unsigned idx;
+ unsigned size;
+};
+
+static inline bool trace_parser_loaded(struct trace_parser *parser)
+{
+ return (parser->idx != 0);
+}
+
+static inline bool trace_parser_cont(struct trace_parser *parser)
+{
+ return parser->cont;
+}
+
+static inline void trace_parser_clear(struct trace_parser *parser)
+{
+ parser->cont = false;
+ parser->idx = 0;
+}
+
+extern int trace_parser_get_init(struct trace_parser *parser, int size);
+extern void trace_parser_put(struct trace_parser *parser);
+extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
+ size_t cnt, loff_t *ppos);
+
+/*
+ * trace_iterator_flags is an enumeration that defines bit
+ * positions into trace_flags that controls the output.
+ *
+ * NOTE: These bits must match the trace_options array in
+ * trace.c.
+ */
+enum trace_iterator_flags {
+ TRACE_ITER_PRINT_PARENT = 0x01,
+ TRACE_ITER_SYM_OFFSET = 0x02,
+ TRACE_ITER_SYM_ADDR = 0x04,
+ TRACE_ITER_VERBOSE = 0x08,
+ TRACE_ITER_RAW = 0x10,
+ TRACE_ITER_HEX = 0x20,
+ TRACE_ITER_BIN = 0x40,
+ TRACE_ITER_BLOCK = 0x80,
+ TRACE_ITER_STACKTRACE = 0x100,
+ TRACE_ITER_PRINTK = 0x200,
+ TRACE_ITER_PREEMPTONLY = 0x400,
+ TRACE_ITER_BRANCH = 0x800,
+ TRACE_ITER_ANNOTATE = 0x1000,
+ TRACE_ITER_USERSTACKTRACE = 0x2000,
+ TRACE_ITER_SYM_USEROBJ = 0x4000,
+ TRACE_ITER_PRINTK_MSGONLY = 0x8000,
+ TRACE_ITER_CONTEXT_INFO = 0x10000, /* Print pid/cpu/time */
+ TRACE_ITER_LATENCY_FMT = 0x20000,
+ TRACE_ITER_SLEEP_TIME = 0x40000,
+ TRACE_ITER_GRAPH_TIME = 0x80000,
+};
+
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
+#define TRACE_ITER_SYM_MASK \
+ (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
+
+extern struct tracer nop_trace;
+
+/**
+ * ftrace_preempt_disable - disable preemption scheduler safe
+ *
+ * When tracing can happen inside the scheduler, there exists
+ * cases that the tracing might happen before the need_resched
+ * flag is checked. If this happens and the tracer calls
+ * preempt_enable (after a disable), a schedule might take place
+ * causing an infinite recursion.
+ *
+ * To prevent this, we read the need_resched flag before
+ * disabling preemption. When we want to enable preemption we
+ * check the flag, if it is set, then we call preempt_enable_no_resched.
+ * Otherwise, we call preempt_enable.
+ *
+ * The rational for doing the above is that if need_resched is set
+ * and we have yet to reschedule, we are either in an atomic location
+ * (where we do not need to check for scheduling) or we are inside
+ * the scheduler and do not want to resched.
+ */
+static inline int ftrace_preempt_disable(void)
+{
+ int resched;
+
+ resched = need_resched();
+ preempt_disable_notrace();
+
+ return resched;
+}
+
+/**
+ * ftrace_preempt_enable - enable preemption scheduler safe
+ * @resched: the return value from ftrace_preempt_disable
+ *
+ * This is a scheduler safe way to enable preemption and not miss
+ * any preemption checks. The disabled saved the state of preemption.
+ * If resched is set, then we are either inside an atomic or
+ * are inside the scheduler (we would have already scheduled
+ * otherwise). In this case, we do not want to call normal
+ * preempt_enable, but preempt_enable_no_resched instead.
+ */
+static inline void ftrace_preempt_enable(int resched)
+{
+ if (resched)
+ preempt_enable_no_resched_notrace();
+ else
+ preempt_enable_notrace();
+}
+
+#ifdef CONFIG_BRANCH_TRACER
+extern int enable_branch_tracing(struct trace_array *tr);
+extern void disable_branch_tracing(void);
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+ if (trace_flags & TRACE_ITER_BRANCH)
+ return enable_branch_tracing(tr);
+ return 0;
+}
+static inline void trace_branch_disable(void)
+{
+ /* due to races, always disable */
+ disable_branch_tracing();
+}
+#else
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+ return 0;
+}
+static inline void trace_branch_disable(void)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+/* set ring buffers to default size if not already done so */
+int tracing_update_buffers(void);
+
+/* trace event type bit fields, not numeric */
+enum {
+ TRACE_EVENT_TYPE_PRINTF = 1,
+ TRACE_EVENT_TYPE_RAW = 2,
+};
+
+struct ftrace_event_field {
+ struct list_head link;
+ char *name;
+ char *type;
+ int filter_type;
+ int offset;
+ int size;
+ int is_signed;
+};
+
+struct event_filter {
+ int n_preds;
+ struct filter_pred **preds;
+ char *filter_string;
+};
+
+struct event_subsystem {
+ struct list_head list;
+ const char *name;
+ struct dentry *entry;
+ struct event_filter *filter;
+ int nr_events;
+};
+
+struct filter_pred;
+struct regex;
+
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
+ int val1, int val2);
+
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+ MATCH_FULL = 0,
+ MATCH_FRONT_ONLY,
+ MATCH_MIDDLE_ONLY,
+ MATCH_END_ONLY,
+};
+
+struct regex {
+ char pattern[MAX_FILTER_STR_VAL];
+ int len;
+ int field_len;
+ regex_match_func match;
+};
+
+struct filter_pred {
+ filter_pred_fn_t fn;
+ u64 val;
+ struct regex regex;
+ char *field_name;
+ int offset;
+ int not;
+ int op;
+ int pop_n;
+};
+
+extern enum regex_type
+filter_parse_regex(char *buff, int len, char **search, int *not);
+extern void print_event_filter(struct ftrace_event_call *call,
+ struct trace_seq *s);
+extern int apply_event_filter(struct ftrace_event_call *call,
+ char *filter_string);
+extern int apply_subsystem_event_filter(struct event_subsystem *system,
+ char *filter_string);
+extern void print_subsystem_event_filter(struct event_subsystem *system,
+ struct trace_seq *s);
+extern int filter_assign_type(const char *type);
+
+static inline int
+filter_check_discard(struct ftrace_event_call *call, void *rec,
+ struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ if (unlikely(call->filter_active) &&
+ !filter_match_preds(call->filter, rec)) {
+ ring_buffer_discard_commit(buffer, event);
+ return 1;
+ }
+
+ return 0;
+}
+
+extern struct mutex event_mutex;
+extern struct list_head ftrace_events;
+
+extern const char *__start___trace_bprintk_fmt[];
+extern const char *__stop___trace_bprintk_fmt[];
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
+ extern struct ftrace_event_call \
+ __attribute__((__aligned__(4))) event_##call;
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \
+ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#include "trace_entries.h"
+
+#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
new file mode 100644
index 00000000000..c21d5f3956a
--- /dev/null
+++ b/kernel/trace/trace_boot.c
@@ -0,0 +1,185 @@
+/*
+ * ring buffer based initcalls tracer
+ *
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+#include <linux/time.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+static struct trace_array *boot_trace;
+static bool pre_initcalls_finished;
+
+/* Tells the boot tracer that the pre_smp_initcalls are finished.
+ * So we are ready .
+ * It doesn't enable sched events tracing however.
+ * You have to call enable_boot_trace to do so.
+ */
+void start_boot_trace(void)
+{
+ pre_initcalls_finished = true;
+}
+
+void enable_boot_trace(void)
+{
+ if (boot_trace && pre_initcalls_finished)
+ tracing_start_sched_switch_record();
+}
+
+void disable_boot_trace(void)
+{
+ if (boot_trace && pre_initcalls_finished)
+ tracing_stop_sched_switch_record();
+}
+
+static int boot_trace_init(struct trace_array *tr)
+{
+ boot_trace = tr;
+
+ if (!tr)
+ return 0;
+
+ tracing_reset_online_cpus(tr);
+
+ tracing_sched_switch_assign_trace(tr);
+ return 0;
+}
+
+static enum print_line_t
+initcall_call_print_line(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct trace_boot_call *field;
+ struct boot_trace_call *call;
+ u64 ts;
+ unsigned long nsec_rem;
+ int ret;
+
+ trace_assign_type(field, entry);
+ call = &field->boot_call;
+ ts = iter->ts;
+ nsec_rem = do_div(ts, NSEC_PER_SEC);
+
+ ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n",
+ (unsigned long)ts, nsec_rem, call->func, call->caller);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ else
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+initcall_ret_print_line(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct trace_boot_ret *field;
+ struct boot_trace_ret *init_ret;
+ u64 ts;
+ unsigned long nsec_rem;
+ int ret;
+
+ trace_assign_type(field, entry);
+ init_ret = &field->boot_ret;
+ ts = iter->ts;
+ nsec_rem = do_div(ts, NSEC_PER_SEC);
+
+ ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
+ "returned %d after %llu msecs\n",
+ (unsigned long) ts,
+ nsec_rem,
+ init_ret->func, init_ret->result, init_ret->duration);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ else
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+
+ switch (entry->type) {
+ case TRACE_BOOT_CALL:
+ return initcall_call_print_line(iter);
+ case TRACE_BOOT_RET:
+ return initcall_ret_print_line(iter);
+ default:
+ return TRACE_TYPE_UNHANDLED;
+ }
+}
+
+struct tracer boot_tracer __read_mostly =
+{
+ .name = "initcall",
+ .init = boot_trace_init,
+ .reset = tracing_reset_online_cpus,
+ .print_line = initcall_print_line,
+};
+
+void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
+{
+ struct ftrace_event_call *call = &event_boot_call;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct trace_boot_call *entry;
+ struct trace_array *tr = boot_trace;
+
+ if (!tr || !pre_initcalls_finished)
+ return;
+
+ /* Get its name now since this function could
+ * disappear because it is in the .init section.
+ */
+ sprint_symbol(bt->func, (unsigned long)fn);
+ preempt_disable();
+
+ buffer = tr->buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL,
+ sizeof(*entry), 0, 0);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ entry->boot_call = *bt;
+ if (!filter_check_discard(call, entry, buffer, event))
+ trace_buffer_unlock_commit(buffer, event, 0, 0);
+ out:
+ preempt_enable();
+}
+
+void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
+{
+ struct ftrace_event_call *call = &event_boot_ret;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct trace_boot_ret *entry;
+ struct trace_array *tr = boot_trace;
+
+ if (!tr || !pre_initcalls_finished)
+ return;
+
+ sprint_symbol(bt->func, (unsigned long)fn);
+ preempt_disable();
+
+ buffer = tr->buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET,
+ sizeof(*entry), 0, 0);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ entry->boot_ret = *bt;
+ if (!filter_check_discard(call, entry, buffer, event))
+ trace_buffer_unlock_commit(buffer, event, 0, 0);
+ out:
+ preempt_enable();
+}
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
new file mode 100644
index 00000000000..4a194f08f88
--- /dev/null
+++ b/kernel/trace/trace_branch.c
@@ -0,0 +1,392 @@
+/*
+ * unlikely profiler
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/irqflags.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/hash.h>
+#include <linux/fs.h>
+#include <asm/local.h>
+
+#include "trace.h"
+#include "trace_stat.h"
+#include "trace_output.h"
+
+#ifdef CONFIG_BRANCH_TRACER
+
+static struct tracer branch_trace;
+static int branch_tracing_enabled __read_mostly;
+static DEFINE_MUTEX(branch_tracing_mutex);
+
+static struct trace_array *branch_tracer;
+
+static void
+probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+ struct ftrace_event_call *call = &event_branch;
+ struct trace_array *tr = branch_tracer;
+ struct ring_buffer_event *event;
+ struct trace_branch *entry;
+ struct ring_buffer *buffer;
+ unsigned long flags;
+ int cpu, pc;
+ const char *p;
+
+ /*
+ * I would love to save just the ftrace_likely_data pointer, but
+ * this code can also be used by modules. Ugly things can happen
+ * if the module is unloaded, and then we go and read the
+ * pointer. This is slower, but much safer.
+ */
+
+ if (unlikely(!tr))
+ return;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+ goto out;
+
+ pc = preempt_count();
+ buffer = tr->buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ goto out;
+
+ entry = ring_buffer_event_data(event);
+
+ /* Strip off the path, only save the file */
+ p = f->file + strlen(f->file);
+ while (p >= f->file && *p != '/')
+ p--;
+ p++;
+
+ strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
+ strncpy(entry->file, p, TRACE_FILE_SIZE);
+ entry->func[TRACE_FUNC_SIZE] = 0;
+ entry->file[TRACE_FILE_SIZE] = 0;
+ entry->line = f->line;
+ entry->correct = val == expect;
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+
+ out:
+ atomic_dec(&tr->data[cpu]->disabled);
+ local_irq_restore(flags);
+}
+
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+ if (!branch_tracing_enabled)
+ return;
+
+ probe_likely_condition(f, val, expect);
+}
+
+int enable_branch_tracing(struct trace_array *tr)
+{
+ mutex_lock(&branch_tracing_mutex);
+ branch_tracer = tr;
+ /*
+ * Must be seen before enabling. The reader is a condition
+ * where we do not need a matching rmb()
+ */
+ smp_wmb();
+ branch_tracing_enabled++;
+ mutex_unlock(&branch_tracing_mutex);
+
+ return 0;
+}
+
+void disable_branch_tracing(void)
+{
+ mutex_lock(&branch_tracing_mutex);
+
+ if (!branch_tracing_enabled)
+ goto out_unlock;
+
+ branch_tracing_enabled--;
+
+ out_unlock:
+ mutex_unlock(&branch_tracing_mutex);
+}
+
+static void start_branch_trace(struct trace_array *tr)
+{
+ enable_branch_tracing(tr);
+}
+
+static void stop_branch_trace(struct trace_array *tr)
+{
+ disable_branch_tracing();
+}
+
+static int branch_trace_init(struct trace_array *tr)
+{
+ start_branch_trace(tr);
+ return 0;
+}
+
+static void branch_trace_reset(struct trace_array *tr)
+{
+ stop_branch_trace(tr);
+}
+
+static enum print_line_t trace_branch_print(struct trace_iterator *iter,
+ int flags)
+{
+ struct trace_branch *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (trace_seq_printf(&iter->seq, "[%s] %s:%s:%d\n",
+ field->correct ? " ok " : " MISS ",
+ field->func,
+ field->file,
+ field->line))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static void branch_print_header(struct seq_file *s)
+{
+ seq_puts(s, "# TASK-PID CPU# TIMESTAMP CORRECT"
+ " FUNC:FILE:LINE\n");
+ seq_puts(s, "# | | | | | "
+ " |\n");
+}
+
+static struct trace_event trace_branch_event = {
+ .type = TRACE_BRANCH,
+ .trace = trace_branch_print,
+};
+
+static struct tracer branch_trace __read_mostly =
+{
+ .name = "branch",
+ .init = branch_trace_init,
+ .reset = branch_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_branch,
+#endif /* CONFIG_FTRACE_SELFTEST */
+ .print_header = branch_print_header,
+};
+
+__init static int init_branch_tracer(void)
+{
+ int ret;
+
+ ret = register_ftrace_event(&trace_branch_event);
+ if (!ret) {
+ printk(KERN_WARNING "Warning: could not register "
+ "branch events\n");
+ return 1;
+ }
+ return register_tracer(&branch_trace);
+}
+device_initcall(init_branch_tracer);
+
+#else
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
+{
+ /*
+ * I would love to have a trace point here instead, but the
+ * trace point code is so inundated with unlikely and likely
+ * conditions that the recursive nightmare that exists is too
+ * much to try to get working. At least for now.
+ */
+ trace_likely_condition(f, val, expect);
+
+ /* FIXME: Make this atomic! */
+ if (val == expect)
+ f->correct++;
+ else
+ f->incorrect++;
+}
+EXPORT_SYMBOL(ftrace_likely_update);
+
+extern unsigned long __start_annotated_branch_profile[];
+extern unsigned long __stop_annotated_branch_profile[];
+
+static int annotated_branch_stat_headers(struct seq_file *m)
+{
+ seq_printf(m, " correct incorrect %% ");
+ seq_printf(m, " Function "
+ " File Line\n"
+ " ------- --------- - "
+ " -------- "
+ " ---- ----\n");
+ return 0;
+}
+
+static inline long get_incorrect_percent(struct ftrace_branch_data *p)
+{
+ long percent;
+
+ if (p->correct) {
+ percent = p->incorrect * 100;
+ percent /= p->correct + p->incorrect;
+ } else
+ percent = p->incorrect ? 100 : -1;
+
+ return percent;
+}
+
+static int branch_stat_show(struct seq_file *m, void *v)
+{
+ struct ftrace_branch_data *p = v;
+ const char *f;
+ long percent;
+
+ /* Only print the file, not the path */
+ f = p->file + strlen(p->file);
+ while (f >= p->file && *f != '/')
+ f--;
+ f++;
+
+ /*
+ * The miss is overlayed on correct, and hit on incorrect.
+ */
+ percent = get_incorrect_percent(p);
+
+ seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect);
+ if (percent < 0)
+ seq_printf(m, " X ");
+ else
+ seq_printf(m, "%3ld ", percent);
+ seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
+ return 0;
+}
+
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
+{
+ return __start_annotated_branch_profile;
+}
+
+static void *
+annotated_branch_stat_next(void *v, int idx)
+{
+ struct ftrace_branch_data *p = v;
+
+ ++p;
+
+ if ((void *)p >= (void *)__stop_annotated_branch_profile)
+ return NULL;
+
+ return p;
+}
+
+static int annotated_branch_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_branch_data *a = p1;
+ struct ftrace_branch_data *b = p2;
+
+ long percent_a, percent_b;
+
+ percent_a = get_incorrect_percent(a);
+ percent_b = get_incorrect_percent(b);
+
+ if (percent_a < percent_b)
+ return -1;
+ if (percent_a > percent_b)
+ return 1;
+ else
+ return 0;
+}
+
+static struct tracer_stat annotated_branch_stats = {
+ .name = "branch_annotated",
+ .stat_start = annotated_branch_stat_start,
+ .stat_next = annotated_branch_stat_next,
+ .stat_cmp = annotated_branch_stat_cmp,
+ .stat_headers = annotated_branch_stat_headers,
+ .stat_show = branch_stat_show
+};
+
+__init static int init_annotated_branch_stats(void)
+{
+ int ret;
+
+ ret = register_stat_tracer(&annotated_branch_stats);
+ if (!ret) {
+ printk(KERN_WARNING "Warning: could not register "
+ "annotated branches stats\n");
+ return 1;
+ }
+ return 0;
+}
+fs_initcall(init_annotated_branch_stats);
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+
+extern unsigned long __start_branch_profile[];
+extern unsigned long __stop_branch_profile[];
+
+static int all_branch_stat_headers(struct seq_file *m)
+{
+ seq_printf(m, " miss hit %% ");
+ seq_printf(m, " Function "
+ " File Line\n"
+ " ------- --------- - "
+ " -------- "
+ " ---- ----\n");
+ return 0;
+}
+
+static void *all_branch_stat_start(struct tracer_stat *trace)
+{
+ return __start_branch_profile;
+}
+
+static void *
+all_branch_stat_next(void *v, int idx)
+{
+ struct ftrace_branch_data *p = v;
+
+ ++p;
+
+ if ((void *)p >= (void *)__stop_branch_profile)
+ return NULL;
+
+ return p;
+}
+
+static struct tracer_stat all_branch_stats = {
+ .name = "branch_all",
+ .stat_start = all_branch_stat_start,
+ .stat_next = all_branch_stat_next,
+ .stat_headers = all_branch_stat_headers,
+ .stat_show = branch_stat_show
+};
+
+__init static int all_annotated_branch_stats(void)
+{
+ int ret;
+
+ ret = register_stat_tracer(&all_branch_stats);
+ if (!ret) {
+ printk(KERN_WARNING "Warning: could not register "
+ "all branches stats\n");
+ return 1;
+ }
+ return 0;
+}
+fs_initcall(all_annotated_branch_stats);
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
new file mode 100644
index 00000000000..84a3a7ba072
--- /dev/null
+++ b/kernel/trace/trace_clock.c
@@ -0,0 +1,115 @@
+/*
+ * tracing clocks
+ *
+ * Copyright (C) 2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * Implements 3 trace clock variants, with differing scalability/precision
+ * tradeoffs:
+ *
+ * - local: CPU-local trace clock
+ * - medium: scalable global clock with some jitter
+ * - global: globally monotonic, serialized clock
+ *
+ * Tracer plugins will chose a default from these clocks.
+ */
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/ktime.h>
+#include <linux/trace_clock.h>
+
+#include "trace.h"
+
+/*
+ * trace_clock_local(): the simplest and least coherent tracing clock.
+ *
+ * Useful for tracing that does not cross to other CPUs nor
+ * does it go through idle events.
+ */
+u64 notrace trace_clock_local(void)
+{
+ u64 clock;
+ int resched;
+
+ /*
+ * sched_clock() is an architecture implemented, fast, scalable,
+ * lockless clock. It is not guaranteed to be coherent across
+ * CPUs, nor across CPU idle events.
+ */
+ resched = ftrace_preempt_disable();
+ clock = sched_clock();
+ ftrace_preempt_enable(resched);
+
+ return clock;
+}
+
+/*
+ * trace_clock(): 'inbetween' trace clock. Not completely serialized,
+ * but not completely incorrect when crossing CPUs either.
+ *
+ * This is based on cpu_clock(), which will allow at most ~1 jiffy of
+ * jitter between CPUs. So it's a pretty scalable clock, but there
+ * can be offsets in the trace data.
+ */
+u64 notrace trace_clock(void)
+{
+ return cpu_clock(raw_smp_processor_id());
+}
+
+
+/*
+ * trace_clock_global(): special globally coherent trace clock
+ *
+ * It has higher overhead than the other trace clocks but is still
+ * an order of magnitude faster than GTOD derived hardware clocks.
+ *
+ * Used by plugins that need globally coherent timestamps.
+ */
+
+/* keep prev_time and lock in the same cacheline. */
+static struct {
+ u64 prev_time;
+ arch_spinlock_t lock;
+} trace_clock_struct ____cacheline_aligned_in_smp =
+ {
+ .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED,
+ };
+
+u64 notrace trace_clock_global(void)
+{
+ unsigned long flags;
+ int this_cpu;
+ u64 now;
+
+ raw_local_irq_save(flags);
+
+ this_cpu = raw_smp_processor_id();
+ now = cpu_clock(this_cpu);
+ /*
+ * If in an NMI context then dont risk lockups and return the
+ * cpu_clock() time:
+ */
+ if (unlikely(in_nmi()))
+ goto out;
+
+ arch_spin_lock(&trace_clock_struct.lock);
+
+ /*
+ * TODO: if this happens often then maybe we should reset
+ * my_scd->clock to prev_time+1, to make sure
+ * we start ticking with the local clock from now on?
+ */
+ if ((s64)(now - trace_clock_struct.prev_time) < 0)
+ now = trace_clock_struct.prev_time + 1;
+
+ trace_clock_struct.prev_time = now;
+
+ arch_spin_unlock(&trace_clock_struct.lock);
+
+ out:
+ raw_local_irq_restore(flags);
+
+ return now;
+}
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
new file mode 100644
index 00000000000..c16a08f399d
--- /dev/null
+++ b/kernel/trace/trace_entries.h
@@ -0,0 +1,382 @@
+/*
+ * This file defines the trace event structures that go into the ring
+ * buffer directly. They are created via macros so that changes for them
+ * appear in the format file. Using macros will automate this process.
+ *
+ * The macro used to create a ftrace data structure is:
+ *
+ * FTRACE_ENTRY( name, struct_name, id, structure, print )
+ *
+ * @name: the name used the event name, as well as the name of
+ * the directory that holds the format file.
+ *
+ * @struct_name: the name of the structure that is created.
+ *
+ * @id: The event identifier that is used to detect what event
+ * this is from the ring buffer.
+ *
+ * @structure: the structure layout
+ *
+ * - __field( type, item )
+ * This is equivalent to declaring
+ * type item;
+ * in the structure.
+ * - __array( type, item, size )
+ * This is equivalent to declaring
+ * type item[size];
+ * in the structure.
+ *
+ * * for structures within structures, the format of the internal
+ * structure is layed out. This allows the internal structure
+ * to be deciphered for the format file. Although these macros
+ * may become out of sync with the internal structure, they
+ * will create a compile error if it happens. Since the
+ * internel structures are just tracing helpers, this is not
+ * an issue.
+ *
+ * When an internal structure is used, it should use:
+ *
+ * __field_struct( type, item )
+ *
+ * instead of __field. This will prevent it from being shown in
+ * the output file. The fields in the structure should use.
+ *
+ * __field_desc( type, container, item )
+ * __array_desc( type, container, item, len )
+ *
+ * type, item and len are the same as __field and __array, but
+ * container is added. This is the name of the item in
+ * __field_struct that this is describing.
+ *
+ *
+ * @print: the print format shown to users in the format file.
+ */
+
+/*
+ * Function trace entry - function address and parent function addres:
+ */
+FTRACE_ENTRY(function, ftrace_entry,
+
+ TRACE_FN,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __field( unsigned long, parent_ip )
+ ),
+
+ F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+);
+
+/* Function call entry */
+FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
+
+ TRACE_GRAPH_ENT,
+
+ F_STRUCT(
+ __field_struct( struct ftrace_graph_ent, graph_ent )
+ __field_desc( unsigned long, graph_ent, func )
+ __field_desc( int, graph_ent, depth )
+ ),
+
+ F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+);
+
+/* Function return entry */
+FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
+
+ TRACE_GRAPH_RET,
+
+ F_STRUCT(
+ __field_struct( struct ftrace_graph_ret, ret )
+ __field_desc( unsigned long, ret, func )
+ __field_desc( unsigned long long, ret, calltime)
+ __field_desc( unsigned long long, ret, rettime )
+ __field_desc( unsigned long, ret, overrun )
+ __field_desc( int, ret, depth )
+ ),
+
+ F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d",
+ __entry->func, __entry->depth,
+ __entry->calltime, __entry->rettime,
+ __entry->depth)
+);
+
+/*
+ * Context switch trace entry - which task (and prio) we switched from/to:
+ *
+ * This is used for both wakeup and context switches. We only want
+ * to create one structure, but we need two outputs for it.
+ */
+#define FTRACE_CTX_FIELDS \
+ __field( unsigned int, prev_pid ) \
+ __field( unsigned char, prev_prio ) \
+ __field( unsigned char, prev_state ) \
+ __field( unsigned int, next_pid ) \
+ __field( unsigned char, next_prio ) \
+ __field( unsigned char, next_state ) \
+ __field( unsigned int, next_cpu )
+
+FTRACE_ENTRY(context_switch, ctx_switch_entry,
+
+ TRACE_CTX,
+
+ F_STRUCT(
+ FTRACE_CTX_FIELDS
+ ),
+
+ F_printk("%u:%u:%u ==> %u:%u:%u [%03u]",
+ __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+ __entry->next_pid, __entry->next_prio, __entry->next_state,
+ __entry->next_cpu
+ )
+);
+
+/*
+ * FTRACE_ENTRY_DUP only creates the format file, it will not
+ * create another structure.
+ */
+FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
+
+ TRACE_WAKE,
+
+ F_STRUCT(
+ FTRACE_CTX_FIELDS
+ ),
+
+ F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]",
+ __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+ __entry->next_pid, __entry->next_prio, __entry->next_state,
+ __entry->next_cpu
+ )
+);
+
+/*
+ * Special (free-form) trace entry:
+ */
+FTRACE_ENTRY(special, special_entry,
+
+ TRACE_SPECIAL,
+
+ F_STRUCT(
+ __field( unsigned long, arg1 )
+ __field( unsigned long, arg2 )
+ __field( unsigned long, arg3 )
+ ),
+
+ F_printk("(%08lx) (%08lx) (%08lx)",
+ __entry->arg1, __entry->arg2, __entry->arg3)
+);
+
+/*
+ * Stack-trace entry:
+ */
+
+#define FTRACE_STACK_ENTRIES 8
+
+FTRACE_ENTRY(kernel_stack, stack_entry,
+
+ TRACE_STACK,
+
+ F_STRUCT(
+ __array( unsigned long, caller, FTRACE_STACK_ENTRIES )
+ ),
+
+ F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
+ "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+ __entry->caller[0], __entry->caller[1], __entry->caller[2],
+ __entry->caller[3], __entry->caller[4], __entry->caller[5],
+ __entry->caller[6], __entry->caller[7])
+);
+
+FTRACE_ENTRY(user_stack, userstack_entry,
+
+ TRACE_USER_STACK,
+
+ F_STRUCT(
+ __field( unsigned int, tgid )
+ __array( unsigned long, caller, FTRACE_STACK_ENTRIES )
+ ),
+
+ F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
+ "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+ __entry->caller[0], __entry->caller[1], __entry->caller[2],
+ __entry->caller[3], __entry->caller[4], __entry->caller[5],
+ __entry->caller[6], __entry->caller[7])
+);
+
+/*
+ * trace_printk entry:
+ */
+FTRACE_ENTRY(bprint, bprint_entry,
+
+ TRACE_BPRINT,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __field( const char *, fmt )
+ __dynamic_array( u32, buf )
+ ),
+
+ F_printk("%08lx fmt:%p",
+ __entry->ip, __entry->fmt)
+);
+
+FTRACE_ENTRY(print, print_entry,
+
+ TRACE_PRINT,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __dynamic_array( char, buf )
+ ),
+
+ F_printk("%08lx %s",
+ __entry->ip, __entry->buf)
+);
+
+FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
+
+ TRACE_MMIO_RW,
+
+ F_STRUCT(
+ __field_struct( struct mmiotrace_rw, rw )
+ __field_desc( resource_size_t, rw, phys )
+ __field_desc( unsigned long, rw, value )
+ __field_desc( unsigned long, rw, pc )
+ __field_desc( int, rw, map_id )
+ __field_desc( unsigned char, rw, opcode )
+ __field_desc( unsigned char, rw, width )
+ ),
+
+ F_printk("%lx %lx %lx %d %x %x",
+ (unsigned long)__entry->phys, __entry->value, __entry->pc,
+ __entry->map_id, __entry->opcode, __entry->width)
+);
+
+FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
+
+ TRACE_MMIO_MAP,
+
+ F_STRUCT(
+ __field_struct( struct mmiotrace_map, map )
+ __field_desc( resource_size_t, map, phys )
+ __field_desc( unsigned long, map, virt )
+ __field_desc( unsigned long, map, len )
+ __field_desc( int, map, map_id )
+ __field_desc( unsigned char, map, opcode )
+ ),
+
+ F_printk("%lx %lx %lx %d %x",
+ (unsigned long)__entry->phys, __entry->virt, __entry->len,
+ __entry->map_id, __entry->opcode)
+);
+
+FTRACE_ENTRY(boot_call, trace_boot_call,
+
+ TRACE_BOOT_CALL,
+
+ F_STRUCT(
+ __field_struct( struct boot_trace_call, boot_call )
+ __field_desc( pid_t, boot_call, caller )
+ __array_desc( char, boot_call, func, KSYM_SYMBOL_LEN)
+ ),
+
+ F_printk("%d %s", __entry->caller, __entry->func)
+);
+
+FTRACE_ENTRY(boot_ret, trace_boot_ret,
+
+ TRACE_BOOT_RET,
+
+ F_STRUCT(
+ __field_struct( struct boot_trace_ret, boot_ret )
+ __array_desc( char, boot_ret, func, KSYM_SYMBOL_LEN)
+ __field_desc( int, boot_ret, result )
+ __field_desc( unsigned long, boot_ret, duration )
+ ),
+
+ F_printk("%s %d %lx",
+ __entry->func, __entry->result, __entry->duration)
+);
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+
+FTRACE_ENTRY(branch, trace_branch,
+
+ TRACE_BRANCH,
+
+ F_STRUCT(
+ __field( unsigned int, line )
+ __array( char, func, TRACE_FUNC_SIZE+1 )
+ __array( char, file, TRACE_FILE_SIZE+1 )
+ __field( char, correct )
+ ),
+
+ F_printk("%u:%s:%s (%u)",
+ __entry->line,
+ __entry->func, __entry->file, __entry->correct)
+);
+
+FTRACE_ENTRY(hw_branch, hw_branch_entry,
+
+ TRACE_HW_BRANCHES,
+
+ F_STRUCT(
+ __field( u64, from )
+ __field( u64, to )
+ ),
+
+ F_printk("from: %llx to: %llx", __entry->from, __entry->to)
+);
+
+FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
+
+ TRACE_KMEM_ALLOC,
+
+ F_STRUCT(
+ __field( enum kmemtrace_type_id, type_id )
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ __field( size_t, bytes_req )
+ __field( size_t, bytes_alloc )
+ __field( gfp_t, gfp_flags )
+ __field( int, node )
+ ),
+
+ F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi"
+ " flags:%x node:%d",
+ __entry->type_id, __entry->call_site, __entry->ptr,
+ __entry->bytes_req, __entry->bytes_alloc,
+ __entry->gfp_flags, __entry->node)
+);
+
+FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
+
+ TRACE_KMEM_FREE,
+
+ F_STRUCT(
+ __field( enum kmemtrace_type_id, type_id )
+ __field( unsigned long, call_site )
+ __field( const void *, ptr )
+ ),
+
+ F_printk("type:%u call_site:%lx ptr:%p",
+ __entry->type_id, __entry->call_site, __entry->ptr)
+);
+
+FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
+
+ TRACE_KSYM,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __field( unsigned char, type )
+ __array( char , cmd, TASK_COMM_LEN )
+ __field( unsigned long, addr )
+ ),
+
+ F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s",
+ (void *)__entry->ip, (unsigned int)__entry->type,
+ (void *)__entry->addr, __entry->cmd)
+);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
new file mode 100644
index 00000000000..9e25573242c
--- /dev/null
+++ b/kernel/trace/trace_event_profile.c
@@ -0,0 +1,122 @@
+/*
+ * trace event based perf counter profiling
+ *
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ */
+
+#include <linux/module.h>
+#include "trace.h"
+
+
+char *perf_trace_buf;
+EXPORT_SYMBOL_GPL(perf_trace_buf);
+
+char *perf_trace_buf_nmi;
+EXPORT_SYMBOL_GPL(perf_trace_buf_nmi);
+
+typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
+
+/* Count the events in use (per event id, not per instance) */
+static int total_profile_count;
+
+static int ftrace_profile_enable_event(struct ftrace_event_call *event)
+{
+ char *buf;
+ int ret = -ENOMEM;
+
+ if (event->profile_count++ > 0)
+ return 0;
+
+ if (!total_profile_count) {
+ buf = (char *)alloc_percpu(perf_trace_t);
+ if (!buf)
+ goto fail_buf;
+
+ rcu_assign_pointer(perf_trace_buf, buf);
+
+ buf = (char *)alloc_percpu(perf_trace_t);
+ if (!buf)
+ goto fail_buf_nmi;
+
+ rcu_assign_pointer(perf_trace_buf_nmi, buf);
+ }
+
+ ret = event->profile_enable(event);
+ if (!ret) {
+ total_profile_count++;
+ return 0;
+ }
+
+fail_buf_nmi:
+ if (!total_profile_count) {
+ free_percpu(perf_trace_buf_nmi);
+ free_percpu(perf_trace_buf);
+ perf_trace_buf_nmi = NULL;
+ perf_trace_buf = NULL;
+ }
+fail_buf:
+ event->profile_count--;
+
+ return ret;
+}
+
+int ftrace_profile_enable(int event_id)
+{
+ struct ftrace_event_call *event;
+ int ret = -EINVAL;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(event, &ftrace_events, list) {
+ if (event->id == event_id && event->profile_enable &&
+ try_module_get(event->mod)) {
+ ret = ftrace_profile_enable_event(event);
+ break;
+ }
+ }
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+static void ftrace_profile_disable_event(struct ftrace_event_call *event)
+{
+ char *buf, *nmi_buf;
+
+ if (--event->profile_count > 0)
+ return;
+
+ event->profile_disable(event);
+
+ if (!--total_profile_count) {
+ buf = perf_trace_buf;
+ rcu_assign_pointer(perf_trace_buf, NULL);
+
+ nmi_buf = perf_trace_buf_nmi;
+ rcu_assign_pointer(perf_trace_buf_nmi, NULL);
+
+ /*
+ * Ensure every events in profiling have finished before
+ * releasing the buffers
+ */
+ synchronize_sched();
+
+ free_percpu(buf);
+ free_percpu(nmi_buf);
+ }
+}
+
+void ftrace_profile_disable(int event_id)
+{
+ struct ftrace_event_call *event;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(event, &ftrace_events, list) {
+ if (event->id == event_id) {
+ ftrace_profile_disable_event(event);
+ module_put(event->mod);
+ break;
+ }
+ }
+ mutex_unlock(&event_mutex);
+}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
new file mode 100644
index 00000000000..189b09baf4f
--- /dev/null
+++ b/kernel/trace/trace_events.c
@@ -0,0 +1,1546 @@
+/*
+ * event tracer
+ *
+ * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * - Added format output of fields of the trace point.
+ * This was based off of work by Tom Zanussi <tzanussi@gmail.com>.
+ *
+ */
+
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/delay.h>
+
+#include <asm/setup.h>
+
+#include "trace_output.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM "TRACE_SYSTEM"
+
+DEFINE_MUTEX(event_mutex);
+
+LIST_HEAD(ftrace_events);
+
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+ const char *name, int offset, int size, int is_signed,
+ int filter_type)
+{
+ struct ftrace_event_field *field;
+
+ field = kzalloc(sizeof(*field), GFP_KERNEL);
+ if (!field)
+ goto err;
+
+ field->name = kstrdup(name, GFP_KERNEL);
+ if (!field->name)
+ goto err;
+
+ field->type = kstrdup(type, GFP_KERNEL);
+ if (!field->type)
+ goto err;
+
+ if (filter_type == FILTER_OTHER)
+ field->filter_type = filter_assign_type(type);
+ else
+ field->filter_type = filter_type;
+
+ field->offset = offset;
+ field->size = size;
+ field->is_signed = is_signed;
+
+ list_add(&field->link, &call->fields);
+
+ return 0;
+
+err:
+ if (field) {
+ kfree(field->name);
+ kfree(field->type);
+ }
+ kfree(field);
+
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(trace_define_field);
+
+#define __common_field(type, item) \
+ ret = trace_define_field(call, #type, "common_" #item, \
+ offsetof(typeof(ent), item), \
+ sizeof(ent.item), \
+ is_signed_type(type), FILTER_OTHER); \
+ if (ret) \
+ return ret;
+
+static int trace_define_common_fields(struct ftrace_event_call *call)
+{
+ int ret;
+ struct trace_entry ent;
+
+ __common_field(unsigned short, type);
+ __common_field(unsigned char, flags);
+ __common_field(unsigned char, preempt_count);
+ __common_field(int, pid);
+ __common_field(int, lock_depth);
+
+ return ret;
+}
+
+void trace_destroy_fields(struct ftrace_event_call *call)
+{
+ struct ftrace_event_field *field, *next;
+
+ list_for_each_entry_safe(field, next, &call->fields, link) {
+ list_del(&field->link);
+ kfree(field->type);
+ kfree(field->name);
+ kfree(field);
+ }
+}
+
+int trace_event_raw_init(struct ftrace_event_call *call)
+{
+ int id;
+
+ id = register_ftrace_event(call->event);
+ if (!id)
+ return -ENODEV;
+ call->id = id;
+ INIT_LIST_HEAD(&call->fields);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(trace_event_raw_init);
+
+static int ftrace_event_enable_disable(struct ftrace_event_call *call,
+ int enable)
+{
+ int ret = 0;
+
+ switch (enable) {
+ case 0:
+ if (call->enabled) {
+ call->enabled = 0;
+ tracing_stop_cmdline_record();
+ call->unregfunc(call);
+ }
+ break;
+ case 1:
+ if (!call->enabled) {
+ tracing_start_cmdline_record();
+ ret = call->regfunc(call);
+ if (ret) {
+ tracing_stop_cmdline_record();
+ pr_info("event trace: Could not enable event "
+ "%s\n", call->name);
+ break;
+ }
+ call->enabled = 1;
+ }
+ break;
+ }
+
+ return ret;
+}
+
+static void ftrace_clear_events(void)
+{
+ struct ftrace_event_call *call;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ ftrace_event_enable_disable(call, 0);
+ }
+ mutex_unlock(&event_mutex);
+}
+
+/*
+ * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
+ */
+static int __ftrace_set_clr_event(const char *match, const char *sub,
+ const char *event, int set)
+{
+ struct ftrace_event_call *call;
+ int ret = -EINVAL;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (match &&
+ strcmp(match, call->name) != 0 &&
+ strcmp(match, call->system) != 0)
+ continue;
+
+ if (sub && strcmp(sub, call->system) != 0)
+ continue;
+
+ if (event && strcmp(event, call->name) != 0)
+ continue;
+
+ ftrace_event_enable_disable(call, set);
+
+ ret = 0;
+ }
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+static int ftrace_set_clr_event(char *buf, int set)
+{
+ char *event = NULL, *sub = NULL, *match;
+
+ /*
+ * The buf format can be <subsystem>:<event-name>
+ * *:<event-name> means any event by that name.
+ * :<event-name> is the same.
+ *
+ * <subsystem>:* means all events in that subsystem
+ * <subsystem>: means the same.
+ *
+ * <name> (no ':') means all events in a subsystem with
+ * the name <name> or any event that matches <name>
+ */
+
+ match = strsep(&buf, ":");
+ if (buf) {
+ sub = match;
+ event = buf;
+ match = NULL;
+
+ if (!strlen(sub) || strcmp(sub, "*") == 0)
+ sub = NULL;
+ if (!strlen(event) || strcmp(event, "*") == 0)
+ event = NULL;
+ }
+
+ return __ftrace_set_clr_event(match, sub, event, set);
+}
+
+/**
+ * trace_set_clr_event - enable or disable an event
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @set: 1 to enable, 0 to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_set_clr_event(const char *system, const char *event, int set)
+{
+ return __ftrace_set_clr_event(NULL, system, event, set);
+}
+
+/* 128 should be much more than enough */
+#define EVENT_BUF_SIZE 127
+
+static ssize_t
+ftrace_event_write(struct file *file, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct trace_parser parser;
+ ssize_t read, ret;
+
+ if (!cnt)
+ return 0;
+
+ ret = tracing_update_buffers();
+ if (ret < 0)
+ return ret;
+
+ if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
+ return -ENOMEM;
+
+ read = trace_get_user(&parser, ubuf, cnt, ppos);
+
+ if (read >= 0 && trace_parser_loaded((&parser))) {
+ int set = 1;
+
+ if (*parser.buffer == '!')
+ set = 0;
+
+ parser.buffer[parser.idx] = 0;
+
+ ret = ftrace_set_clr_event(parser.buffer + !set, set);
+ if (ret)
+ goto out_put;
+ }
+
+ ret = read;
+
+ out_put:
+ trace_parser_put(&parser);
+
+ return ret;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct ftrace_event_call *call = v;
+
+ (*pos)++;
+
+ list_for_each_entry_continue(call, &ftrace_events, list) {
+ /*
+ * The ftrace subsystem is for showing formats only.
+ * They can not be enabled or disabled via the event files.
+ */
+ if (call->regfunc)
+ return call;
+ }
+
+ return NULL;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_event_call *call;
+ loff_t l;
+
+ mutex_lock(&event_mutex);
+
+ call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+ for (l = 0; l <= *pos; ) {
+ call = t_next(m, call, &l);
+ if (!call)
+ break;
+ }
+ return call;
+}
+
+static void *
+s_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct ftrace_event_call *call = v;
+
+ (*pos)++;
+
+ list_for_each_entry_continue(call, &ftrace_events, list) {
+ if (call->enabled)
+ return call;
+ }
+
+ return NULL;
+}
+
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_event_call *call;
+ loff_t l;
+
+ mutex_lock(&event_mutex);
+
+ call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+ for (l = 0; l <= *pos; ) {
+ call = s_next(m, call, &l);
+ if (!call)
+ break;
+ }
+ return call;
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+ struct ftrace_event_call *call = v;
+
+ if (strcmp(call->system, TRACE_SYSTEM) != 0)
+ seq_printf(m, "%s:", call->system);
+ seq_printf(m, "%s\n", call->name);
+
+ return 0;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&event_mutex);
+}
+
+static int
+ftrace_event_seq_open(struct inode *inode, struct file *file)
+{
+ const struct seq_operations *seq_ops;
+
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ ftrace_clear_events();
+
+ seq_ops = inode->i_private;
+ return seq_open(file, seq_ops);
+}
+
+static ssize_t
+event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ char *buf;
+
+ if (call->enabled)
+ buf = "1\n";
+ else
+ buf = "0\n";
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+}
+
+static ssize_t
+event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ char buf[64];
+ unsigned long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = tracing_update_buffers();
+ if (ret < 0)
+ return ret;
+
+ switch (val) {
+ case 0:
+ case 1:
+ mutex_lock(&event_mutex);
+ ret = ftrace_event_enable_disable(call, val);
+ mutex_unlock(&event_mutex);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ *ppos += cnt;
+
+ return ret ? ret : cnt;
+}
+
+static ssize_t
+system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ const char set_to_char[4] = { '?', '0', '1', 'X' };
+ const char *system = filp->private_data;
+ struct ftrace_event_call *call;
+ char buf[2];
+ int set = 0;
+ int ret;
+
+ mutex_lock(&event_mutex);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->name || !call->regfunc)
+ continue;
+
+ if (system && strcmp(call->system, system) != 0)
+ continue;
+
+ /*
+ * We need to find out if all the events are set
+ * or if all events or cleared, or if we have
+ * a mixture.
+ */
+ set |= (1 << !!call->enabled);
+
+ /*
+ * If we have a mixture, no need to look further.
+ */
+ if (set == 3)
+ break;
+ }
+ mutex_unlock(&event_mutex);
+
+ buf[0] = set_to_char[set];
+ buf[1] = '\n';
+
+ ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+
+ return ret;
+}
+
+static ssize_t
+system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ const char *system = filp->private_data;
+ unsigned long val;
+ char buf[64];
+ ssize_t ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = tracing_update_buffers();
+ if (ret < 0)
+ return ret;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
+ ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+ if (ret)
+ goto out;
+
+ ret = cnt;
+
+out:
+ *ppos += cnt;
+
+ return ret;
+}
+
+extern char *__bad_type_size(void);
+
+#undef FIELD
+#define FIELD(type, name) \
+ sizeof(type) != sizeof(field.name) ? __bad_type_size() : \
+ #type, "common_" #name, offsetof(typeof(field), name), \
+ sizeof(field.name), is_signed_type(type)
+
+static int trace_write_header(struct trace_seq *s)
+{
+ struct trace_entry field;
+
+ /* struct trace_entry */
+ return trace_seq_printf(s,
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\n",
+ FIELD(unsigned short, type),
+ FIELD(unsigned char, flags),
+ FIELD(unsigned char, preempt_count),
+ FIELD(int, pid),
+ FIELD(int, lock_depth));
+}
+
+static ssize_t
+event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ struct trace_seq *s;
+ char *buf;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ /* If any of the first writes fail, so will the show_format. */
+
+ trace_seq_printf(s, "name: %s\n", call->name);
+ trace_seq_printf(s, "ID: %d\n", call->id);
+ trace_seq_printf(s, "format:\n");
+ trace_write_header(s);
+
+ r = call->show_format(call, s);
+ if (!r) {
+ /*
+ * ug! The format output is bigger than a PAGE!!
+ */
+ buf = "FORMAT TOO BIG\n";
+ r = simple_read_from_buffer(ubuf, cnt, ppos,
+ buf, strlen(buf));
+ goto out;
+ }
+
+ r = simple_read_from_buffer(ubuf, cnt, ppos,
+ s->buffer, s->len);
+ out:
+ kfree(s);
+ return r;
+}
+
+static ssize_t
+event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+ trace_seq_printf(s, "%d\n", call->id);
+
+ r = simple_read_from_buffer(ubuf, cnt, ppos,
+ s->buffer, s->len);
+ kfree(s);
+ return r;
+}
+
+static ssize_t
+event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ print_event_filter(call, s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
+static ssize_t
+event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct ftrace_event_call *call = filp->private_data;
+ char *buf;
+ int err;
+
+ if (cnt >= PAGE_SIZE)
+ return -EINVAL;
+
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long) buf);
+ return -EFAULT;
+ }
+ buf[cnt] = '\0';
+
+ err = apply_event_filter(call, buf);
+ free_page((unsigned long) buf);
+ if (err < 0)
+ return err;
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct event_subsystem *system = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ print_subsystem_event_filter(system, s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
+static ssize_t
+subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ loff_t *ppos)
+{
+ struct event_subsystem *system = filp->private_data;
+ char *buf;
+ int err;
+
+ if (cnt >= PAGE_SIZE)
+ return -EINVAL;
+
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long) buf);
+ return -EFAULT;
+ }
+ buf[cnt] = '\0';
+
+ err = apply_subsystem_event_filter(system, buf);
+ free_page((unsigned long) buf);
+ if (err < 0)
+ return err;
+
+ *ppos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ int (*func)(struct trace_seq *s) = filp->private_data;
+ struct trace_seq *s;
+ int r;
+
+ if (*ppos)
+ return 0;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ trace_seq_init(s);
+
+ func(s);
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+ kfree(s);
+
+ return r;
+}
+
+static const struct seq_operations show_event_seq_ops = {
+ .start = t_start,
+ .next = t_next,
+ .show = t_show,
+ .stop = t_stop,
+};
+
+static const struct seq_operations show_set_event_seq_ops = {
+ .start = s_start,
+ .next = s_next,
+ .show = t_show,
+ .stop = t_stop,
+};
+
+static const struct file_operations ftrace_avail_fops = {
+ .open = ftrace_event_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static const struct file_operations ftrace_set_event_fops = {
+ .open = ftrace_event_seq_open,
+ .read = seq_read,
+ .write = ftrace_event_write,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static const struct file_operations ftrace_enable_fops = {
+ .open = tracing_open_generic,
+ .read = event_enable_read,
+ .write = event_enable_write,
+};
+
+static const struct file_operations ftrace_event_format_fops = {
+ .open = tracing_open_generic,
+ .read = event_format_read,
+};
+
+static const struct file_operations ftrace_event_id_fops = {
+ .open = tracing_open_generic,
+ .read = event_id_read,
+};
+
+static const struct file_operations ftrace_event_filter_fops = {
+ .open = tracing_open_generic,
+ .read = event_filter_read,
+ .write = event_filter_write,
+};
+
+static const struct file_operations ftrace_subsystem_filter_fops = {
+ .open = tracing_open_generic,
+ .read = subsystem_filter_read,
+ .write = subsystem_filter_write,
+};
+
+static const struct file_operations ftrace_system_enable_fops = {
+ .open = tracing_open_generic,
+ .read = system_enable_read,
+ .write = system_enable_write,
+};
+
+static const struct file_operations ftrace_show_header_fops = {
+ .open = tracing_open_generic,
+ .read = show_header,
+};
+
+static struct dentry *event_trace_events_dir(void)
+{
+ static struct dentry *d_tracer;
+ static struct dentry *d_events;
+
+ if (d_events)
+ return d_events;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return NULL;
+
+ d_events = debugfs_create_dir("events", d_tracer);
+ if (!d_events)
+ pr_warning("Could not create debugfs "
+ "'events' directory\n");
+
+ return d_events;
+}
+
+static LIST_HEAD(event_subsystems);
+
+static struct dentry *
+event_subsystem_dir(const char *name, struct dentry *d_events)
+{
+ struct event_subsystem *system;
+ struct dentry *entry;
+
+ /* First see if we did not already create this dir */
+ list_for_each_entry(system, &event_subsystems, list) {
+ if (strcmp(system->name, name) == 0) {
+ system->nr_events++;
+ return system->entry;
+ }
+ }
+
+ /* need to create new entry */
+ system = kmalloc(sizeof(*system), GFP_KERNEL);
+ if (!system) {
+ pr_warning("No memory to create event subsystem %s\n",
+ name);
+ return d_events;
+ }
+
+ system->entry = debugfs_create_dir(name, d_events);
+ if (!system->entry) {
+ pr_warning("Could not create event subsystem %s\n",
+ name);
+ kfree(system);
+ return d_events;
+ }
+
+ system->nr_events = 1;
+ system->name = kstrdup(name, GFP_KERNEL);
+ if (!system->name) {
+ debugfs_remove(system->entry);
+ kfree(system);
+ return d_events;
+ }
+
+ list_add(&system->list, &event_subsystems);
+
+ system->filter = NULL;
+
+ system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+ if (!system->filter) {
+ pr_warning("Could not allocate filter for subsystem "
+ "'%s'\n", name);
+ return system->entry;
+ }
+
+ entry = debugfs_create_file("filter", 0644, system->entry, system,
+ &ftrace_subsystem_filter_fops);
+ if (!entry) {
+ kfree(system->filter);
+ system->filter = NULL;
+ pr_warning("Could not create debugfs "
+ "'%s/filter' entry\n", name);
+ }
+
+ trace_create_file("enable", 0644, system->entry,
+ (void *)system->name,
+ &ftrace_system_enable_fops);
+
+ return system->entry;
+}
+
+static int
+event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+ const struct file_operations *id,
+ const struct file_operations *enable,
+ const struct file_operations *filter,
+ const struct file_operations *format)
+{
+ int ret;
+
+ /*
+ * If the trace point header did not define TRACE_SYSTEM
+ * then the system would be called "TRACE_SYSTEM".
+ */
+ if (strcmp(call->system, TRACE_SYSTEM) != 0)
+ d_events = event_subsystem_dir(call->system, d_events);
+
+ call->dir = debugfs_create_dir(call->name, d_events);
+ if (!call->dir) {
+ pr_warning("Could not create debugfs "
+ "'%s' directory\n", call->name);
+ return -1;
+ }
+
+ if (call->regfunc)
+ trace_create_file("enable", 0644, call->dir, call,
+ enable);
+
+ if (call->id && call->profile_enable)
+ trace_create_file("id", 0444, call->dir, call,
+ id);
+
+ if (call->define_fields) {
+ ret = trace_define_common_fields(call);
+ if (!ret)
+ ret = call->define_fields(call);
+ if (ret < 0) {
+ pr_warning("Could not initialize trace point"
+ " events/%s\n", call->name);
+ return ret;
+ }
+ trace_create_file("filter", 0644, call->dir, call,
+ filter);
+ }
+
+ /* A trace may not want to export its format */
+ if (!call->show_format)
+ return 0;
+
+ trace_create_file("format", 0444, call->dir, call,
+ format);
+
+ return 0;
+}
+
+static int __trace_add_event_call(struct ftrace_event_call *call)
+{
+ struct dentry *d_events;
+ int ret;
+
+ if (!call->name)
+ return -EINVAL;
+
+ if (call->raw_init) {
+ ret = call->raw_init(call);
+ if (ret < 0) {
+ if (ret != -ENOSYS)
+ pr_warning("Could not initialize trace "
+ "events/%s\n", call->name);
+ return ret;
+ }
+ }
+
+ d_events = event_trace_events_dir();
+ if (!d_events)
+ return -ENOENT;
+
+ ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+ &ftrace_enable_fops, &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ if (!ret)
+ list_add(&call->list, &ftrace_events);
+
+ return ret;
+}
+
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct ftrace_event_call *call)
+{
+ int ret;
+ mutex_lock(&event_mutex);
+ ret = __trace_add_event_call(call);
+ mutex_unlock(&event_mutex);
+ return ret;
+}
+
+static void remove_subsystem_dir(const char *name)
+{
+ struct event_subsystem *system;
+
+ if (strcmp(name, TRACE_SYSTEM) == 0)
+ return;
+
+ list_for_each_entry(system, &event_subsystems, list) {
+ if (strcmp(system->name, name) == 0) {
+ if (!--system->nr_events) {
+ struct event_filter *filter = system->filter;
+
+ debugfs_remove_recursive(system->entry);
+ list_del(&system->list);
+ if (filter) {
+ kfree(filter->filter_string);
+ kfree(filter);
+ }
+ kfree(system->name);
+ kfree(system);
+ }
+ break;
+ }
+ }
+}
+
+/*
+ * Must be called under locking both of event_mutex and trace_event_mutex.
+ */
+static void __trace_remove_event_call(struct ftrace_event_call *call)
+{
+ ftrace_event_enable_disable(call, 0);
+ if (call->event)
+ __unregister_ftrace_event(call->event);
+ debugfs_remove_recursive(call->dir);
+ list_del(&call->list);
+ trace_destroy_fields(call);
+ destroy_preds(call);
+ remove_subsystem_dir(call->system);
+}
+
+/* Remove an event_call */
+void trace_remove_event_call(struct ftrace_event_call *call)
+{
+ mutex_lock(&event_mutex);
+ down_write(&trace_event_mutex);
+ __trace_remove_event_call(call);
+ up_write(&trace_event_mutex);
+ mutex_unlock(&event_mutex);
+}
+
+#define for_each_event(event, start, end) \
+ for (event = start; \
+ (unsigned long)event < (unsigned long)end; \
+ event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+ struct list_head list;
+ struct module *mod;
+ struct file_operations id;
+ struct file_operations enable;
+ struct file_operations format;
+ struct file_operations filter;
+};
+
+static struct ftrace_module_file_ops *
+trace_create_file_ops(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops;
+
+ /*
+ * This is a bit of a PITA. To allow for correct reference
+ * counting, modules must "own" their file_operations.
+ * To do this, we allocate the file operations that will be
+ * used in the event directory.
+ */
+
+ file_ops = kmalloc(sizeof(*file_ops), GFP_KERNEL);
+ if (!file_ops)
+ return NULL;
+
+ file_ops->mod = mod;
+
+ file_ops->id = ftrace_event_id_fops;
+ file_ops->id.owner = mod;
+
+ file_ops->enable = ftrace_enable_fops;
+ file_ops->enable.owner = mod;
+
+ file_ops->filter = ftrace_event_filter_fops;
+ file_ops->filter.owner = mod;
+
+ file_ops->format = ftrace_event_format_fops;
+ file_ops->format.owner = mod;
+
+ list_add(&file_ops->list, &ftrace_module_file_list);
+
+ return file_ops;
+}
+
+static void trace_module_add_events(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops = NULL;
+ struct ftrace_event_call *call, *start, *end;
+ struct dentry *d_events;
+ int ret;
+
+ start = mod->trace_events;
+ end = mod->trace_events + mod->num_trace_events;
+
+ if (start == end)
+ return;
+
+ d_events = event_trace_events_dir();
+ if (!d_events)
+ return;
+
+ for_each_event(call, start, end) {
+ /* The linker may leave blanks */
+ if (!call->name)
+ continue;
+ if (call->raw_init) {
+ ret = call->raw_init(call);
+ if (ret < 0) {
+ if (ret != -ENOSYS)
+ pr_warning("Could not initialize trace "
+ "point events/%s\n", call->name);
+ continue;
+ }
+ }
+ /*
+ * This module has events, create file ops for this module
+ * if not already done.
+ */
+ if (!file_ops) {
+ file_ops = trace_create_file_ops(mod);
+ if (!file_ops)
+ return;
+ }
+ call->mod = mod;
+ ret = event_create_dir(call, d_events,
+ &file_ops->id, &file_ops->enable,
+ &file_ops->filter, &file_ops->format);
+ if (!ret)
+ list_add(&call->list, &ftrace_events);
+ }
+}
+
+static void trace_module_remove_events(struct module *mod)
+{
+ struct ftrace_module_file_ops *file_ops;
+ struct ftrace_event_call *call, *p;
+ bool found = false;
+
+ down_write(&trace_event_mutex);
+ list_for_each_entry_safe(call, p, &ftrace_events, list) {
+ if (call->mod == mod) {
+ found = true;
+ __trace_remove_event_call(call);
+ }
+ }
+
+ /* Now free the file_operations */
+ list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+ if (file_ops->mod == mod)
+ break;
+ }
+ if (&file_ops->list != &ftrace_module_file_list) {
+ list_del(&file_ops->list);
+ kfree(file_ops);
+ }
+
+ /*
+ * It is safest to reset the ring buffer if the module being unloaded
+ * registered any events.
+ */
+ if (found)
+ tracing_reset_current_online_cpus();
+ up_write(&trace_event_mutex);
+}
+
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ mutex_lock(&event_mutex);
+ switch (val) {
+ case MODULE_STATE_COMING:
+ trace_module_add_events(mod);
+ break;
+ case MODULE_STATE_GOING:
+ trace_module_remove_events(mod);
+ break;
+ }
+ mutex_unlock(&event_mutex);
+
+ return 0;
+}
+#else
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static struct notifier_block trace_module_nb = {
+ .notifier_call = trace_module_notify,
+ .priority = 0,
+};
+
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
+
+static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
+
+static __init int setup_trace_event(char *str)
+{
+ strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+ ring_buffer_expanded = 1;
+ tracing_selftest_disabled = 1;
+
+ return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
+static __init int event_trace_init(void)
+{
+ struct ftrace_event_call *call;
+ struct dentry *d_tracer;
+ struct dentry *entry;
+ struct dentry *d_events;
+ int ret;
+ char *buf = bootup_event_buf;
+ char *token;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ entry = debugfs_create_file("available_events", 0444, d_tracer,
+ (void *)&show_event_seq_ops,
+ &ftrace_avail_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'available_events' entry\n");
+
+ entry = debugfs_create_file("set_event", 0644, d_tracer,
+ (void *)&show_set_event_seq_ops,
+ &ftrace_set_event_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'set_event' entry\n");
+
+ d_events = event_trace_events_dir();
+ if (!d_events)
+ return 0;
+
+ /* ring buffer internal formats */
+ trace_create_file("header_page", 0444, d_events,
+ ring_buffer_print_page_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("header_event", 0444, d_events,
+ ring_buffer_print_entry_header,
+ &ftrace_show_header_fops);
+
+ trace_create_file("enable", 0644, d_events,
+ NULL, &ftrace_system_enable_fops);
+
+ for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
+ /* The linker may leave blanks */
+ if (!call->name)
+ continue;
+ if (call->raw_init) {
+ ret = call->raw_init(call);
+ if (ret < 0) {
+ if (ret != -ENOSYS)
+ pr_warning("Could not initialize trace "
+ "point events/%s\n", call->name);
+ continue;
+ }
+ }
+ ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+ &ftrace_enable_fops,
+ &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ if (!ret)
+ list_add(&call->list, &ftrace_events);
+ }
+
+ while (true) {
+ token = strsep(&buf, ",");
+
+ if (!token)
+ break;
+ if (!*token)
+ continue;
+
+ ret = ftrace_set_clr_event(token, 1);
+ if (ret)
+ pr_warning("Failed to enable trace event: %s\n", token);
+ }
+
+ ret = register_module_notifier(&trace_module_nb);
+ if (ret)
+ pr_warning("Failed to register trace events module notifier\n");
+
+ return 0;
+}
+fs_initcall(event_trace_init);
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static DEFINE_SPINLOCK(test_spinlock);
+static DEFINE_SPINLOCK(test_spinlock_irq);
+static DEFINE_MUTEX(test_mutex);
+
+static __init void test_work(struct work_struct *dummy)
+{
+ spin_lock(&test_spinlock);
+ spin_lock_irq(&test_spinlock_irq);
+ udelay(1);
+ spin_unlock_irq(&test_spinlock_irq);
+ spin_unlock(&test_spinlock);
+
+ mutex_lock(&test_mutex);
+ msleep(1);
+ mutex_unlock(&test_mutex);
+}
+
+static __init int event_test_thread(void *unused)
+{
+ void *test_malloc;
+
+ test_malloc = kmalloc(1234, GFP_KERNEL);
+ if (!test_malloc)
+ pr_info("failed to kmalloc\n");
+
+ schedule_on_each_cpu(test_work);
+
+ kfree(test_malloc);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop())
+ schedule();
+
+ return 0;
+}
+
+/*
+ * Do various things that may trigger events.
+ */
+static __init void event_test_stuff(void)
+{
+ struct task_struct *test_thread;
+
+ test_thread = kthread_run(event_test_thread, NULL, "test-events");
+ msleep(1);
+ kthread_stop(test_thread);
+}
+
+/*
+ * For every trace event defined, we will test each trace point separately,
+ * and then by groups, and finally all trace points.
+ */
+static __init void event_trace_self_tests(void)
+{
+ struct ftrace_event_call *call;
+ struct event_subsystem *system;
+ int ret;
+
+ pr_info("Running tests on trace events:\n");
+
+ list_for_each_entry(call, &ftrace_events, list) {
+
+ /* Only test those that have a regfunc */
+ if (!call->regfunc)
+ continue;
+
+/*
+ * Testing syscall events here is pretty useless, but
+ * we still do it if configured. But this is time consuming.
+ * What we really need is a user thread to perform the
+ * syscalls as we test.
+ */
+#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
+ if (call->system &&
+ strcmp(call->system, "syscalls") == 0)
+ continue;
+#endif
+
+ pr_info("Testing event %s: ", call->name);
+
+ /*
+ * If an event is already enabled, someone is using
+ * it and the self test should not be on.
+ */
+ if (call->enabled) {
+ pr_warning("Enabled event during self test!\n");
+ WARN_ON_ONCE(1);
+ continue;
+ }
+
+ ftrace_event_enable_disable(call, 1);
+ event_test_stuff();
+ ftrace_event_enable_disable(call, 0);
+
+ pr_cont("OK\n");
+ }
+
+ /* Now test at the sub system level */
+
+ pr_info("Running tests on trace event systems:\n");
+
+ list_for_each_entry(system, &event_subsystems, list) {
+
+ /* the ftrace system is special, skip it */
+ if (strcmp(system->name, "ftrace") == 0)
+ continue;
+
+ pr_info("Testing event system %s: ", system->name);
+
+ ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error enabling system %s\n",
+ system->name);
+ continue;
+ }
+
+ event_test_stuff();
+
+ ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error disabling system %s\n",
+ system->name);
+
+ pr_cont("OK\n");
+ }
+
+ /* Test with all events enabled */
+
+ pr_info("Running tests on all trace events:\n");
+ pr_info("Testing all events: ");
+
+ ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error enabling all events\n");
+ return;
+ }
+
+ event_test_stuff();
+
+ /* reset sysname */
+ ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error disabling all events\n");
+ return;
+ }
+
+ pr_cont("OK\n");
+}
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
+
+static void
+function_test_events_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct ftrace_entry *entry;
+ unsigned long flags;
+ long disabled;
+ int resched;
+ int cpu;
+ int pc;
+
+ pc = preempt_count();
+ resched = ftrace_preempt_disable();
+ cpu = raw_smp_processor_id();
+ disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
+
+ if (disabled != 1)
+ goto out;
+
+ local_save_flags(flags);
+
+ event = trace_current_buffer_lock_reserve(&buffer,
+ TRACE_FN, sizeof(*entry),
+ flags, pc);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ entry->ip = ip;
+ entry->parent_ip = parent_ip;
+
+ trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
+
+ out:
+ atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
+ ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __initdata =
+{
+ .func = function_test_events_call,
+};
+
+static __init void event_trace_self_test_with_function(void)
+{
+ register_ftrace_function(&trace_ops);
+ pr_info("Running tests again, along with the function tracer\n");
+ event_trace_self_tests();
+ unregister_ftrace_function(&trace_ops);
+}
+#else
+static __init void event_trace_self_test_with_function(void)
+{
+}
+#endif
+
+static __init int event_trace_self_tests_init(void)
+{
+ if (!tracing_selftest_disabled) {
+ event_trace_self_tests();
+ event_trace_self_test_with_function();
+ }
+
+ return 0;
+}
+
+late_initcall(event_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
new file mode 100644
index 00000000000..e42af9aad69
--- /dev/null
+++ b/kernel/trace/trace_events_filter.c
@@ -0,0 +1,1443 @@
+/*
+ * trace_events_filter - generic event filtering
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/perf_event.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+enum filter_op_ids
+{
+ OP_OR,
+ OP_AND,
+ OP_GLOB,
+ OP_NE,
+ OP_EQ,
+ OP_LT,
+ OP_LE,
+ OP_GT,
+ OP_GE,
+ OP_NONE,
+ OP_OPEN_PAREN,
+};
+
+struct filter_op {
+ int id;
+ char *string;
+ int precedence;
+};
+
+static struct filter_op filter_ops[] = {
+ { OP_OR, "||", 1 },
+ { OP_AND, "&&", 2 },
+ { OP_GLOB, "~", 4 },
+ { OP_NE, "!=", 4 },
+ { OP_EQ, "==", 4 },
+ { OP_LT, "<", 5 },
+ { OP_LE, "<=", 5 },
+ { OP_GT, ">", 5 },
+ { OP_GE, ">=", 5 },
+ { OP_NONE, "OP_NONE", 0 },
+ { OP_OPEN_PAREN, "(", 0 },
+};
+
+enum {
+ FILT_ERR_NONE,
+ FILT_ERR_INVALID_OP,
+ FILT_ERR_UNBALANCED_PAREN,
+ FILT_ERR_TOO_MANY_OPERANDS,
+ FILT_ERR_OPERAND_TOO_LONG,
+ FILT_ERR_FIELD_NOT_FOUND,
+ FILT_ERR_ILLEGAL_FIELD_OP,
+ FILT_ERR_ILLEGAL_INTVAL,
+ FILT_ERR_BAD_SUBSYS_FILTER,
+ FILT_ERR_TOO_MANY_PREDS,
+ FILT_ERR_MISSING_FIELD,
+ FILT_ERR_INVALID_FILTER,
+};
+
+static char *err_text[] = {
+ "No error",
+ "Invalid operator",
+ "Unbalanced parens",
+ "Too many operands",
+ "Operand too long",
+ "Field not found",
+ "Illegal operation for field type",
+ "Illegal integer value",
+ "Couldn't find or set field in one of a subsystem's events",
+ "Too many terms in predicate expression",
+ "Missing field name and/or value",
+ "Meaningless filter expression",
+};
+
+struct opstack_op {
+ int op;
+ struct list_head list;
+};
+
+struct postfix_elt {
+ int op;
+ char *operand;
+ struct list_head list;
+};
+
+struct filter_parse_state {
+ struct filter_op *ops;
+ struct list_head opstack;
+ struct list_head postfix;
+ int lasterr;
+ int lasterr_pos;
+
+ struct {
+ char *string;
+ unsigned int cnt;
+ unsigned int tail;
+ } infix;
+
+ struct {
+ char string[MAX_FILTER_STR_VAL];
+ int pos;
+ unsigned int tail;
+ } operand;
+};
+
+#define DEFINE_COMPARISON_PRED(type) \
+static int filter_pred_##type(struct filter_pred *pred, void *event, \
+ int val1, int val2) \
+{ \
+ type *addr = (type *)(event + pred->offset); \
+ type val = (type)pred->val; \
+ int match = 0; \
+ \
+ switch (pred->op) { \
+ case OP_LT: \
+ match = (*addr < val); \
+ break; \
+ case OP_LE: \
+ match = (*addr <= val); \
+ break; \
+ case OP_GT: \
+ match = (*addr > val); \
+ break; \
+ case OP_GE: \
+ match = (*addr >= val); \
+ break; \
+ default: \
+ break; \
+ } \
+ \
+ return match; \
+}
+
+#define DEFINE_EQUALITY_PRED(size) \
+static int filter_pred_##size(struct filter_pred *pred, void *event, \
+ int val1, int val2) \
+{ \
+ u##size *addr = (u##size *)(event + pred->offset); \
+ u##size val = (u##size)pred->val; \
+ int match; \
+ \
+ match = (val == *addr) ^ pred->not; \
+ \
+ return match; \
+}
+
+DEFINE_COMPARISON_PRED(s64);
+DEFINE_COMPARISON_PRED(u64);
+DEFINE_COMPARISON_PRED(s32);
+DEFINE_COMPARISON_PRED(u32);
+DEFINE_COMPARISON_PRED(s16);
+DEFINE_COMPARISON_PRED(u16);
+DEFINE_COMPARISON_PRED(s8);
+DEFINE_COMPARISON_PRED(u8);
+
+DEFINE_EQUALITY_PRED(64);
+DEFINE_EQUALITY_PRED(32);
+DEFINE_EQUALITY_PRED(16);
+DEFINE_EQUALITY_PRED(8);
+
+static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
+ void *event __attribute((unused)),
+ int val1, int val2)
+{
+ return val1 && val2;
+}
+
+static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
+ void *event __attribute((unused)),
+ int val1, int val2)
+{
+ return val1 || val2;
+}
+
+/* Filter predicate for fixed sized arrays of characters */
+static int filter_pred_string(struct filter_pred *pred, void *event,
+ int val1, int val2)
+{
+ char *addr = (char *)(event + pred->offset);
+ int cmp, match;
+
+ cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
+
+ match = cmp ^ pred->not;
+
+ return match;
+}
+
+/* Filter predicate for char * pointers */
+static int filter_pred_pchar(struct filter_pred *pred, void *event,
+ int val1, int val2)
+{
+ char **addr = (char **)(event + pred->offset);
+ int cmp, match;
+ int len = strlen(*addr) + 1; /* including tailing '\0' */
+
+ cmp = pred->regex.match(*addr, &pred->regex, len);
+
+ match = cmp ^ pred->not;
+
+ return match;
+}
+
+/*
+ * Filter predicate for dynamic sized arrays of characters.
+ * These are implemented through a list of strings at the end
+ * of the entry.
+ * Also each of these strings have a field in the entry which
+ * contains its offset from the beginning of the entry.
+ * We have then first to get this field, dereference it
+ * and add it to the address of the entry, and at last we have
+ * the address of the string.
+ */
+static int filter_pred_strloc(struct filter_pred *pred, void *event,
+ int val1, int val2)
+{
+ u32 str_item = *(u32 *)(event + pred->offset);
+ int str_loc = str_item & 0xffff;
+ int str_len = str_item >> 16;
+ char *addr = (char *)(event + str_loc);
+ int cmp, match;
+
+ cmp = pred->regex.match(addr, &pred->regex, str_len);
+
+ match = cmp ^ pred->not;
+
+ return match;
+}
+
+static int filter_pred_none(struct filter_pred *pred, void *event,
+ int val1, int val2)
+{
+ return 0;
+}
+
+/*
+ * regex_match_foo - Basic regex callbacks
+ *
+ * @str: the string to be searched
+ * @r: the regex structure containing the pattern string
+ * @len: the length of the string to be searched (including '\0')
+ *
+ * Note:
+ * - @str might not be NULL-terminated if it's of type DYN_STRING
+ * or STATIC_STRING
+ */
+
+static int regex_match_full(char *str, struct regex *r, int len)
+{
+ if (strncmp(str, r->pattern, len) == 0)
+ return 1;
+ return 0;
+}
+
+static int regex_match_front(char *str, struct regex *r, int len)
+{
+ if (strncmp(str, r->pattern, r->len) == 0)
+ return 1;
+ return 0;
+}
+
+static int regex_match_middle(char *str, struct regex *r, int len)
+{
+ if (strnstr(str, r->pattern, len))
+ return 1;
+ return 0;
+}
+
+static int regex_match_end(char *str, struct regex *r, int len)
+{
+ int strlen = len - 1;
+
+ if (strlen >= r->len &&
+ memcmp(str + strlen - r->len, r->pattern, r->len) == 0)
+ return 1;
+ return 0;
+}
+
+/**
+ * filter_parse_regex - parse a basic regex
+ * @buff: the raw regex
+ * @len: length of the regex
+ * @search: will point to the beginning of the string to compare
+ * @not: tell whether the match will have to be inverted
+ *
+ * This passes in a buffer containing a regex and this function will
+ * set search to point to the search part of the buffer and
+ * return the type of search it is (see enum above).
+ * This does modify buff.
+ *
+ * Returns enum type.
+ * search returns the pointer to use for comparison.
+ * not returns 1 if buff started with a '!'
+ * 0 otherwise.
+ */
+enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
+{
+ int type = MATCH_FULL;
+ int i;
+
+ if (buff[0] == '!') {
+ *not = 1;
+ buff++;
+ len--;
+ } else
+ *not = 0;
+
+ *search = buff;
+
+ for (i = 0; i < len; i++) {
+ if (buff[i] == '*') {
+ if (!i) {
+ *search = buff + 1;
+ type = MATCH_END_ONLY;
+ } else {
+ if (type == MATCH_END_ONLY)
+ type = MATCH_MIDDLE_ONLY;
+ else
+ type = MATCH_FRONT_ONLY;
+ buff[i] = 0;
+ break;
+ }
+ }
+ }
+
+ return type;
+}
+
+static void filter_build_regex(struct filter_pred *pred)
+{
+ struct regex *r = &pred->regex;
+ char *search;
+ enum regex_type type = MATCH_FULL;
+ int not = 0;
+
+ if (pred->op == OP_GLOB) {
+ type = filter_parse_regex(r->pattern, r->len, &search, &not);
+ r->len = strlen(search);
+ memmove(r->pattern, search, r->len+1);
+ }
+
+ switch (type) {
+ case MATCH_FULL:
+ r->match = regex_match_full;
+ break;
+ case MATCH_FRONT_ONLY:
+ r->match = regex_match_front;
+ break;
+ case MATCH_MIDDLE_ONLY:
+ r->match = regex_match_middle;
+ break;
+ case MATCH_END_ONLY:
+ r->match = regex_match_end;
+ break;
+ }
+
+ pred->not ^= not;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct event_filter *filter, void *rec)
+{
+ int match, top = 0, val1 = 0, val2 = 0;
+ int stack[MAX_FILTER_PRED];
+ struct filter_pred *pred;
+ int i;
+
+ for (i = 0; i < filter->n_preds; i++) {
+ pred = filter->preds[i];
+ if (!pred->pop_n) {
+ match = pred->fn(pred, rec, val1, val2);
+ stack[top++] = match;
+ continue;
+ }
+ if (pred->pop_n > top) {
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+ val1 = stack[--top];
+ val2 = stack[--top];
+ match = pred->fn(pred, rec, val1, val2);
+ stack[top++] = match;
+ }
+
+ return stack[--top];
+}
+EXPORT_SYMBOL_GPL(filter_match_preds);
+
+static void parse_error(struct filter_parse_state *ps, int err, int pos)
+{
+ ps->lasterr = err;
+ ps->lasterr_pos = pos;
+}
+
+static void remove_filter_string(struct event_filter *filter)
+{
+ kfree(filter->filter_string);
+ filter->filter_string = NULL;
+}
+
+static int replace_filter_string(struct event_filter *filter,
+ char *filter_string)
+{
+ kfree(filter->filter_string);
+ filter->filter_string = kstrdup(filter_string, GFP_KERNEL);
+ if (!filter->filter_string)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int append_filter_string(struct event_filter *filter,
+ char *string)
+{
+ int newlen;
+ char *new_filter_string;
+
+ BUG_ON(!filter->filter_string);
+ newlen = strlen(filter->filter_string) + strlen(string) + 1;
+ new_filter_string = kmalloc(newlen, GFP_KERNEL);
+ if (!new_filter_string)
+ return -ENOMEM;
+
+ strcpy(new_filter_string, filter->filter_string);
+ strcat(new_filter_string, string);
+ kfree(filter->filter_string);
+ filter->filter_string = new_filter_string;
+
+ return 0;
+}
+
+static void append_filter_err(struct filter_parse_state *ps,
+ struct event_filter *filter)
+{
+ int pos = ps->lasterr_pos;
+ char *buf, *pbuf;
+
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return;
+
+ append_filter_string(filter, "\n");
+ memset(buf, ' ', PAGE_SIZE);
+ if (pos > PAGE_SIZE - 128)
+ pos = 0;
+ buf[pos] = '^';
+ pbuf = &buf[pos] + 1;
+
+ sprintf(pbuf, "\nparse_error: %s\n", err_text[ps->lasterr]);
+ append_filter_string(filter, buf);
+ free_page((unsigned long) buf);
+}
+
+void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
+{
+ struct event_filter *filter = call->filter;
+
+ mutex_lock(&event_mutex);
+ if (filter && filter->filter_string)
+ trace_seq_printf(s, "%s\n", filter->filter_string);
+ else
+ trace_seq_printf(s, "none\n");
+ mutex_unlock(&event_mutex);
+}
+
+void print_subsystem_event_filter(struct event_subsystem *system,
+ struct trace_seq *s)
+{
+ struct event_filter *filter = system->filter;
+
+ mutex_lock(&event_mutex);
+ if (filter && filter->filter_string)
+ trace_seq_printf(s, "%s\n", filter->filter_string);
+ else
+ trace_seq_printf(s, "none\n");
+ mutex_unlock(&event_mutex);
+}
+
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+ struct ftrace_event_field *field;
+
+ list_for_each_entry(field, &call->fields, link) {
+ if (!strcmp(field->name, name))
+ return field;
+ }
+
+ return NULL;
+}
+
+static void filter_free_pred(struct filter_pred *pred)
+{
+ if (!pred)
+ return;
+
+ kfree(pred->field_name);
+ kfree(pred);
+}
+
+static void filter_clear_pred(struct filter_pred *pred)
+{
+ kfree(pred->field_name);
+ pred->field_name = NULL;
+ pred->regex.len = 0;
+}
+
+static int filter_set_pred(struct filter_pred *dest,
+ struct filter_pred *src,
+ filter_pred_fn_t fn)
+{
+ *dest = *src;
+ if (src->field_name) {
+ dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
+ if (!dest->field_name)
+ return -ENOMEM;
+ }
+ dest->fn = fn;
+
+ return 0;
+}
+
+static void filter_disable_preds(struct ftrace_event_call *call)
+{
+ struct event_filter *filter = call->filter;
+ int i;
+
+ call->filter_active = 0;
+ filter->n_preds = 0;
+
+ for (i = 0; i < MAX_FILTER_PRED; i++)
+ filter->preds[i]->fn = filter_pred_none;
+}
+
+static void __free_preds(struct event_filter *filter)
+{
+ int i;
+
+ if (!filter)
+ return;
+
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ if (filter->preds[i])
+ filter_free_pred(filter->preds[i]);
+ }
+ kfree(filter->preds);
+ kfree(filter->filter_string);
+ kfree(filter);
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+ __free_preds(call->filter);
+ call->filter = NULL;
+ call->filter_active = 0;
+}
+
+static struct event_filter *__alloc_preds(void)
+{
+ struct event_filter *filter;
+ struct filter_pred *pred;
+ int i;
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return ERR_PTR(-ENOMEM);
+
+ filter->n_preds = 0;
+
+ filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
+ if (!filter->preds)
+ goto oom;
+
+ for (i = 0; i < MAX_FILTER_PRED; i++) {
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ goto oom;
+ pred->fn = filter_pred_none;
+ filter->preds[i] = pred;
+ }
+
+ return filter;
+
+oom:
+ __free_preds(filter);
+ return ERR_PTR(-ENOMEM);
+}
+
+static int init_preds(struct ftrace_event_call *call)
+{
+ if (call->filter)
+ return 0;
+
+ call->filter_active = 0;
+ call->filter = __alloc_preds();
+ if (IS_ERR(call->filter))
+ return PTR_ERR(call->filter);
+
+ return 0;
+}
+
+static int init_subsystem_preds(struct event_subsystem *system)
+{
+ struct ftrace_event_call *call;
+ int err;
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->define_fields)
+ continue;
+
+ if (strcmp(call->system, system->name) != 0)
+ continue;
+
+ err = init_preds(call);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+ struct ftrace_event_call *call;
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (!call->define_fields)
+ continue;
+
+ if (strcmp(call->system, system->name) != 0)
+ continue;
+
+ filter_disable_preds(call);
+ remove_filter_string(call->filter);
+ }
+}
+
+static int filter_add_pred_fn(struct filter_parse_state *ps,
+ struct ftrace_event_call *call,
+ struct event_filter *filter,
+ struct filter_pred *pred,
+ filter_pred_fn_t fn)
+{
+ int idx, err;
+
+ if (filter->n_preds == MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
+ }
+
+ idx = filter->n_preds;
+ filter_clear_pred(filter->preds[idx]);
+ err = filter_set_pred(filter->preds[idx], pred, fn);
+ if (err)
+ return err;
+
+ filter->n_preds++;
+
+ return 0;
+}
+
+int filter_assign_type(const char *type)
+{
+ if (strstr(type, "__data_loc") && strstr(type, "char"))
+ return FILTER_DYN_STRING;
+
+ if (strchr(type, '[') && strstr(type, "char"))
+ return FILTER_STATIC_STRING;
+
+ return FILTER_OTHER;
+}
+
+static bool is_string_field(struct ftrace_event_field *field)
+{
+ return field->filter_type == FILTER_DYN_STRING ||
+ field->filter_type == FILTER_STATIC_STRING ||
+ field->filter_type == FILTER_PTR_STRING;
+}
+
+static int is_legal_op(struct ftrace_event_field *field, int op)
+{
+ if (is_string_field(field) &&
+ (op != OP_EQ && op != OP_NE && op != OP_GLOB))
+ return 0;
+ if (!is_string_field(field) && op == OP_GLOB)
+ return 0;
+
+ return 1;
+}
+
+static filter_pred_fn_t select_comparison_fn(int op, int field_size,
+ int field_is_signed)
+{
+ filter_pred_fn_t fn = NULL;
+
+ switch (field_size) {
+ case 8:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_64;
+ else if (field_is_signed)
+ fn = filter_pred_s64;
+ else
+ fn = filter_pred_u64;
+ break;
+ case 4:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_32;
+ else if (field_is_signed)
+ fn = filter_pred_s32;
+ else
+ fn = filter_pred_u32;
+ break;
+ case 2:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_16;
+ else if (field_is_signed)
+ fn = filter_pred_s16;
+ else
+ fn = filter_pred_u16;
+ break;
+ case 1:
+ if (op == OP_EQ || op == OP_NE)
+ fn = filter_pred_8;
+ else if (field_is_signed)
+ fn = filter_pred_s8;
+ else
+ fn = filter_pred_u8;
+ break;
+ }
+
+ return fn;
+}
+
+static int filter_add_pred(struct filter_parse_state *ps,
+ struct ftrace_event_call *call,
+ struct event_filter *filter,
+ struct filter_pred *pred,
+ bool dry_run)
+{
+ struct ftrace_event_field *field;
+ filter_pred_fn_t fn;
+ unsigned long long val;
+ int ret;
+
+ pred->fn = filter_pred_none;
+
+ if (pred->op == OP_AND) {
+ pred->pop_n = 2;
+ fn = filter_pred_and;
+ goto add_pred_fn;
+ } else if (pred->op == OP_OR) {
+ pred->pop_n = 2;
+ fn = filter_pred_or;
+ goto add_pred_fn;
+ }
+
+ field = find_event_field(call, pred->field_name);
+ if (!field) {
+ parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
+ return -EINVAL;
+ }
+
+ pred->offset = field->offset;
+
+ if (!is_legal_op(field, pred->op)) {
+ parse_error(ps, FILT_ERR_ILLEGAL_FIELD_OP, 0);
+ return -EINVAL;
+ }
+
+ if (is_string_field(field)) {
+ filter_build_regex(pred);
+
+ if (field->filter_type == FILTER_STATIC_STRING) {
+ fn = filter_pred_string;
+ pred->regex.field_len = field->size;
+ } else if (field->filter_type == FILTER_DYN_STRING)
+ fn = filter_pred_strloc;
+ else
+ fn = filter_pred_pchar;
+ } else {
+ if (field->is_signed)
+ ret = strict_strtoll(pred->regex.pattern, 0, &val);
+ else
+ ret = strict_strtoull(pred->regex.pattern, 0, &val);
+ if (ret) {
+ parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
+ return -EINVAL;
+ }
+ pred->val = val;
+
+ fn = select_comparison_fn(pred->op, field->size,
+ field->is_signed);
+ if (!fn) {
+ parse_error(ps, FILT_ERR_INVALID_OP, 0);
+ return -EINVAL;
+ }
+ }
+
+ if (pred->op == OP_NE)
+ pred->not = 1;
+
+add_pred_fn:
+ if (!dry_run)
+ return filter_add_pred_fn(ps, call, filter, pred, fn);
+ return 0;
+}
+
+static void parse_init(struct filter_parse_state *ps,
+ struct filter_op *ops,
+ char *infix_string)
+{
+ memset(ps, '\0', sizeof(*ps));
+
+ ps->infix.string = infix_string;
+ ps->infix.cnt = strlen(infix_string);
+ ps->ops = ops;
+
+ INIT_LIST_HEAD(&ps->opstack);
+ INIT_LIST_HEAD(&ps->postfix);
+}
+
+static char infix_next(struct filter_parse_state *ps)
+{
+ ps->infix.cnt--;
+
+ return ps->infix.string[ps->infix.tail++];
+}
+
+static char infix_peek(struct filter_parse_state *ps)
+{
+ if (ps->infix.tail == strlen(ps->infix.string))
+ return 0;
+
+ return ps->infix.string[ps->infix.tail];
+}
+
+static void infix_advance(struct filter_parse_state *ps)
+{
+ ps->infix.cnt--;
+ ps->infix.tail++;
+}
+
+static inline int is_precedence_lower(struct filter_parse_state *ps,
+ int a, int b)
+{
+ return ps->ops[a].precedence < ps->ops[b].precedence;
+}
+
+static inline int is_op_char(struct filter_parse_state *ps, char c)
+{
+ int i;
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (ps->ops[i].string[0] == c)
+ return 1;
+ }
+
+ return 0;
+}
+
+static int infix_get_op(struct filter_parse_state *ps, char firstc)
+{
+ char nextc = infix_peek(ps);
+ char opstr[3];
+ int i;
+
+ opstr[0] = firstc;
+ opstr[1] = nextc;
+ opstr[2] = '\0';
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (!strcmp(opstr, ps->ops[i].string)) {
+ infix_advance(ps);
+ return ps->ops[i].id;
+ }
+ }
+
+ opstr[1] = '\0';
+
+ for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+ if (!strcmp(opstr, ps->ops[i].string))
+ return ps->ops[i].id;
+ }
+
+ return OP_NONE;
+}
+
+static inline void clear_operand_string(struct filter_parse_state *ps)
+{
+ memset(ps->operand.string, '\0', MAX_FILTER_STR_VAL);
+ ps->operand.tail = 0;
+}
+
+static inline int append_operand_char(struct filter_parse_state *ps, char c)
+{
+ if (ps->operand.tail == MAX_FILTER_STR_VAL - 1)
+ return -EINVAL;
+
+ ps->operand.string[ps->operand.tail++] = c;
+
+ return 0;
+}
+
+static int filter_opstack_push(struct filter_parse_state *ps, int op)
+{
+ struct opstack_op *opstack_op;
+
+ opstack_op = kmalloc(sizeof(*opstack_op), GFP_KERNEL);
+ if (!opstack_op)
+ return -ENOMEM;
+
+ opstack_op->op = op;
+ list_add(&opstack_op->list, &ps->opstack);
+
+ return 0;
+}
+
+static int filter_opstack_empty(struct filter_parse_state *ps)
+{
+ return list_empty(&ps->opstack);
+}
+
+static int filter_opstack_top(struct filter_parse_state *ps)
+{
+ struct opstack_op *opstack_op;
+
+ if (filter_opstack_empty(ps))
+ return OP_NONE;
+
+ opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+
+ return opstack_op->op;
+}
+
+static int filter_opstack_pop(struct filter_parse_state *ps)
+{
+ struct opstack_op *opstack_op;
+ int op;
+
+ if (filter_opstack_empty(ps))
+ return OP_NONE;
+
+ opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+ op = opstack_op->op;
+ list_del(&opstack_op->list);
+
+ kfree(opstack_op);
+
+ return op;
+}
+
+static void filter_opstack_clear(struct filter_parse_state *ps)
+{
+ while (!filter_opstack_empty(ps))
+ filter_opstack_pop(ps);
+}
+
+static char *curr_operand(struct filter_parse_state *ps)
+{
+ return ps->operand.string;
+}
+
+static int postfix_append_operand(struct filter_parse_state *ps, char *operand)
+{
+ struct postfix_elt *elt;
+
+ elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+ if (!elt)
+ return -ENOMEM;
+
+ elt->op = OP_NONE;
+ elt->operand = kstrdup(operand, GFP_KERNEL);
+ if (!elt->operand) {
+ kfree(elt);
+ return -ENOMEM;
+ }
+
+ list_add_tail(&elt->list, &ps->postfix);
+
+ return 0;
+}
+
+static int postfix_append_op(struct filter_parse_state *ps, int op)
+{
+ struct postfix_elt *elt;
+
+ elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+ if (!elt)
+ return -ENOMEM;
+
+ elt->op = op;
+ elt->operand = NULL;
+
+ list_add_tail(&elt->list, &ps->postfix);
+
+ return 0;
+}
+
+static void postfix_clear(struct filter_parse_state *ps)
+{
+ struct postfix_elt *elt;
+
+ while (!list_empty(&ps->postfix)) {
+ elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
+ list_del(&elt->list);
+ kfree(elt->operand);
+ kfree(elt);
+ }
+}
+
+static int filter_parse(struct filter_parse_state *ps)
+{
+ int in_string = 0;
+ int op, top_op;
+ char ch;
+
+ while ((ch = infix_next(ps))) {
+ if (ch == '"') {
+ in_string ^= 1;
+ continue;
+ }
+
+ if (in_string)
+ goto parse_operand;
+
+ if (isspace(ch))
+ continue;
+
+ if (is_op_char(ps, ch)) {
+ op = infix_get_op(ps, ch);
+ if (op == OP_NONE) {
+ parse_error(ps, FILT_ERR_INVALID_OP, 0);
+ return -EINVAL;
+ }
+
+ if (strlen(curr_operand(ps))) {
+ postfix_append_operand(ps, curr_operand(ps));
+ clear_operand_string(ps);
+ }
+
+ while (!filter_opstack_empty(ps)) {
+ top_op = filter_opstack_top(ps);
+ if (!is_precedence_lower(ps, top_op, op)) {
+ top_op = filter_opstack_pop(ps);
+ postfix_append_op(ps, top_op);
+ continue;
+ }
+ break;
+ }
+
+ filter_opstack_push(ps, op);
+ continue;
+ }
+
+ if (ch == '(') {
+ filter_opstack_push(ps, OP_OPEN_PAREN);
+ continue;
+ }
+
+ if (ch == ')') {
+ if (strlen(curr_operand(ps))) {
+ postfix_append_operand(ps, curr_operand(ps));
+ clear_operand_string(ps);
+ }
+
+ top_op = filter_opstack_pop(ps);
+ while (top_op != OP_NONE) {
+ if (top_op == OP_OPEN_PAREN)
+ break;
+ postfix_append_op(ps, top_op);
+ top_op = filter_opstack_pop(ps);
+ }
+ if (top_op == OP_NONE) {
+ parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+ return -EINVAL;
+ }
+ continue;
+ }
+parse_operand:
+ if (append_operand_char(ps, ch)) {
+ parse_error(ps, FILT_ERR_OPERAND_TOO_LONG, 0);
+ return -EINVAL;
+ }
+ }
+
+ if (strlen(curr_operand(ps)))
+ postfix_append_operand(ps, curr_operand(ps));
+
+ while (!filter_opstack_empty(ps)) {
+ top_op = filter_opstack_pop(ps);
+ if (top_op == OP_NONE)
+ break;
+ if (top_op == OP_OPEN_PAREN) {
+ parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+ return -EINVAL;
+ }
+ postfix_append_op(ps, top_op);
+ }
+
+ return 0;
+}
+
+static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+{
+ struct filter_pred *pred;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return NULL;
+
+ pred->field_name = kstrdup(operand1, GFP_KERNEL);
+ if (!pred->field_name) {
+ kfree(pred);
+ return NULL;
+ }
+
+ strcpy(pred->regex.pattern, operand2);
+ pred->regex.len = strlen(pred->regex.pattern);
+
+ pred->op = op;
+
+ return pred;
+}
+
+static struct filter_pred *create_logical_pred(int op)
+{
+ struct filter_pred *pred;
+
+ pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+ if (!pred)
+ return NULL;
+
+ pred->op = op;
+
+ return pred;
+}
+
+static int check_preds(struct filter_parse_state *ps)
+{
+ int n_normal_preds = 0, n_logical_preds = 0;
+ struct postfix_elt *elt;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE)
+ continue;
+
+ if (elt->op == OP_AND || elt->op == OP_OR) {
+ n_logical_preds++;
+ continue;
+ }
+ n_normal_preds++;
+ }
+
+ if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+ parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int replace_preds(struct ftrace_event_call *call,
+ struct event_filter *filter,
+ struct filter_parse_state *ps,
+ char *filter_string,
+ bool dry_run)
+{
+ char *operand1 = NULL, *operand2 = NULL;
+ struct filter_pred *pred;
+ struct postfix_elt *elt;
+ int err;
+ int n_preds = 0;
+
+ err = check_preds(ps);
+ if (err)
+ return err;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE) {
+ if (!operand1)
+ operand1 = elt->operand;
+ else if (!operand2)
+ operand2 = elt->operand;
+ else {
+ parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
+ return -EINVAL;
+ }
+ continue;
+ }
+
+ if (n_preds++ == MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
+ }
+
+ if (elt->op == OP_AND || elt->op == OP_OR) {
+ pred = create_logical_pred(elt->op);
+ goto add_pred;
+ }
+
+ if (!operand1 || !operand2) {
+ parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
+ return -EINVAL;
+ }
+
+ pred = create_pred(elt->op, operand1, operand2);
+add_pred:
+ if (!pred)
+ return -ENOMEM;
+ err = filter_add_pred(ps, call, filter, pred, dry_run);
+ filter_free_pred(pred);
+ if (err)
+ return err;
+
+ operand1 = operand2 = NULL;
+ }
+
+ return 0;
+}
+
+static int replace_system_preds(struct event_subsystem *system,
+ struct filter_parse_state *ps,
+ char *filter_string)
+{
+ struct ftrace_event_call *call;
+ bool fail = true;
+ int err;
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ struct event_filter *filter = call->filter;
+
+ if (!call->define_fields)
+ continue;
+
+ if (strcmp(call->system, system->name) != 0)
+ continue;
+
+ /* try to see if the filter can be applied */
+ err = replace_preds(call, filter, ps, filter_string, true);
+ if (err)
+ continue;
+
+ /* really apply the filter */
+ filter_disable_preds(call);
+ err = replace_preds(call, filter, ps, filter_string, false);
+ if (err)
+ filter_disable_preds(call);
+ else {
+ call->filter_active = 1;
+ replace_filter_string(filter, filter_string);
+ }
+ fail = false;
+ }
+
+ if (fail) {
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+ int err;
+ struct filter_parse_state *ps;
+
+ mutex_lock(&event_mutex);
+
+ err = init_preds(call);
+ if (err)
+ goto out_unlock;
+
+ if (!strcmp(strstrip(filter_string), "0")) {
+ filter_disable_preds(call);
+ remove_filter_string(call->filter);
+ goto out_unlock;
+ }
+
+ err = -ENOMEM;
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ goto out_unlock;
+
+ filter_disable_preds(call);
+ replace_filter_string(call->filter, filter_string);
+
+ parse_init(ps, filter_ops, filter_string);
+ err = filter_parse(ps);
+ if (err) {
+ append_filter_err(ps, call->filter);
+ goto out;
+ }
+
+ err = replace_preds(call, call->filter, ps, filter_string, false);
+ if (err)
+ append_filter_err(ps, call->filter);
+ else
+ call->filter_active = 1;
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+out_unlock:
+ mutex_unlock(&event_mutex);
+
+ return err;
+}
+
+int apply_subsystem_event_filter(struct event_subsystem *system,
+ char *filter_string)
+{
+ int err;
+ struct filter_parse_state *ps;
+
+ mutex_lock(&event_mutex);
+
+ err = init_subsystem_preds(system);
+ if (err)
+ goto out_unlock;
+
+ if (!strcmp(strstrip(filter_string), "0")) {
+ filter_free_subsystem_preds(system);
+ remove_filter_string(system->filter);
+ goto out_unlock;
+ }
+
+ err = -ENOMEM;
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ goto out_unlock;
+
+ replace_filter_string(system->filter, filter_string);
+
+ parse_init(ps, filter_ops, filter_string);
+ err = filter_parse(ps);
+ if (err) {
+ append_filter_err(ps, system->filter);
+ goto out;
+ }
+
+ err = replace_system_preds(system, ps, filter_string);
+ if (err)
+ append_filter_err(ps, system->filter);
+
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+out_unlock:
+ mutex_unlock(&event_mutex);
+
+ return err;
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+void ftrace_profile_free_filter(struct perf_event *event)
+{
+ struct event_filter *filter = event->filter;
+
+ event->filter = NULL;
+ __free_preds(filter);
+}
+
+int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+ char *filter_str)
+{
+ int err;
+ struct event_filter *filter;
+ struct filter_parse_state *ps;
+ struct ftrace_event_call *call = NULL;
+
+ mutex_lock(&event_mutex);
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (call->id == event_id)
+ break;
+ }
+
+ err = -EINVAL;
+ if (!call)
+ goto out_unlock;
+
+ err = -EEXIST;
+ if (event->filter)
+ goto out_unlock;
+
+ filter = __alloc_preds();
+ if (IS_ERR(filter)) {
+ err = PTR_ERR(filter);
+ goto out_unlock;
+ }
+
+ err = -ENOMEM;
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ goto free_preds;
+
+ parse_init(ps, filter_ops, filter_str);
+ err = filter_parse(ps);
+ if (err)
+ goto free_ps;
+
+ err = replace_preds(call, filter, ps, filter_str, false);
+ if (!err)
+ event->filter = filter;
+
+free_ps:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+
+free_preds:
+ if (err)
+ __free_preds(filter);
+
+out_unlock:
+ mutex_unlock(&event_mutex);
+
+ return err;
+}
+
+#endif /* CONFIG_EVENT_PROFILE */
+
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
new file mode 100644
index 00000000000..d4fa5dc1ee4
--- /dev/null
+++ b/kernel/trace/trace_export.c
@@ -0,0 +1,230 @@
+/*
+ * trace_export.c - export basic ftrace utilities to user space
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/stringify.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ftrace
+
+/* not needed for this file */
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field
+#define __field(type, item) type item;
+
+#undef __field_desc
+#define __field_desc(type, container, item) type item;
+
+#undef __array
+#define __array(type, item, size) type item[size];
+
+#undef __array_desc
+#define __array_desc(type, container, item, size) type item[size];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item) type item[];
+
+#undef F_STRUCT
+#define F_STRUCT(args...) args
+
+#undef F_printk
+#define F_printk(fmt, args...) fmt, args
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
+struct ____ftrace_##name { \
+ tstruct \
+}; \
+static void __always_unused ____ftrace_check_##name(void) \
+{ \
+ struct ____ftrace_##name *__entry = NULL; \
+ \
+ /* force compile-time check on F_printk() */ \
+ printk(print); \
+}
+
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
+ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+
+#include "trace_entries.h"
+
+
+#undef __field
+#define __field(type, item) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed_type(type)); \
+ if (!ret) \
+ return 0;
+
+#undef __field_desc
+#define __field_desc(type, container, item) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
+ offsetof(typeof(field), container.item), \
+ sizeof(field.container.item), \
+ is_signed_type(type)); \
+ if (!ret) \
+ return 0;
+
+#undef __array
+#define __array(type, item, len) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed_type(type)); \
+ if (!ret) \
+ return 0;
+
+#undef __array_desc
+#define __array_desc(type, container, item, len) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
+ offsetof(typeof(field), container.item), \
+ sizeof(field.container.item), \
+ is_signed_type(type)); \
+ if (!ret) \
+ return 0;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item) \
+ ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
+ "offset:%zu;\tsize:0;\tsigned:%u;\n", \
+ offsetof(typeof(field), item), \
+ is_signed_type(type)); \
+ if (!ret) \
+ return 0;
+
+#undef F_printk
+#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+
+#undef __entry
+#define __entry REC
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
+static int \
+ftrace_format_##name(struct ftrace_event_call *unused, \
+ struct trace_seq *s) \
+{ \
+ struct struct_name field __attribute__((unused)); \
+ int ret = 0; \
+ \
+ tstruct; \
+ \
+ trace_seq_printf(s, "\nprint fmt: " print); \
+ \
+ return ret; \
+}
+
+#include "trace_entries.h"
+
+#undef __field
+#define __field(type, item) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), \
+ is_signed_type(type), FILTER_OTHER); \
+ if (ret) \
+ return ret;
+
+#undef __field_desc
+#define __field_desc(type, container, item) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), \
+ container.item), \
+ sizeof(field.container.item), \
+ is_signed_type(type), FILTER_OTHER); \
+ if (ret) \
+ return ret;
+
+#undef __array
+#define __array(type, item, len) \
+ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
+ ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), \
+ is_signed_type(type), FILTER_OTHER); \
+ if (ret) \
+ return ret;
+
+#undef __array_desc
+#define __array_desc(type, container, item, len) \
+ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
+ ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ offsetof(typeof(field), \
+ container.item), \
+ sizeof(field.container.item), \
+ is_signed_type(type), FILTER_OTHER); \
+ if (ret) \
+ return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
+int \
+ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
+{ \
+ struct struct_name field; \
+ int ret; \
+ \
+ tstruct; \
+ \
+ return ret; \
+}
+
+#include "trace_entries.h"
+
+static int ftrace_raw_init_event(struct ftrace_event_call *call)
+{
+ INIT_LIST_HEAD(&call->fields);
+ return 0;
+}
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_desc
+#define __field_desc(type, container, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __array_desc
+#define __array_desc(type, container, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
+ \
+struct ftrace_event_call __used \
+__attribute__((__aligned__(4))) \
+__attribute__((section("_ftrace_events"))) event_##call = { \
+ .name = #call, \
+ .id = type, \
+ .system = __stringify(TRACE_SYSTEM), \
+ .raw_init = ftrace_raw_init_event, \
+ .show_format = ftrace_format_##call, \
+ .define_fields = ftrace_define_fields_##call, \
+}; \
+
+#include "trace_entries.h"
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
new file mode 100644
index 00000000000..b3f3776b0cd
--- /dev/null
+++ b/kernel/trace/trace_functions.c
@@ -0,0 +1,403 @@
+/*
+ * ring buffer based function tracer
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Based on code from the latency_tracer, that is:
+ *
+ * Copyright (C) 2004-2006 Ingo Molnar
+ * Copyright (C) 2004 William Lee Irwin III
+ */
+#include <linux/ring_buffer.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+/* function tracing enabled */
+static int ftrace_function_enabled;
+
+static struct trace_array *func_trace;
+
+static void tracing_start_function_trace(void);
+static void tracing_stop_function_trace(void);
+
+static int function_trace_init(struct trace_array *tr)
+{
+ func_trace = tr;
+ tr->cpu = get_cpu();
+ put_cpu();
+
+ tracing_start_cmdline_record();
+ tracing_start_function_trace();
+ return 0;
+}
+
+static void function_trace_reset(struct trace_array *tr)
+{
+ tracing_stop_function_trace();
+ tracing_stop_cmdline_record();
+}
+
+static void function_trace_start(struct trace_array *tr)
+{
+ tracing_reset_online_cpus(tr);
+}
+
+static void
+function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
+{
+ struct trace_array *tr = func_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu, resched;
+ int pc;
+
+ if (unlikely(!ftrace_function_enabled))
+ return;
+
+ pc = preempt_count();
+ resched = ftrace_preempt_disable();
+ local_save_flags(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1))
+ trace_function(tr, ip, parent_ip, flags, pc);
+
+ atomic_dec(&data->disabled);
+ ftrace_preempt_enable(resched);
+}
+
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct trace_array *tr = func_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ if (unlikely(!ftrace_function_enabled))
+ return;
+
+ /*
+ * Need to use raw, since this must be called before the
+ * recursive protection is performed.
+ */
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ trace_function(tr, ip, parent_ip, flags, pc);
+ }
+
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+
+static void
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct trace_array *tr = func_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ if (unlikely(!ftrace_function_enabled))
+ return;
+
+ /*
+ * Need to use raw, since this must be called before the
+ * recursive protection is performed.
+ */
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ trace_function(tr, ip, parent_ip, flags, pc);
+ /*
+ * skip over 5 funcs:
+ * __ftrace_trace_stack,
+ * __trace_stack,
+ * function_stack_trace_call
+ * ftrace_list_func
+ * ftrace_call
+ */
+ __trace_stack(tr, flags, 5, pc);
+ }
+
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+ .func = function_trace_call,
+};
+
+static struct ftrace_ops trace_stack_ops __read_mostly =
+{
+ .func = function_stack_trace_call,
+};
+
+/* Our two options */
+enum {
+ TRACE_FUNC_OPT_STACK = 0x1,
+};
+
+static struct tracer_opt func_opts[] = {
+#ifdef CONFIG_STACKTRACE
+ { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) },
+#endif
+ { } /* Always set a last empty entry */
+};
+
+static struct tracer_flags func_flags = {
+ .val = 0, /* By default: all flags disabled */
+ .opts = func_opts
+};
+
+static void tracing_start_function_trace(void)
+{
+ ftrace_function_enabled = 0;
+
+ if (trace_flags & TRACE_ITER_PREEMPTONLY)
+ trace_ops.func = function_trace_call_preempt_only;
+ else
+ trace_ops.func = function_trace_call;
+
+ if (func_flags.val & TRACE_FUNC_OPT_STACK)
+ register_ftrace_function(&trace_stack_ops);
+ else
+ register_ftrace_function(&trace_ops);
+
+ ftrace_function_enabled = 1;
+}
+
+static void tracing_stop_function_trace(void)
+{
+ ftrace_function_enabled = 0;
+
+ if (func_flags.val & TRACE_FUNC_OPT_STACK)
+ unregister_ftrace_function(&trace_stack_ops);
+ else
+ unregister_ftrace_function(&trace_ops);
+}
+
+static int func_set_flag(u32 old_flags, u32 bit, int set)
+{
+ if (bit == TRACE_FUNC_OPT_STACK) {
+ /* do nothing if already set */
+ if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
+ return 0;
+
+ if (set) {
+ unregister_ftrace_function(&trace_ops);
+ register_ftrace_function(&trace_stack_ops);
+ } else {
+ unregister_ftrace_function(&trace_stack_ops);
+ register_ftrace_function(&trace_ops);
+ }
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static struct tracer function_trace __read_mostly =
+{
+ .name = "function",
+ .init = function_trace_init,
+ .reset = function_trace_reset,
+ .start = function_trace_start,
+ .wait_pipe = poll_wait_pipe,
+ .flags = &func_flags,
+ .set_flag = func_set_flag,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_function,
+#endif
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static void
+ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ long *count = (long *)data;
+
+ if (tracing_is_on())
+ return;
+
+ if (!*count)
+ return;
+
+ if (*count != -1)
+ (*count)--;
+
+ tracing_on();
+}
+
+static void
+ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
+{
+ long *count = (long *)data;
+
+ if (!tracing_is_on())
+ return;
+
+ if (!*count)
+ return;
+
+ if (*count != -1)
+ (*count)--;
+
+ tracing_off();
+}
+
+static int
+ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
+ struct ftrace_probe_ops *ops, void *data);
+
+static struct ftrace_probe_ops traceon_probe_ops = {
+ .func = ftrace_traceon,
+ .print = ftrace_trace_onoff_print,
+};
+
+static struct ftrace_probe_ops traceoff_probe_ops = {
+ .func = ftrace_traceoff,
+ .print = ftrace_trace_onoff_print,
+};
+
+static int
+ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
+ struct ftrace_probe_ops *ops, void *data)
+{
+ long count = (long)data;
+
+ seq_printf(m, "%ps:", (void *)ip);
+
+ if (ops == &traceon_probe_ops)
+ seq_printf(m, "traceon");
+ else
+ seq_printf(m, "traceoff");
+
+ if (count == -1)
+ seq_printf(m, ":unlimited\n");
+ else
+ seq_printf(m, ":count=%ld\n", count);
+
+ return 0;
+}
+
+static int
+ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param)
+{
+ struct ftrace_probe_ops *ops;
+
+ /* we register both traceon and traceoff to this callback */
+ if (strcmp(cmd, "traceon") == 0)
+ ops = &traceon_probe_ops;
+ else
+ ops = &traceoff_probe_ops;
+
+ unregister_ftrace_function_probe_func(glob, ops);
+
+ return 0;
+}
+
+static int
+ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
+{
+ struct ftrace_probe_ops *ops;
+ void *count = (void *)-1;
+ char *number;
+ int ret;
+
+ /* hash funcs only work with set_ftrace_filter */
+ if (!enable)
+ return -EINVAL;
+
+ if (glob[0] == '!')
+ return ftrace_trace_onoff_unreg(glob+1, cmd, param);
+
+ /* we register both traceon and traceoff to this callback */
+ if (strcmp(cmd, "traceon") == 0)
+ ops = &traceon_probe_ops;
+ else
+ ops = &traceoff_probe_ops;
+
+ if (!param)
+ goto out_reg;
+
+ number = strsep(&param, ":");
+
+ if (!strlen(number))
+ goto out_reg;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = strict_strtoul(number, 0, (unsigned long *)&count);
+ if (ret)
+ return ret;
+
+ out_reg:
+ ret = register_ftrace_function_probe(glob, ops, count);
+
+ return ret < 0 ? ret : 0;
+}
+
+static struct ftrace_func_command ftrace_traceon_cmd = {
+ .name = "traceon",
+ .func = ftrace_trace_onoff_callback,
+};
+
+static struct ftrace_func_command ftrace_traceoff_cmd = {
+ .name = "traceoff",
+ .func = ftrace_trace_onoff_callback,
+};
+
+static int __init init_func_cmd_traceon(void)
+{
+ int ret;
+
+ ret = register_ftrace_command(&ftrace_traceoff_cmd);
+ if (ret)
+ return ret;
+
+ ret = register_ftrace_command(&ftrace_traceon_cmd);
+ if (ret)
+ unregister_ftrace_command(&ftrace_traceoff_cmd);
+ return ret;
+}
+#else
+static inline int init_func_cmd_traceon(void)
+{
+ return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+static __init int init_function_trace(void)
+{
+ init_func_cmd_traceon();
+ return register_tracer(&function_trace);
+}
+device_initcall(init_function_trace);
+
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
new file mode 100644
index 00000000000..b1342c5d37c
--- /dev/null
+++ b/kernel/trace/trace_functions_graph.c
@@ -0,0 +1,1173 @@
+/*
+ *
+ * Function graph tracer.
+ * Copyright (c) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
+ * Mostly borrowed from function tracer which
+ * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+struct fgraph_cpu_data {
+ pid_t last_pid;
+ int depth;
+ int ignore;
+};
+
+struct fgraph_data {
+ struct fgraph_cpu_data *cpu_data;
+
+ /* Place to preserve last processed entry. */
+ struct ftrace_graph_ent_entry ent;
+ struct ftrace_graph_ret_entry ret;
+ int failed;
+ int cpu;
+};
+
+#define TRACE_GRAPH_INDENT 2
+
+/* Flag options */
+#define TRACE_GRAPH_PRINT_OVERRUN 0x1
+#define TRACE_GRAPH_PRINT_CPU 0x2
+#define TRACE_GRAPH_PRINT_OVERHEAD 0x4
+#define TRACE_GRAPH_PRINT_PROC 0x8
+#define TRACE_GRAPH_PRINT_DURATION 0x10
+#define TRACE_GRAPH_PRINT_ABS_TIME 0X20
+
+static struct tracer_opt trace_opts[] = {
+ /* Display overruns? (for self-debug purpose) */
+ { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
+ /* Display CPU ? */
+ { TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) },
+ /* Display Overhead ? */
+ { TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) },
+ /* Display proc name/pid */
+ { TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) },
+ /* Display duration of execution */
+ { TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) },
+ /* Display absolute time of an entry */
+ { TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
+ { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+ /* Don't display overruns and proc by default */
+ .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
+ TRACE_GRAPH_PRINT_DURATION,
+ .opts = trace_opts
+};
+
+static struct trace_array *graph_array;
+
+
+/* Add a function return address to the trace stack on thread info.*/
+int
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+ unsigned long frame_pointer)
+{
+ unsigned long long calltime;
+ int index;
+
+ if (!current->ret_stack)
+ return -EBUSY;
+
+ /*
+ * We must make sure the ret_stack is tested before we read
+ * anything else.
+ */
+ smp_rmb();
+
+ /* The return trace stack is full */
+ if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
+ atomic_inc(&current->trace_overrun);
+ return -EBUSY;
+ }
+
+ calltime = trace_clock_local();
+
+ index = ++current->curr_ret_stack;
+ barrier();
+ current->ret_stack[index].ret = ret;
+ current->ret_stack[index].func = func;
+ current->ret_stack[index].calltime = calltime;
+ current->ret_stack[index].subtime = 0;
+ current->ret_stack[index].fp = frame_pointer;
+ *depth = index;
+
+ return 0;
+}
+
+/* Retrieve a function return address to the trace stack on thread info.*/
+static void
+ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
+ unsigned long frame_pointer)
+{
+ int index;
+
+ index = current->curr_ret_stack;
+
+ if (unlikely(index < 0)) {
+ ftrace_graph_stop();
+ WARN_ON(1);
+ /* Might as well panic, otherwise we have no where to go */
+ *ret = (unsigned long)panic;
+ return;
+ }
+
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+ /*
+ * The arch may choose to record the frame pointer used
+ * and check it here to make sure that it is what we expect it
+ * to be. If gcc does not set the place holder of the return
+ * address in the frame pointer, and does a copy instead, then
+ * the function graph trace will fail. This test detects this
+ * case.
+ *
+ * Currently, x86_32 with optimize for size (-Os) makes the latest
+ * gcc do the above.
+ */
+ if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
+ ftrace_graph_stop();
+ WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
+ " from func %ps return to %lx\n",
+ current->ret_stack[index].fp,
+ frame_pointer,
+ (void *)current->ret_stack[index].func,
+ current->ret_stack[index].ret);
+ *ret = (unsigned long)panic;
+ return;
+ }
+#endif
+
+ *ret = current->ret_stack[index].ret;
+ trace->func = current->ret_stack[index].func;
+ trace->calltime = current->ret_stack[index].calltime;
+ trace->overrun = atomic_read(&current->trace_overrun);
+ trace->depth = index;
+}
+
+/*
+ * Send the trace to the ring-buffer.
+ * @return the original return address.
+ */
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
+{
+ struct ftrace_graph_ret trace;
+ unsigned long ret;
+
+ ftrace_pop_return_trace(&trace, &ret, frame_pointer);
+ trace.rettime = trace_clock_local();
+ ftrace_graph_return(&trace);
+ barrier();
+ current->curr_ret_stack--;
+
+ if (unlikely(!ret)) {
+ ftrace_graph_stop();
+ WARN_ON(1);
+ /* Might as well panic. What else to do? */
+ ret = (unsigned long)panic;
+ }
+
+ return ret;
+}
+
+static int __trace_graph_entry(struct trace_array *tr,
+ struct ftrace_graph_ent *trace,
+ unsigned long flags,
+ int pc)
+{
+ struct ftrace_event_call *call = &event_funcgraph_entry;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer = tr->buffer;
+ struct ftrace_graph_ent_entry *entry;
+
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ return 0;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ return 0;
+ entry = ring_buffer_event_data(event);
+ entry->graph_ent = *trace;
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ ring_buffer_unlock_commit(buffer, event);
+
+ return 1;
+}
+
+int trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+ struct trace_array *tr = graph_array;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int ret;
+ int cpu;
+ int pc;
+
+ if (unlikely(!tr))
+ return 0;
+
+ if (!ftrace_trace_task(current))
+ return 0;
+
+ if (!ftrace_graph_addr(trace->func))
+ return 0;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ ret = __trace_graph_entry(tr, trace, flags, pc);
+ } else {
+ ret = 0;
+ }
+ /* Only do the atomic if it is not already set */
+ if (!test_tsk_trace_graph(current))
+ set_tsk_trace_graph(current);
+
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+
+ return ret;
+}
+
+static void __trace_graph_return(struct trace_array *tr,
+ struct ftrace_graph_ret *trace,
+ unsigned long flags,
+ int pc)
+{
+ struct ftrace_event_call *call = &event_funcgraph_exit;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer = tr->buffer;
+ struct ftrace_graph_ret_entry *entry;
+
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ return;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ entry->ret = *trace;
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ ring_buffer_unlock_commit(buffer, event);
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct trace_array *tr = graph_array;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ __trace_graph_return(tr, trace, flags, pc);
+ }
+ if (!trace->depth)
+ clear_tsk_trace_graph(current);
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+
+static int graph_trace_init(struct trace_array *tr)
+{
+ int ret;
+
+ graph_array = tr;
+ ret = register_ftrace_graph(&trace_graph_return,
+ &trace_graph_entry);
+ if (ret)
+ return ret;
+ tracing_start_cmdline_record();
+
+ return 0;
+}
+
+void set_graph_array(struct trace_array *tr)
+{
+ graph_array = tr;
+}
+
+static void graph_trace_reset(struct trace_array *tr)
+{
+ tracing_stop_cmdline_record();
+ unregister_ftrace_graph();
+}
+
+static int max_bytes_for_cpu;
+
+static enum print_line_t
+print_graph_cpu(struct trace_seq *s, int cpu)
+{
+ int ret;
+
+ /*
+ * Start with a space character - to make it stand out
+ * to the right a bit when trace output is pasted into
+ * email:
+ */
+ ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+#define TRACE_GRAPH_PROCINFO_LENGTH 14
+
+static enum print_line_t
+print_graph_proc(struct trace_seq *s, pid_t pid)
+{
+ char comm[TASK_COMM_LEN];
+ /* sign + log10(MAX_INT) + '\0' */
+ char pid_str[11];
+ int spaces = 0;
+ int ret;
+ int len;
+ int i;
+
+ trace_find_cmdline(pid, comm);
+ comm[7] = '\0';
+ sprintf(pid_str, "%d", pid);
+
+ /* 1 stands for the "-" character */
+ len = strlen(comm) + strlen(pid_str) + 1;
+
+ if (len < TRACE_GRAPH_PROCINFO_LENGTH)
+ spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;
+
+ /* First spaces to align center */
+ for (i = 0; i < spaces / 2; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "%s-%s", comm, pid_str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Last spaces to align center */
+ for (i = 0; i < spaces - (spaces / 2); i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ return TRACE_TYPE_HANDLED;
+}
+
+
+static enum print_line_t
+print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
+{
+ if (!trace_seq_putc(s, ' '))
+ return 0;
+
+ return trace_print_lat_fmt(s, entry);
+}
+
+/* If the pid changed since the last trace, output this event */
+static enum print_line_t
+verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
+{
+ pid_t prev_pid;
+ pid_t *last_pid;
+ int ret;
+
+ if (!data)
+ return TRACE_TYPE_HANDLED;
+
+ last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
+
+ if (*last_pid == pid)
+ return TRACE_TYPE_HANDLED;
+
+ prev_pid = *last_pid;
+ *last_pid = pid;
+
+ if (prev_pid == -1)
+ return TRACE_TYPE_HANDLED;
+/*
+ * Context-switch trace line:
+
+ ------------------------------------------
+ | 1) migration/0--1 => sshd-1755
+ ------------------------------------------
+
+ */
+ ret = trace_seq_printf(s,
+ " ------------------------------------------\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = print_graph_proc(s, prev_pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " => ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = print_graph_proc(s, pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s,
+ "\n ------------------------------------------\n\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct ftrace_graph_ret_entry *
+get_return_for_leaf(struct trace_iterator *iter,
+ struct ftrace_graph_ent_entry *curr)
+{
+ struct fgraph_data *data = iter->private;
+ struct ring_buffer_iter *ring_iter = NULL;
+ struct ring_buffer_event *event;
+ struct ftrace_graph_ret_entry *next;
+
+ /*
+ * If the previous output failed to write to the seq buffer,
+ * then we just reuse the data from before.
+ */
+ if (data && data->failed) {
+ curr = &data->ent;
+ next = &data->ret;
+ } else {
+
+ ring_iter = iter->buffer_iter[iter->cpu];
+
+ /* First peek to compare current entry and the next one */
+ if (ring_iter)
+ event = ring_buffer_iter_peek(ring_iter, NULL);
+ else {
+ /*
+ * We need to consume the current entry to see
+ * the next one.
+ */
+ ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+ event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+ NULL);
+ }
+
+ if (!event)
+ return NULL;
+
+ next = ring_buffer_event_data(event);
+
+ if (data) {
+ /*
+ * Save current and next entries for later reference
+ * if the output fails.
+ */
+ data->ent = *curr;
+ data->ret = *next;
+ }
+ }
+
+ if (next->ent.type != TRACE_GRAPH_RET)
+ return NULL;
+
+ if (curr->ent.pid != next->ent.pid ||
+ curr->graph_ent.func != next->ret.func)
+ return NULL;
+
+ /* this is a leaf, now advance the iterator */
+ if (ring_iter)
+ ring_buffer_read(ring_iter, NULL);
+
+ return next;
+}
+
+/* Signal a overhead of time execution to the output */
+static int
+print_graph_overhead(unsigned long long duration, struct trace_seq *s)
+{
+ /* If duration disappear, we don't need anything */
+ if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION))
+ return 1;
+
+ /* Non nested entry or return */
+ if (duration == -1)
+ return trace_seq_printf(s, " ");
+
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ /* Duration exceeded 100 msecs */
+ if (duration > 100000ULL)
+ return trace_seq_printf(s, "! ");
+
+ /* Duration exceeded 10 msecs */
+ if (duration > 10000ULL)
+ return trace_seq_printf(s, "+ ");
+ }
+
+ return trace_seq_printf(s, " ");
+}
+
+static int print_graph_abs_time(u64 t, struct trace_seq *s)
+{
+ unsigned long usecs_rem;
+
+ usecs_rem = do_div(t, NSEC_PER_SEC);
+ usecs_rem /= 1000;
+
+ return trace_seq_printf(s, "%5lu.%06lu | ",
+ (unsigned long)t, usecs_rem);
+}
+
+static enum print_line_t
+print_graph_irq(struct trace_iterator *iter, unsigned long addr,
+ enum trace_type type, int cpu, pid_t pid)
+{
+ int ret;
+ struct trace_seq *s = &iter->seq;
+
+ if (addr < (unsigned long)__irqentry_text_start ||
+ addr >= (unsigned long)__irqentry_text_end)
+ return TRACE_TYPE_UNHANDLED;
+
+ /* Absolute time */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+ ret = print_graph_abs_time(iter->ts, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Cpu */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Proc */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ ret = print_graph_proc(s, pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* No overhead */
+ ret = print_graph_overhead(-1, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (type == TRACE_GRAPH_ENT)
+ ret = trace_seq_printf(s, "==========>");
+ else
+ ret = trace_seq_printf(s, "<==========");
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Don't close the duration column if haven't one */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+ trace_seq_printf(s, " |");
+ ret = trace_seq_printf(s, "\n");
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ return TRACE_TYPE_HANDLED;
+}
+
+enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+ unsigned long nsecs_rem = do_div(duration, 1000);
+ /* log10(ULONG_MAX) + '\0' */
+ char msecs_str[21];
+ char nsecs_str[5];
+ int ret, len;
+ int i;
+
+ sprintf(msecs_str, "%lu", (unsigned long) duration);
+
+ /* Print msecs */
+ ret = trace_seq_printf(s, "%s", msecs_str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ len = strlen(msecs_str);
+
+ /* Print nsecs (we don't want to exceed 7 numbers) */
+ if (len < 7) {
+ snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
+ ret = trace_seq_printf(s, ".%s", nsecs_str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ len += strlen(nsecs_str);
+ }
+
+ ret = trace_seq_printf(s, " us ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Print remaining spaces to fit the row's width */
+ for (i = len; i < 7; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_print_graph_duration(duration, s);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
+
+ ret = trace_seq_printf(s, "| ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+/* Case of a leaf function on its call entry */
+static enum print_line_t
+print_graph_entry_leaf(struct trace_iterator *iter,
+ struct ftrace_graph_ent_entry *entry,
+ struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
+{
+ struct fgraph_data *data = iter->private;
+ struct ftrace_graph_ret *graph_ret;
+ struct ftrace_graph_ent *call;
+ unsigned long long duration;
+ int ret;
+ int i;
+
+ graph_ret = &ret_entry->ret;
+ call = &entry->graph_ent;
+ duration = graph_ret->rettime - graph_ret->calltime;
+
+ if (data) {
+ int cpu = iter->cpu;
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ /*
+ * Comments display at + 1 to depth. Since
+ * this is a leaf function, keep the comments
+ * equal to this depth.
+ */
+ *depth = call->depth - 1;
+ }
+
+ /* Overhead */
+ ret = print_graph_overhead(duration, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Duration */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ ret = print_graph_duration(duration, s);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Function */
+ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "%ps();\n", (void *)call->func);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_entry_nested(struct trace_iterator *iter,
+ struct ftrace_graph_ent_entry *entry,
+ struct trace_seq *s, int cpu)
+{
+ struct ftrace_graph_ent *call = &entry->graph_ent;
+ struct fgraph_data *data = iter->private;
+ int ret;
+ int i;
+
+ if (data) {
+ int cpu = iter->cpu;
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ *depth = call->depth;
+ }
+
+ /* No overhead */
+ ret = print_graph_overhead(-1, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* No time */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Function */
+ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "%ps() {\n", (void *)call->func);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /*
+ * we already consumed the current entry to check the next one
+ * and see if this is a leaf.
+ */
+ return TRACE_TYPE_NO_CONSUME;
+}
+
+static enum print_line_t
+print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
+ int type, unsigned long addr)
+{
+ struct fgraph_data *data = iter->private;
+ struct trace_entry *ent = iter->ent;
+ int cpu = iter->cpu;
+ int ret;
+
+ /* Pid */
+ if (verif_pid(s, ent->pid, cpu, data) == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (type) {
+ /* Interrupt */
+ ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Absolute time */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+ ret = print_graph_abs_time(iter->ts, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Cpu */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Proc */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ ret = print_graph_proc(s, ent->pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Latency format */
+ if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+ ret = print_graph_lat_fmt(s, ent);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ return 0;
+}
+
+static enum print_line_t
+print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
+ struct trace_iterator *iter)
+{
+ struct fgraph_data *data = iter->private;
+ struct ftrace_graph_ent *call = &field->graph_ent;
+ struct ftrace_graph_ret_entry *leaf_ret;
+ static enum print_line_t ret;
+ int cpu = iter->cpu;
+
+ if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ leaf_ret = get_return_for_leaf(iter, field);
+ if (leaf_ret)
+ ret = print_graph_entry_leaf(iter, field, leaf_ret, s);
+ else
+ ret = print_graph_entry_nested(iter, field, s, cpu);
+
+ if (data) {
+ /*
+ * If we failed to write our output, then we need to make
+ * note of it. Because we already consumed our entry.
+ */
+ if (s->full) {
+ data->failed = 1;
+ data->cpu = cpu;
+ } else
+ data->failed = 0;
+ }
+
+ return ret;
+}
+
+static enum print_line_t
+print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
+ struct trace_entry *ent, struct trace_iterator *iter)
+{
+ unsigned long long duration = trace->rettime - trace->calltime;
+ struct fgraph_data *data = iter->private;
+ pid_t pid = ent->pid;
+ int cpu = iter->cpu;
+ int ret;
+ int i;
+
+ if (data) {
+ int cpu = iter->cpu;
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ /*
+ * Comments display at + 1 to depth. This is the
+ * return from a function, we now want the comments
+ * to display at the same level of the bracket.
+ */
+ *depth = trace->depth - 1;
+ }
+
+ if (print_graph_prologue(iter, s, 0, 0))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Overhead */
+ ret = print_graph_overhead(duration, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Duration */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ ret = print_graph_duration(duration, s);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Closing brace */
+ for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "}\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Overrun */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+ ret = trace_seq_printf(s, " (Overruns: %lu)\n",
+ trace->overrun);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
+ struct trace_iterator *iter)
+{
+ unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+ struct fgraph_data *data = iter->private;
+ struct trace_event *event;
+ int depth = 0;
+ int ret;
+ int i;
+
+ if (data)
+ depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
+
+ if (print_graph_prologue(iter, s, 0, 0))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* No overhead */
+ ret = print_graph_overhead(-1, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* No time */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Indentation */
+ if (depth > 0)
+ for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* The comment */
+ ret = trace_seq_printf(s, "/* ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ switch (iter->ent->type) {
+ case TRACE_BPRINT:
+ ret = trace_print_bprintk_msg_only(iter);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
+ break;
+ case TRACE_PRINT:
+ ret = trace_print_printk_msg_only(iter);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
+ break;
+ default:
+ event = ftrace_find_event(ent->type);
+ if (!event)
+ return TRACE_TYPE_UNHANDLED;
+
+ ret = event->trace(iter, sym_flags);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
+ }
+
+ /* Strip ending newline */
+ if (s->buffer[s->len - 1] == '\n') {
+ s->buffer[s->len - 1] = '\0';
+ s->len--;
+ }
+
+ ret = trace_seq_printf(s, " */\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+
+enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct fgraph_data *data = iter->private;
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ int cpu = iter->cpu;
+ int ret;
+
+ if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
+ per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
+ return TRACE_TYPE_HANDLED;
+ }
+
+ /*
+ * If the last output failed, there's a possibility we need
+ * to print out the missing entry which would never go out.
+ */
+ if (data && data->failed) {
+ field = &data->ent;
+ iter->cpu = data->cpu;
+ ret = print_graph_entry(field, s, iter);
+ if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
+ per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
+ ret = TRACE_TYPE_NO_CONSUME;
+ }
+ iter->cpu = cpu;
+ return ret;
+ }
+
+ switch (entry->type) {
+ case TRACE_GRAPH_ENT: {
+ /*
+ * print_graph_entry() may consume the current event,
+ * thus @field may become invalid, so we need to save it.
+ * sizeof(struct ftrace_graph_ent_entry) is very small,
+ * it can be safely saved at the stack.
+ */
+ struct ftrace_graph_ent_entry saved;
+ trace_assign_type(field, entry);
+ saved = *field;
+ return print_graph_entry(&saved, s, iter);
+ }
+ case TRACE_GRAPH_RET: {
+ struct ftrace_graph_ret_entry *field;
+ trace_assign_type(field, entry);
+ return print_graph_return(&field->ret, s, entry, iter);
+ }
+ default:
+ return print_graph_comment(s, entry, iter);
+ }
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static void print_lat_header(struct seq_file *s)
+{
+ static const char spaces[] = " " /* 16 spaces */
+ " " /* 4 spaces */
+ " "; /* 17 spaces */
+ int size = 0;
+
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+ size += 16;
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ size += 4;
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ size += 17;
+
+ seq_printf(s, "#%.*s _-----=> irqs-off \n", size, spaces);
+ seq_printf(s, "#%.*s / _----=> need-resched \n", size, spaces);
+ seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
+ seq_printf(s, "#%.*s|| / _--=> preempt-depth \n", size, spaces);
+ seq_printf(s, "#%.*s||| / _-=> lock-depth \n", size, spaces);
+ seq_printf(s, "#%.*s|||| / \n", size, spaces);
+}
+
+static void print_graph_headers(struct seq_file *s)
+{
+ int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
+
+ if (lat)
+ print_lat_header(s);
+
+ /* 1st line */
+ seq_printf(s, "#");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+ seq_printf(s, " TIME ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ seq_printf(s, " CPU");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ seq_printf(s, " TASK/PID ");
+ if (lat)
+ seq_printf(s, "|||||");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+ seq_printf(s, " DURATION ");
+ seq_printf(s, " FUNCTION CALLS\n");
+
+ /* 2nd line */
+ seq_printf(s, "#");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+ seq_printf(s, " | ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ seq_printf(s, " | ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ seq_printf(s, " | | ");
+ if (lat)
+ seq_printf(s, "|||||");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+ seq_printf(s, " | | ");
+ seq_printf(s, " | | | |\n");
+}
+
+static void graph_trace_open(struct trace_iterator *iter)
+{
+ /* pid and depth on the last trace processed */
+ struct fgraph_data *data;
+ int cpu;
+
+ iter->private = NULL;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_err;
+
+ data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+ if (!data->cpu_data)
+ goto out_err_free;
+
+ for_each_possible_cpu(cpu) {
+ pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+ int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
+ *pid = -1;
+ *depth = 0;
+ *ignore = 0;
+ }
+
+ iter->private = data;
+
+ return;
+
+ out_err_free:
+ kfree(data);
+ out_err:
+ pr_warning("function graph tracer: not enough memory\n");
+}
+
+static void graph_trace_close(struct trace_iterator *iter)
+{
+ struct fgraph_data *data = iter->private;
+
+ if (data) {
+ free_percpu(data->cpu_data);
+ kfree(data);
+ }
+}
+
+static struct tracer graph_trace __read_mostly = {
+ .name = "function_graph",
+ .open = graph_trace_open,
+ .pipe_open = graph_trace_open,
+ .close = graph_trace_close,
+ .pipe_close = graph_trace_close,
+ .wait_pipe = poll_wait_pipe,
+ .init = graph_trace_init,
+ .reset = graph_trace_reset,
+ .print_line = print_graph_function,
+ .print_header = print_graph_headers,
+ .flags = &tracer_flags,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_function_graph,
+#endif
+};
+
+static __init int init_graph_trace(void)
+{
+ max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
+
+ return register_tracer(&graph_trace);
+}
+
+device_initcall(init_graph_trace);
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
new file mode 100644
index 00000000000..7b97000745f
--- /dev/null
+++ b/kernel/trace/trace_hw_branches.c
@@ -0,0 +1,312 @@
+/*
+ * h/w branch tracer for x86 based on BTS
+ *
+ * Copyright (C) 2008-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
+ */
+#include <linux/kallsyms.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/fs.h>
+
+#include <asm/ds.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+
+#define BTS_BUFFER_SIZE (1 << 13)
+
+static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
+
+#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
+
+static int trace_hw_branches_enabled __read_mostly;
+static int trace_hw_branches_suspended __read_mostly;
+static struct trace_array *hw_branch_trace __read_mostly;
+
+
+static void bts_trace_init_cpu(int cpu)
+{
+ per_cpu(hwb_tracer, cpu) =
+ ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
+ BTS_BUFFER_SIZE, NULL, (size_t)-1,
+ BTS_KERNEL);
+
+ if (IS_ERR(per_cpu(hwb_tracer, cpu)))
+ per_cpu(hwb_tracer, cpu) = NULL;
+}
+
+static int bts_trace_init(struct trace_array *tr)
+{
+ int cpu;
+
+ hw_branch_trace = tr;
+ trace_hw_branches_enabled = 0;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ bts_trace_init_cpu(cpu);
+
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ trace_hw_branches_enabled = 1;
+ }
+ trace_hw_branches_suspended = 0;
+ put_online_cpus();
+
+ /* If we could not enable tracing on a single cpu, we fail. */
+ return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
+}
+
+static void bts_trace_reset(struct trace_array *tr)
+{
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ if (likely(per_cpu(hwb_tracer, cpu))) {
+ ds_release_bts(per_cpu(hwb_tracer, cpu));
+ per_cpu(hwb_tracer, cpu) = NULL;
+ }
+ }
+ trace_hw_branches_enabled = 0;
+ trace_hw_branches_suspended = 0;
+ put_online_cpus();
+}
+
+static void bts_trace_start(struct trace_array *tr)
+{
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_resume_bts(per_cpu(hwb_tracer, cpu));
+ trace_hw_branches_suspended = 0;
+ put_online_cpus();
+}
+
+static void bts_trace_stop(struct trace_array *tr)
+{
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
+ trace_hw_branches_suspended = 1;
+ put_online_cpus();
+}
+
+static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ int cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_DOWN_FAILED:
+ /* The notification is sent with interrupts enabled. */
+ if (trace_hw_branches_enabled) {
+ bts_trace_init_cpu(cpu);
+
+ if (trace_hw_branches_suspended &&
+ likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
+ }
+ break;
+
+ case CPU_DOWN_PREPARE:
+ /* The notification is sent with interrupts enabled. */
+ if (likely(per_cpu(hwb_tracer, cpu))) {
+ ds_release_bts(per_cpu(hwb_tracer, cpu));
+ per_cpu(hwb_tracer, cpu) = NULL;
+ }
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
+ .notifier_call = bts_hotcpu_handler
+};
+
+static void bts_trace_print_header(struct seq_file *m)
+{
+ seq_puts(m, "# CPU# TO <- FROM\n");
+}
+
+static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
+{
+ unsigned long symflags = TRACE_ITER_SYM_OFFSET;
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *seq = &iter->seq;
+ struct hw_branch_entry *it;
+
+ trace_assign_type(it, entry);
+
+ if (entry->type == TRACE_HW_BRANCHES) {
+ if (trace_seq_printf(seq, "%4d ", iter->cpu) &&
+ seq_print_ip_sym(seq, it->to, symflags) &&
+ trace_seq_printf(seq, "\t <- ") &&
+ seq_print_ip_sym(seq, it->from, symflags) &&
+ trace_seq_printf(seq, "\n"))
+ return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ return TRACE_TYPE_UNHANDLED;
+}
+
+void trace_hw_branch(u64 from, u64 to)
+{
+ struct ftrace_event_call *call = &event_hw_branch;
+ struct trace_array *tr = hw_branch_trace;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buf;
+ struct hw_branch_entry *entry;
+ unsigned long irq1;
+ int cpu;
+
+ if (unlikely(!tr))
+ return;
+
+ if (unlikely(!trace_hw_branches_enabled))
+ return;
+
+ local_irq_save(irq1);
+ cpu = raw_smp_processor_id();
+ if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+ goto out;
+
+ buf = tr->buffer;
+ event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
+ sizeof(*entry), 0, 0);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, from);
+ entry->ent.type = TRACE_HW_BRANCHES;
+ entry->from = from;
+ entry->to = to;
+ if (!filter_check_discard(call, entry, buf, event))
+ trace_buffer_unlock_commit(buf, event, 0, 0);
+
+ out:
+ atomic_dec(&tr->data[cpu]->disabled);
+ local_irq_restore(irq1);
+}
+
+static void trace_bts_at(const struct bts_trace *trace, void *at)
+{
+ struct bts_struct bts;
+ int err = 0;
+
+ WARN_ON_ONCE(!trace->read);
+ if (!trace->read)
+ return;
+
+ err = trace->read(this_tracer, at, &bts);
+ if (err < 0)
+ return;
+
+ switch (bts.qualifier) {
+ case BTS_BRANCH:
+ trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to);
+ break;
+ }
+}
+
+/*
+ * Collect the trace on the current cpu and write it into the ftrace buffer.
+ *
+ * pre: tracing must be suspended on the current cpu
+ */
+static void trace_bts_cpu(void *arg)
+{
+ struct trace_array *tr = (struct trace_array *)arg;
+ const struct bts_trace *trace;
+ unsigned char *at;
+
+ if (unlikely(!tr))
+ return;
+
+ if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled)))
+ return;
+
+ if (unlikely(!this_tracer))
+ return;
+
+ trace = ds_read_bts(this_tracer);
+ if (!trace)
+ return;
+
+ for (at = trace->ds.top; (void *)at < trace->ds.end;
+ at += trace->ds.size)
+ trace_bts_at(trace, at);
+
+ for (at = trace->ds.begin; (void *)at < trace->ds.top;
+ at += trace->ds.size)
+ trace_bts_at(trace, at);
+}
+
+static void trace_bts_prepare(struct trace_iterator *iter)
+{
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
+ /*
+ * We need to collect the trace on the respective cpu since ftrace
+ * implicitly adds the record for the current cpu.
+ * Once that is more flexible, we could collect the data from any cpu.
+ */
+ on_each_cpu(trace_bts_cpu, iter->tr, 1);
+
+ for_each_online_cpu(cpu)
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_resume_bts(per_cpu(hwb_tracer, cpu));
+ put_online_cpus();
+}
+
+static void trace_bts_close(struct trace_iterator *iter)
+{
+ tracing_reset_online_cpus(iter->tr);
+}
+
+void trace_hw_branch_oops(void)
+{
+ if (this_tracer) {
+ ds_suspend_bts_noirq(this_tracer);
+ trace_bts_cpu(hw_branch_trace);
+ ds_resume_bts_noirq(this_tracer);
+ }
+}
+
+struct tracer bts_tracer __read_mostly =
+{
+ .name = "hw-branch-tracer",
+ .init = bts_trace_init,
+ .reset = bts_trace_reset,
+ .print_header = bts_trace_print_header,
+ .print_line = bts_trace_print_line,
+ .start = bts_trace_start,
+ .stop = bts_trace_stop,
+ .open = trace_bts_prepare,
+ .close = trace_bts_close,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_hw_branches,
+#endif /* CONFIG_FTRACE_SELFTEST */
+};
+
+__init static int init_bts_trace(void)
+{
+ register_hotcpu_notifier(&bts_hotcpu_notifier);
+ return register_tracer(&bts_tracer);
+}
+device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
new file mode 100644
index 00000000000..2974bc7538c
--- /dev/null
+++ b/kernel/trace/trace_irqsoff.c
@@ -0,0 +1,484 @@
+/*
+ * trace irqs off critical timings
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * From code in the latency_tracer, that is:
+ *
+ * Copyright (C) 2004-2006 Ingo Molnar
+ * Copyright (C) 2004 William Lee Irwin III
+ */
+#include <linux/kallsyms.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+static struct trace_array *irqsoff_trace __read_mostly;
+static int tracer_enabled __read_mostly;
+
+static DEFINE_PER_CPU(int, tracing_cpu);
+
+static DEFINE_SPINLOCK(max_trace_lock);
+
+enum {
+ TRACER_IRQS_OFF = (1 << 1),
+ TRACER_PREEMPT_OFF = (1 << 2),
+};
+
+static int trace_type __read_mostly;
+
+static int save_lat_flag;
+
+#ifdef CONFIG_PREEMPT_TRACER
+static inline int
+preempt_trace(void)
+{
+ return ((trace_type & TRACER_PREEMPT_OFF) && preempt_count());
+}
+#else
+# define preempt_trace() (0)
+#endif
+
+#ifdef CONFIG_IRQSOFF_TRACER
+static inline int
+irq_trace(void)
+{
+ return ((trace_type & TRACER_IRQS_OFF) &&
+ irqs_disabled());
+}
+#else
+# define irq_trace() (0)
+#endif
+
+/*
+ * Sequence count - we record it when starting a measurement and
+ * skip the latency if the sequence has changed - some other section
+ * did a maximum and could disturb our measurement with serial console
+ * printouts, etc. Truly coinciding maximum latencies should be rare
+ * and what happens together happens separately as well, so this doesnt
+ * decrease the validity of the maximum found:
+ */
+static __cacheline_aligned_in_smp unsigned long max_sequence;
+
+#ifdef CONFIG_FUNCTION_TRACER
+/*
+ * irqsoff uses its own tracer function to keep the overhead down:
+ */
+static void
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct trace_array *tr = irqsoff_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+
+ /*
+ * Does not matter if we preempt. We test the flags
+ * afterward, to see if irqs are disabled or not.
+ * If we preempt and get a false positive, the flags
+ * test will fail.
+ */
+ cpu = raw_smp_processor_id();
+ if (likely(!per_cpu(tracing_cpu, cpu)))
+ return;
+
+ local_save_flags(flags);
+ /* slight chance to get a false positive on tracing_cpu */
+ if (!irqs_disabled_flags(flags))
+ return;
+
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1))
+ trace_function(tr, ip, parent_ip, flags, preempt_count());
+
+ atomic_dec(&data->disabled);
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+ .func = irqsoff_tracer_call,
+};
+#endif /* CONFIG_FUNCTION_TRACER */
+
+/*
+ * Should this new latency be reported/recorded?
+ */
+static int report_latency(cycle_t delta)
+{
+ if (tracing_thresh) {
+ if (delta < tracing_thresh)
+ return 0;
+ } else {
+ if (delta <= tracing_max_latency)
+ return 0;
+ }
+ return 1;
+}
+
+static void
+check_critical_timing(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ unsigned long parent_ip,
+ int cpu)
+{
+ cycle_t T0, T1, delta;
+ unsigned long flags;
+ int pc;
+
+ T0 = data->preempt_timestamp;
+ T1 = ftrace_now(cpu);
+ delta = T1-T0;
+
+ local_save_flags(flags);
+
+ pc = preempt_count();
+
+ if (!report_latency(delta))
+ goto out;
+
+ spin_lock_irqsave(&max_trace_lock, flags);
+
+ /* check if we are still the max latency */
+ if (!report_latency(delta))
+ goto out_unlock;
+
+ trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+ /* Skip 5 functions to get to the irq/preempt enable function */
+ __trace_stack(tr, flags, 5, pc);
+
+ if (data->critical_sequence != max_sequence)
+ goto out_unlock;
+
+ data->critical_end = parent_ip;
+
+ if (likely(!is_tracing_stopped())) {
+ tracing_max_latency = delta;
+ update_max_tr_single(tr, current, cpu);
+ }
+
+ max_sequence++;
+
+out_unlock:
+ spin_unlock_irqrestore(&max_trace_lock, flags);
+
+out:
+ data->critical_sequence = max_sequence;
+ data->preempt_timestamp = ftrace_now(cpu);
+ trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+}
+
+static inline void
+start_critical_timing(unsigned long ip, unsigned long parent_ip)
+{
+ int cpu;
+ struct trace_array *tr = irqsoff_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+
+ if (likely(!tracer_enabled))
+ return;
+
+ cpu = raw_smp_processor_id();
+
+ if (per_cpu(tracing_cpu, cpu))
+ return;
+
+ data = tr->data[cpu];
+
+ if (unlikely(!data) || atomic_read(&data->disabled))
+ return;
+
+ atomic_inc(&data->disabled);
+
+ data->critical_sequence = max_sequence;
+ data->preempt_timestamp = ftrace_now(cpu);
+ data->critical_start = parent_ip ? : ip;
+
+ local_save_flags(flags);
+
+ trace_function(tr, ip, parent_ip, flags, preempt_count());
+
+ per_cpu(tracing_cpu, cpu) = 1;
+
+ atomic_dec(&data->disabled);
+}
+
+static inline void
+stop_critical_timing(unsigned long ip, unsigned long parent_ip)
+{
+ int cpu;
+ struct trace_array *tr = irqsoff_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+
+ cpu = raw_smp_processor_id();
+ /* Always clear the tracing cpu on stopping the trace */
+ if (unlikely(per_cpu(tracing_cpu, cpu)))
+ per_cpu(tracing_cpu, cpu) = 0;
+ else
+ return;
+
+ if (!tracer_enabled)
+ return;
+
+ data = tr->data[cpu];
+
+ if (unlikely(!data) ||
+ !data->critical_start || atomic_read(&data->disabled))
+ return;
+
+ atomic_inc(&data->disabled);
+
+ local_save_flags(flags);
+ trace_function(tr, ip, parent_ip, flags, preempt_count());
+ check_critical_timing(tr, data, parent_ip ? : ip, cpu);
+ data->critical_start = 0;
+ atomic_dec(&data->disabled);
+}
+
+/* start and stop critical timings used to for stoppage (in idle) */
+void start_critical_timings(void)
+{
+ if (preempt_trace() || irq_trace())
+ start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+}
+EXPORT_SYMBOL_GPL(start_critical_timings);
+
+void stop_critical_timings(void)
+{
+ if (preempt_trace() || irq_trace())
+ stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+}
+EXPORT_SYMBOL_GPL(stop_critical_timings);
+
+#ifdef CONFIG_IRQSOFF_TRACER
+#ifdef CONFIG_PROVE_LOCKING
+void time_hardirqs_on(unsigned long a0, unsigned long a1)
+{
+ if (!preempt_trace() && irq_trace())
+ stop_critical_timing(a0, a1);
+}
+
+void time_hardirqs_off(unsigned long a0, unsigned long a1)
+{
+ if (!preempt_trace() && irq_trace())
+ start_critical_timing(a0, a1);
+}
+
+#else /* !CONFIG_PROVE_LOCKING */
+
+/*
+ * Stubs:
+ */
+
+void early_boot_irqs_off(void)
+{
+}
+
+void early_boot_irqs_on(void)
+{
+}
+
+void trace_softirqs_on(unsigned long ip)
+{
+}
+
+void trace_softirqs_off(unsigned long ip)
+{
+}
+
+inline void print_irqtrace_events(struct task_struct *curr)
+{
+}
+
+/*
+ * We are only interested in hardirq on/off events:
+ */
+void trace_hardirqs_on(void)
+{
+ if (!preempt_trace() && irq_trace())
+ stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+}
+EXPORT_SYMBOL(trace_hardirqs_on);
+
+void trace_hardirqs_off(void)
+{
+ if (!preempt_trace() && irq_trace())
+ start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+}
+EXPORT_SYMBOL(trace_hardirqs_off);
+
+void trace_hardirqs_on_caller(unsigned long caller_addr)
+{
+ if (!preempt_trace() && irq_trace())
+ stop_critical_timing(CALLER_ADDR0, caller_addr);
+}
+EXPORT_SYMBOL(trace_hardirqs_on_caller);
+
+void trace_hardirqs_off_caller(unsigned long caller_addr)
+{
+ if (!preempt_trace() && irq_trace())
+ start_critical_timing(CALLER_ADDR0, caller_addr);
+}
+EXPORT_SYMBOL(trace_hardirqs_off_caller);
+
+#endif /* CONFIG_PROVE_LOCKING */
+#endif /* CONFIG_IRQSOFF_TRACER */
+
+#ifdef CONFIG_PREEMPT_TRACER
+void trace_preempt_on(unsigned long a0, unsigned long a1)
+{
+ if (preempt_trace())
+ stop_critical_timing(a0, a1);
+}
+
+void trace_preempt_off(unsigned long a0, unsigned long a1)
+{
+ if (preempt_trace())
+ start_critical_timing(a0, a1);
+}
+#endif /* CONFIG_PREEMPT_TRACER */
+
+static void start_irqsoff_tracer(struct trace_array *tr)
+{
+ register_ftrace_function(&trace_ops);
+ if (tracing_is_enabled())
+ tracer_enabled = 1;
+ else
+ tracer_enabled = 0;
+}
+
+static void stop_irqsoff_tracer(struct trace_array *tr)
+{
+ tracer_enabled = 0;
+ unregister_ftrace_function(&trace_ops);
+}
+
+static void __irqsoff_tracer_init(struct trace_array *tr)
+{
+ save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
+ trace_flags |= TRACE_ITER_LATENCY_FMT;
+
+ tracing_max_latency = 0;
+ irqsoff_trace = tr;
+ /* make sure that the tracer is visible */
+ smp_wmb();
+ tracing_reset_online_cpus(tr);
+ start_irqsoff_tracer(tr);
+}
+
+static void irqsoff_tracer_reset(struct trace_array *tr)
+{
+ stop_irqsoff_tracer(tr);
+
+ if (!save_lat_flag)
+ trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+}
+
+static void irqsoff_tracer_start(struct trace_array *tr)
+{
+ tracer_enabled = 1;
+}
+
+static void irqsoff_tracer_stop(struct trace_array *tr)
+{
+ tracer_enabled = 0;
+}
+
+#ifdef CONFIG_IRQSOFF_TRACER
+static int irqsoff_tracer_init(struct trace_array *tr)
+{
+ trace_type = TRACER_IRQS_OFF;
+
+ __irqsoff_tracer_init(tr);
+ return 0;
+}
+static struct tracer irqsoff_tracer __read_mostly =
+{
+ .name = "irqsoff",
+ .init = irqsoff_tracer_init,
+ .reset = irqsoff_tracer_reset,
+ .start = irqsoff_tracer_start,
+ .stop = irqsoff_tracer_stop,
+ .print_max = 1,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_irqsoff,
+#endif
+};
+# define register_irqsoff(trace) register_tracer(&trace)
+#else
+# define register_irqsoff(trace) do { } while (0)
+#endif
+
+#ifdef CONFIG_PREEMPT_TRACER
+static int preemptoff_tracer_init(struct trace_array *tr)
+{
+ trace_type = TRACER_PREEMPT_OFF;
+
+ __irqsoff_tracer_init(tr);
+ return 0;
+}
+
+static struct tracer preemptoff_tracer __read_mostly =
+{
+ .name = "preemptoff",
+ .init = preemptoff_tracer_init,
+ .reset = irqsoff_tracer_reset,
+ .start = irqsoff_tracer_start,
+ .stop = irqsoff_tracer_stop,
+ .print_max = 1,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_preemptoff,
+#endif
+};
+# define register_preemptoff(trace) register_tracer(&trace)
+#else
+# define register_preemptoff(trace) do { } while (0)
+#endif
+
+#if defined(CONFIG_IRQSOFF_TRACER) && \
+ defined(CONFIG_PREEMPT_TRACER)
+
+static int preemptirqsoff_tracer_init(struct trace_array *tr)
+{
+ trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
+
+ __irqsoff_tracer_init(tr);
+ return 0;
+}
+
+static struct tracer preemptirqsoff_tracer __read_mostly =
+{
+ .name = "preemptirqsoff",
+ .init = preemptirqsoff_tracer_init,
+ .reset = irqsoff_tracer_reset,
+ .start = irqsoff_tracer_start,
+ .stop = irqsoff_tracer_stop,
+ .print_max = 1,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_preemptirqsoff,
+#endif
+};
+
+# define register_preemptirqsoff(trace) register_tracer(&trace)
+#else
+# define register_preemptirqsoff(trace) do { } while (0)
+#endif
+
+__init static int init_irqsoff_tracer(void)
+{
+ register_irqsoff(irqsoff_tracer);
+ register_preemptoff(preemptoff_tracer);
+ register_preemptirqsoff(preemptirqsoff_tracer);
+
+ return 0;
+}
+device_initcall(init_irqsoff_tracer);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
new file mode 100644
index 00000000000..50b1b823980
--- /dev/null
+++ b/kernel/trace/trace_kprobe.c
@@ -0,0 +1,1553 @@
+/*
+ * Kprobes-based tracing events
+ *
+ * Created by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+ "common_type",
+ "common_flags",
+ "common_preempt_count",
+ "common_pid",
+ "common_tgid",
+ "common_lock_depth",
+ FIELD_STRING_IP,
+ FIELD_STRING_NARGS,
+ FIELD_STRING_RETIP,
+ FIELD_STRING_FUNC,
+};
+
+struct fetch_func {
+ unsigned long (*func)(struct pt_regs *, void *);
+ void *data;
+};
+
+static __kprobes unsigned long call_fetch(struct fetch_func *f,
+ struct pt_regs *regs)
+{
+ return f->func(regs, f->data);
+}
+
+/* fetch handlers */
+static __kprobes unsigned long fetch_register(struct pt_regs *regs,
+ void *offset)
+{
+ return regs_get_register(regs, (unsigned int)((unsigned long)offset));
+}
+
+static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
+ void *num)
+{
+ return regs_get_kernel_stack_nth(regs,
+ (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
+{
+ unsigned long retval;
+
+ if (probe_kernel_address(addr, retval))
+ return 0;
+ return retval;
+}
+
+static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
+{
+ return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
+ void *dummy)
+{
+ return regs_return_value(regs);
+}
+
+static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
+ void *dummy)
+{
+ return kernel_stack_pointer(regs);
+}
+
+/* Memory fetching by symbol */
+struct symbol_cache {
+ char *symbol;
+ long offset;
+ unsigned long addr;
+};
+
+static unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+ sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+ if (sc->addr)
+ sc->addr += sc->offset;
+ return sc->addr;
+}
+
+static void free_symbol_cache(struct symbol_cache *sc)
+{
+ kfree(sc->symbol);
+ kfree(sc);
+}
+
+static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+ struct symbol_cache *sc;
+
+ if (!sym || strlen(sym) == 0)
+ return NULL;
+ sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+ if (!sc)
+ return NULL;
+
+ sc->symbol = kstrdup(sym, GFP_KERNEL);
+ if (!sc->symbol) {
+ kfree(sc);
+ return NULL;
+ }
+ sc->offset = offset;
+
+ update_symbol_cache(sc);
+ return sc;
+}
+
+static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
+{
+ struct symbol_cache *sc = data;
+
+ if (sc->addr)
+ return fetch_memory(regs, (void *)sc->addr);
+ else
+ return 0;
+}
+
+/* Special indirect memory access interface */
+struct indirect_fetch_data {
+ struct fetch_func orig;
+ long offset;
+};
+
+static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
+{
+ struct indirect_fetch_data *ind = data;
+ unsigned long addr;
+
+ addr = call_fetch(&ind->orig, regs);
+ if (addr) {
+ addr += ind->offset;
+ return fetch_memory(regs, (void *)addr);
+ } else
+ return 0;
+}
+
+static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+{
+ if (data->orig.func == fetch_indirect)
+ free_indirect_fetch_data(data->orig.data);
+ else if (data->orig.func == fetch_symbol)
+ free_symbol_cache(data->orig.data);
+ kfree(data);
+}
+
+/**
+ * Kprobe event core functions
+ */
+
+struct probe_arg {
+ struct fetch_func fetch;
+ const char *name;
+};
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE 1
+#define TP_FLAG_PROFILE 2
+
+struct trace_probe {
+ struct list_head list;
+ struct kretprobe rp; /* Use rp.kp for kprobe use */
+ unsigned long nhit;
+ unsigned int flags; /* For TP_FLAG_* */
+ const char *symbol; /* symbol name */
+ struct ftrace_event_call call;
+ struct trace_event event;
+ unsigned int nr_args;
+ struct probe_arg args[];
+};
+
+#define SIZEOF_TRACE_PROBE(n) \
+ (offsetof(struct trace_probe, args) + \
+ (sizeof(struct probe_arg) * (n)))
+
+static __kprobes int probe_is_return(struct trace_probe *tp)
+{
+ return tp->rp.handler != NULL;
+}
+
+static __kprobes const char *probe_symbol(struct trace_probe *tp)
+{
+ return tp->symbol ? tp->symbol : "unknown";
+}
+
+static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
+{
+ int ret = -EINVAL;
+
+ if (ff->func == fetch_argument)
+ ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data);
+ else if (ff->func == fetch_register) {
+ const char *name;
+ name = regs_query_register_name((unsigned int)((long)ff->data));
+ ret = snprintf(buf, n, "%%%s", name);
+ } else if (ff->func == fetch_stack)
+ ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
+ else if (ff->func == fetch_memory)
+ ret = snprintf(buf, n, "@0x%p", ff->data);
+ else if (ff->func == fetch_symbol) {
+ struct symbol_cache *sc = ff->data;
+ if (sc->offset)
+ ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
+ sc->offset);
+ else
+ ret = snprintf(buf, n, "@%s", sc->symbol);
+ } else if (ff->func == fetch_retvalue)
+ ret = snprintf(buf, n, "$retval");
+ else if (ff->func == fetch_stack_address)
+ ret = snprintf(buf, n, "$stack");
+ else if (ff->func == fetch_indirect) {
+ struct indirect_fetch_data *id = ff->data;
+ size_t l = 0;
+ ret = snprintf(buf, n, "%+ld(", id->offset);
+ if (ret >= n)
+ goto end;
+ l += ret;
+ ret = probe_arg_string(buf + l, n - l, &id->orig);
+ if (ret < 0)
+ goto end;
+ l += ret;
+ ret = snprintf(buf + l, n - l, ")");
+ ret += l;
+ }
+end:
+ if (ret >= n)
+ return -ENOSPC;
+ return ret;
+}
+
+static int register_probe_event(struct trace_probe *tp);
+static void unregister_probe_event(struct trace_probe *tp);
+
+static DEFINE_MUTEX(probe_lock);
+static LIST_HEAD(probe_list);
+
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
+static int kretprobe_dispatcher(struct kretprobe_instance *ri,
+ struct pt_regs *regs);
+
+/* Check the name is good for event/group */
+static int check_event_name(const char *name)
+{
+ if (!isalpha(*name) && *name != '_')
+ return 0;
+ while (*++name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return 0;
+ }
+ return 1;
+}
+
+/*
+ * Allocate new trace_probe and initialize it (including kprobes).
+ */
+static struct trace_probe *alloc_trace_probe(const char *group,
+ const char *event,
+ void *addr,
+ const char *symbol,
+ unsigned long offs,
+ int nargs, int is_return)
+{
+ struct trace_probe *tp;
+ int ret = -ENOMEM;
+
+ tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
+ if (!tp)
+ return ERR_PTR(ret);
+
+ if (symbol) {
+ tp->symbol = kstrdup(symbol, GFP_KERNEL);
+ if (!tp->symbol)
+ goto error;
+ tp->rp.kp.symbol_name = tp->symbol;
+ tp->rp.kp.offset = offs;
+ } else
+ tp->rp.kp.addr = addr;
+
+ if (is_return)
+ tp->rp.handler = kretprobe_dispatcher;
+ else
+ tp->rp.kp.pre_handler = kprobe_dispatcher;
+
+ if (!event || !check_event_name(event)) {
+ ret = -EINVAL;
+ goto error;
+ }
+
+ tp->call.name = kstrdup(event, GFP_KERNEL);
+ if (!tp->call.name)
+ goto error;
+
+ if (!group || !check_event_name(group)) {
+ ret = -EINVAL;
+ goto error;
+ }
+
+ tp->call.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->call.system)
+ goto error;
+
+ INIT_LIST_HEAD(&tp->list);
+ return tp;
+error:
+ kfree(tp->call.name);
+ kfree(tp->symbol);
+ kfree(tp);
+ return ERR_PTR(ret);
+}
+
+static void free_probe_arg(struct probe_arg *arg)
+{
+ if (arg->fetch.func == fetch_symbol)
+ free_symbol_cache(arg->fetch.data);
+ else if (arg->fetch.func == fetch_indirect)
+ free_indirect_fetch_data(arg->fetch.data);
+ kfree(arg->name);
+}
+
+static void free_trace_probe(struct trace_probe *tp)
+{
+ int i;
+
+ for (i = 0; i < tp->nr_args; i++)
+ free_probe_arg(&tp->args[i]);
+
+ kfree(tp->call.system);
+ kfree(tp->call.name);
+ kfree(tp->symbol);
+ kfree(tp);
+}
+
+static struct trace_probe *find_probe_event(const char *event,
+ const char *group)
+{
+ struct trace_probe *tp;
+
+ list_for_each_entry(tp, &probe_list, list)
+ if (strcmp(tp->call.name, event) == 0 &&
+ strcmp(tp->call.system, group) == 0)
+ return tp;
+ return NULL;
+}
+
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static void unregister_trace_probe(struct trace_probe *tp)
+{
+ if (probe_is_return(tp))
+ unregister_kretprobe(&tp->rp);
+ else
+ unregister_kprobe(&tp->rp.kp);
+ list_del(&tp->list);
+ unregister_probe_event(tp);
+}
+
+/* Register a trace_probe and probe_event */
+static int register_trace_probe(struct trace_probe *tp)
+{
+ struct trace_probe *old_tp;
+ int ret;
+
+ mutex_lock(&probe_lock);
+
+ /* register as an event */
+ old_tp = find_probe_event(tp->call.name, tp->call.system);
+ if (old_tp) {
+ /* delete old event */
+ unregister_trace_probe(old_tp);
+ free_trace_probe(old_tp);
+ }
+ ret = register_probe_event(tp);
+ if (ret) {
+ pr_warning("Faild to register probe event(%d)\n", ret);
+ goto end;
+ }
+
+ tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+ if (probe_is_return(tp))
+ ret = register_kretprobe(&tp->rp);
+ else
+ ret = register_kprobe(&tp->rp.kp);
+
+ if (ret) {
+ pr_warning("Could not insert probe(%d)\n", ret);
+ if (ret == -EILSEQ) {
+ pr_warning("Probing address(0x%p) is not an "
+ "instruction boundary.\n",
+ tp->rp.kp.addr);
+ ret = -EINVAL;
+ }
+ unregister_probe_event(tp);
+ } else
+ list_add_tail(&tp->list, &probe_list);
+end:
+ mutex_unlock(&probe_lock);
+ return ret;
+}
+
+/* Split symbol and offset. */
+static int split_symbol_offset(char *symbol, unsigned long *offset)
+{
+ char *tmp;
+ int ret;
+
+ if (!offset)
+ return -EINVAL;
+
+ tmp = strchr(symbol, '+');
+ if (tmp) {
+ /* skip sign because strict_strtol doesn't accept '+' */
+ ret = strict_strtoul(tmp + 1, 0, offset);
+ if (ret)
+ return ret;
+ *tmp = '\0';
+ } else
+ *offset = 0;
+ return 0;
+}
+
+#define PARAM_MAX_ARGS 16
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+{
+ int ret = 0;
+ unsigned long param;
+
+ if (strcmp(arg, "retval") == 0) {
+ if (is_return) {
+ ff->func = fetch_retvalue;
+ ff->data = NULL;
+ } else
+ ret = -EINVAL;
+ } else if (strncmp(arg, "stack", 5) == 0) {
+ if (arg[5] == '\0') {
+ ff->func = fetch_stack_address;
+ ff->data = NULL;
+ } else if (isdigit(arg[5])) {
+ ret = strict_strtoul(arg + 5, 10, &param);
+ if (ret || param > PARAM_MAX_STACK)
+ ret = -EINVAL;
+ else {
+ ff->func = fetch_stack;
+ ff->data = (void *)param;
+ }
+ } else
+ ret = -EINVAL;
+ } else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) {
+ ret = strict_strtoul(arg + 3, 10, &param);
+ if (ret || param > PARAM_MAX_ARGS)
+ ret = -EINVAL;
+ else {
+ ff->func = fetch_argument;
+ ff->data = (void *)param;
+ }
+ } else
+ ret = -EINVAL;
+ return ret;
+}
+
+/* Recursive argument parser */
+static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+ int ret = 0;
+ unsigned long param;
+ long offset;
+ char *tmp;
+
+ switch (arg[0]) {
+ case '$':
+ ret = parse_probe_vars(arg + 1, ff, is_return);
+ break;
+ case '%': /* named register */
+ ret = regs_query_register_offset(arg + 1);
+ if (ret >= 0) {
+ ff->func = fetch_register;
+ ff->data = (void *)(unsigned long)ret;
+ ret = 0;
+ }
+ break;
+ case '@': /* memory or symbol */
+ if (isdigit(arg[1])) {
+ ret = strict_strtoul(arg + 1, 0, &param);
+ if (ret)
+ break;
+ ff->func = fetch_memory;
+ ff->data = (void *)param;
+ } else {
+ ret = split_symbol_offset(arg + 1, &offset);
+ if (ret)
+ break;
+ ff->data = alloc_symbol_cache(arg + 1, offset);
+ if (ff->data)
+ ff->func = fetch_symbol;
+ else
+ ret = -EINVAL;
+ }
+ break;
+ case '+': /* indirect memory */
+ case '-':
+ tmp = strchr(arg, '(');
+ if (!tmp) {
+ ret = -EINVAL;
+ break;
+ }
+ *tmp = '\0';
+ ret = strict_strtol(arg + 1, 0, &offset);
+ if (ret)
+ break;
+ if (arg[0] == '-')
+ offset = -offset;
+ arg = tmp + 1;
+ tmp = strrchr(arg, ')');
+ if (tmp) {
+ struct indirect_fetch_data *id;
+ *tmp = '\0';
+ id = kzalloc(sizeof(struct indirect_fetch_data),
+ GFP_KERNEL);
+ if (!id)
+ return -ENOMEM;
+ id->offset = offset;
+ ret = __parse_probe_arg(arg, &id->orig, is_return);
+ if (ret)
+ kfree(id);
+ else {
+ ff->func = fetch_indirect;
+ ff->data = (void *)id;
+ }
+ } else
+ ret = -EINVAL;
+ break;
+ default:
+ /* TODO: support custom handler */
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
+/* String length checking wrapper */
+static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+ if (strlen(arg) > MAX_ARGSTR_LEN) {
+ pr_info("Argument is too long.: %s\n", arg);
+ return -ENOSPC;
+ }
+ return __parse_probe_arg(arg, ff, is_return);
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+ struct probe_arg *args, int narg)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+ if (strcmp(reserved_field_names[i], name) == 0)
+ return 1;
+ for (i = 0; i < narg; i++)
+ if (strcmp(args[i].name, name) == 0)
+ return 1;
+ return 0;
+}
+
+static int create_trace_probe(int argc, char **argv)
+{
+ /*
+ * Argument syntax:
+ * - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
+ * - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+ * Fetch args:
+ * $argN : fetch Nth of function argument. (N:0-)
+ * $retval : fetch return value
+ * $stack : fetch stack address
+ * $stackN : fetch Nth of stack (N:0-)
+ * @ADDR : fetch memory at ADDR (ADDR should be in kernel)
+ * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
+ * %REG : fetch register REG
+ * Indirect memory fetch:
+ * +|-offs(ARG) : fetch memory at ARG +|- offs address.
+ * Alias name of args:
+ * NAME=FETCHARG : set NAME as alias of FETCHARG.
+ */
+ struct trace_probe *tp;
+ int i, ret = 0;
+ int is_return = 0, is_delete = 0;
+ char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+ unsigned long offset = 0;
+ void *addr = NULL;
+ char buf[MAX_EVENT_NAME_LEN];
+
+ /* argc must be >= 1 */
+ if (argv[0][0] == 'p')
+ is_return = 0;
+ else if (argv[0][0] == 'r')
+ is_return = 1;
+ else if (argv[0][0] == '-')
+ is_delete = 1;
+ else {
+ pr_info("Probe definition must be started with 'p', 'r' or"
+ " '-'.\n");
+ return -EINVAL;
+ }
+
+ if (argv[0][1] == ':') {
+ event = &argv[0][2];
+ if (strchr(event, '/')) {
+ group = event;
+ event = strchr(group, '/') + 1;
+ event[-1] = '\0';
+ if (strlen(group) == 0) {
+ pr_info("Group name is not specifiled\n");
+ return -EINVAL;
+ }
+ }
+ if (strlen(event) == 0) {
+ pr_info("Event name is not specifiled\n");
+ return -EINVAL;
+ }
+ }
+ if (!group)
+ group = KPROBE_EVENT_SYSTEM;
+
+ if (is_delete) {
+ if (!event) {
+ pr_info("Delete command needs an event name.\n");
+ return -EINVAL;
+ }
+ tp = find_probe_event(event, group);
+ if (!tp) {
+ pr_info("Event %s/%s doesn't exist.\n", group, event);
+ return -ENOENT;
+ }
+ /* delete an event */
+ unregister_trace_probe(tp);
+ free_trace_probe(tp);
+ return 0;
+ }
+
+ if (argc < 2) {
+ pr_info("Probe point is not specified.\n");
+ return -EINVAL;
+ }
+ if (isdigit(argv[1][0])) {
+ if (is_return) {
+ pr_info("Return probe point must be a symbol.\n");
+ return -EINVAL;
+ }
+ /* an address specified */
+ ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr);
+ if (ret) {
+ pr_info("Failed to parse address.\n");
+ return ret;
+ }
+ } else {
+ /* a symbol specified */
+ symbol = argv[1];
+ /* TODO: support .init module functions */
+ ret = split_symbol_offset(symbol, &offset);
+ if (ret) {
+ pr_info("Failed to parse symbol.\n");
+ return ret;
+ }
+ if (offset && is_return) {
+ pr_info("Return probe must be used without offset.\n");
+ return -EINVAL;
+ }
+ }
+ argc -= 2; argv += 2;
+
+ /* setup a probe */
+ if (!event) {
+ /* Make a new event name */
+ if (symbol)
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld",
+ is_return ? 'r' : 'p', symbol, offset);
+ else
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p",
+ is_return ? 'r' : 'p', addr);
+ event = buf;
+ }
+ tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+ is_return);
+ if (IS_ERR(tp)) {
+ pr_info("Failed to allocate trace_probe.(%d)\n",
+ (int)PTR_ERR(tp));
+ return PTR_ERR(tp);
+ }
+
+ /* parse arguments */
+ ret = 0;
+ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ /* Parse argument name */
+ arg = strchr(argv[i], '=');
+ if (arg)
+ *arg++ = '\0';
+ else
+ arg = argv[i];
+
+ if (conflict_field_name(argv[i], tp->args, i)) {
+ pr_info("Argument%d name '%s' conflicts with "
+ "another field.\n", i, argv[i]);
+ ret = -EINVAL;
+ goto error;
+ }
+
+ tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ if (!tp->args[i].name) {
+ pr_info("Failed to allocate argument%d name '%s'.\n",
+ i, argv[i]);
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ /* Parse fetch argument */
+ ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+ if (ret) {
+ pr_info("Parse error at argument%d. (%d)\n", i, ret);
+ kfree(tp->args[i].name);
+ goto error;
+ }
+
+ tp->nr_args++;
+ }
+
+ ret = register_trace_probe(tp);
+ if (ret)
+ goto error;
+ return 0;
+
+error:
+ free_trace_probe(tp);
+ return ret;
+}
+
+static void cleanup_all_probes(void)
+{
+ struct trace_probe *tp;
+
+ mutex_lock(&probe_lock);
+ /* TODO: Use batch unregistration */
+ while (!list_empty(&probe_list)) {
+ tp = list_entry(probe_list.next, struct trace_probe, list);
+ unregister_trace_probe(tp);
+ free_trace_probe(tp);
+ }
+ mutex_unlock(&probe_lock);
+}
+
+
+/* Probes listing interfaces */
+static void *probes_seq_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&probe_lock);
+ return seq_list_start(&probe_list, *pos);
+}
+
+static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ return seq_list_next(v, &probe_list, pos);
+}
+
+static void probes_seq_stop(struct seq_file *m, void *v)
+{
+ mutex_unlock(&probe_lock);
+}
+
+static int probes_seq_show(struct seq_file *m, void *v)
+{
+ struct trace_probe *tp = v;
+ int i, ret;
+ char buf[MAX_ARGSTR_LEN + 1];
+
+ seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+ seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+
+ if (!tp->symbol)
+ seq_printf(m, " 0x%p", tp->rp.kp.addr);
+ else if (tp->rp.kp.offset)
+ seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+ else
+ seq_printf(m, " %s", probe_symbol(tp));
+
+ for (i = 0; i < tp->nr_args; i++) {
+ ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
+ if (ret < 0) {
+ pr_warning("Argument%d decoding error(%d).\n", i, ret);
+ return ret;
+ }
+ seq_printf(m, " %s=%s", tp->args[i].name, buf);
+ }
+ seq_printf(m, "\n");
+ return 0;
+}
+
+static const struct seq_operations probes_seq_op = {
+ .start = probes_seq_start,
+ .next = probes_seq_next,
+ .stop = probes_seq_stop,
+ .show = probes_seq_show
+};
+
+static int probes_open(struct inode *inode, struct file *file)
+{
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ cleanup_all_probes();
+
+ return seq_open(file, &probes_seq_op);
+}
+
+static int command_trace_probe(const char *buf)
+{
+ char **argv;
+ int argc = 0, ret = 0;
+
+ argv = argv_split(GFP_KERNEL, buf, &argc);
+ if (!argv)
+ return -ENOMEM;
+
+ if (argc)
+ ret = create_trace_probe(argc, argv);
+
+ argv_free(argv);
+ return ret;
+}
+
+#define WRITE_BUFSIZE 128
+
+static ssize_t probes_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ char *kbuf, *tmp;
+ int ret;
+ size_t done;
+ size_t size;
+
+ kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ ret = done = 0;
+ while (done < count) {
+ size = count - done;
+ if (size >= WRITE_BUFSIZE)
+ size = WRITE_BUFSIZE - 1;
+ if (copy_from_user(kbuf, buffer + done, size)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ kbuf[size] = '\0';
+ tmp = strchr(kbuf, '\n');
+ if (tmp) {
+ *tmp = '\0';
+ size = tmp - kbuf + 1;
+ } else if (done + size < count) {
+ pr_warning("Line length is too long: "
+ "Should be less than %d.", WRITE_BUFSIZE);
+ ret = -EINVAL;
+ goto out;
+ }
+ done += size;
+ /* Remove comments */
+ tmp = strchr(kbuf, '#');
+ if (tmp)
+ *tmp = '\0';
+
+ ret = command_trace_probe(kbuf);
+ if (ret)
+ goto out;
+ }
+ ret = done;
+out:
+ kfree(kbuf);
+ return ret;
+}
+
+static const struct file_operations kprobe_events_ops = {
+ .owner = THIS_MODULE,
+ .open = probes_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+ .write = probes_write,
+};
+
+/* Probes profiling interfaces */
+static int probes_profile_seq_show(struct seq_file *m, void *v)
+{
+ struct trace_probe *tp = v;
+
+ seq_printf(m, " %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
+ tp->rp.kp.nmissed);
+
+ return 0;
+}
+
+static const struct seq_operations profile_seq_op = {
+ .start = probes_seq_start,
+ .next = probes_seq_next,
+ .stop = probes_seq_stop,
+ .show = probes_profile_seq_show
+};
+
+static int profile_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &profile_seq_op);
+}
+
+static const struct file_operations kprobe_profile_ops = {
+ .owner = THIS_MODULE,
+ .open = profile_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+/* Kprobe handler */
+static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct kprobe_trace_entry *entry;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ int size, i, pc;
+ unsigned long irq_flags;
+ struct ftrace_event_call *call = &tp->call;
+
+ tp->nhit++;
+
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
+ size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+
+ event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+ irq_flags, pc);
+ if (!event)
+ return 0;
+
+ entry = ring_buffer_event_data(event);
+ entry->nargs = tp->nr_args;
+ entry->ip = (unsigned long)kp->addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ return 0;
+}
+
+/* Kretprobe handler */
+static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct kretprobe_trace_entry *entry;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ int size, i, pc;
+ unsigned long irq_flags;
+ struct ftrace_event_call *call = &tp->call;
+
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
+ size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+
+ event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+ irq_flags, pc);
+ if (!event)
+ return 0;
+
+ entry = ring_buffer_event_data(event);
+ entry->nargs = tp->nr_args;
+ entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->ret_ip = (unsigned long)ri->ret_addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+
+ return 0;
+}
+
+/* Event entry printers */
+enum print_line_t
+print_kprobe_event(struct trace_iterator *iter, int flags)
+{
+ struct kprobe_trace_entry *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_event *event;
+ struct trace_probe *tp;
+ int i;
+
+ field = (struct kprobe_trace_entry *)iter->ent;
+ event = ftrace_find_event(field->ent.type);
+ tp = container_of(event, struct trace_probe, event);
+
+ if (!trace_seq_printf(s, "%s: (", tp->call.name))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, ")"))
+ goto partial;
+
+ for (i = 0; i < field->nargs; i++)
+ if (!trace_seq_printf(s, " %s=%lx",
+ tp->args[i].name, field->args[i]))
+ goto partial;
+
+ if (!trace_seq_puts(s, "\n"))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+enum print_line_t
+print_kretprobe_event(struct trace_iterator *iter, int flags)
+{
+ struct kretprobe_trace_entry *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_event *event;
+ struct trace_probe *tp;
+ int i;
+
+ field = (struct kretprobe_trace_entry *)iter->ent;
+ event = ftrace_find_event(field->ent.type);
+ tp = container_of(event, struct trace_probe, event);
+
+ if (!trace_seq_printf(s, "%s: (", tp->call.name))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, " <- "))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, ")"))
+ goto partial;
+
+ for (i = 0; i < field->nargs; i++)
+ if (!trace_seq_printf(s, " %s=%lx",
+ tp->args[i].name, field->args[i]))
+ goto partial;
+
+ if (!trace_seq_puts(s, "\n"))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static int probe_event_enable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags |= TP_FLAG_TRACE;
+ if (probe_is_return(tp))
+ return enable_kretprobe(&tp->rp);
+ else
+ return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_event_disable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags &= ~TP_FLAG_TRACE;
+ if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
+ if (probe_is_return(tp))
+ disable_kretprobe(&tp->rp);
+ else
+ disable_kprobe(&tp->rp.kp);
+ }
+}
+
+static int probe_event_raw_init(struct ftrace_event_call *event_call)
+{
+ INIT_LIST_HEAD(&event_call->fields);
+
+ return 0;
+}
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed) \
+ do { \
+ ret = trace_define_field(event_call, #type, name, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed, \
+ FILTER_OTHER); \
+ if (ret) \
+ return ret; \
+ } while (0)
+
+static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+ int ret, i;
+ struct kprobe_trace_entry field;
+ struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+ DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++)
+ DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ return 0;
+}
+
+static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+ int ret, i;
+ struct kretprobe_trace_entry field;
+ struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+ DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+ DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++)
+ DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ return 0;
+}
+
+static int __probe_event_show_format(struct trace_seq *s,
+ struct trace_probe *tp, const char *fmt,
+ const char *arg)
+{
+ int i;
+
+ /* Show format */
+ if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
+ return 0;
+
+ for (i = 0; i < tp->nr_args; i++)
+ if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
+ return 0;
+
+ if (!trace_seq_printf(s, "\", %s", arg))
+ return 0;
+
+ for (i = 0; i < tp->nr_args; i++)
+ if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
+ return 0;
+
+ return trace_seq_puts(s, "\n");
+}
+
+#undef SHOW_FIELD
+#define SHOW_FIELD(type, item, name) \
+ do { \
+ ret = trace_seq_printf(s, "\tfield:" #type " %s;\t" \
+ "offset:%u;\tsize:%u;\tsigned:%d;\n", name,\
+ (unsigned int)offsetof(typeof(field), item),\
+ (unsigned int)sizeof(type), \
+ is_signed_type(type)); \
+ if (!ret) \
+ return 0; \
+ } while (0)
+
+static int kprobe_event_show_format(struct ftrace_event_call *call,
+ struct trace_seq *s)
+{
+ struct kprobe_trace_entry field __attribute__((unused));
+ int ret, i;
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
+ SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+ /* Show fields */
+ for (i = 0; i < tp->nr_args; i++)
+ SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+ trace_seq_puts(s, "\n");
+
+ return __probe_event_show_format(s, tp, "(%lx)",
+ "REC->" FIELD_STRING_IP);
+}
+
+static int kretprobe_event_show_format(struct ftrace_event_call *call,
+ struct trace_seq *s)
+{
+ struct kretprobe_trace_entry field __attribute__((unused));
+ int ret, i;
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
+ SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
+ SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+ /* Show fields */
+ for (i = 0; i < tp->nr_args; i++)
+ SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+ trace_seq_puts(s, "\n");
+
+ return __probe_event_show_format(s, tp, "(%lx <- %lx)",
+ "REC->" FIELD_STRING_FUNC
+ ", REC->" FIELD_STRING_RETIP);
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+/* Kprobe profile handler */
+static __kprobes int kprobe_profile_func(struct kprobe *kp,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct ftrace_event_call *call = &tp->call;
+ struct kprobe_trace_entry *entry;
+ struct trace_entry *ent;
+ int size, __size, i, pc, __cpu;
+ unsigned long irq_flags;
+ char *trace_buf;
+ char *raw_data;
+ int rctx;
+
+ pc = preempt_count();
+ __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ "profile buffer not large enough"))
+ return 0;
+
+ /*
+ * Protect the non nmi buffer
+ * This also protects the rcu read side
+ */
+ local_irq_save(irq_flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
+ __cpu = smp_processor_id();
+
+ if (in_nmi())
+ trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ else
+ trace_buf = rcu_dereference(perf_trace_buf);
+
+ if (!trace_buf)
+ goto end;
+
+ raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+ /* Zero dead bytes from alignment to avoid buffer leak to userspace */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+ entry = (struct kprobe_trace_entry *)raw_data;
+ ent = &entry->ent;
+
+ tracing_generic_entry_update(ent, irq_flags, pc);
+ ent->type = call->id;
+ entry->nargs = tp->nr_args;
+ entry->ip = (unsigned long)kp->addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+ perf_tp_event(call->id, entry->ip, 1, entry, size);
+
+end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
+ local_irq_restore(irq_flags);
+
+ return 0;
+}
+
+/* Kretprobe profile handler */
+static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct ftrace_event_call *call = &tp->call;
+ struct kretprobe_trace_entry *entry;
+ struct trace_entry *ent;
+ int size, __size, i, pc, __cpu;
+ unsigned long irq_flags;
+ char *trace_buf;
+ char *raw_data;
+ int rctx;
+
+ pc = preempt_count();
+ __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ "profile buffer not large enough"))
+ return 0;
+
+ /*
+ * Protect the non nmi buffer
+ * This also protects the rcu read side
+ */
+ local_irq_save(irq_flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
+ __cpu = smp_processor_id();
+
+ if (in_nmi())
+ trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ else
+ trace_buf = rcu_dereference(perf_trace_buf);
+
+ if (!trace_buf)
+ goto end;
+
+ raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+ /* Zero dead bytes from alignment to avoid buffer leak to userspace */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+ entry = (struct kretprobe_trace_entry *)raw_data;
+ ent = &entry->ent;
+
+ tracing_generic_entry_update(ent, irq_flags, pc);
+ ent->type = call->id;
+ entry->nargs = tp->nr_args;
+ entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->ret_ip = (unsigned long)ri->ret_addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+ perf_tp_event(call->id, entry->ret_ip, 1, entry, size);
+
+end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
+ local_irq_restore(irq_flags);
+
+ return 0;
+}
+
+static int probe_profile_enable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags |= TP_FLAG_PROFILE;
+
+ if (probe_is_return(tp))
+ return enable_kretprobe(&tp->rp);
+ else
+ return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_profile_disable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags &= ~TP_FLAG_PROFILE;
+
+ if (!(tp->flags & TP_FLAG_TRACE)) {
+ if (probe_is_return(tp))
+ disable_kretprobe(&tp->rp);
+ else
+ disable_kprobe(&tp->rp.kp);
+ }
+}
+#endif /* CONFIG_EVENT_PROFILE */
+
+
+static __kprobes
+int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+
+ if (tp->flags & TP_FLAG_TRACE)
+ kprobe_trace_func(kp, regs);
+#ifdef CONFIG_EVENT_PROFILE
+ if (tp->flags & TP_FLAG_PROFILE)
+ kprobe_profile_func(kp, regs);
+#endif /* CONFIG_EVENT_PROFILE */
+ return 0; /* We don't tweek kernel, so just return 0 */
+}
+
+static __kprobes
+int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+
+ if (tp->flags & TP_FLAG_TRACE)
+ kretprobe_trace_func(ri, regs);
+#ifdef CONFIG_EVENT_PROFILE
+ if (tp->flags & TP_FLAG_PROFILE)
+ kretprobe_profile_func(ri, regs);
+#endif /* CONFIG_EVENT_PROFILE */
+ return 0; /* We don't tweek kernel, so just return 0 */
+}
+
+static int register_probe_event(struct trace_probe *tp)
+{
+ struct ftrace_event_call *call = &tp->call;
+ int ret;
+
+ /* Initialize ftrace_event_call */
+ if (probe_is_return(tp)) {
+ tp->event.trace = print_kretprobe_event;
+ call->raw_init = probe_event_raw_init;
+ call->show_format = kretprobe_event_show_format;
+ call->define_fields = kretprobe_event_define_fields;
+ } else {
+ tp->event.trace = print_kprobe_event;
+ call->raw_init = probe_event_raw_init;
+ call->show_format = kprobe_event_show_format;
+ call->define_fields = kprobe_event_define_fields;
+ }
+ call->event = &tp->event;
+ call->id = register_ftrace_event(&tp->event);
+ if (!call->id)
+ return -ENODEV;
+ call->enabled = 0;
+ call->regfunc = probe_event_enable;
+ call->unregfunc = probe_event_disable;
+
+#ifdef CONFIG_EVENT_PROFILE
+ call->profile_enable = probe_profile_enable;
+ call->profile_disable = probe_profile_disable;
+#endif
+ call->data = tp;
+ ret = trace_add_event_call(call);
+ if (ret) {
+ pr_info("Failed to register kprobe event: %s\n", call->name);
+ unregister_ftrace_event(&tp->event);
+ }
+ return ret;
+}
+
+static void unregister_probe_event(struct trace_probe *tp)
+{
+ /* tp->event is unregistered in trace_remove_event_call() */
+ trace_remove_event_call(&tp->call);
+}
+
+/* Make a debugfs interface for controling probe points */
+static __init int init_kprobe_trace(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+ NULL, &kprobe_events_ops);
+
+ /* Event list interface */
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'kprobe_events' entry\n");
+
+ /* Profile interface */
+ entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+ NULL, &kprobe_profile_ops);
+
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'kprobe_profile' entry\n");
+ return 0;
+}
+fs_initcall(init_kprobe_trace);
+
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static int kprobe_trace_selftest_target(int a1, int a2, int a3,
+ int a4, int a5, int a6)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6;
+}
+
+static __init int kprobe_trace_self_tests_init(void)
+{
+ int ret;
+ int (*target)(int, int, int, int, int, int);
+
+ target = kprobe_trace_selftest_target;
+
+ pr_info("Testing kprobe tracing: ");
+
+ ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
+ "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error enabling function entry\n");
+
+ ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
+ "$retval");
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error enabling function return\n");
+
+ ret = target(1, 2, 3, 4, 5, 6);
+
+ cleanup_all_probes();
+
+ pr_cont("OK\n");
+ return 0;
+}
+
+late_initcall(kprobe_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
new file mode 100644
index 00000000000..94103cdcf9d
--- /dev/null
+++ b/kernel/trace/trace_ksym.c
@@ -0,0 +1,519 @@
+/*
+ * trace_ksym.c - Kernel Symbol Tracer
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+#include <linux/hw_breakpoint.h>
+#include <asm/hw_breakpoint.h>
+
+#include <asm/atomic.h>
+
+/*
+ * For now, let us restrict the no. of symbols traced simultaneously to number
+ * of available hardware breakpoint registers.
+ */
+#define KSYM_TRACER_MAX HBP_NUM
+
+#define KSYM_TRACER_OP_LEN 3 /* rw- */
+
+struct trace_ksym {
+ struct perf_event **ksym_hbp;
+ struct perf_event_attr attr;
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ atomic64_t counter;
+#endif
+ struct hlist_node ksym_hlist;
+};
+
+static struct trace_array *ksym_trace_array;
+
+static unsigned int ksym_filter_entry_count;
+static unsigned int ksym_tracing_enabled;
+
+static HLIST_HEAD(ksym_filter_head);
+
+static DEFINE_MUTEX(ksym_tracer_mutex);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+
+#define MAX_UL_INT 0xffffffff
+
+void ksym_collect_stats(unsigned long hbp_hit_addr)
+{
+ struct hlist_node *node;
+ struct trace_ksym *entry;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+ if (entry->attr.bp_addr == hbp_hit_addr) {
+ atomic64_inc(&entry->counter);
+ break;
+ }
+ }
+ rcu_read_unlock();
+}
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+void ksym_hbp_handler(struct perf_event *hbp, int nmi,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct ring_buffer_event *event;
+ struct ksym_trace_entry *entry;
+ struct ring_buffer *buffer;
+ int pc;
+
+ if (!ksym_tracing_enabled)
+ return;
+
+ buffer = ksym_trace_array->buffer;
+
+ pc = preempt_count();
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_KSYM,
+ sizeof(*entry), 0, pc);
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = instruction_pointer(regs);
+ entry->type = hw_breakpoint_type(hbp);
+ entry->addr = hw_breakpoint_addr(hbp);
+ strlcpy(entry->cmd, current->comm, TASK_COMM_LEN);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ ksym_collect_stats(hw_breakpoint_addr(hbp));
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+/* Valid access types are represented as
+ *
+ * rw- : Set Read/Write Access Breakpoint
+ * -w- : Set Write Access Breakpoint
+ * --- : Clear Breakpoints
+ * --x : Set Execution Break points (Not available yet)
+ *
+ */
+static int ksym_trace_get_access_type(char *str)
+{
+ int access = 0;
+
+ if (str[0] == 'r')
+ access |= HW_BREAKPOINT_R;
+
+ if (str[1] == 'w')
+ access |= HW_BREAKPOINT_W;
+
+ if (str[2] == 'x')
+ access |= HW_BREAKPOINT_X;
+
+ switch (access) {
+ case HW_BREAKPOINT_R:
+ case HW_BREAKPOINT_W:
+ case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+ return access;
+ default:
+ return -EINVAL;
+ }
+}
+
+/*
+ * There can be several possible malformed requests and we attempt to capture
+ * all of them. We enumerate some of the rules
+ * 1. We will not allow kernel symbols with ':' since it is used as a delimiter.
+ * i.e. multiple ':' symbols disallowed. Possible uses are of the form
+ * <module>:<ksym_name>:<op>.
+ * 2. No delimiter symbol ':' in the input string
+ * 3. Spurious operator symbols or symbols not in their respective positions
+ * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file
+ * 5. Kernel symbol not a part of /proc/kallsyms
+ * 6. Duplicate requests
+ */
+static int parse_ksym_trace_str(char *input_string, char **ksymname,
+ unsigned long *addr)
+{
+ int ret;
+
+ *ksymname = strsep(&input_string, ":");
+ *addr = kallsyms_lookup_name(*ksymname);
+
+ /* Check for malformed request: (2), (1) and (5) */
+ if ((!input_string) ||
+ (strlen(input_string) != KSYM_TRACER_OP_LEN) ||
+ (*addr == 0))
+ return -EINVAL;;
+
+ ret = ksym_trace_get_access_type(input_string);
+
+ return ret;
+}
+
+int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
+{
+ struct trace_ksym *entry;
+ int ret = -ENOMEM;
+
+ if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
+ printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
+ " new requests for tracing can be accepted now.\n",
+ KSYM_TRACER_MAX);
+ return -ENOSPC;
+ }
+
+ entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ hw_breakpoint_init(&entry->attr);
+
+ entry->attr.bp_type = op;
+ entry->attr.bp_addr = addr;
+ entry->attr.bp_len = HW_BREAKPOINT_LEN_4;
+
+ entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr,
+ ksym_hbp_handler);
+
+ if (IS_ERR(entry->ksym_hbp)) {
+ ret = PTR_ERR(entry->ksym_hbp);
+ printk(KERN_INFO "ksym_tracer request failed. Try again"
+ " later!!\n");
+ goto err;
+ }
+
+ hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
+ ksym_filter_entry_count++;
+
+ return 0;
+
+err:
+ kfree(entry);
+
+ return ret;
+}
+
+static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node;
+ struct trace_seq *s;
+ ssize_t cnt = 0;
+ int ret;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+ trace_seq_init(s);
+
+ mutex_lock(&ksym_tracer_mutex);
+
+ hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+ ret = trace_seq_printf(s, "%pS:",
+ (void *)(unsigned long)entry->attr.bp_addr);
+ if (entry->attr.bp_type == HW_BREAKPOINT_R)
+ ret = trace_seq_puts(s, "r--\n");
+ else if (entry->attr.bp_type == HW_BREAKPOINT_W)
+ ret = trace_seq_puts(s, "-w-\n");
+ else if (entry->attr.bp_type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R))
+ ret = trace_seq_puts(s, "rw-\n");
+ WARN_ON_ONCE(!ret);
+ }
+
+ cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+ mutex_unlock(&ksym_tracer_mutex);
+
+ kfree(s);
+
+ return cnt;
+}
+
+static void __ksym_trace_reset(void)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node, *node1;
+
+ mutex_lock(&ksym_tracer_mutex);
+ hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
+ ksym_hlist) {
+ unregister_wide_hw_breakpoint(entry->ksym_hbp);
+ ksym_filter_entry_count--;
+ hlist_del_rcu(&(entry->ksym_hlist));
+ synchronize_rcu();
+ kfree(entry);
+ }
+ mutex_unlock(&ksym_tracer_mutex);
+}
+
+static ssize_t ksym_trace_filter_write(struct file *file,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node;
+ char *buf, *input_string, *ksymname = NULL;
+ unsigned long ksym_addr = 0;
+ int ret, op, changed = 0;
+
+ buf = kzalloc(count + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = -EFAULT;
+ if (copy_from_user(buf, buffer, count))
+ goto out;
+
+ buf[count] = '\0';
+ input_string = strstrip(buf);
+
+ /*
+ * Clear all breakpoints if:
+ * 1: echo > ksym_trace_filter
+ * 2: echo 0 > ksym_trace_filter
+ * 3: echo "*:---" > ksym_trace_filter
+ */
+ if (!input_string[0] || !strcmp(input_string, "0") ||
+ !strcmp(input_string, "*:---")) {
+ __ksym_trace_reset();
+ ret = 0;
+ goto out;
+ }
+
+ ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
+ if (ret < 0)
+ goto out;
+
+ mutex_lock(&ksym_tracer_mutex);
+
+ ret = -EINVAL;
+ hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+ if (entry->attr.bp_addr == ksym_addr) {
+ /* Check for malformed request: (6) */
+ if (entry->attr.bp_type != op)
+ changed = 1;
+ else
+ goto out_unlock;
+ break;
+ }
+ }
+ if (changed) {
+ unregister_wide_hw_breakpoint(entry->ksym_hbp);
+ entry->attr.bp_type = op;
+ ret = 0;
+ if (op > 0) {
+ entry->ksym_hbp =
+ register_wide_hw_breakpoint(&entry->attr,
+ ksym_hbp_handler);
+ if (IS_ERR(entry->ksym_hbp))
+ ret = PTR_ERR(entry->ksym_hbp);
+ else
+ goto out_unlock;
+ }
+ /* Error or "symbol:---" case: drop it */
+ ksym_filter_entry_count--;
+ hlist_del_rcu(&(entry->ksym_hlist));
+ synchronize_rcu();
+ kfree(entry);
+ goto out_unlock;
+ } else {
+ /* Check for malformed request: (4) */
+ if (op)
+ ret = process_new_ksym_entry(ksymname, op, ksym_addr);
+ }
+out_unlock:
+ mutex_unlock(&ksym_tracer_mutex);
+out:
+ kfree(buf);
+ return !ret ? count : ret;
+}
+
+static const struct file_operations ksym_tracing_fops = {
+ .open = tracing_open_generic,
+ .read = ksym_trace_filter_read,
+ .write = ksym_trace_filter_write,
+};
+
+static void ksym_trace_reset(struct trace_array *tr)
+{
+ ksym_tracing_enabled = 0;
+ __ksym_trace_reset();
+}
+
+static int ksym_trace_init(struct trace_array *tr)
+{
+ int cpu, ret = 0;
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr, cpu);
+ ksym_tracing_enabled = 1;
+ ksym_trace_array = tr;
+
+ return ret;
+}
+
+static void ksym_trace_print_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "# TASK-PID CPU# Symbol "
+ "Type Function\n");
+ seq_puts(m,
+ "# | | | "
+ " | |\n");
+}
+
+static enum print_line_t ksym_trace_output(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct ksym_trace_entry *field;
+ char str[KSYM_SYMBOL_LEN];
+ int ret;
+
+ if (entry->type != TRACE_KSYM)
+ return TRACE_TYPE_UNHANDLED;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd,
+ entry->pid, iter->cpu, (char *)field->addr);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ switch (field->type) {
+ case HW_BREAKPOINT_R:
+ ret = trace_seq_printf(s, " R ");
+ break;
+ case HW_BREAKPOINT_W:
+ ret = trace_seq_printf(s, " W ");
+ break;
+ case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+ ret = trace_seq_printf(s, " RW ");
+ break;
+ default:
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ sprint_symbol(str, field->ip);
+ ret = trace_seq_printf(s, "%s\n", str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+struct tracer ksym_tracer __read_mostly =
+{
+ .name = "ksym_tracer",
+ .init = ksym_trace_init,
+ .reset = ksym_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_ksym,
+#endif
+ .print_header = ksym_trace_print_header,
+ .print_line = ksym_trace_output
+};
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+static int ksym_profile_show(struct seq_file *m, void *v)
+{
+ struct hlist_node *node;
+ struct trace_ksym *entry;
+ int access_type = 0;
+ char fn_name[KSYM_NAME_LEN];
+
+ seq_puts(m, " Access Type ");
+ seq_puts(m, " Symbol Counter\n");
+ seq_puts(m, " ----------- ");
+ seq_puts(m, " ------ -------\n");
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+
+ access_type = entry->attr.bp_type;
+
+ switch (access_type) {
+ case HW_BREAKPOINT_R:
+ seq_puts(m, " R ");
+ break;
+ case HW_BREAKPOINT_W:
+ seq_puts(m, " W ");
+ break;
+ case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+ seq_puts(m, " RW ");
+ break;
+ default:
+ seq_puts(m, " NA ");
+ }
+
+ if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0)
+ seq_printf(m, " %-36s", fn_name);
+ else
+ seq_printf(m, " %-36s", "<NA>");
+ seq_printf(m, " %15llu\n",
+ (unsigned long long)atomic64_read(&entry->counter));
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int ksym_profile_open(struct inode *node, struct file *file)
+{
+ return single_open(file, ksym_profile_show, NULL);
+}
+
+static const struct file_operations ksym_profile_fops = {
+ .open = ksym_profile_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+__init static int init_ksym_trace(void)
+{
+ struct dentry *d_tracer;
+
+ d_tracer = tracing_init_dentry();
+
+ trace_create_file("ksym_trace_filter", 0644, d_tracer,
+ NULL, &ksym_tracing_fops);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ trace_create_file("ksym_profile", 0444, d_tracer,
+ NULL, &ksym_profile_fops);
+#endif
+
+ return register_tracer(&ksym_tracer);
+}
+device_initcall(init_ksym_trace);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
new file mode 100644
index 00000000000..0acd834659e
--- /dev/null
+++ b/kernel/trace/trace_mmiotrace.c
@@ -0,0 +1,373 @@
+/*
+ * Memory mapped I/O tracing
+ *
+ * Copyright (C) 2008 Pekka Paalanen <pq@iki.fi>
+ */
+
+#define DEBUG 1
+
+#include <linux/kernel.h>
+#include <linux/mmiotrace.h>
+#include <linux/pci.h>
+#include <linux/time.h>
+
+#include <asm/atomic.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+struct header_iter {
+ struct pci_dev *dev;
+};
+
+static struct trace_array *mmio_trace_array;
+static bool overrun_detected;
+static unsigned long prev_overruns;
+static atomic_t dropped_count;
+
+static void mmio_reset_data(struct trace_array *tr)
+{
+ overrun_detected = false;
+ prev_overruns = 0;
+
+ tracing_reset_online_cpus(tr);
+}
+
+static int mmio_trace_init(struct trace_array *tr)
+{
+ pr_debug("in %s\n", __func__);
+ mmio_trace_array = tr;
+
+ mmio_reset_data(tr);
+ enable_mmiotrace();
+ return 0;
+}
+
+static void mmio_trace_reset(struct trace_array *tr)
+{
+ pr_debug("in %s\n", __func__);
+
+ disable_mmiotrace();
+ mmio_reset_data(tr);
+ mmio_trace_array = NULL;
+}
+
+static void mmio_trace_start(struct trace_array *tr)
+{
+ pr_debug("in %s\n", __func__);
+ mmio_reset_data(tr);
+}
+
+static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
+{
+ int ret = 0;
+ int i;
+ resource_size_t start, end;
+ const struct pci_driver *drv = pci_dev_driver(dev);
+
+ /* XXX: incomplete checks for trace_seq_printf() return value */
+ ret += trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
+ dev->bus->number, dev->devfn,
+ dev->vendor, dev->device, dev->irq);
+ /*
+ * XXX: is pci_resource_to_user() appropriate, since we are
+ * supposed to interpret the __ioremap() phys_addr argument based on
+ * these printed values?
+ */
+ for (i = 0; i < 7; i++) {
+ pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+ ret += trace_seq_printf(s, " %llx",
+ (unsigned long long)(start |
+ (dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
+ }
+ for (i = 0; i < 7; i++) {
+ pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+ ret += trace_seq_printf(s, " %llx",
+ dev->resource[i].start < dev->resource[i].end ?
+ (unsigned long long)(end - start) + 1 : 0);
+ }
+ if (drv)
+ ret += trace_seq_printf(s, " %s\n", drv->name);
+ else
+ ret += trace_seq_printf(s, " \n");
+ return ret;
+}
+
+static void destroy_header_iter(struct header_iter *hiter)
+{
+ if (!hiter)
+ return;
+ pci_dev_put(hiter->dev);
+ kfree(hiter);
+}
+
+static void mmio_pipe_open(struct trace_iterator *iter)
+{
+ struct header_iter *hiter;
+ struct trace_seq *s = &iter->seq;
+
+ trace_seq_printf(s, "VERSION 20070824\n");
+
+ hiter = kzalloc(sizeof(*hiter), GFP_KERNEL);
+ if (!hiter)
+ return;
+
+ hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL);
+ iter->private = hiter;
+}
+
+/* XXX: This is not called when the pipe is closed! */
+static void mmio_close(struct trace_iterator *iter)
+{
+ struct header_iter *hiter = iter->private;
+ destroy_header_iter(hiter);
+ iter->private = NULL;
+}
+
+static unsigned long count_overruns(struct trace_iterator *iter)
+{
+ unsigned long cnt = atomic_xchg(&dropped_count, 0);
+ unsigned long over = ring_buffer_overruns(iter->tr->buffer);
+
+ if (over > prev_overruns)
+ cnt += over - prev_overruns;
+ prev_overruns = over;
+ return cnt;
+}
+
+static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
+ char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ ssize_t ret;
+ struct header_iter *hiter = iter->private;
+ struct trace_seq *s = &iter->seq;
+ unsigned long n;
+
+ n = count_overruns(iter);
+ if (n) {
+ /* XXX: This is later than where events were lost. */
+ trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
+ if (!overrun_detected)
+ pr_warning("mmiotrace has lost events.\n");
+ overrun_detected = true;
+ goto print_out;
+ }
+
+ if (!hiter)
+ return 0;
+
+ mmio_print_pcidev(s, hiter->dev);
+ hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, hiter->dev);
+
+ if (!hiter->dev) {
+ destroy_header_iter(hiter);
+ iter->private = NULL;
+ }
+
+print_out:
+ ret = trace_seq_to_user(s, ubuf, cnt);
+ return (ret == -EBUSY) ? 0 : ret;
+}
+
+static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_mmiotrace_rw *field;
+ struct mmiotrace_rw *rw;
+ struct trace_seq *s = &iter->seq;
+ unsigned long long t = ns2usecs(iter->ts);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
+ unsigned secs = (unsigned long)t;
+ int ret = 1;
+
+ trace_assign_type(field, entry);
+ rw = &field->rw;
+
+ switch (rw->opcode) {
+ case MMIO_READ:
+ ret = trace_seq_printf(s,
+ "R %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
+ rw->width, secs, usec_rem, rw->map_id,
+ (unsigned long long)rw->phys,
+ rw->value, rw->pc, 0);
+ break;
+ case MMIO_WRITE:
+ ret = trace_seq_printf(s,
+ "W %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
+ rw->width, secs, usec_rem, rw->map_id,
+ (unsigned long long)rw->phys,
+ rw->value, rw->pc, 0);
+ break;
+ case MMIO_UNKNOWN_OP:
+ ret = trace_seq_printf(s,
+ "UNKNOWN %u.%06lu %d 0x%llx %02lx,%02lx,"
+ "%02lx 0x%lx %d\n",
+ secs, usec_rem, rw->map_id,
+ (unsigned long long)rw->phys,
+ (rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff,
+ (rw->value >> 0) & 0xff, rw->pc, 0);
+ break;
+ default:
+ ret = trace_seq_printf(s, "rw what?\n");
+ break;
+ }
+ if (ret)
+ return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t mmio_print_map(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_mmiotrace_map *field;
+ struct mmiotrace_map *m;
+ struct trace_seq *s = &iter->seq;
+ unsigned long long t = ns2usecs(iter->ts);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
+ unsigned secs = (unsigned long)t;
+ int ret;
+
+ trace_assign_type(field, entry);
+ m = &field->map;
+
+ switch (m->opcode) {
+ case MMIO_PROBE:
+ ret = trace_seq_printf(s,
+ "MAP %u.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n",
+ secs, usec_rem, m->map_id,
+ (unsigned long long)m->phys, m->virt, m->len,
+ 0UL, 0);
+ break;
+ case MMIO_UNPROBE:
+ ret = trace_seq_printf(s,
+ "UNMAP %u.%06lu %d 0x%lx %d\n",
+ secs, usec_rem, m->map_id, 0UL, 0);
+ break;
+ default:
+ ret = trace_seq_printf(s, "map what?\n");
+ break;
+ }
+ if (ret)
+ return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t mmio_print_mark(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct print_entry *print = (struct print_entry *)entry;
+ const char *msg = print->buf;
+ struct trace_seq *s = &iter->seq;
+ unsigned long long t = ns2usecs(iter->ts);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
+ unsigned secs = (unsigned long)t;
+ int ret;
+
+ /* The trailing newline must be in the message. */
+ ret = trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t mmio_print_line(struct trace_iterator *iter)
+{
+ switch (iter->ent->type) {
+ case TRACE_MMIO_RW:
+ return mmio_print_rw(iter);
+ case TRACE_MMIO_MAP:
+ return mmio_print_map(iter);
+ case TRACE_PRINT:
+ return mmio_print_mark(iter);
+ default:
+ return TRACE_TYPE_HANDLED; /* ignore unknown entries */
+ }
+}
+
+static struct tracer mmio_tracer __read_mostly =
+{
+ .name = "mmiotrace",
+ .init = mmio_trace_init,
+ .reset = mmio_trace_reset,
+ .start = mmio_trace_start,
+ .pipe_open = mmio_pipe_open,
+ .close = mmio_close,
+ .read = mmio_read,
+ .print_line = mmio_print_line,
+};
+
+__init static int init_mmio_trace(void)
+{
+ return register_tracer(&mmio_tracer);
+}
+device_initcall(init_mmio_trace);
+
+static void __trace_mmiotrace_rw(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ struct mmiotrace_rw *rw)
+{
+ struct ftrace_event_call *call = &event_mmiotrace_rw;
+ struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer_event *event;
+ struct trace_mmiotrace_rw *entry;
+ int pc = preempt_count();
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
+ sizeof(*entry), 0, pc);
+ if (!event) {
+ atomic_inc(&dropped_count);
+ return;
+ }
+ entry = ring_buffer_event_data(event);
+ entry->rw = *rw;
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+void mmio_trace_rw(struct mmiotrace_rw *rw)
+{
+ struct trace_array *tr = mmio_trace_array;
+ struct trace_array_cpu *data = tr->data[smp_processor_id()];
+ __trace_mmiotrace_rw(tr, data, rw);
+}
+
+static void __trace_mmiotrace_map(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ struct mmiotrace_map *map)
+{
+ struct ftrace_event_call *call = &event_mmiotrace_map;
+ struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer_event *event;
+ struct trace_mmiotrace_map *entry;
+ int pc = preempt_count();
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
+ sizeof(*entry), 0, pc);
+ if (!event) {
+ atomic_inc(&dropped_count);
+ return;
+ }
+ entry = ring_buffer_event_data(event);
+ entry->map = *map;
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+void mmio_trace_mapping(struct mmiotrace_map *map)
+{
+ struct trace_array *tr = mmio_trace_array;
+ struct trace_array_cpu *data;
+
+ preempt_disable();
+ data = tr->data[smp_processor_id()];
+ __trace_mmiotrace_map(tr, data, map);
+ preempt_enable();
+}
+
+int mmio_trace_printk(const char *fmt, va_list args)
+{
+ return trace_vprintk(0, fmt, args);
+}
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
new file mode 100644
index 00000000000..394f94417e2
--- /dev/null
+++ b/kernel/trace/trace_nop.c
@@ -0,0 +1,101 @@
+/*
+ * nop tracer
+ *
+ * Copyright (C) 2008 Steven Noonan <steven@uplinklabs.net>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+
+/* Our two options */
+enum {
+ TRACE_NOP_OPT_ACCEPT = 0x1,
+ TRACE_NOP_OPT_REFUSE = 0x2
+};
+
+/* Options for the tracer (see trace_options file) */
+static struct tracer_opt nop_opts[] = {
+ /* Option that will be accepted by set_flag callback */
+ { TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) },
+ /* Option that will be refused by set_flag callback */
+ { TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) },
+ { } /* Always set a last empty entry */
+};
+
+static struct tracer_flags nop_flags = {
+ /* You can check your flags value here when you want. */
+ .val = 0, /* By default: all flags disabled */
+ .opts = nop_opts
+};
+
+static struct trace_array *ctx_trace;
+
+static void start_nop_trace(struct trace_array *tr)
+{
+ /* Nothing to do! */
+}
+
+static void stop_nop_trace(struct trace_array *tr)
+{
+ /* Nothing to do! */
+}
+
+static int nop_trace_init(struct trace_array *tr)
+{
+ ctx_trace = tr;
+ start_nop_trace(tr);
+ return 0;
+}
+
+static void nop_trace_reset(struct trace_array *tr)
+{
+ stop_nop_trace(tr);
+}
+
+/* It only serves as a signal handler and a callback to
+ * accept or refuse tthe setting of a flag.
+ * If you don't implement it, then the flag setting will be
+ * automatically accepted.
+ */
+static int nop_set_flag(u32 old_flags, u32 bit, int set)
+{
+ /*
+ * Note that you don't need to update nop_flags.val yourself.
+ * The tracing Api will do it automatically if you return 0
+ */
+ if (bit == TRACE_NOP_OPT_ACCEPT) {
+ printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept."
+ " Now cat trace_options to see the result\n",
+ set);
+ return 0;
+ }
+
+ if (bit == TRACE_NOP_OPT_REFUSE) {
+ printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
+ "Now cat trace_options to see the result\n",
+ set);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+
+struct tracer nop_trace __read_mostly =
+{
+ .name = "nop",
+ .init = nop_trace_init,
+ .reset = nop_trace_reset,
+ .wait_pipe = poll_wait_pipe,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_nop,
+#endif
+ .flags = &nop_flags,
+ .set_flag = nop_set_flag
+};
+
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
new file mode 100644
index 00000000000..8e46b3323cd
--- /dev/null
+++ b/kernel/trace/trace_output.c
@@ -0,0 +1,1280 @@
+/*
+ * trace_output.c
+ *
+ * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/ftrace.h>
+
+#include "trace_output.h"
+
+/* must be a power of 2 */
+#define EVENT_HASHSIZE 128
+
+DECLARE_RWSEM(trace_event_mutex);
+
+DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq);
+EXPORT_PER_CPU_SYMBOL(ftrace_event_seq);
+
+static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
+
+static int next_event_type = __TRACE_LAST_TYPE + 1;
+
+int trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+ int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+ int ret;
+
+ ret = seq_write(m, s->buffer, len);
+
+ /*
+ * Only reset this buffer if we successfully wrote to the
+ * seq_file buffer.
+ */
+ if (!ret)
+ trace_seq_init(s);
+
+ return ret;
+}
+
+enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct bprint_entry *field;
+ int ret;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_bprintf(s, field->fmt, field->buf);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct print_entry *field;
+ int ret;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_printf(s, "%s", field->buf);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, 1 otherwise.
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+ int len = (PAGE_SIZE - 1) - s->len;
+ va_list ap;
+ int ret;
+
+ if (s->full || !len)
+ return 0;
+
+ va_start(ap, fmt);
+ ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
+ va_end(ap);
+
+ /* If we can't write it all, don't bother writing anything */
+ if (ret >= len) {
+ s->full = 1;
+ return 0;
+ }
+
+ s->len += ret;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(trace_seq_printf);
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+ int len = (PAGE_SIZE - 1) - s->len;
+ int ret;
+
+ if (s->full || !len)
+ return 0;
+
+ ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+
+ /* If we can't write it all, don't bother writing anything */
+ if (ret >= len) {
+ s->full = 1;
+ return 0;
+ }
+
+ s->len += ret;
+
+ return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_vprintf);
+
+int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+ int len = (PAGE_SIZE - 1) - s->len;
+ int ret;
+
+ if (s->full || !len)
+ return 0;
+
+ ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
+
+ /* If we can't write it all, don't bother writing anything */
+ if (ret >= len) {
+ s->full = 1;
+ return 0;
+ }
+
+ s->len += ret;
+
+ return len;
+}
+
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
+int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+ int len = strlen(str);
+
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
+ return 0;
+ }
+
+ memcpy(s->buffer + s->len, str, len);
+ s->len += len;
+
+ return len;
+}
+
+int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+ if (s->full)
+ return 0;
+
+ if (s->len >= (PAGE_SIZE - 1)) {
+ s->full = 1;
+ return 0;
+ }
+
+ s->buffer[s->len++] = c;
+
+ return 1;
+}
+
+int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+{
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
+ return 0;
+ }
+
+ memcpy(s->buffer + s->len, mem, len);
+ s->len += len;
+
+ return len;
+}
+
+int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
+{
+ unsigned char hex[HEX_CHARS];
+ const unsigned char *data = mem;
+ int i, j;
+
+ if (s->full)
+ return 0;
+
+#ifdef __BIG_ENDIAN
+ for (i = 0, j = 0; i < len; i++) {
+#else
+ for (i = len-1, j = 0; i >= 0; i--) {
+#endif
+ hex[j++] = hex_asc_hi(data[i]);
+ hex[j++] = hex_asc_lo(data[i]);
+ }
+ hex[j++] = ' ';
+
+ return trace_seq_putmem(s, hex, j);
+}
+
+void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+ void *ret;
+
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
+ return NULL;
+ }
+
+ ret = s->buffer + s->len;
+ s->len += len;
+
+ return ret;
+}
+
+int trace_seq_path(struct trace_seq *s, struct path *path)
+{
+ unsigned char *p;
+
+ if (s->full)
+ return 0;
+
+ if (s->len >= (PAGE_SIZE - 1)) {
+ s->full = 1;
+ return 0;
+ }
+
+ p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
+ if (!IS_ERR(p)) {
+ p = mangle_path(s->buffer + s->len, p, "\n");
+ if (p) {
+ s->len = p - s->buffer;
+ return 1;
+ }
+ } else {
+ s->buffer[s->len++] = '?';
+ return 1;
+ }
+
+ s->full = 1;
+ return 0;
+}
+
+const char *
+ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+ unsigned long flags,
+ const struct trace_print_flags *flag_array)
+{
+ unsigned long mask;
+ const char *str;
+ const char *ret = p->buffer + p->len;
+ int i;
+
+ for (i = 0; flag_array[i].name && flags; i++) {
+
+ mask = flag_array[i].mask;
+ if ((flags & mask) != mask)
+ continue;
+
+ str = flag_array[i].name;
+ flags &= ~mask;
+ if (p->len && delim)
+ trace_seq_puts(p, delim);
+ trace_seq_puts(p, str);
+ }
+
+ /* check for left over flags */
+ if (flags) {
+ if (p->len && delim)
+ trace_seq_puts(p, delim);
+ trace_seq_printf(p, "0x%lx", flags);
+ }
+
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL(ftrace_print_flags_seq);
+
+const char *
+ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+ const struct trace_print_flags *symbol_array)
+{
+ int i;
+ const char *ret = p->buffer + p->len;
+
+ for (i = 0; symbol_array[i].name; i++) {
+
+ if (val != symbol_array[i].mask)
+ continue;
+
+ trace_seq_puts(p, symbol_array[i].name);
+ break;
+ }
+
+ if (!p->len)
+ trace_seq_printf(p, "0x%lx", val);
+
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq);
+
+#ifdef CONFIG_KRETPROBES
+static inline const char *kretprobed(const char *name)
+{
+ static const char tramp_name[] = "kretprobe_trampoline";
+ int size = sizeof(tramp_name);
+
+ if (strncmp(tramp_name, name, size) == 0)
+ return "[unknown/kretprobe'd]";
+ return name;
+}
+#else
+static inline const char *kretprobed(const char *name)
+{
+ return name;
+}
+#endif /* CONFIG_KRETPROBES */
+
+static int
+seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
+{
+#ifdef CONFIG_KALLSYMS
+ char str[KSYM_SYMBOL_LEN];
+ const char *name;
+
+ kallsyms_lookup(address, NULL, NULL, NULL, str);
+
+ name = kretprobed(str);
+
+ return trace_seq_printf(s, fmt, name);
+#endif
+ return 1;
+}
+
+static int
+seq_print_sym_offset(struct trace_seq *s, const char *fmt,
+ unsigned long address)
+{
+#ifdef CONFIG_KALLSYMS
+ char str[KSYM_SYMBOL_LEN];
+ const char *name;
+
+ sprint_symbol(str, address);
+ name = kretprobed(str);
+
+ return trace_seq_printf(s, fmt, name);
+#endif
+ return 1;
+}
+
+#ifndef CONFIG_64BIT
+# define IP_FMT "%08lx"
+#else
+# define IP_FMT "%016lx"
+#endif
+
+int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+ unsigned long ip, unsigned long sym_flags)
+{
+ struct file *file = NULL;
+ unsigned long vmstart = 0;
+ int ret = 1;
+
+ if (s->full)
+ return 0;
+
+ if (mm) {
+ const struct vm_area_struct *vma;
+
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, ip);
+ if (vma) {
+ file = vma->vm_file;
+ vmstart = vma->vm_start;
+ }
+ if (file) {
+ ret = trace_seq_path(s, &file->f_path);
+ if (ret)
+ ret = trace_seq_printf(s, "[+0x%lx]",
+ ip - vmstart);
+ }
+ up_read(&mm->mmap_sem);
+ }
+ if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
+ ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+ return ret;
+}
+
+int
+seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
+ unsigned long sym_flags)
+{
+ struct mm_struct *mm = NULL;
+ int ret = 1;
+ unsigned int i;
+
+ if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
+ struct task_struct *task;
+ /*
+ * we do the lookup on the thread group leader,
+ * since individual threads might have already quit!
+ */
+ rcu_read_lock();
+ task = find_task_by_vpid(entry->tgid);
+ if (task)
+ mm = get_task_mm(task);
+ rcu_read_unlock();
+ }
+
+ for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+ unsigned long ip = entry->caller[i];
+
+ if (ip == ULONG_MAX || !ret)
+ break;
+ if (ret)
+ ret = trace_seq_puts(s, " => ");
+ if (!ip) {
+ if (ret)
+ ret = trace_seq_puts(s, "??");
+ if (ret)
+ ret = trace_seq_puts(s, "\n");
+ continue;
+ }
+ if (!ret)
+ break;
+ if (ret)
+ ret = seq_print_user_ip(s, mm, ip, sym_flags);
+ ret = trace_seq_puts(s, "\n");
+ }
+
+ if (mm)
+ mmput(mm);
+ return ret;
+}
+
+int
+seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
+{
+ int ret;
+
+ if (!ip)
+ return trace_seq_printf(s, "0");
+
+ if (sym_flags & TRACE_ITER_SYM_OFFSET)
+ ret = seq_print_sym_offset(s, "%s", ip);
+ else
+ ret = seq_print_sym_short(s, "%s", ip);
+
+ if (!ret)
+ return 0;
+
+ if (sym_flags & TRACE_ITER_SYM_ADDR)
+ ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+ return ret;
+}
+
+/**
+ * trace_print_lat_fmt - print the irq, preempt and lockdep fields
+ * @s: trace seq struct to write to
+ * @entry: The trace entry field from the ring buffer
+ *
+ * Prints the generic fields of irqs off, in hard or softirq, preempt
+ * count and lock depth.
+ */
+int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
+{
+ int hardirq, softirq;
+ int ret;
+
+ hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
+ softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
+
+ if (!trace_seq_printf(s, "%c%c%c",
+ (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+ (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
+ 'X' : '.',
+ (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
+ 'N' : '.',
+ (hardirq && softirq) ? 'H' :
+ hardirq ? 'h' : softirq ? 's' : '.'))
+ return 0;
+
+ if (entry->preempt_count)
+ ret = trace_seq_printf(s, "%x", entry->preempt_count);
+ else
+ ret = trace_seq_putc(s, '.');
+
+ if (!ret)
+ return 0;
+
+ if (entry->lock_depth < 0)
+ return trace_seq_putc(s, '.');
+
+ return trace_seq_printf(s, "%d", entry->lock_depth);
+}
+
+static int
+lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
+{
+ char comm[TASK_COMM_LEN];
+
+ trace_find_cmdline(entry->pid, comm);
+
+ if (!trace_seq_printf(s, "%8.8s-%-5d %3d",
+ comm, entry->pid, cpu))
+ return 0;
+
+ return trace_print_lat_fmt(s, entry);
+}
+
+static unsigned long preempt_mark_thresh = 100;
+
+static int
+lat_print_timestamp(struct trace_seq *s, u64 abs_usecs,
+ unsigned long rel_usecs)
+{
+ return trace_seq_printf(s, " %4lldus%c: ", abs_usecs,
+ rel_usecs > preempt_mark_thresh ? '!' :
+ rel_usecs > 1 ? '+' : ' ');
+}
+
+int trace_print_context(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ unsigned long long t = ns2usecs(iter->ts);
+ unsigned long usec_rem = do_div(t, USEC_PER_SEC);
+ unsigned long secs = (unsigned long)t;
+ char comm[TASK_COMM_LEN];
+
+ trace_find_cmdline(entry->pid, comm);
+
+ return trace_seq_printf(s, "%16s-%-5d [%03d] %5lu.%06lu: ",
+ comm, entry->pid, iter->cpu, secs, usec_rem);
+}
+
+int trace_print_lat_context(struct trace_iterator *iter)
+{
+ u64 next_ts;
+ int ret;
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent,
+ *next_entry = trace_find_next_entry(iter, NULL,
+ &next_ts);
+ unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE);
+ unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
+ unsigned long rel_usecs;
+
+ if (!next_entry)
+ next_ts = iter->ts;
+ rel_usecs = ns2usecs(next_ts - iter->ts);
+
+ if (verbose) {
+ char comm[TASK_COMM_LEN];
+
+ trace_find_cmdline(entry->pid, comm);
+
+ ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]"
+ " %ld.%03ldms (+%ld.%03ldms): ", comm,
+ entry->pid, iter->cpu, entry->flags,
+ entry->preempt_count, iter->idx,
+ ns2usecs(iter->ts),
+ abs_usecs / USEC_PER_MSEC,
+ abs_usecs % USEC_PER_MSEC,
+ rel_usecs / USEC_PER_MSEC,
+ rel_usecs % USEC_PER_MSEC);
+ } else {
+ ret = lat_print_generic(s, entry, iter->cpu);
+ if (ret)
+ ret = lat_print_timestamp(s, abs_usecs, rel_usecs);
+ }
+
+ return ret;
+}
+
+static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+
+static int task_state_char(unsigned long state)
+{
+ int bit = state ? __ffs(state) + 1 : 0;
+
+ return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
+/**
+ * ftrace_find_event - find a registered event
+ * @type: the type of event to look for
+ *
+ * Returns an event of type @type otherwise NULL
+ * Called with trace_event_read_lock() held.
+ */
+struct trace_event *ftrace_find_event(int type)
+{
+ struct trace_event *event;
+ struct hlist_node *n;
+ unsigned key;
+
+ key = type & (EVENT_HASHSIZE - 1);
+
+ hlist_for_each_entry(event, n, &event_hash[key], node) {
+ if (event->type == type)
+ return event;
+ }
+
+ return NULL;
+}
+
+static LIST_HEAD(ftrace_event_list);
+
+static int trace_search_list(struct list_head **list)
+{
+ struct trace_event *e;
+ int last = __TRACE_LAST_TYPE;
+
+ if (list_empty(&ftrace_event_list)) {
+ *list = &ftrace_event_list;
+ return last + 1;
+ }
+
+ /*
+ * We used up all possible max events,
+ * lets see if somebody freed one.
+ */
+ list_for_each_entry(e, &ftrace_event_list, list) {
+ if (e->type != last + 1)
+ break;
+ last++;
+ }
+
+ /* Did we used up all 65 thousand events??? */
+ if ((last + 1) > FTRACE_MAX_EVENT)
+ return 0;
+
+ *list = &e->list;
+ return last + 1;
+}
+
+void trace_event_read_lock(void)
+{
+ down_read(&trace_event_mutex);
+}
+
+void trace_event_read_unlock(void)
+{
+ up_read(&trace_event_mutex);
+}
+
+/**
+ * register_ftrace_event - register output for an event type
+ * @event: the event type to register
+ *
+ * Event types are stored in a hash and this hash is used to
+ * find a way to print an event. If the @event->type is set
+ * then it will use that type, otherwise it will assign a
+ * type to use.
+ *
+ * If you assign your own type, please make sure it is added
+ * to the trace_type enum in trace.h, to avoid collisions
+ * with the dynamic types.
+ *
+ * Returns the event type number or zero on error.
+ */
+int register_ftrace_event(struct trace_event *event)
+{
+ unsigned key;
+ int ret = 0;
+
+ down_write(&trace_event_mutex);
+
+ if (WARN_ON(!event))
+ goto out;
+
+ INIT_LIST_HEAD(&event->list);
+
+ if (!event->type) {
+ struct list_head *list = NULL;
+
+ if (next_event_type > FTRACE_MAX_EVENT) {
+
+ event->type = trace_search_list(&list);
+ if (!event->type)
+ goto out;
+
+ } else {
+
+ event->type = next_event_type++;
+ list = &ftrace_event_list;
+ }
+
+ if (WARN_ON(ftrace_find_event(event->type)))
+ goto out;
+
+ list_add_tail(&event->list, list);
+
+ } else if (event->type > __TRACE_LAST_TYPE) {
+ printk(KERN_WARNING "Need to add type to trace.h\n");
+ WARN_ON(1);
+ goto out;
+ } else {
+ /* Is this event already used */
+ if (ftrace_find_event(event->type))
+ goto out;
+ }
+
+ if (event->trace == NULL)
+ event->trace = trace_nop_print;
+ if (event->raw == NULL)
+ event->raw = trace_nop_print;
+ if (event->hex == NULL)
+ event->hex = trace_nop_print;
+ if (event->binary == NULL)
+ event->binary = trace_nop_print;
+
+ key = event->type & (EVENT_HASHSIZE - 1);
+
+ hlist_add_head(&event->node, &event_hash[key]);
+
+ ret = event->type;
+ out:
+ up_write(&trace_event_mutex);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_event);
+
+/*
+ * Used by module code with the trace_event_mutex held for write.
+ */
+int __unregister_ftrace_event(struct trace_event *event)
+{
+ hlist_del(&event->node);
+ list_del(&event->list);
+ return 0;
+}
+
+/**
+ * unregister_ftrace_event - remove a no longer used event
+ * @event: the event to remove
+ */
+int unregister_ftrace_event(struct trace_event *event)
+{
+ down_write(&trace_event_mutex);
+ __unregister_ftrace_event(event);
+ up_write(&trace_event_mutex);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_event);
+
+/*
+ * Standard events
+ */
+
+enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags)
+{
+ return TRACE_TYPE_HANDLED;
+}
+
+/* TRACE_FN */
+static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
+{
+ struct ftrace_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!seq_print_ip_sym(s, field->ip, flags))
+ goto partial;
+
+ if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) {
+ if (!trace_seq_printf(s, " <-"))
+ goto partial;
+ if (!seq_print_ip_sym(s,
+ field->parent_ip,
+ flags))
+ goto partial;
+ }
+ if (!trace_seq_printf(s, "\n"))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
+{
+ struct ftrace_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(&iter->seq, "%lx %lx\n",
+ field->ip,
+ field->parent_ip))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
+{
+ struct ftrace_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD_RET(s, field->ip);
+ SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
+{
+ struct ftrace_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD_RET(s, field->ip);
+ SEQ_PUT_FIELD_RET(s, field->parent_ip);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event trace_fn_event = {
+ .type = TRACE_FN,
+ .trace = trace_fn_trace,
+ .raw = trace_fn_raw,
+ .hex = trace_fn_hex,
+ .binary = trace_fn_bin,
+};
+
+/* TRACE_CTX an TRACE_WAKE */
+static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
+ char *delim)
+{
+ struct ctx_switch_entry *field;
+ char comm[TASK_COMM_LEN];
+ int S, T;
+
+
+ trace_assign_type(field, iter->ent);
+
+ T = task_state_char(field->next_state);
+ S = task_state_char(field->prev_state);
+ trace_find_cmdline(field->next_pid, comm);
+ if (!trace_seq_printf(&iter->seq,
+ " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+ field->prev_pid,
+ field->prev_prio,
+ S, delim,
+ field->next_cpu,
+ field->next_pid,
+ field->next_prio,
+ T, comm))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags)
+{
+ return trace_ctxwake_print(iter, "==>");
+}
+
+static enum print_line_t trace_wake_print(struct trace_iterator *iter,
+ int flags)
+{
+ return trace_ctxwake_print(iter, " +");
+}
+
+static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
+{
+ struct ctx_switch_entry *field;
+ int T;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!S)
+ S = task_state_char(field->prev_state);
+ T = task_state_char(field->next_state);
+ if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
+ field->prev_pid,
+ field->prev_prio,
+ S,
+ field->next_cpu,
+ field->next_pid,
+ field->next_prio,
+ T))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags)
+{
+ return trace_ctxwake_raw(iter, 0);
+}
+
+static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags)
+{
+ return trace_ctxwake_raw(iter, '+');
+}
+
+
+static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
+{
+ struct ctx_switch_entry *field;
+ struct trace_seq *s = &iter->seq;
+ int T;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!S)
+ S = task_state_char(field->prev_state);
+ T = task_state_char(field->next_state);
+
+ SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
+ SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio);
+ SEQ_PUT_HEX_FIELD_RET(s, S);
+ SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu);
+ SEQ_PUT_HEX_FIELD_RET(s, field->next_pid);
+ SEQ_PUT_HEX_FIELD_RET(s, field->next_prio);
+ SEQ_PUT_HEX_FIELD_RET(s, T);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags)
+{
+ return trace_ctxwake_hex(iter, 0);
+}
+
+static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags)
+{
+ return trace_ctxwake_hex(iter, '+');
+}
+
+static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
+ int flags)
+{
+ struct ctx_switch_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD_RET(s, field->prev_pid);
+ SEQ_PUT_FIELD_RET(s, field->prev_prio);
+ SEQ_PUT_FIELD_RET(s, field->prev_state);
+ SEQ_PUT_FIELD_RET(s, field->next_pid);
+ SEQ_PUT_FIELD_RET(s, field->next_prio);
+ SEQ_PUT_FIELD_RET(s, field->next_state);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event trace_ctx_event = {
+ .type = TRACE_CTX,
+ .trace = trace_ctx_print,
+ .raw = trace_ctx_raw,
+ .hex = trace_ctx_hex,
+ .binary = trace_ctxwake_bin,
+};
+
+static struct trace_event trace_wake_event = {
+ .type = TRACE_WAKE,
+ .trace = trace_wake_print,
+ .raw = trace_wake_raw,
+ .hex = trace_wake_hex,
+ .binary = trace_ctxwake_bin,
+};
+
+/* TRACE_SPECIAL */
+static enum print_line_t trace_special_print(struct trace_iterator *iter,
+ int flags)
+{
+ struct special_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(&iter->seq, "# %ld %ld %ld\n",
+ field->arg1,
+ field->arg2,
+ field->arg3))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_special_hex(struct trace_iterator *iter,
+ int flags)
+{
+ struct special_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD_RET(s, field->arg1);
+ SEQ_PUT_HEX_FIELD_RET(s, field->arg2);
+ SEQ_PUT_HEX_FIELD_RET(s, field->arg3);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_special_bin(struct trace_iterator *iter,
+ int flags)
+{
+ struct special_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD_RET(s, field->arg1);
+ SEQ_PUT_FIELD_RET(s, field->arg2);
+ SEQ_PUT_FIELD_RET(s, field->arg3);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event trace_special_event = {
+ .type = TRACE_SPECIAL,
+ .trace = trace_special_print,
+ .raw = trace_special_print,
+ .hex = trace_special_hex,
+ .binary = trace_special_bin,
+};
+
+/* TRACE_STACK */
+
+static enum print_line_t trace_stack_print(struct trace_iterator *iter,
+ int flags)
+{
+ struct stack_entry *field;
+ struct trace_seq *s = &iter->seq;
+ int i;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_puts(s, "<stack trace>\n"))
+ goto partial;
+ for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+ if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
+ break;
+ if (!trace_seq_puts(s, " => "))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->caller[i], flags))
+ goto partial;
+ if (!trace_seq_puts(s, "\n"))
+ goto partial;
+ }
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static struct trace_event trace_stack_event = {
+ .type = TRACE_STACK,
+ .trace = trace_stack_print,
+ .raw = trace_special_print,
+ .hex = trace_special_hex,
+ .binary = trace_special_bin,
+};
+
+/* TRACE_USER_STACK */
+static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
+ int flags)
+{
+ struct userstack_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_puts(s, "<user stack trace>\n"))
+ goto partial;
+
+ if (!seq_print_userip_objs(field, s, flags))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static struct trace_event trace_user_stack_event = {
+ .type = TRACE_USER_STACK,
+ .trace = trace_user_stack_print,
+ .raw = trace_special_print,
+ .hex = trace_special_hex,
+ .binary = trace_special_bin,
+};
+
+/* TRACE_BPRINT */
+static enum print_line_t
+trace_bprint_print(struct trace_iterator *iter, int flags)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct bprint_entry *field;
+
+ trace_assign_type(field, entry);
+
+ if (!seq_print_ip_sym(s, field->ip, flags))
+ goto partial;
+
+ if (!trace_seq_puts(s, ": "))
+ goto partial;
+
+ if (!trace_seq_bprintf(s, field->fmt, field->buf))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+
+static enum print_line_t
+trace_bprint_raw(struct trace_iterator *iter, int flags)
+{
+ struct bprint_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(s, ": %lx : ", field->ip))
+ goto partial;
+
+ if (!trace_seq_bprintf(s, field->fmt, field->buf))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+
+static struct trace_event trace_bprint_event = {
+ .type = TRACE_BPRINT,
+ .trace = trace_bprint_print,
+ .raw = trace_bprint_raw,
+};
+
+/* TRACE_PRINT */
+static enum print_line_t trace_print_print(struct trace_iterator *iter,
+ int flags)
+{
+ struct print_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!seq_print_ip_sym(s, field->ip, flags))
+ goto partial;
+
+ if (!trace_seq_printf(s, ": %s", field->buf))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+{
+ struct print_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ if (!trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+
+ partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static struct trace_event trace_print_event = {
+ .type = TRACE_PRINT,
+ .trace = trace_print_print,
+ .raw = trace_print_raw,
+};
+
+
+static struct trace_event *events[] __initdata = {
+ &trace_fn_event,
+ &trace_ctx_event,
+ &trace_wake_event,
+ &trace_special_event,
+ &trace_stack_event,
+ &trace_user_stack_event,
+ &trace_bprint_event,
+ &trace_print_event,
+ NULL
+};
+
+__init static int init_events(void)
+{
+ struct trace_event *event;
+ int i, ret;
+
+ for (i = 0; events[i]; i++) {
+ event = events[i];
+
+ ret = register_ftrace_event(event);
+ if (!ret) {
+ printk(KERN_WARNING "event %d failed to register\n",
+ event->type);
+ WARN_ON_ONCE(1);
+ }
+ }
+
+ return 0;
+}
+device_initcall(init_events);
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
new file mode 100644
index 00000000000..9d91c72ba38
--- /dev/null
+++ b/kernel/trace/trace_output.h
@@ -0,0 +1,53 @@
+#ifndef __TRACE_EVENTS_H
+#define __TRACE_EVENTS_H
+
+#include <linux/trace_seq.h>
+#include "trace.h"
+
+extern enum print_line_t
+trace_print_bprintk_msg_only(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_printk_msg_only(struct trace_iterator *iter);
+
+extern int
+seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
+ unsigned long sym_flags);
+extern int seq_print_userip_objs(const struct userstack_entry *entry,
+ struct trace_seq *s, unsigned long sym_flags);
+extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+ unsigned long ip, unsigned long sym_flags);
+
+extern int trace_print_context(struct trace_iterator *iter);
+extern int trace_print_lat_context(struct trace_iterator *iter);
+
+extern void trace_event_read_lock(void);
+extern void trace_event_read_unlock(void);
+extern struct trace_event *ftrace_find_event(int type);
+
+extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
+ int flags);
+extern int
+trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
+
+/* used by module unregistering */
+extern int __unregister_ftrace_event(struct trace_event *event);
+extern struct rw_semaphore trace_event_mutex;
+
+#define MAX_MEMHEX_BYTES 8
+#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1)
+
+#define SEQ_PUT_FIELD_RET(s, x) \
+do { \
+ if (!trace_seq_putmem(s, &(x), sizeof(x))) \
+ return TRACE_TYPE_PARTIAL_LINE; \
+} while (0)
+
+#define SEQ_PUT_HEX_FIELD_RET(s, x) \
+do { \
+ BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \
+ if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \
+ return TRACE_TYPE_PARTIAL_LINE; \
+} while (0)
+
+#endif
+
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
new file mode 100644
index 00000000000..2547d8813cf
--- /dev/null
+++ b/kernel/trace/trace_printk.c
@@ -0,0 +1,251 @@
+/*
+ * trace binary printk
+ *
+ * Copyright (C) 2008 Lai Jiangshan <laijs@cn.fujitsu.com>
+ *
+ */
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+#ifdef CONFIG_MODULES
+
+/*
+ * modules trace_printk()'s formats are autosaved in struct trace_bprintk_fmt
+ * which are queued on trace_bprintk_fmt_list.
+ */
+static LIST_HEAD(trace_bprintk_fmt_list);
+
+/* serialize accesses to trace_bprintk_fmt_list */
+static DEFINE_MUTEX(btrace_mutex);
+
+struct trace_bprintk_fmt {
+ struct list_head list;
+ char fmt[0];
+};
+
+static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
+{
+ struct trace_bprintk_fmt *pos;
+ list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
+ if (!strcmp(pos->fmt, fmt))
+ return pos;
+ }
+ return NULL;
+}
+
+static
+void hold_module_trace_bprintk_format(const char **start, const char **end)
+{
+ const char **iter;
+
+ mutex_lock(&btrace_mutex);
+ for (iter = start; iter < end; iter++) {
+ struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
+ if (tb_fmt) {
+ *iter = tb_fmt->fmt;
+ continue;
+ }
+
+ tb_fmt = kmalloc(offsetof(struct trace_bprintk_fmt, fmt)
+ + strlen(*iter) + 1, GFP_KERNEL);
+ if (tb_fmt) {
+ list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list);
+ strcpy(tb_fmt->fmt, *iter);
+ *iter = tb_fmt->fmt;
+ } else
+ *iter = NULL;
+ }
+ mutex_unlock(&btrace_mutex);
+}
+
+static int module_trace_bprintk_format_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+ if (mod->num_trace_bprintk_fmt) {
+ const char **start = mod->trace_bprintk_fmt_start;
+ const char **end = start + mod->num_trace_bprintk_fmt;
+
+ if (val == MODULE_STATE_COMING)
+ hold_module_trace_bprintk_format(start, end);
+ }
+ return 0;
+}
+
+#else /* !CONFIG_MODULES */
+__init static int
+module_trace_bprintk_format_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+
+__initdata_or_module static
+struct notifier_block module_trace_bprintk_format_nb = {
+ .notifier_call = module_trace_bprintk_format_notify,
+};
+
+int __trace_bprintk(unsigned long ip, const char *fmt, ...)
+ {
+ int ret;
+ va_list ap;
+
+ if (unlikely(!fmt))
+ return 0;
+
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ va_start(ap, fmt);
+ ret = trace_vbprintk(ip, fmt, ap);
+ va_end(ap);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__trace_bprintk);
+
+int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap)
+ {
+ if (unlikely(!fmt))
+ return 0;
+
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ return trace_vbprintk(ip, fmt, ap);
+}
+EXPORT_SYMBOL_GPL(__ftrace_vbprintk);
+
+int __trace_printk(unsigned long ip, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ va_start(ap, fmt);
+ ret = trace_vprintk(ip, fmt, ap);
+ va_end(ap);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__trace_printk);
+
+int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
+{
+ if (!(trace_flags & TRACE_ITER_PRINTK))
+ return 0;
+
+ return trace_vprintk(ip, fmt, ap);
+}
+EXPORT_SYMBOL_GPL(__ftrace_vprintk);
+
+static void *
+t_start(struct seq_file *m, loff_t *pos)
+{
+ const char **fmt = __start___trace_bprintk_fmt + *pos;
+
+ if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
+ return NULL;
+ return fmt;
+}
+
+static void *t_next(struct seq_file *m, void * v, loff_t *pos)
+{
+ (*pos)++;
+ return t_start(m, pos);
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+ const char **fmt = v;
+ const char *str = *fmt;
+ int i;
+
+ seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
+
+ /*
+ * Tabs and new lines need to be converted.
+ */
+ for (i = 0; str[i]; i++) {
+ switch (str[i]) {
+ case '\n':
+ seq_puts(m, "\\n");
+ break;
+ case '\t':
+ seq_puts(m, "\\t");
+ break;
+ case '\\':
+ seq_puts(m, "\\");
+ break;
+ case '"':
+ seq_puts(m, "\\\"");
+ break;
+ default:
+ seq_putc(m, str[i]);
+ }
+ }
+ seq_puts(m, "\"\n");
+
+ return 0;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+}
+
+static const struct seq_operations show_format_seq_ops = {
+ .start = t_start,
+ .next = t_next,
+ .show = t_show,
+ .stop = t_stop,
+};
+
+static int
+ftrace_formats_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &show_format_seq_ops);
+}
+
+static const struct file_operations ftrace_formats_fops = {
+ .open = ftrace_formats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static __init int init_trace_printk_function_export(void)
+{
+ struct dentry *d_tracer;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ trace_create_file("printk_formats", 0444, d_tracer,
+ NULL, &ftrace_formats_fops);
+
+ return 0;
+}
+
+fs_initcall(init_trace_printk_function_export);
+
+static __init int init_trace_printk(void)
+{
+ return register_module_notifier(&module_trace_bprintk_format_nb);
+}
+
+early_initcall(init_trace_printk);
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
new file mode 100644
index 00000000000..5fca0f51fde
--- /dev/null
+++ b/kernel/trace/trace_sched_switch.c
@@ -0,0 +1,298 @@
+/*
+ * trace context switch
+ *
+ * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <trace/events/sched.h>
+
+#include "trace.h"
+
+static struct trace_array *ctx_trace;
+static int __read_mostly tracer_enabled;
+static int sched_ref;
+static DEFINE_MUTEX(sched_register_mutex);
+static int sched_stopped;
+
+
+void
+tracing_sched_switch_trace(struct trace_array *tr,
+ struct task_struct *prev,
+ struct task_struct *next,
+ unsigned long flags, int pc)
+{
+ struct ftrace_event_call *call = &event_context_switch;
+ struct ring_buffer *buffer = tr->buffer;
+ struct ring_buffer_event *event;
+ struct ctx_switch_entry *entry;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ entry->prev_pid = prev->pid;
+ entry->prev_prio = prev->prio;
+ entry->prev_state = prev->state;
+ entry->next_pid = next->pid;
+ entry->next_prio = next->prio;
+ entry->next_state = next->state;
+ entry->next_cpu = task_cpu(next);
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ trace_buffer_unlock_commit(buffer, event, flags, pc);
+}
+
+static void
+probe_sched_switch(struct rq *__rq, struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ int cpu;
+ int pc;
+
+ if (unlikely(!sched_ref))
+ return;
+
+ tracing_record_cmdline(prev);
+ tracing_record_cmdline(next);
+
+ if (!tracer_enabled || sched_stopped)
+ return;
+
+ pc = preempt_count();
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = ctx_trace->data[cpu];
+
+ if (likely(!atomic_read(&data->disabled)))
+ tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc);
+
+ local_irq_restore(flags);
+}
+
+void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+ struct task_struct *wakee,
+ struct task_struct *curr,
+ unsigned long flags, int pc)
+{
+ struct ftrace_event_call *call = &event_wakeup;
+ struct ring_buffer_event *event;
+ struct ctx_switch_entry *entry;
+ struct ring_buffer *buffer = tr->buffer;
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
+ sizeof(*entry), flags, pc);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ entry->prev_pid = curr->pid;
+ entry->prev_prio = curr->prio;
+ entry->prev_state = curr->state;
+ entry->next_pid = wakee->pid;
+ entry->next_prio = wakee->prio;
+ entry->next_state = wakee->state;
+ entry->next_cpu = task_cpu(wakee);
+
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(tr->buffer, flags, 6, pc);
+ ftrace_trace_userstack(tr->buffer, flags, pc);
+}
+
+static void
+probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
+{
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ int cpu, pc;
+
+ if (unlikely(!sched_ref))
+ return;
+
+ tracing_record_cmdline(current);
+
+ if (!tracer_enabled || sched_stopped)
+ return;
+
+ pc = preempt_count();
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = ctx_trace->data[cpu];
+
+ if (likely(!atomic_read(&data->disabled)))
+ tracing_sched_wakeup_trace(ctx_trace, wakee, current,
+ flags, pc);
+
+ local_irq_restore(flags);
+}
+
+static int tracing_sched_register(void)
+{
+ int ret;
+
+ ret = register_trace_sched_wakeup(probe_sched_wakeup);
+ if (ret) {
+ pr_info("wakeup trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_wakeup\n");
+ return ret;
+ }
+
+ ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
+ if (ret) {
+ pr_info("wakeup trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_wakeup_new\n");
+ goto fail_deprobe;
+ }
+
+ ret = register_trace_sched_switch(probe_sched_switch);
+ if (ret) {
+ pr_info("sched trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_switch\n");
+ goto fail_deprobe_wake_new;
+ }
+
+ return ret;
+fail_deprobe_wake_new:
+ unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+fail_deprobe:
+ unregister_trace_sched_wakeup(probe_sched_wakeup);
+ return ret;
+}
+
+static void tracing_sched_unregister(void)
+{
+ unregister_trace_sched_switch(probe_sched_switch);
+ unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+ unregister_trace_sched_wakeup(probe_sched_wakeup);
+}
+
+static void tracing_start_sched_switch(void)
+{
+ mutex_lock(&sched_register_mutex);
+ if (!(sched_ref++))
+ tracing_sched_register();
+ mutex_unlock(&sched_register_mutex);
+}
+
+static void tracing_stop_sched_switch(void)
+{
+ mutex_lock(&sched_register_mutex);
+ if (!(--sched_ref))
+ tracing_sched_unregister();
+ mutex_unlock(&sched_register_mutex);
+}
+
+void tracing_start_cmdline_record(void)
+{
+ tracing_start_sched_switch();
+}
+
+void tracing_stop_cmdline_record(void)
+{
+ tracing_stop_sched_switch();
+}
+
+/**
+ * tracing_start_sched_switch_record - start tracing context switches
+ *
+ * Turns on context switch tracing for a tracer.
+ */
+void tracing_start_sched_switch_record(void)
+{
+ if (unlikely(!ctx_trace)) {
+ WARN_ON(1);
+ return;
+ }
+
+ tracing_start_sched_switch();
+
+ mutex_lock(&sched_register_mutex);
+ tracer_enabled++;
+ mutex_unlock(&sched_register_mutex);
+}
+
+/**
+ * tracing_stop_sched_switch_record - start tracing context switches
+ *
+ * Turns off context switch tracing for a tracer.
+ */
+void tracing_stop_sched_switch_record(void)
+{
+ mutex_lock(&sched_register_mutex);
+ tracer_enabled--;
+ WARN_ON(tracer_enabled < 0);
+ mutex_unlock(&sched_register_mutex);
+
+ tracing_stop_sched_switch();
+}
+
+/**
+ * tracing_sched_switch_assign_trace - assign a trace array for ctx switch
+ * @tr: trace array pointer to assign
+ *
+ * Some tracers might want to record the context switches in their
+ * trace. This function lets those tracers assign the trace array
+ * to use.
+ */
+void tracing_sched_switch_assign_trace(struct trace_array *tr)
+{
+ ctx_trace = tr;
+}
+
+static void stop_sched_trace(struct trace_array *tr)
+{
+ tracing_stop_sched_switch_record();
+}
+
+static int sched_switch_trace_init(struct trace_array *tr)
+{
+ ctx_trace = tr;
+ tracing_reset_online_cpus(tr);
+ tracing_start_sched_switch_record();
+ return 0;
+}
+
+static void sched_switch_trace_reset(struct trace_array *tr)
+{
+ if (sched_ref)
+ stop_sched_trace(tr);
+}
+
+static void sched_switch_trace_start(struct trace_array *tr)
+{
+ sched_stopped = 0;
+}
+
+static void sched_switch_trace_stop(struct trace_array *tr)
+{
+ sched_stopped = 1;
+}
+
+static struct tracer sched_switch_trace __read_mostly =
+{
+ .name = "sched_switch",
+ .init = sched_switch_trace_init,
+ .reset = sched_switch_trace_reset,
+ .start = sched_switch_trace_start,
+ .stop = sched_switch_trace_stop,
+ .wait_pipe = poll_wait_pipe,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_sched_switch,
+#endif
+};
+
+__init static int init_sched_switch_trace(void)
+{
+ return register_tracer(&sched_switch_trace);
+}
+device_initcall(init_sched_switch_trace);
+
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
new file mode 100644
index 00000000000..0271742abb8
--- /dev/null
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -0,0 +1,415 @@
+/*
+ * trace task wakeup timings
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Based on code from the latency_tracer, that is:
+ *
+ * Copyright (C) 2004-2006 Ingo Molnar
+ * Copyright (C) 2004 William Lee Irwin III
+ */
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <trace/events/sched.h>
+
+#include "trace.h"
+
+static struct trace_array *wakeup_trace;
+static int __read_mostly tracer_enabled;
+
+static struct task_struct *wakeup_task;
+static int wakeup_cpu;
+static int wakeup_current_cpu;
+static unsigned wakeup_prio = -1;
+static int wakeup_rt;
+
+static arch_spinlock_t wakeup_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+static void __wakeup_reset(struct trace_array *tr);
+
+static int save_lat_flag;
+
+#ifdef CONFIG_FUNCTION_TRACER
+/*
+ * irqsoff uses its own tracer function to keep the overhead down:
+ */
+static void
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct trace_array *tr = wakeup_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int resched;
+ int cpu;
+ int pc;
+
+ if (likely(!wakeup_task))
+ return;
+
+ pc = preempt_count();
+ resched = ftrace_preempt_disable();
+
+ cpu = raw_smp_processor_id();
+ if (cpu != wakeup_current_cpu)
+ goto out_enable;
+
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+ if (unlikely(disabled != 1))
+ goto out;
+
+ local_irq_save(flags);
+
+ trace_function(tr, ip, parent_ip, flags, pc);
+
+ local_irq_restore(flags);
+
+ out:
+ atomic_dec(&data->disabled);
+ out_enable:
+ ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+ .func = wakeup_tracer_call,
+};
+#endif /* CONFIG_FUNCTION_TRACER */
+
+/*
+ * Should this new latency be reported/recorded?
+ */
+static int report_latency(cycle_t delta)
+{
+ if (tracing_thresh) {
+ if (delta < tracing_thresh)
+ return 0;
+ } else {
+ if (delta <= tracing_max_latency)
+ return 0;
+ }
+ return 1;
+}
+
+static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
+{
+ if (task != wakeup_task)
+ return;
+
+ wakeup_current_cpu = cpu;
+}
+
+static void notrace
+probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct trace_array_cpu *data;
+ cycle_t T0, T1, delta;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ tracing_record_cmdline(prev);
+
+ if (unlikely(!tracer_enabled))
+ return;
+
+ /*
+ * When we start a new trace, we set wakeup_task to NULL
+ * and then set tracer_enabled = 1. We want to make sure
+ * that another CPU does not see the tracer_enabled = 1
+ * and the wakeup_task with an older task, that might
+ * actually be the same as next.
+ */
+ smp_rmb();
+
+ if (next != wakeup_task)
+ return;
+
+ pc = preempt_count();
+
+ /* disable local data, not wakeup_cpu data */
+ cpu = raw_smp_processor_id();
+ disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
+ if (likely(disabled != 1))
+ goto out;
+
+ local_irq_save(flags);
+ arch_spin_lock(&wakeup_lock);
+
+ /* We could race with grabbing wakeup_lock */
+ if (unlikely(!tracer_enabled || next != wakeup_task))
+ goto out_unlock;
+
+ /* The task we are waiting for is waking up */
+ data = wakeup_trace->data[wakeup_cpu];
+
+ trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
+ tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
+
+ T0 = data->preempt_timestamp;
+ T1 = ftrace_now(cpu);
+ delta = T1-T0;
+
+ if (!report_latency(delta))
+ goto out_unlock;
+
+ if (likely(!is_tracing_stopped())) {
+ tracing_max_latency = delta;
+ update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
+ }
+
+out_unlock:
+ __wakeup_reset(wakeup_trace);
+ arch_spin_unlock(&wakeup_lock);
+ local_irq_restore(flags);
+out:
+ atomic_dec(&wakeup_trace->data[cpu]->disabled);
+}
+
+static void __wakeup_reset(struct trace_array *tr)
+{
+ wakeup_cpu = -1;
+ wakeup_prio = -1;
+
+ if (wakeup_task)
+ put_task_struct(wakeup_task);
+
+ wakeup_task = NULL;
+}
+
+static void wakeup_reset(struct trace_array *tr)
+{
+ unsigned long flags;
+
+ tracing_reset_online_cpus(tr);
+
+ local_irq_save(flags);
+ arch_spin_lock(&wakeup_lock);
+ __wakeup_reset(tr);
+ arch_spin_unlock(&wakeup_lock);
+ local_irq_restore(flags);
+}
+
+static void
+probe_wakeup(struct rq *rq, struct task_struct *p, int success)
+{
+ struct trace_array_cpu *data;
+ int cpu = smp_processor_id();
+ unsigned long flags;
+ long disabled;
+ int pc;
+
+ if (likely(!tracer_enabled))
+ return;
+
+ tracing_record_cmdline(p);
+ tracing_record_cmdline(current);
+
+ if ((wakeup_rt && !rt_task(p)) ||
+ p->prio >= wakeup_prio ||
+ p->prio >= current->prio)
+ return;
+
+ pc = preempt_count();
+ disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
+ if (unlikely(disabled != 1))
+ goto out;
+
+ /* interrupts should be off from try_to_wake_up */
+ arch_spin_lock(&wakeup_lock);
+
+ /* check for races. */
+ if (!tracer_enabled || p->prio >= wakeup_prio)
+ goto out_locked;
+
+ /* reset the trace */
+ __wakeup_reset(wakeup_trace);
+
+ wakeup_cpu = task_cpu(p);
+ wakeup_current_cpu = wakeup_cpu;
+ wakeup_prio = p->prio;
+
+ wakeup_task = p;
+ get_task_struct(wakeup_task);
+
+ local_save_flags(flags);
+
+ data = wakeup_trace->data[wakeup_cpu];
+ data->preempt_timestamp = ftrace_now(cpu);
+ tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
+
+ /*
+ * We must be careful in using CALLER_ADDR2. But since wake_up
+ * is not called by an assembly function (where as schedule is)
+ * it should be safe to use it here.
+ */
+ trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+
+out_locked:
+ arch_spin_unlock(&wakeup_lock);
+out:
+ atomic_dec(&wakeup_trace->data[cpu]->disabled);
+}
+
+static void start_wakeup_tracer(struct trace_array *tr)
+{
+ int ret;
+
+ ret = register_trace_sched_wakeup(probe_wakeup);
+ if (ret) {
+ pr_info("wakeup trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_wakeup\n");
+ return;
+ }
+
+ ret = register_trace_sched_wakeup_new(probe_wakeup);
+ if (ret) {
+ pr_info("wakeup trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_wakeup_new\n");
+ goto fail_deprobe;
+ }
+
+ ret = register_trace_sched_switch(probe_wakeup_sched_switch);
+ if (ret) {
+ pr_info("sched trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_switch\n");
+ goto fail_deprobe_wake_new;
+ }
+
+ ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task);
+ if (ret) {
+ pr_info("wakeup trace: Couldn't activate tracepoint"
+ " probe to kernel_sched_migrate_task\n");
+ return;
+ }
+
+ wakeup_reset(tr);
+
+ /*
+ * Don't let the tracer_enabled = 1 show up before
+ * the wakeup_task is reset. This may be overkill since
+ * wakeup_reset does a spin_unlock after setting the
+ * wakeup_task to NULL, but I want to be safe.
+ * This is a slow path anyway.
+ */
+ smp_wmb();
+
+ register_ftrace_function(&trace_ops);
+
+ if (tracing_is_enabled())
+ tracer_enabled = 1;
+ else
+ tracer_enabled = 0;
+
+ return;
+fail_deprobe_wake_new:
+ unregister_trace_sched_wakeup_new(probe_wakeup);
+fail_deprobe:
+ unregister_trace_sched_wakeup(probe_wakeup);
+}
+
+static void stop_wakeup_tracer(struct trace_array *tr)
+{
+ tracer_enabled = 0;
+ unregister_ftrace_function(&trace_ops);
+ unregister_trace_sched_switch(probe_wakeup_sched_switch);
+ unregister_trace_sched_wakeup_new(probe_wakeup);
+ unregister_trace_sched_wakeup(probe_wakeup);
+ unregister_trace_sched_migrate_task(probe_wakeup_migrate_task);
+}
+
+static int __wakeup_tracer_init(struct trace_array *tr)
+{
+ save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
+ trace_flags |= TRACE_ITER_LATENCY_FMT;
+
+ tracing_max_latency = 0;
+ wakeup_trace = tr;
+ start_wakeup_tracer(tr);
+ return 0;
+}
+
+static int wakeup_tracer_init(struct trace_array *tr)
+{
+ wakeup_rt = 0;
+ return __wakeup_tracer_init(tr);
+}
+
+static int wakeup_rt_tracer_init(struct trace_array *tr)
+{
+ wakeup_rt = 1;
+ return __wakeup_tracer_init(tr);
+}
+
+static void wakeup_tracer_reset(struct trace_array *tr)
+{
+ stop_wakeup_tracer(tr);
+ /* make sure we put back any tasks we are tracing */
+ wakeup_reset(tr);
+
+ if (!save_lat_flag)
+ trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+}
+
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+ wakeup_reset(tr);
+ tracer_enabled = 1;
+}
+
+static void wakeup_tracer_stop(struct trace_array *tr)
+{
+ tracer_enabled = 0;
+}
+
+static struct tracer wakeup_tracer __read_mostly =
+{
+ .name = "wakeup",
+ .init = wakeup_tracer_init,
+ .reset = wakeup_tracer_reset,
+ .start = wakeup_tracer_start,
+ .stop = wakeup_tracer_stop,
+ .print_max = 1,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_wakeup,
+#endif
+};
+
+static struct tracer wakeup_rt_tracer __read_mostly =
+{
+ .name = "wakeup_rt",
+ .init = wakeup_rt_tracer_init,
+ .reset = wakeup_tracer_reset,
+ .start = wakeup_tracer_start,
+ .stop = wakeup_tracer_stop,
+ .wait_pipe = poll_wait_pipe,
+ .print_max = 1,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_wakeup,
+#endif
+};
+
+__init static int init_wakeup_tracer(void)
+{
+ int ret;
+
+ ret = register_tracer(&wakeup_tracer);
+ if (ret)
+ return ret;
+
+ ret = register_tracer(&wakeup_rt_tracer);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+device_initcall(init_wakeup_tracer);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
new file mode 100644
index 00000000000..280fea470d6
--- /dev/null
+++ b/kernel/trace/trace_selftest.c
@@ -0,0 +1,865 @@
+/* Include in trace.c */
+
+#include <linux/stringify.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+
+static inline int trace_valid_entry(struct trace_entry *entry)
+{
+ switch (entry->type) {
+ case TRACE_FN:
+ case TRACE_CTX:
+ case TRACE_WAKE:
+ case TRACE_STACK:
+ case TRACE_PRINT:
+ case TRACE_SPECIAL:
+ case TRACE_BRANCH:
+ case TRACE_GRAPH_ENT:
+ case TRACE_GRAPH_RET:
+ case TRACE_HW_BRANCHES:
+ case TRACE_KSYM:
+ return 1;
+ }
+ return 0;
+}
+
+static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
+{
+ struct ring_buffer_event *event;
+ struct trace_entry *entry;
+ unsigned int loops = 0;
+
+ while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+ entry = ring_buffer_event_data(event);
+
+ /*
+ * The ring buffer is a size of trace_buf_size, if
+ * we loop more than the size, there's something wrong
+ * with the ring buffer.
+ */
+ if (loops++ > trace_buf_size) {
+ printk(KERN_CONT ".. bad ring buffer ");
+ goto failed;
+ }
+ if (!trace_valid_entry(entry)) {
+ printk(KERN_CONT ".. invalid entry %d ",
+ entry->type);
+ goto failed;
+ }
+ }
+ return 0;
+
+ failed:
+ /* disable tracing */
+ tracing_disabled = 1;
+ printk(KERN_CONT ".. corrupted trace buffer .. ");
+ return -1;
+}
+
+/*
+ * Test the trace buffer to see if all the elements
+ * are still sane.
+ */
+static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
+{
+ unsigned long flags, cnt = 0;
+ int cpu, ret = 0;
+
+ /* Don't allow flipping of max traces now */
+ local_irq_save(flags);
+ arch_spin_lock(&ftrace_max_lock);
+
+ cnt = ring_buffer_entries(tr->buffer);
+
+ /*
+ * The trace_test_buffer_cpu runs a while loop to consume all data.
+ * If the calling tracer is broken, and is constantly filling
+ * the buffer, this will run forever, and hard lock the box.
+ * We disable the ring buffer while we do this test to prevent
+ * a hard lock up.
+ */
+ tracing_off();
+ for_each_possible_cpu(cpu) {
+ ret = trace_test_buffer_cpu(tr, cpu);
+ if (ret)
+ break;
+ }
+ tracing_on();
+ arch_spin_unlock(&ftrace_max_lock);
+ local_irq_restore(flags);
+
+ if (count)
+ *count = cnt;
+
+ return ret;
+}
+
+static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
+{
+ printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n",
+ trace->name, init_ret);
+}
+#ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Test dynamic code modification and ftrace filters */
+int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
+ struct trace_array *tr,
+ int (*func)(void))
+{
+ int save_ftrace_enabled = ftrace_enabled;
+ int save_tracer_enabled = tracer_enabled;
+ unsigned long count;
+ char *func_name;
+ int ret;
+
+ /* The ftrace test PASSED */
+ printk(KERN_CONT "PASSED\n");
+ pr_info("Testing dynamic ftrace: ");
+
+ /* enable tracing, and record the filter function */
+ ftrace_enabled = 1;
+ tracer_enabled = 1;
+
+ /* passed in by parameter to fool gcc from optimizing */
+ func();
+
+ /*
+ * Some archs *cough*PowerPC*cough* add characters to the
+ * start of the function names. We simply put a '*' to
+ * accommodate them.
+ */
+ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+
+ /* filter only on our function */
+ ftrace_set_filter(func_name, strlen(func_name), 1);
+
+ /* enable tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out;
+ }
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+
+ /* we should have nothing in the buffer */
+ ret = trace_test_buffer(tr, &count);
+ if (ret)
+ goto out;
+
+ if (count) {
+ ret = -1;
+ printk(KERN_CONT ".. filter did not filter .. ");
+ goto out;
+ }
+
+ /* call our function again */
+ func();
+
+ /* sleep again */
+ msleep(100);
+
+ /* stop the tracing. */
+ tracing_stop();
+ ftrace_enabled = 0;
+
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ /* we should only have one item */
+ if (!ret && count != 1) {
+ printk(KERN_CONT ".. filter failed count=%ld ..", count);
+ ret = -1;
+ goto out;
+ }
+
+ out:
+ ftrace_enabled = save_ftrace_enabled;
+ tracer_enabled = save_tracer_enabled;
+
+ /* Enable tracing on all functions again */
+ ftrace_set_filter(NULL, 0, 1);
+
+ return ret;
+}
+#else
+# define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * Simple verification test of ftrace function tracer.
+ * Enable ftrace, sleep 1/10 second, and then read the trace
+ * buffer to see if all is in order.
+ */
+int
+trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
+{
+ int save_ftrace_enabled = ftrace_enabled;
+ int save_tracer_enabled = tracer_enabled;
+ unsigned long count;
+ int ret;
+
+ /* make sure msleep has been recorded */
+ msleep(1);
+
+ /* start the tracing */
+ ftrace_enabled = 1;
+ tracer_enabled = 1;
+
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out;
+ }
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+ /* stop the tracing. */
+ tracing_stop();
+ ftrace_enabled = 0;
+
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ goto out;
+ }
+
+ ret = trace_selftest_startup_dynamic_tracing(trace, tr,
+ DYN_FTRACE_TEST_NAME);
+
+ out:
+ ftrace_enabled = save_ftrace_enabled;
+ tracer_enabled = save_tracer_enabled;
+
+ /* kill ftrace totally if we failed */
+ if (ret)
+ ftrace_kill();
+
+ return ret;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+/* Maximum number of functions to trace before diagnosing a hang */
+#define GRAPH_MAX_FUNC_TEST 100000000
+
+static void __ftrace_dump(bool disable_tracing);
+static unsigned int graph_hang_thresh;
+
+/* Wrap the real function entry probe to avoid possible hanging */
+static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
+{
+ /* This is harmlessly racy, we want to approximately detect a hang */
+ if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
+ ftrace_graph_stop();
+ printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
+ if (ftrace_dump_on_oops)
+ __ftrace_dump(false);
+ return 0;
+ }
+
+ return trace_graph_entry(trace);
+}
+
+/*
+ * Pretty much the same than for the function tracer from which the selftest
+ * has been borrowed.
+ */
+int
+trace_selftest_startup_function_graph(struct tracer *trace,
+ struct trace_array *tr)
+{
+ int ret;
+ unsigned long count;
+
+ /*
+ * Simulate the init() callback but we attach a watchdog callback
+ * to detect and recover from possible hangs
+ */
+ tracing_reset_online_cpus(tr);
+ set_graph_array(tr);
+ ret = register_ftrace_graph(&trace_graph_return,
+ &trace_graph_entry_watchdog);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out;
+ }
+ tracing_start_cmdline_record();
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+
+ /* Have we just recovered from a hang? */
+ if (graph_hang_thresh > GRAPH_MAX_FUNC_TEST) {
+ tracing_selftest_disabled = true;
+ ret = -1;
+ goto out;
+ }
+
+ tracing_stop();
+
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ goto out;
+ }
+
+ /* Don't test dynamic tracing, the function tracer already did */
+
+out:
+ /* Stop it if we failed */
+ if (ret)
+ ftrace_graph_stop();
+
+ return ret;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+
+#ifdef CONFIG_IRQSOFF_TRACER
+int
+trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long save_max = tracing_max_latency;
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* reset the max latency */
+ tracing_max_latency = 0;
+ /* disable interrupts for a bit */
+ local_irq_disable();
+ udelay(100);
+ local_irq_enable();
+
+ /*
+ * Stop the tracer to avoid a warning subsequent
+ * to buffer flipping failure because tracing_stop()
+ * disables the tr and max buffers, making flipping impossible
+ * in case of parallels max irqs off latencies.
+ */
+ trace->stop(tr);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check both trace buffers */
+ ret = trace_test_buffer(tr, NULL);
+ if (!ret)
+ ret = trace_test_buffer(&max_tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ }
+
+ tracing_max_latency = save_max;
+
+ return ret;
+}
+#endif /* CONFIG_IRQSOFF_TRACER */
+
+#ifdef CONFIG_PREEMPT_TRACER
+int
+trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long save_max = tracing_max_latency;
+ unsigned long count;
+ int ret;
+
+ /*
+ * Now that the big kernel lock is no longer preemptable,
+ * and this is called with the BKL held, it will always
+ * fail. If preemption is already disabled, simply
+ * pass the test. When the BKL is removed, or becomes
+ * preemptible again, we will once again test this,
+ * so keep it in.
+ */
+ if (preempt_count()) {
+ printk(KERN_CONT "can not test ... force ");
+ return 0;
+ }
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* reset the max latency */
+ tracing_max_latency = 0;
+ /* disable preemption for a bit */
+ preempt_disable();
+ udelay(100);
+ preempt_enable();
+
+ /*
+ * Stop the tracer to avoid a warning subsequent
+ * to buffer flipping failure because tracing_stop()
+ * disables the tr and max buffers, making flipping impossible
+ * in case of parallels max preempt off latencies.
+ */
+ trace->stop(tr);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check both trace buffers */
+ ret = trace_test_buffer(tr, NULL);
+ if (!ret)
+ ret = trace_test_buffer(&max_tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ }
+
+ tracing_max_latency = save_max;
+
+ return ret;
+}
+#endif /* CONFIG_PREEMPT_TRACER */
+
+#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER)
+int
+trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long save_max = tracing_max_latency;
+ unsigned long count;
+ int ret;
+
+ /*
+ * Now that the big kernel lock is no longer preemptable,
+ * and this is called with the BKL held, it will always
+ * fail. If preemption is already disabled, simply
+ * pass the test. When the BKL is removed, or becomes
+ * preemptible again, we will once again test this,
+ * so keep it in.
+ */
+ if (preempt_count()) {
+ printk(KERN_CONT "can not test ... force ");
+ return 0;
+ }
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out_no_start;
+ }
+
+ /* reset the max latency */
+ tracing_max_latency = 0;
+
+ /* disable preemption and interrupts for a bit */
+ preempt_disable();
+ local_irq_disable();
+ udelay(100);
+ preempt_enable();
+ /* reverse the order of preempt vs irqs */
+ local_irq_enable();
+
+ /*
+ * Stop the tracer to avoid a warning subsequent
+ * to buffer flipping failure because tracing_stop()
+ * disables the tr and max buffers, making flipping impossible
+ * in case of parallels max irqs/preempt off latencies.
+ */
+ trace->stop(tr);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check both trace buffers */
+ ret = trace_test_buffer(tr, NULL);
+ if (ret)
+ goto out;
+
+ ret = trace_test_buffer(&max_tr, &count);
+ if (ret)
+ goto out;
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ goto out;
+ }
+
+ /* do the test by disabling interrupts first this time */
+ tracing_max_latency = 0;
+ tracing_start();
+ trace->start(tr);
+
+ preempt_disable();
+ local_irq_disable();
+ udelay(100);
+ preempt_enable();
+ /* reverse the order of preempt vs irqs */
+ local_irq_enable();
+
+ trace->stop(tr);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check both trace buffers */
+ ret = trace_test_buffer(tr, NULL);
+ if (ret)
+ goto out;
+
+ ret = trace_test_buffer(&max_tr, &count);
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ goto out;
+ }
+
+out:
+ tracing_start();
+out_no_start:
+ trace->reset(tr);
+ tracing_max_latency = save_max;
+
+ return ret;
+}
+#endif /* CONFIG_IRQSOFF_TRACER && CONFIG_PREEMPT_TRACER */
+
+#ifdef CONFIG_NOP_TRACER
+int
+trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
+{
+ /* What could possibly go wrong? */
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SCHED_TRACER
+static int trace_wakeup_test_thread(void *data)
+{
+ /* Make this a RT thread, doesn't need to be too high */
+ struct sched_param param = { .sched_priority = 5 };
+ struct completion *x = data;
+
+ sched_setscheduler(current, SCHED_FIFO, &param);
+
+ /* Make it know we have a new prio */
+ complete(x);
+
+ /* now go to sleep and let the test wake us up */
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+
+ /* we are awake, now wait to disappear */
+ while (!kthread_should_stop()) {
+ /*
+ * This is an RT task, do short sleeps to let
+ * others run.
+ */
+ msleep(100);
+ }
+
+ return 0;
+}
+
+int
+trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long save_max = tracing_max_latency;
+ struct task_struct *p;
+ struct completion isrt;
+ unsigned long count;
+ int ret;
+
+ init_completion(&isrt);
+
+ /* create a high prio thread */
+ p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+ if (IS_ERR(p)) {
+ printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
+ return -1;
+ }
+
+ /* make sure the thread is running at an RT prio */
+ wait_for_completion(&isrt);
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* reset the max latency */
+ tracing_max_latency = 0;
+
+ /* sleep to let the RT thread sleep too */
+ msleep(100);
+
+ /*
+ * Yes this is slightly racy. It is possible that for some
+ * strange reason that the RT thread we created, did not
+ * call schedule for 100ms after doing the completion,
+ * and we do a wakeup on a task that already is awake.
+ * But that is extremely unlikely, and the worst thing that
+ * happens in such a case, is that we disable tracing.
+ * Honestly, if this race does happen something is horrible
+ * wrong with the system.
+ */
+
+ wake_up_process(p);
+
+ /* give a little time to let the thread wake up */
+ msleep(100);
+
+ /* stop the tracing. */
+ tracing_stop();
+ /* check both trace buffers */
+ ret = trace_test_buffer(tr, NULL);
+ if (!ret)
+ ret = trace_test_buffer(&max_tr, &count);
+
+
+ trace->reset(tr);
+ tracing_start();
+
+ tracing_max_latency = save_max;
+
+ /* kill the thread */
+ kthread_stop(p);
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_SCHED_TRACER */
+
+#ifdef CONFIG_CONTEXT_SWITCH_TRACER
+int
+trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_CONTEXT_SWITCH_TRACER */
+
+#ifdef CONFIG_SYSPROF_TRACER
+int
+trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_SYSPROF_TRACER */
+
+#ifdef CONFIG_BRANCH_TRACER
+int
+trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT ".. no entries found ..");
+ ret = -1;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+int
+trace_selftest_startup_hw_branches(struct tracer *trace,
+ struct trace_array *tr)
+{
+ struct trace_iterator *iter;
+ struct tracer tracer;
+ unsigned long count;
+ int ret;
+
+ if (!trace->open) {
+ printk(KERN_CONT "missing open function...");
+ return -1;
+ }
+
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /*
+ * The hw-branch tracer needs to collect the trace from the various
+ * cpu trace buffers - before tracing is stopped.
+ */
+ iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ memcpy(&tracer, trace, sizeof(tracer));
+
+ iter->trace = &tracer;
+ iter->tr = tr;
+ iter->pos = -1;
+ mutex_init(&iter->mutex);
+
+ trace->open(iter);
+
+ mutex_destroy(&iter->mutex);
+ kfree(iter);
+
+ tracing_stop();
+
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ if (!ret && !count) {
+ printk(KERN_CONT "no entries found..");
+ ret = -1;
+ }
+
+ return ret;
+}
+#endif /* CONFIG_HW_BRANCH_TRACER */
+
+#ifdef CONFIG_KSYM_TRACER
+static int ksym_selftest_dummy;
+
+int
+trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ ksym_selftest_dummy = 0;
+ /* Register the read-write tracing request */
+
+ ret = process_new_ksym_entry("ksym_selftest_dummy",
+ HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+ (unsigned long)(&ksym_selftest_dummy));
+
+ if (ret < 0) {
+ printk(KERN_CONT "ksym_trace read-write startup test failed\n");
+ goto ret_path;
+ }
+ /* Perform a read and a write operation over the dummy variable to
+ * trigger the tracer
+ */
+ if (ksym_selftest_dummy == 0)
+ ksym_selftest_dummy++;
+
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ /* read & write operations - one each is performed on the dummy variable
+ * triggering two entries in the trace buffer
+ */
+ if (!ret && count != 2) {
+ printk(KERN_CONT "Ksym tracer startup test failed");
+ ret = -1;
+ }
+
+ret_path:
+ return ret;
+}
+#endif /* CONFIG_KSYM_TRACER */
+
diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c
new file mode 100644
index 00000000000..54dd77cce5b
--- /dev/null
+++ b/kernel/trace/trace_selftest_dynamic.c
@@ -0,0 +1,7 @@
+#include "trace.h"
+
+int DYN_FTRACE_TEST_NAME(void)
+{
+ /* used to call mcount */
+ return 0;
+}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
new file mode 100644
index 00000000000..f4bc9b27de5
--- /dev/null
+++ b/kernel/trace/trace_stack.c
@@ -0,0 +1,374 @@
+/*
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include "trace.h"
+
+#define STACK_TRACE_ENTRIES 500
+
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
+ { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
+static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
+
+static struct stack_trace max_stack_trace = {
+ .max_entries = STACK_TRACE_ENTRIES,
+ .entries = stack_dump_trace,
+};
+
+static unsigned long max_stack_size;
+static arch_spinlock_t max_stack_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+static int stack_trace_disabled __read_mostly;
+static DEFINE_PER_CPU(int, trace_active);
+static DEFINE_MUTEX(stack_sysctl_mutex);
+
+int stack_tracer_enabled;
+static int last_stack_tracer_enabled;
+
+static inline void check_stack(void)
+{
+ unsigned long this_size, flags;
+ unsigned long *p, *top, *start;
+ int i;
+
+ this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+ this_size = THREAD_SIZE - this_size;
+
+ if (this_size <= max_stack_size)
+ return;
+
+ /* we do not handle interrupt stacks yet */
+ if (!object_is_on_stack(&this_size))
+ return;
+
+ local_irq_save(flags);
+ arch_spin_lock(&max_stack_lock);
+
+ /* a race could have already updated it */
+ if (this_size <= max_stack_size)
+ goto out;
+
+ max_stack_size = this_size;
+
+ max_stack_trace.nr_entries = 0;
+ max_stack_trace.skip = 3;
+
+ save_stack_trace(&max_stack_trace);
+
+ /*
+ * Now find where in the stack these are.
+ */
+ i = 0;
+ start = &this_size;
+ top = (unsigned long *)
+ (((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
+
+ /*
+ * Loop through all the entries. One of the entries may
+ * for some reason be missed on the stack, so we may
+ * have to account for them. If they are all there, this
+ * loop will only happen once. This code only takes place
+ * on a new max, so it is far from a fast path.
+ */
+ while (i < max_stack_trace.nr_entries) {
+ int found = 0;
+
+ stack_dump_index[i] = this_size;
+ p = start;
+
+ for (; p < top && i < max_stack_trace.nr_entries; p++) {
+ if (*p == stack_dump_trace[i]) {
+ this_size = stack_dump_index[i++] =
+ (top - p) * sizeof(unsigned long);
+ found = 1;
+ /* Start the search from here */
+ start = p + 1;
+ }
+ }
+
+ if (!found)
+ i++;
+ }
+
+ out:
+ arch_spin_unlock(&max_stack_lock);
+ local_irq_restore(flags);
+}
+
+static void
+stack_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+ int cpu, resched;
+
+ if (unlikely(!ftrace_enabled || stack_trace_disabled))
+ return;
+
+ resched = ftrace_preempt_disable();
+
+ cpu = raw_smp_processor_id();
+ /* no atomic needed, we only modify this variable by this cpu */
+ if (per_cpu(trace_active, cpu)++ != 0)
+ goto out;
+
+ check_stack();
+
+ out:
+ per_cpu(trace_active, cpu)--;
+ /* prevent recursion in schedule */
+ ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+ .func = stack_trace_call,
+};
+
+static ssize_t
+stack_max_size_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long *ptr = filp->private_data;
+ char buf[64];
+ int r;
+
+ r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
+ if (r > sizeof(buf))
+ r = sizeof(buf);
+ return simple_read_from_buffer(ubuf, count, ppos, buf, r);
+}
+
+static ssize_t
+stack_max_size_write(struct file *filp, const char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ long *ptr = filp->private_data;
+ unsigned long val, flags;
+ char buf[64];
+ int ret;
+ int cpu;
+
+ if (count >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, count))
+ return -EFAULT;
+
+ buf[count] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ local_irq_save(flags);
+
+ /*
+ * In case we trace inside arch_spin_lock() or after (NMI),
+ * we will cause circular lock, so we also need to increase
+ * the percpu trace_active here.
+ */
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)++;
+
+ arch_spin_lock(&max_stack_lock);
+ *ptr = val;
+ arch_spin_unlock(&max_stack_lock);
+
+ per_cpu(trace_active, cpu)--;
+ local_irq_restore(flags);
+
+ return count;
+}
+
+static const struct file_operations stack_max_size_fops = {
+ .open = tracing_open_generic,
+ .read = stack_max_size_read,
+ .write = stack_max_size_write,
+};
+
+static void *
+__next(struct seq_file *m, loff_t *pos)
+{
+ long n = *pos - 1;
+
+ if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+ return NULL;
+
+ m->private = (void *)n;
+ return &m->private;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return __next(m, pos);
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+ int cpu;
+
+ local_irq_disable();
+
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)++;
+
+ arch_spin_lock(&max_stack_lock);
+
+ if (*pos == 0)
+ return SEQ_START_TOKEN;
+
+ return __next(m, pos);
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+ int cpu;
+
+ arch_spin_unlock(&max_stack_lock);
+
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)--;
+
+ local_irq_enable();
+}
+
+static int trace_lookup_stack(struct seq_file *m, long i)
+{
+ unsigned long addr = stack_dump_trace[i];
+
+ return seq_printf(m, "%pF\n", (void *)addr);
+}
+
+static void print_disabled(struct seq_file *m)
+{
+ seq_puts(m, "#\n"
+ "# Stack tracer disabled\n"
+ "#\n"
+ "# To enable the stack tracer, either add 'stacktrace' to the\n"
+ "# kernel command line\n"
+ "# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n"
+ "#\n");
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+ long i;
+ int size;
+
+ if (v == SEQ_START_TOKEN) {
+ seq_printf(m, " Depth Size Location"
+ " (%d entries)\n"
+ " ----- ---- --------\n",
+ max_stack_trace.nr_entries - 1);
+
+ if (!stack_tracer_enabled && !max_stack_size)
+ print_disabled(m);
+
+ return 0;
+ }
+
+ i = *(long *)v;
+
+ if (i >= max_stack_trace.nr_entries ||
+ stack_dump_trace[i] == ULONG_MAX)
+ return 0;
+
+ if (i+1 == max_stack_trace.nr_entries ||
+ stack_dump_trace[i+1] == ULONG_MAX)
+ size = stack_dump_index[i];
+ else
+ size = stack_dump_index[i] - stack_dump_index[i+1];
+
+ seq_printf(m, "%3ld) %8d %5d ", i, stack_dump_index[i], size);
+
+ trace_lookup_stack(m, i);
+
+ return 0;
+}
+
+static const struct seq_operations stack_trace_seq_ops = {
+ .start = t_start,
+ .next = t_next,
+ .stop = t_stop,
+ .show = t_show,
+};
+
+static int stack_trace_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &stack_trace_seq_ops);
+}
+
+static const struct file_operations stack_trace_fops = {
+ .open = stack_trace_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+int
+stack_trace_sysctl(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+
+ mutex_lock(&stack_sysctl_mutex);
+
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (ret || !write ||
+ (last_stack_tracer_enabled == !!stack_tracer_enabled))
+ goto out;
+
+ last_stack_tracer_enabled = !!stack_tracer_enabled;
+
+ if (stack_tracer_enabled)
+ register_ftrace_function(&trace_ops);
+ else
+ unregister_ftrace_function(&trace_ops);
+
+ out:
+ mutex_unlock(&stack_sysctl_mutex);
+ return ret;
+}
+
+static __init int enable_stacktrace(char *str)
+{
+ stack_tracer_enabled = 1;
+ last_stack_tracer_enabled = 1;
+ return 1;
+}
+__setup("stacktrace", enable_stacktrace);
+
+static __init int stack_trace_init(void)
+{
+ struct dentry *d_tracer;
+
+ d_tracer = tracing_init_dentry();
+
+ trace_create_file("stack_max_size", 0644, d_tracer,
+ &max_stack_size, &stack_max_size_fops);
+
+ trace_create_file("stack_trace", 0444, d_tracer,
+ NULL, &stack_trace_fops);
+
+ if (stack_tracer_enabled)
+ register_ftrace_function(&trace_ops);
+
+ return 0;
+}
+
+device_initcall(stack_trace_init);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
new file mode 100644
index 00000000000..a4bb239eb98
--- /dev/null
+++ b/kernel/trace/trace_stat.c
@@ -0,0 +1,387 @@
+/*
+ * Infrastructure for statistic tracing (histogram output).
+ *
+ * Copyright (C) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ * Based on the code from trace_branch.c which is
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/debugfs.h>
+#include "trace_stat.h"
+#include "trace.h"
+
+
+/*
+ * List of stat red-black nodes from a tracer
+ * We use a such tree to sort quickly the stat
+ * entries from the tracer.
+ */
+struct stat_node {
+ struct rb_node node;
+ void *stat;
+};
+
+/* A stat session is the stats output in one file */
+struct stat_session {
+ struct list_head session_list;
+ struct tracer_stat *ts;
+ struct rb_root stat_root;
+ struct mutex stat_mutex;
+ struct dentry *file;
+};
+
+/* All of the sessions currently in use. Each stat file embed one session */
+static LIST_HEAD(all_stat_sessions);
+static DEFINE_MUTEX(all_stat_sessions_mutex);
+
+/* The root directory for all stat files */
+static struct dentry *stat_dir;
+
+/*
+ * Iterate through the rbtree using a post order traversal path
+ * to release the next node.
+ * It won't necessary release one at each iteration
+ * but it will at least advance closer to the next one
+ * to be released.
+ */
+static struct rb_node *release_next(struct tracer_stat *ts,
+ struct rb_node *node)
+{
+ struct stat_node *snode;
+ struct rb_node *parent = rb_parent(node);
+
+ if (node->rb_left)
+ return node->rb_left;
+ else if (node->rb_right)
+ return node->rb_right;
+ else {
+ if (!parent)
+ ;
+ else if (parent->rb_left == node)
+ parent->rb_left = NULL;
+ else
+ parent->rb_right = NULL;
+
+ snode = container_of(node, struct stat_node, node);
+ if (ts->stat_release)
+ ts->stat_release(snode->stat);
+ kfree(snode);
+
+ return parent;
+ }
+}
+
+static void __reset_stat_session(struct stat_session *session)
+{
+ struct rb_node *node = session->stat_root.rb_node;
+
+ while (node)
+ node = release_next(session->ts, node);
+
+ session->stat_root = RB_ROOT;
+}
+
+static void reset_stat_session(struct stat_session *session)
+{
+ mutex_lock(&session->stat_mutex);
+ __reset_stat_session(session);
+ mutex_unlock(&session->stat_mutex);
+}
+
+static void destroy_session(struct stat_session *session)
+{
+ debugfs_remove(session->file);
+ __reset_stat_session(session);
+ mutex_destroy(&session->stat_mutex);
+ kfree(session);
+}
+
+typedef int (*cmp_stat_t)(void *, void *);
+
+static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+ struct stat_node *data;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+ data->stat = stat;
+
+ /*
+ * Figure out where to put new node
+ * This is a descendent sorting
+ */
+ while (*new) {
+ struct stat_node *this;
+ int result;
+
+ this = container_of(*new, struct stat_node, node);
+ result = cmp(data->stat, this->stat);
+
+ parent = *new;
+ if (result >= 0)
+ new = &((*new)->rb_left);
+ else
+ new = &((*new)->rb_right);
+ }
+
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+ return 0;
+}
+
+/*
+ * For tracers that don't provide a stat_cmp callback.
+ * This one will force an insertion as right-most node
+ * in the rbtree.
+ */
+static int dummy_cmp(void *p1, void *p2)
+{
+ return -1;
+}
+
+/*
+ * Initialize the stat rbtree at each trace_stat file opening.
+ * All of these copies and sorting are required on all opening
+ * since the stats could have changed between two file sessions.
+ */
+static int stat_seq_init(struct stat_session *session)
+{
+ struct tracer_stat *ts = session->ts;
+ struct rb_root *root = &session->stat_root;
+ void *stat;
+ int ret = 0;
+ int i;
+
+ mutex_lock(&session->stat_mutex);
+ __reset_stat_session(session);
+
+ if (!ts->stat_cmp)
+ ts->stat_cmp = dummy_cmp;
+
+ stat = ts->stat_start(ts);
+ if (!stat)
+ goto exit;
+
+ ret = insert_stat(root, stat, ts->stat_cmp);
+ if (ret)
+ goto exit;
+
+ /*
+ * Iterate over the tracer stat entries and store them in an rbtree.
+ */
+ for (i = 1; ; i++) {
+ stat = ts->stat_next(stat, i);
+
+ /* End of insertion */
+ if (!stat)
+ break;
+
+ ret = insert_stat(root, stat, ts->stat_cmp);
+ if (ret)
+ goto exit_free_rbtree;
+ }
+
+exit:
+ mutex_unlock(&session->stat_mutex);
+ return ret;
+
+exit_free_rbtree:
+ __reset_stat_session(session);
+ mutex_unlock(&session->stat_mutex);
+ return ret;
+}
+
+
+static void *stat_seq_start(struct seq_file *s, loff_t *pos)
+{
+ struct stat_session *session = s->private;
+ struct rb_node *node;
+ int n = *pos;
+ int i;
+
+ /* Prevent from tracer switch or rbtree modification */
+ mutex_lock(&session->stat_mutex);
+
+ /* If we are in the beginning of the file, print the headers */
+ if (session->ts->stat_headers) {
+ if (n == 0)
+ return SEQ_START_TOKEN;
+ n--;
+ }
+
+ node = rb_first(&session->stat_root);
+ for (i = 0; node && i < n; i++)
+ node = rb_next(node);
+
+ return node;
+}
+
+static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
+{
+ struct stat_session *session = s->private;
+ struct rb_node *node = p;
+
+ (*pos)++;
+
+ if (p == SEQ_START_TOKEN)
+ return rb_first(&session->stat_root);
+
+ return rb_next(node);
+}
+
+static void stat_seq_stop(struct seq_file *s, void *p)
+{
+ struct stat_session *session = s->private;
+ mutex_unlock(&session->stat_mutex);
+}
+
+static int stat_seq_show(struct seq_file *s, void *v)
+{
+ struct stat_session *session = s->private;
+ struct stat_node *l = container_of(v, struct stat_node, node);
+
+ if (v == SEQ_START_TOKEN)
+ return session->ts->stat_headers(s);
+
+ return session->ts->stat_show(s, l->stat);
+}
+
+static const struct seq_operations trace_stat_seq_ops = {
+ .start = stat_seq_start,
+ .next = stat_seq_next,
+ .stop = stat_seq_stop,
+ .show = stat_seq_show
+};
+
+/* The session stat is refilled and resorted at each stat file opening */
+static int tracing_stat_open(struct inode *inode, struct file *file)
+{
+ int ret;
+ struct seq_file *m;
+ struct stat_session *session = inode->i_private;
+
+ ret = stat_seq_init(session);
+ if (ret)
+ return ret;
+
+ ret = seq_open(file, &trace_stat_seq_ops);
+ if (ret) {
+ reset_stat_session(session);
+ return ret;
+ }
+
+ m = file->private_data;
+ m->private = session;
+ return ret;
+}
+
+/*
+ * Avoid consuming memory with our now useless rbtree.
+ */
+static int tracing_stat_release(struct inode *i, struct file *f)
+{
+ struct stat_session *session = i->i_private;
+
+ reset_stat_session(session);
+
+ return seq_release(i, f);
+}
+
+static const struct file_operations tracing_stat_fops = {
+ .open = tracing_stat_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = tracing_stat_release
+};
+
+static int tracing_stat_init(void)
+{
+ struct dentry *d_tracing;
+
+ d_tracing = tracing_init_dentry();
+
+ stat_dir = debugfs_create_dir("trace_stat", d_tracing);
+ if (!stat_dir)
+ pr_warning("Could not create debugfs "
+ "'trace_stat' entry\n");
+ return 0;
+}
+
+static int init_stat_file(struct stat_session *session)
+{
+ if (!stat_dir && tracing_stat_init())
+ return -ENODEV;
+
+ session->file = debugfs_create_file(session->ts->name, 0644,
+ stat_dir,
+ session, &tracing_stat_fops);
+ if (!session->file)
+ return -ENOMEM;
+ return 0;
+}
+
+int register_stat_tracer(struct tracer_stat *trace)
+{
+ struct stat_session *session, *node;
+ int ret;
+
+ if (!trace)
+ return -EINVAL;
+
+ if (!trace->stat_start || !trace->stat_next || !trace->stat_show)
+ return -EINVAL;
+
+ /* Already registered? */
+ mutex_lock(&all_stat_sessions_mutex);
+ list_for_each_entry(node, &all_stat_sessions, session_list) {
+ if (node->ts == trace) {
+ mutex_unlock(&all_stat_sessions_mutex);
+ return -EINVAL;
+ }
+ }
+ mutex_unlock(&all_stat_sessions_mutex);
+
+ /* Init the session */
+ session = kzalloc(sizeof(*session), GFP_KERNEL);
+ if (!session)
+ return -ENOMEM;
+
+ session->ts = trace;
+ INIT_LIST_HEAD(&session->session_list);
+ mutex_init(&session->stat_mutex);
+
+ ret = init_stat_file(session);
+ if (ret) {
+ destroy_session(session);
+ return ret;
+ }
+
+ /* Register */
+ mutex_lock(&all_stat_sessions_mutex);
+ list_add_tail(&session->session_list, &all_stat_sessions);
+ mutex_unlock(&all_stat_sessions_mutex);
+
+ return 0;
+}
+
+void unregister_stat_tracer(struct tracer_stat *trace)
+{
+ struct stat_session *node, *tmp;
+
+ mutex_lock(&all_stat_sessions_mutex);
+ list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
+ if (node->ts == trace) {
+ list_del(&node->session_list);
+ destroy_session(node);
+ break;
+ }
+ }
+ mutex_unlock(&all_stat_sessions_mutex);
+}
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
new file mode 100644
index 00000000000..8f03914b9a6
--- /dev/null
+++ b/kernel/trace/trace_stat.h
@@ -0,0 +1,33 @@
+#ifndef __TRACE_STAT_H
+#define __TRACE_STAT_H
+
+#include <linux/seq_file.h>
+
+/*
+ * If you want to provide a stat file (one-shot statistics), fill
+ * an iterator with stat_start/stat_next and a stat_show callbacks.
+ * The others callbacks are optional.
+ */
+struct tracer_stat {
+ /* The name of your stat file */
+ const char *name;
+ /* Iteration over statistic entries */
+ void *(*stat_start)(struct tracer_stat *trace);
+ void *(*stat_next)(void *prev, int idx);
+ /* Compare two entries for stats sorting */
+ int (*stat_cmp)(void *p1, void *p2);
+ /* Print a stat entry */
+ int (*stat_show)(struct seq_file *s, void *p);
+ /* Release an entry */
+ void (*stat_release)(void *stat);
+ /* Print the headers of your stat entries */
+ int (*stat_headers)(struct seq_file *s);
+};
+
+/*
+ * Destroy or create a stat file
+ */
+extern int register_stat_tracer(struct tracer_stat *trace);
+extern void unregister_stat_tracer(struct tracer_stat *trace);
+
+#endif /* __TRACE_STAT_H */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
new file mode 100644
index 00000000000..75289f372dd
--- /dev/null
+++ b/kernel/trace/trace_syscalls.c
@@ -0,0 +1,631 @@
+#include <trace/syscall.h>
+#include <trace/events/syscalls.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/perf_event.h>
+#include <asm/syscall.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+static DEFINE_MUTEX(syscall_trace_lock);
+static int sys_refcount_enter;
+static int sys_refcount_exit;
+static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+ struct syscall_metadata *start;
+ struct syscall_metadata *stop;
+ char str[KSYM_SYMBOL_LEN];
+
+
+ start = (struct syscall_metadata *)__start_syscalls_metadata;
+ stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+ kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+ for ( ; start < stop; start++) {
+ /*
+ * Only compare after the "sys" prefix. Archs that use
+ * syscall wrappers may have syscalls symbols aliases prefixed
+ * with "SyS" instead of "sys", leading to an unwanted
+ * mismatch.
+ */
+ if (start->name && !strcmp(start->name + 3, str + 3))
+ return start;
+ }
+ return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+ if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+ return NULL;
+
+ return syscalls_metadata[nr];
+}
+
+enum print_line_t
+print_syscall_enter(struct trace_iterator *iter, int flags)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *ent = iter->ent;
+ struct syscall_trace_enter *trace;
+ struct syscall_metadata *entry;
+ int i, ret, syscall;
+
+ trace = (typeof(trace))ent;
+ syscall = trace->nr;
+ entry = syscall_nr_to_meta(syscall);
+
+ if (!entry)
+ goto end;
+
+ if (entry->enter_event->id != ent->type) {
+ WARN_ON_ONCE(1);
+ goto end;
+ }
+
+ ret = trace_seq_printf(s, "%s(", entry->name);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ for (i = 0; i < entry->nb_args; i++) {
+ /* parameter types */
+ if (trace_flags & TRACE_ITER_VERBOSE) {
+ ret = trace_seq_printf(s, "%s ", entry->types[i]);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ /* parameter values */
+ ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i],
+ trace->args[i],
+ i == entry->nb_args - 1 ? "" : ", ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_putc(s, ')');
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+end:
+ ret = trace_seq_putc(s, '\n');
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+enum print_line_t
+print_syscall_exit(struct trace_iterator *iter, int flags)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *ent = iter->ent;
+ struct syscall_trace_exit *trace;
+ int syscall;
+ struct syscall_metadata *entry;
+ int ret;
+
+ trace = (typeof(trace))ent;
+ syscall = trace->nr;
+ entry = syscall_nr_to_meta(syscall);
+
+ if (!entry) {
+ trace_seq_printf(s, "\n");
+ return TRACE_TYPE_HANDLED;
+ }
+
+ if (entry->exit_event->id != ent->type) {
+ WARN_ON_ONCE(1);
+ return TRACE_TYPE_UNHANDLED;
+ }
+
+ ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
+ trace->ret);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+extern char *__bad_type_size(void);
+
+#define SYSCALL_FIELD(type, name) \
+ sizeof(type) != sizeof(trace.name) ? \
+ __bad_type_size() : \
+ #type, #name, offsetof(typeof(trace), name), \
+ sizeof(trace.name), is_signed_type(type)
+
+int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
+{
+ int i;
+ int ret;
+ struct syscall_metadata *entry = call->data;
+ struct syscall_trace_enter trace;
+ int offset = offsetof(struct syscall_trace_enter, args);
+
+ ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+ "\tsigned:%u;\n",
+ SYSCALL_FIELD(int, nr));
+ if (!ret)
+ return 0;
+
+ for (i = 0; i < entry->nb_args; i++) {
+ ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
+ entry->args[i]);
+ if (!ret)
+ return 0;
+ ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
+ "\tsigned:%u;\n", offset,
+ sizeof(unsigned long),
+ is_signed_type(unsigned long));
+ if (!ret)
+ return 0;
+ offset += sizeof(unsigned long);
+ }
+
+ trace_seq_puts(s, "\nprint fmt: \"");
+ for (i = 0; i < entry->nb_args; i++) {
+ ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
+ sizeof(unsigned long),
+ i == entry->nb_args - 1 ? "" : ", ");
+ if (!ret)
+ return 0;
+ }
+ trace_seq_putc(s, '"');
+
+ for (i = 0; i < entry->nb_args; i++) {
+ ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
+ entry->args[i]);
+ if (!ret)
+ return 0;
+ }
+
+ return trace_seq_putc(s, '\n');
+}
+
+int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
+{
+ int ret;
+ struct syscall_trace_exit trace;
+
+ ret = trace_seq_printf(s,
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+ "\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+ "\tsigned:%u;\n",
+ SYSCALL_FIELD(int, nr),
+ SYSCALL_FIELD(long, ret));
+ if (!ret)
+ return 0;
+
+ return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+}
+
+int syscall_enter_define_fields(struct ftrace_event_call *call)
+{
+ struct syscall_trace_enter trace;
+ struct syscall_metadata *meta = call->data;
+ int ret;
+ int i;
+ int offset = offsetof(typeof(trace), args);
+
+ ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < meta->nb_args; i++) {
+ ret = trace_define_field(call, meta->types[i],
+ meta->args[i], offset,
+ sizeof(unsigned long), 0,
+ FILTER_OTHER);
+ offset += sizeof(unsigned long);
+ }
+
+ return ret;
+}
+
+int syscall_exit_define_fields(struct ftrace_event_call *call)
+{
+ struct syscall_trace_exit trace;
+ int ret;
+
+ ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+ if (ret)
+ return ret;
+
+ ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
+ FILTER_OTHER);
+
+ return ret;
+}
+
+void ftrace_syscall_enter(struct pt_regs *regs, long id)
+{
+ struct syscall_trace_enter *entry;
+ struct syscall_metadata *sys_data;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ int size;
+ int syscall_nr;
+
+ syscall_nr = syscall_get_nr(current, regs);
+ if (syscall_nr < 0)
+ return;
+ if (!test_bit(syscall_nr, enabled_enter_syscalls))
+ return;
+
+ sys_data = syscall_nr_to_meta(syscall_nr);
+ if (!sys_data)
+ return;
+
+ size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
+
+ event = trace_current_buffer_lock_reserve(&buffer,
+ sys_data->enter_event->id, size, 0, 0);
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ entry->nr = syscall_nr;
+ syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
+
+ if (!filter_current_check_discard(buffer, sys_data->enter_event,
+ entry, event))
+ trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+}
+
+void ftrace_syscall_exit(struct pt_regs *regs, long ret)
+{
+ struct syscall_trace_exit *entry;
+ struct syscall_metadata *sys_data;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ int syscall_nr;
+
+ syscall_nr = syscall_get_nr(current, regs);
+ if (syscall_nr < 0)
+ return;
+ if (!test_bit(syscall_nr, enabled_exit_syscalls))
+ return;
+
+ sys_data = syscall_nr_to_meta(syscall_nr);
+ if (!sys_data)
+ return;
+
+ event = trace_current_buffer_lock_reserve(&buffer,
+ sys_data->exit_event->id, sizeof(*entry), 0, 0);
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ entry->nr = syscall_nr;
+ entry->ret = syscall_get_return_value(current, regs);
+
+ if (!filter_current_check_discard(buffer, sys_data->exit_event,
+ entry, event))
+ trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+}
+
+int reg_event_syscall_enter(struct ftrace_event_call *call)
+{
+ int ret = 0;
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+ if (num < 0 || num >= NR_syscalls)
+ return -ENOSYS;
+ mutex_lock(&syscall_trace_lock);
+ if (!sys_refcount_enter)
+ ret = register_trace_sys_enter(ftrace_syscall_enter);
+ if (!ret) {
+ set_bit(num, enabled_enter_syscalls);
+ sys_refcount_enter++;
+ }
+ mutex_unlock(&syscall_trace_lock);
+ return ret;
+}
+
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
+{
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+ if (num < 0 || num >= NR_syscalls)
+ return;
+ mutex_lock(&syscall_trace_lock);
+ sys_refcount_enter--;
+ clear_bit(num, enabled_enter_syscalls);
+ if (!sys_refcount_enter)
+ unregister_trace_sys_enter(ftrace_syscall_enter);
+ mutex_unlock(&syscall_trace_lock);
+}
+
+int reg_event_syscall_exit(struct ftrace_event_call *call)
+{
+ int ret = 0;
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+ if (num < 0 || num >= NR_syscalls)
+ return -ENOSYS;
+ mutex_lock(&syscall_trace_lock);
+ if (!sys_refcount_exit)
+ ret = register_trace_sys_exit(ftrace_syscall_exit);
+ if (!ret) {
+ set_bit(num, enabled_exit_syscalls);
+ sys_refcount_exit++;
+ }
+ mutex_unlock(&syscall_trace_lock);
+ return ret;
+}
+
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
+{
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+ if (num < 0 || num >= NR_syscalls)
+ return;
+ mutex_lock(&syscall_trace_lock);
+ sys_refcount_exit--;
+ clear_bit(num, enabled_exit_syscalls);
+ if (!sys_refcount_exit)
+ unregister_trace_sys_exit(ftrace_syscall_exit);
+ mutex_unlock(&syscall_trace_lock);
+}
+
+int init_syscall_trace(struct ftrace_event_call *call)
+{
+ int id;
+
+ id = register_ftrace_event(call->event);
+ if (!id)
+ return -ENODEV;
+ call->id = id;
+ INIT_LIST_HEAD(&call->fields);
+ return 0;
+}
+
+int __init init_ftrace_syscalls(void)
+{
+ struct syscall_metadata *meta;
+ unsigned long addr;
+ int i;
+
+ syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+ NR_syscalls, GFP_KERNEL);
+ if (!syscalls_metadata) {
+ WARN_ON(1);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < NR_syscalls; i++) {
+ addr = arch_syscall_addr(i);
+ meta = find_syscall_meta(addr);
+ if (!meta)
+ continue;
+
+ meta->syscall_nr = i;
+ syscalls_metadata[i] = meta;
+ }
+
+ return 0;
+}
+core_initcall(init_ftrace_syscalls);
+
+#ifdef CONFIG_EVENT_PROFILE
+
+static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
+static int sys_prof_refcount_enter;
+static int sys_prof_refcount_exit;
+
+static void prof_syscall_enter(struct pt_regs *regs, long id)
+{
+ struct syscall_metadata *sys_data;
+ struct syscall_trace_enter *rec;
+ unsigned long flags;
+ char *trace_buf;
+ char *raw_data;
+ int syscall_nr;
+ int rctx;
+ int size;
+ int cpu;
+
+ syscall_nr = syscall_get_nr(current, regs);
+ if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+ return;
+
+ sys_data = syscall_nr_to_meta(syscall_nr);
+ if (!sys_data)
+ return;
+
+ /* get the size after alignment with the u32 buffer size field */
+ size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
+ size = ALIGN(size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+
+ if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ "profile buffer not large enough"))
+ return;
+
+ /* Protect the per cpu buffer, begin the rcu read side */
+ local_irq_save(flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
+ cpu = smp_processor_id();
+
+ trace_buf = rcu_dereference(perf_trace_buf);
+
+ if (!trace_buf)
+ goto end;
+
+ raw_data = per_cpu_ptr(trace_buf, cpu);
+
+ /* zero the dead bytes from align to not leak stack to user */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+ rec = (struct syscall_trace_enter *) raw_data;
+ tracing_generic_entry_update(&rec->ent, 0, 0);
+ rec->ent.type = sys_data->enter_event->id;
+ rec->nr = syscall_nr;
+ syscall_get_arguments(current, regs, 0, sys_data->nb_args,
+ (unsigned long *)&rec->args);
+ perf_tp_event(sys_data->enter_event->id, 0, 1, rec, size);
+
+end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
+ local_irq_restore(flags);
+}
+
+int prof_sysenter_enable(struct ftrace_event_call *call)
+{
+ int ret = 0;
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+ mutex_lock(&syscall_trace_lock);
+ if (!sys_prof_refcount_enter)
+ ret = register_trace_sys_enter(prof_syscall_enter);
+ if (ret) {
+ pr_info("event trace: Could not activate"
+ "syscall entry trace point");
+ } else {
+ set_bit(num, enabled_prof_enter_syscalls);
+ sys_prof_refcount_enter++;
+ }
+ mutex_unlock(&syscall_trace_lock);
+ return ret;
+}
+
+void prof_sysenter_disable(struct ftrace_event_call *call)
+{
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+ mutex_lock(&syscall_trace_lock);
+ sys_prof_refcount_enter--;
+ clear_bit(num, enabled_prof_enter_syscalls);
+ if (!sys_prof_refcount_enter)
+ unregister_trace_sys_enter(prof_syscall_enter);
+ mutex_unlock(&syscall_trace_lock);
+}
+
+static void prof_syscall_exit(struct pt_regs *regs, long ret)
+{
+ struct syscall_metadata *sys_data;
+ struct syscall_trace_exit *rec;
+ unsigned long flags;
+ int syscall_nr;
+ char *trace_buf;
+ char *raw_data;
+ int rctx;
+ int size;
+ int cpu;
+
+ syscall_nr = syscall_get_nr(current, regs);
+ if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+ return;
+
+ sys_data = syscall_nr_to_meta(syscall_nr);
+ if (!sys_data)
+ return;
+
+ /* We can probably do that at build time */
+ size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+
+ /*
+ * Impossible, but be paranoid with the future
+ * How to put this check outside runtime?
+ */
+ if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ "exit event has grown above profile buffer size"))
+ return;
+
+ /* Protect the per cpu buffer, begin the rcu read side */
+ local_irq_save(flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
+ cpu = smp_processor_id();
+
+ trace_buf = rcu_dereference(perf_trace_buf);
+
+ if (!trace_buf)
+ goto end;
+
+ raw_data = per_cpu_ptr(trace_buf, cpu);
+
+ /* zero the dead bytes from align to not leak stack to user */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+ rec = (struct syscall_trace_exit *)raw_data;
+
+ tracing_generic_entry_update(&rec->ent, 0, 0);
+ rec->ent.type = sys_data->exit_event->id;
+ rec->nr = syscall_nr;
+ rec->ret = syscall_get_return_value(current, regs);
+
+ perf_tp_event(sys_data->exit_event->id, 0, 1, rec, size);
+
+end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
+ local_irq_restore(flags);
+}
+
+int prof_sysexit_enable(struct ftrace_event_call *call)
+{
+ int ret = 0;
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+ mutex_lock(&syscall_trace_lock);
+ if (!sys_prof_refcount_exit)
+ ret = register_trace_sys_exit(prof_syscall_exit);
+ if (ret) {
+ pr_info("event trace: Could not activate"
+ "syscall entry trace point");
+ } else {
+ set_bit(num, enabled_prof_exit_syscalls);
+ sys_prof_refcount_exit++;
+ }
+ mutex_unlock(&syscall_trace_lock);
+ return ret;
+}
+
+void prof_sysexit_disable(struct ftrace_event_call *call)
+{
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+ mutex_lock(&syscall_trace_lock);
+ sys_prof_refcount_exit--;
+ clear_bit(num, enabled_prof_exit_syscalls);
+ if (!sys_prof_refcount_exit)
+ unregister_trace_sys_exit(prof_syscall_exit);
+ mutex_unlock(&syscall_trace_lock);
+}
+
+#endif
+
+
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
new file mode 100644
index 00000000000..a7974a552ca
--- /dev/null
+++ b/kernel/trace/trace_sysprof.c
@@ -0,0 +1,329 @@
+/*
+ * trace stack traces
+ *
+ * Copyright (C) 2004-2008, Soeren Sandmann
+ * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ */
+#include <linux/kallsyms.h>
+#include <linux/debugfs.h>
+#include <linux/hrtimer.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/fs.h>
+
+#include <asm/stacktrace.h>
+
+#include "trace.h"
+
+static struct trace_array *sysprof_trace;
+static int __read_mostly tracer_enabled;
+
+/*
+ * 1 msec sample interval by default:
+ */
+static unsigned long sample_period = 1000000;
+static const unsigned int sample_max_depth = 512;
+
+static DEFINE_MUTEX(sample_timer_lock);
+/*
+ * Per CPU hrtimers that do the profiling:
+ */
+static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer);
+
+struct stack_frame {
+ const void __user *next_fp;
+ unsigned long return_address;
+};
+
+static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+{
+ int ret;
+
+ if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+ return 0;
+
+ ret = 1;
+ pagefault_disable();
+ if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
+ ret = 0;
+ pagefault_enable();
+
+ return ret;
+}
+
+struct backtrace_info {
+ struct trace_array_cpu *data;
+ struct trace_array *tr;
+ int pos;
+};
+
+static void
+backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+ /* Ignore warnings */
+}
+
+static void backtrace_warning(void *data, char *msg)
+{
+ /* Ignore warnings */
+}
+
+static int backtrace_stack(void *data, char *name)
+{
+ /* Don't bother with IRQ stacks for now */
+ return -1;
+}
+
+static void backtrace_address(void *data, unsigned long addr, int reliable)
+{
+ struct backtrace_info *info = data;
+
+ if (info->pos < sample_max_depth && reliable) {
+ __trace_special(info->tr, info->data, 1, addr, 0);
+
+ info->pos++;
+ }
+}
+
+static const struct stacktrace_ops backtrace_ops = {
+ .warning = backtrace_warning,
+ .warning_symbol = backtrace_warning_symbol,
+ .stack = backtrace_stack,
+ .address = backtrace_address,
+ .walk_stack = print_context_stack,
+};
+
+static int
+trace_kernel(struct pt_regs *regs, struct trace_array *tr,
+ struct trace_array_cpu *data)
+{
+ struct backtrace_info info;
+ unsigned long bp;
+ char *stack;
+
+ info.tr = tr;
+ info.data = data;
+ info.pos = 1;
+
+ __trace_special(info.tr, info.data, 1, regs->ip, 0);
+
+ stack = ((char *)regs + sizeof(struct pt_regs));
+#ifdef CONFIG_FRAME_POINTER
+ bp = regs->bp;
+#else
+ bp = 0;
+#endif
+
+ dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, &info);
+
+ return info.pos;
+}
+
+static void timer_notify(struct pt_regs *regs, int cpu)
+{
+ struct trace_array_cpu *data;
+ struct stack_frame frame;
+ struct trace_array *tr;
+ const void __user *fp;
+ int is_user;
+ int i;
+
+ if (!regs)
+ return;
+
+ tr = sysprof_trace;
+ data = tr->data[cpu];
+ is_user = user_mode(regs);
+
+ if (!current || current->pid == 0)
+ return;
+
+ if (is_user && current->state != TASK_RUNNING)
+ return;
+
+ __trace_special(tr, data, 0, 0, current->pid);
+
+ if (!is_user)
+ i = trace_kernel(regs, tr, data);
+ else
+ i = 0;
+
+ /*
+ * Trace user stack if we are not a kernel thread
+ */
+ if (current->mm && i < sample_max_depth) {
+ regs = (struct pt_regs *)current->thread.sp0 - 1;
+
+ fp = (void __user *)regs->bp;
+
+ __trace_special(tr, data, 2, regs->ip, 0);
+
+ while (i < sample_max_depth) {
+ frame.next_fp = NULL;
+ frame.return_address = 0;
+ if (!copy_stack_frame(fp, &frame))
+ break;
+ if ((unsigned long)fp < regs->sp)
+ break;
+
+ __trace_special(tr, data, 2, frame.return_address,
+ (unsigned long)fp);
+ fp = frame.next_fp;
+
+ i++;
+ }
+
+ }
+
+ /*
+ * Special trace entry if we overflow the max depth:
+ */
+ if (i == sample_max_depth)
+ __trace_special(tr, data, -1, -1, -1);
+
+ __trace_special(tr, data, 3, current->pid, i);
+}
+
+static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer)
+{
+ /* trace here */
+ timer_notify(get_irq_regs(), smp_processor_id());
+
+ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
+
+ return HRTIMER_RESTART;
+}
+
+static void start_stack_timer(void *unused)
+{
+ struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer);
+
+ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer->function = stack_trace_timer_fn;
+
+ hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+ HRTIMER_MODE_REL_PINNED);
+}
+
+static void start_stack_timers(void)
+{
+ on_each_cpu(start_stack_timer, NULL, 1);
+}
+
+static void stop_stack_timer(int cpu)
+{
+ struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu);
+
+ hrtimer_cancel(hrtimer);
+}
+
+static void stop_stack_timers(void)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ stop_stack_timer(cpu);
+}
+
+static void stop_stack_trace(struct trace_array *tr)
+{
+ mutex_lock(&sample_timer_lock);
+ stop_stack_timers();
+ tracer_enabled = 0;
+ mutex_unlock(&sample_timer_lock);
+}
+
+static int stack_trace_init(struct trace_array *tr)
+{
+ sysprof_trace = tr;
+
+ tracing_start_cmdline_record();
+
+ mutex_lock(&sample_timer_lock);
+ start_stack_timers();
+ tracer_enabled = 1;
+ mutex_unlock(&sample_timer_lock);
+ return 0;
+}
+
+static void stack_trace_reset(struct trace_array *tr)
+{
+ tracing_stop_cmdline_record();
+ stop_stack_trace(tr);
+}
+
+static struct tracer stack_trace __read_mostly =
+{
+ .name = "sysprof",
+ .init = stack_trace_init,
+ .reset = stack_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_sysprof,
+#endif
+};
+
+__init static int init_stack_trace(void)
+{
+ return register_tracer(&stack_trace);
+}
+device_initcall(init_stack_trace);
+
+#define MAX_LONG_DIGITS 22
+
+static ssize_t
+sysprof_sample_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[MAX_LONG_DIGITS];
+ int r;
+
+ r = sprintf(buf, "%ld\n", nsecs_to_usecs(sample_period));
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+sysprof_sample_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[MAX_LONG_DIGITS];
+ unsigned long val;
+
+ if (cnt > MAX_LONG_DIGITS-1)
+ cnt = MAX_LONG_DIGITS-1;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ val = simple_strtoul(buf, NULL, 10);
+ /*
+ * Enforce a minimum sample period of 100 usecs:
+ */
+ if (val < 100)
+ val = 100;
+
+ mutex_lock(&sample_timer_lock);
+ stop_stack_timers();
+ sample_period = val * 1000;
+ start_stack_timers();
+ mutex_unlock(&sample_timer_lock);
+
+ return cnt;
+}
+
+static const struct file_operations sysprof_sample_fops = {
+ .read = sysprof_sample_read,
+ .write = sysprof_sample_write,
+};
+
+void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
+{
+
+ trace_create_file("sysprof_sample_period", 0644,
+ d_tracer, NULL, &sysprof_sample_fops);
+}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
new file mode 100644
index 00000000000..40cafb07dff
--- /dev/null
+++ b/kernel/trace/trace_workqueue.c
@@ -0,0 +1,295 @@
+/*
+ * Workqueue statistical tracer.
+ *
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+
+#include <trace/events/workqueue.h>
+#include <linux/list.h>
+#include <linux/percpu.h>
+#include <linux/kref.h>
+#include "trace_stat.h"
+#include "trace.h"
+
+
+/* A cpu workqueue thread */
+struct cpu_workqueue_stats {
+ struct list_head list;
+ struct kref kref;
+ int cpu;
+ pid_t pid;
+/* Can be inserted from interrupt or user context, need to be atomic */
+ atomic_t inserted;
+/*
+ * Don't need to be atomic, works are serialized in a single workqueue thread
+ * on a single CPU.
+ */
+ unsigned int executed;
+};
+
+/* List of workqueue threads on one cpu */
+struct workqueue_global_stats {
+ struct list_head list;
+ spinlock_t lock;
+};
+
+/* Don't need a global lock because allocated before the workqueues, and
+ * never freed.
+ */
+static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
+#define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu))
+
+static void cpu_workqueue_stat_free(struct kref *kref)
+{
+ kfree(container_of(kref, struct cpu_workqueue_stats, kref));
+}
+
+/* Insertion of a work */
+static void
+probe_workqueue_insertion(struct task_struct *wq_thread,
+ struct work_struct *work)
+{
+ int cpu = cpumask_first(&wq_thread->cpus_allowed);
+ struct cpu_workqueue_stats *node;
+ unsigned long flags;
+
+ spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+ list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
+ if (node->pid == wq_thread->pid) {
+ atomic_inc(&node->inserted);
+ goto found;
+ }
+ }
+ pr_debug("trace_workqueue: entry not found\n");
+found:
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+}
+
+/* Execution of a work */
+static void
+probe_workqueue_execution(struct task_struct *wq_thread,
+ struct work_struct *work)
+{
+ int cpu = cpumask_first(&wq_thread->cpus_allowed);
+ struct cpu_workqueue_stats *node;
+ unsigned long flags;
+
+ spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+ list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
+ if (node->pid == wq_thread->pid) {
+ node->executed++;
+ goto found;
+ }
+ }
+ pr_debug("trace_workqueue: entry not found\n");
+found:
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+}
+
+/* Creation of a cpu workqueue thread */
+static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
+{
+ struct cpu_workqueue_stats *cws;
+ unsigned long flags;
+
+ WARN_ON(cpu < 0);
+
+ /* Workqueues are sometimes created in atomic context */
+ cws = kzalloc(sizeof(struct cpu_workqueue_stats), GFP_ATOMIC);
+ if (!cws) {
+ pr_warning("trace_workqueue: not enough memory\n");
+ return;
+ }
+ INIT_LIST_HEAD(&cws->list);
+ kref_init(&cws->kref);
+ cws->cpu = cpu;
+ cws->pid = wq_thread->pid;
+
+ spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+ list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list);
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+}
+
+/* Destruction of a cpu workqueue thread */
+static void probe_workqueue_destruction(struct task_struct *wq_thread)
+{
+ /* Workqueue only execute on one cpu */
+ int cpu = cpumask_first(&wq_thread->cpus_allowed);
+ struct cpu_workqueue_stats *node, *next;
+ unsigned long flags;
+
+ spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+ list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
+ list) {
+ if (node->pid == wq_thread->pid) {
+ list_del(&node->list);
+ kref_put(&node->kref, cpu_workqueue_stat_free);
+ goto found;
+ }
+ }
+
+ pr_debug("trace_workqueue: don't find workqueue to destroy\n");
+found:
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+
+}
+
+static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
+{
+ unsigned long flags;
+ struct cpu_workqueue_stats *ret = NULL;
+
+
+ spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+
+ if (!list_empty(&workqueue_cpu_stat(cpu)->list)) {
+ ret = list_entry(workqueue_cpu_stat(cpu)->list.next,
+ struct cpu_workqueue_stats, list);
+ kref_get(&ret->kref);
+ }
+
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+
+ return ret;
+}
+
+static void *workqueue_stat_start(struct tracer_stat *trace)
+{
+ int cpu;
+ void *ret = NULL;
+
+ for_each_possible_cpu(cpu) {
+ ret = workqueue_stat_start_cpu(cpu);
+ if (ret)
+ return ret;
+ }
+ return NULL;
+}
+
+static void *workqueue_stat_next(void *prev, int idx)
+{
+ struct cpu_workqueue_stats *prev_cws = prev;
+ struct cpu_workqueue_stats *ret;
+ int cpu = prev_cws->cpu;
+ unsigned long flags;
+
+ spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+ if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) {
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+ do {
+ cpu = cpumask_next(cpu, cpu_possible_mask);
+ if (cpu >= nr_cpu_ids)
+ return NULL;
+ } while (!(ret = workqueue_stat_start_cpu(cpu)));
+ return ret;
+ } else {
+ ret = list_entry(prev_cws->list.next,
+ struct cpu_workqueue_stats, list);
+ kref_get(&ret->kref);
+ }
+ spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+
+ return ret;
+}
+
+static int workqueue_stat_show(struct seq_file *s, void *p)
+{
+ struct cpu_workqueue_stats *cws = p;
+ struct pid *pid;
+ struct task_struct *tsk;
+
+ pid = find_get_pid(cws->pid);
+ if (pid) {
+ tsk = get_pid_task(pid, PIDTYPE_PID);
+ if (tsk) {
+ seq_printf(s, "%3d %6d %6u %s\n", cws->cpu,
+ atomic_read(&cws->inserted), cws->executed,
+ tsk->comm);
+ put_task_struct(tsk);
+ }
+ put_pid(pid);
+ }
+
+ return 0;
+}
+
+static void workqueue_stat_release(void *stat)
+{
+ struct cpu_workqueue_stats *node = stat;
+
+ kref_put(&node->kref, cpu_workqueue_stat_free);
+}
+
+static int workqueue_stat_headers(struct seq_file *s)
+{
+ seq_printf(s, "# CPU INSERTED EXECUTED NAME\n");
+ seq_printf(s, "# | | | |\n");
+ return 0;
+}
+
+struct tracer_stat workqueue_stats __read_mostly = {
+ .name = "workqueues",
+ .stat_start = workqueue_stat_start,
+ .stat_next = workqueue_stat_next,
+ .stat_show = workqueue_stat_show,
+ .stat_release = workqueue_stat_release,
+ .stat_headers = workqueue_stat_headers
+};
+
+
+int __init stat_workqueue_init(void)
+{
+ if (register_stat_tracer(&workqueue_stats)) {
+ pr_warning("Unable to register workqueue stat tracer\n");
+ return 1;
+ }
+
+ return 0;
+}
+fs_initcall(stat_workqueue_init);
+
+/*
+ * Workqueues are created very early, just after pre-smp initcalls.
+ * So we must register our tracepoints at this stage.
+ */
+int __init trace_workqueue_early_init(void)
+{
+ int ret, cpu;
+
+ ret = register_trace_workqueue_insertion(probe_workqueue_insertion);
+ if (ret)
+ goto out;
+
+ ret = register_trace_workqueue_execution(probe_workqueue_execution);
+ if (ret)
+ goto no_insertion;
+
+ ret = register_trace_workqueue_creation(probe_workqueue_creation);
+ if (ret)
+ goto no_execution;
+
+ ret = register_trace_workqueue_destruction(probe_workqueue_destruction);
+ if (ret)
+ goto no_creation;
+
+ for_each_possible_cpu(cpu) {
+ spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
+ INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
+ }
+
+ return 0;
+
+no_creation:
+ unregister_trace_workqueue_creation(probe_workqueue_creation);
+no_execution:
+ unregister_trace_workqueue_execution(probe_workqueue_execution);
+no_insertion:
+ unregister_trace_workqueue_insertion(probe_workqueue_insertion);
+out:
+ pr_warning("trace_workqueue: unable to trace workqueues\n");
+
+ return 1;
+}
+early_initcall(trace_workqueue_early_init);