From 499e547057f5bba5cd6f87ebe59b05d0c59da905 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 22 Feb 2012 15:50:28 -0500 Subject: tracing/ring-buffer: Only have tracing_on disable tracing buffers As the ring-buffer code is being used by other facilities in the kernel, having tracing_on file disable *all* buffers is not a desired affect. It should only disable the ftrace buffers that are being used. Move the code into the trace.c file and use the buffer disabling for tracing_on() and tracing_off(). This way only the ftrace buffers will be affected by them and other kernel utilities will not be confused to why their output suddenly stopped. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 157 +++++++++++++++++---------------------------- kernel/trace/trace.c | 107 ++++++++++++++++++++++++++++++ kernel/trace/trace.h | 1 + 3 files changed, 168 insertions(+), 97 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f5b7b5c1195b..cf8d11e91efd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -154,33 +154,10 @@ enum { 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); +/* Used for individual buffers (after the counter) */ +#define RB_BUFFER_OFF (1 << 20) -/** - * 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); +#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) /** * tracing_off_permanent - permanently disable ring buffers @@ -193,15 +170,6 @@ 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) @@ -2618,6 +2586,63 @@ void ring_buffer_record_enable(struct ring_buffer *buffer) } EXPORT_SYMBOL_GPL(ring_buffer_record_enable); +/** + * ring_buffer_record_off - 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. + * + * This is different than ring_buffer_record_disable() as + * it works like an on/off switch, where as the disable() verison + * must be paired with a enable(). + */ +void ring_buffer_record_off(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd | RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_off); + +/** + * ring_buffer_record_on - restart writes into the buffer + * @buffer: The ring buffer to start writes to. + * + * This enables all writes to the buffer that was disabled by + * ring_buffer_record_off(). + * + * This is different than ring_buffer_record_enable() as + * it works like an on/off switch, where as the enable() verison + * must be paired with a disable(). + */ +void ring_buffer_record_on(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd & ~RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_on); + +/** + * ring_buffer_record_is_on - return true if the ring buffer can write + * @buffer: The ring buffer to see if write is enabled + * + * Returns true if the ring buffer is in a state that it accepts writes. + */ +int ring_buffer_record_is_on(struct ring_buffer *buffer) +{ + return !atomic_read(&buffer->record_disabled); +} + /** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. @@ -4039,68 +4064,6 @@ int ring_buffer_read_page(struct ring_buffer *buffer, } 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; - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - 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, - .llseek = default_llseek, -}; - - -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) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 10d5503f0d04..f3c13d63d064 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -351,6 +351,59 @@ static void wakeup_work_handler(struct work_struct *work) static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); +/** + * tracing_on - enable tracing buffers + * + * This function enables tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 0; +} +EXPORT_SYMBOL_GPL(tracing_on); + +/** + * tracing_off - turn off tracing buffers + * + * This function stops the 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) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 1; +} +EXPORT_SYMBOL_GPL(tracing_off); + +/** + * tracing_is_on - show state of ring buffers enabled + */ +int tracing_is_on(void) +{ + if (global_trace.buffer) + return ring_buffer_record_is_on(global_trace.buffer); + return !global_trace.buffer_disabled; +} +EXPORT_SYMBOL_GPL(tracing_is_on); + /** * trace_wake_up - wake up tasks waiting for trace input * @@ -4567,6 +4620,55 @@ static __init void create_trace_options_dir(void) create_trace_option_core_file(trace_options[i], i); } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + char buf[64]; + int r; + + if (buffer) + r = ring_buffer_record_is_on(buffer); + else + r = 0; + + r = sprintf(buf, "%d\n", r); + + 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) +{ + struct ring_buffer *buffer = filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (buffer) { + if (val) + ring_buffer_record_on(buffer); + else + ring_buffer_record_off(buffer); + } + + (*ppos)++; + + return cnt; +} + +static const struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, + .llseek = default_llseek, +}; + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; @@ -4626,6 +4728,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("trace_clock", 0644, d_tracer, NULL, &trace_clock_fops); + trace_create_file("tracing_on", 0644, d_tracer, + global_trace.buffer, &rb_simple_fops); + #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); @@ -4863,6 +4968,8 @@ __init static int tracer_alloc_buffers(void) goto out_free_cpumask; } global_trace.entries = ring_buffer_size(global_trace.buffer); + if (global_trace.buffer_disabled) + tracing_off(); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 54faec790bc1..ce887c0eca56 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -154,6 +154,7 @@ struct trace_array { struct ring_buffer *buffer; unsigned long entries; int cpu; + int buffer_disabled; cycle_t time_start; struct task_struct *waiter; struct trace_array_cpu *data[NR_CPUS]; -- cgit v1.3-8-gc7d7 From 8c9cf542b8a66c231747a550573d910daf17f0e9 Mon Sep 17 00:00:00 2001 From: Gerlando Falauto Date: Mon, 27 Feb 2012 09:08:21 +0100 Subject: tracing: Do not select FRAME_POINTER on PPC On PowerPC, FUNCTION_TRACER selects FRAME_POINTER, even though the architecture does not support it. This causes the following warning: warning: (LOCKDEP && FAULT_INJECTION_STACKTRACE_FILTER && LATENCYTOP && FUNCTION_TRACER && KMEMCHECK) selects FRAME_POINTER which has unmet direct dependencies (DEBUG_KERNEL && (CRIS || M68K || FRV || UML || AVR32 || SUPERH || BLACKFIN || MN10300) || ARCH_WANT_FRAME_POINTERS) So remove the warning by adding the extra condition "if !PPC" to FUNCTION_TRACER for FRAME_POINTER selection Link: http://lkml.kernel.org/r/1330330101-8618-1-git-send-email-gerlando.falauto@keymile.com Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Gerlando Falauto Signed-off-by: Steven Rostedt --- kernel/trace/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index cd3134510f3d..a1d2849f2473 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,7 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE + select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER -- cgit v1.3-8-gc7d7 From b892e5c89787716b95a8e55d77d25a1c0748df10 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 1 Mar 2012 22:06:48 -0500 Subject: tracing: Keep NMI watchdog from triggering when dumping trace As ftrace_dump() (called by ftrace_dump_on_oops) disables interrupts as it dumps its output to the console, it can keep interrupts disabled for long periods of time. This is likely to trigger the NMI watchdog, and it can disrupt the output of critical data. Add a touch_nmi_watchdog() to each event that is written to the screen to keep the NMI watchdog from affecting the output. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f3c13d63d064..3a19c354edd6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include "trace.h" @@ -4903,6 +4904,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); } + touch_nmi_watchdog(); trace_printk_seq(&iter.seq); } -- cgit v1.3-8-gc7d7 From db6544e0075d192e5ad16eda8689c55fa9c6f8f4 Mon Sep 17 00:00:00 2001 From: Rajesh Bhagat Date: Fri, 17 Feb 2012 13:59:15 +0530 Subject: ftrace: Fix function_graph for archs that test ftrace_trace_function When CONFIG_DYNAMIC_FTRACE is not set, some archs (ARM) test the variable function_trace_function to determine if it should call the function tracer. If it is not set to ftrace_stub, then it will call the function and return, and not call the function graph tracer. But some of these archs (ARM) do not have the assembly code to test if function tracing is enabled or not (quick stop of tracing) and it calls the helper routine ftrace_test_stop_func() instead. If function tracer is enabled and then disabled, the variable ftrace_trace_function is still set to the helper routine ftrace_test_stop_func(), and not to ftrace_stub. This will prevent the function graph tracer from ever running. Output before patch /debug/tracing # echo function > current_tracer /debug/tracing # echo function_graph > current_tracer /debug/tracing # cat trace Output after patch /debug/tracing # echo function > current_tracer /debug/tracing # echo function_graph > current_tracer /debug/tracing # cat trace 0) ! 253.375 us | } /* irq_enter */ 0) | generic_handle_irq() { 0) | handle_fasteoi_irq() { 0) 9.208 us | _raw_spin_lock(); 0) | handle_irq_event() { 0) | handle_irq_event_percpu() { Signed-off-by: Rajesh Bhagat Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 867bd1dd2dd0..0fa92f677c92 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -249,7 +249,8 @@ static void update_ftrace_function(void) #else __ftrace_trace_function = func; #endif - ftrace_trace_function = ftrace_test_stop_func; + ftrace_trace_function = + (func == ftrace_stub) ? func : ftrace_test_stop_func; #endif } -- cgit v1.3-8-gc7d7 From fa73dc9400516945bcbae8d98c23393bcefe1440 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 28 Feb 2012 11:02:46 +0000 Subject: tracing: Fix build breakage without CONFIG_PERF_EVENTS Today's -next fails to build for me: CC kernel/trace/trace_export.o In file included from kernel/trace/trace_export.c:197: kernel/trace/trace_entries.h:58: error: 'perf_ftrace_event_register' undeclared here (not in a function) make[2]: *** [kernel/trace/trace_export.o] Error 1 make[1]: *** [kernel/trace] Error 2 make: *** [kernel] Error 2 because as of ced390 (ftrace, perf: Add support to use function tracepoint in perf) perf_trace_event_register() is declared in trace.h only if CONFIG_PERF_EVENTS is enabled but I don't have that set. Ensure that we always have a definition of perf_trace_event_register() by making the definition unconditional. Link: http://lkml.kernel.org/r/1330426967-17067-1-git-send-email-broonie@opensource.wolfsonmicro.com Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Signed-off-by: Mark Brown Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ce887c0eca56..95059f091a24 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -836,13 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[]; filter) #include "trace_entries.h" -#ifdef CONFIG_PERF_EVENTS #ifdef CONFIG_FUNCTION_TRACER int perf_ftrace_event_register(struct ftrace_event_call *call, enum trace_reg type, void *data); #else #define perf_ftrace_event_register NULL #endif /* CONFIG_FUNCTION_TRACER */ -#endif /* CONFIG_PERF_EVENTS */ #endif /* _LINUX_KERNEL_TRACE_H */ -- cgit v1.3-8-gc7d7 From 01de982abf8c9e10fc3089e10585cd2cc914bdab Mon Sep 17 00:00:00 2001 From: Wolfgang Mauerer Date: Thu, 22 Mar 2012 11:18:20 +0100 Subject: tracing: Fix ftrace stack trace entries 8 hex characters tell only half the tale for 64 bit CPUs, so use the appropriate length. Link: http://lkml.kernel.org/r/1332411501-8059-2-git-send-email-wolfgang.mauerer@siemens.com Cc: stable@vger.kernel.org Signed-off-by: Wolfgang Mauerer Signed-off-by: Steven Rostedt --- kernel/trace/trace_entries.h | 16 ++++++++++++---- kernel/trace/trace_export.c | 2 +- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 93365907f219..205dcac89206 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -156,6 +156,12 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, #define FTRACE_STACK_ENTRIES 8 +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + FTRACE_ENTRY(kernel_stack, stack_entry, TRACE_STACK, @@ -165,8 +171,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry, __dynamic_array(unsigned long, caller ) ), - 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", + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\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]) @@ -181,8 +188,9 @@ FTRACE_ENTRY(user_stack, userstack_entry, __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", + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\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]) diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index bbeec31e0ae3..ad4000c71be0 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -150,7 +150,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #define __dynamic_array(type, item) #undef F_printk -#define F_printk(fmt, args...) #fmt ", " __stringify(args) +#define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ -- cgit v1.3-8-gc7d7 From 12b5da349a8b94c9dbc3430a6bc42eabd9eaf50b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 27 Mar 2012 10:43:28 -0400 Subject: tracing: Fix ent_size in trace output When reading the trace file, the records of each of the per_cpu buffers are examined to find the next event to print out. At the point of looking at the event, the size of the event is recorded. But if the first event is chosen, the other events in the other CPU buffers will reset the event size that is stored in the iterator descriptor, causing the event size passed to the output functions to be incorrect. In most cases this is not a problem, but for the case of stack traces, it is. With the change to the stack tracing to record a dynamic number of back traces, the output depends on the size of the entry instead of the fixed 8 back traces. When the entry size is not correct, the back traces would not be fully printed. Note, reading from the per-cpu trace files were not affected. Reported-by: Thomas Gleixner Tested-by: Thomas Gleixner Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3a19c354edd6..ed7b5d1e12f4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1698,6 +1698,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; + int next_size = 0; int cpu; /* @@ -1729,9 +1730,12 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, next_cpu = cpu; next_ts = ts; next_lost = lost_events; + next_size = iter->ent_size; } } + iter->ent_size = next_size; + if (ent_cpu) *ent_cpu = next_cpu; -- cgit v1.3-8-gc7d7 From 234e340582901211f40d8c732afc49f0630ecf05 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 5 Apr 2012 14:25:11 -0700 Subject: simple_open: automatically convert to simple_open() Many users of debugfs copy the implementation of default_open() when they want to support a custom read/write function op. This leads to a proliferation of the default_open() implementation across the entire tree. Now that the common implementation has been consolidated into libfs we can replace all the users of this function with simple_open(). This replacement was done with the following semantic patch: @ open @ identifier open_f != simple_open; identifier i, f; @@ -int open_f(struct inode *i, struct file *f) -{ ( -if (i->i_private) -f->private_data = i->i_private; | -f->private_data = i->i_private; ) -return 0; -} @ has_open depends on open @ identifier fops; identifier open.open_f; @@ struct file_operations fops = { ... -.open = open_f, +.open = simple_open, ... }; [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Stephen Boyd Cc: Greg Kroah-Hartman Cc: Al Viro Cc: Julia Lawall Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-msm/smd_debug.c | 8 +---- arch/x86/kernel/kdebugfs.c | 9 +----- drivers/acpi/ec_sys.c | 8 +---- drivers/base/regmap/regmap-debugfs.c | 12 ++----- drivers/bluetooth/btmrvl_debugfs.c | 26 ++++++--------- drivers/char/virtio_console.c | 8 +---- drivers/dma/coh901318.c | 9 +----- drivers/gpu/drm/i915/i915_debugfs.c | 14 ++------- drivers/hid/hid-picolcd.c | 16 ++-------- drivers/hid/hid-wiimote-debug.c | 8 +---- drivers/idle/i7300_idle.c | 8 +---- drivers/iommu/omap-iommu-debug.c | 10 ++---- drivers/mfd/aat2870-core.c | 9 +----- drivers/mfd/ab3100-core.c | 8 +---- drivers/misc/ibmasm/ibmasmfs.c | 8 +---- drivers/mtd/ubi/debug.c | 10 +----- drivers/net/caif/caif_spi.c | 10 ++---- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 9 +----- drivers/net/wimax/i2400m/debugfs.c | 15 ++------- drivers/net/wireless/ath/ath5k/debug.c | 23 +++++--------- drivers/net/wireless/ath/ath6kl/debug.c | 42 +++++++++++-------------- drivers/net/wireless/ath/ath9k/debug.c | 37 ++++++++++------------ drivers/net/wireless/ath/ath9k/dfs_debug.c | 9 +----- drivers/net/wireless/ath/ath9k/htc_drv_debug.c | 26 ++++++--------- drivers/net/wireless/ath/ath9k/rc.c | 8 +---- drivers/net/wireless/ath/carl9170/debug.c | 7 +---- drivers/net/wireless/b43/debugfs.c | 8 +---- drivers/net/wireless/b43legacy/debugfs.c | 8 +---- drivers/net/wireless/iwlegacy/3945-rs.c | 8 +---- drivers/net/wireless/iwlegacy/4965-rs.c | 12 ++----- drivers/net/wireless/iwlegacy/debug.c | 12 ++----- drivers/net/wireless/iwlwifi/iwl-agn-rs.c | 11 ++----- drivers/net/wireless/iwlwifi/iwl-debugfs.c | 12 ++----- drivers/net/wireless/iwlwifi/iwl-trans-pcie.c | 12 ++----- drivers/net/wireless/iwmc3200wifi/debugfs.c | 14 +++------ drivers/net/wireless/iwmc3200wifi/sdio.c | 9 +----- drivers/net/wireless/libertas/debugfs.c | 10 ++---- drivers/net/wireless/mwifiex/debugfs.c | 18 ++--------- drivers/net/wireless/wl1251/debugfs.c | 14 +++------ drivers/net/wireless/wl12xx/debugfs.c | 38 ++++++++++------------ drivers/oprofile/oprofilefs.c | 14 ++------- drivers/remoteproc/remoteproc_debugfs.c | 13 ++------ drivers/scsi/lpfc/lpfc_debugfs.c | 9 +----- drivers/spi/spi-dw.c | 8 +---- drivers/tty/serial/mfd.c | 9 ++---- drivers/tty/serial/pch_uart.c | 8 ++--- drivers/usb/core/inode.c | 10 +----- drivers/usb/host/ehci-dbg.c | 9 +----- drivers/uwb/uwb-debug.c | 9 +----- fs/debugfs/file.c | 14 ++------- fs/dlm/debug_fs.c | 9 +----- fs/pstore/inode.c | 8 +---- kernel/trace/blktrace.c | 18 ++--------- net/mac80211/debugfs.c | 12 ++----- net/mac80211/debugfs.h | 1 - net/mac80211/debugfs_key.c | 4 +-- net/mac80211/debugfs_netdev.c | 2 +- net/mac80211/debugfs_sta.c | 4 +-- net/mac80211/rate.c | 2 +- net/wireless/debugfs.c | 10 ++---- sound/soc/imx/imx-audmux.c | 8 +---- sound/soc/soc-core.c | 8 +---- sound/soc/soc-dapm.c | 16 ++-------- 63 files changed, 176 insertions(+), 572 deletions(-) (limited to 'kernel/trace') diff --git a/arch/arm/mach-msm/smd_debug.c b/arch/arm/mach-msm/smd_debug.c index 0c56a5aaf588..c56df9e932ae 100644 --- a/arch/arm/mach-msm/smd_debug.c +++ b/arch/arm/mach-msm/smd_debug.c @@ -203,15 +203,9 @@ static ssize_t debug_read(struct file *file, char __user *buf, return simple_read_from_buffer(buf, count, ppos, debug_buffer, bsize); } -static int debug_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static const struct file_operations debug_ops = { .read = debug_read, - .open = debug_open, + .open = simple_open, .llseek = default_llseek, }; diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 90fcf62854bb..1d5d31ea686b 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, return count; } -static int setup_data_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - - return 0; -} - static const struct file_operations fops_setup_data = { .read = setup_data_read, - .open = setup_data_open, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c index b258cab9061c..7586544fddb4 100644 --- a/drivers/acpi/ec_sys.c +++ b/drivers/acpi/ec_sys.c @@ -27,12 +27,6 @@ MODULE_PARM_DESC(write_support, "Dangerous, reboot and removal of battery may " static struct dentry *acpi_ec_debugfs_dir; -static int acpi_ec_open_io(struct inode *i, struct file *f) -{ - f->private_data = i->i_private; - return 0; -} - static ssize_t acpi_ec_read_io(struct file *f, char __user *buf, size_t count, loff_t *off) { @@ -95,7 +89,7 @@ static ssize_t acpi_ec_write_io(struct file *f, const char __user *buf, static const struct file_operations acpi_ec_io_ops = { .owner = THIS_MODULE, - .open = acpi_ec_open_io, + .open = simple_open, .read = acpi_ec_read_io, .write = acpi_ec_write_io, .llseek = default_llseek, diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index 58517a5dac13..251eb70f83e7 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -27,12 +27,6 @@ static size_t regmap_calc_reg_len(int max_val, char *buf, size_t buf_size) return strlen(buf); } -static int regmap_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t regmap_name_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -57,7 +51,7 @@ static ssize_t regmap_name_read_file(struct file *file, } static const struct file_operations regmap_name_fops = { - .open = regmap_open_file, + .open = simple_open, .read = regmap_name_read_file, .llseek = default_llseek, }; @@ -174,7 +168,7 @@ static ssize_t regmap_map_write_file(struct file *file, #endif static const struct file_operations regmap_map_fops = { - .open = regmap_open_file, + .open = simple_open, .read = regmap_map_read_file, .write = regmap_map_write_file, .llseek = default_llseek, @@ -243,7 +237,7 @@ out: } static const struct file_operations regmap_access_fops = { - .open = regmap_open_file, + .open = simple_open, .read = regmap_access_read_file, .llseek = default_llseek, }; diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index 6c20bbb54b71..428dbb7574bd 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -45,12 +45,6 @@ struct btmrvl_debugfs_data { struct dentry *txdnldready; }; -static int btmrvl_open_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t btmrvl_hscfgcmd_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { @@ -93,7 +87,7 @@ static ssize_t btmrvl_hscfgcmd_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_hscfgcmd_fops = { .read = btmrvl_hscfgcmd_read, .write = btmrvl_hscfgcmd_write, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -134,7 +128,7 @@ static ssize_t btmrvl_psmode_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_psmode_fops = { .read = btmrvl_psmode_read, .write = btmrvl_psmode_write, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -180,7 +174,7 @@ static ssize_t btmrvl_pscmd_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_pscmd_fops = { .read = btmrvl_pscmd_read, .write = btmrvl_pscmd_write, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -221,7 +215,7 @@ static ssize_t btmrvl_gpiogap_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_gpiogap_fops = { .read = btmrvl_gpiogap_read, .write = btmrvl_gpiogap_write, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -265,7 +259,7 @@ static ssize_t btmrvl_hscmd_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_hscmd_fops = { .read = btmrvl_hscmd_read, .write = btmrvl_hscmd_write, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -305,7 +299,7 @@ static ssize_t btmrvl_hsmode_read(struct file *file, char __user * userbuf, static const struct file_operations btmrvl_hsmode_fops = { .read = btmrvl_hsmode_read, .write = btmrvl_hsmode_write, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -323,7 +317,7 @@ static ssize_t btmrvl_curpsmode_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_curpsmode_fops = { .read = btmrvl_curpsmode_read, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -341,7 +335,7 @@ static ssize_t btmrvl_psstate_read(struct file *file, char __user * userbuf, static const struct file_operations btmrvl_psstate_fops = { .read = btmrvl_psstate_read, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -359,7 +353,7 @@ static ssize_t btmrvl_hsstate_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_hsstate_fops = { .read = btmrvl_hsstate_read, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -378,7 +372,7 @@ static ssize_t btmrvl_txdnldready_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_txdnldready_fops = { .read = btmrvl_txdnldready_read, - .open = btmrvl_open_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index b58b56187065..ddf86b6500b7 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1038,12 +1038,6 @@ static struct attribute_group port_attribute_group = { .attrs = port_sysfs_entries, }; -static int debugfs_open(struct inode *inode, struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count, loff_t *offp) { @@ -1087,7 +1081,7 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf, static const struct file_operations port_debugfs_ops = { .owner = THIS_MODULE, - .open = debugfs_open, + .open = simple_open, .read = debugfs_read, }; diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c index d65a718c0f9b..a63badcd2d6e 100644 --- a/drivers/dma/coh901318.c +++ b/drivers/dma/coh901318.c @@ -104,13 +104,6 @@ static void coh901318_list_print(struct coh901318_chan *cohc, static struct coh901318_base *debugfs_dma_base; static struct dentry *dma_dentry; -static int coh901318_debugfs_open(struct inode *inode, struct file *file) -{ - - file->private_data = inode->i_private; - return 0; -} - static int coh901318_debugfs_read(struct file *file, char __user *buf, size_t count, loff_t *f_pos) { @@ -158,7 +151,7 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf, static const struct file_operations coh901318_debugfs_status_operations = { .owner = THIS_MODULE, - .open = coh901318_debugfs_open, + .open = simple_open, .read = coh901318_debugfs_read, .llseek = default_llseek, }; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index fdb7ccefffbd..b505b70dba05 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1502,14 +1502,6 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) return 0; } -static int -i915_debugfs_common_open(struct inode *inode, - struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - static ssize_t i915_wedged_read(struct file *filp, char __user *ubuf, @@ -1560,7 +1552,7 @@ i915_wedged_write(struct file *filp, static const struct file_operations i915_wedged_fops = { .owner = THIS_MODULE, - .open = i915_debugfs_common_open, + .open = simple_open, .read = i915_wedged_read, .write = i915_wedged_write, .llseek = default_llseek, @@ -1622,7 +1614,7 @@ i915_max_freq_write(struct file *filp, static const struct file_operations i915_max_freq_fops = { .owner = THIS_MODULE, - .open = i915_debugfs_common_open, + .open = simple_open, .read = i915_max_freq_read, .write = i915_max_freq_write, .llseek = default_llseek, @@ -1693,7 +1685,7 @@ i915_cache_sharing_write(struct file *filp, static const struct file_operations i915_cache_sharing_fops = { .owner = THIS_MODULE, - .open = i915_debugfs_common_open, + .open = simple_open, .read = i915_cache_sharing_read, .write = i915_cache_sharing_write, .llseek = default_llseek, diff --git a/drivers/hid/hid-picolcd.c b/drivers/hid/hid-picolcd.c index 12f9777c385d..45c3433f7986 100644 --- a/drivers/hid/hid-picolcd.c +++ b/drivers/hid/hid-picolcd.c @@ -1525,12 +1525,6 @@ static const struct file_operations picolcd_debug_reset_fops = { /* * The "eeprom" file */ -static int picolcd_debug_eeprom_open(struct inode *i, struct file *f) -{ - f->private_data = i->i_private; - return 0; -} - static ssize_t picolcd_debug_eeprom_read(struct file *f, char __user *u, size_t s, loff_t *off) { @@ -1618,7 +1612,7 @@ static ssize_t picolcd_debug_eeprom_write(struct file *f, const char __user *u, */ static const struct file_operations picolcd_debug_eeprom_fops = { .owner = THIS_MODULE, - .open = picolcd_debug_eeprom_open, + .open = simple_open, .read = picolcd_debug_eeprom_read, .write = picolcd_debug_eeprom_write, .llseek = generic_file_llseek, @@ -1627,12 +1621,6 @@ static const struct file_operations picolcd_debug_eeprom_fops = { /* * The "flash" file */ -static int picolcd_debug_flash_open(struct inode *i, struct file *f) -{ - f->private_data = i->i_private; - return 0; -} - /* record a flash address to buf (bounds check to be done by caller) */ static int _picolcd_flash_setaddr(struct picolcd_data *data, u8 *buf, long off) { @@ -1817,7 +1805,7 @@ static ssize_t picolcd_debug_flash_write(struct file *f, const char __user *u, */ static const struct file_operations picolcd_debug_flash_fops = { .owner = THIS_MODULE, - .open = picolcd_debug_flash_open, + .open = simple_open, .read = picolcd_debug_flash_read, .write = picolcd_debug_flash_write, .llseek = generic_file_llseek, diff --git a/drivers/hid/hid-wiimote-debug.c b/drivers/hid/hid-wiimote-debug.c index 17dabc1f339e..eec329197c16 100644 --- a/drivers/hid/hid-wiimote-debug.c +++ b/drivers/hid/hid-wiimote-debug.c @@ -23,12 +23,6 @@ struct wiimote_debug { struct dentry *drm; }; -static int wiidebug_eeprom_open(struct inode *i, struct file *f) -{ - f->private_data = i->i_private; - return 0; -} - static ssize_t wiidebug_eeprom_read(struct file *f, char __user *u, size_t s, loff_t *off) { @@ -83,7 +77,7 @@ static ssize_t wiidebug_eeprom_read(struct file *f, char __user *u, size_t s, static const struct file_operations wiidebug_eeprom_fops = { .owner = THIS_MODULE, - .open = wiidebug_eeprom_open, + .open = simple_open, .read = wiidebug_eeprom_read, .llseek = generic_file_llseek, }; diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c index c976285d313e..fa080ebd568f 100644 --- a/drivers/idle/i7300_idle.c +++ b/drivers/idle/i7300_idle.c @@ -516,12 +516,6 @@ static struct notifier_block i7300_idle_nb = { MODULE_DEVICE_TABLE(pci, pci_tbl); -int stats_open_generic(struct inode *inode, struct file *fp) -{ - fp->private_data = inode->i_private; - return 0; -} - static ssize_t stats_read_ul(struct file *fp, char __user *ubuf, size_t count, loff_t *off) { @@ -534,7 +528,7 @@ static ssize_t stats_read_ul(struct file *fp, char __user *ubuf, size_t count, } static const struct file_operations idle_fops = { - .open = stats_open_generic, + .open = simple_open, .read = stats_read_ul, .llseek = default_llseek, }; diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index 103dbd92e256..f55fc5dfbadc 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -323,15 +323,9 @@ err_out: return count; } -static int debug_open_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUG_FOPS(name) \ static const struct file_operations debug_##name##_fops = { \ - .open = debug_open_generic, \ + .open = simple_open, \ .read = debug_read_##name, \ .write = debug_write_##name, \ .llseek = generic_file_llseek, \ @@ -339,7 +333,7 @@ static int debug_open_generic(struct inode *inode, struct file *file) #define DEBUG_FOPS_RO(name) \ static const struct file_operations debug_##name##_fops = { \ - .open = debug_open_generic, \ + .open = simple_open, \ .read = debug_read_##name, \ .llseek = generic_file_llseek, \ }; diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c index 3aa36eb5c79b..44a3fdbadef4 100644 --- a/drivers/mfd/aat2870-core.c +++ b/drivers/mfd/aat2870-core.c @@ -262,13 +262,6 @@ static ssize_t aat2870_dump_reg(struct aat2870_data *aat2870, char *buf) return count; } -static int aat2870_reg_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - - return 0; -} - static ssize_t aat2870_reg_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -330,7 +323,7 @@ static ssize_t aat2870_reg_write_file(struct file *file, } static const struct file_operations aat2870_reg_fops = { - .open = aat2870_reg_open_file, + .open = simple_open, .read = aat2870_reg_read_file, .write = aat2870_reg_write_file, }; diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c index 60107ee166fc..1efad20fb175 100644 --- a/drivers/mfd/ab3100-core.c +++ b/drivers/mfd/ab3100-core.c @@ -483,12 +483,6 @@ struct ab3100_get_set_reg_priv { bool mode; }; -static int ab3100_get_set_reg_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t ab3100_get_set_reg(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) @@ -583,7 +577,7 @@ static ssize_t ab3100_get_set_reg(struct file *file, } static const struct file_operations ab3100_get_set_reg_fops = { - .open = ab3100_get_set_reg_open_file, + .open = simple_open, .write = ab3100_get_set_reg, .llseek = noop_llseek, }; diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index 1c034b80d408..6673e578b3e9 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -500,12 +500,6 @@ static ssize_t r_heartbeat_file_write(struct file *file, const char __user *buf, return 1; } -static int remote_settings_file_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static int remote_settings_file_close(struct inode *inode, struct file *file) { return 0; @@ -600,7 +594,7 @@ static const struct file_operations r_heartbeat_fops = { }; static const struct file_operations remote_settings_fops = { - .open = remote_settings_file_open, + .open = simple_open, .release = remote_settings_file_close, .read = remote_settings_file_read, .write = remote_settings_file_write, diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index e2cdebf40840..61af9bb560ab 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -386,19 +386,11 @@ out: return count; } -static int default_open(struct inode *inode, struct file *file) -{ - if (inode->i_private) - file->private_data = inode->i_private; - - return 0; -} - /* File operations for all UBI debugfs files */ static const struct file_operations dfs_fops = { .read = dfs_file_read, .write = dfs_file_write, - .open = default_open, + .open = simple_open, .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c index 96391c36fa74..b71ce9bf0afb 100644 --- a/drivers/net/caif/caif_spi.c +++ b/drivers/net/caif/caif_spi.c @@ -127,12 +127,6 @@ static inline void dev_debugfs_rem(struct cfspi *cfspi) debugfs_remove(cfspi->dbgfs_dir); } -static int dbgfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t dbgfs_state(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -243,13 +237,13 @@ static ssize_t dbgfs_frame(struct file *file, char __user *user_buf, } static const struct file_operations dbgfs_state_fops = { - .open = dbgfs_open, + .open = simple_open, .read = dbgfs_state, .owner = THIS_MODULE }; static const struct file_operations dbgfs_frame_fops = { - .open = dbgfs_open, + .open = simple_open, .read = dbgfs_frame, .owner = THIS_MODULE }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 05ff076af06d..b126b98065a9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2000,13 +2000,6 @@ static const struct ethtool_ops cxgb_ethtool_ops = { /* * debugfs support */ - -static int mem_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t mem_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -2050,7 +2043,7 @@ static ssize_t mem_read(struct file *file, char __user *buf, size_t count, static const struct file_operations mem_debugfs_fops = { .owner = THIS_MODULE, - .open = mem_open, + .open = simple_open, .read = mem_read, .llseek = default_llseek, }; diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c index 129ba36bd04d..4b66ab1d0e5c 100644 --- a/drivers/net/wimax/i2400m/debugfs.c +++ b/drivers/net/wimax/i2400m/debugfs.c @@ -53,17 +53,6 @@ struct dentry *debugfs_create_netdev_queue_stopped( &fops_netdev_queue_stopped); } - -/* - * inode->i_private has the @data argument to debugfs_create_file() - */ -static -int i2400m_stats_open(struct inode *inode, struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - /* * We don't allow partial reads of this file, as then the reader would * get weirdly confused data as it is updated. @@ -117,7 +106,7 @@ ssize_t i2400m_rx_stats_write(struct file *filp, const char __user *buffer, static const struct file_operations i2400m_rx_stats_fops = { .owner = THIS_MODULE, - .open = i2400m_stats_open, + .open = simple_open, .read = i2400m_rx_stats_read, .write = i2400m_rx_stats_write, .llseek = default_llseek, @@ -170,7 +159,7 @@ ssize_t i2400m_tx_stats_write(struct file *filp, const char __user *buffer, static const struct file_operations i2400m_tx_stats_fops = { .owner = THIS_MODULE, - .open = i2400m_stats_open, + .open = simple_open, .read = i2400m_tx_stats_read, .write = i2400m_tx_stats_write, .llseek = default_llseek, diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c index 8c5ce8b0c734..e5e8f45d86ac 100644 --- a/drivers/net/wireless/ath/ath5k/debug.c +++ b/drivers/net/wireless/ath/ath5k/debug.c @@ -71,13 +71,6 @@ static unsigned int ath5k_debug; module_param_named(debug, ath5k_debug, uint, 0); -static int ath5k_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - - /* debugfs: registers */ struct reg { @@ -265,7 +258,7 @@ static ssize_t write_file_beacon(struct file *file, static const struct file_operations fops_beacon = { .read = read_file_beacon, .write = write_file_beacon, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -285,7 +278,7 @@ static ssize_t write_file_reset(struct file *file, static const struct file_operations fops_reset = { .write = write_file_reset, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = noop_llseek, }; @@ -365,7 +358,7 @@ static ssize_t write_file_debug(struct file *file, static const struct file_operations fops_debug = { .read = read_file_debug, .write = write_file_debug, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -477,7 +470,7 @@ static ssize_t write_file_antenna(struct file *file, static const struct file_operations fops_antenna = { .read = read_file_antenna, .write = write_file_antenna, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -532,7 +525,7 @@ static ssize_t read_file_misc(struct file *file, char __user *user_buf, static const struct file_operations fops_misc = { .read = read_file_misc, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, }; @@ -647,7 +640,7 @@ static ssize_t write_file_frameerrors(struct file *file, static const struct file_operations fops_frameerrors = { .read = read_file_frameerrors, .write = write_file_frameerrors, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -810,7 +803,7 @@ static ssize_t write_file_ani(struct file *file, static const struct file_operations fops_ani = { .read = read_file_ani, .write = write_file_ani, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -881,7 +874,7 @@ static ssize_t write_file_queue(struct file *file, static const struct file_operations fops_queue = { .read = read_file_queue, .write = write_file_queue, - .open = ath5k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/ath/ath6kl/debug.c b/drivers/net/wireless/ath/ath6kl/debug.c index 552adb3f80d0..d01403a263ff 100644 --- a/drivers/net/wireless/ath/ath6kl/debug.c +++ b/drivers/net/wireless/ath/ath6kl/debug.c @@ -217,12 +217,6 @@ void dump_cred_dist_stats(struct htc_target *target) target->credit_info->cur_free_credits); } -static int ath6kl_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - void ath6kl_debug_war(struct ath6kl *ar, enum ath6kl_war war) { switch (war) { @@ -263,7 +257,7 @@ static ssize_t read_file_war_stats(struct file *file, char __user *user_buf, static const struct file_operations fops_war_stats = { .read = read_file_war_stats, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -488,7 +482,7 @@ static ssize_t ath6kl_fwlog_mask_write(struct file *file, } static const struct file_operations fops_fwlog_mask = { - .open = ath6kl_debugfs_open, + .open = simple_open, .read = ath6kl_fwlog_mask_read, .write = ath6kl_fwlog_mask_write, .owner = THIS_MODULE, @@ -634,7 +628,7 @@ static ssize_t read_file_tgt_stats(struct file *file, char __user *user_buf, static const struct file_operations fops_tgt_stats = { .read = read_file_tgt_stats, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -699,7 +693,7 @@ static ssize_t read_file_credit_dist_stats(struct file *file, static const struct file_operations fops_credit_dist_stats = { .read = read_file_credit_dist_stats, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -802,7 +796,7 @@ static ssize_t ath6kl_endpoint_stats_write(struct file *file, } static const struct file_operations fops_endpoint_stats = { - .open = ath6kl_debugfs_open, + .open = simple_open, .read = ath6kl_endpoint_stats_read, .write = ath6kl_endpoint_stats_write, .owner = THIS_MODULE, @@ -875,7 +869,7 @@ static ssize_t ath6kl_regread_write(struct file *file, static const struct file_operations fops_diag_reg_read = { .read = ath6kl_regread_read, .write = ath6kl_regread_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -999,7 +993,7 @@ static ssize_t ath6kl_lrssi_roam_read(struct file *file, static const struct file_operations fops_lrssi_roam_threshold = { .read = ath6kl_lrssi_roam_read, .write = ath6kl_lrssi_roam_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1061,7 +1055,7 @@ static ssize_t ath6kl_regwrite_write(struct file *file, static const struct file_operations fops_diag_reg_write = { .read = ath6kl_regwrite_read, .write = ath6kl_regwrite_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1166,7 +1160,7 @@ static ssize_t ath6kl_roam_table_read(struct file *file, char __user *user_buf, static const struct file_operations fops_roam_table = { .read = ath6kl_roam_table_read, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1204,7 +1198,7 @@ static ssize_t ath6kl_force_roam_write(struct file *file, static const struct file_operations fops_force_roam = { .write = ath6kl_force_roam_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1244,7 +1238,7 @@ static ssize_t ath6kl_roam_mode_write(struct file *file, static const struct file_operations fops_roam_mode = { .write = ath6kl_roam_mode_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1286,7 +1280,7 @@ static ssize_t ath6kl_keepalive_write(struct file *file, } static const struct file_operations fops_keepalive = { - .open = ath6kl_debugfs_open, + .open = simple_open, .read = ath6kl_keepalive_read, .write = ath6kl_keepalive_write, .owner = THIS_MODULE, @@ -1331,7 +1325,7 @@ static ssize_t ath6kl_disconnect_timeout_write(struct file *file, } static const struct file_operations fops_disconnect_timeout = { - .open = ath6kl_debugfs_open, + .open = simple_open, .read = ath6kl_disconnect_timeout_read, .write = ath6kl_disconnect_timeout_write, .owner = THIS_MODULE, @@ -1512,7 +1506,7 @@ static ssize_t ath6kl_create_qos_write(struct file *file, static const struct file_operations fops_create_qos = { .write = ath6kl_create_qos_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1560,7 +1554,7 @@ static ssize_t ath6kl_delete_qos_write(struct file *file, static const struct file_operations fops_delete_qos = { .write = ath6kl_delete_qos_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1593,7 +1587,7 @@ static ssize_t ath6kl_bgscan_int_write(struct file *file, static const struct file_operations fops_bgscan_int = { .write = ath6kl_bgscan_int_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1651,7 +1645,7 @@ static ssize_t ath6kl_listen_int_read(struct file *file, static const struct file_operations fops_listen_int = { .read = ath6kl_listen_int_read, .write = ath6kl_listen_int_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1711,7 +1705,7 @@ static ssize_t ath6kl_power_params_write(struct file *file, static const struct file_operations fops_power_params = { .write = ath6kl_power_params_write, - .open = ath6kl_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 35d1c8e91d1c..ff47b32ecaf4 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -26,11 +26,6 @@ #define REG_READ_D(_ah, _reg) \ ath9k_hw_common(_ah)->ops->read((_ah), (_reg)) -static int ath9k_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} static ssize_t ath9k_debugfs_read_buf(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -83,7 +78,7 @@ static ssize_t write_file_debug(struct file *file, const char __user *user_buf, static const struct file_operations fops_debug = { .read = read_file_debug, .write = write_file_debug, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -129,7 +124,7 @@ static ssize_t write_file_tx_chainmask(struct file *file, const char __user *use static const struct file_operations fops_tx_chainmask = { .read = read_file_tx_chainmask, .write = write_file_tx_chainmask, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -172,7 +167,7 @@ static ssize_t write_file_rx_chainmask(struct file *file, const char __user *use static const struct file_operations fops_rx_chainmask = { .read = read_file_rx_chainmask, .write = write_file_rx_chainmask, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -223,7 +218,7 @@ static ssize_t write_file_disable_ani(struct file *file, static const struct file_operations fops_disable_ani = { .read = read_file_disable_ani, .write = write_file_disable_ani, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -324,7 +319,7 @@ static ssize_t read_file_dma(struct file *file, char __user *user_buf, static const struct file_operations fops_dma = { .read = read_file_dma, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -446,7 +441,7 @@ static ssize_t read_file_interrupt(struct file *file, char __user *user_buf, static const struct file_operations fops_interrupt = { .read = read_file_interrupt, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -852,28 +847,28 @@ void ath_debug_stat_tx(struct ath_softc *sc, struct ath_buf *bf, static const struct file_operations fops_xmit = { .read = read_file_xmit, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; static const struct file_operations fops_stations = { .read = read_file_stations, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; static const struct file_operations fops_misc = { .read = read_file_misc, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; static const struct file_operations fops_reset = { .read = read_file_reset, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1016,7 +1011,7 @@ void ath_debug_stat_rx(struct ath_softc *sc, struct ath_rx_status *rs) static const struct file_operations fops_recv = { .read = read_file_recv, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1055,7 +1050,7 @@ static ssize_t write_file_regidx(struct file *file, const char __user *user_buf, static const struct file_operations fops_regidx = { .read = read_file_regidx, .write = write_file_regidx, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1102,7 +1097,7 @@ static ssize_t write_file_regval(struct file *file, const char __user *user_buf, static const struct file_operations fops_regval = { .read = read_file_regval, .write = write_file_regval, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1191,7 +1186,7 @@ static ssize_t read_file_dump_nfcal(struct file *file, char __user *user_buf, static const struct file_operations fops_dump_nfcal = { .read = read_file_dump_nfcal, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1219,7 +1214,7 @@ static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf, static const struct file_operations fops_base_eeprom = { .read = read_file_base_eeprom, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -1247,7 +1242,7 @@ static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf, static const struct file_operations fops_modal_eeprom = { .read = read_file_modal_eeprom, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/ath/ath9k/dfs_debug.c b/drivers/net/wireless/ath/ath9k/dfs_debug.c index 106d031d834a..4364c103ed33 100644 --- a/drivers/net/wireless/ath/ath9k/dfs_debug.c +++ b/drivers/net/wireless/ath/ath9k/dfs_debug.c @@ -60,16 +60,9 @@ static ssize_t read_file_dfs(struct file *file, char __user *user_buf, return retval; } -static int ath9k_dfs_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - - return 0; -} - static const struct file_operations fops_dfs_stats = { .read = read_file_dfs, - .open = ath9k_dfs_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c index d3ff33c71aa5..3035deb7a0cd 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c @@ -16,12 +16,6 @@ #include "htc.h" -static int ath9k_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t read_file_tgt_int_stats(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -75,7 +69,7 @@ static ssize_t read_file_tgt_int_stats(struct file *file, char __user *user_buf, static const struct file_operations fops_tgt_int_stats = { .read = read_file_tgt_int_stats, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -145,7 +139,7 @@ static ssize_t read_file_tgt_tx_stats(struct file *file, char __user *user_buf, static const struct file_operations fops_tgt_tx_stats = { .read = read_file_tgt_tx_stats, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -191,7 +185,7 @@ static ssize_t read_file_tgt_rx_stats(struct file *file, char __user *user_buf, static const struct file_operations fops_tgt_rx_stats = { .read = read_file_tgt_rx_stats, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -243,7 +237,7 @@ static ssize_t read_file_xmit(struct file *file, char __user *user_buf, static const struct file_operations fops_xmit = { .read = read_file_xmit, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -364,7 +358,7 @@ static ssize_t read_file_recv(struct file *file, char __user *user_buf, static const struct file_operations fops_recv = { .read = read_file_recv, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -399,7 +393,7 @@ static ssize_t read_file_slot(struct file *file, char __user *user_buf, static const struct file_operations fops_slot = { .read = read_file_slot, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -446,7 +440,7 @@ static ssize_t read_file_queue(struct file *file, char __user *user_buf, static const struct file_operations fops_queue = { .read = read_file_queue, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -487,7 +481,7 @@ static ssize_t write_file_debug(struct file *file, const char __user *user_buf, static const struct file_operations fops_debug = { .read = read_file_debug, .write = write_file_debug, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -636,7 +630,7 @@ static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf, static const struct file_operations fops_base_eeprom = { .read = read_file_base_eeprom, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; @@ -917,7 +911,7 @@ static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf, static const struct file_operations fops_modal_eeprom = { .read = read_file_modal_eeprom, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c index 4f848493fece..08bb45532701 100644 --- a/drivers/net/wireless/ath/ath9k/rc.c +++ b/drivers/net/wireless/ath/ath9k/rc.c @@ -1480,12 +1480,6 @@ static void ath_rate_update(void *priv, struct ieee80211_supported_band *sband, #ifdef CONFIG_ATH9K_DEBUGFS -static int ath9k_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t read_file_rcstat(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -1553,7 +1547,7 @@ static ssize_t read_file_rcstat(struct file *file, char __user *user_buf, static const struct file_operations fops_rcstat = { .read = read_file_rcstat, - .open = ath9k_debugfs_open, + .open = simple_open, .owner = THIS_MODULE }; diff --git a/drivers/net/wireless/ath/carl9170/debug.c b/drivers/net/wireless/ath/carl9170/debug.c index 3c164226687f..93fe6003a493 100644 --- a/drivers/net/wireless/ath/carl9170/debug.c +++ b/drivers/net/wireless/ath/carl9170/debug.c @@ -48,11 +48,6 @@ #define ADD(buf, off, max, fmt, args...) \ off += snprintf(&buf[off], max - off, fmt, ##args); -static int carl9170_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} struct carl9170_debugfs_fops { unsigned int read_bufsize; @@ -178,7 +173,7 @@ static const struct carl9170_debugfs_fops carl_debugfs_##name ##_ops = {\ .attr = _attr, \ .req_dev_state = _dstate, \ .fops = { \ - .open = carl9170_debugfs_open, \ + .open = simple_open, \ .read = carl9170_debugfs_read, \ .write = carl9170_debugfs_write, \ .owner = THIS_MODULE \ diff --git a/drivers/net/wireless/b43/debugfs.c b/drivers/net/wireless/b43/debugfs.c index e751fdee89b2..e807bd930647 100644 --- a/drivers/net/wireless/b43/debugfs.c +++ b/drivers/net/wireless/b43/debugfs.c @@ -500,12 +500,6 @@ out: #undef fappend -static int b43_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t b43_debugfs_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -624,7 +618,7 @@ out_unlock: .read = _read, \ .write = _write, \ .fops = { \ - .open = b43_debugfs_open, \ + .open = simple_open, \ .read = b43_debugfs_read, \ .write = b43_debugfs_write, \ .llseek = generic_file_llseek, \ diff --git a/drivers/net/wireless/b43legacy/debugfs.c b/drivers/net/wireless/b43legacy/debugfs.c index 5e28ad0d6d17..1965edb765a2 100644 --- a/drivers/net/wireless/b43legacy/debugfs.c +++ b/drivers/net/wireless/b43legacy/debugfs.c @@ -197,12 +197,6 @@ static int restart_write_file(struct b43legacy_wldev *dev, const char *buf, size #undef fappend -static int b43legacy_debugfs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t b43legacy_debugfs_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -331,7 +325,7 @@ out_unlock: .read = _read, \ .write = _write, \ .fops = { \ - .open = b43legacy_debugfs_open, \ + .open = simple_open, \ .read = b43legacy_debugfs_read, \ .write = b43legacy_debugfs_write, \ .llseek = generic_file_llseek, \ diff --git a/drivers/net/wireless/iwlegacy/3945-rs.c b/drivers/net/wireless/iwlegacy/3945-rs.c index 70bee1a4d876..4b10157d8686 100644 --- a/drivers/net/wireless/iwlegacy/3945-rs.c +++ b/drivers/net/wireless/iwlegacy/3945-rs.c @@ -821,12 +821,6 @@ out: } #ifdef CONFIG_MAC80211_DEBUGFS -static int -il3945_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} static ssize_t il3945_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf, @@ -862,7 +856,7 @@ il3945_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf, static const struct file_operations rs_sta_dbgfs_stats_table_ops = { .read = il3945_sta_dbgfs_stats_table_read, - .open = il3945_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/iwlegacy/4965-rs.c b/drivers/net/wireless/iwlegacy/4965-rs.c index d7e2856e41d3..11ab1247fae1 100644 --- a/drivers/net/wireless/iwlegacy/4965-rs.c +++ b/drivers/net/wireless/iwlegacy/4965-rs.c @@ -2518,12 +2518,6 @@ il4965_rs_free_sta(void *il_r, struct ieee80211_sta *sta, void *il_sta) } #ifdef CONFIG_MAC80211_DEBUGFS -static int -il4965_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} static void il4965_rs_dbgfs_set_mcs(struct il_lq_sta *lq_sta, u32 * rate_n_flags, int idx) @@ -2695,7 +2689,7 @@ il4965_rs_sta_dbgfs_scale_table_read(struct file *file, char __user *user_buf, static const struct file_operations rs_sta_dbgfs_scale_table_ops = { .write = il4965_rs_sta_dbgfs_scale_table_write, .read = il4965_rs_sta_dbgfs_scale_table_read, - .open = il4965_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -2740,7 +2734,7 @@ il4965_rs_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf, static const struct file_operations rs_sta_dbgfs_stats_table_ops = { .read = il4965_rs_sta_dbgfs_stats_table_read, - .open = il4965_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -2768,7 +2762,7 @@ il4965_rs_sta_dbgfs_rate_scale_data_read(struct file *file, static const struct file_operations rs_sta_dbgfs_rate_scale_data_ops = { .read = il4965_rs_sta_dbgfs_rate_scale_data_read, - .open = il4965_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/iwlegacy/debug.c b/drivers/net/wireless/iwlegacy/debug.c index 229849150aac..eff26501d60a 100644 --- a/drivers/net/wireless/iwlegacy/debug.c +++ b/drivers/net/wireless/iwlegacy/debug.c @@ -160,18 +160,12 @@ static ssize_t il_dbgfs_##name##_write(struct file *file, \ const char __user *user_buf, \ size_t count, loff_t *ppos); -static int -il_dbgfs_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} #define DEBUGFS_READ_FILE_OPS(name) \ DEBUGFS_READ_FUNC(name); \ static const struct file_operations il_dbgfs_##name##_ops = { \ .read = il_dbgfs_##name##_read, \ - .open = il_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -179,7 +173,7 @@ static const struct file_operations il_dbgfs_##name##_ops = { \ DEBUGFS_WRITE_FUNC(name); \ static const struct file_operations il_dbgfs_##name##_ops = { \ .write = il_dbgfs_##name##_write, \ - .open = il_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -189,7 +183,7 @@ static const struct file_operations il_dbgfs_##name##_ops = { \ static const struct file_operations il_dbgfs_##name##_ops = { \ .write = il_dbgfs_##name##_write, \ .read = il_dbgfs_##name##_read, \ - .open = il_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c index 53f8c51cfcdb..7e590b349dd7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c @@ -3083,11 +3083,6 @@ static void rs_free_sta(void *priv_r, struct ieee80211_sta *sta, } #ifdef CONFIG_MAC80211_DEBUGFS -static int open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} static void rs_dbgfs_set_mcs(struct iwl_lq_sta *lq_sta, u32 *rate_n_flags, int index) { @@ -3226,7 +3221,7 @@ static ssize_t rs_sta_dbgfs_scale_table_read(struct file *file, static const struct file_operations rs_sta_dbgfs_scale_table_ops = { .write = rs_sta_dbgfs_scale_table_write, .read = rs_sta_dbgfs_scale_table_read, - .open = open_file_generic, + .open = simple_open, .llseek = default_llseek, }; static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file, @@ -3269,7 +3264,7 @@ static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file, static const struct file_operations rs_sta_dbgfs_stats_table_ops = { .read = rs_sta_dbgfs_stats_table_read, - .open = open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -3295,7 +3290,7 @@ static ssize_t rs_sta_dbgfs_rate_scale_data_read(struct file *file, static const struct file_operations rs_sta_dbgfs_rate_scale_data_ops = { .read = rs_sta_dbgfs_rate_scale_data_read, - .open = open_file_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c index b7b1c04f2fba..2bbaebd99ad4 100644 --- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c +++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c @@ -84,17 +84,11 @@ static ssize_t iwl_dbgfs_##name##_write(struct file *file, \ size_t count, loff_t *ppos); -static int iwl_dbgfs_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUGFS_READ_FILE_OPS(name) \ DEBUGFS_READ_FUNC(name); \ static const struct file_operations iwl_dbgfs_##name##_ops = { \ .read = iwl_dbgfs_##name##_read, \ - .open = iwl_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -102,7 +96,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = { \ DEBUGFS_WRITE_FUNC(name); \ static const struct file_operations iwl_dbgfs_##name##_ops = { \ .write = iwl_dbgfs_##name##_write, \ - .open = iwl_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -113,7 +107,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = { \ static const struct file_operations iwl_dbgfs_##name##_ops = { \ .write = iwl_dbgfs_##name##_write, \ .read = iwl_dbgfs_##name##_read, \ - .open = iwl_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c index b4f796c82e1e..4d7b30d3e648 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c +++ b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c @@ -1898,17 +1898,11 @@ static ssize_t iwl_dbgfs_##name##_write(struct file *file, \ size_t count, loff_t *ppos); -static int iwl_dbgfs_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUGFS_READ_FILE_OPS(name) \ DEBUGFS_READ_FUNC(name); \ static const struct file_operations iwl_dbgfs_##name##_ops = { \ .read = iwl_dbgfs_##name##_read, \ - .open = iwl_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -1916,7 +1910,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = { \ DEBUGFS_WRITE_FUNC(name); \ static const struct file_operations iwl_dbgfs_##name##_ops = { \ .write = iwl_dbgfs_##name##_write, \ - .open = iwl_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -1926,7 +1920,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = { \ static const struct file_operations iwl_dbgfs_##name##_ops = { \ .write = iwl_dbgfs_##name##_write, \ .read = iwl_dbgfs_##name##_read, \ - .open = iwl_dbgfs_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; diff --git a/drivers/net/wireless/iwmc3200wifi/debugfs.c b/drivers/net/wireless/iwmc3200wifi/debugfs.c index 87eef5773a02..b6199d124bb9 100644 --- a/drivers/net/wireless/iwmc3200wifi/debugfs.c +++ b/drivers/net/wireless/iwmc3200wifi/debugfs.c @@ -99,12 +99,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_iwm_dbg_modules, iwm_debugfs_u32_read, iwm_debugfs_dbg_modules_write, "%llu\n"); -static int iwm_generic_open(struct inode *inode, struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - static ssize_t iwm_debugfs_txq_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) @@ -401,28 +395,28 @@ out: static const struct file_operations iwm_debugfs_txq_fops = { .owner = THIS_MODULE, - .open = iwm_generic_open, + .open = simple_open, .read = iwm_debugfs_txq_read, .llseek = default_llseek, }; static const struct file_operations iwm_debugfs_tx_credit_fops = { .owner = THIS_MODULE, - .open = iwm_generic_open, + .open = simple_open, .read = iwm_debugfs_tx_credit_read, .llseek = default_llseek, }; static const struct file_operations iwm_debugfs_rx_ticket_fops = { .owner = THIS_MODULE, - .open = iwm_generic_open, + .open = simple_open, .read = iwm_debugfs_rx_ticket_read, .llseek = default_llseek, }; static const struct file_operations iwm_debugfs_fw_err_fops = { .owner = THIS_MODULE, - .open = iwm_generic_open, + .open = simple_open, .read = iwm_debugfs_fw_err_read, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/iwmc3200wifi/sdio.c b/drivers/net/wireless/iwmc3200wifi/sdio.c index 764b40dd24ad..0042f204b07f 100644 --- a/drivers/net/wireless/iwmc3200wifi/sdio.c +++ b/drivers/net/wireless/iwmc3200wifi/sdio.c @@ -264,13 +264,6 @@ static int if_sdio_send_chunk(struct iwm_priv *iwm, u8 *buf, int count) return ret; } -/* debugfs hooks */ -static int iwm_debugfs_sdio_open(struct inode *inode, struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - static ssize_t iwm_debugfs_sdio_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { @@ -363,7 +356,7 @@ err: static const struct file_operations iwm_debugfs_sdio_fops = { .owner = THIS_MODULE, - .open = iwm_debugfs_sdio_open, + .open = simple_open, .read = iwm_debugfs_sdio_read, .llseek = default_llseek, }; diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c index c192671610fc..a06cc283e23d 100644 --- a/drivers/net/wireless/libertas/debugfs.c +++ b/drivers/net/wireless/libertas/debugfs.c @@ -21,12 +21,6 @@ static char *szStates[] = { static void lbs_debug_init(struct lbs_private *priv); #endif -static int open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t write_file_dummy(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -696,7 +690,7 @@ out_unlock: #define FOPS(fread, fwrite) { \ .owner = THIS_MODULE, \ - .open = open_file_generic, \ + .open = simple_open, \ .read = (fread), \ .write = (fwrite), \ .llseek = generic_file_llseek, \ @@ -962,7 +956,7 @@ static ssize_t lbs_debugfs_write(struct file *f, const char __user *buf, static const struct file_operations lbs_debug_fops = { .owner = THIS_MODULE, - .open = open_file_generic, + .open = simple_open, .write = lbs_debugfs_write, .read = lbs_debugfs_read, .llseek = default_llseek, diff --git a/drivers/net/wireless/mwifiex/debugfs.c b/drivers/net/wireless/mwifiex/debugfs.c index d26a78b6b3c4..1a845074c52a 100644 --- a/drivers/net/wireless/mwifiex/debugfs.c +++ b/drivers/net/wireless/mwifiex/debugfs.c @@ -139,18 +139,6 @@ static struct mwifiex_debug_data items[] = { static int num_of_items = ARRAY_SIZE(items); -/* - * Generic proc file open handler. - * - * This function is called every time a file is accessed for read or write. - */ -static int -mwifiex_open_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - /* * Proc info file read handler. * @@ -676,19 +664,19 @@ done: static const struct file_operations mwifiex_dfs_##name##_fops = { \ .read = mwifiex_##name##_read, \ .write = mwifiex_##name##_write, \ - .open = mwifiex_open_generic, \ + .open = simple_open, \ }; #define MWIFIEX_DFS_FILE_READ_OPS(name) \ static const struct file_operations mwifiex_dfs_##name##_fops = { \ .read = mwifiex_##name##_read, \ - .open = mwifiex_open_generic, \ + .open = simple_open, \ }; #define MWIFIEX_DFS_FILE_WRITE_OPS(name) \ static const struct file_operations mwifiex_dfs_##name##_fops = { \ .write = mwifiex_##name##_write, \ - .open = mwifiex_open_generic, \ + .open = simple_open, \ }; diff --git a/drivers/net/wireless/wl1251/debugfs.c b/drivers/net/wireless/wl1251/debugfs.c index 6c274007d200..448da1f8c22f 100644 --- a/drivers/net/wireless/wl1251/debugfs.c +++ b/drivers/net/wireless/wl1251/debugfs.c @@ -47,7 +47,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf, \ \ static const struct file_operations name## _ops = { \ .read = name## _read, \ - .open = wl1251_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -84,7 +84,7 @@ static ssize_t sub## _ ##name## _read(struct file *file, \ \ static const struct file_operations sub## _ ##name## _ops = { \ .read = sub## _ ##name## _read, \ - .open = wl1251_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -117,12 +117,6 @@ out: mutex_unlock(&wl->mutex); } -static int wl1251_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - DEBUGFS_FWSTATS_FILE(tx, internal_desc_overflow, 20, "%u"); DEBUGFS_FWSTATS_FILE(rx, out_of_mem, 20, "%u"); @@ -235,7 +229,7 @@ static ssize_t tx_queue_len_read(struct file *file, char __user *userbuf, static const struct file_operations tx_queue_len_ops = { .read = tx_queue_len_read, - .open = wl1251_open_file_generic, + .open = simple_open, .llseek = generic_file_llseek, }; @@ -257,7 +251,7 @@ static ssize_t tx_queue_status_read(struct file *file, char __user *userbuf, static const struct file_operations tx_queue_status_ops = { .read = tx_queue_status_read, - .open = wl1251_open_file_generic, + .open = simple_open, .llseek = generic_file_llseek, }; diff --git a/drivers/net/wireless/wl12xx/debugfs.c b/drivers/net/wireless/wl12xx/debugfs.c index e1cf72765965..564d49575c94 100644 --- a/drivers/net/wireless/wl12xx/debugfs.c +++ b/drivers/net/wireless/wl12xx/debugfs.c @@ -63,7 +63,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf, \ \ static const struct file_operations name## _ops = { \ .read = name## _read, \ - .open = wl1271_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -96,7 +96,7 @@ static ssize_t sub## _ ##name## _read(struct file *file, \ \ static const struct file_operations sub## _ ##name## _ops = { \ .read = sub## _ ##name## _read, \ - .open = wl1271_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -126,12 +126,6 @@ out: mutex_unlock(&wl->mutex); } -static int wl1271_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - DEBUGFS_FWSTATS_FILE(tx, internal_desc_overflow, "%u"); DEBUGFS_FWSTATS_FILE(rx, out_of_mem, "%u"); @@ -243,7 +237,7 @@ static ssize_t tx_queue_len_read(struct file *file, char __user *userbuf, static const struct file_operations tx_queue_len_ops = { .read = tx_queue_len_read, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -289,7 +283,7 @@ static ssize_t gpio_power_write(struct file *file, static const struct file_operations gpio_power_ops = { .read = gpio_power_read, .write = gpio_power_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -308,7 +302,7 @@ static ssize_t start_recovery_write(struct file *file, static const struct file_operations start_recovery_ops = { .write = start_recovery_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -372,7 +366,7 @@ out: static const struct file_operations dynamic_ps_timeout_ops = { .read = dynamic_ps_timeout_read, .write = dynamic_ps_timeout_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -441,7 +435,7 @@ out: static const struct file_operations forced_ps_ops = { .read = forced_ps_read, .write = forced_ps_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -483,7 +477,7 @@ static ssize_t split_scan_timeout_write(struct file *file, static const struct file_operations split_scan_timeout_ops = { .read = split_scan_timeout_read, .write = split_scan_timeout_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -566,7 +560,7 @@ static ssize_t driver_state_read(struct file *file, char __user *user_buf, static const struct file_operations driver_state_ops = { .read = driver_state_read, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -675,7 +669,7 @@ static ssize_t vifs_state_read(struct file *file, char __user *user_buf, static const struct file_operations vifs_state_ops = { .read = vifs_state_read, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -733,7 +727,7 @@ static ssize_t dtim_interval_write(struct file *file, static const struct file_operations dtim_interval_ops = { .read = dtim_interval_read, .write = dtim_interval_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -791,7 +785,7 @@ static ssize_t suspend_dtim_interval_write(struct file *file, static const struct file_operations suspend_dtim_interval_ops = { .read = suspend_dtim_interval_read, .write = suspend_dtim_interval_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -849,7 +843,7 @@ static ssize_t beacon_interval_write(struct file *file, static const struct file_operations beacon_interval_ops = { .read = beacon_interval_read, .write = beacon_interval_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -904,7 +898,7 @@ static ssize_t rx_streaming_interval_read(struct file *file, static const struct file_operations rx_streaming_interval_ops = { .read = rx_streaming_interval_read, .write = rx_streaming_interval_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -959,7 +953,7 @@ static ssize_t rx_streaming_always_read(struct file *file, static const struct file_operations rx_streaming_always_ops = { .read = rx_streaming_always_read, .write = rx_streaming_always_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; @@ -1003,7 +997,7 @@ out: static const struct file_operations beacon_filtering_ops = { .write = beacon_filtering_write, - .open = wl1271_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index ee8fd037bb53..849357c1045c 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -117,25 +117,17 @@ static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_ } -static int default_open(struct inode *inode, struct file *filp) -{ - if (inode->i_private) - filp->private_data = inode->i_private; - return 0; -} - - static const struct file_operations ulong_fops = { .read = ulong_read_file, .write = ulong_write_file, - .open = default_open, + .open = simple_open, .llseek = default_llseek, }; static const struct file_operations ulong_ro_fops = { .read = ulong_read_file, - .open = default_open, + .open = simple_open, .llseek = default_llseek, }; @@ -187,7 +179,7 @@ static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t coun static const struct file_operations atomic_ro_fops = { .read = atomic_read_file, - .open = default_open, + .open = simple_open, .llseek = default_llseek, }; diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c index 70277a530133..85d31a69e117 100644 --- a/drivers/remoteproc/remoteproc_debugfs.c +++ b/drivers/remoteproc/remoteproc_debugfs.c @@ -50,16 +50,9 @@ static ssize_t rproc_trace_read(struct file *filp, char __user *userbuf, return simple_read_from_buffer(userbuf, count, ppos, trace->va, len); } -static int rproc_open_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - - return 0; -} - static const struct file_operations trace_rproc_ops = { .read = rproc_trace_read, - .open = rproc_open_generic, + .open = simple_open, .llseek = generic_file_llseek, }; @@ -94,7 +87,7 @@ static ssize_t rproc_state_read(struct file *filp, char __user *userbuf, static const struct file_operations rproc_state_ops = { .read = rproc_state_read, - .open = rproc_open_generic, + .open = simple_open, .llseek = generic_file_llseek, }; @@ -114,7 +107,7 @@ static ssize_t rproc_name_read(struct file *filp, char __user *userbuf, static const struct file_operations rproc_name_ops = { .read = rproc_name_read, - .open = rproc_open_generic, + .open = simple_open, .llseek = generic_file_llseek, }; diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 22e17be04d8a..34f7cf76bf4f 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -997,13 +997,6 @@ lpfc_debugfs_dumpDataDif_write(struct file *file, const char __user *buf, return nbytes; } -static int -lpfc_debugfs_dif_err_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t lpfc_debugfs_dif_err_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) @@ -3521,7 +3514,7 @@ static const struct file_operations lpfc_debugfs_op_dumpDif = { #undef lpfc_debugfs_op_dif_err static const struct file_operations lpfc_debugfs_op_dif_err = { .owner = THIS_MODULE, - .open = lpfc_debugfs_dif_err_open, + .open = simple_open, .llseek = lpfc_debugfs_lseek, .read = lpfc_debugfs_dif_err_read, .write = lpfc_debugfs_dif_err_write, diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index 082458d73ce9..d1a495f64e2d 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -63,12 +63,6 @@ struct chip_data { }; #ifdef CONFIG_DEBUG_FS -static int spi_show_regs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define SPI_REGS_BUFSIZE 1024 static ssize_t spi_show_regs(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -128,7 +122,7 @@ static ssize_t spi_show_regs(struct file *file, char __user *user_buf, static const struct file_operations mrst_spi_regs_ops = { .owner = THIS_MODULE, - .open = spi_show_regs_open, + .open = simple_open, .read = spi_show_regs, .llseek = default_llseek, }; diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c index a9234ba8f8d5..c4b50af46c44 100644 --- a/drivers/tty/serial/mfd.c +++ b/drivers/tty/serial/mfd.c @@ -127,11 +127,6 @@ static inline void serial_out(struct uart_hsu_port *up, int offset, int value) #define HSU_REGS_BUFSIZE 1024 -static int hsu_show_regs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} static ssize_t port_show_regs(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -231,14 +226,14 @@ static ssize_t dma_show_regs(struct file *file, char __user *user_buf, static const struct file_operations port_regs_ops = { .owner = THIS_MODULE, - .open = hsu_show_regs_open, + .open = simple_open, .read = port_show_regs, .llseek = default_llseek, }; static const struct file_operations dma_regs_ops = { .owner = THIS_MODULE, - .open = hsu_show_regs_open, + .open = simple_open, .read = dma_show_regs, .llseek = default_llseek, }; diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 332f2eb8abbc..46ec722b4406 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -304,11 +304,7 @@ static const int trigger_level_1[4] = { 1, 1, 1, 1 }; #ifdef CONFIG_DEBUG_FS #define PCH_REGS_BUFSIZE 1024 -static int pch_show_regs_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} + static ssize_t port_show_regs(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -362,7 +358,7 @@ static ssize_t port_show_regs(struct file *file, char __user *user_buf, static const struct file_operations port_regs_ops = { .owner = THIS_MODULE, - .open = pch_show_regs_open, + .open = simple_open, .read = port_show_regs, .llseek = default_llseek, }; diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index cefa0c8b5b6a..d2b9af59cba9 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -428,18 +428,10 @@ static loff_t default_file_lseek (struct file *file, loff_t offset, int orig) return retval; } -static int default_open (struct inode *inode, struct file *file) -{ - if (inode->i_private) - file->private_data = inode->i_private; - - return 0; -} - static const struct file_operations default_file_operations = { .read = default_read_file, .write = default_write_file, - .open = default_open, + .open = simple_open, .llseek = default_file_lseek, }; diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c index fd9109d7eb0e..680e1a31fb87 100644 --- a/drivers/usb/host/ehci-dbg.c +++ b/drivers/usb/host/ehci-dbg.c @@ -352,7 +352,6 @@ static int debug_async_open(struct inode *, struct file *); static int debug_periodic_open(struct inode *, struct file *); static int debug_registers_open(struct inode *, struct file *); static int debug_async_open(struct inode *, struct file *); -static int debug_lpm_open(struct inode *, struct file *); static ssize_t debug_lpm_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos); static ssize_t debug_lpm_write(struct file *file, const char __user *buffer, @@ -385,7 +384,7 @@ static const struct file_operations debug_registers_fops = { }; static const struct file_operations debug_lpm_fops = { .owner = THIS_MODULE, - .open = debug_lpm_open, + .open = simple_open, .read = debug_lpm_read, .write = debug_lpm_write, .release = debug_lpm_close, @@ -970,12 +969,6 @@ static int debug_registers_open(struct inode *inode, struct file *file) return file->private_data ? 0 : -ENOMEM; } -static int debug_lpm_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static int debug_lpm_close(struct inode *inode, struct file *file) { return 0; diff --git a/drivers/uwb/uwb-debug.c b/drivers/uwb/uwb-debug.c index 2eecec0c13c9..6ec45beb7af5 100644 --- a/drivers/uwb/uwb-debug.c +++ b/drivers/uwb/uwb-debug.c @@ -159,13 +159,6 @@ static int cmd_ie_rm(struct uwb_rc *rc, struct uwb_dbg_cmd_ie *ie_to_rm) return uwb_rc_ie_rm(rc, ie_to_rm->data[0]); } -static int command_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - - return 0; -} - static ssize_t command_write(struct file *file, const char __user *buf, size_t len, loff_t *off) { @@ -206,7 +199,7 @@ static ssize_t command_write(struct file *file, const char __user *buf, } static const struct file_operations command_fops = { - .open = command_open, + .open = simple_open, .write = command_write, .read = NULL, .llseek = no_llseek, diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 21e93605161c..5dfafdd1dbd3 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -33,18 +33,10 @@ static ssize_t default_write_file(struct file *file, const char __user *buf, return count; } -static int default_open(struct inode *inode, struct file *file) -{ - if (inode->i_private) - file->private_data = inode->i_private; - - return 0; -} - const struct file_operations debugfs_file_operations = { .read = default_read_file, .write = default_write_file, - .open = default_open, + .open = simple_open, .llseek = noop_llseek, }; @@ -447,7 +439,7 @@ static ssize_t write_file_bool(struct file *file, const char __user *user_buf, static const struct file_operations fops_bool = { .read = read_file_bool, .write = write_file_bool, - .open = default_open, + .open = simple_open, .llseek = default_llseek, }; @@ -492,7 +484,7 @@ static ssize_t read_file_blob(struct file *file, char __user *user_buf, static const struct file_operations fops_blob = { .read = read_file_blob, - .open = default_open, + .open = simple_open, .llseek = default_llseek, }; diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 3dca2b39e83f..1c9b08095f98 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -609,13 +609,6 @@ static const struct file_operations format3_fops = { /* * dump lkb's on the ls_waiters list */ - -static int waiters_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t waiters_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -644,7 +637,7 @@ static ssize_t waiters_read(struct file *file, char __user *userbuf, static const struct file_operations waiters_fops = { .owner = THIS_MODULE, - .open = waiters_open, + .open = simple_open, .read = waiters_read, .llseek = default_llseek, }; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index f37c32b94525..8ae5a03376ae 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -52,12 +52,6 @@ struct pstore_private { char data[]; }; -static int pstore_file_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t pstore_file_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -67,7 +61,7 @@ static ssize_t pstore_file_read(struct file *file, char __user *userbuf, } static const struct file_operations pstore_file_operations = { - .open = pstore_file_open, + .open = simple_open, .read = pstore_file_read, .llseek = default_llseek, }; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index cdea7b56b0c9..c0bd0308741c 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -311,13 +311,6 @@ int blk_trace_remove(struct request_queue *q) } 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) { @@ -331,18 +324,11 @@ static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, static const struct file_operations blk_dropped_fops = { .owner = THIS_MODULE, - .open = blk_dropped_open, + .open = simple_open, .read = blk_dropped_read, .llseek = default_llseek, }; -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) { @@ -371,7 +357,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, static const struct file_operations blk_msg_fops = { .owner = THIS_MODULE, - .open = blk_msg_open, + .open = simple_open, .write = blk_msg_write, .llseek = noop_llseek, }; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index cc5b7a6e7e0b..778e5916d7c3 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -15,12 +15,6 @@ #include "rate.h" #include "debugfs.h" -int mac80211_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUGFS_FORMAT_BUFFER_SIZE 100 int mac80211_format_buffer(char __user *userbuf, size_t count, @@ -50,7 +44,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf, \ #define DEBUGFS_READONLY_FILE_OPS(name) \ static const struct file_operations name## _ops = { \ .read = name## _read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -93,7 +87,7 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, static const struct file_operations reset_ops = { .write = reset_write, - .open = mac80211_open_file_generic, + .open = simple_open, .llseek = noop_llseek, }; @@ -254,7 +248,7 @@ static ssize_t stats_ ##name## _read(struct file *file, \ \ static const struct file_operations stats_ ##name## _ops = { \ .read = stats_ ##name## _read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; diff --git a/net/mac80211/debugfs.h b/net/mac80211/debugfs.h index 7c87529630f5..9be4e6d71d00 100644 --- a/net/mac80211/debugfs.h +++ b/net/mac80211/debugfs.h @@ -3,7 +3,6 @@ #ifdef CONFIG_MAC80211_DEBUGFS extern void debugfs_hw_add(struct ieee80211_local *local); -extern int mac80211_open_file_generic(struct inode *inode, struct file *file); extern int mac80211_format_buffer(char __user *userbuf, size_t count, loff_t *ppos, char *fmt, ...); #else diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 59edcd95a58d..7932767bb482 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -30,7 +30,7 @@ static ssize_t key_##name##_read(struct file *file, \ #define KEY_OPS(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_##name##_read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } @@ -45,7 +45,7 @@ static const struct file_operations key_ ##name## _ops = { \ #define KEY_CONF_OPS(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_conf_##name##_read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index a32eeda04aa3..30f99c344847 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -135,7 +135,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file, \ static const struct file_operations name##_ops = { \ .read = ieee80211_if_read_##name, \ .write = (_write), \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 6d45804d09bc..832b2da5e4cd 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -33,7 +33,7 @@ static ssize_t sta_ ##name## _read(struct file *file, \ #define STA_OPS(name) \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } @@ -41,7 +41,7 @@ static const struct file_operations sta_ ##name## _ops = { \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ .write = sta_##name##_write, \ - .open = mac80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index b4f7600a3e36..3313c117b322 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -145,7 +145,7 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf, static const struct file_operations rcname_ops = { .read = rcname_read, - .open = mac80211_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; #endif diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c index 39765bcfb472..920cabe0461b 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -13,12 +13,6 @@ #include "core.h" #include "debugfs.h" -static int cfg80211_open_file_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - #define DEBUGFS_READONLY_FILE(name, buflen, fmt, value...) \ static ssize_t name## _read(struct file *file, char __user *userbuf, \ size_t count, loff_t *ppos) \ @@ -33,7 +27,7 @@ static ssize_t name## _read(struct file *file, char __user *userbuf, \ \ static const struct file_operations name## _ops = { \ .read = name## _read, \ - .open = cfg80211_open_file_generic, \ + .open = simple_open, \ .llseek = generic_file_llseek, \ }; @@ -102,7 +96,7 @@ static ssize_t ht40allow_map_read(struct file *file, static const struct file_operations ht40allow_map_ops = { .read = ht40allow_map_read, - .open = cfg80211_open_file_generic, + .open = simple_open, .llseek = default_llseek, }; diff --git a/sound/soc/imx/imx-audmux.c b/sound/soc/imx/imx-audmux.c index 601df809a26a..1765a197acb0 100644 --- a/sound/soc/imx/imx-audmux.c +++ b/sound/soc/imx/imx-audmux.c @@ -40,12 +40,6 @@ static void __iomem *audmux_base; #ifdef CONFIG_DEBUG_FS static struct dentry *audmux_debugfs_root; -static int audmux_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - /* There is an annoying discontinuity in the SSI numbering with regard * to the Linux number of the devices */ static const char *audmux_port_string(int port) @@ -142,7 +136,7 @@ static ssize_t audmux_read_file(struct file *file, char __user *user_buf, } static const struct file_operations audmux_debugfs_fops = { - .open = audmux_open_file, + .open = simple_open, .read = audmux_read_file, .llseek = default_llseek, }; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index a4deebc0801a..e19c24ade414 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -201,12 +201,6 @@ static ssize_t pmdown_time_set(struct device *dev, static DEVICE_ATTR(pmdown_time, 0644, pmdown_time_show, pmdown_time_set); #ifdef CONFIG_DEBUG_FS -static int codec_reg_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t codec_reg_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -264,7 +258,7 @@ static ssize_t codec_reg_write_file(struct file *file, } static const struct file_operations codec_reg_fops = { - .open = codec_reg_open_file, + .open = simple_open, .read = codec_reg_read_file, .write = codec_reg_write_file, .llseek = default_llseek, diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 6241490fff30..5cbd2d7623b8 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1544,12 +1544,6 @@ static int dapm_power_widgets(struct snd_soc_dapm_context *dapm, int event) } #ifdef CONFIG_DEBUG_FS -static int dapm_widget_power_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t dapm_widget_power_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -1613,17 +1607,11 @@ static ssize_t dapm_widget_power_read_file(struct file *file, } static const struct file_operations dapm_widget_power_fops = { - .open = dapm_widget_power_open_file, + .open = simple_open, .read = dapm_widget_power_read_file, .llseek = default_llseek, }; -static int dapm_bias_open_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - static ssize_t dapm_bias_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -1654,7 +1642,7 @@ static ssize_t dapm_bias_read_file(struct file *file, char __user *user_buf, } static const struct file_operations dapm_bias_fops = { - .open = dapm_bias_open_file, + .open = simple_open, .read = dapm_bias_read_file, .llseek = default_llseek, }; -- cgit v1.3-8-gc7d7 From d3283fb45c06dfd7b1a36da8e6ff39d313f0600c Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 9 Apr 2012 11:00:25 -0700 Subject: trace: Remove unused workqueue tracer This tracer was temporarily removed in 6416669 (workqueue: temporarily remove workqueue tracing, 2010-06-29) but never reinstated after concurrency managed workqueues were completed. For almost two years it hasn't been compilable so it seems nobody is using it. Delete it. Signed-off-by: Stephen Boyd Acked-by: Frederic Weisbecker Signed-off-by: Tejun Heo --- kernel/trace/Makefile | 1 - kernel/trace/trace_workqueue.c | 300 ----------------------------------------- 2 files changed, 301 deletions(-) delete mode 100644 kernel/trace/trace_workqueue.c (limited to 'kernel/trace') diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 5f39a07fe5ea..b3afe0e76f79 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.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 diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c deleted file mode 100644 index 209b379a4721..000000000000 --- a/kernel/trace/trace_workqueue.c +++ /dev/null @@ -1,300 +0,0 @@ -/* - * Workqueue statistical tracer. - * - * Copyright (C) 2008 Frederic Weisbecker - * - */ - - -#include -#include -#include -#include -#include -#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(void *ignore, - 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(void *ignore, - 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(void *ignore, - 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(void *ignore, 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; - - for_each_possible_cpu(cpu) { - spin_lock_init(&workqueue_cpu_stat(cpu)->lock); - INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list); - } - - ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL); - if (ret) - goto out; - - ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL); - if (ret) - goto no_insertion; - - ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL); - if (ret) - goto no_execution; - - ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL); - if (ret) - goto no_creation; - - return 0; - -no_creation: - unregister_trace_workqueue_creation(probe_workqueue_creation, NULL); -no_execution: - unregister_trace_workqueue_execution(probe_workqueue_execution, NULL); -no_insertion: - unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL); -out: - pr_warning("trace_workqueue: unable to trace workqueues\n"); - - return 1; -} -early_initcall(trace_workqueue_early_init); -- cgit v1.3-8-gc7d7 From 6e48b550d1f5f1919e6500547ae14a73fbf66c7b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 13 Apr 2012 09:52:59 +0100 Subject: tracing: Fix build breakage without CONFIG_PERF_EVENTS (again) Today's -next fails to link for me: kernel/built-in.o:(.data+0x178e50): undefined reference to `perf_ftrace_event_register' It looks like multiple fixes have been merged for the issue fixed by commit fa73dc9 (tracing: Fix build breakage without CONFIG_PERF_EVENTS) though I can't identify the other changes that have gone in at the minute, it's possible that the changes which caused the breakage fixed by the previous commit got dropped but the fix made it in. Link: http://lkml.kernel.org/r/1334307179-21255-1-git-send-email-broonie@opensource.wolfsonmicro.com Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Mark Brown Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 95059f091a24..f95d65da6db8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -836,11 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[]; filter) #include "trace_entries.h" -#ifdef CONFIG_FUNCTION_TRACER +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER) int perf_ftrace_event_register(struct ftrace_event_call *call, enum trace_reg type, void *data); #else #define perf_ftrace_event_register NULL -#endif /* CONFIG_FUNCTION_TRACER */ +#endif #endif /* _LINUX_KERNEL_TRACE_H */ -- cgit v1.3-8-gc7d7 From 348f0fc238efb441a28e7644c51f9fd3001b228a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Apr 2012 15:41:28 -0400 Subject: tracing: Fix regression with tracing_on The change to make tracing_on affect only the ftrace ring buffer, caused a bug where it wont affect any ring buffer. The problem was that the buffer of the trace_array was passed to the write function and not the trace array itself. The trace_array can change the buffer when running a latency tracer. If this happens, then the buffer being disabled may not be the buffer currently used by ftrace. This will cause the tracing_on file to become useless. The simple fix is to pass the trace_array to the write function instead of the buffer. Then the actual buffer may be changed. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ed7b5d1e12f4..2a22255c1010 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4629,7 +4629,8 @@ static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ring_buffer *buffer = filp->private_data; + struct trace_array *tr = filp->private_data; + struct ring_buffer *buffer = tr->buffer; char buf[64]; int r; @@ -4647,7 +4648,8 @@ static ssize_t rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ring_buffer *buffer = filp->private_data; + struct trace_array *tr = filp->private_data; + struct ring_buffer *buffer = tr->buffer; unsigned long val; int ret; @@ -4734,7 +4736,7 @@ static __init int tracer_init_debugfs(void) &trace_clock_fops); trace_create_file("tracing_on", 0644, d_tracer, - global_trace.buffer, &rb_simple_fops); + &global_trace, &rb_simple_fops); #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, -- cgit v1.3-8-gc7d7 From 59bf896406471ac49d124b3e5f4edcafe28e5360 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Wed, 18 Apr 2012 00:01:21 +0900 Subject: Fix "the the" in various Kconfig Fix typo "the the" in various Kconfig. Signed-off-by: Masanari Iida Signed-off-by: Jiri Kosina --- arch/arm/Kconfig | 4 ++-- arch/arm/mach-s3c64xx/Kconfig | 4 ++-- arch/blackfin/Kconfig | 2 +- drivers/iommu/Kconfig | 4 ++-- drivers/net/can/sja1000/Kconfig | 2 +- drivers/net/irda/Kconfig | 2 +- kernel/trace/Kconfig | 2 +- sound/soc/imx/Kconfig | 2 +- 8 files changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel/trace') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index cf006d40342c..73f90dd5554b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1927,10 +1927,10 @@ choice default ZBOOT_ROM_NONE help Include experimental SD/MMC loading code in the ROM-able zImage. - With this enabled it is possible to write the the ROM-able zImage + With this enabled it is possible to write the ROM-able zImage kernel image to an MMC or SD card and boot the kernel straight from the reset vector. At reset the processor Mask ROM will load - the first part of the the ROM-able zImage which in turn loads the + the first part of the ROM-able zImage which in turn loads the rest the kernel image to RAM. config ZBOOT_ROM_NONE diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig index 82c0915729ee..06ca1cd4cae2 100644 --- a/arch/arm/mach-s3c64xx/Kconfig +++ b/arch/arm/mach-s3c64xx/Kconfig @@ -210,7 +210,7 @@ config SMDK6410_WM1190_EV1 and audio daughtercard for the Samsung SMDK6410 reference platform. Enabling this option will build support for this module into the kernel. The presence of the module will be - detected at runtime so the the resulting kernel can be used + detected at runtime so the resulting kernel can be used with or without the 1190-EV1 fitted. config SMDK6410_WM1192_EV1 @@ -226,7 +226,7 @@ config SMDK6410_WM1192_EV1 daughtercard for the Samsung SMDK6410 reference platform. Enabling this option will build support for this module into the kernel. The presence of the daughtercard will be - detected at runtime so the the resulting kernel can be used + detected at runtime so the resulting kernel can be used with or without the 1192-EV1 fitted. config MACH_NCP diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 373a6902d8fa..b83e89ced988 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -1258,7 +1258,7 @@ config PM_BFIN_WAKE_GP (all processors, except ADSP-BF549). This option sets the general-purpose wake-up enable (GPWE) control bit to enable wake-up upon detection of an active low signal on the /GPW (PH7) pin. - On ADSP-BF549 this option enables the the same functionality on the + On ADSP-BF549 this option enables the same functionality on the /MRXON pin also PH7. endmenu diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 3bd9fff5c589..c69843742bb0 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -43,7 +43,7 @@ config AMD_IOMMU With this option you can enable support for AMD IOMMU hardware in your system. An IOMMU is a hardware component which provides remapping of DMA memory accesses from devices. With an AMD IOMMU you - can isolate the the DMA memory of different devices and protect the + can isolate the DMA memory of different devices and protect the system from misbehaving device drivers or hardware. You can find out if your system has an AMD IOMMU if you look into @@ -67,7 +67,7 @@ config AMD_IOMMU_V2 ---help--- This option enables support for the AMD IOMMUv2 features of the IOMMU hardware. Select this option if you want to use devices that support - the the PCI PRI and PASID interface. + the PCI PRI and PASID interface. # Intel IOMMU support config DMAR_TABLE diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig index b60d6c5f29a0..03df9a8f2bbf 100644 --- a/drivers/net/can/sja1000/Kconfig +++ b/drivers/net/can/sja1000/Kconfig @@ -75,7 +75,7 @@ config CAN_KVASER_PCI tristate "Kvaser PCIcanx and Kvaser PCIcan PCI Cards" depends on PCI ---help--- - This driver is for the the PCIcanx and PCIcan cards (1, 2 or + This driver is for the PCIcanx and PCIcan cards (1, 2 or 4 channel) from Kvaser (http://www.kvaser.com). config CAN_PLX_PCI diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig index 468047866c8c..1b6d5c03edfa 100644 --- a/drivers/net/irda/Kconfig +++ b/drivers/net/irda/Kconfig @@ -316,7 +316,7 @@ config AU1000_FIR tristate "Alchemy IrDA SIR/FIR" depends on IRDA && MIPS_ALCHEMY help - Say Y/M here to build suppor the the IrDA peripheral on the + Say Y/M here to build support the IrDA peripheral on the Alchemy Au1000 and Au1100 SoCs. Say M to build a module; it will be called au1k_ir.ko diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a1d2849f2473..33f768b779c9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -272,7 +272,7 @@ config PROFILE_ANNOTATED_BRANCHES bool "Trace likely/unlikely profiler" select TRACE_BRANCH_PROFILING help - This tracer profiles all the the likely and unlikely macros + This tracer profiles all likely and unlikely macros in the kernel. It will display the results in: /sys/kernel/debug/tracing/trace_stat/branch_annotated diff --git a/sound/soc/imx/Kconfig b/sound/soc/imx/Kconfig index 810acaa09009..d83e5d0b5d52 100644 --- a/sound/soc/imx/Kconfig +++ b/sound/soc/imx/Kconfig @@ -28,7 +28,7 @@ config SND_SOC_IMX_AUDMUX tristate config SND_MXC_SOC_WM1133_EV1 - tristate "Audio on the the i.MX31ADS with WM1133-EV1 fitted" + tristate "Audio on the i.MX31ADS with WM1133-EV1 fitted" depends on MACH_MX31ADS_WM1133_EV1 && EXPERIMENTAL select SND_SOC_WM8350 select SND_MXC_SOC_FIQ -- cgit v1.3-8-gc7d7 From db4c75cbebd7e5910cd3bcb6790272fcc3042857 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Apr 2012 10:31:47 -0400 Subject: tracing: Fix stacktrace of latency tracers (irqsoff and friends) While debugging a latency with someone on IRC (mirage335) on #linux-rt (OFTC), we discovered that the stacktrace output of the latency tracers (preemptirqsoff) was empty. This bug was caused by the creation of the dynamic length stack trace again (like commit 12b5da3 "tracing: Fix ent_size in trace output" was). This bug is caused by the latency tracers requiring the next event to determine the time between the current event and the next. But by grabbing the next event, the iter->ent_size is set to the next event instead of the current one. As the stacktrace event is the last event, this makes the ent_size zero and causes nothing to be printed for the stack trace. The dynamic stacktrace uses the ent_size to determine how much of the stack can be printed. The ent_size of zero means no stack. The simple fix is to save the iter->ent_size before finding the next event. Note, mirage335 asked to remain anonymous from LKML and git, so I will not add the Reported-by and Tested-by tags, even though he did report the issue and tested the fix. Cc: stable@vger.kernel.org # 3.1+ Signed-off-by: Steven Rostedt --- kernel/trace/trace_output.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 859fae6b1825..df611a0e76c5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -652,6 +652,8 @@ int trace_print_lat_context(struct trace_iterator *iter) { u64 next_ts; int ret; + /* trace_find_next_entry will reset ent_size */ + int ent_size = iter->ent_size; struct trace_seq *s = &iter->seq; struct trace_entry *entry = iter->ent, *next_entry = trace_find_next_entry(iter, NULL, @@ -660,6 +662,9 @@ int trace_print_lat_context(struct trace_iterator *iter) unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start); unsigned long rel_usecs; + /* Restore the original ent_size */ + iter->ent_size = ent_size; + if (!next_entry) next_ts = iter->ts; rel_usecs = ns2usecs(next_ts - iter->ts); -- cgit v1.3-8-gc7d7 From 07d777fe8c3985bc83428c2866713c2d1b3d4129 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Sep 2011 14:01:55 -0400 Subject: tracing: Add percpu buffers for trace_printk() Currently, trace_printk() uses a single buffer to write into to calculate the size and format needed to save the trace. To do this safely in an SMP environment, a spin_lock() is taken to only allow one writer at a time to the buffer. But this could also affect what is being traced, and add synchronization that would not be there otherwise. Ideally, using percpu buffers would be useful, but since trace_printk() is only used in development, having per cpu buffers for something never used is a waste of space. Thus, the use of the trace_bprintk() format section is changed to be used for static fmts as well as dynamic ones. Then at boot up, we can check if the section that holds the trace_printk formats is non-empty, and if it does contain something, then we know a trace_printk() has been added to the kernel. At this time the trace_printk per cpu buffers are allocated. A check is also done at module load time in case a module is added that contains a trace_printk(). Once the buffers are allocated, they are never freed. If you use a trace_printk() then you should know what you are doing. A buffer is made for each type of context: normal softirq irq nmi The context is checked and the appropriate buffer is used. This allows for totally lockless usage of trace_printk(), and they no longer even disable interrupts. Requested-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 13 ++-- kernel/trace/trace.c | 184 ++++++++++++++++++++++++++++++++------------ kernel/trace/trace.h | 2 + kernel/trace/trace_printk.c | 4 + 4 files changed, 148 insertions(+), 55 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 645231c373c8..c0d34420a913 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -480,15 +480,16 @@ do { \ #define trace_printk(fmt, args...) \ do { \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ __trace_printk_check_format(fmt, ##args); \ - if (__builtin_constant_p(fmt)) { \ - static const char *trace_printk_fmt \ - __attribute__((section("__trace_printk_fmt"))) = \ - __builtin_constant_p(fmt) ? fmt : NULL; \ \ + if (__builtin_constant_p(fmt)) \ __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \ - } else \ - __trace_printk(_THIS_IP_, fmt, ##args); \ + else \ + __trace_printk(_THIS_IP_, fmt, ##args); \ } while (0) extern __printf(2, 3) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ed7b5d1e12f4..1ab8e35d069b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1498,25 +1498,119 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags) #endif /* CONFIG_STACKTRACE */ +/* created for use with alloc_percpu */ +struct trace_buffer_struct { + char buffer[TRACE_BUF_SIZE]; +}; + +static struct trace_buffer_struct *trace_percpu_buffer; +static struct trace_buffer_struct *trace_percpu_sirq_buffer; +static struct trace_buffer_struct *trace_percpu_irq_buffer; +static struct trace_buffer_struct *trace_percpu_nmi_buffer; + +/* + * The buffer used is dependent on the context. There is a per cpu + * buffer for normal context, softirq contex, hard irq context and + * for NMI context. Thise allows for lockless recording. + * + * Note, if the buffers failed to be allocated, then this returns NULL + */ +static char *get_trace_buf(void) +{ + struct trace_buffer_struct *percpu_buffer; + struct trace_buffer_struct *buffer; + + /* + * If we have allocated per cpu buffers, then we do not + * need to do any locking. + */ + if (in_nmi()) + percpu_buffer = trace_percpu_nmi_buffer; + else if (in_irq()) + percpu_buffer = trace_percpu_irq_buffer; + else if (in_softirq()) + percpu_buffer = trace_percpu_sirq_buffer; + else + percpu_buffer = trace_percpu_buffer; + + if (!percpu_buffer) + return NULL; + + buffer = per_cpu_ptr(percpu_buffer, smp_processor_id()); + + return buffer->buffer; +} + +static int alloc_percpu_trace_buffer(void) +{ + struct trace_buffer_struct *buffers; + struct trace_buffer_struct *sirq_buffers; + struct trace_buffer_struct *irq_buffers; + struct trace_buffer_struct *nmi_buffers; + + buffers = alloc_percpu(struct trace_buffer_struct); + if (!buffers) + goto err_warn; + + sirq_buffers = alloc_percpu(struct trace_buffer_struct); + if (!sirq_buffers) + goto err_sirq; + + irq_buffers = alloc_percpu(struct trace_buffer_struct); + if (!irq_buffers) + goto err_irq; + + nmi_buffers = alloc_percpu(struct trace_buffer_struct); + if (!nmi_buffers) + goto err_nmi; + + trace_percpu_buffer = buffers; + trace_percpu_sirq_buffer = sirq_buffers; + trace_percpu_irq_buffer = irq_buffers; + trace_percpu_nmi_buffer = nmi_buffers; + + return 0; + + err_nmi: + free_percpu(irq_buffers); + err_irq: + free_percpu(sirq_buffers); + err_sirq: + free_percpu(buffers); + err_warn: + WARN(1, "Could not allocate percpu trace_printk buffer"); + return -ENOMEM; +} + +void trace_printk_init_buffers(void) +{ + static int buffers_allocated; + + if (buffers_allocated) + return; + + if (alloc_percpu_trace_buffer()) + return; + + pr_info("ftrace: Allocated trace_printk buffers\n"); + + buffers_allocated = 1; +} + /** * 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 cpu, len = 0, size, pc; + char *tbuffer; + int len = 0, size, pc; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -1526,43 +1620,36 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) 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)) + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; 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); + len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); - if (len > TRACE_BUF_SIZE || len < 0) - goto out_unlock; + if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) + goto out; + local_save_flags(flags); 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; + goto out; entry = ring_buffer_event_data(event); entry->ip = ip; entry->fmt = fmt; - memcpy(entry->buf, trace_buf, sizeof(u32) * len); + memcpy(entry->buf, tbuffer, sizeof(u32) * len); if (!filter_check_discard(call, entry, buffer, event)) { ring_buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } -out_unlock: - arch_spin_unlock(&trace_buf_lock); - local_irq_restore(flags); - out: - atomic_dec_return(&data->disabled); preempt_enable_notrace(); unpause_graph_tracing(); @@ -1588,58 +1675,53 @@ int trace_array_printk(struct trace_array *tr, 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; + int len = 0, size, pc; struct print_entry *entry; - unsigned long irq_flags; - int disable; + unsigned long flags; + char *tbuffer; if (tracing_disabled || tracing_selftest_running) return 0; + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + 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)) + + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; 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); + len = vsnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); + if (len > TRACE_BUF_SIZE) + goto out; + local_save_flags(flags); size = sizeof(*entry) + len + 1; buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - irq_flags, pc); + flags, pc); if (!event) - goto out_unlock; + goto out; entry = ring_buffer_event_data(event); entry->ip = ip; - memcpy(&entry->buf, trace_buf, len); + memcpy(&entry->buf, tbuffer, len); entry->buf[len] = '\0'; if (!filter_check_discard(call, entry, buffer, event)) { ring_buffer_unlock_commit(buffer, event); - ftrace_trace_stack(buffer, irq_flags, 6, pc); + ftrace_trace_stack(buffer, flags, 6, pc); } - - 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(); + unpause_graph_tracing(); return len; } @@ -4955,6 +5037,10 @@ __init static int tracer_alloc_buffers(void) if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL)) goto out_free_buffer_mask; + /* Only allocate trace_printk buffers if a trace_printk exists */ + if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + trace_printk_init_buffers(); + /* To save memory, keep the ring buffer size to its minimum */ if (ring_buffer_expanded) ring_buf_size = trace_buf_size; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 95059f091a24..f9d85504f04b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -826,6 +826,8 @@ extern struct list_head ftrace_events; extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; +void trace_printk_init_buffers(void); + #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 6fd4ffd042f9..a9077c1b4ad3 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -51,6 +51,10 @@ void hold_module_trace_bprintk_format(const char **start, const char **end) const char **iter; char *fmt; + /* allocate the trace_printk per cpu buffers */ + if (start != end) + trace_printk_init_buffers(); + mutex_lock(&btrace_mutex); for (iter = start; iter < end; iter++) { struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter); -- cgit v1.3-8-gc7d7 From 5a26c8f0cf1e95106858bb4e23ca6dd14c9b842f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 20 Apr 2012 09:31:45 +0300 Subject: tracing: Remove an unneeded check in trace_seq_buffer() memcpy() returns a pointer to "bug". Hopefully, it's not NULL here or we would already have Oopsed. Link: http://lkml.kernel.org/r/20120420063145.GA22649@elgon.mountain Cc: Frederic Weisbecker Cc: Eduard - Gabriel Munteanu Signed-off-by: Dan Carpenter Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1ab8e35d069b..bbcde546f9f7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -629,7 +629,6 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t 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; @@ -637,9 +636,7 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) len = s->len - s->readpos; if (cnt > len) cnt = len; - ret = memcpy(buf, s->buffer + s->readpos, cnt); - if (!ret) - return -EFAULT; + memcpy(buf, s->buffer + s->readpos, cnt); s->readpos += cnt; return cnt; -- cgit v1.3-8-gc7d7 From 438ced1720b584000a9e8a4349d1f6bb7ee3ad6d Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Thu, 2 Feb 2012 12:00:41 -0800 Subject: ring-buffer: Add per_cpu ring buffer control files Add a debugfs entry under per_cpu/ folder for each cpu called buffer_size_kb to control the ring buffer size for each CPU independently. If the global file buffer_size_kb is used to set size, the individual ring buffers will be adjusted to the given size. The buffer_size_kb will report the common size to maintain backward compatibility. If the buffer_size_kb file under the per_cpu/ directory is used to change buffer size for a specific CPU, only the size of the respective ring buffer is updated. When tracing/buffer_size_kb is read, it reports 'X' to indicate that sizes of per_cpu ring buffers are not equivalent. Link: http://lkml.kernel.org/r/1328212844-11889-1-git-send-email-vnagarnaik@google.com Cc: Frederic Weisbecker Cc: Michael Rubin Cc: David Sharp Cc: Justin Teravest Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 6 +- kernel/trace/ring_buffer.c | 248 +++++++++++++++++++++++++------------------- kernel/trace/trace.c | 190 ++++++++++++++++++++++++++------- kernel/trace/trace.h | 2 +- 4 files changed, 297 insertions(+), 149 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 7be2e88f23fd..6c8835f74f79 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -96,9 +96,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +#define RING_BUFFER_ALL_CPUS -1 + void ring_buffer_free(struct ring_buffer *buffer); -int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size); +int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, int cpu); void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val); @@ -129,7 +131,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts); void ring_buffer_iter_reset(struct ring_buffer_iter *iter); int ring_buffer_iter_empty(struct ring_buffer_iter *iter); -unsigned long ring_buffer_size(struct ring_buffer *buffer); +unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu); void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_reset(struct ring_buffer *buffer); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index cf8d11e91efd..2d5eb3320827 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -449,6 +449,7 @@ struct ring_buffer_per_cpu { raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; + unsigned int nr_pages; struct list_head *pages; struct buffer_page *head_page; /* read from head */ struct buffer_page *tail_page; /* write to tail */ @@ -466,10 +467,12 @@ struct ring_buffer_per_cpu { unsigned long read_bytes; u64 write_stamp; u64 read_stamp; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ + int nr_pages_to_update; + struct list_head new_pages; /* new pages to add */ }; struct ring_buffer { - unsigned pages; unsigned flags; int cpus; atomic_t record_disabled; @@ -963,14 +966,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) return 0; } -static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, - unsigned nr_pages) +static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu) { + int i; struct buffer_page *bpage, *tmp; - LIST_HEAD(pages); - unsigned i; - - WARN_ON(!nr_pages); for (i = 0; i < nr_pages; i++) { struct page *page; @@ -981,15 +980,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, */ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL | __GFP_NORETRY, - cpu_to_node(cpu_buffer->cpu)); + cpu_to_node(cpu)); if (!bpage) goto free_pages; - rb_check_bpage(cpu_buffer, bpage); + list_add(&bpage->list, pages); - list_add(&bpage->list, &pages); - - page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); if (!page) goto free_pages; @@ -997,6 +994,27 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_init_page(bpage->page); } + 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 int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, + unsigned nr_pages) +{ + LIST_HEAD(pages); + + WARN_ON(!nr_pages); + + if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu)) + return -ENOMEM; + /* * 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 @@ -1005,20 +1023,15 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, cpu_buffer->pages = pages.next; list_del(&pages); + cpu_buffer->nr_pages = nr_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) +rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; @@ -1052,7 +1065,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) INIT_LIST_HEAD(&cpu_buffer->reader_page->list); - ret = rb_allocate_pages(cpu_buffer, buffer->pages); + ret = rb_allocate_pages(cpu_buffer, nr_pages); if (ret < 0) goto fail_free_reader; @@ -1113,7 +1126,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, { struct ring_buffer *buffer; int bsize; - int cpu; + int cpu, nr_pages; /* keep it in its own cache line */ buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()), @@ -1124,14 +1137,14 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) goto fail_free_buffer; - buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + nr_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; + if (nr_pages < 2) + nr_pages = 2; /* * In case of non-hotplug cpu, if the ring-buffer is allocated @@ -1154,7 +1167,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, for_each_buffer_cpu(buffer, cpu) { buffer->buffers[cpu] = - rb_allocate_cpu_buffer(buffer, cpu); + rb_allocate_cpu_buffer(buffer, nr_pages, cpu); if (!buffer->buffers[cpu]) goto fail_free_buffers; } @@ -1276,6 +1289,18 @@ out: raw_spin_unlock_irq(&cpu_buffer->reader_lock); } +static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer) +{ + if (cpu_buffer->nr_pages_to_update > 0) + rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages, + cpu_buffer->nr_pages_to_update); + else + rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update); + cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; + /* reset this value */ + cpu_buffer->nr_pages_to_update = 0; +} + /** * ring_buffer_resize - resize the ring buffer * @buffer: the buffer to resize. @@ -1285,14 +1310,12 @@ out: * * Returns -1 on failure. */ -int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) +int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, + int cpu_id) { struct ring_buffer_per_cpu *cpu_buffer; - unsigned nr_pages, rm_pages, new_pages; - struct buffer_page *bpage, *tmp; - unsigned long buffer_size; - LIST_HEAD(pages); - int i, cpu; + unsigned nr_pages; + int cpu; /* * Always succeed at resizing a non-existent buffer: @@ -1302,15 +1325,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long 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. */ @@ -1321,68 +1340,56 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) 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; - + if (cpu_id == RING_BUFFER_ALL_CPUS) { + /* calculate the pages to update */ 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; + cpu_buffer->nr_pages_to_update = nr_pages - + cpu_buffer->nr_pages; - new_pages = nr_pages - buffer->pages; + /* + * nothing more to do for removing pages or no update + */ + if (cpu_buffer->nr_pages_to_update <= 0) + continue; - for_each_buffer_cpu(buffer, cpu) { - for (i = 0; i < new_pages; i++) { - struct page *page; /* - * __GFP_NORETRY flag makes sure that the allocation - * fails gracefully without invoking oom-killer and - * the system is not destabilized. + * to add pages, make sure all new pages can be + * allocated without receiving ENOMEM */ - bpage = kzalloc_node(ALIGN(sizeof(*bpage), - cache_line_size()), - GFP_KERNEL | __GFP_NORETRY, - cpu_to_node(cpu)); - if (!bpage) - goto free_pages; - list_add(&bpage->list, &pages); - page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) - goto free_pages; - bpage->page = page_address(page); - rb_init_page(bpage->page); + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages, cpu)) + /* not enough memory for new pages */ + goto no_mem; } - } - for_each_buffer_cpu(buffer, cpu) { - cpu_buffer = buffer->buffers[cpu]; - rb_insert_pages(cpu_buffer, &pages, new_pages); - } + /* wait for all the updates to complete */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (cpu_buffer->nr_pages_to_update) { + update_pages_handler(cpu_buffer); + } + } + } else { + cpu_buffer = buffer->buffers[cpu_id]; + if (nr_pages == cpu_buffer->nr_pages) + goto out; - if (RB_WARN_ON(buffer, !list_empty(&pages))) - goto out_fail; + cpu_buffer->nr_pages_to_update = nr_pages - + cpu_buffer->nr_pages; + + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (cpu_buffer->nr_pages_to_update > 0 && + __rb_allocate_pages(cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages, cpu_id)) + goto no_mem; + + update_pages_handler(cpu_buffer); + } out: - buffer->pages = nr_pages; put_online_cpus(); mutex_unlock(&buffer->mutex); @@ -1390,25 +1397,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) return size; - free_pages: - list_for_each_entry_safe(bpage, tmp, &pages, list) { - list_del_init(&bpage->list); - free_buffer_page(bpage); + no_mem: + for_each_buffer_cpu(buffer, cpu) { + struct buffer_page *bpage, *tmp; + cpu_buffer = buffer->buffers[cpu]; + /* reset this number regardless */ + cpu_buffer->nr_pages_to_update = 0; + if (list_empty(&cpu_buffer->new_pages)) + continue; + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_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); @@ -1510,7 +1516,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) * assign the commit to the tail. */ again: - max_count = cpu_buffer->buffer->pages * 100; + max_count = cpu_buffer->nr_pages * 100; while (cpu_buffer->commit_page != cpu_buffer->tail_page) { if (RB_WARN_ON(cpu_buffer, !(--max_count))) @@ -3588,9 +3594,18 @@ 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) +unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu) { - return BUF_PAGE_SIZE * buffer->pages; + /* + * Earlier, this method returned + * BUF_PAGE_SIZE * buffer->nr_pages + * Since the nr_pages field is now removed, we have converted this to + * return the per cpu buffer value. + */ + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages; } EXPORT_SYMBOL_GPL(ring_buffer_size); @@ -3765,8 +3780,11 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, !cpumask_test_cpu(cpu, buffer_b->cpumask)) goto out; + cpu_buffer_a = buffer_a->buffers[cpu]; + cpu_buffer_b = buffer_b->buffers[cpu]; + /* At least make sure the two buffers are somewhat the same */ - if (buffer_a->pages != buffer_b->pages) + if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; ret = -EAGAIN; @@ -3780,9 +3798,6 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, 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; @@ -4071,6 +4086,8 @@ static int rb_cpu_notify(struct notifier_block *self, struct ring_buffer *buffer = container_of(self, struct ring_buffer, cpu_notify); long cpu = (long)hcpu; + int cpu_i, nr_pages_same; + unsigned int nr_pages; switch (action) { case CPU_UP_PREPARE: @@ -4078,8 +4095,23 @@ static int rb_cpu_notify(struct notifier_block *self, if (cpumask_test_cpu(cpu, buffer->cpumask)) return NOTIFY_OK; + nr_pages = 0; + nr_pages_same = 1; + /* check if all cpu sizes are same */ + for_each_buffer_cpu(buffer, cpu_i) { + /* fill in the size from first enabled cpu */ + if (nr_pages == 0) + nr_pages = buffer->buffers[cpu_i]->nr_pages; + if (nr_pages != buffer->buffers[cpu_i]->nr_pages) { + nr_pages_same = 0; + break; + } + } + /* allocate minimum pages, user can later expand it */ + if (!nr_pages_same) + nr_pages = 2; buffer->buffers[cpu] = - rb_allocate_cpu_buffer(buffer, cpu); + rb_allocate_cpu_buffer(buffer, nr_pages, cpu); if (!buffer->buffers[cpu]) { WARN(1, "failed to allocate ring buffer on CPU %ld\n", cpu); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bbcde546f9f7..f11a285ee5bb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -838,7 +838,8 @@ __acquires(kernel_lock) /* If we expanded the buffers, make sure the max is expanded too */ if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, trace_buf_size); + ring_buffer_resize(max_tr.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); @@ -854,7 +855,8 @@ __acquires(kernel_lock) /* Shrink the max buffer again */ if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, 1); + ring_buffer_resize(max_tr.buffer, 1, + RING_BUFFER_ALL_CPUS); printk(KERN_CONT "PASSED\n"); } @@ -3053,7 +3055,14 @@ int tracer_init(struct tracer *t, struct trace_array *tr) return t->init(tr); } -static int __tracing_resize_ring_buffer(unsigned long size) +static void set_buffer_entries(struct trace_array *tr, unsigned long val) +{ + int cpu; + for_each_tracing_cpu(cpu) + tr->data[cpu]->entries = val; +} + +static int __tracing_resize_ring_buffer(unsigned long size, int cpu) { int ret; @@ -3064,19 +3073,32 @@ static int __tracing_resize_ring_buffer(unsigned long size) */ ring_buffer_expanded = 1; - ret = ring_buffer_resize(global_trace.buffer, size); + ret = ring_buffer_resize(global_trace.buffer, size, cpu); if (ret < 0) return ret; if (!current_trace->use_max_tr) goto out; - ret = ring_buffer_resize(max_tr.buffer, size); + ret = ring_buffer_resize(max_tr.buffer, size, cpu); if (ret < 0) { - int r; + int r = 0; + + if (cpu == RING_BUFFER_ALL_CPUS) { + int i; + for_each_tracing_cpu(i) { + r = ring_buffer_resize(global_trace.buffer, + global_trace.data[i]->entries, + i); + if (r < 0) + break; + } + } else { + r = ring_buffer_resize(global_trace.buffer, + global_trace.data[cpu]->entries, + cpu); + } - r = ring_buffer_resize(global_trace.buffer, - global_trace.entries); if (r < 0) { /* * AARGH! We are left with different @@ -3098,14 +3120,21 @@ static int __tracing_resize_ring_buffer(unsigned long size) return ret; } - max_tr.entries = size; + if (cpu == RING_BUFFER_ALL_CPUS) + set_buffer_entries(&max_tr, size); + else + max_tr.data[cpu]->entries = size; + out: - global_trace.entries = size; + if (cpu == RING_BUFFER_ALL_CPUS) + set_buffer_entries(&global_trace, size); + else + global_trace.data[cpu]->entries = size; return ret; } -static ssize_t tracing_resize_ring_buffer(unsigned long size) +static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) { int cpu, ret = size; @@ -3121,12 +3150,19 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size) atomic_inc(&max_tr.data[cpu]->disabled); } - if (size != global_trace.entries) - ret = __tracing_resize_ring_buffer(size); + if (cpu_id != RING_BUFFER_ALL_CPUS) { + /* make sure, this cpu is enabled in the mask */ + if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { + ret = -EINVAL; + goto out; + } + } + ret = __tracing_resize_ring_buffer(size, cpu_id); if (ret < 0) ret = -ENOMEM; +out: for_each_tracing_cpu(cpu) { if (global_trace.data[cpu]) atomic_dec(&global_trace.data[cpu]->disabled); @@ -3157,7 +3193,8 @@ int tracing_update_buffers(void) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) - ret = __tracing_resize_ring_buffer(trace_buf_size); + ret = __tracing_resize_ring_buffer(trace_buf_size, + RING_BUFFER_ALL_CPUS); mutex_unlock(&trace_types_lock); return ret; @@ -3181,7 +3218,8 @@ static int tracing_set_tracer(const char *buf) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) { - ret = __tracing_resize_ring_buffer(trace_buf_size); + ret = __tracing_resize_ring_buffer(trace_buf_size, + RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; ret = 0; @@ -3207,8 +3245,8 @@ static int tracing_set_tracer(const char *buf) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ - ring_buffer_resize(max_tr.buffer, 1); - max_tr.entries = 1; + ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&max_tr, 1); } destroy_trace_option_files(topts); @@ -3216,10 +3254,17 @@ static int tracing_set_tracer(const char *buf) topts = create_trace_option_files(current_trace); if (current_trace->use_max_tr) { - ret = ring_buffer_resize(max_tr.buffer, global_trace.entries); - if (ret < 0) - goto out; - max_tr.entries = global_trace.entries; + int cpu; + /* we need to make per cpu buffer sizes equivalent */ + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(max_tr.buffer, + global_trace.data[cpu]->entries, + cpu); + if (ret < 0) + goto out; + max_tr.data[cpu]->entries = + global_trace.data[cpu]->entries; + } } if (t->init) { @@ -3721,30 +3766,82 @@ out_err: goto out; } +struct ftrace_entries_info { + struct trace_array *tr; + int cpu; +}; + +static int tracing_entries_open(struct inode *inode, struct file *filp) +{ + struct ftrace_entries_info *info; + + if (tracing_disabled) + return -ENODEV; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->tr = &global_trace; + info->cpu = (unsigned long)inode->i_private; + + filp->private_data = info; + + return 0; +} + 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; + struct ftrace_entries_info *info = filp->private_data; + struct trace_array *tr = info->tr; + char buf[64]; + int r = 0; + ssize_t ret; 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); + + if (info->cpu == RING_BUFFER_ALL_CPUS) { + int cpu, buf_size_same; + unsigned long size; + + size = 0; + buf_size_same = 1; + /* check if all cpu sizes are same */ + for_each_tracing_cpu(cpu) { + /* fill in the size from first enabled cpu */ + if (size == 0) + size = tr->data[cpu]->entries; + if (size != tr->data[cpu]->entries) { + buf_size_same = 0; + break; + } + } + + if (buf_size_same) { + if (!ring_buffer_expanded) + r = sprintf(buf, "%lu (expanded: %lu)\n", + size >> 10, + trace_buf_size >> 10); + else + r = sprintf(buf, "%lu\n", size >> 10); + } else + r = sprintf(buf, "X\n"); + } else + r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10); + mutex_unlock(&trace_types_lock); - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + return ret; } static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct ftrace_entries_info *info = filp->private_data; unsigned long val; int ret; @@ -3759,7 +3856,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, /* value is in KB */ val <<= 10; - ret = tracing_resize_ring_buffer(val); + ret = tracing_resize_ring_buffer(val, info->cpu); if (ret < 0) return ret; @@ -3768,6 +3865,16 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, return cnt; } +static int +tracing_entries_release(struct inode *inode, struct file *filp) +{ + struct ftrace_entries_info *info = filp->private_data; + + kfree(info); + + return 0; +} + static ssize_t tracing_total_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -3779,7 +3886,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += tr->entries >> 10; + size += tr->data[cpu]->entries >> 10; if (!ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } @@ -3813,7 +3920,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) if (trace_flags & TRACE_ITER_STOP_ON_FREE) tracing_off(); /* resize the ring buffer to 0 */ - tracing_resize_ring_buffer(0); + tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS); return 0; } @@ -4012,9 +4119,10 @@ static const struct file_operations tracing_pipe_fops = { }; static const struct file_operations tracing_entries_fops = { - .open = tracing_open_generic, + .open = tracing_entries_open, .read = tracing_entries_read, .write = tracing_entries_write, + .release = tracing_entries_release, .llseek = generic_file_llseek, }; @@ -4466,6 +4574,9 @@ static void tracing_init_debugfs_percpu(long cpu) trace_create_file("stats", 0444, d_cpu, (void *) cpu, &tracing_stats_fops); + + trace_create_file("buffer_size_kb", 0444, d_cpu, + (void *) cpu, &tracing_entries_fops); } #ifdef CONFIG_FTRACE_SELFTEST @@ -4795,7 +4906,7 @@ static __init int tracer_init_debugfs(void) (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops); trace_create_file("buffer_size_kb", 0644, d_tracer, - &global_trace, &tracing_entries_fops); + (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops); trace_create_file("buffer_total_size_kb", 0444, d_tracer, &global_trace, &tracing_total_entries_fops); @@ -5056,7 +5167,6 @@ __init static int tracer_alloc_buffers(void) WARN_ON(1); goto out_free_cpumask; } - global_trace.entries = ring_buffer_size(global_trace.buffer); if (global_trace.buffer_disabled) tracing_off(); @@ -5069,7 +5179,6 @@ __init static int tracer_alloc_buffers(void) ring_buffer_free(global_trace.buffer); goto out_free_cpumask; } - max_tr.entries = 1; #endif /* Allocate the first page for all buffers */ @@ -5078,6 +5187,11 @@ __init static int tracer_alloc_buffers(void) max_tr.data[i] = &per_cpu(max_tr_data, i); } + set_buffer_entries(&global_trace, ring_buf_size); +#ifdef CONFIG_TRACER_MAX_TRACE + set_buffer_entries(&max_tr, 1); +#endif + trace_init_cmdlines(); register_tracer(&nop_trace); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f9d85504f04b..1c8b7c6f7b3b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -131,6 +131,7 @@ struct trace_array_cpu { atomic_t disabled; void *buffer_page; /* ring buffer spare */ + unsigned long entries; unsigned long saved_latency; unsigned long critical_start; unsigned long critical_end; @@ -152,7 +153,6 @@ struct trace_array_cpu { */ struct trace_array { struct ring_buffer *buffer; - unsigned long entries; int cpu; int buffer_disabled; cycle_t time_start; -- cgit v1.3-8-gc7d7 From 3a6b76661da8e92124a813b43607f5bec1a618de Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 9 Apr 2012 14:41:33 +0530 Subject: tracing: Modify is_delete, is_return from int to bool is_delete and is_return can take utmost 2 values and are better of being a boolean than a int. There are no functional changes. Signed-off-by: Srikar Dronamraju Acked-by: Steven Rostedt Acked-by: Masami Hiramatsu Cc: Linus Torvalds Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Linux-mm Cc: Oleg Nesterov Cc: Andi Kleen Cc: Christoph Hellwig Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120409091133.8343.65289.sendpatchset@srdronam.in.ibm.com Signed-off-by: Ingo Molnar --- kernel/trace/trace_kprobe.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 580a05ec926b..4f935f83cd46 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -651,7 +651,7 @@ static struct trace_probe *alloc_trace_probe(const char *group, void *addr, const char *symbol, unsigned long offs, - int nargs, int is_return) + int nargs, bool is_return) { struct trace_probe *tp; int ret = -ENOMEM; @@ -944,7 +944,7 @@ static int split_symbol_offset(char *symbol, unsigned long *offset) #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) static int parse_probe_vars(char *arg, const struct fetch_type *t, - struct fetch_param *f, int is_return) + struct fetch_param *f, bool is_return) { int ret = 0; unsigned long param; @@ -977,7 +977,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, /* Recursive argument parser */ static int __parse_probe_arg(char *arg, const struct fetch_type *t, - struct fetch_param *f, int is_return) + struct fetch_param *f, bool is_return) { int ret = 0; unsigned long param; @@ -1089,7 +1089,7 @@ static int __parse_bitfield_probe_arg(const char *bf, /* String length checking wrapper */ static int parse_probe_arg(char *arg, struct trace_probe *tp, - struct probe_arg *parg, int is_return) + struct probe_arg *parg, bool is_return) { const char *t; int ret; @@ -1162,7 +1162,7 @@ static int create_trace_probe(int argc, char **argv) */ struct trace_probe *tp; int i, ret = 0; - int is_return = 0, is_delete = 0; + bool is_return = false, is_delete = false; char *symbol = NULL, *event = NULL, *group = NULL; char *arg; unsigned long offset = 0; @@ -1171,11 +1171,11 @@ static int create_trace_probe(int argc, char **argv) /* argc must be >= 1 */ if (argv[0][0] == 'p') - is_return = 0; + is_return = false; else if (argv[0][0] == 'r') - is_return = 1; + is_return = true; else if (argv[0][0] == '-') - is_delete = 1; + is_delete = true; else { pr_info("Probe definition must be started with 'p', 'r' or" " '-'.\n"); -- cgit v1.3-8-gc7d7 From 8ab83f56475ec9151645a888dfe1941f4a92091d Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 9 Apr 2012 14:41:44 +0530 Subject: tracing: Extract out common code for kprobes/uprobes trace events Move parts of trace_kprobe.c that can be shared with upcoming trace_uprobe.c. Common code to kernel/trace/trace_probe.h and kernel/trace/trace_probe.c. There are no functional changes. Signed-off-by: Srikar Dronamraju Acked-by: Steven Rostedt Acked-by: Masami Hiramatsu Cc: Linus Torvalds Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Linux-mm Cc: Oleg Nesterov Cc: Andi Kleen Cc: Christoph Hellwig Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120409091144.8343.76218.sendpatchset@srdronam.in.ibm.com Signed-off-by: Ingo Molnar --- kernel/trace/Kconfig | 4 + kernel/trace/Makefile | 1 + kernel/trace/trace_kprobe.c | 889 +------------------------------------------- kernel/trace/trace_probe.c | 833 +++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace_probe.h | 160 ++++++++ 5 files changed, 1016 insertions(+), 871 deletions(-) create mode 100644 kernel/trace/trace_probe.c create mode 100644 kernel/trace/trace_probe.h (limited to 'kernel/trace') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a1d2849f2473..ce5a5c54ac8f 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -373,6 +373,7 @@ config KPROBE_EVENT depends on HAVE_REGS_AND_STACK_ACCESS_API bool "Enable kprobes-based dynamic events" select TRACING + select PROBE_EVENTS default y help This allows the user to add tracing events (similar to tracepoints) @@ -385,6 +386,9 @@ config KPROBE_EVENT This option is also required by perf-probe subcommand of perf tools. If you want to use perf tools, this option is strongly recommended. +config PROBE_EVENTS + def_bool n + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" depends on FUNCTION_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 5f39a07fe5ea..fa10d5ca5ab1 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -61,5 +61,6 @@ endif ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif +obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o libftrace-y := ftrace.o diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 4f935f83cd46..f8b777367d8e 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -19,547 +19,15 @@ #include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "trace.h" -#include "trace_output.h" - -#define MAX_TRACE_ARGS 128 -#define MAX_ARGSTR_LEN 63 -#define MAX_EVENT_NAME_LEN 64 -#define MAX_STRING_SIZE PATH_MAX -#define KPROBE_EVENT_SYSTEM "kprobes" - -/* Reserved field names */ -#define FIELD_STRING_IP "__probe_ip" -#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", - FIELD_STRING_IP, - FIELD_STRING_RETIP, - FIELD_STRING_FUNC, -}; - -/* Printing function type */ -typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, - void *); -#define PRINT_TYPE_FUNC_NAME(type) print_type_##type -#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type - -/* Printing in basic type function template */ -#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \ -static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \ - const char *name, \ - void *data, void *ent)\ -{ \ - return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\ -} \ -static const char PRINT_TYPE_FMT_NAME(type)[] = fmt; - -DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int) -DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int) -DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long) -DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long) -DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int) -DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int) -DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long) -DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long) - -/* data_rloc: data relative location, compatible with u32 */ -#define make_data_rloc(len, roffs) \ - (((u32)(len) << 16) | ((u32)(roffs) & 0xffff)) -#define get_rloc_len(dl) ((u32)(dl) >> 16) -#define get_rloc_offs(dl) ((u32)(dl) & 0xffff) - -static inline void *get_rloc_data(u32 *dl) -{ - return (u8 *)dl + get_rloc_offs(*dl); -} - -/* For data_loc conversion */ -static inline void *get_loc_data(u32 *dl, void *ent) -{ - return (u8 *)ent + get_rloc_offs(*dl); -} - -/* - * Convert data_rloc to data_loc: - * data_rloc stores the offset from data_rloc itself, but data_loc - * stores the offset from event entry. - */ -#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs)) - -/* For defining macros, define string/string_size types */ -typedef u32 string; -typedef u32 string_size; - -/* Print type function for string type */ -static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, - const char *name, - void *data, void *ent) -{ - int len = *(u32 *)data >> 16; - - if (!len) - return trace_seq_printf(s, " %s=(fault)", name); - else - return trace_seq_printf(s, " %s=\"%s\"", name, - (const char *)get_loc_data(data, ent)); -} -static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; - -/* Data fetch function type */ -typedef void (*fetch_func_t)(struct pt_regs *, void *, void *); - -struct fetch_param { - fetch_func_t fn; - void *data; -}; - -static __kprobes void call_fetch(struct fetch_param *fprm, - struct pt_regs *regs, void *dest) -{ - return fprm->fn(regs, fprm->data, dest); -} - -#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type -/* - * Define macro for basic types - we don't need to define s* types, because - * we have to care only about bitwidth at recording time. - */ -#define DEFINE_BASIC_FETCH_FUNCS(method) \ -DEFINE_FETCH_##method(u8) \ -DEFINE_FETCH_##method(u16) \ -DEFINE_FETCH_##method(u32) \ -DEFINE_FETCH_##method(u64) - -#define CHECK_FETCH_FUNCS(method, fn) \ - (((FETCH_FUNC_NAME(method, u8) == fn) || \ - (FETCH_FUNC_NAME(method, u16) == fn) || \ - (FETCH_FUNC_NAME(method, u32) == fn) || \ - (FETCH_FUNC_NAME(method, u64) == fn) || \ - (FETCH_FUNC_NAME(method, string) == fn) || \ - (FETCH_FUNC_NAME(method, string_size) == fn)) \ - && (fn != NULL)) - -/* Data fetch function templates */ -#define DEFINE_FETCH_reg(type) \ -static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \ - void *offset, void *dest) \ -{ \ - *(type *)dest = (type)regs_get_register(regs, \ - (unsigned int)((unsigned long)offset)); \ -} -DEFINE_BASIC_FETCH_FUNCS(reg) -/* No string on the register */ -#define fetch_reg_string NULL -#define fetch_reg_string_size NULL - -#define DEFINE_FETCH_stack(type) \ -static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ - void *offset, void *dest) \ -{ \ - *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \ - (unsigned int)((unsigned long)offset)); \ -} -DEFINE_BASIC_FETCH_FUNCS(stack) -/* No string on the stack entry */ -#define fetch_stack_string NULL -#define fetch_stack_string_size NULL - -#define DEFINE_FETCH_retval(type) \ -static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\ - void *dummy, void *dest) \ -{ \ - *(type *)dest = (type)regs_return_value(regs); \ -} -DEFINE_BASIC_FETCH_FUNCS(retval) -/* No string on the retval */ -#define fetch_retval_string NULL -#define fetch_retval_string_size NULL - -#define DEFINE_FETCH_memory(type) \ -static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ - void *addr, void *dest) \ -{ \ - type retval; \ - if (probe_kernel_address(addr, retval)) \ - *(type *)dest = 0; \ - else \ - *(type *)dest = retval; \ -} -DEFINE_BASIC_FETCH_FUNCS(memory) -/* - * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max - * length and relative data location. - */ -static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, - void *addr, void *dest) -{ - long ret; - int maxlen = get_rloc_len(*(u32 *)dest); - u8 *dst = get_rloc_data(dest); - u8 *src = addr; - mm_segment_t old_fs = get_fs(); - if (!maxlen) - return; - /* - * Try to get string again, since the string can be changed while - * probing. - */ - set_fs(KERNEL_DS); - pagefault_disable(); - do - ret = __copy_from_user_inatomic(dst++, src++, 1); - while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen); - dst[-1] = '\0'; - pagefault_enable(); - set_fs(old_fs); - - if (ret < 0) { /* Failed to fetch string */ - ((u8 *)get_rloc_data(dest))[0] = '\0'; - *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest)); - } else - *(u32 *)dest = make_data_rloc(src - (u8 *)addr, - get_rloc_offs(*(u32 *)dest)); -} -/* Return the length of string -- including null terminal byte */ -static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, - void *addr, void *dest) -{ - int ret, len = 0; - u8 c; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - pagefault_disable(); - do { - ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); - len++; - } while (c && ret == 0 && len < MAX_STRING_SIZE); - pagefault_enable(); - set_fs(old_fs); - - if (ret < 0) /* Failed to check the length */ - *(u32 *)dest = 0; - else - *(u32 *)dest = len; -} - -/* 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; -} - -#define DEFINE_FETCH_symbol(type) \ -static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\ - void *data, void *dest) \ -{ \ - struct symbol_cache *sc = data; \ - if (sc->addr) \ - fetch_memory_##type(regs, (void *)sc->addr, dest); \ - else \ - *(type *)dest = 0; \ -} -DEFINE_BASIC_FETCH_FUNCS(symbol) -DEFINE_FETCH_symbol(string) -DEFINE_FETCH_symbol(string_size) - -/* Dereference memory access function */ -struct deref_fetch_param { - struct fetch_param orig; - long offset; -}; - -#define DEFINE_FETCH_deref(type) \ -static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\ - void *data, void *dest) \ -{ \ - struct deref_fetch_param *dprm = data; \ - unsigned long addr; \ - call_fetch(&dprm->orig, regs, &addr); \ - if (addr) { \ - addr += dprm->offset; \ - fetch_memory_##type(regs, (void *)addr, dest); \ - } else \ - *(type *)dest = 0; \ -} -DEFINE_BASIC_FETCH_FUNCS(deref) -DEFINE_FETCH_deref(string) -DEFINE_FETCH_deref(string_size) - -static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data) -{ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - update_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - update_symbol_cache(data->orig.data); -} - -static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) -{ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - free_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - free_symbol_cache(data->orig.data); - kfree(data); -} - -/* Bitfield fetch function */ -struct bitfield_fetch_param { - struct fetch_param orig; - unsigned char hi_shift; - unsigned char low_shift; -}; +#include "trace_probe.h" -#define DEFINE_FETCH_bitfield(type) \ -static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\ - void *data, void *dest) \ -{ \ - struct bitfield_fetch_param *bprm = data; \ - type buf = 0; \ - call_fetch(&bprm->orig, regs, &buf); \ - if (buf) { \ - buf <<= bprm->hi_shift; \ - buf >>= bprm->low_shift; \ - } \ - *(type *)dest = buf; \ -} -DEFINE_BASIC_FETCH_FUNCS(bitfield) -#define fetch_bitfield_string NULL -#define fetch_bitfield_string_size NULL - -static __kprobes void -update_bitfield_fetch_param(struct bitfield_fetch_param *data) -{ - /* - * Don't check the bitfield itself, because this must be the - * last fetch function. - */ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - update_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - update_symbol_cache(data->orig.data); -} - -static __kprobes void -free_bitfield_fetch_param(struct bitfield_fetch_param *data) -{ - /* - * Don't check the bitfield itself, because this must be the - * last fetch function. - */ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - free_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - free_symbol_cache(data->orig.data); - kfree(data); -} - -/* Default (unsigned long) fetch type */ -#define __DEFAULT_FETCH_TYPE(t) u##t -#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t) -#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG) -#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE) - -/* Fetch types */ -enum { - FETCH_MTD_reg = 0, - FETCH_MTD_stack, - FETCH_MTD_retval, - FETCH_MTD_memory, - FETCH_MTD_symbol, - FETCH_MTD_deref, - FETCH_MTD_bitfield, - FETCH_MTD_END, -}; - -#define ASSIGN_FETCH_FUNC(method, type) \ - [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type) - -#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \ - {.name = _name, \ - .size = _size, \ - .is_signed = sign, \ - .print = PRINT_TYPE_FUNC_NAME(ptype), \ - .fmt = PRINT_TYPE_FMT_NAME(ptype), \ - .fmttype = _fmttype, \ - .fetch = { \ -ASSIGN_FETCH_FUNC(reg, ftype), \ -ASSIGN_FETCH_FUNC(stack, ftype), \ -ASSIGN_FETCH_FUNC(retval, ftype), \ -ASSIGN_FETCH_FUNC(memory, ftype), \ -ASSIGN_FETCH_FUNC(symbol, ftype), \ -ASSIGN_FETCH_FUNC(deref, ftype), \ -ASSIGN_FETCH_FUNC(bitfield, ftype), \ - } \ - } - -#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ - __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype) - -#define FETCH_TYPE_STRING 0 -#define FETCH_TYPE_STRSIZE 1 - -/* Fetch type information table */ -static const struct fetch_type { - const char *name; /* Name of type */ - size_t size; /* Byte size of type */ - int is_signed; /* Signed flag */ - print_type_func_t print; /* Print functions */ - const char *fmt; /* Fromat string */ - const char *fmttype; /* Name in format file */ - /* Fetch functions */ - fetch_func_t fetch[FETCH_MTD_END]; -} fetch_type_table[] = { - /* Special types */ - [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, - sizeof(u32), 1, "__data_loc char[]"), - [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, - string_size, sizeof(u32), 0, "u32"), - /* Basic types */ - ASSIGN_FETCH_TYPE(u8, u8, 0), - ASSIGN_FETCH_TYPE(u16, u16, 0), - ASSIGN_FETCH_TYPE(u32, u32, 0), - ASSIGN_FETCH_TYPE(u64, u64, 0), - ASSIGN_FETCH_TYPE(s8, u8, 1), - ASSIGN_FETCH_TYPE(s16, u16, 1), - ASSIGN_FETCH_TYPE(s32, u32, 1), - ASSIGN_FETCH_TYPE(s64, u64, 1), -}; - -static const struct fetch_type *find_fetch_type(const char *type) -{ - int i; - - if (!type) - type = DEFAULT_FETCH_TYPE_STR; - - /* Special case: bitfield */ - if (*type == 'b') { - unsigned long bs; - type = strchr(type, '/'); - if (!type) - goto fail; - type++; - if (strict_strtoul(type, 0, &bs)) - goto fail; - switch (bs) { - case 8: - return find_fetch_type("u8"); - case 16: - return find_fetch_type("u16"); - case 32: - return find_fetch_type("u32"); - case 64: - return find_fetch_type("u64"); - default: - goto fail; - } - } - - for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++) - if (strcmp(type, fetch_type_table[i].name) == 0) - return &fetch_type_table[i]; -fail: - return NULL; -} - -/* Special function : only accept unsigned long */ -static __kprobes void fetch_stack_address(struct pt_regs *regs, - void *dummy, void *dest) -{ - *(unsigned long *)dest = kernel_stack_pointer(regs); -} - -static fetch_func_t get_fetch_size_function(const struct fetch_type *type, - fetch_func_t orig_fn) -{ - int i; - - if (type != &fetch_type_table[FETCH_TYPE_STRING]) - return NULL; /* Only string type needs size function */ - for (i = 0; i < FETCH_MTD_END; i++) - if (type->fetch[i] == orig_fn) - return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i]; - - WARN_ON(1); /* This should not happen */ - return NULL; -} +#define KPROBE_EVENT_SYSTEM "kprobes" /** * Kprobe event core functions */ -struct probe_arg { - struct fetch_param fetch; - struct fetch_param fetch_size; - unsigned int offset; /* Offset from argument entry */ - const char *name; /* Name of this argument */ - const char *comm; /* Command of this argument */ - const struct fetch_type *type; /* Type of this argument */ -}; - -/* Flags for trace_probe */ -#define TP_FLAG_TRACE 1 -#define TP_FLAG_PROFILE 2 -#define TP_FLAG_REGISTERED 4 - struct trace_probe { struct list_head list; struct kretprobe rp; /* Use rp.kp for kprobe use */ @@ -631,18 +99,6 @@ 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/fields */ -static int is_good_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). */ @@ -702,34 +158,12 @@ error: return ERR_PTR(ret); } -static void update_probe_arg(struct probe_arg *arg) -{ - if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) - update_bitfield_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) - update_deref_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) - update_symbol_cache(arg->fetch.data); -} - -static void free_probe_arg(struct probe_arg *arg) -{ - if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) - free_bitfield_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) - free_deref_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) - free_symbol_cache(arg->fetch.data); - kfree(arg->name); - kfree(arg->comm); -} - 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]); + traceprobe_free_probe_arg(&tp->args[i]); kfree(tp->call.class->system); kfree(tp->call.name); @@ -787,7 +221,7 @@ static int __register_trace_probe(struct trace_probe *tp) return -EINVAL; for (i = 0; i < tp->nr_args; i++) - update_probe_arg(&tp->args[i]); + traceprobe_update_arg(&tp->args[i]); /* Set/clear disabled flag according to tp->flag */ if (trace_probe_is_enabled(tp)) @@ -919,227 +353,6 @@ static struct notifier_block trace_probe_module_nb = { .priority = 1 /* Invoked after kprobe module callback */ }; -/* 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, const struct fetch_type *t, - struct fetch_param *f, bool is_return) -{ - int ret = 0; - unsigned long param; - - if (strcmp(arg, "retval") == 0) { - if (is_return) - f->fn = t->fetch[FETCH_MTD_retval]; - else - ret = -EINVAL; - } else if (strncmp(arg, "stack", 5) == 0) { - if (arg[5] == '\0') { - if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0) - f->fn = fetch_stack_address; - else - ret = -EINVAL; - } else if (isdigit(arg[5])) { - ret = strict_strtoul(arg + 5, 10, ¶m); - if (ret || param > PARAM_MAX_STACK) - ret = -EINVAL; - else { - f->fn = t->fetch[FETCH_MTD_stack]; - f->data = (void *)param; - } - } else - ret = -EINVAL; - } else - ret = -EINVAL; - return ret; -} - -/* Recursive argument parser */ -static int __parse_probe_arg(char *arg, const struct fetch_type *t, - struct fetch_param *f, bool is_return) -{ - int ret = 0; - unsigned long param; - long offset; - char *tmp; - - switch (arg[0]) { - case '$': - ret = parse_probe_vars(arg + 1, t, f, is_return); - break; - case '%': /* named register */ - ret = regs_query_register_offset(arg + 1); - if (ret >= 0) { - f->fn = t->fetch[FETCH_MTD_reg]; - f->data = (void *)(unsigned long)ret; - ret = 0; - } - break; - case '@': /* memory or symbol */ - if (isdigit(arg[1])) { - ret = strict_strtoul(arg + 1, 0, ¶m); - if (ret) - break; - f->fn = t->fetch[FETCH_MTD_memory]; - f->data = (void *)param; - } else { - ret = split_symbol_offset(arg + 1, &offset); - if (ret) - break; - f->data = alloc_symbol_cache(arg + 1, offset); - if (f->data) - f->fn = t->fetch[FETCH_MTD_symbol]; - } - break; - case '+': /* deref memory */ - arg++; /* Skip '+', because strict_strtol() rejects it. */ - case '-': - tmp = strchr(arg, '('); - if (!tmp) - break; - *tmp = '\0'; - ret = strict_strtol(arg, 0, &offset); - if (ret) - break; - arg = tmp + 1; - tmp = strrchr(arg, ')'); - if (tmp) { - struct deref_fetch_param *dprm; - const struct fetch_type *t2 = find_fetch_type(NULL); - *tmp = '\0'; - dprm = kzalloc(sizeof(struct deref_fetch_param), - GFP_KERNEL); - if (!dprm) - return -ENOMEM; - dprm->offset = offset; - ret = __parse_probe_arg(arg, t2, &dprm->orig, - is_return); - if (ret) - kfree(dprm); - else { - f->fn = t->fetch[FETCH_MTD_deref]; - f->data = (void *)dprm; - } - } - break; - } - if (!ret && !f->fn) { /* Parsed, but do not find fetch method */ - pr_info("%s type has no corresponding fetch method.\n", - t->name); - ret = -EINVAL; - } - return ret; -} - -#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) - -/* Bitfield type needs to be parsed into a fetch function */ -static int __parse_bitfield_probe_arg(const char *bf, - const struct fetch_type *t, - struct fetch_param *f) -{ - struct bitfield_fetch_param *bprm; - unsigned long bw, bo; - char *tail; - - if (*bf != 'b') - return 0; - - bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); - if (!bprm) - return -ENOMEM; - bprm->orig = *f; - f->fn = t->fetch[FETCH_MTD_bitfield]; - f->data = (void *)bprm; - - bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */ - if (bw == 0 || *tail != '@') - return -EINVAL; - - bf = tail + 1; - bo = simple_strtoul(bf, &tail, 0); - if (tail == bf || *tail != '/') - return -EINVAL; - - bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo); - bprm->low_shift = bprm->hi_shift + bo; - return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0; -} - -/* String length checking wrapper */ -static int parse_probe_arg(char *arg, struct trace_probe *tp, - struct probe_arg *parg, bool is_return) -{ - const char *t; - int ret; - - if (strlen(arg) > MAX_ARGSTR_LEN) { - pr_info("Argument is too long.: %s\n", arg); - return -ENOSPC; - } - parg->comm = kstrdup(arg, GFP_KERNEL); - if (!parg->comm) { - pr_info("Failed to allocate memory for command '%s'.\n", arg); - return -ENOMEM; - } - t = strchr(parg->comm, ':'); - if (t) { - arg[t - parg->comm] = '\0'; - t++; - } - parg->type = find_fetch_type(t); - if (!parg->type) { - pr_info("Unsupported type: %s\n", t); - return -EINVAL; - } - parg->offset = tp->size; - tp->size += parg->type->size; - ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return); - if (ret >= 0 && t != NULL) - ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); - if (ret >= 0) { - parg->fetch_size.fn = get_fetch_size_function(parg->type, - parg->fetch.fn); - parg->fetch_size.data = parg->fetch.data; - } - return ret; -} - -/* 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) { /* @@ -1240,7 +453,7 @@ static int create_trace_probe(int argc, char **argv) /* a symbol specified */ symbol = argv[1]; /* TODO: support .init module functions */ - ret = split_symbol_offset(symbol, &offset); + ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret) { pr_info("Failed to parse symbol.\n"); return ret; @@ -1302,7 +515,8 @@ static int create_trace_probe(int argc, char **argv) goto error; } - if (conflict_field_name(tp->args[i].name, tp->args, i)) { + if (traceprobe_conflict_field_name(tp->args[i].name, + tp->args, i)) { pr_info("Argument[%d] name '%s' conflicts with " "another field.\n", i, argv[i]); ret = -EINVAL; @@ -1310,7 +524,8 @@ static int create_trace_probe(int argc, char **argv) } /* Parse fetch argument */ - ret = parse_probe_arg(arg, tp, &tp->args[i], is_return); + ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i], + is_return); if (ret) { pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; @@ -1412,70 +627,11 @@ static int probes_open(struct inode *inode, struct file *file) 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 4096 - 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; + return traceprobe_probes_write(file, buffer, count, ppos, + create_trace_probe); } static const struct file_operations kprobe_events_ops = { @@ -1711,16 +867,6 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -#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) { @@ -2051,8 +1197,9 @@ static __init int kprobe_trace_self_tests_init(void) pr_info("Testing kprobe tracing: "); - ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target " - "$stack $stack0 +0($stack)"); + ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target " + "$stack $stack0 +0($stack)", + create_trace_probe); if (WARN_ON_ONCE(ret)) { pr_warning("error on probing function entry.\n"); warn++; @@ -2066,8 +1213,8 @@ static __init int kprobe_trace_self_tests_init(void) enable_trace_probe(tp, TP_FLAG_TRACE); } - ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target " - "$retval"); + ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target " + "$retval", create_trace_probe); if (WARN_ON_ONCE(ret)) { pr_warning("error on probing function return.\n"); warn++; @@ -2101,13 +1248,13 @@ static __init int kprobe_trace_self_tests_init(void) } else disable_trace_probe(tp, TP_FLAG_TRACE); - ret = command_trace_probe("-:testprobe"); + ret = traceprobe_command("-:testprobe", create_trace_probe); if (WARN_ON_ONCE(ret)) { pr_warning("error on deleting a probe.\n"); warn++; } - ret = command_trace_probe("-:testprobe2"); + ret = traceprobe_command("-:testprobe2", create_trace_probe); if (WARN_ON_ONCE(ret)) { pr_warning("error on deleting a probe.\n"); warn++; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c new file mode 100644 index 000000000000..8e526b9286e9 --- /dev/null +++ b/kernel/trace/trace_probe.c @@ -0,0 +1,833 @@ +/* + * Common code for probe-based Dynamic events. + * + * 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 + * + * This code was copied from kernel/trace/trace_kprobe.c written by + * Masami Hiramatsu + * + * Updates to make this generic: + * Copyright (C) IBM Corporation, 2010-2011 + * Author: Srikar Dronamraju + */ + +#include "trace_probe.h" + +const char *reserved_field_names[] = { + "common_type", + "common_flags", + "common_preempt_count", + "common_pid", + "common_tgid", + FIELD_STRING_IP, + FIELD_STRING_RETIP, + FIELD_STRING_FUNC, +}; + +/* Printing function type */ +#define PRINT_TYPE_FUNC_NAME(type) print_type_##type +#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type + +/* Printing in basic type function template */ +#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \ +static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \ + const char *name, \ + void *data, void *ent)\ +{ \ + return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\ +} \ +static const char PRINT_TYPE_FMT_NAME(type)[] = fmt; + +DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int) +DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int) +DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long) +DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long) +DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int) +DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int) +DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long) +DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long) + +static inline void *get_rloc_data(u32 *dl) +{ + return (u8 *)dl + get_rloc_offs(*dl); +} + +/* For data_loc conversion */ +static inline void *get_loc_data(u32 *dl, void *ent) +{ + return (u8 *)ent + get_rloc_offs(*dl); +} + +/* For defining macros, define string/string_size types */ +typedef u32 string; +typedef u32 string_size; + +/* Print type function for string type */ +static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, + const char *name, + void *data, void *ent) +{ + int len = *(u32 *)data >> 16; + + if (!len) + return trace_seq_printf(s, " %s=(fault)", name); + else + return trace_seq_printf(s, " %s=\"%s\"", name, + (const char *)get_loc_data(data, ent)); +} + +static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; + +#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type +/* + * Define macro for basic types - we don't need to define s* types, because + * we have to care only about bitwidth at recording time. + */ +#define DEFINE_BASIC_FETCH_FUNCS(method) \ +DEFINE_FETCH_##method(u8) \ +DEFINE_FETCH_##method(u16) \ +DEFINE_FETCH_##method(u32) \ +DEFINE_FETCH_##method(u64) + +#define CHECK_FETCH_FUNCS(method, fn) \ + (((FETCH_FUNC_NAME(method, u8) == fn) || \ + (FETCH_FUNC_NAME(method, u16) == fn) || \ + (FETCH_FUNC_NAME(method, u32) == fn) || \ + (FETCH_FUNC_NAME(method, u64) == fn) || \ + (FETCH_FUNC_NAME(method, string) == fn) || \ + (FETCH_FUNC_NAME(method, string_size) == fn)) \ + && (fn != NULL)) + +/* Data fetch function templates */ +#define DEFINE_FETCH_reg(type) \ +static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)regs_get_register(regs, \ + (unsigned int)((unsigned long)offset)); \ +} +DEFINE_BASIC_FETCH_FUNCS(reg) +/* No string on the register */ +#define fetch_reg_string NULL +#define fetch_reg_string_size NULL + +#define DEFINE_FETCH_stack(type) \ +static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \ + (unsigned int)((unsigned long)offset)); \ +} +DEFINE_BASIC_FETCH_FUNCS(stack) +/* No string on the stack entry */ +#define fetch_stack_string NULL +#define fetch_stack_string_size NULL + +#define DEFINE_FETCH_retval(type) \ +static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\ + void *dummy, void *dest) \ +{ \ + *(type *)dest = (type)regs_return_value(regs); \ +} +DEFINE_BASIC_FETCH_FUNCS(retval) +/* No string on the retval */ +#define fetch_retval_string NULL +#define fetch_retval_string_size NULL + +#define DEFINE_FETCH_memory(type) \ +static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ + void *addr, void *dest) \ +{ \ + type retval; \ + if (probe_kernel_address(addr, retval)) \ + *(type *)dest = 0; \ + else \ + *(type *)dest = retval; \ +} +DEFINE_BASIC_FETCH_FUNCS(memory) +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max + * length and relative data location. + */ +static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) +{ + long ret; + int maxlen = get_rloc_len(*(u32 *)dest); + u8 *dst = get_rloc_data(dest); + u8 *src = addr; + mm_segment_t old_fs = get_fs(); + + if (!maxlen) + return; + + /* + * Try to get string again, since the string can be changed while + * probing. + */ + set_fs(KERNEL_DS); + pagefault_disable(); + + do + ret = __copy_from_user_inatomic(dst++, src++, 1); + while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen); + + dst[-1] = '\0'; + pagefault_enable(); + set_fs(old_fs); + + if (ret < 0) { /* Failed to fetch string */ + ((u8 *)get_rloc_data(dest))[0] = '\0'; + *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest)); + } else { + *(u32 *)dest = make_data_rloc(src - (u8 *)addr, + get_rloc_offs(*(u32 *)dest)); + } +} + +/* Return the length of string -- including null terminal byte */ +static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) +{ + mm_segment_t old_fs; + int ret, len = 0; + u8 c; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + pagefault_disable(); + + do { + ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); + len++; + } while (c && ret == 0 && len < MAX_STRING_SIZE); + + pagefault_enable(); + set_fs(old_fs); + + if (ret < 0) /* Failed to check the length */ + *(u32 *)dest = 0; + else + *(u32 *)dest = len; +} + +/* 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; +} + +#define DEFINE_FETCH_symbol(type) \ +static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\ + void *data, void *dest) \ +{ \ + struct symbol_cache *sc = data; \ + if (sc->addr) \ + fetch_memory_##type(regs, (void *)sc->addr, dest); \ + else \ + *(type *)dest = 0; \ +} +DEFINE_BASIC_FETCH_FUNCS(symbol) +DEFINE_FETCH_symbol(string) +DEFINE_FETCH_symbol(string_size) + +/* Dereference memory access function */ +struct deref_fetch_param { + struct fetch_param orig; + long offset; +}; + +#define DEFINE_FETCH_deref(type) \ +static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\ + void *data, void *dest) \ +{ \ + struct deref_fetch_param *dprm = data; \ + unsigned long addr; \ + call_fetch(&dprm->orig, regs, &addr); \ + if (addr) { \ + addr += dprm->offset; \ + fetch_memory_##type(regs, (void *)addr, dest); \ + } else \ + *(type *)dest = 0; \ +} +DEFINE_BASIC_FETCH_FUNCS(deref) +DEFINE_FETCH_deref(string) +DEFINE_FETCH_deref(string_size) + +static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data) +{ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + update_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + update_symbol_cache(data->orig.data); +} + +static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) +{ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + free_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + free_symbol_cache(data->orig.data); + kfree(data); +} + +/* Bitfield fetch function */ +struct bitfield_fetch_param { + struct fetch_param orig; + unsigned char hi_shift; + unsigned char low_shift; +}; + +#define DEFINE_FETCH_bitfield(type) \ +static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\ + void *data, void *dest) \ +{ \ + struct bitfield_fetch_param *bprm = data; \ + type buf = 0; \ + call_fetch(&bprm->orig, regs, &buf); \ + if (buf) { \ + buf <<= bprm->hi_shift; \ + buf >>= bprm->low_shift; \ + } \ + *(type *)dest = buf; \ +} + +DEFINE_BASIC_FETCH_FUNCS(bitfield) +#define fetch_bitfield_string NULL +#define fetch_bitfield_string_size NULL + +static __kprobes void +update_bitfield_fetch_param(struct bitfield_fetch_param *data) +{ + /* + * Don't check the bitfield itself, because this must be the + * last fetch function. + */ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + update_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + update_symbol_cache(data->orig.data); +} + +static __kprobes void +free_bitfield_fetch_param(struct bitfield_fetch_param *data) +{ + /* + * Don't check the bitfield itself, because this must be the + * last fetch function. + */ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + free_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + free_symbol_cache(data->orig.data); + + kfree(data); +} + +/* Default (unsigned long) fetch type */ +#define __DEFAULT_FETCH_TYPE(t) u##t +#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t) +#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG) +#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE) + +#define ASSIGN_FETCH_FUNC(method, type) \ + [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type) + +#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \ + {.name = _name, \ + .size = _size, \ + .is_signed = sign, \ + .print = PRINT_TYPE_FUNC_NAME(ptype), \ + .fmt = PRINT_TYPE_FMT_NAME(ptype), \ + .fmttype = _fmttype, \ + .fetch = { \ +ASSIGN_FETCH_FUNC(reg, ftype), \ +ASSIGN_FETCH_FUNC(stack, ftype), \ +ASSIGN_FETCH_FUNC(retval, ftype), \ +ASSIGN_FETCH_FUNC(memory, ftype), \ +ASSIGN_FETCH_FUNC(symbol, ftype), \ +ASSIGN_FETCH_FUNC(deref, ftype), \ +ASSIGN_FETCH_FUNC(bitfield, ftype), \ + } \ + } + +#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ + __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype) + +#define FETCH_TYPE_STRING 0 +#define FETCH_TYPE_STRSIZE 1 + +/* Fetch type information table */ +static const struct fetch_type fetch_type_table[] = { + /* Special types */ + [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, + sizeof(u32), 1, "__data_loc char[]"), + [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, + string_size, sizeof(u32), 0, "u32"), + /* Basic types */ + ASSIGN_FETCH_TYPE(u8, u8, 0), + ASSIGN_FETCH_TYPE(u16, u16, 0), + ASSIGN_FETCH_TYPE(u32, u32, 0), + ASSIGN_FETCH_TYPE(u64, u64, 0), + ASSIGN_FETCH_TYPE(s8, u8, 1), + ASSIGN_FETCH_TYPE(s16, u16, 1), + ASSIGN_FETCH_TYPE(s32, u32, 1), + ASSIGN_FETCH_TYPE(s64, u64, 1), +}; + +static const struct fetch_type *find_fetch_type(const char *type) +{ + int i; + + if (!type) + type = DEFAULT_FETCH_TYPE_STR; + + /* Special case: bitfield */ + if (*type == 'b') { + unsigned long bs; + + type = strchr(type, '/'); + if (!type) + goto fail; + + type++; + if (strict_strtoul(type, 0, &bs)) + goto fail; + + switch (bs) { + case 8: + return find_fetch_type("u8"); + case 16: + return find_fetch_type("u16"); + case 32: + return find_fetch_type("u32"); + case 64: + return find_fetch_type("u64"); + default: + goto fail; + } + } + + for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++) + if (strcmp(type, fetch_type_table[i].name) == 0) + return &fetch_type_table[i]; + +fail: + return NULL; +} + +/* Special function : only accept unsigned long */ +static __kprobes void fetch_stack_address(struct pt_regs *regs, + void *dummy, void *dest) +{ + *(unsigned long *)dest = kernel_stack_pointer(regs); +} + +static fetch_func_t get_fetch_size_function(const struct fetch_type *type, + fetch_func_t orig_fn) +{ + int i; + + if (type != &fetch_type_table[FETCH_TYPE_STRING]) + return NULL; /* Only string type needs size function */ + + for (i = 0; i < FETCH_MTD_END; i++) + if (type->fetch[i] == orig_fn) + return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i]; + + WARN_ON(1); /* This should not happen */ + + return NULL; +} + +/* Split symbol and offset. */ +int traceprobe_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_STACK (THREAD_SIZE / sizeof(unsigned long)) + +static int parse_probe_vars(char *arg, const struct fetch_type *t, + struct fetch_param *f, bool is_return) +{ + int ret = 0; + unsigned long param; + + if (strcmp(arg, "retval") == 0) { + if (is_return) + f->fn = t->fetch[FETCH_MTD_retval]; + else + ret = -EINVAL; + } else if (strncmp(arg, "stack", 5) == 0) { + if (arg[5] == '\0') { + if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0) + f->fn = fetch_stack_address; + else + ret = -EINVAL; + } else if (isdigit(arg[5])) { + ret = strict_strtoul(arg + 5, 10, ¶m); + if (ret || param > PARAM_MAX_STACK) + ret = -EINVAL; + else { + f->fn = t->fetch[FETCH_MTD_stack]; + f->data = (void *)param; + } + } else + ret = -EINVAL; + } else + ret = -EINVAL; + + return ret; +} + +/* Recursive argument parser */ +static int parse_probe_arg(char *arg, const struct fetch_type *t, + struct fetch_param *f, bool is_return) +{ + unsigned long param; + long offset; + char *tmp; + int ret; + + ret = 0; + switch (arg[0]) { + case '$': + ret = parse_probe_vars(arg + 1, t, f, is_return); + break; + + case '%': /* named register */ + ret = regs_query_register_offset(arg + 1); + if (ret >= 0) { + f->fn = t->fetch[FETCH_MTD_reg]; + f->data = (void *)(unsigned long)ret; + ret = 0; + } + break; + + case '@': /* memory or symbol */ + if (isdigit(arg[1])) { + ret = strict_strtoul(arg + 1, 0, ¶m); + if (ret) + break; + + f->fn = t->fetch[FETCH_MTD_memory]; + f->data = (void *)param; + } else { + ret = traceprobe_split_symbol_offset(arg + 1, &offset); + if (ret) + break; + + f->data = alloc_symbol_cache(arg + 1, offset); + if (f->data) + f->fn = t->fetch[FETCH_MTD_symbol]; + } + break; + + case '+': /* deref memory */ + arg++; /* Skip '+', because strict_strtol() rejects it. */ + case '-': + tmp = strchr(arg, '('); + if (!tmp) + break; + + *tmp = '\0'; + ret = strict_strtol(arg, 0, &offset); + + if (ret) + break; + + arg = tmp + 1; + tmp = strrchr(arg, ')'); + + if (tmp) { + struct deref_fetch_param *dprm; + const struct fetch_type *t2; + + t2 = find_fetch_type(NULL); + *tmp = '\0'; + dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL); + + if (!dprm) + return -ENOMEM; + + dprm->offset = offset; + ret = parse_probe_arg(arg, t2, &dprm->orig, is_return); + if (ret) + kfree(dprm); + else { + f->fn = t->fetch[FETCH_MTD_deref]; + f->data = (void *)dprm; + } + } + break; + } + if (!ret && !f->fn) { /* Parsed, but do not find fetch method */ + pr_info("%s type has no corresponding fetch method.\n", t->name); + ret = -EINVAL; + } + + return ret; +} + +#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) + +/* Bitfield type needs to be parsed into a fetch function */ +static int __parse_bitfield_probe_arg(const char *bf, + const struct fetch_type *t, + struct fetch_param *f) +{ + struct bitfield_fetch_param *bprm; + unsigned long bw, bo; + char *tail; + + if (*bf != 'b') + return 0; + + bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); + if (!bprm) + return -ENOMEM; + + bprm->orig = *f; + f->fn = t->fetch[FETCH_MTD_bitfield]; + f->data = (void *)bprm; + bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */ + + if (bw == 0 || *tail != '@') + return -EINVAL; + + bf = tail + 1; + bo = simple_strtoul(bf, &tail, 0); + + if (tail == bf || *tail != '/') + return -EINVAL; + + bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo); + bprm->low_shift = bprm->hi_shift + bo; + + return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0; +} + +/* String length checking wrapper */ +int traceprobe_parse_probe_arg(char *arg, ssize_t *size, + struct probe_arg *parg, bool is_return) +{ + const char *t; + int ret; + + if (strlen(arg) > MAX_ARGSTR_LEN) { + pr_info("Argument is too long.: %s\n", arg); + return -ENOSPC; + } + parg->comm = kstrdup(arg, GFP_KERNEL); + if (!parg->comm) { + pr_info("Failed to allocate memory for command '%s'.\n", arg); + return -ENOMEM; + } + t = strchr(parg->comm, ':'); + if (t) { + arg[t - parg->comm] = '\0'; + t++; + } + parg->type = find_fetch_type(t); + if (!parg->type) { + pr_info("Unsupported type: %s\n", t); + return -EINVAL; + } + parg->offset = *size; + *size += parg->type->size; + ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return); + + if (ret >= 0 && t != NULL) + ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); + + if (ret >= 0) { + parg->fetch_size.fn = get_fetch_size_function(parg->type, + parg->fetch.fn); + parg->fetch_size.data = parg->fetch.data; + } + + return ret; +} + +/* Return 1 if name is reserved or already used by another argument */ +int traceprobe_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; +} + +void traceprobe_update_arg(struct probe_arg *arg) +{ + if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) + update_bitfield_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) + update_deref_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) + update_symbol_cache(arg->fetch.data); +} + +void traceprobe_free_probe_arg(struct probe_arg *arg) +{ + if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) + free_bitfield_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) + free_deref_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) + free_symbol_cache(arg->fetch.data); + + kfree(arg->name); + kfree(arg->comm); +} + +int traceprobe_command(const char *buf, int (*createfn)(int, char **)) +{ + char **argv; + int argc, ret; + + argc = 0; + ret = 0; + argv = argv_split(GFP_KERNEL, buf, &argc); + if (!argv) + return -ENOMEM; + + if (argc) + ret = createfn(argc, argv); + + argv_free(argv); + + return ret; +} + +#define WRITE_BUFSIZE 4096 + +ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos, + int (*createfn)(int, char **)) +{ + char *kbuf, *tmp; + int ret = 0; + size_t done = 0; + size_t size; + + kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + 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 = traceprobe_command(kbuf, createfn); + if (ret) + goto out; + } + ret = done; + +out: + kfree(kbuf); + + return ret; +} diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h new file mode 100644 index 000000000000..2df9a18e0252 --- /dev/null +++ b/kernel/trace/trace_probe.h @@ -0,0 +1,160 @@ +/* + * Common header file for probe-based Dynamic events. + * + * 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 + * + * This code was copied from kernel/trace/trace_kprobe.h written by + * Masami Hiramatsu + * + * Updates to make this generic: + * Copyright (C) IBM Corporation, 2010-2011 + * Author: Srikar Dronamraju + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +#define MAX_TRACE_ARGS 128 +#define MAX_ARGSTR_LEN 63 +#define MAX_EVENT_NAME_LEN 64 +#define MAX_STRING_SIZE PATH_MAX + +/* Reserved field names */ +#define FIELD_STRING_IP "__probe_ip" +#define FIELD_STRING_RETIP "__probe_ret_ip" +#define FIELD_STRING_FUNC "__probe_func" + +#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) + + +/* Flags for trace_probe */ +#define TP_FLAG_TRACE 1 +#define TP_FLAG_PROFILE 2 +#define TP_FLAG_REGISTERED 4 + + +/* data_rloc: data relative location, compatible with u32 */ +#define make_data_rloc(len, roffs) \ + (((u32)(len) << 16) | ((u32)(roffs) & 0xffff)) +#define get_rloc_len(dl) ((u32)(dl) >> 16) +#define get_rloc_offs(dl) ((u32)(dl) & 0xffff) + +/* + * Convert data_rloc to data_loc: + * data_rloc stores the offset from data_rloc itself, but data_loc + * stores the offset from event entry. + */ +#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs)) + +/* Data fetch function type */ +typedef void (*fetch_func_t)(struct pt_regs *, void *, void *); +/* Printing function type */ +typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, void *); + +/* Fetch types */ +enum { + FETCH_MTD_reg = 0, + FETCH_MTD_stack, + FETCH_MTD_retval, + FETCH_MTD_memory, + FETCH_MTD_symbol, + FETCH_MTD_deref, + FETCH_MTD_bitfield, + FETCH_MTD_END, +}; + +/* Fetch type information table */ +struct fetch_type { + const char *name; /* Name of type */ + size_t size; /* Byte size of type */ + int is_signed; /* Signed flag */ + print_type_func_t print; /* Print functions */ + const char *fmt; /* Fromat string */ + const char *fmttype; /* Name in format file */ + /* Fetch functions */ + fetch_func_t fetch[FETCH_MTD_END]; +}; + +struct fetch_param { + fetch_func_t fn; + void *data; +}; + +struct probe_arg { + struct fetch_param fetch; + struct fetch_param fetch_size; + unsigned int offset; /* Offset from argument entry */ + const char *name; /* Name of this argument */ + const char *comm; /* Command of this argument */ + const struct fetch_type *type; /* Type of this argument */ +}; + +static inline __kprobes void call_fetch(struct fetch_param *fprm, + struct pt_regs *regs, void *dest) +{ + return fprm->fn(regs, fprm->data, dest); +} + +/* Check the name is good for event/group/fields */ +static inline int is_good_name(const char *name) +{ + if (!isalpha(*name) && *name != '_') + return 0; + while (*++name != '\0') { + if (!isalpha(*name) && !isdigit(*name) && *name != '_') + return 0; + } + return 1; +} + +extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, + struct probe_arg *parg, bool is_return); + +extern int traceprobe_conflict_field_name(const char *name, + struct probe_arg *args, int narg); + +extern void traceprobe_update_arg(struct probe_arg *arg); +extern void traceprobe_free_probe_arg(struct probe_arg *arg); + +extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset); + +extern ssize_t traceprobe_probes_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos, + int (*createfn)(int, char**)); + +extern int traceprobe_command(const char *buf, int (*createfn)(int, char**)); -- cgit v1.3-8-gc7d7 From f3f096cfedf8113380c56fc855275cc75cd8cf55 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Wed, 11 Apr 2012 16:00:43 +0530 Subject: tracing: Provide trace events interface for uprobes Implements trace_event support for uprobes. In its current form it can be used to put probes at a specified offset in a file and dump the required registers when the code flow reaches the probed address. The following example shows how to dump the instruction pointer and %ax a register at the probed text address. Here we are trying to probe zfree in /bin/zsh: # cd /sys/kernel/debug/tracing/ # cat /proc/`pgrep zsh`/maps | grep /bin/zsh | grep r-xp 00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh # objdump -T /bin/zsh | grep -w zfree 0000000000446420 g DF .text 0000000000000012 Base zfree # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events # cat uprobe_events p:uprobes/p_zsh_0x46420 /bin/zsh:0x0000000000046420 # echo 1 > events/uprobes/enable # sleep 20 # echo 0 > events/uprobes/enable # cat trace # tracer: nop # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 Signed-off-by: Srikar Dronamraju Acked-by: Steven Rostedt Acked-by: Masami Hiramatsu Cc: Linus Torvalds Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Linux-mm Cc: Oleg Nesterov Cc: Andi Kleen Cc: Christoph Hellwig Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120411103043.GB29437@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- Documentation/trace/uprobetracer.txt | 95 +++++ arch/Kconfig | 2 +- kernel/trace/Kconfig | 16 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 5 + kernel/trace/trace_kprobe.c | 2 +- kernel/trace/trace_probe.c | 14 +- kernel/trace/trace_probe.h | 3 +- kernel/trace/trace_uprobe.c | 788 +++++++++++++++++++++++++++++++++++ 9 files changed, 919 insertions(+), 7 deletions(-) create mode 100644 Documentation/trace/uprobetracer.txt create mode 100644 kernel/trace/trace_uprobe.c (limited to 'kernel/trace') diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt new file mode 100644 index 000000000000..eae40a003eec --- /dev/null +++ b/Documentation/trace/uprobetracer.txt @@ -0,0 +1,95 @@ + Uprobe-tracer: Uprobe-based Event Tracing + ========================================= + Documentation written by Srikar Dronamraju + +Overview +-------- +Uprobe based trace events are similar to kprobe based trace events. +To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y. + +Similar to the kprobe-event tracer, this doesn't need to be activated via +current_tracer. Instead of that, add probe points via +/sys/kernel/debug/tracing/uprobe_events, and enable it via +/sys/kernel/debug/tracing/events/uprobes//enabled. + +However unlike kprobe-event tracer, the uprobe event interface expects the +user to calculate the offset of the probepoint in the object + +Synopsis of uprobe_tracer +------------------------- + p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a probe + + GRP : Group name. If omitted, use "uprobes" for it. + EVENT : Event name. If omitted, the event name is generated + based on SYMBOL+offs. + PATH : path to an executable or a library. + SYMBOL[+offs] : Symbol+offset where the probe is inserted. + + FETCHARGS : Arguments. Each probe can have up to 128 args. + %REG : Fetch register REG + +Event Profiling +--------------- + You can check the total number of probe hits and probe miss-hits via +/sys/kernel/debug/tracing/uprobe_profile. + The first column is event name, the second is the number of probe hits, +the third is the number of probe miss-hits. + +Usage examples +-------------- +To add a probe as a new event, write a new definition to uprobe_events +as below. + + echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events + + This sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash + + echo > /sys/kernel/debug/tracing/uprobe_events + + This clears all probe points. + +The following example shows how to dump the instruction pointer and %ax +a register at the probed text address. Here we are trying to probe +function zfree in /bin/zsh + + # cd /sys/kernel/debug/tracing/ + # cat /proc/`pgrep zsh`/maps | grep /bin/zsh | grep r-xp + 00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh + # objdump -T /bin/zsh | grep -w zfree + 0000000000446420 g DF .text 0000000000000012 Base zfree + +0x46420 is the offset of zfree in object /bin/zsh that is loaded at +0x00400000. Hence the command to probe would be : + + # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events + +Please note: User has to explicitly calculate the offset of the probepoint +in the object. We can see the events that are registered by looking at the +uprobe_events file. + + # cat uprobe_events + p:uprobes/p_zsh_0x46420 /bin/zsh:0x0000000000046420 + +Right after definition, each event is disabled by default. For tracing these +events, you need to enable it by: + + # echo 1 > events/uprobes/enable + +Lets disable the event after sleeping for some time. + # sleep 20 + # echo 0 > events/uprobes/enable + +And you can see the traced information via /sys/kernel/debug/tracing/trace. + + # cat trace + # tracer: nop + # + # TASK-PID CPU# TIMESTAMP FUNCTION + # | | | | | + zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 + zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 + zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 + zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 + +Each line shows us probes were triggered for a pid 24842 with ip being +0x446421 and contents of ax register being 79. diff --git a/arch/Kconfig b/arch/Kconfig index e5d3778d5554..0f8f968015e2 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -78,7 +78,7 @@ config OPTPROBES config UPROBES bool "Transparent user-space probes (EXPERIMENTAL)" - depends on ARCH_SUPPORTS_UPROBES && PERF_EVENTS + depends on UPROBE_EVENTS && PERF_EVENTS default n help Uprobes is the user-space counterpart to kprobes: they diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index ce5a5c54ac8f..ea4bff6295fc 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -386,6 +386,22 @@ config KPROBE_EVENT This option is also required by perf-probe subcommand of perf tools. If you want to use perf tools, this option is strongly recommended. +config UPROBE_EVENT + bool "Enable uprobes-based dynamic events" + depends on ARCH_SUPPORTS_UPROBES + depends on MMU + select UPROBES + select PROBE_EVENTS + select TRACING + default n + help + This allows the user to add tracing events on top of userspace + dynamic events (similar to tracepoints) on the fly via the trace + events interface. Those events can be inserted wherever uprobes + can probe, and record various registers. + This option is required if you plan to use perf-probe subcommand + of perf tools on user space applications. + config PROBE_EVENTS def_bool n diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index fa10d5ca5ab1..1734c03e048b 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -62,5 +62,6 @@ ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o +obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o libftrace-y := ftrace.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 95059f091a24..1bcdbec95a11 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -103,6 +103,11 @@ struct kretprobe_trace_entry_head { unsigned long ret_ip; }; +struct uprobe_trace_entry_head { + struct trace_entry ent; + unsigned long ip; +}; + /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f8b777367d8e..b31d3d5699fe 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -525,7 +525,7 @@ static int create_trace_probe(int argc, char **argv) /* Parse fetch argument */ ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i], - is_return); + is_return, true); if (ret) { pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 8e526b9286e9..daa9980153af 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -550,7 +550,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, /* Recursive argument parser */ static int parse_probe_arg(char *arg, const struct fetch_type *t, - struct fetch_param *f, bool is_return) + struct fetch_param *f, bool is_return, bool is_kprobe) { unsigned long param; long offset; @@ -558,6 +558,11 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, int ret; ret = 0; + + /* Until uprobe_events supports only reg arguments */ + if (!is_kprobe && arg[0] != '%') + return -EINVAL; + switch (arg[0]) { case '$': ret = parse_probe_vars(arg + 1, t, f, is_return); @@ -619,7 +624,8 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, return -ENOMEM; dprm->offset = offset; - ret = parse_probe_arg(arg, t2, &dprm->orig, is_return); + ret = parse_probe_arg(arg, t2, &dprm->orig, is_return, + is_kprobe); if (ret) kfree(dprm); else { @@ -677,7 +683,7 @@ static int __parse_bitfield_probe_arg(const char *bf, /* String length checking wrapper */ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return) + struct probe_arg *parg, bool is_return, bool is_kprobe) { const char *t; int ret; @@ -703,7 +709,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, } parg->offset = *size; *size += parg->type->size; - ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return); + ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, is_kprobe); if (ret >= 0 && t != NULL) ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 2df9a18e0252..933708677814 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -66,6 +66,7 @@ #define TP_FLAG_TRACE 1 #define TP_FLAG_PROFILE 2 #define TP_FLAG_REGISTERED 4 +#define TP_FLAG_UPROBE 8 /* data_rloc: data relative location, compatible with u32 */ @@ -143,7 +144,7 @@ static inline int is_good_name(const char *name) } extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return); + struct probe_arg *parg, bool is_return, bool is_kprobe); extern int traceprobe_conflict_field_name(const char *name, struct probe_arg *args, int narg); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c new file mode 100644 index 000000000000..2b36ac68549e --- /dev/null +++ b/kernel/trace/trace_uprobe.c @@ -0,0 +1,788 @@ +/* + * uprobes-based tracing events + * + * 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 + * + * Copyright (C) IBM Corporation, 2010-2012 + * Author: Srikar Dronamraju + */ + +#include +#include +#include +#include + +#include "trace_probe.h" + +#define UPROBE_EVENT_SYSTEM "uprobes" + +/* + * uprobe event core functions + */ +struct trace_uprobe; +struct uprobe_trace_consumer { + struct uprobe_consumer cons; + struct trace_uprobe *tu; +}; + +struct trace_uprobe { + struct list_head list; + struct ftrace_event_class class; + struct ftrace_event_call call; + struct uprobe_trace_consumer *consumer; + struct inode *inode; + char *filename; + unsigned long offset; + unsigned long nhit; + unsigned int flags; /* For TP_FLAG_* */ + ssize_t size; /* trace entry size */ + unsigned int nr_args; + struct probe_arg args[]; +}; + +#define SIZEOF_TRACE_UPROBE(n) \ + (offsetof(struct trace_uprobe, args) + \ + (sizeof(struct probe_arg) * (n))) + +static int register_uprobe_event(struct trace_uprobe *tu); +static void unregister_uprobe_event(struct trace_uprobe *tu); + +static DEFINE_MUTEX(uprobe_lock); +static LIST_HEAD(uprobe_list); + +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); + +/* + * Allocate new trace_uprobe and initialize it (including uprobes). + */ +static struct trace_uprobe * +alloc_trace_uprobe(const char *group, const char *event, int nargs) +{ + struct trace_uprobe *tu; + + if (!event || !is_good_name(event)) + return ERR_PTR(-EINVAL); + + if (!group || !is_good_name(group)) + return ERR_PTR(-EINVAL); + + tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); + if (!tu) + return ERR_PTR(-ENOMEM); + + tu->call.class = &tu->class; + tu->call.name = kstrdup(event, GFP_KERNEL); + if (!tu->call.name) + goto error; + + tu->class.system = kstrdup(group, GFP_KERNEL); + if (!tu->class.system) + goto error; + + INIT_LIST_HEAD(&tu->list); + return tu; + +error: + kfree(tu->call.name); + kfree(tu); + + return ERR_PTR(-ENOMEM); +} + +static void free_trace_uprobe(struct trace_uprobe *tu) +{ + int i; + + for (i = 0; i < tu->nr_args; i++) + traceprobe_free_probe_arg(&tu->args[i]); + + iput(tu->inode); + kfree(tu->call.class->system); + kfree(tu->call.name); + kfree(tu->filename); + kfree(tu); +} + +static struct trace_uprobe *find_probe_event(const char *event, const char *group) +{ + struct trace_uprobe *tu; + + list_for_each_entry(tu, &uprobe_list, list) + if (strcmp(tu->call.name, event) == 0 && + strcmp(tu->call.class->system, group) == 0) + return tu; + + return NULL; +} + +/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ +static void unregister_trace_uprobe(struct trace_uprobe *tu) +{ + list_del(&tu->list); + unregister_uprobe_event(tu); + free_trace_uprobe(tu); +} + +/* Register a trace_uprobe and probe_event */ +static int register_trace_uprobe(struct trace_uprobe *tu) +{ + struct trace_uprobe *old_tp; + int ret; + + mutex_lock(&uprobe_lock); + + /* register as an event */ + old_tp = find_probe_event(tu->call.name, tu->call.class->system); + if (old_tp) + /* delete old event */ + unregister_trace_uprobe(old_tp); + + ret = register_uprobe_event(tu); + if (ret) { + pr_warning("Failed to register probe event(%d)\n", ret); + goto end; + } + + list_add_tail(&tu->list, &uprobe_list); + +end: + mutex_unlock(&uprobe_lock); + + return ret; +} + +/* + * Argument syntax: + * - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] + * + * - Remove uprobe: -:[GRP/]EVENT + */ +static int create_trace_uprobe(int argc, char **argv) +{ + struct trace_uprobe *tu; + struct inode *inode; + char *arg, *event, *group, *filename; + char buf[MAX_EVENT_NAME_LEN]; + struct path path; + unsigned long offset; + bool is_delete; + int i, ret; + + inode = NULL; + ret = 0; + is_delete = false; + event = NULL; + group = NULL; + + /* argc must be >= 1 */ + if (argv[0][0] == '-') + is_delete = true; + else if (argv[0][0] != 'p') { + pr_info("Probe definition must be started with 'p', 'r' or" " '-'.\n"); + return -EINVAL; + } + + if (argv[0][1] == ':') { + event = &argv[0][2]; + arg = strchr(event, '/'); + + if (arg) { + group = event; + event = arg + 1; + event[-1] = '\0'; + + if (strlen(group) == 0) { + pr_info("Group name is not specified\n"); + return -EINVAL; + } + } + if (strlen(event) == 0) { + pr_info("Event name is not specified\n"); + return -EINVAL; + } + } + if (!group) + group = UPROBE_EVENT_SYSTEM; + + if (is_delete) { + if (!event) { + pr_info("Delete command needs an event name.\n"); + return -EINVAL; + } + mutex_lock(&uprobe_lock); + tu = find_probe_event(event, group); + + if (!tu) { + mutex_unlock(&uprobe_lock); + pr_info("Event %s/%s doesn't exist.\n", group, event); + return -ENOENT; + } + /* delete an event */ + unregister_trace_uprobe(tu); + mutex_unlock(&uprobe_lock); + return 0; + } + + if (argc < 2) { + pr_info("Probe point is not specified.\n"); + return -EINVAL; + } + if (isdigit(argv[1][0])) { + pr_info("probe point must be have a filename.\n"); + return -EINVAL; + } + arg = strchr(argv[1], ':'); + if (!arg) + goto fail_address_parse; + + *arg++ = '\0'; + filename = argv[1]; + ret = kern_path(filename, LOOKUP_FOLLOW, &path); + if (ret) + goto fail_address_parse; + + ret = strict_strtoul(arg, 0, &offset); + if (ret) + goto fail_address_parse; + + inode = igrab(path.dentry->d_inode); + + argc -= 2; + argv += 2; + + /* setup a probe */ + if (!event) { + char *tail = strrchr(filename, '/'); + char *ptr; + + ptr = kstrdup((tail ? tail + 1 : filename), GFP_KERNEL); + if (!ptr) { + ret = -ENOMEM; + goto fail_address_parse; + } + + tail = ptr; + ptr = strpbrk(tail, ".-_"); + if (ptr) + *ptr = '\0'; + + snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); + event = buf; + kfree(tail); + } + + tu = alloc_trace_uprobe(group, event, argc); + if (IS_ERR(tu)) { + pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); + ret = PTR_ERR(tu); + goto fail_address_parse; + } + tu->offset = offset; + tu->inode = inode; + tu->filename = kstrdup(filename, GFP_KERNEL); + + if (!tu->filename) { + pr_info("Failed to allocate filename.\n"); + ret = -ENOMEM; + goto error; + } + + /* parse arguments */ + ret = 0; + for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + /* Increment count for freeing args in error case */ + tu->nr_args++; + + /* Parse argument name */ + arg = strchr(argv[i], '='); + if (arg) { + *arg++ = '\0'; + tu->args[i].name = kstrdup(argv[i], GFP_KERNEL); + } else { + arg = argv[i]; + /* If argument name is omitted, set "argN" */ + snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); + tu->args[i].name = kstrdup(buf, GFP_KERNEL); + } + + if (!tu->args[i].name) { + pr_info("Failed to allocate argument[%d] name.\n", i); + ret = -ENOMEM; + goto error; + } + + if (!is_good_name(tu->args[i].name)) { + pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name); + ret = -EINVAL; + goto error; + } + + if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) { + pr_info("Argument[%d] name '%s' conflicts with " + "another field.\n", i, argv[i]); + ret = -EINVAL; + goto error; + } + + /* Parse fetch argument */ + ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false); + if (ret) { + pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + goto error; + } + } + + ret = register_trace_uprobe(tu); + if (ret) + goto error; + return 0; + +error: + free_trace_uprobe(tu); + return ret; + +fail_address_parse: + if (inode) + iput(inode); + + pr_info("Failed to parse address.\n"); + + return ret; +} + +static void cleanup_all_probes(void) +{ + struct trace_uprobe *tu; + + mutex_lock(&uprobe_lock); + while (!list_empty(&uprobe_list)) { + tu = list_entry(uprobe_list.next, struct trace_uprobe, list); + unregister_trace_uprobe(tu); + } + mutex_unlock(&uprobe_lock); +} + +/* Probes listing interfaces */ +static void *probes_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&uprobe_lock); + return seq_list_start(&uprobe_list, *pos); +} + +static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &uprobe_list, pos); +} + +static void probes_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&uprobe_lock); +} + +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct trace_uprobe *tu = v; + int i; + + seq_printf(m, "p:%s/%s", tu->call.class->system, tu->call.name); + seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); + + for (i = 0; i < tu->nr_args; i++) + seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm); + + 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 ssize_t probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe); +} + +static const struct file_operations uprobe_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_uprobe *tu = v; + + seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit); + 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 uprobe_profile_ops = { + .owner = THIS_MODULE, + .open = profile_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* uprobe handler */ +static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +{ + struct uprobe_trace_entry_head *entry; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + u8 *data; + int size, i, pc; + unsigned long irq_flags; + struct ftrace_event_call *call = &tu->call; + + tu->nhit++; + + local_save_flags(irq_flags); + pc = preempt_count(); + + size = sizeof(*entry) + tu->size; + + event = trace_current_buffer_lock_reserve(&buffer, call->event.type, + size, irq_flags, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + data = (u8 *)&entry[1]; + for (i = 0; i < tu->nr_args; i++) + call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); + + if (!filter_current_check_discard(buffer, call, entry, event)) + trace_buffer_unlock_commit(buffer, event, irq_flags, pc); +} + +/* Event entry printers */ +static enum print_line_t +print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) +{ + struct uprobe_trace_entry_head *field; + struct trace_seq *s = &iter->seq; + struct trace_uprobe *tu; + u8 *data; + int i; + + field = (struct uprobe_trace_entry_head *)iter->ent; + tu = container_of(event, struct trace_uprobe, call.event); + + if (!trace_seq_printf(s, "%s: (", tu->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; + + data = (u8 *)&field[1]; + for (i = 0; i < tu->nr_args; i++) { + if (!tu->args[i].type->print(s, tu->args[i].name, + data + tu->args[i].offset, field)) + goto partial; + } + + if (trace_seq_puts(s, "\n")) + return TRACE_TYPE_HANDLED; + +partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int probe_event_enable(struct trace_uprobe *tu, int flag) +{ + struct uprobe_trace_consumer *utc; + int ret = 0; + + if (!tu->inode || tu->consumer) + return -EINTR; + + utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL); + if (!utc) + return -EINTR; + + utc->cons.handler = uprobe_dispatcher; + utc->cons.filter = NULL; + ret = uprobe_register(tu->inode, tu->offset, &utc->cons); + if (ret) { + kfree(utc); + return ret; + } + + tu->flags |= flag; + utc->tu = tu; + tu->consumer = utc; + + return 0; +} + +static void probe_event_disable(struct trace_uprobe *tu, int flag) +{ + if (!tu->inode || !tu->consumer) + return; + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons); + tu->flags &= ~flag; + kfree(tu->consumer); + tu->consumer = NULL; +} + +static int uprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i; + struct uprobe_trace_entry_head field; + struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data; + + DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); + /* Set argument names as fields */ + for (i = 0; i < tu->nr_args; i++) { + ret = trace_define_field(event_call, tu->args[i].type->fmttype, + tu->args[i].name, + sizeof(field) + tu->args[i].offset, + tu->args[i].type->size, + tu->args[i].type->is_signed, + FILTER_OTHER); + + if (ret) + return ret; + } + return 0; +} + +#define LEN_OR_ZERO (len ? len - pos : 0) +static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len) +{ + const char *fmt, *arg; + int i; + int pos = 0; + + fmt = "(%lx)"; + arg = "REC->" FIELD_STRING_IP; + + /* When len=0, we just calculate the needed length */ + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); + + for (i = 0; i < tu->nr_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s", + tu->args[i].name, tu->args[i].type->fmt); + } + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + + for (i = 0; i < tu->nr_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", + tu->args[i].name); + } + + return pos; /* return the length of print_fmt */ +} +#undef LEN_OR_ZERO + +static int set_print_fmt(struct trace_uprobe *tu) +{ + char *print_fmt; + int len; + + /* First: called with 0 length to calculate the needed length */ + len = __set_print_fmt(tu, NULL, 0); + print_fmt = kmalloc(len + 1, GFP_KERNEL); + if (!print_fmt) + return -ENOMEM; + + /* Second: actually write the @print_fmt */ + __set_print_fmt(tu, print_fmt, len + 1); + tu->call.print_fmt = print_fmt; + + return 0; +} + +#ifdef CONFIG_PERF_EVENTS +/* uprobe profile handler */ +static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +{ + struct ftrace_event_call *call = &tu->call; + struct uprobe_trace_entry_head *entry; + struct hlist_head *head; + u8 *data; + int size, __size, i; + int rctx; + + __size = sizeof(*entry) + tu->size; + size = ALIGN(__size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) + return; + + preempt_disable(); + + entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + if (!entry) + goto out; + + entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + data = (u8 *)&entry[1]; + for (i = 0; i < tu->nr_args; i++) + call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); + + head = this_cpu_ptr(call->perf_events); + perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head); + + out: + preempt_enable(); +} +#endif /* CONFIG_PERF_EVENTS */ + +static +int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) +{ + struct trace_uprobe *tu = (struct trace_uprobe *)event->data; + + switch (type) { + case TRACE_REG_REGISTER: + return probe_event_enable(tu, TP_FLAG_TRACE); + + case TRACE_REG_UNREGISTER: + probe_event_disable(tu, TP_FLAG_TRACE); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return probe_event_enable(tu, TP_FLAG_PROFILE); + + case TRACE_REG_PERF_UNREGISTER: + probe_event_disable(tu, TP_FLAG_PROFILE); + return 0; +#endif + default: + return 0; + } + return 0; +} + +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) +{ + struct uprobe_trace_consumer *utc; + struct trace_uprobe *tu; + + utc = container_of(con, struct uprobe_trace_consumer, cons); + tu = utc->tu; + if (!tu || tu->consumer != utc) + return 0; + + if (tu->flags & TP_FLAG_TRACE) + uprobe_trace_func(tu, regs); + +#ifdef CONFIG_PERF_EVENTS + if (tu->flags & TP_FLAG_PROFILE) + uprobe_perf_func(tu, regs); +#endif + return 0; +} + +static struct trace_event_functions uprobe_funcs = { + .trace = print_uprobe_event +}; + +static int register_uprobe_event(struct trace_uprobe *tu) +{ + struct ftrace_event_call *call = &tu->call; + int ret; + + /* Initialize ftrace_event_call */ + INIT_LIST_HEAD(&call->class->fields); + call->event.funcs = &uprobe_funcs; + call->class->define_fields = uprobe_event_define_fields; + + if (set_print_fmt(tu) < 0) + return -ENOMEM; + + ret = register_ftrace_event(&call->event); + if (!ret) { + kfree(call->print_fmt); + return -ENODEV; + } + call->flags = 0; + call->class->reg = trace_uprobe_register; + call->data = tu; + ret = trace_add_event_call(call); + + if (ret) { + pr_info("Failed to register uprobe event: %s\n", call->name); + kfree(call->print_fmt); + unregister_ftrace_event(&call->event); + } + + return ret; +} + +static void unregister_uprobe_event(struct trace_uprobe *tu) +{ + /* tu->event is unregistered in trace_remove_event_call() */ + trace_remove_event_call(&tu->call); + kfree(tu->call.print_fmt); + tu->call.print_fmt = NULL; +} + +/* Make a trace interface for controling probe points */ +static __init int init_uprobe_trace(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + trace_create_file("uprobe_events", 0644, d_tracer, + NULL, &uprobe_events_ops); + /* Profile interface */ + trace_create_file("uprobe_profile", 0444, d_tracer, + NULL, &uprobe_profile_ops); + return 0; +} + +fs_initcall(init_uprobe_trace); -- cgit v1.3-8-gc7d7 From 50e18b94c695644d824381e7574b9c44acc25ffe Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 25 Apr 2012 10:23:39 +0200 Subject: tracing: Use seq_*_private interface for some seq files It's appropriate to use __seq_open_private interface to open some of trace seq files, because it covers all steps we are duplicating in tracing code - zallocating the iterator and setting it as seq_file's private. Using this for following files: trace available_filter_functions enabled_functions Link: http://lkml.kernel.org/r/1335342219-2782-5-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa [ Fixed warnings for: kernel/trace/trace.c: In function '__tracing_open': kernel/trace/trace.c:2418:11: warning: unused variable 'ret' [-Wunused-variable] kernel/trace/trace.c:2417:19: warning: unused variable 'm' [-Wunused-variable] ] Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 44 +++++++++++--------------------------------- kernel/trace/trace.c | 30 +++++------------------------- 2 files changed, 16 insertions(+), 58 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0fa92f677c92..cf81f27ce6c6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2469,57 +2469,35 @@ 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; - iter->ops = &global_ops; - - ret = seq_open(file, &show_ftrace_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - - m->private = iter; - } else { - kfree(iter); + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (iter) { + iter->pg = ftrace_pages_start; + iter->ops = &global_ops; } - return ret; + return iter ? 0 : -ENOMEM; } static int ftrace_enabled_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; - iter->flags = FTRACE_ITER_ENABLED; - iter->ops = &global_ops; - - ret = seq_open(file, &show_ftrace_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - - m->private = iter; - } else { - kfree(iter); + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (iter) { + iter->pg = ftrace_pages_start; + iter->flags = FTRACE_ITER_ENABLED; + iter->ops = &global_ops; } - return ret; + return iter ? 0 : -ENOMEM; } static void ftrace_filter_reset(struct ftrace_hash *hash) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f11a285ee5bb..4fb10ef727d3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2413,15 +2413,13 @@ 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; + int cpu; if (tracing_disabled) return ERR_PTR(-ENODEV); - iter = kzalloc(sizeof(*iter), GFP_KERNEL); + iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter)); if (!iter) return ERR_PTR(-ENOMEM); @@ -2478,32 +2476,15 @@ __tracing_open(struct inode *inode, struct file *file) 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; + seq_release_private(inode, file); + return ERR_PTR(-ENOMEM); } int tracing_open_generic(struct inode *inode, struct file *filp) @@ -2539,11 +2520,10 @@ static int tracing_release(struct inode *inode, struct file *file) 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); + seq_release_private(inode, file); return 0; } -- cgit v1.3-8-gc7d7 From 68179686ac67cb08f08b1ef28b860d5ed899f242 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 8 May 2012 20:57:53 -0400 Subject: tracing: Remove ftrace_disable/enable_cpu() The ftrace_disable_cpu() and ftrace_enable_cpu() functions were needed back before the ring buffer was lockless. Now that the ring buffer is lockless (and has been for some time), these functions serve no purpose, and unnecessarily slow down operations of the tracer. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 44 ++------------------------------------------ 1 file changed, 2 insertions(+), 42 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4fb10ef727d3..48ef4960ec90 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -87,18 +87,6 @@ static int tracing_disabled = 1; DEFINE_PER_CPU(int, ftrace_cpu_disabled); -static inline void ftrace_disable_cpu(void) -{ - preempt_disable(); - __this_cpu_inc(ftrace_cpu_disabled); -} - -static inline void ftrace_enable_cpu(void) -{ - __this_cpu_dec(ftrace_cpu_disabled); - preempt_enable(); -} - cpumask_var_t __read_mostly tracing_buffer_mask; /* @@ -748,8 +736,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&ftrace_max_lock); - ftrace_disable_cpu(); - ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); if (ret == -EBUSY) { @@ -763,8 +749,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) "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); @@ -916,13 +900,6 @@ 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; @@ -931,7 +908,7 @@ void tracing_reset(struct trace_array *tr, int cpu) /* Make sure all commits have finished */ synchronize_sched(); - __tracing_reset(buffer, cpu); + ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } @@ -949,7 +926,7 @@ void tracing_reset_online_cpus(struct trace_array *tr) tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) - __tracing_reset(buffer, cpu); + ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } @@ -1733,14 +1710,9 @@ EXPORT_SYMBOL_GPL(trace_vprintk); 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 * @@ -1750,17 +1722,12 @@ 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, lost_events); - ftrace_enable_cpu(); - if (event) { iter->ent_size = ring_buffer_event_length(event); return ring_buffer_event_data(event); @@ -1850,11 +1817,8 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter) 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, &iter->lost_events); - ftrace_enable_cpu(); } static void *s_next(struct seq_file *m, void *v, loff_t *pos) @@ -1943,16 +1907,12 @@ static void *s_start(struct seq_file *m, loff_t *pos) 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)) ; -- cgit v1.3-8-gc7d7 From 9b63776fa3ca96c4ecda76f6fa947b7b0add66ac Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 10 May 2012 15:55:43 -0400 Subject: tracing: Do not enable function event with enable With the adding of function tracing event to perf, it caused a side effect that produces the following warning when enabling all events in ftrace: # echo 1 > /sys/kernel/debug/tracing/events/enable [console] event trace: Could not enable event function This is because when enabling all events via the debugfs system it ignores events that do not have a ->reg() function assigned. This was to skip over the ftrace internal events (as they are not TRACE_EVENTs). But as the ftrace function event now has a ->reg() function attached to it for use with perf, it is no longer ignored. Worse yet, this ->reg() function is being called when it should not be. It returns an error and causes the above warning to be printed. By adding a new event_call flag (TRACE_EVENT_FL_IGNORE_ENABLE) and have all ftrace internel event structures have it set, setting the events/enable will no longe try to incorrectly enable the function event and does not warn. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 ++ kernel/trace/trace_events.c | 5 ++++- kernel/trace/trace_export.c | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 5f3f3be5af09..176a939d1547 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -179,6 +179,7 @@ enum { TRACE_EVENT_FL_RECORDED_CMD_BIT, TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, + TRACE_EVENT_FL_IGNORE_ENABLE_BIT, }; enum { @@ -187,6 +188,7 @@ enum { TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), + TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), }; struct ftrace_event_call { diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 079a93ae8a9d..29111da1d100 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -294,6 +294,9 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, if (!call->name || !call->class || !call->class->reg) continue; + if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + continue; + if (match && strcmp(match, call->name) != 0 && strcmp(match, call->class->system) != 0) @@ -1164,7 +1167,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return -1; } - if (call->class->reg) + if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) trace_create_file("enable", 0644, call->dir, call, enable); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 3dd15e8bc856..e039906b037d 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -180,6 +180,7 @@ struct ftrace_event_call __used event_##call = { \ .event.type = etype, \ .class = &event_class_ftrace_##call, \ .print_fmt = print, \ + .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ }; \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; -- cgit v1.3-8-gc7d7 From 6edb2a8a385f0cdef51dae37ff23e74d76d8a6ce Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 May 2012 23:28:49 -0400 Subject: tracing: Clean up tracing_mark_write() On gcc 4.5 the function tracing_mark_write() would give a warning of page2 being uninitialized. This is due to a bug in gcc because the logic prevents page2 from being used uninitialized, and gcc 4.6+ does not complain (correctly). Instead of adding a "unitialized" around page2, which could show a bug later on, I combined page1 and page2 into an array map_pages[]. This binds the two and the two are modified according to nr_pages (what gcc 4.5 seems to ignore). This no longer gives a warning with gcc 4.5 nor with gcc 4.6. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 48ef4960ec90..d1b3469b62e3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3875,14 +3875,14 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, struct print_entry *entry; unsigned long irq_flags; struct page *pages[2]; + void *map_page[2]; int nr_pages = 1; ssize_t written; - void *page1; - void *page2; int offset; int size; int len; int ret; + int i; if (tracing_disabled) return -EINVAL; @@ -3921,9 +3921,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, goto out; } - page1 = kmap_atomic(pages[0]); - if (nr_pages == 2) - page2 = kmap_atomic(pages[1]); + for (i = 0; i < nr_pages; i++) + map_page[i] = kmap_atomic(pages[i]); local_save_flags(irq_flags); size = sizeof(*entry) + cnt + 2; /* possible \n added */ @@ -3941,10 +3940,10 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (nr_pages == 2) { len = PAGE_SIZE - offset; - memcpy(&entry->buf, page1 + offset, len); - memcpy(&entry->buf[len], page2, cnt - len); + memcpy(&entry->buf, map_page[0] + offset, len); + memcpy(&entry->buf[len], map_page[1], cnt - len); } else - memcpy(&entry->buf, page1 + offset, cnt); + memcpy(&entry->buf, map_page[0] + offset, cnt); if (entry->buf[cnt - 1] != '\n') { entry->buf[cnt] = '\n'; @@ -3959,11 +3958,10 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, *fpos += written; out_unlock: - if (nr_pages == 2) - kunmap_atomic(page2); - kunmap_atomic(page1); - while (nr_pages > 0) - put_page(pages[--nr_pages]); + for (i = 0; i < nr_pages; i++){ + kunmap_atomic(map_page[i]); + put_page(pages[i]); + } out: return written; } -- cgit v1.3-8-gc7d7 From 83f40318dab00e3298a1f6d0b12ac025e84e478d Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Thu, 3 May 2012 18:59:50 -0700 Subject: ring-buffer: Make removal of ring buffer pages atomic This patch adds the capability to remove pages from a ring buffer without destroying any existing data in it. This is done by removing the pages after the tail page. This makes sure that first all the empty pages in the ring buffer are removed. If the head page is one in the list of pages to be removed, then the page after the removed ones is made the head page. This removes the oldest data from the ring buffer and keeps the latest data around to be read. To do this in a non-racey manner, tracing is stopped for a very short time while the pages to be removed are identified and unlinked from the ring buffer. The pages are freed after the tracing is restarted to minimize the time needed to stop tracing. The context in which the pages from the per-cpu ring buffer are removed runs on the respective CPU. This minimizes the events not traced to only NMI trace contexts. Link: http://lkml.kernel.org/r/1336096792-25373-1-git-send-email-vnagarnaik@google.com Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Laurent Chavey Cc: Justin Teravest Cc: David Sharp Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 265 +++++++++++++++++++++++++++++++++++---------- kernel/trace/trace.c | 20 +--- 2 files changed, 209 insertions(+), 76 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2d5eb3320827..27ac37efb2b0 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -23,6 +23,8 @@ #include #include "trace.h" +static void update_pages_handler(struct work_struct *work); + /* * The ring buffer header is special. We must manually up keep it. */ @@ -470,12 +472,15 @@ struct ring_buffer_per_cpu { /* ring buffer pages to update, > 0 to add, < 0 to remove */ int nr_pages_to_update; struct list_head new_pages; /* new pages to add */ + struct work_struct update_pages_work; + struct completion update_completion; }; struct ring_buffer { unsigned flags; int cpus; atomic_t record_disabled; + atomic_t resize_disabled; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; @@ -1048,6 +1053,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) raw_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; + INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler); + init_completion(&cpu_buffer->update_completion); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1235,32 +1242,123 @@ void ring_buffer_set_clock(struct ring_buffer *buffer, static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); +static inline unsigned long rb_page_entries(struct buffer_page *bpage) +{ + return local_read(&bpage->entries) & RB_WRITE_MASK; +} + +static inline unsigned long rb_page_write(struct buffer_page *bpage) +{ + return local_read(&bpage->write) & RB_WRITE_MASK; +} + static void -rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) +rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages) { - struct buffer_page *bpage; - struct list_head *p; - unsigned i; + struct list_head *tail_page, *to_remove, *next_page; + struct buffer_page *to_remove_page, *tmp_iter_page; + struct buffer_page *last_page, *first_page; + unsigned int nr_removed; + unsigned long head_bit; + int page_entries; + + head_bit = 0; raw_spin_lock_irq(&cpu_buffer->reader_lock); - rb_head_page_deactivate(cpu_buffer); + atomic_inc(&cpu_buffer->record_disabled); + /* + * We don't race with the readers since we have acquired the reader + * lock. We also don't race with writers after disabling recording. + * This makes it easy to figure out the first and the last page to be + * removed from the list. We unlink all the pages in between including + * the first and last pages. This is done in a busy loop so that we + * lose the least number of traces. + * The pages are freed after we restart recording and unlock readers. + */ + tail_page = &cpu_buffer->tail_page->list; - for (i = 0; i < nr_pages; i++) { - if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages))) - goto out; - p = cpu_buffer->pages->next; - bpage = list_entry(p, struct buffer_page, list); - list_del_init(&bpage->list); - free_buffer_page(bpage); + /* + * tail page might be on reader page, we remove the next page + * from the ring buffer + */ + if (cpu_buffer->tail_page == cpu_buffer->reader_page) + tail_page = rb_list_head(tail_page->next); + to_remove = tail_page; + + /* start of pages to remove */ + first_page = list_entry(rb_list_head(to_remove->next), + struct buffer_page, list); + + for (nr_removed = 0; nr_removed < nr_pages; nr_removed++) { + to_remove = rb_list_head(to_remove)->next; + head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD; } - if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages))) - goto out; - rb_reset_cpu(cpu_buffer); - rb_check_pages(cpu_buffer); + next_page = rb_list_head(to_remove)->next; -out: + /* + * Now we remove all pages between tail_page and next_page. + * Make sure that we have head_bit value preserved for the + * next page + */ + tail_page->next = (struct list_head *)((unsigned long)next_page | + head_bit); + next_page = rb_list_head(next_page); + next_page->prev = tail_page; + + /* make sure pages points to a valid page in the ring buffer */ + cpu_buffer->pages = next_page; + + /* update head page */ + if (head_bit) + cpu_buffer->head_page = list_entry(next_page, + struct buffer_page, list); + + /* + * change read pointer to make sure any read iterators reset + * themselves + */ + cpu_buffer->read = 0; + + /* pages are removed, resume tracing and then free the pages */ + atomic_dec(&cpu_buffer->record_disabled); raw_spin_unlock_irq(&cpu_buffer->reader_lock); + + RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)); + + /* last buffer page to remove */ + last_page = list_entry(rb_list_head(to_remove), struct buffer_page, + list); + tmp_iter_page = first_page; + + do { + to_remove_page = tmp_iter_page; + rb_inc_page(cpu_buffer, &tmp_iter_page); + + /* update the counters */ + page_entries = rb_page_entries(to_remove_page); + if (page_entries) { + /* + * If something was added to this page, it was full + * since it is not the tail page. So we deduct the + * bytes consumed in ring buffer from here. + * No need to update overruns, since this page is + * deleted from ring buffer and its entries are + * already accounted for. + */ + local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + } + + /* + * We have already removed references to this list item, just + * free up the buffer_page and its page + */ + free_buffer_page(to_remove_page); + nr_removed--; + + } while (to_remove_page != last_page); + + RB_WARN_ON(cpu_buffer, nr_removed); } static void @@ -1272,6 +1370,8 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned i; raw_spin_lock_irq(&cpu_buffer->reader_lock); + /* stop the writers while inserting pages */ + atomic_inc(&cpu_buffer->record_disabled); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1286,19 +1386,27 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_check_pages(cpu_buffer); out: + atomic_dec(&cpu_buffer->record_disabled); raw_spin_unlock_irq(&cpu_buffer->reader_lock); } -static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer) +static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer) { if (cpu_buffer->nr_pages_to_update > 0) rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages, cpu_buffer->nr_pages_to_update); else rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update); + cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; - /* reset this value */ - cpu_buffer->nr_pages_to_update = 0; +} + +static void update_pages_handler(struct work_struct *work) +{ + struct ring_buffer_per_cpu *cpu_buffer = container_of(work, + struct ring_buffer_per_cpu, update_pages_work); + rb_update_pages(cpu_buffer); + complete(&cpu_buffer->update_completion); } /** @@ -1308,14 +1416,14 @@ static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer) * * Minimum size is 2 * BUF_PAGE_SIZE. * - * Returns -1 on failure. + * Returns 0 on success and < 0 on failure. */ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, int cpu_id) { struct ring_buffer_per_cpu *cpu_buffer; unsigned nr_pages; - int cpu; + int cpu, err = 0; /* * Always succeed at resizing a non-existent buffer: @@ -1330,15 +1438,18 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, if (size < BUF_PAGE_SIZE * 2) size = BUF_PAGE_SIZE * 2; - atomic_inc(&buffer->record_disabled); + nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); - /* Make sure all writers are done with this buffer. */ - synchronize_sched(); + /* + * Don't succeed if resizing is disabled, as a reader might be + * manipulating the ring buffer and is expecting a sane state while + * this is true. + */ + if (atomic_read(&buffer->resize_disabled)) + return -EBUSY; + /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); - get_online_cpus(); - - nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); if (cpu_id == RING_BUFFER_ALL_CPUS) { /* calculate the pages to update */ @@ -1347,33 +1458,67 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, cpu_buffer->nr_pages_to_update = nr_pages - cpu_buffer->nr_pages; - /* * nothing more to do for removing pages or no update */ if (cpu_buffer->nr_pages_to_update <= 0) continue; - /* * to add pages, make sure all new pages can be * allocated without receiving ENOMEM */ INIT_LIST_HEAD(&cpu_buffer->new_pages); if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update, - &cpu_buffer->new_pages, cpu)) + &cpu_buffer->new_pages, cpu)) { /* not enough memory for new pages */ - goto no_mem; + err = -ENOMEM; + goto out_err; + } + } + + get_online_cpus(); + /* + * Fire off all the required work handlers + * Look out for offline CPUs + */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (!cpu_buffer->nr_pages_to_update || + !cpu_online(cpu)) + continue; + + schedule_work_on(cpu, &cpu_buffer->update_pages_work); + } + /* + * This loop is for the CPUs that are not online. + * We can't schedule anything on them, but it's not necessary + * since we can change their buffer sizes without any race. + */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (!cpu_buffer->nr_pages_to_update || + cpu_online(cpu)) + continue; + + rb_update_pages(cpu_buffer); } /* wait for all the updates to complete */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - if (cpu_buffer->nr_pages_to_update) { - update_pages_handler(cpu_buffer); - } + if (!cpu_buffer->nr_pages_to_update || + !cpu_online(cpu)) + continue; + + wait_for_completion(&cpu_buffer->update_completion); + /* reset this value */ + cpu_buffer->nr_pages_to_update = 0; } + + put_online_cpus(); } else { cpu_buffer = buffer->buffers[cpu_id]; + if (nr_pages == cpu_buffer->nr_pages) goto out; @@ -1383,38 +1528,47 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, INIT_LIST_HEAD(&cpu_buffer->new_pages); if (cpu_buffer->nr_pages_to_update > 0 && __rb_allocate_pages(cpu_buffer->nr_pages_to_update, - &cpu_buffer->new_pages, cpu_id)) - goto no_mem; + &cpu_buffer->new_pages, cpu_id)) { + err = -ENOMEM; + goto out_err; + } - update_pages_handler(cpu_buffer); + get_online_cpus(); + + if (cpu_online(cpu_id)) { + schedule_work_on(cpu_id, + &cpu_buffer->update_pages_work); + wait_for_completion(&cpu_buffer->update_completion); + } else + rb_update_pages(cpu_buffer); + + put_online_cpus(); + /* reset this value */ + cpu_buffer->nr_pages_to_update = 0; } out: - put_online_cpus(); mutex_unlock(&buffer->mutex); - - atomic_dec(&buffer->record_disabled); - return size; - no_mem: + out_err: for_each_buffer_cpu(buffer, cpu) { struct buffer_page *bpage, *tmp; + cpu_buffer = buffer->buffers[cpu]; - /* reset this number regardless */ cpu_buffer->nr_pages_to_update = 0; + if (list_empty(&cpu_buffer->new_pages)) continue; + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_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; + return err; } EXPORT_SYMBOL_GPL(ring_buffer_resize); @@ -1453,21 +1607,11 @@ 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 committed */ static inline unsigned rb_page_size(struct buffer_page *bpage) { @@ -3492,6 +3636,7 @@ ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu) iter->cpu_buffer = cpu_buffer; + atomic_inc(&buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); return iter; @@ -3555,6 +3700,7 @@ 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); + atomic_dec(&cpu_buffer->buffer->resize_disabled); kfree(iter); } EXPORT_SYMBOL_GPL(ring_buffer_read_finish); @@ -3662,8 +3808,12 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; + atomic_inc(&buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); + /* Make sure all commits have finished */ + synchronize_sched(); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) @@ -3679,6 +3829,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); + atomic_dec(&buffer->resize_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d1b3469b62e3..dfbd86cc4876 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3076,20 +3076,10 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) { - int cpu, ret = size; + int ret = size; 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); - } - if (cpu_id != RING_BUFFER_ALL_CPUS) { /* make sure, this cpu is enabled in the mask */ if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { @@ -3103,14 +3093,6 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) ret = -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(); mutex_unlock(&trace_types_lock); return ret; -- cgit v1.3-8-gc7d7 From 5040b4b7bcc26a311c799d46f67174bcb20d05dd Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Thu, 3 May 2012 18:59:51 -0700 Subject: ring-buffer: Make addition of pages in ring buffer atomic This patch adds the capability to add new pages to a ring buffer atomically while write operations are going on. This makes it possible to expand the ring buffer size without reinitializing the ring buffer. The new pages are attached between the head page and its previous page. Link: http://lkml.kernel.org/r/1336096792-25373-2-git-send-email-vnagarnaik@google.com Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Laurent Chavey Cc: Justin Teravest Cc: David Sharp Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 102 ++++++++++++++++++++++++++++++++++----------- 1 file changed, 77 insertions(+), 25 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 27ac37efb2b0..d673ef03d16d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1252,7 +1252,7 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage) return local_read(&bpage->write) & RB_WRITE_MASK; } -static void +static int rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages) { struct list_head *tail_page, *to_remove, *next_page; @@ -1359,46 +1359,97 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages) } while (to_remove_page != last_page); RB_WARN_ON(cpu_buffer, nr_removed); + + return nr_removed == 0; } -static void -rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, - struct list_head *pages, unsigned nr_pages) +static int +rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) { - struct buffer_page *bpage; - struct list_head *p; - unsigned i; + struct list_head *pages = &cpu_buffer->new_pages; + int retries, success; raw_spin_lock_irq(&cpu_buffer->reader_lock); - /* stop the writers while inserting pages */ - atomic_inc(&cpu_buffer->record_disabled); - rb_head_page_deactivate(cpu_buffer); + /* + * We are holding the reader lock, so the reader page won't be swapped + * in the ring buffer. Now we are racing with the writer trying to + * move head page and the tail page. + * We are going to adapt the reader page update process where: + * 1. We first splice the start and end of list of new pages between + * the head page and its previous page. + * 2. We cmpxchg the prev_page->next to point from head page to the + * start of new pages list. + * 3. Finally, we update the head->prev to the end of new list. + * + * We will try this process 10 times, to make sure that we don't keep + * spinning. + */ + retries = 10; + success = 0; + while (retries--) { + struct list_head *head_page, *prev_page, *r; + struct list_head *last_page, *first_page; + struct list_head *head_page_with_bit; - for (i = 0; i < nr_pages; i++) { - if (RB_WARN_ON(cpu_buffer, list_empty(pages))) - goto out; - p = pages->next; - bpage = list_entry(p, struct buffer_page, list); - list_del_init(&bpage->list); - list_add_tail(&bpage->list, cpu_buffer->pages); + head_page = &rb_set_head_page(cpu_buffer)->list; + prev_page = head_page->prev; + + first_page = pages->next; + last_page = pages->prev; + + head_page_with_bit = (struct list_head *) + ((unsigned long)head_page | RB_PAGE_HEAD); + + last_page->next = head_page_with_bit; + first_page->prev = prev_page; + + r = cmpxchg(&prev_page->next, head_page_with_bit, first_page); + + if (r == head_page_with_bit) { + /* + * yay, we replaced the page pointer to our new list, + * now, we just have to update to head page's prev + * pointer to point to end of list + */ + head_page->prev = last_page; + success = 1; + break; + } } - rb_reset_cpu(cpu_buffer); - rb_check_pages(cpu_buffer); -out: - atomic_dec(&cpu_buffer->record_disabled); + if (success) + INIT_LIST_HEAD(pages); + /* + * If we weren't successful in adding in new pages, warn and stop + * tracing + */ + RB_WARN_ON(cpu_buffer, !success); raw_spin_unlock_irq(&cpu_buffer->reader_lock); + + /* free pages if they weren't inserted */ + if (!success) { + struct buffer_page *bpage, *tmp; + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, + list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + } + return success; } static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer) { + int success; + if (cpu_buffer->nr_pages_to_update > 0) - rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages, - cpu_buffer->nr_pages_to_update); + success = rb_insert_pages(cpu_buffer); else - rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update); + success = rb_remove_pages(cpu_buffer, + -cpu_buffer->nr_pages_to_update); - cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; + if (success) + cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; } static void update_pages_handler(struct work_struct *work) @@ -3772,6 +3823,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->commit_page = cpu_buffer->head_page; INIT_LIST_HEAD(&cpu_buffer->reader_page->list); + INIT_LIST_HEAD(&cpu_buffer->new_pages); 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); -- cgit v1.3-8-gc7d7 From 659f451ff21315ebfeeb46b9adccee8ce1b52c25 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 14 May 2012 17:02:33 -0400 Subject: ring-buffer: Add integrity check at end of iter read There use to be ring buffer integrity checks after updating the size of the ring buffer. But now that the ring buffer can modify the size while the system is running, the integrity checks were removed, as they require the ring buffer to be disabed to perform the check. Move the integrity check to the reading of the ring buffer via the iterator reads (the "trace" file). As reading via an iterator requires disabling the ring buffer, it is a perfect place to have it. If the ring buffer happens to be disabled when updating the size, we still perform the integrity check. Cc: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d673ef03d16d..e0573c523b5c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1599,6 +1599,29 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, } out: + /* + * The ring buffer resize can happen with the ring buffer + * enabled, so that the update disturbs the tracing as little + * as possible. But if the buffer is disabled, we do not need + * to worry about that, and we can take the time to verify + * that the buffer is not corrupt. + */ + if (atomic_read(&buffer->record_disabled)) { + atomic_inc(&buffer->record_disabled); + /* + * Even though the buffer was disabled, we must make sure + * that it is truly disabled before calling rb_check_pages. + * There could have been a race between checking + * record_disable and incrementing it. + */ + synchronize_sched(); + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + rb_check_pages(cpu_buffer); + } + atomic_dec(&buffer->record_disabled); + } + mutex_unlock(&buffer->mutex); return size; @@ -3750,6 +3773,12 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + /* + * Ring buffer is disabled from recording, here's a good place + * to check the integrity of the ring buffer. + */ + rb_check_pages(cpu_buffer); + atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->buffer->resize_disabled); kfree(iter); -- cgit v1.3-8-gc7d7 From 308f7eeb7882c27c1d7aa783499cb22f3b199718 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 16 May 2012 19:46:32 -0400 Subject: ring-buffer: Reset head page before running self test When the ring buffer does its consistency test on itself, it removes the head page, runs the tests, and then adds it back to what the "head_page" pointer was. But because the head_page pointer may lack behind the real head page (held by the link list pointer). The reset may be incorrect. Instead, if the head_page exists (it does not on first allocation) reset it back to the real head page before running the consistency tests. Then it will be put back to its original location after the tests are complete. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e0573c523b5c..68388f876d43 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -945,6 +945,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; + /* Reset the head page if it exists */ + if (cpu_buffer->head_page) + rb_set_head_page(cpu_buffer); + rb_head_page_deactivate(cpu_buffer); if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) -- cgit v1.3-8-gc7d7 From 0a3d7ce7e6caa8c39cb5184bd9047a01a40abc2a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 23 Apr 2012 10:11:57 +0900 Subject: tracing: Check return value of tracing_dentry_percpu() If tracing_dentry_percpu() failed, tracing_init_debugfs_percpu() will try to create each cpu directories on debugfs' root directory as d_percpu is NULL. Link: http://lkml.kernel.org/r/1335143517-2285-1-git-send-email-namhyung.kim@lge.com Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dfbd86cc4876..0ed4df0c6a39 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4474,6 +4474,9 @@ static void tracing_init_debugfs_percpu(long cpu) struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ + if (!d_percpu) + return; + snprintf(cpu_dir, 30, "cpu%ld", cpu); d_cpu = debugfs_create_dir(cpu_dir, d_percpu); if (!d_cpu) { -- cgit v1.3-8-gc7d7 From 71babb2705e2203a64c27ede13ae3508a0d2c16c Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Thu, 3 May 2012 18:59:52 -0700 Subject: tracing: change CPU ring buffer state from tracing_cpumask According to Documentation/trace/ftrace.txt: tracing_cpumask: This is a mask that lets the user only trace on specified CPUS. The format is a hex string representing the CPUS. The tracing_cpumask currently doesn't affect the tracing state of per-CPU ring buffers. This patch enables/disables CPU recording as its corresponding bit in tracing_cpumask is set/unset. Link: http://lkml.kernel.org/r/1336096792-25373-3-git-send-email-vnagarnaik@google.com Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Laurent Chavey Cc: Justin Teravest Cc: David Sharp Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0ed4df0c6a39..08a08bab57a3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2669,10 +2669,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, if (cpumask_test_cpu(cpu, tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_inc(&global_trace.data[cpu]->disabled); + ring_buffer_record_disable_cpu(global_trace.buffer, cpu); } if (!cpumask_test_cpu(cpu, tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_dec(&global_trace.data[cpu]->disabled); + ring_buffer_record_enable_cpu(global_trace.buffer, cpu); } } arch_spin_unlock(&ftrace_max_lock); -- cgit v1.3-8-gc7d7 From 9fd49328fc2a1cbfea542bcbcf004b5c81dc495b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 24 Apr 2012 22:32:06 -0400 Subject: ftrace: Sort all function addresses, not just per page Instead of just sorting the ip's of the functions per ftrace page, sort the entire list before adding them to the ftrace pages. This will allow the bsearch algorithm to be sped up as it can also sort by pages, not just records within a page. Signed-off-by: Steven Rostedt --- include/asm-generic/vmlinux.lds.h | 2 +- kernel/trace/ftrace.c | 34 ++++++++++++++++++++++------------ 2 files changed, 23 insertions(+), 13 deletions(-) (limited to 'kernel/trace') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8aeadf6b553a..4e2e1cc505ab 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -486,8 +486,8 @@ CPU_DISCARD(init.data) \ MEM_DISCARD(init.data) \ KERNEL_CTORS() \ - *(.init.rodata) \ MCOUNT_REC() \ + *(.init.rodata) \ FTRACE_EVENTS() \ TRACE_SYSCALLS() \ DEV_DISCARD(init.rodata) \ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cf81f27ce6c6..53ed01ed7aa7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3666,15 +3666,27 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) return 0; } -static void ftrace_swap_recs(void *a, void *b, int size) +static int ftrace_cmp_ips(const void *a, const void *b) { - struct dyn_ftrace *reca = a; - struct dyn_ftrace *recb = b; - struct dyn_ftrace t; + const unsigned long *ipa = a; + const unsigned long *ipb = b; - t = *reca; - *reca = *recb; - *recb = t; + if (*ipa > *ipb) + return 1; + if (*ipa < *ipb) + return -1; + return 0; +} + +static void ftrace_swap_ips(void *a, void *b, int size) +{ + unsigned long *ipa = a; + unsigned long *ipb = b; + unsigned long t; + + t = *ipa; + *ipa = *ipb; + *ipb = t; } static int ftrace_process_locs(struct module *mod, @@ -3693,6 +3705,9 @@ static int ftrace_process_locs(struct module *mod, if (!count) return 0; + sort(start, count, sizeof(*start), + ftrace_cmp_ips, ftrace_swap_ips); + pg = ftrace_allocate_pages(count); if (!pg) return -ENOMEM; @@ -3740,11 +3755,6 @@ static int ftrace_process_locs(struct module *mod, /* These new locations need to be initialized */ ftrace_new_pgs = pg; - /* Make each individual set of pages sorted by ips */ - for (; pg; pg = pg->next) - sort(pg->records, pg->index, sizeof(struct dyn_ftrace), - ftrace_cmp_recs, ftrace_swap_recs); - /* * We only need to disable interrupts on start up * because we are modifying code that an interrupt -- cgit v1.3-8-gc7d7 From 706c81f87f84adbcf1f6553b9e6b69b3e28fc35a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 24 Apr 2012 23:45:26 -0400 Subject: ftrace: Remove extra helper functions The ftrace_record_ip() and ftrace_alloc_dyn_node() were from the time of the ftrace daemon. Although they were still used, they still make things a bit more complex than necessary. Move the code into the one function that uses it, and remove the helper functions. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 61 ++++++++++++++++++++------------------------------- 1 file changed, 24 insertions(+), 37 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 53ed01ed7aa7..e10f9e522c44 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1520,35 +1520,6 @@ static void ftrace_hash_rec_enable(struct ftrace_ops *ops, __ftrace_hash_rec_update(ops, filter_hash, 1); } -static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) -{ - if (ftrace_pages->index == ftrace_pages->size) { - /* We should have allocated enough */ - if (WARN_ON(!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; - - return rec; -} - static void print_ip_ins(const char *fmt, unsigned char *p) { int i; @@ -3693,7 +3664,9 @@ static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { + struct ftrace_page *start_pg; struct ftrace_page *pg; + struct dyn_ftrace *rec; unsigned long count; unsigned long *p; unsigned long addr; @@ -3708,8 +3681,8 @@ static int ftrace_process_locs(struct module *mod, sort(start, count, sizeof(*start), ftrace_cmp_ips, ftrace_swap_ips); - pg = ftrace_allocate_pages(count); - if (!pg) + start_pg = ftrace_allocate_pages(count); + if (!start_pg) return -ENOMEM; mutex_lock(&ftrace_lock); @@ -3722,7 +3695,7 @@ static int ftrace_process_locs(struct module *mod, if (!mod) { WARN_ON(ftrace_pages || ftrace_pages_start); /* First initialization */ - ftrace_pages = ftrace_pages_start = pg; + ftrace_pages = ftrace_pages_start = start_pg; } else { if (!ftrace_pages) goto out; @@ -3733,11 +3706,11 @@ static int ftrace_process_locs(struct module *mod, ftrace_pages = ftrace_pages->next; } - ftrace_pages->next = pg; - ftrace_pages = pg; + ftrace_pages->next = start_pg; } p = start; + pg = start_pg; while (p < end) { addr = ftrace_call_adjust(*p++); /* @@ -3748,12 +3721,26 @@ static int ftrace_process_locs(struct module *mod, */ if (!addr) continue; - if (!ftrace_record_ip(addr)) - break; + + if (pg->index == pg->size) { + /* We should have allocated enough */ + if (WARN_ON(!pg->next)) + break; + pg = pg->next; + } + + rec = &pg->records[pg->index++]; + rec->ip = addr; } + /* We should have used all pages */ + WARN_ON(pg->next); + + /* Assign the last page to ftrace_pages */ + ftrace_pages = pg; + /* These new locations need to be initialized */ - ftrace_new_pgs = pg; + ftrace_new_pgs = start_pg; /* * We only need to disable interrupts on start up -- cgit v1.3-8-gc7d7 From 9644302e3315e7e36495d230d5ac7125a316d33e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 Apr 2012 10:14:43 -0400 Subject: ftrace: Speed up search by skipping pages by address As all records in a page of the ftrace table are sorted, we can speed up the search algorithm by checking if the address to look for falls in between the first and last record ip on the page. This speeds up both the ftrace_location() and ftrace_text_reserved() algorithms, as it can skip full pages when the search address is not in them. Cc: Masami Hiramatsu Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e10f9e522c44..fc93562a6654 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1411,6 +1411,8 @@ int ftrace_location(unsigned long ip) key.ip = ip; for (pg = ftrace_pages_start; pg; pg = pg->next) { + if (ip < pg->records[0].ip || ip > pg->records[pg->index - 1].ip) + continue; rec = bsearch(&key, pg->records, pg->index, sizeof(struct dyn_ftrace), ftrace_cmp_recs); @@ -1571,16 +1573,24 @@ void ftrace_bug(int failed, unsigned long ip) /* Return 1 if the address range is reserved for ftrace */ -int ftrace_text_reserved(void *start, void *end) +int ftrace_text_reserved(void *s, void *e) { struct dyn_ftrace *rec; struct ftrace_page *pg; + unsigned long start = (unsigned long)s; + unsigned long end = (unsigned long)e; + int i; - do_for_each_ftrace_rec(pg, rec) { - if (rec->ip <= (unsigned long)end && - rec->ip + MCOUNT_INSN_SIZE > (unsigned long)start) - return 1; - } while_for_each_ftrace_rec(); + for (pg = ftrace_pages_start; pg; pg = pg->next) { + if (end < pg->records[0].ip || + start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) + continue; + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + if (rec->ip <= end && rec->ip + MCOUNT_INSN_SIZE > start) + return 1; + } + } return 0; } -- cgit v1.3-8-gc7d7 From a650e02a528ab9d6d6f0b8b57745c32f2a138459 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 Apr 2012 13:48:13 -0400 Subject: ftrace: Consolidate ftrace_location() and ftrace_text_reserved() Both ftrace_location() and ftrace_text_reserved() do basically the same thing. They search to see if an address is in the ftace table (contains an address that may change from nop to call ftrace_caller). The difference is that ftrace_location() searches a single address, but ftrace_text_reserved() searches a range. This also makes the ftrace_text_reserved() faster as it now uses a bsearch() instead of linearly searching all the addresses within a page. Cc: Masami Hiramatsu Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 80 +++++++++++++++++++++++++-------------------------- 1 file changed, 40 insertions(+), 40 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fc93562a6654..dd091c84b57f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1383,35 +1383,28 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) static int ftrace_cmp_recs(const void *a, const void *b) { - const struct dyn_ftrace *reca = a; - const struct dyn_ftrace *recb = b; + const struct dyn_ftrace *key = a; + const struct dyn_ftrace *rec = b; - if (reca->ip > recb->ip) - return 1; - if (reca->ip < recb->ip) + if (key->flags < rec->ip) return -1; + if (key->ip >= rec->ip + MCOUNT_INSN_SIZE) + return 1; return 0; } -/** - * ftrace_location - return true if the ip giving is a traced location - * @ip: the instruction pointer to check - * - * Returns 1 if @ip given is a pointer to a ftrace location. - * That is, the instruction that is either a NOP or call to - * the function tracer. It checks the ftrace internal tables to - * determine if the address belongs or not. - */ -int ftrace_location(unsigned long ip) +static int ftrace_location_range(unsigned long start, unsigned long end) { struct ftrace_page *pg; struct dyn_ftrace *rec; struct dyn_ftrace key; - key.ip = ip; + key.ip = start; + key.flags = end; /* overload flags, as it is unsigned long */ for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (ip < pg->records[0].ip || ip > pg->records[pg->index - 1].ip) + if (end < pg->records[0].ip || + start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) continue; rec = bsearch(&key, pg->records, pg->index, sizeof(struct dyn_ftrace), @@ -1423,6 +1416,36 @@ int ftrace_location(unsigned long ip) return 0; } +/** + * ftrace_location - return true if the ip giving is a traced location + * @ip: the instruction pointer to check + * + * Returns 1 if @ip given is a pointer to a ftrace location. + * That is, the instruction that is either a NOP or call to + * the function tracer. It checks the ftrace internal tables to + * determine if the address belongs or not. + */ +int ftrace_location(unsigned long ip) +{ + return ftrace_location_range(ip, ip); +} + +/** + * ftrace_text_reserved - return true if range contains an ftrace location + * @start: start of range to search + * @end: end of range to search (inclusive). @end points to the last byte to check. + * + * Returns 1 if @start and @end contains a ftrace location. + * That is, the instruction that is either a NOP or call to + * the function tracer. It checks the ftrace internal tables to + * determine if the address belongs or not. + */ +int ftrace_text_reserved(void *start, void *end) +{ + return ftrace_location_range((unsigned long)start, + (unsigned long)end); +} + static void __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1571,29 +1594,6 @@ void ftrace_bug(int failed, unsigned long ip) } } - -/* Return 1 if the address range is reserved for ftrace */ -int ftrace_text_reserved(void *s, void *e) -{ - struct dyn_ftrace *rec; - struct ftrace_page *pg; - unsigned long start = (unsigned long)s; - unsigned long end = (unsigned long)e; - int i; - - for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (end < pg->records[0].ip || - start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) - continue; - for (i = 0; i < pg->index; i++) { - rec = &pg->records[i]; - if (rec->ip <= end && rec->ip + MCOUNT_INSN_SIZE > start) - return 1; - } - } - return 0; -} - static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) { unsigned long flag = 0UL; -- cgit v1.3-8-gc7d7 From f0cf973a224a3e3c1dec3395af3ba01cf14b1ff4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 Apr 2012 14:39:54 -0400 Subject: ftrace: Return record ip addr for ftrace_location() ftrace_location() is passed an addr, and returns 1 if the addr is on a ftrace nop (or caller to ftrace_caller), and 0 otherwise. To let kprobes know if it should move a breakpoint or not, it must return the actual addr that is the start of the ftrace nop. This way a kprobe placed on the location of a ftrace nop, can instead be placed on the instruction after the nop. Even if the probe addr is on the second or later byte of the nop, it can simply be moved forward. Cc: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 +- kernel/trace/ftrace.c | 16 ++++++++++------ 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index d32cc5e4b0cc..609948eb2b0a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -295,7 +295,7 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter); int ftrace_update_record(struct dyn_ftrace *rec, int enable); int ftrace_test_record(struct dyn_ftrace *rec, int enable); void ftrace_run_stop_machine(int command); -int ftrace_location(unsigned long ip); +unsigned long ftrace_location(unsigned long ip); extern ftrace_func_t ftrace_trace_function; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index dd091c84b57f..ef0826204840 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1393,7 +1393,7 @@ static int ftrace_cmp_recs(const void *a, const void *b) return 0; } -static int ftrace_location_range(unsigned long start, unsigned long end) +static unsigned long ftrace_location_range(unsigned long start, unsigned long end) { struct ftrace_page *pg; struct dyn_ftrace *rec; @@ -1410,7 +1410,7 @@ static int ftrace_location_range(unsigned long start, unsigned long end) sizeof(struct dyn_ftrace), ftrace_cmp_recs); if (rec) - return 1; + return rec->ip; } return 0; @@ -1420,12 +1420,12 @@ static int ftrace_location_range(unsigned long start, unsigned long end) * ftrace_location - return true if the ip giving is a traced location * @ip: the instruction pointer to check * - * Returns 1 if @ip given is a pointer to a ftrace location. + * Returns rec->ip if @ip given is a pointer to a ftrace location. * That is, the instruction that is either a NOP or call to * the function tracer. It checks the ftrace internal tables to * determine if the address belongs or not. */ -int ftrace_location(unsigned long ip) +unsigned long ftrace_location(unsigned long ip) { return ftrace_location_range(ip, ip); } @@ -1442,8 +1442,12 @@ int ftrace_location(unsigned long ip) */ int ftrace_text_reserved(void *start, void *end) { - return ftrace_location_range((unsigned long)start, - (unsigned long)end); + unsigned long ret; + + ret = ftrace_location_range((unsigned long)start, + (unsigned long)end); + + return (int)!!ret; } static void __ftrace_hash_rec_update(struct ftrace_ops *ops, -- cgit v1.3-8-gc7d7 From 8ed3e2cfe40ffe43630fd8efa34fc97c95b4c298 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 26 Apr 2012 14:59:43 -0400 Subject: ftrace: Make ftrace_modify_all_code() global for archs to use Rename __ftrace_modify_code() to ftrace_modify_all_code() and make it global for all archs to use. This will remove the duplication of code, as archs that can modify code without stop_machine() can use it directly outside of the stop_machine() call. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 ++ kernel/trace/ftrace.c | 21 +++++++++++++-------- 2 files changed, 15 insertions(+), 8 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 609948eb2b0a..cd72ace7ade3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -319,6 +319,8 @@ extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); +void ftrace_modify_all_code(int command); + #ifndef FTRACE_ADDR #define FTRACE_ADDR ((unsigned long)ftrace_caller) #endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ef0826204840..3c345825cc23 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1811,22 +1811,27 @@ int __weak ftrace_arch_code_modify_post_process(void) return 0; } -static int __ftrace_modify_code(void *data) +void ftrace_modify_all_code(int command) { - int *command = data; - - if (*command & FTRACE_UPDATE_CALLS) + if (command & FTRACE_UPDATE_CALLS) ftrace_replace_code(1); - else if (*command & FTRACE_DISABLE_CALLS) + else if (command & FTRACE_DISABLE_CALLS) ftrace_replace_code(0); - if (*command & FTRACE_UPDATE_TRACE_FUNC) + if (command & FTRACE_UPDATE_TRACE_FUNC) ftrace_update_ftrace_func(ftrace_trace_function); - if (*command & FTRACE_START_FUNC_RET) + if (command & FTRACE_START_FUNC_RET) ftrace_enable_ftrace_graph_caller(); - else if (*command & FTRACE_STOP_FUNC_RET) + else if (command & FTRACE_STOP_FUNC_RET) ftrace_disable_ftrace_graph_caller(); +} + +static int __ftrace_modify_code(void *data) +{ + int *command = data; + + ftrace_modify_all_code(*command); return 0; } -- cgit v1.3-8-gc7d7 From e4f5d5440bb860a3e8942ca8f7277a7f31798965 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 27 Apr 2012 09:13:18 -0400 Subject: ftrace/x86: Have x86 ftrace use the ftrace_modify_all_code() To remove duplicate code, have the ftrace arch_ftrace_update_code() use the generic ftrace_modify_all_code(). This requires that the default ftrace_replace_code() becomes a weak function so that an arch may override it. Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 15 ++------------- include/linux/ftrace.h | 1 + kernel/trace/ftrace.c | 4 ++-- 3 files changed, 5 insertions(+), 15 deletions(-) (limited to 'kernel/trace') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4243e8bbdcb1..32ff36596ab1 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -435,7 +435,7 @@ static void run_sync(void) local_irq_disable(); } -static void ftrace_replace_code(int enable) +void ftrace_replace_code(int enable) { struct ftrace_rec_iter *iter; struct dyn_ftrace *rec; @@ -493,18 +493,7 @@ void arch_ftrace_update_code(int command) { modifying_ftrace_code++; - if (command & FTRACE_UPDATE_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(); + ftrace_modify_all_code(command); modifying_ftrace_code--; } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index cd72ace7ade3..55e6d63d46d0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -314,6 +314,7 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable); /* defined in arch */ extern int ftrace_ip_converted(unsigned long ip); extern int ftrace_dyn_arch_init(void *data); +extern void ftrace_replace_code(int enable); extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3c345825cc23..a008663d86c8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1683,7 +1683,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) return -1; /* unknow ftrace bug */ } -static void ftrace_replace_code(int update) +void __weak ftrace_replace_code(int enable) { struct dyn_ftrace *rec; struct ftrace_page *pg; @@ -1693,7 +1693,7 @@ static void ftrace_replace_code(int update) return; do_for_each_ftrace_rec(pg, rec) { - failed = __ftrace_replace_code(rec, update); + failed = __ftrace_replace_code(rec, enable); if (failed) { ftrace_bug(failed, rec->ip); /* Stop processing */ -- cgit v1.3-8-gc7d7 From b732d439cb43336cd6d7e804ecb2c81193ef63b0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 30 Apr 2012 09:17:03 -0400 Subject: ftrace: Remove selecting FRAME_POINTER with FUNCTION_TRACER The function tracer will enable the -pg option with gcc, which requires that frame pointers. When FRAME_POINTER is defined in the kernel config it adds the gcc option -fno-omit-frame-pointer which causes some problems on some architectures. For those architectures, the FRAME_POINTER select was not set. When FUNCTION_TRACER was selected on these architectures that can not have -fno-omit-frame-pointer, the -pg option is still set. But when FRAME_POINTER is not selected, the kernel config would add the gcc option -fomit-frame-pointer. Adding this option is incompatible with -pg even on archs that do not need frame pointers with -pg. The answer to this was to just not add either -fno-omit-frame-pointer or -fomit-frame-pointer on these archs that want function tracing but do not set FRAME_POINTER. As it turns out, for archs that require frame pointers for function tracing, the same can be used. If gcc requires frame pointers with -pg, it will simply add it. The best thing to do is not select FRAME_POINTER when function tracing is selected, and let gcc add it if needed. Only add the -fno-omit-frame-pointer when something else selects FRAME_POINTER, but do not add -fomit-frame-pointer if function tracing is selected. Signed-off-by: Steven Rostedt --- kernel/trace/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a1d2849f2473..d81a1a532994 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,6 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER -- cgit v1.3-8-gc7d7 From 05fdd70d2fe1e34d8b80ec56d6e3272d9293653e Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Fri, 18 May 2012 13:29:51 -0700 Subject: ring-buffer: Merge separate resize loops There are 2 separate loops to resize cpu buffers that are online and offline. Merge them to make the code look better. Also change the name from update_completion to update_done to allow shorter lines. Link: http://lkml.kernel.org/r/1337372991-14783-1-git-send-email-vnagarnaik@google.com Cc: Laurent Chavey Cc: Justin Teravest Cc: David Sharp Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 41 +++++++++++++++-------------------------- 1 file changed, 15 insertions(+), 26 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 68388f876d43..6420cda62336 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -473,7 +473,7 @@ struct ring_buffer_per_cpu { int nr_pages_to_update; struct list_head new_pages; /* new pages to add */ struct work_struct update_pages_work; - struct completion update_completion; + struct completion update_done; }; struct ring_buffer { @@ -1058,7 +1058,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler); - init_completion(&cpu_buffer->update_completion); + init_completion(&cpu_buffer->update_done); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1461,7 +1461,7 @@ static void update_pages_handler(struct work_struct *work) struct ring_buffer_per_cpu *cpu_buffer = container_of(work, struct ring_buffer_per_cpu, update_pages_work); rb_update_pages(cpu_buffer); - complete(&cpu_buffer->update_completion); + complete(&cpu_buffer->update_done); } /** @@ -1534,39 +1534,29 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, get_online_cpus(); /* * Fire off all the required work handlers - * Look out for offline CPUs - */ - for_each_buffer_cpu(buffer, cpu) { - cpu_buffer = buffer->buffers[cpu]; - if (!cpu_buffer->nr_pages_to_update || - !cpu_online(cpu)) - continue; - - schedule_work_on(cpu, &cpu_buffer->update_pages_work); - } - /* - * This loop is for the CPUs that are not online. - * We can't schedule anything on them, but it's not necessary + * We can't schedule on offline CPUs, but it's not necessary * since we can change their buffer sizes without any race. */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - if (!cpu_buffer->nr_pages_to_update || - cpu_online(cpu)) + if (!cpu_buffer->nr_pages_to_update) continue; - rb_update_pages(cpu_buffer); + if (cpu_online(cpu)) + schedule_work_on(cpu, + &cpu_buffer->update_pages_work); + else + rb_update_pages(cpu_buffer); } /* wait for all the updates to complete */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - if (!cpu_buffer->nr_pages_to_update || - !cpu_online(cpu)) + if (!cpu_buffer->nr_pages_to_update) continue; - wait_for_completion(&cpu_buffer->update_completion); - /* reset this value */ + if (cpu_online(cpu)) + wait_for_completion(&cpu_buffer->update_done); cpu_buffer->nr_pages_to_update = 0; } @@ -1593,13 +1583,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, if (cpu_online(cpu_id)) { schedule_work_on(cpu_id, &cpu_buffer->update_pages_work); - wait_for_completion(&cpu_buffer->update_completion); + wait_for_completion(&cpu_buffer->update_done); } else rb_update_pages(cpu_buffer); - put_online_cpus(); - /* reset this value */ cpu_buffer->nr_pages_to_update = 0; + put_online_cpus(); } out: -- cgit v1.3-8-gc7d7 From a591c73f127505cdbd0aa399a92112a8ddff8730 Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Thu, 3 May 2012 10:40:34 -0700 Subject: tracing: Fix initial buffer_size_kb state Make sure that the state of buffer_size_kb is initialized correctly and returns actual size of the ring buffer. Link: http://lkml.kernel.org/r/1336066834-1673-1-git-send-email-vnagarnaik@google.com Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Laurent Chavey Cc: Justin Teravest Cc: David Sharp Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 08a08bab57a3..a44d4c6ca9a8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5112,7 +5112,8 @@ __init static int tracer_alloc_buffers(void) max_tr.data[i] = &per_cpu(max_tr_data, i); } - set_buffer_entries(&global_trace, ring_buf_size); + set_buffer_entries(&global_trace, + ring_buffer_size(global_trace.buffer, 0)); #ifdef CONFIG_TRACER_MAX_TRACE set_buffer_entries(&max_tr, 1); #endif -- cgit v1.3-8-gc7d7 From 895b67fd5830ce18a6f1375a7c062fcf84b4b874 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Mon, 7 Nov 2011 09:23:22 +0100 Subject: tracing: Remove kernel_lock annotations The BKL is gone, these annotations are useless. Link: http://lkml.kernel.org/r/1320654202-4433-1-git-send-email-richard@nod.at Signed-off-by: Richard Weinberger Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a44d4c6ca9a8..b9a507c19c4b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -763,8 +763,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * Register a new plugin tracer. */ int register_tracer(struct tracer *type) -__releases(kernel_lock) -__acquires(kernel_lock) { struct tracer *t; int ret = 0; -- cgit v1.3-8-gc7d7 From 6a31e1f135d1abfb5137697f889c8cd5d72eb522 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 23 May 2012 15:35:17 -0400 Subject: ring-buffer: Check for valid buffer before changing size On some machines the number of possible CPUS is not the same as the number of CPUs that is on the machine. Ftrace uses possible_cpus to update the tracing structures but the ring buffer only allocates per cpu buffers for online CPUs when they come up. When the wakeup tracer was enabled in such a case, the ftrace code enabled all possible cpu buffers, but the code in ring_buffer_resize() did not check to see if the buffer in question was allocated. Since boot up CPUs did not match possible CPUs it caused the following crash: BUG: unable to handle kernel NULL pointer dereference at 00000020 IP: [] ring_buffer_resize+0x16a/0x28d *pde = 00000000 Oops: 0000 [#1] PREEMPT SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: [last unloaded: scsi_wait_scan] Pid: 1387, comm: bash Not tainted 3.4.0-test+ #13 /DG965MQ EIP: 0060:[] EFLAGS: 00010217 CPU: 0 EIP is at ring_buffer_resize+0x16a/0x28d EAX: f5a14340 EBX: f6026b80 ECX: 00000ff4 EDX: 00000ff3 ESI: 00000000 EDI: 00000002 EBP: f4275ecc ESP: f4275eb0 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 80050033 CR2: 00000020 CR3: 34396000 CR4: 000007d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: ffff0ff0 DR7: 00000400 Process bash (pid: 1387, ti=f4274000 task=f4380cb0 task.ti=f4274000) Stack: c109cf9a f6026b98 00000162 00160f68 00000006 00160f68 00000002 f4275ef0 c109d013 f4275ee8 c123b72a c1c0bf00 c1cc81dc 00000005 f4275f98 00000007 f4275f70 c109d0c7 7700000e 75656b61 00000070 f5e90900 f5c4e198 00000301 Call Trace: [] ? tracing_set_tracer+0x115/0x1e9 [] tracing_set_tracer+0x18e/0x1e9 [] ? _copy_from_user+0x30/0x46 [] tracing_set_trace_write+0x59/0x7f [] ? fput+0x18/0x1c6 [] ? security_file_permission+0x27/0x2b [] ? rw_verify_area+0xcf/0xf2 [] ? fput+0x18/0x1c6 [] ? tracing_set_tracer+0x1e9/0x1e9 [] vfs_write+0x8b/0xe3 [] ? fget_light+0x30/0x81 [] sys_write+0x42/0x63 [] sysenter_do_call+0x12/0x28 This happens with the latency tracer as the ftrace code updates the saved max buffer via its cpumask and not with a global setting. Adding a check in ring_buffer_resize() to make sure the buffer being resized exists, fixes the problem. Cc: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6420cda62336..1d0f6a8a0e5e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1486,6 +1486,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, if (!buffer) return size; + /* Make sure the requested buffer exists */ + if (cpu_id != RING_BUFFER_ALL_CPUS && + !cpumask_test_cpu(cpu_id, buffer->cpumask)) + return size; + size = DIV_ROUND_UP(size, BUF_PAGE_SIZE); size *= BUF_PAGE_SIZE; -- cgit v1.3-8-gc7d7