From a358324466b171e145df20bdb74fe81759906de6 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 11 Nov 2008 15:01:42 -0500 Subject: ring-buffer: buffer record on/off switch Impact: enable/disable ring buffer recording API added Several kernel developers have requested that there be a way to stop recording into the ring buffers with a simple switch that can also be enabled from userspace. This patch addes a new kernel API to the ring buffers called: tracing_on() tracing_off() When tracing_off() is called, all ring buffers will not be able to record into their buffers. tracing_on() will enable the ring buffers again. These two act like an on/off switch. That is, there is no counting of the number of times tracing_off or tracing_on has been called. A new file is added to the debugfs/tracing directory called tracing_on This allows for userspace applications to also flip the switch. echo 0 > debugfs/tracing/tracing_on disables the tracing. echo 1 > /debugfs/tracing/tracing_on enables it. Note, this does not disable or enable any tracers. It only sets or clears a flag that needs to be set in order for the ring buffers to write to their buffers. It is a global flag, and affects all ring buffers. The buffers start out with tracing_on enabled. There are now three flags that control recording into the buffers: tracing_on: which affects all ring buffer tracers. buffer->record_disabled: which affects an allocated buffer, which may be set if an anomaly is detected, and tracing is disabled. cpu_buffer->record_disabled: which is set by tracing_stop() or if an anomaly is detected. tracing_start can not reenable this if an anomaly occurred. The userspace debugfs/tracing/tracing_enabled is implemented with tracing_stop() but the user space code can not enable it if the kernel called tracing_stop(). Userspace can enable the tracing_on even if the kernel disabled it. It is just a switch used to stop tracing if a condition was hit. tracing_on is not for protecting critical areas in the kernel nor is it for stopping tracing if an anomaly occurred. This is because userspace can reenable it at any time. Side effect: With this patch, I discovered a dead variable in ftrace.c called tracing_on. This patch removes it. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 8 +--- kernel/trace/ring_buffer.c | 101 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 103 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4a39d24568c8..14fa52297b28 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -185,7 +185,6 @@ enum { }; static int ftrace_filtered; -static int tracing_on; static LIST_HEAD(ftrace_new_addrs); @@ -506,13 +505,10 @@ static int __ftrace_modify_code(void *data) { int *command = data; - if (*command & FTRACE_ENABLE_CALLS) { + if (*command & FTRACE_ENABLE_CALLS) ftrace_replace_code(1); - tracing_on = 1; - } else if (*command & FTRACE_DISABLE_CALLS) { + else if (*command & FTRACE_DISABLE_CALLS) ftrace_replace_code(0); - tracing_on = 0; - } if (*command & FTRACE_UPDATE_TRACE_FUNC) ftrace_update_ftrace_func(ftrace_trace_function); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2f76193c3489..b08ee9f00c8d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -16,6 +16,35 @@ #include #include +#include "trace.h" + +/* Global flag to disable all recording to ring buffers */ +static int ring_buffers_off __read_mostly; + +/** + * tracing_on - enable all tracing buffers + * + * This function enables all tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + ring_buffers_off = 0; +} + +/** + * 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) +{ + ring_buffers_off = 1; +} + /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 @@ -1133,6 +1162,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, struct ring_buffer_event *event; int cpu, resched; + if (ring_buffers_off) + return NULL; + if (atomic_read(&buffer->record_disabled)) return NULL; @@ -1249,6 +1281,9 @@ int ring_buffer_write(struct ring_buffer *buffer, int ret = -EBUSY; int cpu, resched; + if (ring_buffers_off) + return -EBUSY; + if (atomic_read(&buffer->record_disabled)) return -EBUSY; @@ -2070,3 +2105,69 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, return 0; } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + int *p = filp->private_data; + char buf[64]; + int r; + + /* !ring_buffers_off == tracing_on */ + r = sprintf(buf, "%d\n", !*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) +{ + int *p = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + /* !ring_buffers_off == tracing_on */ + *p = !val; + + (*ppos)++; + + return cnt; +} + +static struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, +}; + + +static __init int rb_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("tracing_on", 0644, d_tracer, + &ring_buffers_off, &rb_simple_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_on' entry\n"); + + return 0; +} + +fs_initcall(rb_init_debugfs); -- cgit v1.2.3-58-ga151 From 47e74f2ba8fbf9fb1378e2524e6cfdc2fb37f160 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 12 Nov 2008 00:01:27 -0500 Subject: ring-buffer: no preempt for sched_clock() Impact: disable preemption when calling sched_clock() The ring_buffer_time_stamp still uses sched_clock as its counter. But it is a bug to call it with preemption enabled. This requirement should not be pushed to the ring_buffer_time_stamp callers, so the ring_buffer_time_stamp needs to disable preemption when calling sched_clock. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/ring_buffer.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b08ee9f00c8d..231db209fa82 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -51,8 +51,14 @@ void tracing_off(void) /* FIXME!!! */ u64 ring_buffer_time_stamp(int cpu) { + u64 time; + + preempt_disable_notrace(); /* shift to debug/test normalization and TIME_EXTENTS */ - return sched_clock() << DEBUG_SHIFT; + time = sched_clock() << DEBUG_SHIFT; + preempt_enable_notrace(); + + return time; } void ring_buffer_normalize_time_stamp(int cpu, u64 *ts) -- cgit v1.2.3-58-ga151 From ee51a1de7e3837577412be269e0100038068e691 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 13 Nov 2008 14:58:31 +0100 Subject: tracing: fix mmiotrace resizing crash Pekka reported a crash when resizing the mmiotrace tracer (if only mmiotrace is enabled). This happens because in that case we do not allocate the max buffer, but we try to use it. Make ring_buffer_resize() idempotent against NULL buffers. Reported-by: Pekka Paalanen Signed-off-by: Ingo Molnar --- kernel/trace/ring_buffer.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 231db209fa82..036456cbb4f7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -538,6 +538,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) LIST_HEAD(pages); int i, cpu; + /* + * Always succeed at resizing a non-existent buffer: + */ + if (!buffer) + return size; + size = DIV_ROUND_UP(size, BUF_PAGE_SIZE); size *= BUF_PAGE_SIZE; buffer_size = buffer->pages * BUF_PAGE_SIZE; -- cgit v1.2.3-58-ga151 From 5821e1b74f0d08952cb5da4bfd2d9a388d8df58e Mon Sep 17 00:00:00 2001 From: walimis Date: Sat, 15 Nov 2008 15:19:06 +0800 Subject: function tracing: fix wrong pos computing when read buffer has been fulfilled Impact: make output of available_filter_functions complete phenomenon: The first value of dyn_ftrace_total_info is not equal with `cat available_filter_functions | wc -l`, but they should be equal. root cause: When printing functions with seq_printf in t_show, if the read buffer is just overflowed by current function record, then this function won't be printed to user space through read buffer, it will just be dropped. So we can't see this function printing. So, every time the last function to fill the read buffer, if overflowed, will be dropped. This also applies to set_ftrace_filter if set_ftrace_filter has more bytes than read buffer. fix: Through checking return value of seq_printf, if less than 0, we know this function doesn't be printed. Then we decrease position to force this function to be printed next time, in next read buffer. Another little fix is to show correct allocating pages count. Signed-off-by: walimis Acked-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 14fa52297b28..e60205722d0c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -673,7 +673,7 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) cnt = num_to_init / ENTRIES_PER_PAGE; pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt); + num_to_init, cnt + 1); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -753,13 +753,11 @@ static void *t_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l = -1; - if (*pos != iter->pos) { - for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) - ; - } else { - l = *pos; - p = t_next(m, p, &l); - } + if (*pos > iter->pos) + *pos = iter->pos; + + l = *pos; + p = t_next(m, p, &l); return p; } @@ -770,15 +768,21 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; if (!rec) return 0; kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - seq_printf(m, "%s\n", str); + ret = seq_printf(m, "%s\n", str); + if (ret < 0) { + iter->pos--; + iter->idx--; + } return 0; } @@ -804,7 +808,7 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -891,7 +895,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; iter->flags = enable ? FTRACE_ITER_FILTER : FTRACE_ITER_NOTRACE; -- cgit v1.2.3-58-ga151 From e270219f4372b58bd3eeac12bd9f7edc592b8f6b Mon Sep 17 00:00:00 2001 From: Rakib Mullick Date: Tue, 18 Nov 2008 10:15:24 +0600 Subject: kernel/profile.c: fix section mismatch warning Impact: fix section mismatch warning in kernel/profile.c Here, profile_nop function has been called from a non-init function create_hash_tables(void). Which generetes a section mismatch warning. Previously, create_hash_tables(void) was a init function. So, removing __init from create_hash_tables(void) requires profile_nop to be non-init. This patch makes profile_nop function inline and fixes the following warning: WARNING: vmlinux.o(.text+0x6ebb6): Section mismatch in reference from the function create_hash_tables() to the function .init.text:profile_nop() The function create_hash_tables() references the function __init profile_nop(). This is often because create_hash_tables lacks a __init annotation or the annotation of profile_nop is wrong. Signed-off-by: Rakib Mullick Signed-off-by: Ingo Molnar --- kernel/profile.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/profile.c b/kernel/profile.c index 9830a037d8db..5b7d1ac7124c 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = { }; #ifdef CONFIG_SMP -static void __init profile_nop(void *unused) +static inline void profile_nop(void *unused) { } -- cgit v1.2.3-58-ga151