From 2bccfffd1538f3523847583213567e2f7ce00926 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 9 Sep 2010 08:43:22 -0400 Subject: tracing: Do not reset *pos in set_ftrace_filter After the filtered functions are read, the probed functions are read from the hash in set_ftrace_filter. When the hashed probed functions are read, the *pos passed in is reset. Instead of modifying the pos given to the read function, just record the pos where the filtered functions ended and subtract from that. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fa7ece649fe1..585ea27025b1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1368,6 +1368,7 @@ enum { #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { + loff_t func_pos; struct ftrace_page *pg; int hidx; int idx; @@ -1418,12 +1419,15 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) loff_t l; if (!(iter->flags & FTRACE_ITER_HASH)) - *pos = 0; + iter->func_pos = *pos; + + if (iter->func_pos > *pos) + return NULL; iter->flags |= FTRACE_ITER_HASH; iter->hidx = 0; - for (l = 0; l <= *pos; ) { + for (l = 0; l <= (*pos - iter->func_pos); ) { p = t_hash_next(m, p, &l); if (!p) break; -- cgit v1.2.2 From 4aeb69672d011fac5c8df671f3ca89f7987c104e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 9 Sep 2010 10:00:28 -0400 Subject: tracing: Replace typecasted void pointer in set_ftrace_filter code The set_ftrace_filter uses seq_file and reads from two lists. The pointer returned by t_next() can either be of type struct dyn_ftrace or struct ftrace_func_probe. If there is a bug (there was one) the wrong pointer may be used and the reference can cause an oops. This patch makes t_next() and friends only return the iterator structure which now has a pointer of type struct dyn_ftrace and struct ftrace_func_probe. The t_show() can now test if the pointer is NULL or not and if the pointer exists, it is guaranteed to be of the correct type. Now if there's a bug, only wrong data will be shown but not an oops. Cc: Chris Wright Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 67 +++++++++++++++++++++++++++++++++++---------------- 1 file changed, 46 insertions(+), 21 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 585ea27025b1..c8db0dbb984e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1368,25 +1368,29 @@ enum { #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { - loff_t func_pos; - struct ftrace_page *pg; - int hidx; - int idx; - unsigned flags; - struct trace_parser parser; + loff_t func_pos; + struct ftrace_page *pg; + struct dyn_ftrace *func; + struct ftrace_func_probe *probe; + struct trace_parser parser; + int hidx; + int idx; + unsigned flags; }; static void * -t_hash_next(struct seq_file *m, void *v, loff_t *pos) +t_hash_next(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; - struct hlist_node *hnd = v; + struct hlist_node *hnd = NULL; struct hlist_head *hhd; WARN_ON(!(iter->flags & FTRACE_ITER_HASH)); (*pos)++; + if (iter->probe) + hnd = &iter->probe->node; retry: if (iter->hidx >= FTRACE_FUNC_HASHSIZE) return NULL; @@ -1409,7 +1413,12 @@ t_hash_next(struct seq_file *m, void *v, loff_t *pos) } } - return hnd; + if (WARN_ON_ONCE(!hnd)) + return NULL; + + iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node); + + return iter; } static void *t_hash_start(struct seq_file *m, loff_t *pos) @@ -1428,19 +1437,24 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) iter->hidx = 0; for (l = 0; l <= (*pos - iter->func_pos); ) { - p = t_hash_next(m, p, &l); + p = t_hash_next(m, &l); if (!p) break; } - return p; + if (!p) + return NULL; + + return iter; } -static int t_hash_show(struct seq_file *m, void *v) +static int +t_hash_show(struct seq_file *m, struct ftrace_iterator *iter) { struct ftrace_func_probe *rec; - struct hlist_node *hnd = v; - rec = hlist_entry(hnd, struct ftrace_func_probe, node); + rec = iter->probe; + if (WARN_ON_ONCE(!rec)) + return -EIO; if (rec->ops->print) return rec->ops->print(m, rec->ip, rec->ops, rec->data); @@ -1461,7 +1475,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) struct dyn_ftrace *rec = NULL; if (iter->flags & FTRACE_ITER_HASH) - return t_hash_next(m, v, pos); + return t_hash_next(m, pos); (*pos)++; @@ -1495,7 +1509,12 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } } - return rec; + if (!rec) + return NULL; + + iter->func = rec; + + return iter; } static void *t_start(struct seq_file *m, loff_t *pos) @@ -1530,10 +1549,14 @@ static void *t_start(struct seq_file *m, loff_t *pos) break; } - if (!p && iter->flags & FTRACE_ITER_FILTER) - return t_hash_start(m, pos); + if (!p) { + if (iter->flags & FTRACE_ITER_FILTER) + return t_hash_start(m, pos); - return p; + return NULL; + } + + return iter; } static void t_stop(struct seq_file *m, void *p) @@ -1544,16 +1567,18 @@ 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; + struct dyn_ftrace *rec; if (iter->flags & FTRACE_ITER_HASH) - return t_hash_show(m, v); + return t_hash_show(m, iter); if (iter->flags & FTRACE_ITER_PRINTALL) { seq_printf(m, "#### all functions enabled ####\n"); return 0; } + rec = iter->func; + if (!rec) return 0; -- cgit v1.2.2 From 98c4fd046f07156ca6055677e8f03d4280be16c1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 10 Sep 2010 11:47:43 -0400 Subject: tracing: Keep track of set_ftrace_filter position and allow lseek again This patch keeps track of the index within the elements of set_ftrace_filter and if the position goes backwards, it nicely resets and starts from the beginning again. This allows for lseek and pread to work properly now. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c8db0dbb984e..2d51166b93fe 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1368,6 +1368,7 @@ enum { #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { + loff_t pos; loff_t func_pos; struct ftrace_page *pg; struct dyn_ftrace *func; @@ -1385,9 +1386,8 @@ t_hash_next(struct seq_file *m, loff_t *pos) struct hlist_node *hnd = NULL; struct hlist_head *hhd; - WARN_ON(!(iter->flags & FTRACE_ITER_HASH)); - (*pos)++; + iter->pos = *pos; if (iter->probe) hnd = &iter->probe->node; @@ -1427,14 +1427,9 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l; - if (!(iter->flags & FTRACE_ITER_HASH)) - iter->func_pos = *pos; - if (iter->func_pos > *pos) return NULL; - iter->flags |= FTRACE_ITER_HASH; - iter->hidx = 0; for (l = 0; l <= (*pos - iter->func_pos); ) { p = t_hash_next(m, &l); @@ -1444,6 +1439,9 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) if (!p) return NULL; + /* Only set this if we have an item */ + iter->flags |= FTRACE_ITER_HASH; + return iter; } @@ -1478,6 +1476,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) return t_hash_next(m, pos); (*pos)++; + iter->pos = *pos; + iter->func_pos = *pos; if (iter->flags & FTRACE_ITER_PRINTALL) return NULL; @@ -1517,6 +1517,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos) return iter; } +static void reset_iter_read(struct ftrace_iterator *iter) +{ + iter->pos = 0; + iter->func_pos = 0; + iter->flags &= ~(FTRACE_ITER_PRINTALL & FTRACE_ITER_HASH); +} + static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; @@ -1524,6 +1531,12 @@ static void *t_start(struct seq_file *m, loff_t *pos) loff_t l; mutex_lock(&ftrace_lock); + /* + * If an lseek was done, then reset and start from beginning. + */ + if (*pos < iter->pos) + reset_iter_read(iter); + /* * For set_ftrace_filter reading, if we have the filter * off, we can short cut and just print out that all @@ -1541,6 +1554,11 @@ static void *t_start(struct seq_file *m, loff_t *pos) if (iter->flags & FTRACE_ITER_HASH) return t_hash_start(m, pos); + /* + * Unfortunately, we need to restart at ftrace_pages_start + * every time we let go of the ftrace_mutex. This is because + * those pointers can change without the lock. + */ iter->pg = ftrace_pages_start; iter->idx = 0; for (l = 0; l <= *pos; ) { @@ -2447,7 +2465,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = no_llseek, + .llseek = ftrace_regex_lseek, .release = ftrace_filter_release, }; -- cgit v1.2.2 From 57c072c7113f54f9512624d6c665db6184448782 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 14 Sep 2010 11:21:11 -0400 Subject: tracing: Fix reading of set_ftrace_filter across lists If we do: # cd /sys/kernel/debug # echo 'do_IRQ:traceon schedule:traceon sys_write:traceon' > \ set_ftrace_filter # cat set_ftrace_filter We get the following output: #### all functions enabled #### sys_write:traceon:unlimited schedule:traceon:unlimited do_IRQ:traceon:unlimited This outputs two lists. One is the fact that all functions are currently enabled for function tracing, the other has three probed functions, which happen to have 'traceon' as their commands. Currently, when reading the first list (functions enabled) the seq_file code will receive a "NULL" from the t_next() function causing it to exit early. This makes "read()" from userspace stop reading the code at this boarder. Although read is allowed to do this, some (broken) applications might consider this an end of file and stop early. This patch adds the start of the second list to t_next() when it finishes the first list. It is a simple change and gives the set_ftrace_filter file nicer reading ability. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2d51166b93fe..1884cf5bc110 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1477,10 +1477,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) (*pos)++; iter->pos = *pos; - iter->func_pos = *pos; if (iter->flags & FTRACE_ITER_PRINTALL) - return NULL; + return t_hash_start(m, pos); retry: if (iter->idx >= iter->pg->index) { @@ -1510,8 +1509,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } if (!rec) - return NULL; + return t_hash_start(m, pos); + iter->func_pos = *pos; iter->func = rec; return iter; -- cgit v1.2.2 From 79e406d7b00ab2b261ae32a59f266fd3b7af6f29 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 14 Sep 2010 22:19:46 -0400 Subject: tracing: Remove leftover FTRACE_ENABLE/DISABLE_MCOUNT enums The enums for FTRACE_ENABLE_MCOUNT and FTRACE_DISABLE_MCOUNT were used as commands to ftrace_run_update_code(). But these commands were used by the old nasty ftrace daemon that has long been slain. This is a clean up patch to remove the references to these enums and simplify the code a little. Reported-by: Wu Zhangjin Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 83a16e9ee518..20aff3f1c719 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -884,10 +884,8 @@ enum { FTRACE_ENABLE_CALLS = (1 << 0), FTRACE_DISABLE_CALLS = (1 << 1), FTRACE_UPDATE_TRACE_FUNC = (1 << 2), - FTRACE_ENABLE_MCOUNT = (1 << 3), - FTRACE_DISABLE_MCOUNT = (1 << 4), - FTRACE_START_FUNC_RET = (1 << 5), - FTRACE_STOP_FUNC_RET = (1 << 6), + FTRACE_START_FUNC_RET = (1 << 3), + FTRACE_STOP_FUNC_RET = (1 << 4), }; static int ftrace_filtered; @@ -1226,8 +1224,6 @@ static void ftrace_shutdown(int command) static void ftrace_startup_sysctl(void) { - int command = FTRACE_ENABLE_MCOUNT; - if (unlikely(ftrace_disabled)) return; @@ -1235,23 +1231,17 @@ static void ftrace_startup_sysctl(void) saved_ftrace_func = NULL; /* ftrace_start_up is true if we want ftrace running */ if (ftrace_start_up) - command |= FTRACE_ENABLE_CALLS; - - ftrace_run_update_code(command); + ftrace_run_update_code(FTRACE_ENABLE_CALLS); } static void ftrace_shutdown_sysctl(void) { - int command = FTRACE_DISABLE_MCOUNT; - if (unlikely(ftrace_disabled)) return; /* ftrace_start_up is true if ftrace is running */ if (ftrace_start_up) - command |= FTRACE_DISABLE_CALLS; - - ftrace_run_update_code(command); + ftrace_run_update_code(FTRACE_DISABLE_CALLS); } static cycle_t ftrace_update_time; -- cgit v1.2.2 From 6038f373a3dc1f1c26496e60b6c40b164716f07e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 15 Aug 2010 18:52:59 +0200 Subject: llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann Cc: Julia Lawall Cc: Christoph Hellwig --- kernel/trace/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fa7ece649fe1..5e1ad4763090 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -800,6 +800,7 @@ static const struct file_operations ftrace_profile_fops = { .open = tracing_open_generic, .read = ftrace_profile_read, .write = ftrace_profile_write, + .llseek = default_llseek, }; /* used to initialize the real stat files */ @@ -2632,6 +2633,7 @@ static const struct file_operations ftrace_graph_fops = { .read = seq_read, .write = ftrace_graph_write, .release = ftrace_graph_release, + .llseek = seq_lseek, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -- cgit v1.2.2 From 907f27840985fe6a0c62e43cd4702c6e04b4bcc7 Mon Sep 17 00:00:00 2001 From: matt mooney Date: Mon, 27 Sep 2010 19:04:53 -0700 Subject: tracing/trivial: Remove cast from void* Unnecessary cast from void* in assignment. Signed-off-by: matt mooney Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 65fb077ea79c..ebd80d50c474 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1638,8 +1638,8 @@ ftrace_failures_open(struct inode *inode, struct file *file) ret = ftrace_avail_open(inode, file); if (!ret) { - m = (struct seq_file *)file->private_data; - iter = (struct ftrace_iterator *)m->private; + m = file->private_data; + iter = m->private; iter->flags = FTRACE_ITER_FAILURES; } -- cgit v1.2.2 From 868baf07b1a259f5f3803c1dc2777b6c358f83cf Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 10 Feb 2011 21:26:13 -0500 Subject: ftrace: Fix memory leak with function graph and cpu hotplug When the fuction graph tracer starts, it needs to make a special stack for each task to save the real return values of the tasks. All running tasks have this stack created, as well as any new tasks. On CPU hot plug, the new idle task will allocate a stack as well when init_idle() is called. The problem is that cpu hotplug does not create a new idle_task. Instead it uses the idle task that existed when the cpu went down. ftrace_graph_init_task() will add a new ret_stack to the task that is given to it. Because a clone will make the task have a stack of its parent it does not check if the task's ret_stack is already NULL or not. When the CPU hotplug code starts a CPU up again, it will allocate a new stack even though one already existed for it. The solution is to treat the idle_task specially. In fact, the function_graph code already does, just not at init_idle(). Instead of using the ftrace_graph_init_task() for the idle task, which that function expects the task to be a clone, have a separate ftrace_graph_init_idle_task(). Also, we will create a per_cpu ret_stack that is used by the idle task. When we call ftrace_graph_init_idle_task() it will check if the idle task's ret_stack is NULL, if it is, then it will assign it the per_cpu ret_stack. Reported-by: Benjamin Herrenschmidt Suggested-by: Peter Zijlstra Cc: Stable Tree Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 52 ++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 45 insertions(+), 7 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f3dadae83883..888b611897d3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3328,7 +3328,7 @@ static int start_graph_tracing(void) /* The cpu_boot init_task->ret_stack will never be freed */ for_each_online_cpu(cpu) { if (!idle_task(cpu)->ret_stack) - ftrace_graph_init_task(idle_task(cpu)); + ftrace_graph_init_idle_task(idle_task(cpu), cpu); } do { @@ -3418,6 +3418,49 @@ void unregister_ftrace_graph(void) mutex_unlock(&ftrace_lock); } +static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); + +static void +graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) +{ + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->ftrace_timestamp = 0; + /* make curr_ret_stack visable before we add the ret_stack */ + smp_wmb(); + t->ret_stack = ret_stack; +} + +/* + * Allocate a return stack for the idle task. May be the first + * time through, or it may be done by CPU hotplug online. + */ +void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) +{ + t->curr_ret_stack = -1; + /* + * The idle task has no parent, it either has its own + * stack or no stack at all. + */ + if (t->ret_stack) + WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu)); + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = per_cpu(idle_ret_stack, cpu); + if (!ret_stack) { + ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + per_cpu(idle_ret_stack, cpu) = ret_stack; + } + graph_init_task(t, ret_stack); + } +} + /* Allocate a return stack for newly created task */ void ftrace_graph_init_task(struct task_struct *t) { @@ -3433,12 +3476,7 @@ void ftrace_graph_init_task(struct task_struct *t) GFP_KERNEL); if (!ret_stack) return; - atomic_set(&t->tracing_graph_pause, 0); - atomic_set(&t->trace_overrun, 0); - t->ftrace_timestamp = 0; - /* make curr_ret_stack visable before we add the ret_stack */ - smp_wmb(); - t->ret_stack = ret_stack; + graph_init_task(t, ret_stack); } } -- cgit v1.2.2 From 1106b6997df7d0c0487e21fd9c9dd2ce3d4a52db Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Feb 2011 17:35:34 +0100 Subject: tracing: Fix set_ftrace_filter probe function display If one or more function probes (like traceon) are enabled, and there's no other function filter, the first probe func is skipped (which one depends on the position in the hash). $ echo sys_open:traceon sys_close:traceon > ./set_ftrace_filter $ cat set_ftrace_filter #### all functions enabled #### sys_close:traceon:unlimited $ The reason was, that in the case of no other function filter, the func_pos was not properly updated before calling t_hash_start. Signed-off-by: Jiri Olsa LKML-Reference: <1297874134-7008-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 888b611897d3..c075f4ea6b94 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1467,7 +1467,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) return t_hash_next(m, pos); (*pos)++; - iter->pos = *pos; + iter->pos = iter->func_pos = *pos; if (iter->flags & FTRACE_ITER_PRINTALL) return t_hash_start(m, pos); @@ -1502,7 +1502,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos) if (!rec) return t_hash_start(m, pos); - iter->func_pos = *pos; iter->func = rec; return iter; -- cgit v1.2.2 From 25985edcedea6396277003854657b5f3cb31a628 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 30 Mar 2011 22:57:33 -0300 Subject: Fix common misspellings Fixes generated by 'codespell' and manually reviewed. Signed-off-by: Lucas De Marchi --- kernel/trace/ftrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c075f4ea6b94..ee24fa1935ac 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1268,7 +1268,7 @@ static int ftrace_update_code(struct module *mod) p->flags = 0L; /* - * Do the initial record convertion from mcount jump + * Do the initial record conversion from mcount jump * to the NOP instructions. */ if (!ftrace_code_disable(mod, p)) { @@ -3425,7 +3425,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->ftrace_timestamp = 0; - /* make curr_ret_stack visable before we add the ret_stack */ + /* make curr_ret_stack visible before we add the ret_stack */ smp_wmb(); t->ret_stack = ret_stack; } -- cgit v1.2.2 From 058e297d34a404caaa5ed277de15698d8dc43000 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Apr 2011 22:35:33 -0400 Subject: ftrace: Only update the function code on write to filter files If function tracing is enabled, a read of the filter files will cause the call to stop_machine to update the function trace sites. It should only call stop_machine on write. Cc: stable@kernel.org Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ee24fa1935ac..666880d051ef 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2413,14 +2413,16 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) ftrace_match_records(parser->buffer, parser->idx, enable); } - mutex_lock(&ftrace_lock); - if (ftrace_start_up && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); - mutex_unlock(&ftrace_lock); - trace_parser_put(parser); kfree(iter); + if (file->f_mode & FMODE_WRITE) { + mutex_lock(&ftrace_lock); + if (ftrace_start_up && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + mutex_unlock(&ftrace_lock); + } + mutex_unlock(&ftrace_regex_lock); return 0; } -- cgit v1.2.2 From 0778d9ad33898faab7bf6316108b471790376e35 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Apr 2011 10:36:31 -0400 Subject: ftrace: Make FTRACE_WARN_ON() work in if condition Let FTRACE_WARN_ON() be used as a stand alone statement or inside a conditional: if (FTRACE_WARN_ON(x)) Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ee24fa1935ac..4ff65599c973 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -39,16 +39,20 @@ #include "trace_stat.h" #define FTRACE_WARN_ON(cond) \ - do { \ - if (WARN_ON(cond)) \ + ({ \ + int ___r = cond; \ + if (WARN_ON(___r)) \ ftrace_kill(); \ - } while (0) + ___r; \ + }) #define FTRACE_WARN_ON_ONCE(cond) \ - do { \ - if (WARN_ON_ONCE(cond)) \ + ({ \ + int ___r = cond; \ + if (WARN_ON_ONCE(___r)) \ ftrace_kill(); \ - } while (0) + ___r; \ + }) /* hash bits for specific function selection */ #define FTRACE_HASH_BITS 7 -- cgit v1.2.2 From 8ab2b7efd3e2ccf2c2dda3206b8171ecdbd0af40 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 21 Apr 2011 22:41:35 -0400 Subject: ftrace: Remove unnecessary disabling of irqs The disabling of interrupts around ftrace_update_code() was used to protect against the evil ftrace daemon from years past. But that daemon has long been killed. It is safe to keep interrupts enabled while updating the initial mcount into nops. The ftrace_mutex is also held which keeps other users at bay. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4ff65599c973..f199fb2e1d2c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2707,7 +2707,6 @@ static int ftrace_process_locs(struct module *mod, { unsigned long *p; unsigned long addr; - unsigned long flags; mutex_lock(&ftrace_lock); p = start; @@ -2724,10 +2723,7 @@ static int ftrace_process_locs(struct module *mod, ftrace_record_ip(addr); } - /* disable interrupts to prevent kstop machine */ - local_irq_save(flags); ftrace_update_code(mod); - local_irq_restore(flags); mutex_unlock(&ftrace_lock); return 0; -- cgit v1.2.2 From 3499e461147636bf55c41128d83b679ac6ab2d86 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 21 Apr 2011 22:59:12 -0400 Subject: ftrace: Remove failures file The failures file in the debugfs tracing directory would list the functions that failed to convert when the old dead ftrace daemon tried to update code but failed. Since this code is now dead along with the daemon the failures file is useless. Remove it. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 39 ++------------------------------------- 1 file changed, 2 insertions(+), 37 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f199fb2e1d2c..97b30f818642 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1355,9 +1355,8 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) enum { FTRACE_ITER_FILTER = (1 << 0), FTRACE_ITER_NOTRACE = (1 << 1), - FTRACE_ITER_FAILURES = (1 << 2), - FTRACE_ITER_PRINTALL = (1 << 3), - FTRACE_ITER_HASH = (1 << 4), + FTRACE_ITER_PRINTALL = (1 << 2), + FTRACE_ITER_HASH = (1 << 3), }; #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ @@ -1487,12 +1486,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos) rec = &iter->pg->records[iter->idx++]; if ((rec->flags & FTRACE_FL_FREE) || - (!(iter->flags & FTRACE_ITER_FAILURES) && - (rec->flags & FTRACE_FL_FAILED)) || - - ((iter->flags & FTRACE_ITER_FAILURES) && - !(rec->flags & FTRACE_FL_FAILED)) || - ((iter->flags & FTRACE_ITER_FILTER) && !(rec->flags & FTRACE_FL_FILTER)) || @@ -1633,24 +1626,6 @@ ftrace_avail_open(struct inode *inode, struct file *file) return ret; } -static int -ftrace_failures_open(struct inode *inode, struct file *file) -{ - int ret; - struct seq_file *m; - struct ftrace_iterator *iter; - - ret = ftrace_avail_open(inode, file); - if (!ret) { - m = file->private_data; - iter = m->private; - iter->flags = FTRACE_ITER_FAILURES; - } - - return ret; -} - - static void ftrace_filter_reset(int enable) { struct ftrace_page *pg; @@ -2448,13 +2423,6 @@ static const struct file_operations ftrace_avail_fops = { .release = seq_release_private, }; -static const struct file_operations ftrace_failures_fops = { - .open = ftrace_failures_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; - static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, @@ -2683,9 +2651,6 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) trace_create_file("available_filter_functions", 0444, d_tracer, NULL, &ftrace_avail_fops); - trace_create_file("failures", 0444, - d_tracer, NULL, &ftrace_failures_fops); - trace_create_file("set_ftrace_filter", 0644, d_tracer, NULL, &ftrace_filter_fops); -- cgit v1.2.2 From 45a4a2372b364107cabea79f255b333236626416 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 21 Apr 2011 23:16:46 -0400 Subject: ftrace: Remove FTRACE_FL_FAILED flag Since we disable all function tracer processing if we detect that a modification of a instruction had failed, we do not need to track that the record has failed. No more ftrace processing is allowed, and the FTRACE_FL_FAILED flag is pointless. Removing this flag simplifies some of the code, but some ftrace_disabled checks needed to be added or move around a little. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 76 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 47 insertions(+), 29 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 97b30f818642..eb19fae2c54a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1083,19 +1083,20 @@ static void ftrace_replace_code(int enable) struct ftrace_page *pg; int failed; + if (unlikely(ftrace_disabled)) + return; + do_for_each_ftrace_rec(pg, rec) { /* * Skip over free records, records that have * failed and not converted. */ if (rec->flags & FTRACE_FL_FREE || - rec->flags & FTRACE_FL_FAILED || !(rec->flags & FTRACE_FL_CONVERTED)) continue; failed = __ftrace_replace_code(rec, enable); if (failed) { - rec->flags |= FTRACE_FL_FAILED; ftrace_bug(failed, rec->ip); /* Stop processing */ return; @@ -1111,10 +1112,12 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) ip = rec->ip; + if (unlikely(ftrace_disabled)) + return 0; + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, ip); - rec->flags |= FTRACE_FL_FAILED; return 0; } return 1; @@ -1466,6 +1469,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = NULL; + if (unlikely(ftrace_disabled)) + return NULL; + if (iter->flags & FTRACE_ITER_HASH) return t_hash_next(m, pos); @@ -1518,6 +1524,10 @@ static void *t_start(struct seq_file *m, loff_t *pos) loff_t l; mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + return NULL; + /* * If an lseek was done, then reset and start from beginning. */ @@ -1636,8 +1646,6 @@ static void ftrace_filter_reset(int enable) if (enable) ftrace_filtered = 0; do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; rec->flags &= ~type; } while_for_each_ftrace_rec(); mutex_unlock(&ftrace_lock); @@ -1767,9 +1775,6 @@ static int ftrace_match_records(char *buff, int len, int enable) mutex_lock(&ftrace_lock); do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; - if (ftrace_match_record(rec, search, search_len, type)) { if (not) rec->flags &= ~flag; @@ -1837,10 +1842,11 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) } mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; + if (unlikely(ftrace_disabled)) + goto out_unlock; + + do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_module_record(rec, mod, search, search_len, type)) { @@ -1854,6 +1860,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) ftrace_filtered = 1; } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); return found; @@ -2008,10 +2015,11 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, return -EINVAL; mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; + if (unlikely(ftrace_disabled)) + goto out_unlock; + + do_for_each_ftrace_rec(pg, rec) { if (!ftrace_match_record(rec, search, len, type)) continue; @@ -2218,6 +2226,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, mutex_lock(&ftrace_regex_lock); + ret = -ENODEV; + if (unlikely(ftrace_disabled)) + goto out_unlock; + if (file->f_mode & FMODE_READ) { struct seq_file *m = file->private_data; iter = m->private; @@ -2545,9 +2557,6 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) bool exists; int i; - if (ftrace_disabled) - return -ENODEV; - /* decode regex */ type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS) @@ -2556,9 +2565,15 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) search_len = strlen(search); mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) { + mutex_unlock(&ftrace_lock); + return -ENODEV; + } + do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE)) + if (rec->flags & FTRACE_FL_FREE) continue; if (ftrace_match_record(rec, search, search_len, type)) { @@ -2700,10 +2715,11 @@ void ftrace_release_mod(struct module *mod) struct dyn_ftrace *rec; struct ftrace_page *pg; + mutex_lock(&ftrace_lock); + if (ftrace_disabled) - return; + goto out_unlock; - mutex_lock(&ftrace_lock); do_for_each_ftrace_rec(pg, rec) { if (within_module_core(rec->ip, mod)) { /* @@ -2714,6 +2730,7 @@ void ftrace_release_mod(struct module *mod) ftrace_free_rec(rec); } } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); } @@ -3108,16 +3125,17 @@ void ftrace_kill(void) */ int register_ftrace_function(struct ftrace_ops *ops) { - int ret; - - if (unlikely(ftrace_disabled)) - return -1; + int ret = -1; mutex_lock(&ftrace_lock); + if (unlikely(ftrace_disabled)) + goto out_unlock; + ret = __register_ftrace_function(ops); ftrace_startup(0); + out_unlock: mutex_unlock(&ftrace_lock); return ret; } @@ -3145,14 +3163,14 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; - - if (unlikely(ftrace_disabled)) - return -ENODEV; + int ret = -ENODEV; mutex_lock(&ftrace_lock); - ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (unlikely(ftrace_disabled)) + goto out; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; -- cgit v1.2.2 From d2c8c3eafbf715306ec891e7ca52d3d999acbe31 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 25 Apr 2011 14:32:42 -0400 Subject: ftrace: Remove FTRACE_FL_CONVERTED flag Since we disable all function tracer processing if we detect that a modification of a instruction had failed, we do not need to track that the record has failed. No more ftrace processing is allowed, and the FTRACE_FL_CONVERTED flag is pointless. The FTRACE_FL_CONVERTED flag was used to denote records that were successfully converted from mcount calls into nops. But if a single record fails, all of ftrace is disabled. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eb19fae2c54a..9abaaf46f212 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1087,12 +1087,8 @@ static void ftrace_replace_code(int enable) return; do_for_each_ftrace_rec(pg, rec) { - /* - * Skip over free records, records that have - * failed and not converted. - */ - if (rec->flags & FTRACE_FL_FREE || - !(rec->flags & FTRACE_FL_CONVERTED)) + /* Skip over free records */ + if (rec->flags & FTRACE_FL_FREE) continue; failed = __ftrace_replace_code(rec, enable); @@ -1280,10 +1276,10 @@ static int ftrace_update_code(struct module *mod) */ if (!ftrace_code_disable(mod, p)) { ftrace_free_rec(p); - continue; + /* Game over */ + break; } - p->flags |= FTRACE_FL_CONVERTED; ftrace_update_cnt++; /* -- cgit v1.2.2 From 996e87be7f537fb34638875dd37083166c733425 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 26 Apr 2011 16:11:03 -0400 Subject: ftrace: Move record update for normal and modules into a separate function The updating of a function record is moved to a single function. This will allow us to add specific changes in one location for both modules and kernel functions. Later patches will determine if the function record itself needs to be updated (which enables the mcount caller), or just the ftrace_ops needs the update. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9abaaf46f212..5b758ea344ce 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1743,6 +1743,15 @@ static int ftrace_match(char *str, char *regex, int len, int type) return matched; } +static void +update_record(struct dyn_ftrace *rec, unsigned long flag, int not) +{ + if (not) + rec->flags &= ~flag; + else + rec->flags |= flag; +} + static int ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type) { @@ -1772,10 +1781,7 @@ static int ftrace_match_records(char *buff, int len, int enable) do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_record(rec, search, search_len, type)) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; + update_record(rec, flag, not); found = 1; } /* @@ -1846,10 +1852,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) if (ftrace_match_module_record(rec, mod, search, search_len, type)) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; + update_record(rec, flag, not); found = 1; } if (enable && (rec->flags & FTRACE_FL_FILTER)) -- cgit v1.2.2 From 491d0dcfb9707e1f83eff93ca503eb7573162ef2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 27 Apr 2011 21:43:36 -0400 Subject: ftrace: Consolidate updating of ftrace_trace_function There are three locations that perform almost identical functions in order to update the ftrace_trace_function (the ftrace function variable that gets called by mcount). Consolidate these into a single function called update_ftrace_function(). Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 95 ++++++++++++++++++--------------------------------- 1 file changed, 34 insertions(+), 61 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5b758ea344ce..33bcc71ca09a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -151,6 +151,34 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) } #endif +static void update_ftrace_function(void) +{ + ftrace_func_t func; + + /* + * If there's only one function registered, then call that + * function directly. Otherwise, we need to iterate over the + * registered callers. + */ + if (ftrace_list == &ftrace_list_end || + ftrace_list->next == &ftrace_list_end) + func = ftrace_list->func; + else + func = ftrace_list_func; + + /* If we filter on pids, update to use the pid function */ + if (!list_empty(&ftrace_pids)) { + set_ftrace_pid_function(func); + func = ftrace_pid_func; + } +#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + ftrace_trace_function = func; +#else + __ftrace_trace_function = func; + ftrace_trace_function = ftrace_test_stop_func; +#endif +} + static int __register_ftrace_function(struct ftrace_ops *ops) { ops->next = ftrace_list; @@ -162,30 +190,8 @@ static int __register_ftrace_function(struct ftrace_ops *ops) */ rcu_assign_pointer(ftrace_list, ops); - if (ftrace_enabled) { - ftrace_func_t func; - - if (ops->next == &ftrace_list_end) - func = ops->func; - else - func = ftrace_list_func; - - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } - - /* - * For one func, simply call it directly. - * For more than one func, call the chain. - */ -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ftrace_trace_function = func; -#else - __ftrace_trace_function = func; - ftrace_trace_function = ftrace_test_stop_func; -#endif - } + if (ftrace_enabled) + update_ftrace_function(); return 0; } @@ -213,52 +219,19 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) *p = (*p)->next; - if (ftrace_enabled) { - /* If we only have one func left, then call that directly */ - if (ftrace_list->next == &ftrace_list_end) { - ftrace_func_t func = ftrace_list->func; - - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ftrace_trace_function = func; -#else - __ftrace_trace_function = func; -#endif - } - } + if (ftrace_enabled) + update_ftrace_function(); return 0; } static void ftrace_update_pid_func(void) { - ftrace_func_t func; - + /* Only do something if we are tracing something */ if (ftrace_trace_function == ftrace_stub) return; -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - func = ftrace_trace_function; -#else - func = __ftrace_trace_function; -#endif - - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } else { - if (func == ftrace_pid_func) - func = ftrace_pid_function; - } - -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ftrace_trace_function = func; -#else - __ftrace_trace_function = func; -#endif + update_ftrace_function(); } #ifdef CONFIG_FUNCTION_PROFILER -- cgit v1.2.2 From b9df92d2a94eef8811061aecb1396290df440e2e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 28 Apr 2011 20:32:08 -0400 Subject: ftrace: Consolidate the function match routines for normal and mods The code used for matching functions is almost identical between normal selecting of functions and using the :mod: feature of set_ftrace_notrace. Consolidate the two users into one function. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 98 +++++++++++++++++++-------------------------------- 1 file changed, 36 insertions(+), 62 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 33bcc71ca09a..4f19dbba12f9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1726,34 +1726,52 @@ update_record(struct dyn_ftrace *rec, unsigned long flag, int not) } static int -ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type) +ftrace_match_record(struct dyn_ftrace *rec, char *mod, + char *regex, int len, int type) { char str[KSYM_SYMBOL_LEN]; + char *modname; + + kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + + if (mod) { + /* module lookup requires matching the module */ + if (!modname || strcmp(modname, mod)) + return 0; + + /* blank search means to match all funcs in the mod */ + if (!len) + return 1; + } - kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); return ftrace_match(str, regex, len, type); } -static int ftrace_match_records(char *buff, int len, int enable) +static int match_records(char *buff, int len, char *mod, int enable, int not) { - unsigned int search_len; + unsigned search_len = 0; struct ftrace_page *pg; struct dyn_ftrace *rec; + int type = MATCH_FULL; + char *search = buff; unsigned long flag; - char *search; - int type; - int not; int found = 0; - flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - type = filter_parse_regex(buff, len, &search, ¬); + if (len) { + type = filter_parse_regex(buff, len, &search, ¬); + search_len = strlen(search); + } - search_len = strlen(search); + flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + goto out_unlock; + do_for_each_ftrace_rec(pg, rec) { - if (ftrace_match_record(rec, search, search_len, type)) { + if (ftrace_match_record(rec, mod, search, search_len, type)) { update_record(rec, flag, not); found = 1; } @@ -1763,43 +1781,23 @@ static int ftrace_match_records(char *buff, int len, int enable) */ if (enable && (rec->flags & FTRACE_FL_FILTER)) ftrace_filtered = 1; + } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); return found; } static int -ftrace_match_module_record(struct dyn_ftrace *rec, char *mod, - char *regex, int len, int type) +ftrace_match_records(char *buff, int len, int enable) { - char str[KSYM_SYMBOL_LEN]; - char *modname; - - kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); - - if (!modname || strcmp(modname, mod)) - return 0; - - /* blank search means to match all funcs in the mod */ - if (len) - return ftrace_match(str, regex, len, type); - else - return 1; + return match_records(buff, len, NULL, enable, 0); } static int ftrace_match_module_records(char *buff, char *mod, int enable) { - unsigned search_len = 0; - struct ftrace_page *pg; - struct dyn_ftrace *rec; - int type = MATCH_FULL; - char *search = buff; - unsigned long flag; int not = 0; - int found = 0; - - flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; /* blank or '*' mean the same */ if (strcmp(buff, "*") == 0) @@ -1811,31 +1809,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) not = 1; } - if (strlen(buff)) { - type = filter_parse_regex(buff, strlen(buff), &search, ¬); - search_len = strlen(search); - } - - mutex_lock(&ftrace_lock); - - if (unlikely(ftrace_disabled)) - goto out_unlock; - - do_for_each_ftrace_rec(pg, rec) { - - if (ftrace_match_module_record(rec, mod, - search, search_len, type)) { - update_record(rec, flag, not); - found = 1; - } - if (enable && (rec->flags & FTRACE_FL_FILTER)) - ftrace_filtered = 1; - - } while_for_each_ftrace_rec(); - out_unlock: - mutex_unlock(&ftrace_lock); - - return found; + return match_records(buff, strlen(buff), mod, enable, not); } /* @@ -1993,7 +1967,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, do_for_each_ftrace_rec(pg, rec) { - if (!ftrace_match_record(rec, search, len, type)) + if (!ftrace_match_record(rec, NULL, search, len, type)) continue; entry = kmalloc(sizeof(*entry), GFP_KERNEL); @@ -2548,7 +2522,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) if (rec->flags & FTRACE_FL_FREE) continue; - if (ftrace_match_record(rec, search, search_len, type)) { + if (ftrace_match_record(rec, NULL, search, search_len, type)) { /* if it is in the array */ exists = false; for (i = 0; i < *idx; i++) { -- cgit v1.2.2 From b448c4e3ae6d20108dba1d7833f2c0d3dbad87ce Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Apr 2011 15:12:32 -0400 Subject: ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions To prepare for the accounting system that will allow multiple users of the function tracer, having the FTRACE_FL_NOTRACE as a flag in the dyn_trace record does not make sense. All ftrace_ops will soon have a hash of functions they should trace and not trace. By making a global hash of functions not to trace makes this easier for the transition. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 176 ++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 150 insertions(+), 26 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d3406346ced6..04c002a491fb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -57,6 +57,7 @@ /* hash bits for specific function selection */ #define FTRACE_HASH_BITS 7 #define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) +#define FTRACE_HASH_MAX_BITS 10 /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; @@ -865,6 +866,22 @@ enum { FTRACE_START_FUNC_RET = (1 << 3), FTRACE_STOP_FUNC_RET = (1 << 4), }; +struct ftrace_func_entry { + struct hlist_node hlist; + unsigned long ip; +}; + +struct ftrace_hash { + unsigned long size_bits; + struct hlist_head *buckets; + unsigned long count; +}; + +static struct hlist_head notrace_buckets[1 << FTRACE_HASH_MAX_BITS]; +static struct ftrace_hash notrace_hash = { + .size_bits = FTRACE_HASH_MAX_BITS, + .buckets = notrace_buckets, +}; static int ftrace_filtered; @@ -889,6 +906,79 @@ static struct ftrace_page *ftrace_pages; static struct dyn_ftrace *ftrace_free_records; +static struct ftrace_func_entry * +ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) +{ + unsigned long key; + struct ftrace_func_entry *entry; + struct hlist_head *hhd; + struct hlist_node *n; + + if (!hash->count) + return NULL; + + if (hash->size_bits > 0) + key = hash_long(ip, hash->size_bits); + else + key = 0; + + hhd = &hash->buckets[key]; + + hlist_for_each_entry_rcu(entry, n, hhd, hlist) { + if (entry->ip == ip) + return entry; + } + return NULL; +} + +static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +{ + struct ftrace_func_entry *entry; + struct hlist_head *hhd; + unsigned long key; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + if (hash->size_bits) + key = hash_long(ip, hash->size_bits); + else + key = 0; + + entry->ip = ip; + hhd = &hash->buckets[key]; + hlist_add_head(&entry->hlist, hhd); + hash->count++; + + return 0; +} + +static void +remove_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + kfree(entry); + hash->count--; +} + +static void ftrace_hash_clear(struct ftrace_hash *hash) +{ + struct hlist_head *hhd; + struct hlist_node *tp, *tn; + struct ftrace_func_entry *entry; + int size = 1 << hash->size_bits; + int i; + + for (i = 0; i < size; i++) { + hhd = &hash->buckets[i]; + hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) + remove_hash_entry(hash, entry); + } + FTRACE_WARN_ON(hash->count); +} + /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. @@ -1032,7 +1122,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * If we want to enable it and filtering is on, enable it only if * it's filtered */ - if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) { + if (enable && !ftrace_lookup_ip(¬race_hash, rec->ip)) { if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER)) flag = FTRACE_FL_ENABLED; } @@ -1465,7 +1555,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) !(rec->flags & FTRACE_FL_FILTER)) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !(rec->flags & FTRACE_FL_NOTRACE))) { + !ftrace_lookup_ip(¬race_hash, rec->ip))) { rec = NULL; goto retry; } @@ -1609,14 +1699,15 @@ static void ftrace_filter_reset(int enable) { struct ftrace_page *pg; struct dyn_ftrace *rec; - unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; mutex_lock(&ftrace_lock); - if (enable) + if (enable) { ftrace_filtered = 0; - do_for_each_ftrace_rec(pg, rec) { - rec->flags &= ~type; - } while_for_each_ftrace_rec(); + do_for_each_ftrace_rec(pg, rec) { + rec->flags &= ~FTRACE_FL_FILTER; + } while_for_each_ftrace_rec(); + } else + ftrace_hash_clear(¬race_hash); mutex_unlock(&ftrace_lock); } @@ -1716,13 +1807,36 @@ static int ftrace_match(char *str, char *regex, int len, int type) return matched; } -static void -update_record(struct dyn_ftrace *rec, unsigned long flag, int not) +static int +update_record(struct dyn_ftrace *rec, int enable, int not) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; + struct ftrace_func_entry *entry; + struct ftrace_hash *hash = ¬race_hash; + int ret = 0; + + if (enable) { + if (not) + rec->flags &= ~FTRACE_FL_FILTER; + else + rec->flags |= FTRACE_FL_FILTER; + } else { + if (not) { + /* Do nothing if it doesn't exist */ + entry = ftrace_lookup_ip(hash, rec->ip); + if (!entry) + return 0; + + remove_hash_entry(hash, entry); + } else { + /* Do nothing if it exists */ + entry = ftrace_lookup_ip(hash, rec->ip); + if (entry) + return 0; + + ret = add_hash_entry(hash, rec->ip); + } + } + return ret; } static int @@ -1754,16 +1868,14 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) struct dyn_ftrace *rec; int type = MATCH_FULL; char *search = buff; - unsigned long flag; int found = 0; + int ret; if (len) { type = filter_parse_regex(buff, len, &search, ¬); search_len = strlen(search); } - flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - mutex_lock(&ftrace_lock); if (unlikely(ftrace_disabled)) @@ -1772,7 +1884,11 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_record(rec, mod, search, search_len, type)) { - update_record(rec, flag, not); + ret = update_record(rec, enable, not); + if (ret < 0) { + found = ret; + goto out_unlock; + } found = 1; } /* @@ -1821,6 +1937,7 @@ static int ftrace_mod_callback(char *func, char *cmd, char *param, int enable) { char *mod; + int ret = -EINVAL; /* * cmd == 'mod' because we only registered this func @@ -1832,15 +1949,19 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) /* we must have a module name */ if (!param) - return -EINVAL; + return ret; mod = strsep(¶m, ":"); if (!strlen(mod)) - return -EINVAL; + return ret; - if (ftrace_match_module_records(func, mod, enable)) - return 0; - return -EINVAL; + ret = ftrace_match_module_records(func, mod, enable); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + + return 0; } static struct ftrace_func_command ftrace_mod_cmd = { @@ -2132,14 +2253,17 @@ static int ftrace_process_regex(char *buff, int len, int enable) { char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret = -EINVAL; + int ret; func = strsep(&next, ":"); if (!next) { - if (ftrace_match_records(func, len, enable)) - return 0; - return ret; + ret = ftrace_match_records(func, len, enable); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + return 0; } /* command found */ -- cgit v1.2.2 From 1cf41dd79993389b012e4542ab502ce36ae7343f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Apr 2011 20:59:51 -0400 Subject: ftrace: Use hash instead for FTRACE_FL_FILTER When multiple users are allowed to have their own set of functions to trace, having the FTRACE_FL_FILTER flag will not be enough to handle the accounting of those users. Each user will need their own set of functions. Replace the FTRACE_FL_FILTER with a filter_hash instead. This is temporary until the rest of the function filtering accounting gets in. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 151 +++++++++++++++++++++++--------------------------- 1 file changed, 69 insertions(+), 82 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 04c002a491fb..222eca4c3022 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -883,7 +883,11 @@ static struct ftrace_hash notrace_hash = { .buckets = notrace_buckets, }; -static int ftrace_filtered; +static struct hlist_head filter_buckets[1 << FTRACE_HASH_MAX_BITS]; +static struct ftrace_hash filter_hash = { + .size_bits = FTRACE_HASH_MAX_BITS, + .buckets = filter_buckets, +}; static struct dyn_ftrace *ftrace_new_addrs; @@ -1123,7 +1127,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * it's filtered */ if (enable && !ftrace_lookup_ip(¬race_hash, rec->ip)) { - if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER)) + if (!filter_hash.count || ftrace_lookup_ip(&filter_hash, rec->ip)) flag = FTRACE_FL_ENABLED; } @@ -1430,6 +1434,7 @@ struct ftrace_iterator { struct dyn_ftrace *func; struct ftrace_func_probe *probe; struct trace_parser parser; + struct ftrace_hash *hash; int hidx; int idx; unsigned flags; @@ -1552,7 +1557,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) if ((rec->flags & FTRACE_FL_FREE) || ((iter->flags & FTRACE_ITER_FILTER) && - !(rec->flags & FTRACE_FL_FILTER)) || + !(ftrace_lookup_ip(&filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && !ftrace_lookup_ip(¬race_hash, rec->ip))) { @@ -1598,7 +1603,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && !ftrace_filtered) { + if (iter->flags & FTRACE_ITER_FILTER && !filter_hash.count) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -1695,24 +1700,16 @@ ftrace_avail_open(struct inode *inode, struct file *file) return ret; } -static void ftrace_filter_reset(int enable) +static void ftrace_filter_reset(struct ftrace_hash *hash) { - struct ftrace_page *pg; - struct dyn_ftrace *rec; - mutex_lock(&ftrace_lock); - if (enable) { - ftrace_filtered = 0; - do_for_each_ftrace_rec(pg, rec) { - rec->flags &= ~FTRACE_FL_FILTER; - } while_for_each_ftrace_rec(); - } else - ftrace_hash_clear(¬race_hash); + ftrace_hash_clear(hash); mutex_unlock(&ftrace_lock); } static int -ftrace_regex_open(struct inode *inode, struct file *file, int enable) +ftrace_regex_open(struct ftrace_hash *hash, int flag, + struct inode *inode, struct file *file) { struct ftrace_iterator *iter; int ret = 0; @@ -1729,15 +1726,16 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) return -ENOMEM; } + iter->hash = hash; + mutex_lock(&ftrace_regex_lock); if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_filter_reset(enable); + ftrace_filter_reset(hash); if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->flags = enable ? FTRACE_ITER_FILTER : - FTRACE_ITER_NOTRACE; + iter->flags = flag; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -1757,13 +1755,15 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(inode, file, 1); + return ftrace_regex_open(&filter_hash, FTRACE_ITER_FILTER, + inode, file); } static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(inode, file, 0); + return ftrace_regex_open(¬race_hash, FTRACE_ITER_NOTRACE, + inode, file); } static loff_t @@ -1808,33 +1808,24 @@ static int ftrace_match(char *str, char *regex, int len, int type) } static int -update_record(struct dyn_ftrace *rec, int enable, int not) +enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not) { struct ftrace_func_entry *entry; - struct ftrace_hash *hash = ¬race_hash; int ret = 0; - if (enable) { - if (not) - rec->flags &= ~FTRACE_FL_FILTER; - else - rec->flags |= FTRACE_FL_FILTER; - } else { - if (not) { - /* Do nothing if it doesn't exist */ - entry = ftrace_lookup_ip(hash, rec->ip); - if (!entry) - return 0; + entry = ftrace_lookup_ip(hash, rec->ip); + if (not) { + /* Do nothing if it doesn't exist */ + if (!entry) + return 0; - remove_hash_entry(hash, entry); - } else { - /* Do nothing if it exists */ - entry = ftrace_lookup_ip(hash, rec->ip); - if (entry) - return 0; + remove_hash_entry(hash, entry); + } else { + /* Do nothing if it exists */ + if (entry) + return 0; - ret = add_hash_entry(hash, rec->ip); - } + ret = add_hash_entry(hash, rec->ip); } return ret; } @@ -1861,7 +1852,9 @@ ftrace_match_record(struct dyn_ftrace *rec, char *mod, return ftrace_match(str, regex, len, type); } -static int match_records(char *buff, int len, char *mod, int enable, int not) +static int +match_records(struct ftrace_hash *hash, char *buff, + int len, char *mod, int not) { unsigned search_len = 0; struct ftrace_page *pg; @@ -1884,20 +1877,13 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) do_for_each_ftrace_rec(pg, rec) { if (ftrace_match_record(rec, mod, search, search_len, type)) { - ret = update_record(rec, enable, not); + ret = enter_record(hash, rec, not); if (ret < 0) { found = ret; goto out_unlock; } found = 1; } - /* - * Only enable filtering if we have a function that - * is filtered on. - */ - if (enable && (rec->flags & FTRACE_FL_FILTER)) - ftrace_filtered = 1; - } while_for_each_ftrace_rec(); out_unlock: mutex_unlock(&ftrace_lock); @@ -1906,12 +1892,13 @@ static int match_records(char *buff, int len, char *mod, int enable, int not) } static int -ftrace_match_records(char *buff, int len, int enable) +ftrace_match_records(struct ftrace_hash *hash, char *buff, int len) { - return match_records(buff, len, NULL, enable, 0); + return match_records(hash, buff, len, NULL, 0); } -static int ftrace_match_module_records(char *buff, char *mod, int enable) +static int +ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod) { int not = 0; @@ -1925,7 +1912,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) not = 1; } - return match_records(buff, strlen(buff), mod, enable, not); + return match_records(hash, buff, strlen(buff), mod, not); } /* @@ -1936,6 +1923,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) static int ftrace_mod_callback(char *func, char *cmd, char *param, int enable) { + struct ftrace_hash *hash; char *mod; int ret = -EINVAL; @@ -1955,7 +1943,12 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) if (!strlen(mod)) return ret; - ret = ftrace_match_module_records(func, mod, enable); + if (enable) + hash = &filter_hash; + else + hash = ¬race_hash; + + ret = ftrace_match_module_records(hash, func, mod); if (!ret) ret = -EINVAL; if (ret < 0) @@ -2253,12 +2246,18 @@ static int ftrace_process_regex(char *buff, int len, int enable) { char *func, *command, *next = buff; struct ftrace_func_command *p; + struct ftrace_hash *hash; int ret; + if (enable) + hash = &filter_hash; + else + hash = ¬race_hash; + func = strsep(&next, ":"); if (!next) { - ret = ftrace_match_records(func, len, enable); + ret = ftrace_match_records(hash, func, len); if (!ret) ret = -EINVAL; if (ret < 0) @@ -2340,16 +2339,16 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static void -ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) +ftrace_set_regex(struct ftrace_hash *hash, unsigned char *buf, int len, int reset) { if (unlikely(ftrace_disabled)) return; mutex_lock(&ftrace_regex_lock); if (reset) - ftrace_filter_reset(enable); + ftrace_filter_reset(hash); if (buf) - ftrace_match_records(buf, len, enable); + ftrace_match_records(hash, buf, len); mutex_unlock(&ftrace_regex_lock); } @@ -2364,7 +2363,7 @@ ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) */ void ftrace_set_filter(unsigned char *buf, int len, int reset) { - ftrace_set_regex(buf, len, reset, 1); + ftrace_set_regex(&filter_hash, buf, len, reset); } /** @@ -2379,7 +2378,7 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) */ void ftrace_set_notrace(unsigned char *buf, int len, int reset) { - ftrace_set_regex(buf, len, reset, 0); + ftrace_set_regex(¬race_hash, buf, len, reset); } /* @@ -2431,22 +2430,22 @@ static void __init set_ftrace_early_graph(char *buf) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static void __init set_ftrace_early_filter(char *buf, int enable) +static void __init set_ftrace_early_filter(struct ftrace_hash *hash, char *buf) { char *func; while (buf) { func = strsep(&buf, ","); - ftrace_set_regex(func, strlen(func), 0, enable); + ftrace_set_regex(hash, func, strlen(func), 0); } } static void __init set_ftrace_early_filters(void) { if (ftrace_filter_buf[0]) - set_ftrace_early_filter(ftrace_filter_buf, 1); + set_ftrace_early_filter(&filter_hash, ftrace_filter_buf); if (ftrace_notrace_buf[0]) - set_ftrace_early_filter(ftrace_notrace_buf, 0); + set_ftrace_early_filter(¬race_hash, ftrace_notrace_buf); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) set_ftrace_early_graph(ftrace_graph_buf); @@ -2454,7 +2453,7 @@ static void __init set_ftrace_early_filters(void) } static int -ftrace_regex_release(struct inode *inode, struct file *file, int enable) +ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; @@ -2471,7 +2470,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) parser = &iter->parser; if (trace_parser_loaded(parser)) { parser->buffer[parser->idx] = 0; - ftrace_match_records(parser->buffer, parser->idx, enable); + ftrace_match_records(iter->hash, parser->buffer, parser->idx); } trace_parser_put(parser); @@ -2488,18 +2487,6 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) return 0; } -static int -ftrace_filter_release(struct inode *inode, struct file *file) -{ - return ftrace_regex_release(inode, file, 1); -} - -static int -ftrace_notrace_release(struct inode *inode, struct file *file) -{ - return ftrace_regex_release(inode, file, 0); -} - static const struct file_operations ftrace_avail_fops = { .open = ftrace_avail_open, .read = seq_read, @@ -2512,7 +2499,7 @@ static const struct file_operations ftrace_filter_fops = { .read = seq_read, .write = ftrace_filter_write, .llseek = ftrace_regex_lseek, - .release = ftrace_filter_release, + .release = ftrace_regex_release, }; static const struct file_operations ftrace_notrace_fops = { @@ -2520,7 +2507,7 @@ static const struct file_operations ftrace_notrace_fops = { .read = seq_read, .write = ftrace_notrace_write, .llseek = ftrace_regex_lseek, - .release = ftrace_notrace_release, + .release = ftrace_regex_release, }; #ifdef CONFIG_FUNCTION_GRAPH_TRACER -- cgit v1.2.2 From f45948e898e7bc76a73a468796d2ce80dd040058 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 2 May 2011 12:29:25 -0400 Subject: ftrace: Create a global_ops to hold the filter and notrace hashes Combine the filter and notrace hashes to be accessed by a single entity, the global_ops. The global_ops is a ftrace_ops structure that is passed to different functions that can read or modify the filtering of the function tracer. The ftrace_ops structure was modified to hold a filter and notrace hashes so that later patches may allow each ftrace_ops to have its own set of rules to what functions may be filtered. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 65 ++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 46 insertions(+), 19 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 222eca4c3022..a517a6c40645 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -889,6 +889,12 @@ static struct ftrace_hash filter_hash = { .buckets = filter_buckets, }; +struct ftrace_ops global_ops = { + .func = ftrace_stub, + .notrace_hash = ¬race_hash, + .filter_hash = &filter_hash, +}; + static struct dyn_ftrace *ftrace_new_addrs; static DEFINE_MUTEX(ftrace_regex_lock); @@ -1112,6 +1118,7 @@ int ftrace_text_reserved(void *start, void *end) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { + struct ftrace_ops *ops = &global_ops; unsigned long ftrace_addr; unsigned long flag = 0UL; @@ -1126,8 +1133,9 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) * If we want to enable it and filtering is on, enable it only if * it's filtered */ - if (enable && !ftrace_lookup_ip(¬race_hash, rec->ip)) { - if (!filter_hash.count || ftrace_lookup_ip(&filter_hash, rec->ip)) + if (enable && !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) { + if (!ops->filter_hash->count || + ftrace_lookup_ip(ops->filter_hash, rec->ip)) flag = FTRACE_FL_ENABLED; } @@ -1531,6 +1539,7 @@ static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = &global_ops; struct dyn_ftrace *rec = NULL; if (unlikely(ftrace_disabled)) @@ -1557,10 +1566,10 @@ t_next(struct seq_file *m, void *v, loff_t *pos) if ((rec->flags & FTRACE_FL_FREE) || ((iter->flags & FTRACE_ITER_FILTER) && - !(ftrace_lookup_ip(&filter_hash, rec->ip))) || + !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !ftrace_lookup_ip(¬race_hash, rec->ip))) { + !ftrace_lookup_ip(ops->notrace_hash, rec->ip))) { rec = NULL; goto retry; } @@ -1584,6 +1593,7 @@ static void reset_iter_read(struct ftrace_iterator *iter) static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = &global_ops; void *p = NULL; loff_t l; @@ -1603,7 +1613,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && !filter_hash.count) { + if (iter->flags & FTRACE_ITER_FILTER && !ops->filter_hash->count) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -1708,10 +1718,11 @@ static void ftrace_filter_reset(struct ftrace_hash *hash) } static int -ftrace_regex_open(struct ftrace_hash *hash, int flag, +ftrace_regex_open(struct ftrace_ops *ops, int flag, struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + struct ftrace_hash *hash; int ret = 0; if (unlikely(ftrace_disabled)) @@ -1726,6 +1737,11 @@ ftrace_regex_open(struct ftrace_hash *hash, int flag, return -ENOMEM; } + if (flag & FTRACE_ITER_NOTRACE) + hash = ops->notrace_hash; + else + hash = ops->filter_hash; + iter->hash = hash; mutex_lock(&ftrace_regex_lock); @@ -1755,14 +1771,14 @@ ftrace_regex_open(struct ftrace_hash *hash, int flag, static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&filter_hash, FTRACE_ITER_FILTER, + return ftrace_regex_open(&global_ops, FTRACE_ITER_FILTER, inode, file); } static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(¬race_hash, FTRACE_ITER_NOTRACE, + return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -1923,6 +1939,7 @@ ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod) static int ftrace_mod_callback(char *func, char *cmd, char *param, int enable) { + struct ftrace_ops *ops = &global_ops; struct ftrace_hash *hash; char *mod; int ret = -EINVAL; @@ -1944,9 +1961,9 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) return ret; if (enable) - hash = &filter_hash; + hash = ops->filter_hash; else - hash = ¬race_hash; + hash = ops->notrace_hash; ret = ftrace_match_module_records(hash, func, mod); if (!ret) @@ -2245,14 +2262,15 @@ int unregister_ftrace_command(struct ftrace_func_command *cmd) static int ftrace_process_regex(char *buff, int len, int enable) { char *func, *command, *next = buff; + struct ftrace_ops *ops = &global_ops; struct ftrace_func_command *p; struct ftrace_hash *hash; int ret; if (enable) - hash = &filter_hash; + hash = ops->filter_hash; else - hash = ¬race_hash; + hash = ops->notrace_hash; func = strsep(&next, ":"); @@ -2339,11 +2357,19 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static void -ftrace_set_regex(struct ftrace_hash *hash, unsigned char *buf, int len, int reset) +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) { + struct ftrace_hash *hash; + if (unlikely(ftrace_disabled)) return; + if (enable) + hash = ops->filter_hash; + else + hash = ops->notrace_hash; + mutex_lock(&ftrace_regex_lock); if (reset) ftrace_filter_reset(hash); @@ -2363,7 +2389,7 @@ ftrace_set_regex(struct ftrace_hash *hash, unsigned char *buf, int len, int rese */ void ftrace_set_filter(unsigned char *buf, int len, int reset) { - ftrace_set_regex(&filter_hash, buf, len, reset); + ftrace_set_regex(&global_ops, buf, len, reset, 1); } /** @@ -2378,7 +2404,7 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) */ void ftrace_set_notrace(unsigned char *buf, int len, int reset) { - ftrace_set_regex(¬race_hash, buf, len, reset); + ftrace_set_regex(&global_ops, buf, len, reset, 0); } /* @@ -2430,22 +2456,23 @@ static void __init set_ftrace_early_graph(char *buf) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static void __init set_ftrace_early_filter(struct ftrace_hash *hash, char *buf) +static void __init +set_ftrace_early_filter(struct ftrace_ops *ops, char *buf, int enable) { char *func; while (buf) { func = strsep(&buf, ","); - ftrace_set_regex(hash, func, strlen(func), 0); + ftrace_set_regex(ops, func, strlen(func), 0, enable); } } static void __init set_ftrace_early_filters(void) { if (ftrace_filter_buf[0]) - set_ftrace_early_filter(&filter_hash, ftrace_filter_buf); + set_ftrace_early_filter(&global_ops, ftrace_filter_buf, 1); if (ftrace_notrace_buf[0]) - set_ftrace_early_filter(¬race_hash, ftrace_notrace_buf); + set_ftrace_early_filter(&global_ops, ftrace_notrace_buf, 0); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) set_ftrace_early_graph(ftrace_graph_buf); -- cgit v1.2.2 From 33dc9b1267d59cef46ff0bd6bc043190845dc919 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 2 May 2011 17:34:47 -0400 Subject: ftrace: Separate hash allocation and assignment When filtering, allocate a hash to insert the function records. After the filtering is complete, assign it to the ftrace_ops structure. This allows the ftrace_ops structure to have a much smaller array of hash buckets instead of wasting a lot of memory. A read only empty_hash is created to be the minimum size that any ftrace_ops can point to. When a new hash is created, it has the following steps: o Allocate a default hash. o Walk the function records assigning the filtered records to the hash o Allocate a new hash with the appropriate size buckets o Move the entries from the default hash to the new hash. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 275 ++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 233 insertions(+), 42 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a517a6c40645..46f08264980b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -57,7 +57,8 @@ /* hash bits for specific function selection */ #define FTRACE_HASH_BITS 7 #define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) -#define FTRACE_HASH_MAX_BITS 10 +#define FTRACE_HASH_DEFAULT_BITS 10 +#define FTRACE_HASH_MAX_BITS 12 /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; @@ -877,22 +878,22 @@ struct ftrace_hash { unsigned long count; }; -static struct hlist_head notrace_buckets[1 << FTRACE_HASH_MAX_BITS]; -static struct ftrace_hash notrace_hash = { - .size_bits = FTRACE_HASH_MAX_BITS, - .buckets = notrace_buckets, -}; - -static struct hlist_head filter_buckets[1 << FTRACE_HASH_MAX_BITS]; -static struct ftrace_hash filter_hash = { - .size_bits = FTRACE_HASH_MAX_BITS, - .buckets = filter_buckets, +/* + * We make these constant because no one should touch them, + * but they are used as the default "empty hash", to avoid allocating + * it all the time. These are in a read only section such that if + * anyone does try to modify it, it will cause an exception. + */ +static const struct hlist_head empty_buckets[1]; +static const struct ftrace_hash empty_hash = { + .buckets = (struct hlist_head *)empty_buckets, }; +#define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) struct ftrace_ops global_ops = { .func = ftrace_stub, - .notrace_hash = ¬race_hash, - .filter_hash = &filter_hash, + .notrace_hash = EMPTY_HASH, + .filter_hash = EMPTY_HASH, }; static struct dyn_ftrace *ftrace_new_addrs; @@ -941,31 +942,38 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) return NULL; } -static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +static void __add_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) { - struct ftrace_func_entry *entry; struct hlist_head *hhd; unsigned long key; - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return -ENOMEM; - if (hash->size_bits) - key = hash_long(ip, hash->size_bits); + key = hash_long(entry->ip, hash->size_bits); else key = 0; - entry->ip = ip; hhd = &hash->buckets[key]; hlist_add_head(&entry->hlist, hhd); hash->count++; +} + +static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +{ + struct ftrace_func_entry *entry; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->ip = ip; + __add_hash_entry(hash, entry); return 0; } static void -remove_hash_entry(struct ftrace_hash *hash, +free_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry) { hlist_del(&entry->hlist); @@ -973,6 +981,14 @@ remove_hash_entry(struct ftrace_hash *hash, hash->count--; } +static void +remove_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + hash->count--; +} + static void ftrace_hash_clear(struct ftrace_hash *hash) { struct hlist_head *hhd; @@ -981,14 +997,156 @@ static void ftrace_hash_clear(struct ftrace_hash *hash) int size = 1 << hash->size_bits; int i; + if (!hash->count) + return; + for (i = 0; i < size; i++) { hhd = &hash->buckets[i]; hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) - remove_hash_entry(hash, entry); + free_hash_entry(hash, entry); } FTRACE_WARN_ON(hash->count); } +static void free_ftrace_hash(struct ftrace_hash *hash) +{ + if (!hash || hash == EMPTY_HASH) + return; + ftrace_hash_clear(hash); + kfree(hash->buckets); + kfree(hash); +} + +static struct ftrace_hash *alloc_ftrace_hash(int size_bits) +{ + struct ftrace_hash *hash; + int size; + + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) + return NULL; + + size = 1 << size_bits; + hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL); + + if (!hash->buckets) { + kfree(hash); + return NULL; + } + + hash->size_bits = size_bits; + + return hash; +} + +static struct ftrace_hash * +alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) +{ + struct ftrace_func_entry *entry; + struct ftrace_hash *new_hash; + struct hlist_node *tp; + int size; + int ret; + int i; + + new_hash = alloc_ftrace_hash(size_bits); + if (!new_hash) + return NULL; + + /* Empty hash? */ + if (!hash || !hash->count) + return new_hash; + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, tp, &hash->buckets[i], hlist) { + ret = add_hash_entry(new_hash, entry->ip); + if (ret < 0) + goto free_hash; + } + } + + FTRACE_WARN_ON(new_hash->count != hash->count); + + return new_hash; + + free_hash: + free_ftrace_hash(new_hash); + return NULL; +} + +static int +ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) +{ + struct ftrace_func_entry *entry; + struct hlist_node *tp, *tn; + struct hlist_head *hhd; + struct ftrace_hash *hash = *dst; + unsigned long key; + int size = src->count; + int bits = 0; + int i; + + /* + * If the new source is empty, just free dst and assign it + * the empty_hash. + */ + if (!src->count) { + free_ftrace_hash(*dst); + *dst = EMPTY_HASH; + return 0; + } + + ftrace_hash_clear(hash); + + /* + * Make the hash size about 1/2 the # found + */ + for (size /= 2; size; size >>= 1) + bits++; + + /* Don't allocate too much */ + if (bits > FTRACE_HASH_MAX_BITS) + bits = FTRACE_HASH_MAX_BITS; + + /* We can't modify the empty_hash */ + if (hash == EMPTY_HASH) { + /* Create a new hash */ + *dst = alloc_ftrace_hash(bits); + if (!*dst) { + *dst = EMPTY_HASH; + return -ENOMEM; + } + hash = *dst; + } else { + size = 1 << bits; + + /* Use the old hash, but create new buckets */ + hhd = kzalloc(sizeof(*hhd) * size, GFP_KERNEL); + if (!hhd) + return -ENOMEM; + + kfree(hash->buckets); + hash->buckets = hhd; + hash->size_bits = bits; + } + + size = 1 << src->size_bits; + for (i = 0; i < size; i++) { + hhd = &src->buckets[i]; + hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) { + if (bits > 0) + key = hash_long(entry->ip, bits); + else + key = 0; + remove_hash_entry(src, entry); + __add_hash_entry(hash, entry); + } + } + + return 0; +} + /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. @@ -1443,6 +1601,7 @@ struct ftrace_iterator { struct ftrace_func_probe *probe; struct trace_parser parser; struct ftrace_hash *hash; + struct ftrace_ops *ops; int hidx; int idx; unsigned flags; @@ -1742,22 +1901,37 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, else hash = ops->filter_hash; - iter->hash = hash; + iter->ops = ops; + iter->flags = flag; + + if (file->f_mode & FMODE_WRITE) { + mutex_lock(&ftrace_lock); + iter->hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, hash); + mutex_unlock(&ftrace_lock); + + if (!iter->hash) { + trace_parser_put(&iter->parser); + kfree(iter); + return -ENOMEM; + } + } mutex_lock(&ftrace_regex_lock); + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_filter_reset(hash); + ftrace_filter_reset(iter->hash); if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->flags = flag; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { struct seq_file *m = file->private_data; m->private = iter; } else { + /* Failed */ + free_ftrace_hash(iter->hash); trace_parser_put(&iter->parser); kfree(iter); } @@ -1835,7 +2009,7 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not) if (!entry) return 0; - remove_hash_entry(hash, entry); + free_hash_entry(hash, entry); } else { /* Do nothing if it exists */ if (entry) @@ -2259,19 +2433,13 @@ int unregister_ftrace_command(struct ftrace_func_command *cmd) return ret; } -static int ftrace_process_regex(char *buff, int len, int enable) +static int ftrace_process_regex(struct ftrace_hash *hash, + char *buff, int len, int enable) { char *func, *command, *next = buff; - struct ftrace_ops *ops = &global_ops; struct ftrace_func_command *p; - struct ftrace_hash *hash; int ret; - if (enable) - hash = ops->filter_hash; - else - hash = ops->notrace_hash; - func = strsep(&next, ":"); if (!next) { @@ -2328,7 +2496,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, if (read >= 0 && trace_parser_loaded(parser) && !trace_parser_cont(parser)) { - ret = ftrace_process_regex(parser->buffer, + ret = ftrace_process_regex(iter->hash, parser->buffer, parser->idx, enable); trace_parser_clear(parser); if (ret) @@ -2356,26 +2524,40 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, return ftrace_regex_write(file, ubuf, cnt, ppos, 0); } -static void +static int ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, int reset, int enable) { + struct ftrace_hash **orig_hash; struct ftrace_hash *hash; + int ret; if (unlikely(ftrace_disabled)) - return; + return -ENODEV; if (enable) - hash = ops->filter_hash; + orig_hash = &ops->filter_hash; else - hash = ops->notrace_hash; + orig_hash = &ops->notrace_hash; + + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (!hash) + return -ENOMEM; mutex_lock(&ftrace_regex_lock); if (reset) ftrace_filter_reset(hash); if (buf) ftrace_match_records(hash, buf, len); + + mutex_lock(&ftrace_lock); + ret = ftrace_hash_move(orig_hash, hash); + mutex_unlock(&ftrace_lock); + mutex_unlock(&ftrace_regex_lock); + + free_ftrace_hash(hash); + return ret; } /** @@ -2484,7 +2666,9 @@ ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; + struct ftrace_hash **orig_hash; struct trace_parser *parser; + int ret; mutex_lock(&ftrace_regex_lock); if (file->f_mode & FMODE_READ) { @@ -2501,14 +2685,21 @@ ftrace_regex_release(struct inode *inode, struct file *file) } trace_parser_put(parser); - kfree(iter); if (file->f_mode & FMODE_WRITE) { + if (iter->flags & FTRACE_ITER_NOTRACE) + orig_hash = &iter->ops->notrace_hash; + else + orig_hash = &iter->ops->filter_hash; + mutex_lock(&ftrace_lock); - if (ftrace_start_up && ftrace_enabled) + ret = ftrace_hash_move(orig_hash, iter->hash); + if (!ret && ftrace_start_up && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); mutex_unlock(&ftrace_lock); } + free_ftrace_hash(iter->hash); + kfree(iter); mutex_unlock(&ftrace_regex_lock); return 0; -- cgit v1.2.2 From ed926f9b35cda0988234c356e16a7cb30f4e5338 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 3 May 2011 13:25:24 -0400 Subject: ftrace: Use counters to enable functions to trace Every function has its own record that stores the instruction pointer and flags for the function to be traced. There are only two flags: enabled and free. The enabled flag states that tracing for the function has been enabled (actively traced), and the free flag states that the record no longer points to a function and can be used by new functions (loaded modules). These flags are now moved to the MSB of the flags (actually just the top 32bits). The rest of the bits (30 bits) are now used as a ref counter. Everytime a tracer register functions to trace, those functions will have its counter incremented. When tracing is enabled, to determine if a function should be traced, the counter is examined, and if it is non-zero it is set to trace. When a ftrace_ops is registered to trace functions, its hashes are examined. If the ftrace_ops filter_hash count is zero, then all functions are set to be traced, otherwise only the functions in the hash are to be traced. The exception to this is if a function is also in the ftrace_ops notrace_hash. Then that function's counter is not incremented for this ftrace_ops. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 158 +++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 142 insertions(+), 16 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 46f08264980b..5dd332cc5aa8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -890,6 +890,10 @@ static const struct ftrace_hash empty_hash = { }; #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) +enum { + FTRACE_OPS_FL_ENABLED = 1, +}; + struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, @@ -1161,6 +1165,105 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) } \ } +static void __ftrace_hash_rec_update(struct ftrace_ops *ops, + int filter_hash, + bool inc) +{ + struct ftrace_hash *hash; + struct ftrace_hash *other_hash; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int count = 0; + int all = 0; + + /* Only update if the ops has been registered */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return; + + /* + * In the filter_hash case: + * If the count is zero, we update all records. + * Otherwise we just update the items in the hash. + * + * In the notrace_hash case: + * We enable the update in the hash. + * As disabling notrace means enabling the tracing, + * and enabling notrace means disabling, the inc variable + * gets inversed. + */ + if (filter_hash) { + hash = ops->filter_hash; + other_hash = ops->notrace_hash; + if (!hash->count) + all = 1; + } else { + inc = !inc; + hash = ops->notrace_hash; + other_hash = ops->filter_hash; + /* + * If the notrace hash has no items, + * then there's nothing to do. + */ + if (!hash->count) + return; + } + + do_for_each_ftrace_rec(pg, rec) { + int in_other_hash = 0; + int in_hash = 0; + int match = 0; + + if (all) { + /* + * Only the filter_hash affects all records. + * Update if the record is not in the notrace hash. + */ + if (!ftrace_lookup_ip(other_hash, rec->ip)) + match = 1; + } else { + in_hash = !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); + + /* + * + */ + if (filter_hash && in_hash && !in_other_hash) + match = 1; + else if (!filter_hash && in_hash && + (in_other_hash || !other_hash->count)) + match = 1; + } + if (!match) + continue; + + if (inc) { + rec->flags++; + if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) + return; + } else { + if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) + return; + rec->flags--; + } + count++; + /* Shortcut, if we handled all records, we are done. */ + if (!all && count == hash->count) + return; + } while_for_each_ftrace_rec(); +} + +static void ftrace_hash_rec_disable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 0); +} + +static void ftrace_hash_rec_enable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 1); +} + static void ftrace_free_rec(struct dyn_ftrace *rec) { rec->freelist = ftrace_free_records; @@ -1276,26 +1379,24 @@ int ftrace_text_reserved(void *start, void *end) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { - struct ftrace_ops *ops = &global_ops; unsigned long ftrace_addr; unsigned long flag = 0UL; ftrace_addr = (unsigned long)FTRACE_ADDR; /* - * If this record is not to be traced or we want to disable it, - * then disable it. + * If we are enabling tracing: * - * If we want to enable it and filtering is off, then enable it. + * If the record has a ref count, then we need to enable it + * because someone is using it. * - * If we want to enable it and filtering is on, enable it only if - * it's filtered + * Otherwise we make sure its disabled. + * + * If we are disabling tracing, then disable all records that + * are enabled. */ - if (enable && !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) { - if (!ops->filter_hash->count || - ftrace_lookup_ip(ops->filter_hash, rec->ip)) - flag = FTRACE_FL_ENABLED; - } + if (enable && (rec->flags & ~FTRACE_FL_MASK)) + flag = FTRACE_FL_ENABLED; /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) @@ -1423,17 +1524,25 @@ static void ftrace_startup_enable(int command) static void ftrace_startup(int command) { + struct ftrace_ops *ops = &global_ops; + if (unlikely(ftrace_disabled)) return; ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; + ops->flags |= FTRACE_OPS_FL_ENABLED; + if (ftrace_start_up == 1) + ftrace_hash_rec_enable(ops, 1); + ftrace_startup_enable(command); } static void ftrace_shutdown(int command) { + struct ftrace_ops *ops = &global_ops; + if (unlikely(ftrace_disabled)) return; @@ -1446,7 +1555,12 @@ static void ftrace_shutdown(int command) WARN_ON_ONCE(ftrace_start_up < 0); if (!ftrace_start_up) + ftrace_hash_rec_disable(ops, 1); + + if (!ftrace_start_up) { command |= FTRACE_DISABLE_CALLS; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -2668,6 +2782,7 @@ ftrace_regex_release(struct inode *inode, struct file *file) struct ftrace_iterator *iter; struct ftrace_hash **orig_hash; struct trace_parser *parser; + int filter_hash; int ret; mutex_lock(&ftrace_regex_lock); @@ -2687,15 +2802,26 @@ ftrace_regex_release(struct inode *inode, struct file *file) trace_parser_put(parser); if (file->f_mode & FMODE_WRITE) { - if (iter->flags & FTRACE_ITER_NOTRACE) - orig_hash = &iter->ops->notrace_hash; - else + filter_hash = !!(iter->flags & FTRACE_ITER_FILTER); + + if (filter_hash) orig_hash = &iter->ops->filter_hash; + else + orig_hash = &iter->ops->notrace_hash; mutex_lock(&ftrace_lock); + /* + * Remove the current set, update the hash and add + * them back. + */ + ftrace_hash_rec_disable(iter->ops, filter_hash); ret = ftrace_hash_move(orig_hash, iter->hash); - if (!ret && ftrace_start_up && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); + if (!ret) { + ftrace_hash_rec_enable(iter->ops, filter_hash); + if (iter->ops->flags & FTRACE_OPS_FL_ENABLED + && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + } mutex_unlock(&ftrace_lock); } free_ftrace_hash(iter->hash); -- cgit v1.2.2 From 647bcd03d5b2fb44fd9c9ef1a4f50c2eee8f779a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 3 May 2011 14:39:21 -0400 Subject: ftrace: Add enabled_functions file Add the enabled_functions file that is used to show all the functions that have been enabled for tracing as well as their ref counts. This helps seeing if any function has been registered and what functions are being traced. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5dd332cc5aa8..065f1e61e103 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1703,6 +1703,7 @@ enum { FTRACE_ITER_NOTRACE = (1 << 1), FTRACE_ITER_PRINTALL = (1 << 2), FTRACE_ITER_HASH = (1 << 3), + FTRACE_ITER_ENABLED = (1 << 4), }; #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ @@ -1842,7 +1843,11 @@ t_next(struct seq_file *m, void *v, loff_t *pos) !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !ftrace_lookup_ip(ops->notrace_hash, rec->ip))) { + !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) || + + ((iter->flags & FTRACE_ITER_ENABLED) && + !(rec->flags & ~FTRACE_FL_MASK))) { + rec = NULL; goto retry; } @@ -1944,7 +1949,11 @@ static int t_show(struct seq_file *m, void *v) if (!rec) return 0; - seq_printf(m, "%ps\n", (void *)rec->ip); + seq_printf(m, "%ps", (void *)rec->ip); + if (iter->flags & FTRACE_ITER_ENABLED) + seq_printf(m, " (%ld)", + rec->flags & ~FTRACE_FL_MASK); + seq_printf(m, "\n"); return 0; } @@ -1983,6 +1992,34 @@ ftrace_avail_open(struct inode *inode, struct file *file) return ret; } +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; + + ret = seq_open(file, &show_ftrace_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + + m->private = iter; + } else { + kfree(iter); + } + + return ret; +} + static void ftrace_filter_reset(struct ftrace_hash *hash) { mutex_lock(&ftrace_lock); @@ -2838,6 +2875,13 @@ static const struct file_operations ftrace_avail_fops = { .release = seq_release_private, }; +static const struct file_operations ftrace_enabled_fops = { + .open = ftrace_enabled_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, @@ -3069,6 +3113,9 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) trace_create_file("available_filter_functions", 0444, d_tracer, NULL, &ftrace_avail_fops); + trace_create_file("enabled_functions", 0444, + d_tracer, NULL, &ftrace_enabled_fops); + trace_create_file("set_ftrace_filter", 0644, d_tracer, NULL, &ftrace_filter_fops); -- cgit v1.2.2 From bd69c30b1d08032d97ab0dabd7a1eb7fb73ca2b2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 3 May 2011 21:55:54 -0400 Subject: ftrace: Add ops parameter to ftrace_startup/shutdown functions In order to allow different ops to enable different functions, the ftrace_startup() and ftrace_shutdown() functions need the ops parameter passed to them. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 065f1e61e103..8fef1d99bbbf 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1522,10 +1522,8 @@ static void ftrace_startup_enable(int command) ftrace_run_update_code(command); } -static void ftrace_startup(int command) +static void ftrace_startup(struct ftrace_ops *ops, int command) { - struct ftrace_ops *ops = &global_ops; - if (unlikely(ftrace_disabled)) return; @@ -1539,10 +1537,8 @@ static void ftrace_startup(int command) ftrace_startup_enable(command); } -static void ftrace_shutdown(int command) +static void ftrace_shutdown(struct ftrace_ops *ops, int command) { - struct ftrace_ops *ops = &global_ops; - if (unlikely(ftrace_disabled)) return; @@ -2362,7 +2358,7 @@ static void __enable_ftrace_function_probe(void) return; __register_ftrace_function(&trace_probe_ops); - ftrace_startup(0); + ftrace_startup(&global_ops, 0); ftrace_probe_registered = 1; } @@ -2381,7 +2377,7 @@ static void __disable_ftrace_function_probe(void) /* no more funcs left */ __unregister_ftrace_function(&trace_probe_ops); - ftrace_shutdown(0); + ftrace_shutdown(&global_ops, 0); ftrace_probe_registered = 0; } @@ -3267,6 +3263,10 @@ void __init ftrace_init(void) #else +struct ftrace_ops global_ops = { + .func = ftrace_stub, +}; + static int __init ftrace_nodyn_init(void) { ftrace_enabled = 1; @@ -3277,8 +3277,8 @@ device_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } /* Keep as macros so we do not need to define the commands */ -# define ftrace_startup(command) do { } while (0) -# define ftrace_shutdown(command) do { } while (0) +# define ftrace_startup(ops, command) do { } while (0) +# define ftrace_shutdown(ops, command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) #endif /* CONFIG_DYNAMIC_FTRACE */ @@ -3583,7 +3583,7 @@ int register_ftrace_function(struct ftrace_ops *ops) goto out_unlock; ret = __register_ftrace_function(ops); - ftrace_startup(0); + ftrace_startup(&global_ops, 0); out_unlock: mutex_unlock(&ftrace_lock); @@ -3602,7 +3602,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); ret = __unregister_ftrace_function(ops); - ftrace_shutdown(0); + ftrace_shutdown(&global_ops, 0); mutex_unlock(&ftrace_lock); return ret; @@ -3825,7 +3825,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, ftrace_graph_return = retfunc; ftrace_graph_entry = entryfunc; - ftrace_startup(FTRACE_START_FUNC_RET); + ftrace_startup(&global_ops, FTRACE_START_FUNC_RET); out: mutex_unlock(&ftrace_lock); @@ -3842,7 +3842,7 @@ void unregister_ftrace_graph(void) ftrace_graph_active--; ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; ftrace_graph_entry = ftrace_graph_entry_stub; - ftrace_shutdown(FTRACE_STOP_FUNC_RET); + ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET); unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -- cgit v1.2.2 From 2b499381bc50ede01b3d8eab164ca2fad00655f0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 3 May 2011 22:49:52 -0400 Subject: ftrace: Have global_ops store the functions that are to be traced This is a step towards each ops structure defining its own set of functions to trace. As the current code with pid's and such are specific to the global_ops, it is restructured to be used with the global ops. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 69 +++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 53 insertions(+), 16 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8fef1d99bbbf..dcce0bf9c84d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -91,6 +91,7 @@ static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; +static struct ftrace_ops global_ops; /* * Traverse the ftrace_list, invoking all entries. The reason that we @@ -153,7 +154,7 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) } #endif -static void update_ftrace_function(void) +static void update_global_ops(void) { ftrace_func_t func; @@ -173,6 +174,18 @@ static void update_ftrace_function(void) set_ftrace_pid_function(func); func = ftrace_pid_func; } + + global_ops.func = func; +} + +static void update_ftrace_function(void) +{ + ftrace_func_t func; + + update_global_ops(); + + func = global_ops.func; + #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; #else @@ -181,24 +194,19 @@ static void update_ftrace_function(void) #endif } -static int __register_ftrace_function(struct ftrace_ops *ops) +static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { - ops->next = ftrace_list; + ops->next = *list; /* * We are entering ops into the ftrace_list but another * CPU might be walking that list. We need to make sure * the ops->next pointer is valid before another CPU sees * the ops pointer included into the ftrace_list. */ - rcu_assign_pointer(ftrace_list, ops); - - if (ftrace_enabled) - update_ftrace_function(); - - return 0; + rcu_assign_pointer(*list, ops); } -static int __unregister_ftrace_function(struct ftrace_ops *ops) +static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { struct ftrace_ops **p; @@ -206,13 +214,12 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) * If we are removing the last function, then simply point * to the ftrace_stub. */ - if (ftrace_list == ops && ops->next == &ftrace_list_end) { - ftrace_trace_function = ftrace_stub; - ftrace_list = &ftrace_list_end; + if (*list == ops && ops->next == &ftrace_list_end) { + *list = &ftrace_list_end; return 0; } - for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next) + for (p = list; *p != &ftrace_list_end; p = &(*p)->next) if (*p == ops) break; @@ -220,7 +227,37 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) return -1; *p = (*p)->next; + return 0; +} + +static int __register_ftrace_function(struct ftrace_ops *ops) +{ + if (ftrace_disabled) + return -ENODEV; + + if (FTRACE_WARN_ON(ops == &global_ops)) + return -EINVAL; + + add_ftrace_ops(&ftrace_list, ops); + if (ftrace_enabled) + update_ftrace_function(); + + return 0; +} +static int __unregister_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + if (ftrace_disabled) + return -ENODEV; + + if (FTRACE_WARN_ON(ops == &global_ops)) + return -EINVAL; + + ret = remove_ftrace_ops(&ftrace_list, ops); + if (ret < 0) + return ret; if (ftrace_enabled) update_ftrace_function(); @@ -894,7 +931,7 @@ enum { FTRACE_OPS_FL_ENABLED = 1, }; -struct ftrace_ops global_ops = { +static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, .filter_hash = EMPTY_HASH, @@ -3263,7 +3300,7 @@ void __init ftrace_init(void) #else -struct ftrace_ops global_ops = { +static struct ftrace_ops global_ops = { .func = ftrace_stub, }; -- cgit v1.2.2 From 07fd5515f3b5c20704707f63e7f4485b534508a8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 May 2011 18:03:47 -0400 Subject: ftrace: Free hash with call_rcu_sched() When a hash is modified and might be in use, we need to perform a schedule RCU operation on it, as the hashes will soon be used directly in the function tracer callback. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 55 ++++++++++++++++++++++++++------------------------- 1 file changed, 28 insertions(+), 27 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index dcce0bf9c84d..92b6fdf49ae5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -913,6 +913,7 @@ struct ftrace_hash { unsigned long size_bits; struct hlist_head *buckets; unsigned long count; + struct rcu_head rcu; }; /* @@ -1058,6 +1059,21 @@ static void free_ftrace_hash(struct ftrace_hash *hash) kfree(hash); } +static void __free_ftrace_hash_rcu(struct rcu_head *rcu) +{ + struct ftrace_hash *hash; + + hash = container_of(rcu, struct ftrace_hash, rcu); + free_ftrace_hash(hash); +} + +static void free_ftrace_hash_rcu(struct ftrace_hash *hash) +{ + if (!hash || hash == EMPTY_HASH) + return; + call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); +} + static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { struct ftrace_hash *hash; @@ -1122,7 +1138,8 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) struct ftrace_func_entry *entry; struct hlist_node *tp, *tn; struct hlist_head *hhd; - struct ftrace_hash *hash = *dst; + struct ftrace_hash *old_hash; + struct ftrace_hash *new_hash; unsigned long key; int size = src->count; int bits = 0; @@ -1133,13 +1150,11 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) * the empty_hash. */ if (!src->count) { - free_ftrace_hash(*dst); - *dst = EMPTY_HASH; + free_ftrace_hash_rcu(*dst); + rcu_assign_pointer(*dst, EMPTY_HASH); return 0; } - ftrace_hash_clear(hash); - /* * Make the hash size about 1/2 the # found */ @@ -1150,27 +1165,9 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) if (bits > FTRACE_HASH_MAX_BITS) bits = FTRACE_HASH_MAX_BITS; - /* We can't modify the empty_hash */ - if (hash == EMPTY_HASH) { - /* Create a new hash */ - *dst = alloc_ftrace_hash(bits); - if (!*dst) { - *dst = EMPTY_HASH; - return -ENOMEM; - } - hash = *dst; - } else { - size = 1 << bits; - - /* Use the old hash, but create new buckets */ - hhd = kzalloc(sizeof(*hhd) * size, GFP_KERNEL); - if (!hhd) - return -ENOMEM; - - kfree(hash->buckets); - hash->buckets = hhd; - hash->size_bits = bits; - } + new_hash = alloc_ftrace_hash(bits); + if (!new_hash) + return -ENOMEM; size = 1 << src->size_bits; for (i = 0; i < size; i++) { @@ -1181,10 +1178,14 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) else key = 0; remove_hash_entry(src, entry); - __add_hash_entry(hash, entry); + __add_hash_entry(new_hash, entry); } } + old_hash = *dst; + rcu_assign_pointer(*dst, new_hash); + free_ftrace_hash_rcu(old_hash); + return 0; } -- cgit v1.2.2 From b848914ce39589d89ee0078a6d1ef452b464729e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 4 May 2011 09:27:52 -0400 Subject: ftrace: Implement separate user function filtering ftrace_ops that are registered to trace functions can now be agnostic to each other in respect to what functions they trace. Each ops has their own hash of the functions they want to trace and a hash to what they do not want to trace. A empty hash for the functions they want to trace denotes all functions should be traced that are not in the notrace hash. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 193 ++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 155 insertions(+), 38 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 92b6fdf49ae5..6c7e1df39b57 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -87,24 +87,29 @@ static struct ftrace_ops ftrace_list_end __read_mostly = .func = ftrace_stub, }; -static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; +static void +ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); + /* - * Traverse the ftrace_list, invoking all entries. The reason that we + * Traverse the ftrace_global_list, invoking all entries. The reason that we * can use rcu_dereference_raw() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period * mechanism. The rcu_dereference_raw() calls are needed to handle - * concurrent insertions into the ftrace_list. + * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_global_list_func(unsigned long ip, + unsigned long parent_ip) { - struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/ + struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { op->func(ip, parent_ip); @@ -163,11 +168,11 @@ static void update_global_ops(void) * function directly. Otherwise, we need to iterate over the * registered callers. */ - if (ftrace_list == &ftrace_list_end || - ftrace_list->next == &ftrace_list_end) - func = ftrace_list->func; + if (ftrace_global_list == &ftrace_list_end || + ftrace_global_list->next == &ftrace_list_end) + func = ftrace_global_list->func; else - func = ftrace_list_func; + func = ftrace_global_list_func; /* If we filter on pids, update to use the pid function */ if (!list_empty(&ftrace_pids)) { @@ -184,7 +189,11 @@ static void update_ftrace_function(void) update_global_ops(); - func = global_ops.func; + if (ftrace_ops_list == &ftrace_list_end || + ftrace_ops_list->next == &ftrace_list_end) + func = ftrace_ops_list->func; + else + func = ftrace_ops_list_func; #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; @@ -198,10 +207,10 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { ops->next = *list; /* - * We are entering ops into the ftrace_list but another + * We are entering ops into the list but another * CPU might be walking that list. We need to make sure * the ops->next pointer is valid before another CPU sees - * the ops pointer included into the ftrace_list. + * the ops pointer included into the list. */ rcu_assign_pointer(*list, ops); } @@ -238,7 +247,18 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; - add_ftrace_ops(&ftrace_list, ops); + if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EBUSY; + + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + int first = ftrace_global_list == &ftrace_list_end; + add_ftrace_ops(&ftrace_global_list, ops); + ops->flags |= FTRACE_OPS_FL_ENABLED; + if (first) + add_ftrace_ops(&ftrace_ops_list, &global_ops); + } else + add_ftrace_ops(&ftrace_ops_list, ops); + if (ftrace_enabled) update_ftrace_function(); @@ -252,12 +272,24 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_disabled) return -ENODEV; + if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED))) + return -EBUSY; + if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; - ret = remove_ftrace_ops(&ftrace_list, ops); + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ret = remove_ftrace_ops(&ftrace_global_list, ops); + if (!ret && ftrace_global_list == &ftrace_list_end) + ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops); + if (!ret) + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } else + ret = remove_ftrace_ops(&ftrace_ops_list, ops); + if (ret < 0) return ret; + if (ftrace_enabled) update_ftrace_function(); @@ -928,10 +960,6 @@ static const struct ftrace_hash empty_hash = { }; #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) -enum { - FTRACE_OPS_FL_ENABLED = 1, -}; - static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, @@ -1189,6 +1217,40 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) return 0; } +/* + * Test the hashes for this ops to see if we want to call + * the ops->func or not. + * + * It's a match if the ip is in the ops->filter_hash or + * the filter_hash does not exist or is empty, + * AND + * the ip is not in the ops->notrace_hash. + */ +static int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +{ + struct ftrace_hash *filter_hash; + struct ftrace_hash *notrace_hash; + int ret; + + /* The hashes are freed with call_rcu_sched() */ + preempt_disable_notrace(); + + filter_hash = rcu_dereference_raw(ops->filter_hash); + notrace_hash = rcu_dereference_raw(ops->notrace_hash); + + if ((!filter_hash || !filter_hash->count || + ftrace_lookup_ip(filter_hash, ip)) && + (!notrace_hash || !notrace_hash->count || + !ftrace_lookup_ip(notrace_hash, ip))) + ret = 1; + else + ret = 0; + preempt_enable_notrace(); + + return ret; +} + /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. @@ -1232,7 +1294,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (filter_hash) { hash = ops->filter_hash; other_hash = ops->notrace_hash; - if (!hash->count) + if (!hash || !hash->count) all = 1; } else { inc = !inc; @@ -1242,7 +1304,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * If the notrace hash has no items, * then there's nothing to do. */ - if (!hash->count) + if (hash && !hash->count) return; } @@ -1256,11 +1318,11 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * Only the filter_hash affects all records. * Update if the record is not in the notrace hash. */ - if (!ftrace_lookup_ip(other_hash, rec->ip)) + if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip)) match = 1; } else { - in_hash = !!ftrace_lookup_ip(hash, rec->ip); - in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); + in_hash = hash && !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = other_hash && !!ftrace_lookup_ip(other_hash, rec->ip); /* * @@ -1546,6 +1608,7 @@ static void ftrace_run_update_code(int command) static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; +static int global_start_up; static void ftrace_startup_enable(int command) { @@ -1562,14 +1625,25 @@ static void ftrace_startup_enable(int command) static void ftrace_startup(struct ftrace_ops *ops, int command) { + bool hash_enable = true; + if (unlikely(ftrace_disabled)) return; ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; + /* ops marked global share the filter hashes */ + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ops = &global_ops; + /* Don't update hash if global is already set */ + if (global_start_up) + hash_enable = false; + global_start_up++; + } + ops->flags |= FTRACE_OPS_FL_ENABLED; - if (ftrace_start_up == 1) + if (hash_enable) ftrace_hash_rec_enable(ops, 1); ftrace_startup_enable(command); @@ -1577,6 +1651,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command) static void ftrace_shutdown(struct ftrace_ops *ops, int command) { + bool hash_disable = true; + if (unlikely(ftrace_disabled)) return; @@ -1588,13 +1664,25 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command) */ WARN_ON_ONCE(ftrace_start_up < 0); - if (!ftrace_start_up) + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ops = &global_ops; + global_start_up--; + WARN_ON_ONCE(global_start_up < 0); + /* Don't update hash if global still has users */ + if (global_start_up) { + WARN_ON_ONCE(!ftrace_start_up); + hash_disable = false; + } + } + + if (hash_disable) ftrace_hash_rec_disable(ops, 1); - if (!ftrace_start_up) { - command |= FTRACE_DISABLE_CALLS; + if (ops != &global_ops || !global_start_up) ops->flags &= ~FTRACE_OPS_FL_ENABLED; - } + + if (!ftrace_start_up) + command |= FTRACE_DISABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -2381,6 +2469,7 @@ static int ftrace_probe_registered; static void __enable_ftrace_function_probe(void) { + int ret; int i; if (ftrace_probe_registered) @@ -2395,13 +2484,16 @@ static void __enable_ftrace_function_probe(void) if (i == FTRACE_FUNC_HASHSIZE) return; - __register_ftrace_function(&trace_probe_ops); - ftrace_startup(&global_ops, 0); + ret = __register_ftrace_function(&trace_probe_ops); + if (!ret) + ftrace_startup(&trace_probe_ops, 0); + ftrace_probe_registered = 1; } static void __disable_ftrace_function_probe(void) { + int ret; int i; if (!ftrace_probe_registered) @@ -2414,8 +2506,10 @@ static void __disable_ftrace_function_probe(void) } /* no more funcs left */ - __unregister_ftrace_function(&trace_probe_ops); - ftrace_shutdown(&global_ops, 0); + ret = __unregister_ftrace_function(&trace_probe_ops); + if (!ret) + ftrace_shutdown(&trace_probe_ops, 0); + ftrace_probe_registered = 0; } @@ -3319,8 +3413,28 @@ static inline void ftrace_startup_enable(int command) { } # define ftrace_shutdown(ops, command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) + +static inline int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +{ + return 1; +} + #endif /* CONFIG_DYNAMIC_FTRACE */ +static void +ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +{ + /* see comment above ftrace_global_list_func */ + struct ftrace_ops *op = rcu_dereference_raw(ftrace_ops_list); + + while (op != &ftrace_list_end) { + if (ftrace_ops_test(op, ip)) + op->func(ip, parent_ip); + op = rcu_dereference_raw(op->next); + }; +} + static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -3621,7 +3735,9 @@ int register_ftrace_function(struct ftrace_ops *ops) goto out_unlock; ret = __register_ftrace_function(ops); - ftrace_startup(&global_ops, 0); + if (!ret) + ftrace_startup(ops, 0); + out_unlock: mutex_unlock(&ftrace_lock); @@ -3640,7 +3756,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); ret = __unregister_ftrace_function(ops); - ftrace_shutdown(&global_ops, 0); + if (!ret) + ftrace_shutdown(ops, 0); mutex_unlock(&ftrace_lock); return ret; @@ -3670,11 +3787,11 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); /* we are starting ftrace again */ - if (ftrace_list != &ftrace_list_end) { - if (ftrace_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_list->func; + if (ftrace_ops_list != &ftrace_list_end) { + if (ftrace_ops_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_ops_list->func; else - ftrace_trace_function = ftrace_list_func; + ftrace_trace_function = ftrace_ops_list_func; } } else { -- cgit v1.2.2 From cdbe61bfe70440939e457fb4a8d0995eaaed17de Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 May 2011 21:14:55 -0400 Subject: ftrace: Allow dynamically allocated function tracers Now that functions may be selected individually, it only makes sense that we should allow dynamically allocated trace structures to be traced. This will allow perf to allocate a ftrace_ops structure at runtime and use it to pick and choose which functions that structure will trace. Note, a dynamically allocated ftrace_ops will always be called indirectly instead of being called directly from the mcount in entry.S. This is because there's no safe way to prevent mcount from being preempted before calling the function, unless we modify every entry.S to do so (not likely). Thus, dynamically allocated functions will now be called by the ftrace_ops_list_func() that loops through the ops that are allocated if there are more than one op allocated at a time. This loop is protected with a preempt_disable. To determine if an ftrace_ops structure is allocated or not, a new util function was added to the kernel/extable.c called core_kernel_data(), which returns 1 if the address is between _sdata and _edata. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6c7e1df39b57..5b3ee04e39d9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -189,8 +189,14 @@ static void update_ftrace_function(void) update_global_ops(); + /* + * If we are at the end of the list and this ops is + * not dynamic, then have the mcount trampoline call + * the function directly + */ if (ftrace_ops_list == &ftrace_list_end || - ftrace_ops_list->next == &ftrace_list_end) + (ftrace_ops_list->next == &ftrace_list_end && + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) func = ftrace_ops_list->func; else func = ftrace_ops_list_func; @@ -250,6 +256,9 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) return -EBUSY; + if (!core_kernel_data((unsigned long)ops)) + ops->flags |= FTRACE_OPS_FL_DYNAMIC; + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { int first = ftrace_global_list == &ftrace_list_end; add_ftrace_ops(&ftrace_global_list, ops); @@ -293,6 +302,13 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_enabled) update_ftrace_function(); + /* + * Dynamic ops may be freed, we must make sure that all + * callers are done before leaving this function. + */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC) + synchronize_sched(); + return 0; } @@ -1225,6 +1241,9 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src) * the filter_hash does not exist or is empty, * AND * the ip is not in the ops->notrace_hash. + * + * This needs to be called with preemption disabled as + * the hashes are freed with call_rcu_sched(). */ static int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) @@ -1233,9 +1252,6 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) struct ftrace_hash *notrace_hash; int ret; - /* The hashes are freed with call_rcu_sched() */ - preempt_disable_notrace(); - filter_hash = rcu_dereference_raw(ops->filter_hash); notrace_hash = rcu_dereference_raw(ops->notrace_hash); @@ -1246,7 +1262,6 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) ret = 1; else ret = 0; - preempt_enable_notrace(); return ret; } @@ -3425,14 +3440,20 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { - /* see comment above ftrace_global_list_func */ - struct ftrace_ops *op = rcu_dereference_raw(ftrace_ops_list); + struct ftrace_ops *op; + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) op->func(ip, parent_ip); op = rcu_dereference_raw(op->next); }; + preempt_enable_notrace(); } static void clear_ftrace_swapper(void) @@ -3743,6 +3764,7 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_unlock(&ftrace_lock); return ret; } +EXPORT_SYMBOL_GPL(register_ftrace_function); /** * unregister_ftrace_function - unregister a function for profiling. @@ -3762,6 +3784,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) return ret; } +EXPORT_SYMBOL_GPL(unregister_ftrace_function); int ftrace_enable_sysctl(struct ctl_table *table, int write, -- cgit v1.2.2 From 936e074b286ae779f134312178dbab139ee7ea52 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 May 2011 22:54:01 -0400 Subject: ftrace: Modify ftrace_set_filter/notrace to take ops Since users of the function tracer can now pick and choose which functions they want to trace agnostically from other users of the function tracer, we need to pass the ops struct to the ftrace_set_filter() functions. The functions ftrace_set_global_filter() and ftrace_set_global_notrace() is added to keep the old filter functions which are used to modify the generic function tracers. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 46 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 44 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5b3ee04e39d9..d017c2c82c44 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2826,6 +2826,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, struct ftrace_hash *hash; int ret; + /* All global ops uses the global ops filters */ + if (ops->flags & FTRACE_OPS_FL_GLOBAL) + ops = &global_ops; + if (unlikely(ftrace_disabled)) return -ENODEV; @@ -2856,6 +2860,41 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, /** * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) +{ + ftrace_set_regex(ops, buf, len, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter); + +/** + * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with + * @buf - the string that holds the function notrace text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Notrace Filters denote which functions should not be enabled when tracing + * is enabled. If @buf is NULL and reset is set, all functions will be enabled + * for tracing. + */ +void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) +{ + ftrace_set_regex(ops, buf, len, reset, 0); +} +EXPORT_SYMBOL_GPL(ftrace_set_notrace); +/** + * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with * @buf - the string that holds the function filter text. * @len - the length of the string. * @reset - non zero to reset all filters before applying this filter. @@ -2863,13 +2902,15 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. */ -void ftrace_set_filter(unsigned char *buf, int len, int reset) +void ftrace_set_global_filter(unsigned char *buf, int len, int reset) { ftrace_set_regex(&global_ops, buf, len, reset, 1); } +EXPORT_SYMBOL_GPL(ftrace_set_global_filter); /** * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with * @buf - the string that holds the function notrace text. * @len - the length of the string. * @reset - non zero to reset all filters before applying this filter. @@ -2878,10 +2919,11 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. */ -void ftrace_set_notrace(unsigned char *buf, int len, int reset) +void ftrace_set_global_notrace(unsigned char *buf, int len, int reset) { ftrace_set_regex(&global_ops, buf, len, reset, 0); } +EXPORT_SYMBOL_GPL(ftrace_set_global_notrace); /* * command line interface to allow users to set filters on boot up. -- cgit v1.2.2 From a1cd6173596c6f7d1f0b41ac7d33ecf03c581edc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 May 2011 15:24:25 -0400 Subject: ftrace: Have ftrace_startup() return failure code The register_ftrace_function() returns an error code on failure except if the call to ftrace_startup() fails. Add a error return to ftrace_startup() if it fails to start, allowing register_ftrace_funtion() to return a proper error value. Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d017c2c82c44..bebbc959ee8c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1638,12 +1638,12 @@ static void ftrace_startup_enable(int command) ftrace_run_update_code(command); } -static void ftrace_startup(struct ftrace_ops *ops, int command) +static int ftrace_startup(struct ftrace_ops *ops, int command) { bool hash_enable = true; if (unlikely(ftrace_disabled)) - return; + return -ENODEV; ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; @@ -1662,6 +1662,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command) ftrace_hash_rec_enable(ops, 1); ftrace_startup_enable(command); + + return 0; } static void ftrace_shutdown(struct ftrace_ops *ops, int command) @@ -2501,7 +2503,7 @@ static void __enable_ftrace_function_probe(void) ret = __register_ftrace_function(&trace_probe_ops); if (!ret) - ftrace_startup(&trace_probe_ops, 0); + ret = ftrace_startup(&trace_probe_ops, 0); ftrace_probe_registered = 1; } @@ -3466,7 +3468,7 @@ device_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } /* Keep as macros so we do not need to define the commands */ -# define ftrace_startup(ops, command) do { } while (0) +# define ftrace_startup(ops, command) ({0;}) # define ftrace_shutdown(ops, command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) @@ -3799,7 +3801,7 @@ int register_ftrace_function(struct ftrace_ops *ops) ret = __register_ftrace_function(ops); if (!ret) - ftrace_startup(ops, 0); + ret = ftrace_startup(ops, 0); out_unlock: @@ -4045,7 +4047,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, ftrace_graph_return = retfunc; ftrace_graph_entry = entryfunc; - ftrace_startup(&global_ops, FTRACE_START_FUNC_RET); + ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET); out: mutex_unlock(&ftrace_lock); -- cgit v1.2.2 From 3b6cfdb1714a33ae4d2ca9fbc818a42cf7adee69 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 May 2011 15:33:49 -0400 Subject: ftrace: Set ops->flag to enabled even on static function tracing When dynamic ftrace is not configured, the ops->flags still needs to have its FTRACE_OPS_FL_ENABLED bit set in ftrace_startup(). Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index bebbc959ee8c..25949b33057c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3468,7 +3468,11 @@ device_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } /* Keep as macros so we do not need to define the commands */ -# define ftrace_startup(ops, command) ({0;}) +# define ftrace_startup(ops, command) \ + ({ \ + (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ + 0; \ + }) # define ftrace_shutdown(ops, command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) -- cgit v1.2.2 From b1cff0ad1062621ae63cb6c5dc4165191fe2e9f1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 May 2011 14:27:43 -0400 Subject: ftrace: Add internal recursive checks Witold reported a reboot caused by the selftests of the dynamic function tracer. He sent me a config and I used ktest to do a config_bisect on it (as my config did not cause the crash). It pointed out that the problem config was CONFIG_PROVE_RCU. What happened was that if multiple callbacks are attached to the function tracer, we iterate a list of callbacks. Because the list is managed by synchronize_sched() and preempt_disable, the access to the pointers uses rcu_dereference_raw(). When PROVE_RCU is enabled, the rcu_dereference_raw() calls some debugging functions, which happen to be traced. The tracing of the debug function would then call rcu_dereference_raw() which would then call the debug function and then... well you get the idea. I first wrote two different patches to solve this bug. 1) add a __rcu_dereference_raw() that would not do any checks. 2) add notrace to the offending debug functions. Both of these patches worked. Talking with Paul McKenney on IRC, he suggested to add recursion detection instead. This seemed to be a better solution, so I decided to implement it. As the task_struct already has a trace_recursion to detect recursion in the ring buffer, and that has a very small number it allows, I decided to use that same variable to add flags that can detect the recursion inside the infrastructure of the function tracer. I plan to change it so that the task struct bit can be checked in mcount, but as that requires changes to all archs, I will hold that off to the next merge window. Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Frederic Weisbecker Cc: Paul E. McKenney Link: http://lkml.kernel.org/r/1306348063.1465.116.camel@gandalf.stny.rr.com Reported-by: Witold Baryluk Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 25949b33057c..1ee417fcbfa5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -109,12 +109,18 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); static void ftrace_global_list_func(unsigned long ip, unsigned long parent_ip) { - struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/ + struct ftrace_ops *op; + + if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) + return; + trace_recursion_set(TRACE_GLOBAL_BIT); + op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { op->func(ip, parent_ip); op = rcu_dereference_raw(op->next); /*see above*/ }; + trace_recursion_clear(TRACE_GLOBAL_BIT); } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) @@ -3490,6 +3496,10 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { struct ftrace_ops *op; + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) + return; + + trace_recursion_set(TRACE_INTERNAL_BIT); /* * Some of the ops may be dynamically allocated, * they must be freed after a synchronize_sched(). @@ -3502,6 +3512,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); + trace_recursion_clear(TRACE_INTERNAL_BIT); } static void clear_ftrace_swapper(void) -- cgit v1.2.2 From 0aff1c0cef13b34c17e81a502336fad738151c37 Mon Sep 17 00:00:00 2001 From: GuoWen Li Date: Wed, 1 Jun 2011 19:18:47 +0800 Subject: ftrace: Fix possible undefined return code kernel/trace/ftrace.c: In function 'ftrace_regex_write.clone.15': kernel/trace/ftrace.c:2743:6: warning: 'ret' may be used uninitialized in this function Signed-off-by: GuoWen Li Link: http://lkml.kernel.org/r/201106011918.47939.guowen.li.linux@gmail.com Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1ee417fcbfa5..204b3eb4e690 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2740,7 +2740,7 @@ static int ftrace_process_regex(struct ftrace_hash *hash, { char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret; + int ret = -EINVAL; func = strsep(&next, ":"); -- cgit v1.2.2 From a4f18ed11a4ddf327dd91cd19e237278600ad327 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 7 Jun 2011 09:26:46 -0400 Subject: ftrace: Revert 8ab2b7efd ftrace: Remove unnecessary disabling of irqs Revert the commit that removed the disabling of interrupts around the initial modifying of mcount callers to nops, and update the comment. The original comment was outdated and stated that the interrupts were being disabled to prevent kstop machine, which was required with the old ftrace daemon, but was no longer the case. What the comment failed to mention was that interrupts needed to be disabled to keep interrupts from preempting the modifying of the code and then executing the code that was partially modified. Revert the commit and update the comment. Reported-by: Richard W.M. Jones Tested-by: Richard W.M. Jones Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/trace/ftrace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 204b3eb4e690..908038f57440 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3330,6 +3330,7 @@ static int ftrace_process_locs(struct module *mod, { unsigned long *p; unsigned long addr; + unsigned long flags; mutex_lock(&ftrace_lock); p = start; @@ -3346,7 +3347,13 @@ static int ftrace_process_locs(struct module *mod, ftrace_record_ip(addr); } + /* + * Disable interrupts to prevent interrupts from executing + * code that is being modified. + */ + local_irq_save(flags); ftrace_update_code(mod); + local_irq_restore(flags); mutex_unlock(&ftrace_lock); return 0; -- cgit v1.2.2