UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

This is mostly clean ups and small fixes. Some of the more visible 

changes are:
 
  . The function pid code uses the event pid filtering logic
  . [ku]probe events have access to current->comm
  . trace_printk now has sample code
  . PCI devices now trace physical addresses
  . stack tracing has less unnessary functions traced
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJXl+d2AAoJEKKk/i67LK/83QEH/RDJ0mcfFVsuEeOnZZrZXABm
 4Rxk4FE5UAD+TSrVycwwzcbQab1iPK63mMdYvIBvaOiIC6/OJaEVM7jzZxnNGqmr
 pj0H8bxwOr58pe5pfnP92ow5qTLLzsXraWNl5sRXhSSHON7CXpGVzkErB58GmMYd
 8p6d9ziifQjo8X2O6XC9rGAvYLY5kEkVvyfuE1hI7muNTeOjyOT4EqpkNzxdBk+I
 QkGZGsk3Xhc8II9nu8FPWkaD26TatGJoZtZmVWHOzfsb3HNzG4RXla+WVOQ5u1HV
 noVyB1CJHhkO5CEBPdYIqwBWPQU4B9HfG4gVcUpDDVRxfzMpnEcKi1uwe+uDjfs=
 =XFcv
 -----END PGP SIGNATURE-----

Merge tag 'trace-v4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "This is mostly clean ups and small fixes.  Some of the more visible
  changes are:

   - The function pid code uses the event pid filtering logic
   - [ku]probe events have access to current->comm
   - trace_printk now has sample code
   - PCI devices now trace physical addresses
   - stack tracing has less unnessary functions traced"

* tag 'trace-v4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  printk, tracing: Avoiding unneeded blank lines
  tracing: Use __get_str() when manipulating strings
  tracing, RAS: Cleanup on __get_str() usage
  tracing: Use outer () on __get_str() definition
  ftrace: Reduce size of function graph entries
  tracing: Have HIST_TRIGGERS select TRACING
  tracing: Using for_each_set_bit() to simplify trace_pid_write()
  ftrace: Move toplevel init out of ftrace_init_tracefs()
  tracing/function_graph: Fix filters for function_graph threshold
  tracing: Skip more functions when doing stack tracing of events
  tracing: Expose CPU physical addresses (resource values) for PCI devices
  tracing: Show the preempt count of when the event was called
  tracing: Add trace_printk sample code
  tracing: Choose static tp_printk buffer by explicit nesting count
  tracing: expose current->comm to [ku]probe events
  ftrace: Have set_ftrace_pid use the bitmap like events do
  tracing: Move pid_list write processing into its own function
  tracing: Move the pid_list seq_file functions to be global
  tracing: Move filtered_pid helper functions into trace.c
  tracing: Make the pid filtering helper functions global
This commit is contained in:
Linus Torvalds 2016-07-28 18:20:09 -07:00
parent e55884d2c6 78aebca2c9
commit c624c86615
25 changed files with 677 additions and 478 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
Documentation/trace/kprobetrace.txt
View File

@ -40,6 +40,7 @@ Synopsis of kprobe_events
$stackN : Fetch Nth entry of stack (N >= 0)
$stack : Fetch stack address.
$retval : Fetch return value.(*)
$comm : Fetch current task comm.
+|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
@ -62,6 +63,8 @@ offset, and container-size (usually 32). The syntax is;
b<bit-width>@<bit-offset>/<container-size>
For $comm, the default type is "string"; any other type is invalid.
Per-Probe Event Filtering
-------------------------

3
Documentation/trace/uprobetracer.txt
View File

@ -36,6 +36,7 @@ Synopsis of uprobe_tracer
$stackN : Fetch Nth entry of stack (N >= 0)
$stack : Fetch stack address.
$retval : Fetch return value.(*)
$comm : Fetch current task comm.
+|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
@ -57,6 +58,8 @@ offset, and container-size (usually 32). The syntax is;
b<bit-width>@<bit-offset>/<container-size>
For $comm, the default type is "string"; any other type is invalid.
Event Profiling
---------------

4
fs/nfs/nfs4trace.h
View File

@ -1235,8 +1235,8 @@ DECLARE_EVENT_CLASS(nfs4_idmap_event,
len = 0;
__entry->error = error < 0 ? error : 0;
__entry->id = id;
memcpy(__get_dynamic_array(name), name, len);
((char *)__get_dynamic_array(name))[len] = 0;
memcpy(__get_str(name), name, len);
__get_str(name)[len] = 0;
),
TP_printk(

4
fs/nfs/nfstrace.h
View File

@ -707,9 +707,9 @@ TRACE_EVENT(nfs_sillyrename_unlink,
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
__entry->error = error;
memcpy(__get_dynamic_array(name),
memcpy(__get_str(name),
data->args.name.name, len);
((char *)__get_dynamic_array(name))[len] = 0;
__get_str(name)[len] = 0;
),
TP_printk(

12
include/linux/ftrace.h
View File

@ -754,23 +754,27 @@ static inline void ftrace_init(void) { }
/*
* Structure that defines an entry function trace.
* It's already packed but the attribute "packed" is needed
* to remove extra padding at the end.
*/
struct ftrace_graph_ent {
unsigned long func; /* Current function */
int depth;
};
} __packed;
/*
* Structure that defines a return function trace.
* It's already packed but the attribute "packed" is needed
* to remove extra padding at the end.
*/
struct ftrace_graph_ret {
unsigned long func; /* Current function */
unsigned long long calltime;
unsigned long long rettime;
/* Number of functions that overran the depth limit for current task */
unsigned long overrun;
unsigned long long calltime;
unsigned long long rettime;
int depth;
};
} __packed;
/* Type of the callback handlers for tracing function graph*/
typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */

4
include/ras/ras_event.h
View File

@ -147,7 +147,7 @@ TRACE_EVENT(mc_event,
__entry->error_count,
mc_event_error_type(__entry->error_type),
__entry->error_count > 1 ? "s" : "",
((char *)__get_str(msg))[0] ? " " : "",
__get_str(msg)[0] ? " " : "",
__get_str(msg),
__get_str(label),
__entry->mc_index,
@ -157,7 +157,7 @@ TRACE_EVENT(mc_event,
__entry->address,
1 << __entry->grain_bits,
__entry->syndrome,
((char *)__get_str(driver_detail))[0] ? " " : "",
__get_str(driver_detail)[0] ? " " : "",
__get_str(driver_detail))
);

12
include/trace/events/printk.h
View File

@ -16,8 +16,16 @@ TRACE_EVENT(console,
),
TP_fast_assign(
memcpy(__get_dynamic_array(msg), text, len);
((char *)__get_dynamic_array(msg))[len] = 0;
/*
* Each trace entry is printed in a new line.
* If the msg finishes with '\n', cut it off
* to avoid blank lines in the trace.
*/
if ((len > 0) && (text[len-1] == '\n'))
len -= 1;
memcpy(__get_str(msg), text, len);
__get_str(msg)[len] = 0;
),
TP_printk("%s", __get_str(msg))

2
include/trace/perf.h
View File

@ -15,7 +15,7 @@
((__entry->__data_loc_##field >> 16) & 0xffff)
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
#define __get_str(field) ((char *)__get_dynamic_array(field))
#undef __get_bitmask
#define __get_bitmask(field) (char *)__get_dynamic_array(field)

2
include/trace/trace_events.h
View File

@ -256,7 +256,7 @@ TRACE_MAKE_SYSTEM_STR();
((__entry->__data_loc_##field >> 16) & 0xffff)
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
#define __get_str(field) ((char *)__get_dynamic_array(field))
#undef __get_bitmask
#define __get_bitmask(field) \

1
kernel/trace/Kconfig
View File

@ -542,6 +542,7 @@ config HIST_TRIGGERS
bool "Histogram triggers"
depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
select TRACING_MAP
select TRACING
default n
help
Hist triggers allow one or more arbitrary trace event fields

333
kernel/trace/ftrace.c
View File

@ -89,16 +89,16 @@ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
/* What to set function_trace_op to */
static struct ftrace_ops *set_function_trace_op;
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
struct ftrace_pid {
struct list_head list;
struct pid *pid;
};
static bool ftrace_pids_enabled(void)
static bool ftrace_pids_enabled(struct ftrace_ops *ops)
{
return !list_empty(&ftrace_pids);
struct trace_array *tr;
if (!(ops->flags & FTRACE_OPS_FL_PID) || !ops->private)
return false;
tr = ops->private;
return tr->function_pids != NULL;
}
static void ftrace_update_trampoline(struct ftrace_ops *ops);
@ -179,7 +179,9 @@ int ftrace_nr_registered_ops(void)
static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs)
{
if (!test_tsk_trace_trace(current))
struct trace_array *tr = op->private;
if (tr && this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid))
return;
op->saved_func(ip, parent_ip, op, regs);
@ -417,7 +419,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
/* Always save the function, and reset at unregistering */
ops->saved_func = ops->func;
if (ops->flags & FTRACE_OPS_FL_PID && ftrace_pids_enabled())
if (ftrace_pids_enabled(ops))
ops->func = ftrace_pid_func;
ftrace_update_trampoline(ops);
@ -450,7 +452,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
static void ftrace_update_pid_func(void)
{
bool enabled = ftrace_pids_enabled();
struct ftrace_ops *op;
/* Only do something if we are tracing something */
@ -459,8 +460,8 @@ static void ftrace_update_pid_func(void)
do_for_each_ftrace_op(op, ftrace_ops_list) {
if (op->flags & FTRACE_OPS_FL_PID) {
op->func = enabled ? ftrace_pid_func :
op->saved_func;
op->func = ftrace_pids_enabled(op) ?
ftrace_pid_func : op->saved_func;
ftrace_update_trampoline(op);
}
} while_for_each_ftrace_op(op);
@ -5324,134 +5325,46 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
return ops->func;
}
static void clear_ftrace_swapper(void)
static void
ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
struct task_struct *prev, struct task_struct *next)
{
struct task_struct *p;
struct trace_array *tr = data;
struct trace_pid_list *pid_list;
pid_list = rcu_dereference_sched(tr->function_pids);
this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid,
trace_ignore_this_task(pid_list, next));
}
static void clear_ftrace_pids(struct trace_array *tr)
{
struct trace_pid_list *pid_list;
int cpu;
get_online_cpus();
for_each_online_cpu(cpu) {
p = idle_task(cpu);
clear_tsk_trace_trace(p);
}
put_online_cpus();
pid_list = rcu_dereference_protected(tr->function_pids,
lockdep_is_held(&ftrace_lock));
if (!pid_list)
return;
unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
for_each_possible_cpu(cpu)
per_cpu_ptr(tr->trace_buffer.data, cpu)->ftrace_ignore_pid = false;
rcu_assign_pointer(tr->function_pids, NULL);
/* Wait till all users are no longer using pid filtering */
synchronize_sched();
trace_free_pid_list(pid_list);
}
static void set_ftrace_swapper(void)
static void ftrace_pid_reset(struct trace_array *tr)
{
struct task_struct *p;
int cpu;
get_online_cpus();
for_each_online_cpu(cpu) {
p = idle_task(cpu);
set_tsk_trace_trace(p);
}
put_online_cpus();
}
static void clear_ftrace_pid(struct pid *pid)
{
struct task_struct *p;
rcu_read_lock();
do_each_pid_task(pid, PIDTYPE_PID, p) {
clear_tsk_trace_trace(p);
} while_each_pid_task(pid, PIDTYPE_PID, p);
rcu_read_unlock();
put_pid(pid);
}
static void set_ftrace_pid(struct pid *pid)
{
struct task_struct *p;
rcu_read_lock();
do_each_pid_task(pid, PIDTYPE_PID, p) {
set_tsk_trace_trace(p);
} while_each_pid_task(pid, PIDTYPE_PID, p);
rcu_read_unlock();
}
static void clear_ftrace_pid_task(struct pid *pid)
{
if (pid == ftrace_swapper_pid)
clear_ftrace_swapper();
else
clear_ftrace_pid(pid);
}
static void set_ftrace_pid_task(struct pid *pid)
{
if (pid == ftrace_swapper_pid)
set_ftrace_swapper();
else
set_ftrace_pid(pid);
}
static int ftrace_pid_add(int p)
{
struct pid *pid;
struct ftrace_pid *fpid;
int ret = -EINVAL;
mutex_lock(&ftrace_lock);
if (!p)
pid = ftrace_swapper_pid;
else
pid = find_get_pid(p);
if (!pid)
goto out;
ret = 0;
list_for_each_entry(fpid, &ftrace_pids, list)
if (fpid->pid == pid)
goto out_put;
ret = -ENOMEM;
fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
if (!fpid)
goto out_put;
list_add(&fpid->list, &ftrace_pids);
fpid->pid = pid;
set_ftrace_pid_task(pid);
ftrace_update_pid_func();
ftrace_startup_all(0);
mutex_unlock(&ftrace_lock);
return 0;
out_put:
if (pid != ftrace_swapper_pid)
put_pid(pid);
out:
mutex_unlock(&ftrace_lock);
return ret;
}
static void ftrace_pid_reset(void)
{
struct ftrace_pid *fpid, *safe;
mutex_lock(&ftrace_lock);
list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
struct pid *pid = fpid->pid;
clear_ftrace_pid_task(pid);
list_del(&fpid->list);
kfree(fpid);
}
clear_ftrace_pids(tr);
ftrace_update_pid_func();
ftrace_startup_all(0);
@ -5459,44 +5372,52 @@ static void ftrace_pid_reset(void)
mutex_unlock(&ftrace_lock);
}
/* Greater than any max PID */
#define FTRACE_NO_PIDS (void *)(PID_MAX_LIMIT + 1)
static void *fpid_start(struct seq_file *m, loff_t *pos)
__acquires(RCU)
{
struct trace_pid_list *pid_list;
struct trace_array *tr = m->private;
mutex_lock(&ftrace_lock);
rcu_read_lock_sched();
if (!ftrace_pids_enabled() && (!*pos))
return (void *) 1;
pid_list = rcu_dereference_sched(tr->function_pids);
return seq_list_start(&ftrace_pids, *pos);
if (!pid_list)
return !(*pos) ? FTRACE_NO_PIDS : NULL;
return trace_pid_start(pid_list, pos);
}
static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
{
if (v == (void *)1)
struct trace_array *tr = m->private;
struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids);
if (v == FTRACE_NO_PIDS)
return NULL;
return seq_list_next(v, &ftrace_pids, pos);
return trace_pid_next(pid_list, v, pos);
}
static void fpid_stop(struct seq_file *m, void *p)
__releases(RCU)
{
rcu_read_unlock_sched();
mutex_unlock(&ftrace_lock);
}
static int fpid_show(struct seq_file *m, void *v)
{
const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
if (v == (void *)1) {
if (v == FTRACE_NO_PIDS) {
seq_puts(m, "no pid\n");
return 0;
}
if (fpid->pid == ftrace_swapper_pid)
seq_puts(m, "swapper tasks\n");
else
seq_printf(m, "%u\n", pid_vnr(fpid->pid));
return 0;
return trace_pid_show(m, v);
}
static const struct seq_operations ftrace_pid_sops = {
@ -5509,58 +5430,103 @@ static const struct seq_operations ftrace_pid_sops = {
static int
ftrace_pid_open(struct inode *inode, struct file *file)
{
struct trace_array *tr = inode->i_private;
struct seq_file *m;
int ret = 0;
if (trace_array_get(tr) < 0)
return -ENODEV;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
ftrace_pid_reset();
ftrace_pid_reset(tr);
if (file->f_mode & FMODE_READ)
ret = seq_open(file, &ftrace_pid_sops);
ret = seq_open(file, &ftrace_pid_sops);
if (ret < 0) {
trace_array_put(tr);
} else {
m = file->private_data;
/* copy tr over to seq ops */
m->private = tr;
}
return ret;
}
static void ignore_task_cpu(void *data)
{
struct trace_array *tr = data;
struct trace_pid_list *pid_list;
/*
* This function is called by on_each_cpu() while the
* event_mutex is held.
*/
pid_list = rcu_dereference_protected(tr->function_pids,
mutex_is_locked(&ftrace_lock));
this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid,
trace_ignore_this_task(pid_list, current));
}
static ssize_t
ftrace_pid_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
char buf[64], *tmp;
long val;
int ret;
struct seq_file *m = filp->private_data;
struct trace_array *tr = m->private;
struct trace_pid_list *filtered_pids = NULL;
struct trace_pid_list *pid_list;
ssize_t ret;
if (cnt >= sizeof(buf))
return -EINVAL;
if (!cnt)
return 0;
if (copy_from_user(&buf, ubuf, cnt))
return -EFAULT;
mutex_lock(&ftrace_lock);
buf[cnt] = 0;
filtered_pids = rcu_dereference_protected(tr->function_pids,
lockdep_is_held(&ftrace_lock));
ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
if (ret < 0)
goto out;
rcu_assign_pointer(tr->function_pids, pid_list);
if (filtered_pids) {
synchronize_sched();
trace_free_pid_list(filtered_pids);
} else if (pid_list) {
/* Register a probe to set whether to ignore the tracing of a task */
register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
}
/*
* Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
* to clean the filter quietly.
* Ignoring of pids is done at task switch. But we have to
* check for those tasks that are currently running.
* Always do this in case a pid was appended or removed.
*/
tmp = strstrip(buf);
if (strlen(tmp) == 0)
return 1;
on_each_cpu(ignore_task_cpu, tr, 1);
ret = kstrtol(tmp, 10, &val);
if (ret < 0)
return ret;
ftrace_update_pid_func();
ftrace_startup_all(0);
out:
mutex_unlock(&ftrace_lock);
ret = ftrace_pid_add(val);
if (ret > 0)
*ppos += ret;
return ret ? ret : cnt;
return ret;
}
static int
ftrace_pid_release(struct inode *inode, struct file *file)
{
if (file->f_mode & FMODE_READ)
seq_release(inode, file);
struct trace_array *tr = inode->i_private;
return 0;
trace_array_put(tr);
return seq_release(inode, file);
}
static const struct file_operations ftrace_pid_fops = {
@ -5571,24 +5537,21 @@ static const struct file_operations ftrace_pid_fops = {
.release = ftrace_pid_release,
};
static __init int ftrace_init_tracefs(void)
void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer)
{
struct dentry *d_tracer;
trace_create_file("set_ftrace_pid", 0644, d_tracer,
tr, &ftrace_pid_fops);
}
d_tracer = tracing_init_dentry();
if (IS_ERR(d_tracer))
return 0;
void __init ftrace_init_tracefs_toplevel(struct trace_array *tr,
struct dentry *d_tracer)
{
/* Only the top level directory has the dyn_tracefs and profile */
WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
ftrace_init_dyn_tracefs(d_tracer);
trace_create_file("set_ftrace_pid", 0644, d_tracer,
NULL, &ftrace_pid_fops);
ftrace_profile_tracefs(d_tracer);
return 0;
}
fs_initcall(ftrace_init_tracefs);
/**
* ftrace_kill - kill ftrace

358
kernel/trace/trace.c
View File

@ -25,7 +25,7 @@
#include <linux/hardirq.h>
#include <linux/linkage.h>
#include <linux/uaccess.h>
#include <linux/kprobes.h>
#include <linux/vmalloc.h>
#include <linux/ftrace.h>
#include <linux/module.h>
#include <linux/percpu.h>
@ -319,6 +319,258 @@ int call_filter_check_discard(struct trace_event_call *call, void *rec,
return 0;
}
void trace_free_pid_list(struct trace_pid_list *pid_list)
{
vfree(pid_list->pids);
kfree(pid_list);
}
/**
* trace_find_filtered_pid - check if a pid exists in a filtered_pid list
* @filtered_pids: The list of pids to check
* @search_pid: The PID to find in @filtered_pids
*
* Returns true if @search_pid is fonud in @filtered_pids, and false otherwis.
*/
bool
trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
{
/*
* If pid_max changed after filtered_pids was created, we
* by default ignore all pids greater than the previous pid_max.
*/
if (search_pid >= filtered_pids->pid_max)
return false;
return test_bit(search_pid, filtered_pids->pids);
}
/**
* trace_ignore_this_task - should a task be ignored for tracing
* @filtered_pids: The list of pids to check
* @task: The task that should be ignored if not filtered
*
* Checks if @task should be traced or not from @filtered_pids.
* Returns true if @task should *NOT* be traced.
* Returns false if @task should be traced.
*/
bool
trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
{
/*
* Return false, because if filtered_pids does not exist,
* all pids are good to trace.
*/
if (!filtered_pids)
return false;
return !trace_find_filtered_pid(filtered_pids, task->pid);
}
/**
* trace_pid_filter_add_remove - Add or remove a task from a pid_list
* @pid_list: The list to modify
* @self: The current task for fork or NULL for exit
* @task: The task to add or remove
*
* If adding a task, if @self is defined, the task is only added if @self
* is also included in @pid_list. This happens on fork and tasks should
* only be added when the parent is listed. If @self is NULL, then the
* @task pid will be removed from the list, which would happen on exit
* of a task.
*/
void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
struct task_struct *self,
struct task_struct *task)
{
if (!pid_list)
return;
/* For forks, we only add if the forking task is listed */
if (self) {
if (!trace_find_filtered_pid(pid_list, self->pid))
return;
}
/* Sorry, but we don't support pid_max changing after setting */
if (task->pid >= pid_list->pid_max)
return;
/* "self" is set for forks, and NULL for exits */
if (self)
set_bit(task->pid, pid_list->pids);
else
clear_bit(task->pid, pid_list->pids);
}
/**
* trace_pid_next - Used for seq_file to get to the next pid of a pid_list
* @pid_list: The pid list to show
* @v: The last pid that was shown (+1 the actual pid to let zero be displayed)
* @pos: The position of the file
*
* This is used by the seq_file "next" operation to iterate the pids
* listed in a trace_pid_list structure.
*
* Returns the pid+1 as we want to display pid of zero, but NULL would
* stop the iteration.
*/
void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
{
unsigned long pid = (unsigned long)v;
(*pos)++;
/* pid already is +1 of the actual prevous bit */
pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
/* Return pid + 1 to allow zero to be represented */
if (pid < pid_list->pid_max)
return (void *)(pid + 1);
return NULL;
}
/**
* trace_pid_start - Used for seq_file to start reading pid lists
* @pid_list: The pid list to show
* @pos: The position of the file
*
* This is used by seq_file "start" operation to start the iteration
* of listing pids.
*
* Returns the pid+1 as we want to display pid of zero, but NULL would
* stop the iteration.
*/
void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos)
{
unsigned long pid;
loff_t l = 0;
pid = find_first_bit(pid_list->pids, pid_list->pid_max);
if (pid >= pid_list->pid_max)
return NULL;
/* Return pid + 1 so that zero can be the exit value */
for (pid++; pid && l < *pos;
pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l))
;
return (void *)pid;
}
/**
* trace_pid_show - show the current pid in seq_file processing
* @m: The seq_file structure to write into
* @v: A void pointer of the pid (+1) value to display
*
* Can be directly used by seq_file operations to display the current
* pid value.
*/
int trace_pid_show(struct seq_file *m, void *v)
{
unsigned long pid = (unsigned long)v - 1;
seq_printf(m, "%lu\n", pid);
return 0;
}
/* 128 should be much more than enough */
#define PID_BUF_SIZE 127
int trace_pid_write(struct trace_pid_list *filtered_pids,
struct trace_pid_list **new_pid_list,
const char __user *ubuf, size_t cnt)
{
struct trace_pid_list *pid_list;
struct trace_parser parser;
unsigned long val;
int nr_pids = 0;
ssize_t read = 0;
ssize_t ret = 0;
loff_t pos;
pid_t pid;
if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1))
return -ENOMEM;
/*
* Always recreate a new array. The write is an all or nothing
* operation. Always create a new array when adding new pids by
* the user. If the operation fails, then the current list is
* not modified.
*/
pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
if (!pid_list)
return -ENOMEM;
pid_list->pid_max = READ_ONCE(pid_max);
/* Only truncating will shrink pid_max */
if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
pid_list->pid_max = filtered_pids->pid_max;
pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
if (!pid_list->pids) {
kfree(pid_list);
return -ENOMEM;
}
if (filtered_pids) {
/* copy the current bits to the new max */
for_each_set_bit(pid, filtered_pids->pids,
filtered_pids->pid_max) {
set_bit(pid, pid_list->pids);
nr_pids++;
}
}
while (cnt > 0) {
pos = 0;
ret = trace_get_user(&parser, ubuf, cnt, &pos);
if (ret < 0 || !trace_parser_loaded(&parser))
break;
read += ret;
ubuf += ret;
cnt -= ret;
parser.buffer[parser.idx] = 0;
ret = -EINVAL;
if (kstrtoul(parser.buffer, 0, &val))
break;
if (val >= pid_list->pid_max)
break;
pid = (pid_t)val;
set_bit(pid, pid_list->pids);
nr_pids++;
trace_parser_clear(&parser);
ret = 0;
}
trace_parser_put(&parser);
if (ret < 0) {
trace_free_pid_list(pid_list);
return ret;
}
if (!nr_pids) {
/* Cleared the list of pids */
trace_free_pid_list(pid_list);
read = ret;
pid_list = NULL;
}
*new_pid_list = pid_list;
return read;
}
static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
{
u64 ts;
@ -1862,7 +2114,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
{
__buffer_unlock_commit(buffer, event);
ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
/*
* If regs is not set, then skip the following callers:
* trace_buffer_unlock_commit_regs
* event_trigger_unlock_commit
* trace_event_buffer_commit
* trace_event_raw_event_sched_switch
* Note, we can still get here via blktrace, wakeup tracer
* and mmiotrace, but that's ok if they lose a function or
* two. They are that meaningful.
*/
ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
ftrace_trace_userstack(buffer, flags, pc);
}
@ -1912,6 +2174,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
trace.nr_entries = 0;
trace.skip = skip;
/*
* Add two, for this function and the call to save_stack_trace()
* If regs is set, then these functions will not be in the way.
*/
if (!regs)
trace.skip += 2;
/*
* Since events can happen in NMIs there's no safe way to
* use the per cpu ftrace_stacks. We reserve it and if an interrupt
@ -2083,83 +2352,41 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
/* created for use with alloc_percpu */
struct trace_buffer_struct {
char buffer[TRACE_BUF_SIZE];
int nesting;
char buffer[4][TRACE_BUF_SIZE];
};
static struct trace_buffer_struct *trace_percpu_buffer;
static struct trace_buffer_struct *trace_percpu_sirq_buffer;
static struct trace_buffer_struct *trace_percpu_irq_buffer;
static struct trace_buffer_struct *trace_percpu_nmi_buffer;
/*
* The buffer used is dependent on the context. There is a per cpu
* buffer for normal context, softirq contex, hard irq context and
* for NMI context. Thise allows for lockless recording.
*
* Note, if the buffers failed to be allocated, then this returns NULL
* Thise allows for lockless recording. If we're nested too deeply, then
* this returns NULL.
*/
static char *get_trace_buf(void)
{
struct trace_buffer_struct *percpu_buffer;
struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
/*
* If we have allocated per cpu buffers, then we do not
* need to do any locking.
*/
if (in_nmi())
percpu_buffer = trace_percpu_nmi_buffer;
else if (in_irq())
percpu_buffer = trace_percpu_irq_buffer;
else if (in_softirq())
percpu_buffer = trace_percpu_sirq_buffer;
else
percpu_buffer = trace_percpu_buffer;
if (!percpu_buffer)
if (!buffer || buffer->nesting >= 4)
return NULL;
return this_cpu_ptr(&percpu_buffer->buffer[0]);
return &buffer->buffer[buffer->nesting++][0];
}
static void put_trace_buf(void)
{
this_cpu_dec(trace_percpu_buffer->nesting);
}
static int alloc_percpu_trace_buffer(void)
{
struct trace_buffer_struct *buffers;
struct trace_buffer_struct *sirq_buffers;
struct trace_buffer_struct *irq_buffers;
struct trace_buffer_struct *nmi_buffers;
buffers = alloc_percpu(struct trace_buffer_struct);
if (!buffers)
goto err_warn;
sirq_buffers = alloc_percpu(struct trace_buffer_struct);
if (!sirq_buffers)
goto err_sirq;
irq_buffers = alloc_percpu(struct trace_buffer_struct);
if (!irq_buffers)
goto err_irq;
nmi_buffers = alloc_percpu(struct trace_buffer_struct);
if (!nmi_buffers)
goto err_nmi;
if (WARN(!buffers, "Could not allocate percpu trace_printk buffer"))
return -ENOMEM;
trace_percpu_buffer = buffers;
trace_percpu_sirq_buffer = sirq_buffers;
trace_percpu_irq_buffer = irq_buffers;
trace_percpu_nmi_buffer = nmi_buffers;
return 0;
err_nmi:
free_percpu(irq_buffers);
err_irq:
free_percpu(sirq_buffers);
err_sirq:
free_percpu(buffers);
err_warn:
WARN(1, "Could not allocate percpu trace_printk buffer");
return -ENOMEM;
}
static int buffers_allocated;
@ -2250,7 +2477,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
tbuffer = get_trace_buf();
if (!tbuffer) {
len = 0;
goto out;
goto out_nobuffer;
}
len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args);
@ -2276,6 +2503,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
}
out:
put_trace_buf();
out_nobuffer:
preempt_enable_notrace();
unpause_graph_tracing();
@ -2307,7 +2537,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,
tbuffer = get_trace_buf();
if (!tbuffer) {
len = 0;
goto out;
goto out_nobuffer;
}
len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
@ -2326,7 +2556,11 @@ __trace_array_vprintk(struct ring_buffer *buffer,
__buffer_unlock_commit(buffer, event);
ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL);
}
out:
out:
put_trace_buf();
out_nobuffer:
preempt_enable_notrace();
unpause_graph_tracing();
@ -6977,6 +7211,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
for_each_tracing_cpu(cpu)
tracing_init_tracefs_percpu(tr, cpu);
ftrace_init_tracefs(tr, d_tracer);
}
static struct vfsmount *trace_automount(void *ingore)
@ -7130,6 +7365,7 @@ static __init int tracer_init_tracefs(void)
return 0;
init_tracer_tracefs(&global_trace, d_tracer);
ftrace_init_tracefs_toplevel(&global_trace, d_tracer);
trace_create_file("tracing_thresh", 0644, d_tracer,
&global_trace, &tracing_thresh_fops);

48
kernel/trace/trace.h
View File

@ -80,6 +80,12 @@ enum trace_type {
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
#undef FTRACE_ENTRY_PACKED
#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \
filter) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter) __packed
#include "trace_entries.h"
/*
@ -156,6 +162,9 @@ struct trace_array_cpu {
char comm[TASK_COMM_LEN];
bool ignore_pid;
#ifdef CONFIG_FUNCTION_TRACER
bool ftrace_ignore_pid;
#endif
};
struct tracer;
@ -247,6 +256,7 @@ struct trace_array {
int ref;
#ifdef CONFIG_FUNCTION_TRACER
struct ftrace_ops *ops;
struct trace_pid_list __rcu *function_pids;
/* function tracing enabled */
int function_enabled;
#endif
@ -628,6 +638,25 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs);
extern unsigned long tracing_thresh;
/* PID filtering */
extern int pid_max;
bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids,
pid_t search_pid);
bool trace_ignore_this_task(struct trace_pid_list *filtered_pids,
struct task_struct *task);
void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
struct task_struct *self,
struct task_struct *task);
void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos);
void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos);
int trace_pid_show(struct seq_file *m, void *v);
void trace_free_pid_list(struct trace_pid_list *pid_list);
int trace_pid_write(struct trace_pid_list *filtered_pids,
struct trace_pid_list **new_pid_list,
const char __user *ubuf, size_t cnt);
#ifdef CONFIG_TRACER_MAX_TRACE
void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
void update_max_tr_single(struct trace_array *tr,
@ -821,12 +850,9 @@ extern struct list_head ftrace_pids;
#ifdef CONFIG_FUNCTION_TRACER
extern bool ftrace_filter_param __initdata;
static inline int ftrace_trace_task(struct task_struct *task)
static inline int ftrace_trace_task(struct trace_array *tr)
{
if (list_empty(&ftrace_pids))
return 1;
return test_tsk_trace_trace(task);
return !this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid);
}
extern int ftrace_is_dead(void);
int ftrace_create_function_files(struct trace_array *tr,
@ -836,8 +862,11 @@ void ftrace_init_global_array_ops(struct trace_array *tr);
void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
void ftrace_reset_array_ops(struct trace_array *tr);
int using_ftrace_ops_list_func(void);
void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
void ftrace_init_tracefs_toplevel(struct trace_array *tr,
struct dentry *d_tracer);
#else
static inline int ftrace_trace_task(struct task_struct *task)
static inline int ftrace_trace_task(struct trace_array *tr)
{
return 1;
}
@ -852,6 +881,8 @@ static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
static inline __init void
ftrace_init_global_array_ops(struct trace_array *tr) { }
static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
/* ftace_func_t type is not defined, use macro instead of static inline */
#define ftrace_init_array_ops(tr, func) do { } while (0)
#endif /* CONFIG_FUNCTION_TRACER */
@ -1600,6 +1631,11 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
#undef FTRACE_ENTRY_PACKED
#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
#include "trace_entries.h"
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)

4
kernel/trace/trace_entries.h
View File

@ -72,7 +72,7 @@ FTRACE_ENTRY_REG(function, ftrace_entry,
);
/* Function call entry */
FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
TRACE_GRAPH_ENT,
@ -88,7 +88,7 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
);
/* Function return entry */
FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
TRACE_GRAPH_RET,

219
kernel/trace/trace_events.c
View File

@ -15,7 +15,6 @@
#include <linux/kthread.h>
#include <linux/tracefs.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/sort.h>
@ -262,6 +261,14 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
local_save_flags(fbuffer->flags);
fbuffer->pc = preempt_count();
/*
* If CONFIG_PREEMPT is enabled, then the tracepoint itself disables
* preemption (adding one to the preempt_count). Since we are
* interested in the preempt_count at the time the tracepoint was
* hit, we need to subtract one to offset the increment.
*/
if (IS_ENABLED(CONFIG_PREEMPT))
fbuffer->pc--;
fbuffer->trace_file = trace_file;
fbuffer->event =
@ -499,60 +506,6 @@ static void ftrace_clear_events(struct trace_array *tr)
mutex_unlock(&event_mutex);
}
/* Shouldn't this be in a header? */
extern int pid_max;
/* Returns true if found in filter */
static bool
find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
{
/*
* If pid_max changed after filtered_pids was created, we
* by default ignore all pids greater than the previous pid_max.
*/
if (search_pid >= filtered_pids->pid_max)
return false;
return test_bit(search_pid, filtered_pids->pids);
}
static bool
ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
{
/*
* Return false, because if filtered_pids does not exist,
* all pids are good to trace.
*/
if (!filtered_pids)
return false;
return !find_filtered_pid(filtered_pids, task->pid);
}
static void filter_add_remove_task(struct trace_pid_list *pid_list,
struct task_struct *self,
struct task_struct *task)
{
if (!pid_list)
return;
/* For forks, we only add if the forking task is listed */
if (self) {
if (!find_filtered_pid(pid_list, self->pid))
return;
}
/* Sorry, but we don't support pid_max changing after setting */
if (task->pid >= pid_list->pid_max)
return;
/* "self" is set for forks, and NULL for exits */
if (self)
set_bit(task->pid, pid_list->pids);
else
clear_bit(task->pid, pid_list->pids);
}
static void
event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
{
@ -560,7 +513,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
struct trace_array *tr = data;
pid_list = rcu_dereference_sched(tr->filtered_pids);
filter_add_remove_task(pid_list, NULL, task);
trace_filter_add_remove_task(pid_list, NULL, task);
}
static void
@ -572,7 +525,7 @@ event_filter_pid_sched_process_fork(void *data,
struct trace_array *tr = data;
pid_list = rcu_dereference_sched(tr->filtered_pids);
filter_add_remove_task(pid_list, self, task);
trace_filter_add_remove_task(pid_list, self, task);
}
void trace_event_follow_fork(struct trace_array *tr, bool enable)
@ -600,8 +553,8 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
pid_list = rcu_dereference_sched(tr->filtered_pids);
this_cpu_write(tr->trace_buffer.data->ignore_pid,
ignore_this_task(pid_list, prev) &&
ignore_this_task(pid_list, next));
trace_ignore_this_task(pid_list, prev) &&
trace_ignore_this_task(pid_list, next));
}
static void
@ -614,7 +567,7 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
pid_list = rcu_dereference_sched(tr->filtered_pids);
this_cpu_write(tr->trace_buffer.data->ignore_pid,
ignore_this_task(pid_list, next));
trace_ignore_this_task(pid_list, next));
}
static void
@ -630,7 +583,7 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
pid_list = rcu_dereference_sched(tr->filtered_pids);
this_cpu_write(tr->trace_buffer.data->ignore_pid,
ignore_this_task(pid_list, task));
trace_ignore_this_task(pid_list, task));
}
static void
@ -647,7 +600,7 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
/* Set tracing if current is enabled */
this_cpu_write(tr->trace_buffer.data->ignore_pid,
ignore_this_task(pid_list, current));
trace_ignore_this_task(pid_list, current));
}
static void __ftrace_clear_event_pids(struct trace_array *tr)
@ -685,8 +638,7 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
/* Wait till all users are no longer using pid filtering */
synchronize_sched();
vfree(pid_list->pids);
kfree(pid_list);
trace_free_pid_list(pid_list);
}
static void ftrace_clear_event_pids(struct trace_array *tr)
@ -1034,18 +986,8 @@ p_next(struct seq_file *m, void *v, loff_t *pos)
{
struct trace_array *tr = m->private;
struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids);
unsigned long pid = (unsigned long)v;
(*pos)++;
/* pid already is +1 of the actual prevous bit */
pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
/* Return pid + 1 to allow zero to be represented */
if (pid < pid_list->pid_max)
return (void *)(pid + 1);
return NULL;
return trace_pid_next(pid_list, v, pos);
}
static void *p_start(struct seq_file *m, loff_t *pos)
@ -1053,8 +995,6 @@ static void *p_start(struct seq_file *m, loff_t *pos)
{
struct trace_pid_list *pid_list;
struct trace_array *tr = m->private;
unsigned long pid;
loff_t l = 0;
/*
* Grab the mutex, to keep calls to p_next() having the same
@ -1070,15 +1010,7 @@ static void *p_start(struct seq_file *m, loff_t *pos)
if (!pid_list)
return NULL;
pid = find_first_bit(pid_list->pids, pid_list->pid_max);
if (pid >= pid_list->pid_max)
return NULL;
/* Return pid + 1 so that zero can be the exit value */
for (pid++; pid && l < *pos;
pid = (unsigned long)p_next(m, (void *)pid, &l))
;
return (void *)pid;
return trace_pid_start(pid_list, pos);
}
static void p_stop(struct seq_file *m, void *p)
@ -1088,14 +1020,6 @@ static void p_stop(struct seq_file *m, void *p)
mutex_unlock(&event_mutex);
}
static int p_show(struct seq_file *m, void *v)
{
unsigned long pid = (unsigned long)v - 1;
seq_printf(m, "%lu\n", pid);
return 0;
}
static ssize_t
event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
@ -1654,7 +1578,7 @@ static void ignore_task_cpu(void *data)
mutex_is_locked(&event_mutex));
this_cpu_write(tr->trace_buffer.data->ignore_pid,
ignore_this_task(pid_list, current));
trace_ignore_this_task(pid_list, current));
}
static ssize_t
@ -1666,13 +1590,7 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
struct trace_pid_list *filtered_pids = NULL;
struct trace_pid_list *pid_list;
struct trace_event_file *file;
struct trace_parser parser;
unsigned long val;
loff_t this_pos;
ssize_t read = 0;
ssize_t ret = 0;
pid_t pid;
int nr_pids = 0;
ssize_t ret;
if (!cnt)
return 0;
@ -1681,93 +1599,15 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
if (ret < 0)
return ret;
if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
return -ENOMEM;
mutex_lock(&event_mutex);
filtered_pids = rcu_dereference_protected(tr->filtered_pids,
lockdep_is_held(&event_mutex));
/*
* Always recreate a new array. The write is an all or nothing
* operation. Always create a new array when adding new pids by
* the user. If the operation fails, then the current list is
* not modified.
*/
pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
if (!pid_list) {
read = -ENOMEM;
ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
if (ret < 0)
goto out;
}
pid_list->pid_max = READ_ONCE(pid_max);
/* Only truncating will shrink pid_max */
if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
pid_list->pid_max = filtered_pids->pid_max;
pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
if (!pid_list->pids) {
kfree(pid_list);
read = -ENOMEM;
goto out;
}
if (filtered_pids) {
/* copy the current bits to the new max */
pid = find_first_bit(filtered_pids->pids,
filtered_pids->pid_max);
while (pid < filtered_pids->pid_max) {
set_bit(pid, pid_list->pids);
pid = find_next_bit(filtered_pids->pids,
filtered_pids->pid_max,
pid + 1);
nr_pids++;
}
}
while (cnt > 0) {
this_pos = 0;
ret = trace_get_user(&parser, ubuf, cnt, &this_pos);
if (ret < 0 || !trace_parser_loaded(&parser))
break;
read += ret;
ubuf += ret;
cnt -= ret;
parser.buffer[parser.idx] = 0;
ret = -EINVAL;
if (kstrtoul(parser.buffer, 0, &val))
break;
if (val >= pid_list->pid_max)
break;
pid = (pid_t)val;
set_bit(pid, pid_list->pids);
nr_pids++;
trace_parser_clear(&parser);
ret = 0;
}
trace_parser_put(&parser);
if (ret < 0) {
vfree(pid_list->pids);
kfree(pid_list);
read = ret;
goto out;
}
if (!nr_pids) {
/* Cleared the list of pids */
vfree(pid_list->pids);
kfree(pid_list);
read = ret;
if (!filtered_pids)
goto out;
pid_list = NULL;
}
rcu_assign_pointer(tr->filtered_pids, pid_list);
list_for_each_entry(file, &tr->events, list) {
@ -1776,10 +1616,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
if (filtered_pids) {
synchronize_sched();
vfree(filtered_pids->pids);
kfree(filtered_pids);
} else {
trace_free_pid_list(filtered_pids);
} else if (pid_list) {
/*
* Register a probe that is called before all other probes
* to set ignore_pid if next or prev do not match.
@ -1817,9 +1655,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
out:
mutex_unlock(&event_mutex);
ret = read;
if (read > 0)
*ppos += read;
if (ret > 0)
*ppos += ret;
return ret;
}
@ -1846,7 +1683,7 @@ static const struct seq_operations show_set_event_seq_ops = {
static const struct seq_operations show_set_pid_seq_ops = {
.start = p_start,
.next = p_next,
.show = p_show,
.show = trace_pid_show,
.stop = p_stop,
};

2
kernel/trace/trace_functions.c
View File

@ -43,7 +43,7 @@ static int allocate_ftrace_ops(struct trace_array *tr)
/* Currently only the non stack verision is supported */
ops->func = function_trace_call;
ops->flags = FTRACE_OPS_FL_RECURSION_SAFE;
ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
tr->ops = ops;
ops->private = tr;

19
kernel/trace/trace_functions_graph.c
View File

@ -319,7 +319,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
int cpu;
int pc;
if (!ftrace_trace_task(current))
if (!ftrace_trace_task(tr))
return 0;
/* trace it when it is-nested-in or is a function enabled. */
@ -338,6 +338,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
if (ftrace_graph_notrace_addr(trace->func))
return 1;
/*
* Stop here if tracing_threshold is set. We only write function return
* events to the ring buffer.
*/
if (tracing_thresh)
return 1;
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@ -355,14 +362,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
return ret;
}
static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
{
if (tracing_thresh)
return 1;
else
return trace_graph_entry(trace);
}
static void
__trace_graph_function(struct trace_array *tr,
unsigned long ip, unsigned long flags, int pc)
@ -457,7 +456,7 @@ static int graph_trace_init(struct trace_array *tr)
set_graph_array(tr);
if (tracing_thresh)
ret = register_ftrace_graph(&trace_graph_thresh_return,
&trace_graph_thresh_entry);
&trace_graph_entry);
else
ret = register_ftrace_graph(&trace_graph_return,
&trace_graph_entry);

1
kernel/trace/trace_kprobe.c
View File

@ -587,6 +587,7 @@ static int create_trace_kprobe(int argc, char **argv)
* $retval : fetch return value
* $stack : fetch stack address
* $stackN : fetch Nth of stack (N:0-)
* $comm : fetch current task comm
* @ADDR : fetch memory at ADDR (ADDR should be in kernel)
* @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
* %REG : fetch register REG

10
kernel/trace/trace_mmiotrace.c
View File

@ -68,19 +68,15 @@ static void mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
dev->bus->number, dev->devfn,
dev->vendor, dev->device, dev->irq);
/*
* XXX: is pci_resource_to_user() appropriate, since we are
* supposed to interpret the __ioremap() phys_addr argument based on
* these printed values?
*/
for (i = 0; i < 7; i++) {
pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
start = dev->resource[i].start;
trace_seq_printf(s, " %llx",
(unsigned long long)(start |
(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
}
for (i = 0; i < 7; i++) {
pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
start = dev->resource[i].start;
end = dev->resource[i].end;
trace_seq_printf(s, " %llx",
dev->resource[i].start < dev->resource[i].end ?
(unsigned long long)(end - start) + 1 : 0);

33
kernel/trace/trace_probe.c
View File

@ -218,6 +218,28 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
kfree(data);
}
void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs,
void *data, void *dest)
{
int maxlen = get_rloc_len(*(u32 *)dest);
u8 *dst = get_rloc_data(dest);
long ret;
if (!maxlen)
return;
ret = strlcpy(dst, current->comm, maxlen);
*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
}
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string));
void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs,
void *data, void *dest)
{
*(u32 *)dest = strlen(current->comm) + 1;
}
NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size));
static const struct fetch_type *find_fetch_type(const char *type,
const struct fetch_type *ftbl)
{
@ -348,6 +370,11 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
}
} else
ret = -EINVAL;
} else if (strcmp(arg, "comm") == 0) {
if (strcmp(t->name, "string") != 0 &&
strcmp(t->name, "string_size") != 0)
return -EINVAL;
f->fn = t->fetch[FETCH_MTD_comm];
} else
ret = -EINVAL;
@ -522,6 +549,12 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
arg[t - parg->comm] = '\0';
t++;
}
/*
* The default type of $comm should be "string", and it can't be
* dereferenced.
*/
if (!t && strcmp(arg, "$comm") == 0)
t = "string";
parg->type = find_fetch_type(t, ftbl);
if (!parg->type) {
pr_info("Unsupported type: %s\n", t);

10
kernel/trace/trace_probe.h
View File

@ -102,6 +102,7 @@ enum {
FETCH_MTD_reg = 0,
FETCH_MTD_stack,
FETCH_MTD_retval,
FETCH_MTD_comm,
FETCH_MTD_memory,
FETCH_MTD_symbol,
FETCH_MTD_deref,
@ -183,6 +184,14 @@ DECLARE_BASIC_FETCH_FUNCS(bitfield);
#define fetch_bitfield_string NULL
#define fetch_bitfield_string_size NULL
/* comm only makes sense as a string */
#define fetch_comm_u8 NULL
#define fetch_comm_u16 NULL
#define fetch_comm_u32 NULL
#define fetch_comm_u64 NULL
DECLARE_FETCH_FUNC(comm, string);
DECLARE_FETCH_FUNC(comm, string_size);
/*
* Define macro for basic types - we don't need to define s* types, because
* we have to care only about bitwidth at recording time.
@ -213,6 +222,7 @@ DEFINE_FETCH_##method(u64)
ASSIGN_FETCH_FUNC(reg, ftype), \
ASSIGN_FETCH_FUNC(stack, ftype), \
ASSIGN_FETCH_FUNC(retval, ftype), \
ASSIGN_FETCH_FUNC(comm, ftype), \
ASSIGN_FETCH_FUNC(memory, ftype), \
ASSIGN_FETCH_FUNC(symbol, ftype), \
ASSIGN_FETCH_FUNC(deref, ftype), \

7
samples/Kconfig
View File

@ -11,6 +11,13 @@ config SAMPLE_TRACE_EVENTS
help
This build trace event example modules.
config SAMPLE_TRACE_PRINTK
tristate "Build trace_printk module - tests various trace_printk formats"
depends on EVENT_TRACING && m
help
This builds a module that calls trace_printk() and can be used to
test various trace_printk() calls from a module.
config SAMPLE_KOBJECT
tristate "Build kobject examples -- loadable modules only"
depends on m

2
samples/Makefile
View File

@ -2,4 +2,4 @@
obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ trace_events/ livepatch/ \
hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
configfs/ connector/ v4l/
configfs/ connector/ v4l/ trace_printk/

6
samples/trace_printk/Makefile Normal file
View File

@ -0,0 +1,6 @@
# builds a module that calls various trace_printk routines
# then to use one (as root): insmod <module_name.ko>
# This module can also be used to test the trace_printk code.
obj-$(CONFIG_SAMPLE_TRACE_PRINTK) += trace-printk.o

56
samples/trace_printk/trace-printk.c Normal file
View File

@ -0,0 +1,56 @@
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/irq_work.h>
/* Must not be static to force gcc to consider these non constant */
char *trace_printk_test_global_str =
"This is a dynamic string that will use trace_puts\n";
char *trace_printk_test_global_str_irq =
"(irq) This is a dynamic string that will use trace_puts\n";
char *trace_printk_test_global_str_fmt =
"%sThis is a %s that will use trace_printk\n";
static struct irq_work irqwork;
static void trace_printk_irq_work(struct irq_work *work)
{
trace_printk("(irq) This is a static string that will use trace_bputs\n");
trace_printk(trace_printk_test_global_str_irq);
trace_printk("(irq) This is a %s that will use trace_bprintk()\n",
"static string");
trace_printk(trace_printk_test_global_str_fmt,
"(irq) ", "dynamic string");
}
static int __init trace_printk_init(void)
{
init_irq_work(&irqwork, trace_printk_irq_work);
trace_printk("This is a static string that will use trace_bputs\n");
trace_printk(trace_printk_test_global_str);
/* Kick off printing in irq context */
irq_work_queue(&irqwork);
trace_printk("This is a %s that will use trace_bprintk()\n",
"static string");
trace_printk(trace_printk_test_global_str_fmt, "", "dynamic string");
return 0;
}
static void __exit trace_printk_exit(void)
{
}
module_init(trace_printk_init);
module_exit(trace_printk_exit);
MODULE_AUTHOR("Steven Rostedt");
MODULE_DESCRIPTION("trace-printk");
MODULE_LICENSE("GPL");